diff options
Diffstat (limited to 'xmerge/java/org/openoffice/xmerge/converter/xml')
175 files changed, 38127 insertions, 0 deletions
diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedBinaryObject.java b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedBinaryObject.java new file mode 100644 index 000000000000..9ec0bc5291c6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedBinaryObject.java @@ -0,0 +1,128 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import org.w3c.dom.Document; +import org.w3c.dom.DOMException; +import org.w3c.dom.Element; +import org.w3c.dom.Node; + + +/** + * This class represents embedded object's in an OpenOffice.org document that + * have a binary representation. + */ +public class EmbeddedBinaryObject extends EmbeddedObject { + + /** The object's binary representation. */ + protected byte[] objData = null; + + /** + * Constructor for an embedded object stored using an XML representation. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + */ + public EmbeddedBinaryObject(String name, String type) { + super(name, type); + } + + + /** + * Package private constructor for use when reading an object from a + * compressed SX? file. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + * @param source The OfficeZip representation of the SX? file that stores + * the object. + */ + EmbeddedBinaryObject(String name, String type, OfficeZip source) { + super(name, type, source); + } + + + /** + * This method returns the data for this object. + * + * @return A <code>byte</code> array containing the object's data. + */ + public byte[] getBinaryData() { + + if (objData == null) { + // See if we came from a Zip file + if (zipFile != null) { + objData = zipFile.getNamedBytes(objName); + } + } + + return objData; + } + + + /** + * Sets the data for this object. + * + * @param data A <code>byte</code> array containing data for the object. + */ + public void setBinaryData(byte[] data) { + objData = data; + hasChanged = true; + } + + /** + * Package private method for writing the data of the EmbeddedObject to a + * SX? file. + * + * @param zip An <code>OfficeZip</code> instance representing the file + * the data is to be written to. + */ + void write(OfficeZip zip) { + if (hasChanged) { + zip.setNamedBytes(objName, objData); + } + } + + + /** + * Package private method that constructs the manifest.xml entries for this + * embedded object. + * + * @return Document <code>Document</code> containing the manifest entries. + */ + void writeManifestData(Document manifestDoc) throws DOMException { + Element objNode = manifestDoc.createElement(OfficeConstants.TAG_MANIFEST_FILE); + + objNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_TYPE, objType); + objNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_PATH, objName); + + manifestDoc.getDocumentElement().appendChild(objNode); + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedObject.java b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedObject.java new file mode 100644 index 000000000000..f4220f1b3972 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedObject.java @@ -0,0 +1,117 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml; + +import java.io.IOException; + +import org.w3c.dom.Document; +import org.w3c.dom.DOMException; + + +public abstract class EmbeddedObject { + protected String objName; + protected String objType; + + /** Representation of the file from which this object was read. */ + protected OfficeZip zipFile = null; + + /** Flag indicating if this document has changed since reading or is new. */ + protected boolean hasChanged = false; + + /** + * Constructor for an embedded object stored using an XML representation. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + */ + public EmbeddedObject(String name, String type) { + objName = name; + objType = type; + + hasChanged = true; + } + + + /** + * Package private constructor for use when reading an object from a + * compressed SX? file. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + * @param source The OfficeZip representation of the SX? file that stores + * the object. + */ + EmbeddedObject(String name, String type, OfficeZip source) { + this(name, type); + zipFile = source; + } + + + /** + * Retrieves the name of the embedded object represented by an instance of + * this class. + * + * <b>N.B.</b>The name referes to the name as found in the + * <code>META-INF/manifest.xml</code> file. + * + * @return The name of the object. + */ + public final String getName() { + return objName; + } + + + /** + * Retrieves the type of the embedded object represented by an instance of + * this class. + * + * The <code>META-INF/manifest.xml</code> file currently represents the + * type of an object using MIME types. + */ + public final String getType() { + return objType; + } + + /** + * Package private method for writing the data of the EmbeddedObject to a + * SX? file. + * + * @param zip An <code>OfficeZip</code> instance representing the file + * the data is to be written to. + */ + abstract void write(OfficeZip zip) throws IOException; + + /** + * Package private method that constructs the manifest.xml entries for this + * embedded object. + * + * @return Document <code>Document</code> containing the manifest entries. + */ + abstract void writeManifestData(Document manifestDoc) throws DOMException; +}
\ No newline at end of file diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedXMLObject.java b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedXMLObject.java new file mode 100644 index 000000000000..c07f6f116ca2 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/EmbeddedXMLObject.java @@ -0,0 +1,298 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import java.io.ByteArrayInputStream; +import java.io.IOException; + +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.DocumentBuilderFactory; +import javax.xml.parsers.ParserConfigurationException; + +import org.w3c.dom.Document; +import org.w3c.dom.DOMException; +import org.w3c.dom.Element; +import org.w3c.dom.Node; + +import org.xml.sax.EntityResolver; +import org.xml.sax.InputSource; +import org.xml.sax.SAXException; + +/** + * This class represents those embedded objects in an OpenOffice.org document + * that have an XML representation. Currently, according to the OpenOffice.org + * File Format 1.0 document, there are 6 such objects: + * + * Formulae created with Math (application/vnd.sun.xml.math) + * Charts created with Chart (application/vnd.sun.xml.chart) + * Spreadsheets created with Calc (application/vnd.sun.xml.calc) + * Text created with Writer (application/vnd.sun.xml.writer) + * Drawings created with Draw (application/vnd.sun.xml.draw) + * Presentations created with Impress (application/vnd.sun.xml.impress) + * + * These object types are stored using a combination of content, settings and styles + * XML files. + */ +public class EmbeddedXMLObject extends EmbeddedObject { + + // Entries for the subdocuments that constitute this object; + protected Document contentDOM = null; + protected Document settingsDOM = null; + protected Document stylesDOM = null; + + private DocumentBuilder builder = null; + + /** + * Constructor for an embedded object stored using an XML representation. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + */ + public EmbeddedXMLObject(String name, String type) { + super(name, type); + } + + /** + * Package private constructor for use when reading an object from a + * compressed SX? file. + * + * @param name The name of the object. + * @param type The mime-type of the object. See the class summary. + * @param source The OfficeZip representation of the SX? file that stores + * the object. + */ + EmbeddedXMLObject(String name, String type, OfficeZip source) { + super(name, type, source); + } + + + /** + * Returns the content data for this embedded object. + * + * @return DOM represenation of "content.xml" + * + * @throws SAXException If any parser error occurs + * @throws IOException If any IO error occurs + */ + public Document getContentDOM() throws SAXException, IOException { + + if (contentDOM == null) { + contentDOM = getNamedDOM("content.xml"); + } + + return contentDOM; + } + + + /** + * Sets the content data for the embedded object. + * + * @param content DOM representation of the object's content. + */ + public void setContentDOM(Document content) { + contentDOM = content; + hasChanged = true; + } + + + /** + * Returns the settings data for this embedded object. + * + * @return DOM represenation of "settings.xml" + * + * @throws SAXException If any parser error occurs + * @throws IOException If any IO error occurs + */ + public Document getSettingsDOM() throws SAXException, IOException { + + if (settingsDOM == null) { + settingsDOM = getNamedDOM("settings.xml"); + } + + return settingsDOM; + } + + + /** + * Sets the settings data for the embedded object. + * + * @param styles DOM representation of the object's styles. + */ + public void setSettingsDOM(Document settings) { + settingsDOM = settings; + hasChanged = true; + } + + + /** + * Returns the style data for this embedded object. + * + * @return DOM represenation of "styles.xml" + * + * @throws SAXException If any parser error occurs + * @throws IOException If any IO error occurs + */ + public Document getStylesDOM() throws SAXException, IOException { + + if (stylesDOM == null) { + stylesDOM = getNamedDOM("styles.xml"); + } + + return stylesDOM; + } + + + /** + * Sets the styles data for the embedded object. + * + * @param styles DOM representation of the object's styles. + */ + public void setStylesDOM(Document styles) { + stylesDOM = styles; + hasChanged = true; + } + + + /** + * This method extracts the data for the given XML file from the SX? file + * and creates a DOM representation of it. + * + * @param name The name of the XML file to retrieve. It is paired with + * the object name to access the SX? file. + * + * @return DOM representation of the named XML file. + * + * @throws SAXException If any parser error occurs + * @throws IOException If any IO error occurs + */ + private Document getNamedDOM(String name) throws SAXException, IOException { + if (zipFile == null) { + return null; + } + + try { + if (builder == null) { + DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); + + factory.setValidating(false); + builder = factory.newDocumentBuilder(); + } + + byte[] data = zipFile.getNamedBytes(new String(objName + "/" + name)); + if (data != null) { + return OfficeDocument.parse(builder, data); + } + else { + return null; + } + + } + catch (SAXException se) { + throw se; + } + catch (IOException ioe) { + throw ioe; + } + catch (ParserConfigurationException pce) { + throw new SAXException(pce); + } + } + + + /** + * Package private method for writing the data of the EmbeddedObject to a + * SX? file. + * + * @param zip An <code>OfficeZip</code> instance representing the file + * the data is to be written to. + */ + void write(OfficeZip zip) throws IOException { + if (hasChanged == true) { + if (contentDOM != null) { + zip.setNamedBytes(new String(objName + "/content.xml"), + OfficeDocument.docToBytes(contentDOM)); + } + if (settingsDOM != null) { + zip.setNamedBytes(new String(objName + "/settings.xml"), + OfficeDocument.docToBytes(settingsDOM)); + } + if (stylesDOM != null) { + zip.setNamedBytes(new String(objName + "/styles.xml"), + OfficeDocument.docToBytes(stylesDOM)); + } + } + } + + /** + * Package private method that constructs the manifest.xml entries for this + * embedded object. + * + * @param manifestDoc <code>Document</code> containing the manifest entries. + */ + void writeManifestData(Document manifestDoc) throws DOMException { + Node root = manifestDoc.getDocumentElement(); + + if (contentDOM != null) { + Element contentNode = manifestDoc.createElement(OfficeConstants.TAG_MANIFEST_FILE); + + contentNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + contentNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_PATH, + new String(objName + "/content.xml")); + + root.appendChild(contentNode); + } + + if (settingsDOM != null) { + Element settingsNode = manifestDoc.createElement(OfficeConstants.TAG_MANIFEST_FILE); + + settingsNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + settingsNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_PATH, + new String(objName + "/settings.xml")); + + root.appendChild(settingsNode); + } + + if (stylesDOM != null) { + Element stylesNode = manifestDoc.createElement(OfficeConstants.TAG_MANIFEST_FILE); + + stylesNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + stylesNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_PATH, + new String(objName + "/styles.xml")); + } + + + Element objectNode = manifestDoc.createElement(OfficeConstants.TAG_MANIFEST_FILE); + + objectNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_TYPE, objType); + objectNode.setAttribute(OfficeConstants.ATTRIBUTE_MANIFEST_FILE_PATH, + new String(objName + "/")); + + root.appendChild(objectNode); + } + +}
\ No newline at end of file diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeConstants.java new file mode 100644 index 000000000000..265c7a29e954 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeConstants.java @@ -0,0 +1,439 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +/** + * This interface contains constants for StarOffice XML tags, + * attributes (StarCalc cell types, etc.). + * + * @author Herbie Ong, Paul Rank, Martin Maher + */ +public interface OfficeConstants { + + /** Element tag for <i>office:document</i>, this is the root tag. */ + public final static String TAG_OFFICE_DOCUMENT = "office:document"; + + /** + * Element tag for <i>office:document-content</i>, this is the root + * tag in content.xml. + */ + public final static String TAG_OFFICE_DOCUMENT_CONTENT = "office:document-content"; + + /** + * Element tag for <i>office:document-settings</i>, this is the root + * tag in content.xml. + */ + public final static String TAG_OFFICE_DOCUMENT_SETTINGS= "office:document-settings"; + + /** + * Element tag for <i>office:document-meta</i>, this is the root + * tag in content.xml. + */ + public final static String TAG_OFFICE_DOCUMENT_META= "office:document-meta"; + + /** + * Element tag for <i>office:document-styles</i>, this is the root tag + * in styles.xml. + */ + public final static String TAG_OFFICE_DOCUMENT_STYLES = "office:document-styles"; + + /** + * Attribute tag for <i>office:class</i> of element + * <i>office:document</i>. + */ + public final static String ATTRIBUTE_OFFICE_CLASS = "office:class"; + + /** Element tag for <i>office:styles</i>. */ + public final static String TAG_OFFICE_STYLES = "office:styles"; + + /** Element tag for <i>office:meta</i>. */ + public final static String TAG_OFFICE_META = "office:meta"; + + /** Element tag for <i>office:automatic-styles</i>. */ + public final static String TAG_OFFICE_AUTOMATIC_STYLES = "office:automatic-styles"; + + /** Element tag for <i>office:master-styles</i>. */ + public final static String TAG_OFFICE_MASTER_STYLES = "office:master-styles"; + + /** Element tag for <i>office:body</i>. */ + public final static String TAG_OFFICE_BODY = "office:body"; + + /** Element tag for <i>office:settings</i>. */ + public final static String TAG_OFFICE_SETTINGS = "office:settings"; + + //Adding + + /** Element tag for <i>text:variable-set</i>. */ + public final static String TAG_TEXT_VARIABLE_SET = "text:variable-set"; + + /** Element tag for <i>text:variable-get</i>. */ + public final static String TAG_TEXT_VARIABLE_GET = "text:variable-get"; +/** Element tag for <i>text:expression</i>. */ + public final static String TAG_TEXT_EXPRESSION = "text:expression"; + +/** Element tag for <i>text:user-field-get</i>. */ + public final static String TAG_TEXT_USER_FIELD_GET = "text:user-field-get"; + +/** Element tag for <i>text:page-variable-get</i>. */ + public final static String TAG_TEXT_PAGE_VARIABLE_GET = "text:page-variable-get"; +/** Element tag for <i>text:sequence</i>. */ + public final static String TAG_TEXT_SEQUENCE = "text:sequence"; + + /** Element tag for <i>text:text-input</i>. */ + public final static String TAG_TEXT_VARIABLE_INPUT = "text:variable-input"; + /** Element tag for <i>text:time</i>. */ + public final static String TAG_TEXT_TIME = "text:time"; + + /** Element tag for <i>text:page-count</i>. */ + public final static String TAG_TEXT_PAGE_COUNT = "text:page-count"; + /** Element tag for <i>text:page-number</i>. */ + public final static String TAG_TEXT_PAGE_NUMBER = "text:page-number"; + /** Element tag for <i>text:author-initials</i>. */ + public final static String TAG_TEXT_AUTHOR_INITIALS = "text:author-initials"; + /** Element tag for <i>text:subject</i>. */ + public final static String TAG_TEXT_SUBJECT = "text:subject"; + /** Element tag for <i>text:title</i>. */ + public final static String TAG_TEXT_TITLE = "text:title"; + /** Element tag for <i>text:creation-time</i>. */ + public final static String TAG_TEXT_CREATION_TIME = "text:creation-time"; + + /** Element tag for <i>text:date</i>. */ + public final static String TAG_TEXT_DATE = "text:date"; + /** Element tag for <i>text:text-input</i>. */ + public final static String TAG_TEXT_TEXT_INPUT = "text:text-input"; + + +//end adding + + /** Element tag for <i>office:font-decls</i>. */ + public final static String TAG_OFFICE_FONT_DECLS = "office:font-decls"; + + /** Element tag for <i>style:font-decl</i>. */ + public final static String TAG_STYLE_FONT_DECL = "style:font-decl"; + + /** Attribute tag for <i>style:name</i> of element <i>style:name</i>. */ + public final static String ATTRIBUTE_STYLE_NAME = "style:name"; + + /** + * Attribute tag for <i>style:font-pitch</i> of element + * <i>style:font-pitch</i>. + */ + public final static String ATTRIBUTE_STYLE_FONT_PITCH = "style:font-pitch"; + + /** + * Attribute tag for <i>fo:font-family</i> of element + * <i>fo:font-family</i>. + */ + public final static String ATTRIBUTE_FO_FONT_FAMILY = "fo:font-family"; + + /** + * Attribute tag for <i>fo:font-family</i> of element + * <i>fo:font-family</i>. + */ + public final static String ATTRIBUTE_FO_FONT_FAMILY_GENERIC = "fo:font-family-generic"; + + /** Element tag for <i>text:p</i>. */ + public final static String TAG_PARAGRAPH = "text:p"; + + /** Element tag for <i>text:</i>. */ + public final static String TAG_TEXT = "text:"; + + /** Element tag for <i>text:h</i>. */ + public final static String TAG_HEADING = "text:h"; + + /** Element tag for <i>text:s</i>. */ + public final static String TAG_SPACE = "text:s"; + + /** Element tag for <i>text:tab-stop</i>. */ + public final static String TAG_TAB_STOP = "text:tab-stop"; + + /** Element tag for <i>text:line-break</i>. */ + public final static String TAG_LINE_BREAK = "text:line-break"; + + /** Element tag for <i>text:span</i>. */ + public final static String TAG_SPAN = "text:span"; + + /** Element tag for <i>text:a</i>. */ + public final static String TAG_HYPERLINK = "text:a"; + + /** Element tag for <i>text:bookmark</i>. */ + public final static String TAG_BOOKMARK = "text:bookmark"; + + /** Element tag for <i>text:bookmark-start</i>. */ + public final static String TAG_BOOKMARK_START = "text:bookmark-start"; + + /** Element tag for <i>text:unordered-list</i>. */ + public final static String TAG_UNORDERED_LIST = "text:unordered-list"; + + /** Element tag for <i>text:ordered-list</i>. */ + public final static String TAG_ORDERED_LIST = "text:ordered-list"; + + /** Element tag for <i>text:list-header</i>. */ + public final static String TAG_LIST_HEADER = "text:list-header"; + + /** Element tag for <i>text:list-item</i>. */ + public final static String TAG_LIST_ITEM = "text:list-item"; + + /** Attribute tag for <i>text:c</i> of element <i>text:s</i>. */ + public final static String ATTRIBUTE_SPACE_COUNT = "text:c"; + + /** + * Attribute tag for <i>text:style-name</i> of element + * <i>text:style-name</i>. + */ + public final static String ATTRIBUTE_TEXT_STYLE_NAME = "text:style-name"; + + /** Element tag for <i>table:table</i>. */ + public final static String TAG_TABLE = "table:table"; + + /** Element tag for <i>table:named-expression</i>. */ + public final static String TAG_NAMED_EXPRESSIONS = "table:named-expressions"; + + /** Element tag for <i>table:named-range</i>. */ + public final static String TAG_TABLE_NAMED_RANGE= "table:named-range"; + + /** Element tag for <i>table:named-expression</i>. */ + public final static String TAG_TABLE_NAMED_EXPRESSION= "table:named-expression"; + + /** + * Attribute tag for <i>table:name</i> of element + * <i>table:table</i>. + */ + public final static String ATTRIBUTE_TABLE_NAME = "table:name"; + + /** + * Attribute tag for <i>table:expression</i> of element + * <i>table:named-range</i>. + */ + public final static String ATTRIBUTE_TABLE_EXPRESSION = "table:expression"; + + /** + * Attribute tag for <i>table:base-cell-address</i> of element + * <i>table:named-range</i>. + */ + public final static String ATTRIBUTE_TABLE_BASE_CELL_ADDRESS = "table:base-cell-address"; + + /** + * Attribute tag for <i>table:cell-range-address</i> of element + * <i>table:named-range</i>. + */ + public final static String ATTRIBUTE_TABLE_CELL_RANGE_ADDRESS = "table:cell-range-address"; + + /** Element tag for <i>table:table-row</i>. */ + public final static String TAG_TABLE_ROW = "table:table-row"; + + /** Element tag for <i>table:table-column</i>. */ + public final static String TAG_TABLE_COLUMN = "table:table-column"; + + /** + * Attribute tag for <i>table:default-cell-style-name</i> + * of element <i>table:table-column</i>. + */ + public final static String ATTRIBUTE_DEFAULT_CELL_STYLE = "table:default-cell-style-name"; + + /** Element tag for <i>table:scenario</i>. */ + public final static String TAG_TABLE_SCENARIO = "table:scenario"; + + /** Element tag for <i>table:table-cell</i>. */ + public final static String TAG_TABLE_CELL = "table:table-cell"; + + /** + * Attribute tag for <i>table:value-type</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_VALUE_TYPE = "table:value-type"; + + /** + * Attribute tag for <i>table:number-columns-repeated</i> + * of element <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED = + "table:number-columns-repeated"; + + /** + * Attribute tag for <i>table:number-rows-repeated</i> + * of element <i>table:table-row</i>. + */ + public final static String ATTRIBUTE_TABLE_NUM_ROWS_REPEATED = + "table:number-rows-repeated"; + + /** + * Attribute tag for <i>table:formula</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_FORMULA = "table:formula"; + + /** + * Attribute tag for <i>table:value</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_VALUE = "table:value"; + + /** + * Attribute tag for <i>table:date-value</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_DATE_VALUE = "table:date-value"; + + /** + * Attribute tag for <i>table:time-value</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_TIME_VALUE = "table:time-value"; + + /** + * Attribute tag for <i>table:string-value</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_STRING_VALUE = + "table:string-value"; + + /** + * Attribute tag for <i>table:time-boolean-value</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_BOOLEAN_VALUE = + "table:boolean-value"; + + /** Attribute tag for <i>table:style-name</i> of table elements. */ + public final static String ATTRIBUTE_TABLE_STYLE_NAME = "table:style-name"; + + /** + * Attribute tag for <i>table:currency</i> of element + * <i>table:table-cell</i>. + */ + public final static String ATTRIBUTE_TABLE_CURRENCY = "table:currency"; + + /** The cell contains data of type <i>string</i>. */ + public final static String CELLTYPE_STRING = "string"; + + /** The cell contains data of type <i>float</i>. */ + public final static String CELLTYPE_FLOAT = "float"; + + /** The cell contains data of type <i>time</i>. */ + public final static String CELLTYPE_TIME = "time"; + + /** The cell contains data of type <i>date</i>. */ + public final static String CELLTYPE_DATE = "date"; + + /** The cell contains data of type <i>currency</i>. */ + public final static String CELLTYPE_CURRENCY = "currency"; + + /** The cell contains data of type <i>boolean</i>. */ + public final static String CELLTYPE_BOOLEAN = "boolean"; + + /** The cell contains data of type <i>percent</i>. */ + public final static String CELLTYPE_PERCENT = "percentage"; + + /** StarWriter XML file extension. */ + public final static String SXW_FILE_EXTENSION = ".sxw"; + + /** StarWriter XML <i>office:class</i> value. */ + public final static String SXW_TYPE = "text"; + + /** StarCalc XML file extension. */ + public final static String SXC_FILE_EXTENSION = ".sxc"; + + /** StarCalc XML <i>office:class</i> value. */ + public final static String SXC_TYPE = "spreadsheet"; + + /** Element tag for <i>manifest:manifest</i>entry in Manifest XML */ + public final static String TAG_MANIFEST_ROOT = "manifest:manifest"; + + /** Element tag for <i>manifest:file-entry</i> entry in Manifest XML. */ + public final static String TAG_MANIFEST_FILE = "manifest:file-entry"; + + /** + * Attribute tag for <i>manifest:media-type</i> of element + * <i>manifest:file-entry</i>. + */ + public final static String ATTRIBUTE_MANIFEST_FILE_TYPE = "manifest:media-type"; + + /** + * Attribute tag for <i>manifest:full-path</i> of element + * <i>manifest:file-entry</i>. + */ + public final static String ATTRIBUTE_MANIFEST_FILE_PATH = "manifest:full-path"; + + // Tags and Elements for the settings.xml + + /** Element tag for <i>config:config-item</i>. */ + public final static String TAG_CONFIG_ITEM = "config:config-item"; + + /** Element tag for <i>config:config-item-set</i>. */ + public final static String TAG_CONFIG_ITEM_SET = "config:config-item-set"; + + /** Element tag for <i>config:config-item-map-indexed</i>. */ + public final static String TAG_CONFIG_ITEM_MAP_INDEXED = "config:config-item-map-indexed"; + + /** Element tag for <i>config:config-item-map-named</i>. */ + public final static String TAG_CONFIG_ITEM_MAP_NAMED = "config:config-item-map-named"; + + /** Element tag for <i>config:config-item-map-entry</i>. */ + public final static String TAG_CONFIG_ITEM_MAP_ENTRY= "config:config-item-map-entry"; + + /** + * Attribute tag for <i>config:name</i> of element + * <i>config:config-item</i>. + */ + public final static String ATTRIBUTE_CONFIG_NAME = "config:name"; + + /** + * Attribute tag for <i>config:type</i> of element + * <i>config:config-item</i>. + */ + public final static String ATTRIBUTE_CONFIG_TYPE = "config:type"; + + + /** StarWriter XML MIME type. */ + public final static String SXW_MIME_TYPE = "application/vnd.sun.xml.writer"; + + /** StarWriter XML Template MIME type. */ + public final static String STW_MIME_TYPE = "application/vnd.sun.xml.writer.template"; + + /** StarCalc XML MIME type. */ + public final static String SXC_MIME_TYPE = "application/vnd.sun.xml.calc"; + + /** StarCalc XML Template MIME type. */ + public final static String STC_MIME_TYPE = "application/vnd.sun.xml.calc.template"; + + /** StarImpress XML MIME type. */ + public final static String SXI_MIME_TYPE = "application/vnd.sun.xml.impress"; + + /** StarImpress XML Template MIME type. */ + public final static String STI_MIME_TYPE = "application/vnd.sun.xml.impress.template"; + + /** StarDraw XML MIME type. */ + public final static String SXD_MIME_TYPE = "application/vnd.sun.xml.draw"; + + /** StarMath XML MIME type. */ + public final static String SXM_MIME_TYPE = "application/vnd.sun.xml.math"; + + /** StarWriter Global XML MIME Type */ + public final static String SXG_MIME_TYPE = "application/vnd.sun.xml.writer.global"; +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocument.java b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocument.java new file mode 100644 index 000000000000..54da474289a3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocument.java @@ -0,0 +1,1234 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ +package org.openoffice.xmerge.converter.xml; + +import java.io.InputStream; +import java.io.OutputStream; +import java.io.Reader; +import java.io.BufferedReader; +import java.io.StringReader; +import java.io.InputStreamReader; +import java.io.BufferedInputStream; +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.IOException; +import java.util.zip.ZipEntry; +import java.util.zip.ZipInputStream; +import java.util.Iterator; +import java.util.Map; +import java.util.HashMap; + +import javax.xml.parsers.DocumentBuilderFactory; +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.ParserConfigurationException; + +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import org.w3c.dom.Document; +import org.w3c.dom.DOMImplementation; +import org.w3c.dom.DocumentType; +import org.w3c.dom.NodeList; +import org.xml.sax.InputSource; +import org.w3c.dom.NamedNodeMap; +import org.xml.sax.SAXException; +import org.xml.sax.SAXParseException; + +import org.openoffice.xmerge.util.Resources; +import org.openoffice.xmerge.util.Debug; + +/** + * An implementation of <code>Document</code> for + * StarOffice documents. + */ +public abstract class OfficeDocument + implements org.openoffice.xmerge.Document, + OfficeConstants { + + /** Factory for <code>DocumentBuilder</code> objects. */ + private static DocumentBuilderFactory factory = + DocumentBuilderFactory.newInstance(); + + /** DOM <code>Document</code> of content.xml. */ + private Document contentDoc = null; + + /** DOM <code>Document</code> of meta.xml. */ + private Document metaDoc = null; + + /** DOM <code>Document</code> of settings.xml. */ + private Document settingsDoc = null; + + /** DOM <code>Document</code> of content.xml. */ + private Document styleDoc = null; + + /** DOM <code>Docuemtn</code> of META-INF/manifest.xml. */ + private Document manifestDoc = null; + + private String documentName = null; + private String fileName = null; + + /** Resources object. */ + private Resources res = null; + + /** + * <code>OfficeZip</code> object to store zip contents from + * read <code>InputStream</code>. Note that this member + * will still be null if it was initialized using a template + * file instead of reading from a StarOffice zipped + * XML file. + */ + private OfficeZip zip = null; + + /** Collection to keep track of the embedded objects in the document. */ + private Map embeddedObjects = null; + + /** + * Default constructor. + * + * @param name <code>Document</code> name. + */ + public OfficeDocument(String name) + { + this(name, true, false); + } + + + /** + * Constructor with arguments to set <code>namespaceAware</code> + * and <code>validating</code> flags. + * + * @param name <code>Document</code> name (may or may not + * contain extension). + * @param namespaceAware Value for <code>namespaceAware</code> flag. + * @param validating Value for <code>validating</code> flag. + */ + public OfficeDocument(String name, boolean namespaceAware, boolean validating) { + + res = Resources.getInstance(); + factory.setValidating(validating); + factory.setNamespaceAware(namespaceAware); + this.documentName = trimDocumentName(name); + this.fileName = documentName + getFileExtension(); + } + + + /** + * Removes the file extension from the <code>Document</code> + * name. + * + * @param name Full <code>Document</code> name with extension. + * + * @return Name of <code>Document</code> without the extension. + */ + private String trimDocumentName(String name) { + String temp = name.toLowerCase(); + String ext = getFileExtension(); + + if (temp.endsWith(ext)) { + // strip the extension + int nlen = name.length(); + int endIndex = nlen - ext.length(); + name = name.substring(0,endIndex); + } + + return name; + } + + + /** + * Return a DOM <code>Document</code> object of the content.xml + * file. Note that a content DOM is not created when the constructor + * is called. So, either the <code>read</code> method or the + * <code>initContentDOM</code> method will need to be called ahead + * on this object before calling this method. + * + * @return DOM <code>Document</code> object. + */ + public Document getContentDOM() { + + return contentDoc; + } + + /** + * Return a DOM <code>Document</code> object of the meta.xml + * file. Note that a content DOM is not created when the constructor + * is called. So, either the <code>read</code> method or the + * <code>initContentDOM</code> method will need to be called ahead + * on this object before calling this method. + * + * @return DOM <code>Document</code> object. + */ + public Document getMetaDOM() { + + return metaDoc; + } + + + /** + * Return a DOM <code>Document</code> object of the settings.xml + * file. Note that a content DOM is not created when the constructor + * is called. So, either the <code>read</code> method or the + * <code>initContentDOM</code> method will need to be called ahead + * on this object before calling this method. + * + * @return DOM <code>Document</code> object. + */ + public Document getSettingsDOM() { + + return settingsDoc; + } + + + /** + * Sets the content tree of the document. + * + * @param newDom <code>Node</code> containing the new content tree. + */ + public void setContentDOM( Node newDom) { + contentDoc = (Document)newDom; + } + + + /** + * Sets the meta tree of the document. + * + * @param newDom <code>Node</code> containing the new meta tree. + */ + public void setMetaDOM (Node newDom) { + metaDoc = (Document)newDom; + } + + + /** + * Sets the settings tree of the document. + * + * @param newDom <code>Node</code> containing the new settings tree. + */ + public void setSettingsDOM (Node newDom) { + settingsDoc = (Document)newDom; + } + + + /** + * Sets the style tree of the document. + * + * @param newDom <code>Node</code> containing the new style tree. + */ + public void setStyleDOM (Node newDom) { + styleDoc = (Document)newDom; + } + + + /** + * Return a DOM <code>Document</code> object of the style.xml file. + * Note that this may return null if there is no style DOM. + * Note that a style DOM is not created when the constructor + * is called. Depending on the <code>InputStream</code>, a + * <code>read</code> method may or may not build a style DOM. When + * creating a new style DOM, call the <code>initStyleDOM</code> method + * first. + * + * @return DOM <code>Document</code> object. + */ + public Document getStyleDOM() { + + return styleDoc; + } + + + /** + * Return the name of the <code>Document</code>. + * + * @return The name of <code>Document</code>. + */ + public String getName() { + + return documentName; + } + + + /** + * Return the file name of the <code>Document</code>, possibly + * with the standard extension. + * + * @return The file name of <code>Document</code>. + */ + public String getFileName() { + + return fileName; + } + + + /** + * Returns the file extension for this type of + * <code>Document</code>. + * + * @return The file extension of <code>Document</code>. + */ + protected abstract String getFileExtension(); + + + /** + * Returns all the embedded objects (graphics, formulae, etc.) present in + * this document. + * + * @return An <code>Iterator</code> of <code>EmbeddedObject</code> objects. + */ + public Iterator getEmbeddedObjects() { + + if (embeddedObjects == null && manifestDoc != null) { + embeddedObjects = new HashMap(); + + // Need to read the manifest file and construct a list of objects + NodeList nl = manifestDoc.getElementsByTagName(TAG_MANIFEST_FILE); + + // Dont create the HashMap if there are no embedded objects + int len = nl.getLength(); + for (int i = 0; i < len; i++) { + Node n = nl.item(i); + + NamedNodeMap attrs = n.getAttributes(); + + String type = attrs.getNamedItem(ATTRIBUTE_MANIFEST_FILE_TYPE).getNodeValue(); + String path = attrs.getNamedItem(ATTRIBUTE_MANIFEST_FILE_PATH).getNodeValue(); + + + /* + * According to OpenOffice.org XML File Format document (ver. 1) + * there are only two types of embedded object: + * + * Objects with an XML representation. + * Objects without an XML representation. + * + * The former are represented by one or more XML files. + * The latter are in binary form. + */ + if (type.startsWith("application/vnd.sun.xml")) + { + if (path.equals("/")) { + // Exclude the main document entries + continue; + } + // Take off the trailing '/' + String name = path.substring(0, path.length() - 1); + embeddedObjects.put(name, new EmbeddedXMLObject(name, type, zip)); + } + else if (type.equals("text/xml")) { + // XML entries are either embedded StarOffice doc entries or main + // document entries + continue; + } + else { // FIX (HJ): allows empty MIME type + embeddedObjects.put(path, new EmbeddedBinaryObject(path, type, zip)); + } + } + } + + return embeddedObjects.values().iterator(); + } + + /** + * Returns the embedded object corresponding to the name provided. + * The name should be stripped of any preceding path characters, such as + * '/', '.' or '#'. + * + * @param name The name of the embedded object to retrieve. + * + * @return An <code>EmbeddedObject</code> instance representing the named + * object. + */ + public EmbeddedObject getEmbeddedObject(String name) { + if (name == null) { + return null; + } + + if (embeddedObjects == null) { + getEmbeddedObjects(); + } + + if (embeddedObjects.containsKey(name)) { + return (EmbeddedObject)embeddedObjects.get(name); + } + else { + return null; + } + } + + + /** + * Adds a new embedded object to the document. + * + * @param embObj An instance of <code>EmbeddedObject</code>. + */ + public void addEmbeddedObject(EmbeddedObject embObj) { + if (embObj == null) { + return; + } + + if (embeddedObjects == null) { + embeddedObjects = new HashMap(); + } + + embeddedObjects.put(embObj.getName(), embObj); + } + + + /** + * Read the Office <code>Document</code> from the given + * <code>InputStream</code>. + * + * @param is Office document <code>InputStream</code>. + * + * @throws IOException If any I/O error occurs. + */ + public void read(InputStream is) throws IOException { + + Debug.log(Debug.INFO, "reading Office file"); + + DocumentBuilder builder = null; + + try { + builder = factory.newDocumentBuilder(); + } catch (ParserConfigurationException ex) { + throw new OfficeDocumentException(ex); + } + + // read in Office zip file format + + zip = new OfficeZip(); + zip.read(is); + + // grab the content.xml and + // parse it into contentDoc. + + byte contentBytes[] = zip.getContentXMLBytes(); + + if (contentBytes == null) { + + throw new OfficeDocumentException("Entry content.xml not found in file"); + } + + try { + + contentDoc = parse(builder, contentBytes); + + } catch (SAXException ex) { + + throw new OfficeDocumentException(ex); + } + + // if style.xml exists, grab the style.xml + // parse it into styleDoc. + + byte styleBytes[] = zip.getStyleXMLBytes(); + + if (styleBytes != null) { + + try { + + styleDoc = parse(builder, styleBytes); + + } catch (SAXException ex) { + + throw new OfficeDocumentException(ex); + } + } + + byte metaBytes[] = zip.getMetaXMLBytes(); + + if (metaBytes != null) { + + try { + + metaDoc = parse(builder, metaBytes); + + } catch (SAXException ex) { + + throw new OfficeDocumentException(ex); + } + } + + byte settingsBytes[] = zip.getSettingsXMLBytes(); + + if (settingsBytes != null) { + + try { + + settingsDoc = parse(builder, settingsBytes); + + } catch (SAXException ex) { + + throw new OfficeDocumentException(ex); + } + } + + + // Read in the META-INF/manifest.xml file + byte manifestBytes[] = zip.getManifestXMLBytes(); + + if (manifestBytes != null) { + + try { + manifestDoc = parse(builder, manifestBytes); + } catch (SAXException ex) { + throw new OfficeDocumentException(ex); + } + } + + } + + + /** + * Read the Office <code>Document</code> from the given + * <code>InputStream</code>. + * + * @param is Office document <code>InputStream</code>. + * @param isZip <code>boolean</code> Identifies whether + * a file is zipped or not + * + * @throws IOException If any I/O error occurs. + */ + public void read(InputStream is, boolean isZip) throws IOException { + + Debug.log(Debug.INFO, "reading Office file"); + + DocumentBuilder builder = null; + + try { + builder = factory.newDocumentBuilder(); + } catch (ParserConfigurationException ex) { + throw new OfficeDocumentException(ex); + } + + if (isZip) + { + read(is); + } + else{ + try{ + //System.out.println("\nParsing Input stream, validating?: "+builder.isValidating()); + //contentDoc= builder.parse((InputStream)is); + + Reader r = secondHack(is); + InputSource ins = new InputSource(r); + org.w3c.dom.Document newDoc = builder.parse(ins); + //org.w3c.dom.Document newDoc = builder.parse((InputStream)is); + Element rootElement=newDoc.getDocumentElement(); + + NodeList nodeList; + Node tmpNode; + Node rootNode = (Node)rootElement; + if (newDoc !=null){ + /*content*/ + contentDoc = createDOM(TAG_OFFICE_DOCUMENT_CONTENT); + rootElement=contentDoc.getDocumentElement(); + rootNode = (Node)rootElement; + + // FIX (HJ): Include office:font-decls in content DOM + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_FONT_DECLS); + if (nodeList.getLength()>0){ + tmpNode = contentDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + if (nodeList.getLength()>0){ + tmpNode = contentDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_BODY); + if (nodeList.getLength()>0){ + tmpNode = contentDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + /*Styles*/ + styleDoc = createDOM(TAG_OFFICE_DOCUMENT_STYLES); + rootElement=styleDoc.getDocumentElement(); + rootNode = (Node)rootElement; + + // FIX (HJ): Include office:font-decls in styles DOM + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_FONT_DECLS); + if (nodeList.getLength()>0){ + tmpNode = styleDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_STYLES); + if (nodeList.getLength()>0){ + tmpNode = styleDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + // FIX (HJ): Include office:automatic-styles in styles DOM + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + if (nodeList.getLength()>0){ + tmpNode = styleDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + // FIX (HJ): Include office:master-styles in styles DOM + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_MASTER_STYLES); + if (nodeList.getLength()>0){ + tmpNode = styleDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + /*Settings*/ + settingsDoc = createDOM(TAG_OFFICE_DOCUMENT_SETTINGS); + rootElement=settingsDoc.getDocumentElement(); + rootNode = (Node)rootElement; + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_SETTINGS); + if (nodeList.getLength()>0){ + tmpNode = settingsDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + /*Meta*/ + metaDoc = createDOM(TAG_OFFICE_DOCUMENT_META); + rootElement=metaDoc.getDocumentElement(); + rootNode = (Node)rootElement; + nodeList= newDoc.getElementsByTagName(TAG_OFFICE_META); + if (nodeList.getLength()>0){ + tmpNode = metaDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + } + } + catch (SAXException ex) { + throw new OfficeDocumentException(ex); + } + } + + } + + + + /** + * Parse given <code>byte</code> array into a DOM + * <code>Document</code> object using the + * <code>DocumentBuilder</code> object. + * + * @param builder <code>DocumentBuilder</code> object for parsing. + * @param bytes <code>byte</code> array for parsing. + * + * @return Resulting DOM <code>Document</code> object. + * + * @throws SAXException If any parsing error occurs. + */ + static Document parse(DocumentBuilder builder, byte bytes[]) + throws SAXException, IOException { + + Document doc = null; + + ByteArrayInputStream is = new ByteArrayInputStream(bytes); + + // TODO: replace hack with a more appropriate fix. + + Reader r = hack(is); + InputSource ins = new InputSource(r); + doc = builder.parse(ins); + + return doc; + } + + + /** + * Method to return the MIME type of the document. + * + * @return String The document's MIME type. + */ + protected abstract String getDocumentMimeType(); + + + /** + * Write out Office ZIP file format. + * + * @param os XML <code>OutputStream</code>. + * + * @throws IOException If any I/O error occurs. + */ + public void write(OutputStream os) throws IOException { + if (zip == null) { + zip = new OfficeZip(); + } + + initManifestDOM(); + + Element domEntry; + Element manifestRoot = manifestDoc.getDocumentElement(); + + // The EmbeddedObjects come first. + Iterator embObjs = getEmbeddedObjects(); + while (embObjs.hasNext()) { + EmbeddedObject obj = (EmbeddedObject)embObjs.next(); + obj.writeManifestData(manifestDoc); + + obj.write(zip); + } + + // Add in the entry for the Pictures directory. Always present. + domEntry = manifestDoc.createElement(TAG_MANIFEST_FILE); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "Pictures/"); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, ""); + manifestRoot.appendChild(domEntry); + + // Write content to the Zip file and then write any of the optional + // data, if it exists. + zip.setContentXMLBytes(docToBytes(contentDoc)); + + domEntry = manifestDoc.createElement(TAG_MANIFEST_FILE); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "content.xml"); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + + manifestRoot.appendChild(domEntry); + + if (styleDoc != null) { + zip.setStyleXMLBytes(docToBytes(styleDoc)); + + domEntry = manifestDoc.createElement(TAG_MANIFEST_FILE); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "styles.xml"); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + manifestRoot.appendChild(domEntry); + } + + if (metaDoc != null) { + zip.setMetaXMLBytes(docToBytes(metaDoc)); + + domEntry = manifestDoc.createElement(TAG_MANIFEST_FILE); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "meta.xml"); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + manifestRoot.appendChild(domEntry); + } + + if (settingsDoc != null) { + zip.setSettingsXMLBytes(docToBytes(settingsDoc)); + + domEntry = manifestDoc.createElement(TAG_MANIFEST_FILE); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "settings.xml"); + domEntry.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, "text/xml"); + manifestRoot.appendChild(domEntry); + } + + zip.setManifestXMLBytes(docToBytes(manifestDoc)); + + zip.write(os); + } + + + /** + * Write out Office ZIP file format. + * + * @param os XML <code>OutputStream</code>. + * @param isZip <code>boolean</code> + * + * @throws IOException If any I/O error occurs. + */ + public void write(OutputStream os, boolean isZip) throws IOException { + + // Create an OfficeZip object if one does not exist. + if (isZip){ + write(os); + } + else{ + try{ + DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); + DocumentBuilder builder= builderFactory.newDocumentBuilder(); + DOMImplementation domImpl = builder.getDOMImplementation(); + DocumentType docType =domImpl.createDocumentType("office:document","-//OpenOffice.org//DTD OfficeDocument 1.0//EN",null); + org.w3c.dom.Document newDoc = domImpl.createDocument("http://openoffice.org/2000/office","office:document",null); + + + Element rootElement=newDoc.getDocumentElement(); + rootElement.setAttribute("xmlns:office","http://openoffice.org/2000/office"); + rootElement.setAttribute("xmlns:style","http://openoffice.org/2000/style" ); + rootElement.setAttribute("xmlns:text","http://openoffice.org/2000/text"); + rootElement.setAttribute("xmlns:table","http://openoffice.org/2000/table"); + + rootElement.setAttribute("xmlns:draw","http://openoffice.org/2000/drawing"); + rootElement.setAttribute("xmlns:fo","http://www.w3.org/1999/XSL/Format" ); + rootElement.setAttribute("xmlns:xlink","http://www.w3.org/1999/xlink" ); + rootElement.setAttribute("xmlns:dc","http://purl.org/dc/elements/1.1/" ); + rootElement.setAttribute("xmlns:meta","http://openoffice.org/2000/meta" ); + rootElement.setAttribute("xmlns:number","http://openoffice.org/2000/datastyle" ); + rootElement.setAttribute("xmlns:svg","http://www.w3.org/2000/svg" ); + rootElement.setAttribute("xmlns:chart","http://openoffice.org/2000/chart" ); + rootElement.setAttribute("xmlns:dr3d","http://openoffice.org/2000/dr3d" ); + rootElement.setAttribute("xmlns:math","http://www.w3.org/1998/Math/MathML" ); + rootElement.setAttribute("xmlns:form","http://openoffice.org/2000/form" ); + rootElement.setAttribute("xmlns:script","http://openoffice.org/2000/script" ); + rootElement.setAttribute("xmlns:config","http://openoffice.org/2001/config" ); + // #i41033# OASIS format needs the "office:class" set. + if(getDocumentMimeType() == SXC_MIME_TYPE) + rootElement.setAttribute("office:class","spreadsheet" ); + else if(getDocumentMimeType() == SXW_MIME_TYPE) + rootElement.setAttribute("office:class","text" ); + rootElement.setAttribute("office:version","1.0"); + + + NodeList nodeList; + Node tmpNode; + Node rootNode = (Node)rootElement; + if (metaDoc !=null){ + nodeList= metaDoc.getElementsByTagName(TAG_OFFICE_META); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + }if (styleDoc !=null){ + nodeList= styleDoc.getElementsByTagName(TAG_OFFICE_STYLES); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + }if (settingsDoc !=null){ + nodeList= settingsDoc.getElementsByTagName(TAG_OFFICE_SETTINGS); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + } + if (contentDoc !=null){ + nodeList= contentDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + + nodeList= contentDoc.getElementsByTagName(TAG_OFFICE_BODY); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + } + + byte contentBytes[] = docToBytes(newDoc); + //System.out.println(new String(contentBytes)); + os.write(contentBytes); + } + catch(Exception exc){ + System.out.println("\nException in OfficeDocument.write():" +exc); + } + //byte contentBytes[] = docToBytes(contentDoc); + } + } + + + /** + * <p>Write out a <code>org.w3c.dom.Document</code> object into a + * <code>byte</code> array.</p> + * + * <p>TODO: remove dependency on com.sun.xml.tree.XmlDocument + * package!</p> + * + * @param Document DOM <code>Document</code> object. + * + * @return <code>byte</code> array of DOM <code>Document</code> + * object. + * + * @throws IOException If any I/O error occurs. + */ + static byte[] docToBytes(Document doc) + throws IOException { + + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + + java.lang.reflect.Constructor con; + java.lang.reflect.Method meth; + + String domImpl = doc.getClass().getName(); + + /* + * We may have multiple XML parsers in the Classpath. + * Depending on which one is first, the actual type of + * doc may vary. Need a way to find out which API is being + * used and use an appropriate serialization method. + */ + try { + // First of all try for JAXP 1.0 + if (domImpl.equals("com.sun.xml.tree.XmlDocument")) { + + Debug.log(Debug.INFO, "Using JAXP"); + + Class jaxpDoc = Class.forName("com.sun.xml.tree.XmlDocument"); + + // The method is in the XMLDocument class itself, not a helper + meth = jaxpDoc.getMethod("write", + new Class[] { Class.forName("java.io.OutputStream") } ); + + meth.invoke(doc, new Object [] { baos } ); + } + else if (domImpl.equals("org.apache.crimson.tree.XmlDocument")) + { + Debug.log(Debug.INFO, "Using Crimson"); + + Class crimsonDoc = Class.forName("org.apache.crimson.tree.XmlDocument"); + // The method is in the XMLDocument class itself, not a helper + meth = crimsonDoc.getMethod("write", + new Class[] { Class.forName("java.io.OutputStream") } ); + + meth.invoke(doc, new Object [] { baos } ); + } + else if (domImpl.equals("org.apache.xerces.dom.DocumentImpl") + || domImpl.equals("org.apache.xerces.dom.DeferredDocumentImpl")) { + + Debug.log(Debug.INFO, "Using Xerces"); + + // Try for Xerces + Class xercesSer = + Class.forName("org.apache.xml.serialize.XMLSerializer"); + + // Get the OutputStream constructor + // May want to use the OutputFormat parameter at some stage too + con = xercesSer.getConstructor(new Class [] + { Class.forName("java.io.OutputStream"), + Class.forName("org.apache.xml.serialize.OutputFormat") } ); + + + // Get the serialize method + meth = xercesSer.getMethod("serialize", + new Class [] { Class.forName("org.w3c.dom.Document") } ); + + + // Get an instance + Object serializer = con.newInstance(new Object [] { baos, null } ); + + + // Now call serialize to write the document + meth.invoke(serializer, new Object [] { doc } ); + } + else { + // We don't have another parser + throw new IOException("No appropriate API (JAXP/Xerces) to serialize XML document: " + domImpl); + } + } + catch (ClassNotFoundException cnfe) { + throw new IOException(cnfe.toString()); + } + catch (Exception e) { + // We may get some other errors, but the bottom line is that + // the steps being executed no longer work + throw new IOException(e.toString()); + } + + byte bytes[] = baos.toByteArray(); + + return bytes; + } + + + /** + * Initializes a new DOM <code>Document</code> with the content + * containing minimum OpenOffice XML tags. + * + * @throws IOException If any I/O error occurs. + */ + public final void initContentDOM() throws IOException { + + contentDoc = createDOM(TAG_OFFICE_DOCUMENT_CONTENT); + + // this is a work-around for a bug in Office6.0 - not really + // needed but StarCalc 6.0 will crash without this tag. + Element root = contentDoc.getDocumentElement(); + + Element child = contentDoc.createElement(TAG_OFFICE_FONT_DECLS); + root.appendChild(child); + + child = contentDoc.createElement(TAG_OFFICE_AUTOMATIC_STYLES); + root.appendChild(child); + + child = contentDoc.createElement(TAG_OFFICE_BODY); + root.appendChild(child); + } + + /** + * Initializes a new DOM <code>Document</code> with the content + * containing minimum OpenOffice XML tags. + * + * @throws IOException If any I/O error occurs. + */ + public final void initSettingsDOM() throws IOException { + + settingsDoc = createSettingsDOM(TAG_OFFICE_DOCUMENT_SETTINGS); + + // this is a work-around for a bug in Office6.0 - not really + // needed but StarCalc 6.0 will crash without this tag. + Element root = settingsDoc.getDocumentElement(); + + Element child = settingsDoc.createElement(TAG_OFFICE_SETTINGS); + root.appendChild(child); + } + + /** + * Initializes a new DOM Document with styles + * containing minimum OpenOffice XML tags. + * + * @throws IOException If any I/O error occurs. + */ + public final void initStyleDOM() throws IOException { + + styleDoc = createDOM(TAG_OFFICE_DOCUMENT_STYLES); + } + + /** + * <p>Creates a new DOM <code>Document</code> containing minimum + * OpenOffice XML tags.</p> + * + * <p>This method uses the subclass + * <code>getOfficeClassAttribute</code> method to get the + * attribute for <i>office:class</i>.</p> + * + * @param rootName root name of <code>Document</code>. + * + * @throws IOException If any I/O error occurs. + */ + private final Document createSettingsDOM(String rootName) throws IOException { + + Document doc = null; + + try { + + DocumentBuilder builder = factory.newDocumentBuilder(); + doc = builder.newDocument(); + + } catch (ParserConfigurationException ex) { + + throw new OfficeDocumentException(ex); + + } + + Element root = (Element) doc.createElement(rootName); + doc.appendChild(root); + + root.setAttribute("xmlns:office", "http://openoffice.org/2000/office"); + root.setAttribute("xmlns:xlink", "http://openoffice.org/1999/xlink"); + root.setAttribute("xmlns:config", "http://openoffice.org/2001/config"); + root.setAttribute("office:version", "1.0"); + + return doc; + } + + + /** + * <p>Creates a new DOM <code>Document</code> containing minimum + * OpenOffice XML tags.</p> + * + * <p>This method uses the subclass + * <code>getOfficeClassAttribute</code> method to get the + * attribute for <i>office:class</i>.</p> + * + * @param rootName root name of <code>Document</code>. + * + * @throws IOException If any I/O error occurs. + */ + private final Document createDOM(String rootName) throws IOException { + + Document doc = null; + + try { + + DocumentBuilder builder = factory.newDocumentBuilder(); + doc = builder.newDocument(); + + } catch (ParserConfigurationException ex) { + + throw new OfficeDocumentException(ex); + + } + + Element root = (Element) doc.createElement(rootName); + doc.appendChild(root); + + root.setAttribute("xmlns:office", "http://openoffice.org/2000/office"); + root.setAttribute("xmlns:style", "http://openoffice.org/2000/style"); + root.setAttribute("xmlns:text", "http://openoffice.org/2000/text"); + root.setAttribute("xmlns:table", "http://openoffice.org/2000/table"); + root.setAttribute("xmlns:draw", "http://openoffice.org/2000/drawing"); + root.setAttribute("xmlns:fo", "http://www.w3.org/1999/XSL/Format"); + root.setAttribute("xmlns:xlink", "http://www.w3.org/1999/xlink"); + root.setAttribute("xmlns:number", "http://openoffice.org/2000/datastyle"); + root.setAttribute("xmlns:svg", "http://www.w3.org/2000/svg"); + root.setAttribute("xmlns:chart", "http://openoffice.org/2000/chart"); + root.setAttribute("xmlns:dr3d", "http://openoffice.org/2000/dr3d"); + root.setAttribute("xmlns:math", "http://www.w3.org/1998/Math/MathML"); + root.setAttribute("xmlns:form", "http://openoffice.org/2000/form"); + root.setAttribute("xmlns:script", "http://openoffice.org/2000/script"); + root.setAttribute("office:class", getOfficeClassAttribute()); + root.setAttribute("office:version", "1.0"); + + return doc; + } + + + /** + * Return the <i>office:class</i> attribute value. + * + * @return The attribute value. + */ + protected abstract String getOfficeClassAttribute(); + + + /** + * <p>Hacked code to filter <!DOCTYPE> tag before + * sending stream to parser.</p> + * + * <p>This hacked code needs to be changed later on.</p> + * + * <p>Issue: using current jaxp1.0 parser, there is no way + * to turn off processing of dtds. Current set of dtds + * have bugs, processing them will throw exceptions.</p> + * + * <p>This is a simple hack that assumes the whole <!DOCTYPE> + * tag are all in the same line. This is sufficient for + * current StarOffice 6.0 generated XML files. Since this + * hack really needs to go away, I don't want to spend + * too much time in making it a perfect hack.</p> + * FIX (HJ): Removed requirement for DOCTYPE to be in one line + * FIX (HJ): No longer removes newlines + * + * @param is <code>InputStream</code> to be filtered. + * + * @return Reader value without the <!DOCTYPE> tag. + * + * @throws IOException If any I/O error occurs. + */ + private static Reader hack(InputStream is) throws IOException { + + BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8")); + StringBuffer buffer = new StringBuffer(is.available()); + + String str = null; + + while ((str = br.readLine()) != null) { + + int sIndex = str.indexOf("<!DOCTYPE"); + + if (sIndex > -1) { + + buffer.append(str.substring(0, sIndex)); + + int eIndex = str.indexOf('>', sIndex + 8 ); + + if (eIndex > -1) { + + buffer.append(str.substring(eIndex + 1, str.length())); + // FIX (HJ): Preserve the newline + buffer.append("\n"); + + } else { + + // FIX (HJ): More than one line. Search for '>' in following lines + boolean bOK = false; + while ((str = br.readLine())!=null) { + eIndex = str.indexOf('>'); + if (eIndex>-1) { + buffer.append(str.substring(eIndex+1)); + // FIX (HJ): Preserve the newline + buffer.append("\n"); + bOK = true; + break; + } + } + + if (!bOK) { throw new IOException("Invalid XML"); } + } + + } else { + + buffer.append(str); + // FIX (HJ): Preserve the newline + buffer.append("\n"); + } + } + + StringReader r = new StringReader(buffer.toString()); + return r; + } + + /** + * <p>Transform the InputStream to a Reader Stream.</p> + * + * <p>This hacked code needs to be changed later on.</p> + * + * <p>Issue: the new oasis input file stream means + * that the old input stream fails. see #i33702# </p> + * + * @param is <code>InputStream</code> to be filtered. + * + * @return Reader value of the InputStream(). + * + * @throws IOException If any I/O error occurs. + */ + private static Reader secondHack(InputStream is) throws IOException { + + BufferedReader br = new BufferedReader(new InputStreamReader(is, "UTF-8")); + char[] charArray = new char[is.available()]; + + br.read(charArray,0,is.available()); + String sStr = new String(charArray); + StringBuffer sBuf = new StringBuffer(is.available()); + // ensure there is no trailing garbage after the end of the stream. + int sIndex = sStr.lastIndexOf("</office:document>"); + sBuf.append(sStr.substring(0, sIndex)); + sBuf.append("</office:document>"); + StringReader r = new StringReader(sBuf.toString()); + return r; + } + + + /** + * Method to create the initial entries in the manifest.xml file stored + * in an SX? file. + */ + private void initManifestDOM() throws IOException { + + try { + DocumentBuilder builder = factory.newDocumentBuilder(); + DOMImplementation domImpl = builder.getDOMImplementation(); + + DocumentType docType = domImpl.createDocumentType(TAG_MANIFEST_ROOT, + "-//OpenOffice.org//DTD Manifest 1.0//EN", + "Manifest.dtd"); + manifestDoc = domImpl.createDocument("manifest", TAG_MANIFEST_ROOT, docType); + } catch (ParserConfigurationException ex) { + throw new OfficeDocumentException(ex); + } + + // Add the <manifest:manifest> entry + Element manifestRoot = manifestDoc.getDocumentElement(); + + manifestRoot.setAttribute("xmlns:manifest", "http://openoffice.org/2001/manifest"); + + Element docRoot = manifestDoc.createElement(TAG_MANIFEST_FILE); + + docRoot.setAttribute(ATTRIBUTE_MANIFEST_FILE_PATH, "/"); + docRoot.setAttribute(ATTRIBUTE_MANIFEST_FILE_TYPE, getDocumentMimeType()); + + manifestRoot.appendChild(docRoot); + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocumentException.java b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocumentException.java new file mode 100644 index 000000000000..0de5f1f9d9ef --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeDocumentException.java @@ -0,0 +1,131 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import java.io.IOException; + +import javax.xml.parsers.ParserConfigurationException; +import org.xml.sax.SAXException; +import org.xml.sax.SAXParseException; + +import org.openoffice.xmerge.util.Resources; + +/** + * Used by OfficeDocument to encapsulate exceptions. It will add + * more details to the message string if it is of type + * <code>SAXParseException</code>. + * + * @author Herbie Ong + */ + +public final class OfficeDocumentException extends IOException { + + StringBuffer message = null; + + + /** + * Constructor, capturing additional information from the + * <code>SAXException</code>. + * + * @param e The <code>SAXException</code>. + */ + public OfficeDocumentException(SAXException e) { + super(e.toString()); + message = new StringBuffer(); + if (e instanceof SAXParseException) { + String msgParseError = + Resources.getInstance().getString("PARSE_ERROR"); + String msgLine = + Resources.getInstance().getString("LINE"); + String msgColumn = + Resources.getInstance().getString("COLUMN"); + String msgPublicId = + Resources.getInstance().getString("PUBLIC_ID"); + String msgSystemId = + Resources.getInstance().getString("SYSTEM_ID"); + SAXParseException spe = (SAXParseException) e; + message.append(msgParseError); + message.append(": "); + message.append(msgLine); + message.append(": "); + message.append(spe.getLineNumber()); + message.append(", "); + message.append(msgColumn); + message.append(": "); + message.append(spe.getColumnNumber()); + message.append(", "); + message.append(msgSystemId); + message.append(": "); + message.append(spe.getSystemId()); + message.append(", "); + message.append(msgPublicId); + message.append(": "); + message.append(spe.getPublicId()); + message.append("\n"); + } + + // if there exists an embedded exception + Exception ex = e.getException(); + if (ex != null) { + message.append(ex.getMessage()); + } + } + + + /** + * Constructor, creates exception with provided message. + * + * @param s Message value for the exception. + */ + public OfficeDocumentException(String s) { + super(s); + } + + + /** + * Constructor, creates exception with the message + * corresponding to the message value of the provided + * exception. + * + * @param e The Exception. + */ + public OfficeDocumentException(Exception e) { + super(e.getMessage()); + } + + + /** + * Returns the message value for the <code>Exception</code>. + * + * @return The message value for the <code>Exception</code>. + */ + public String getMessage() { + return message.toString() + super.getMessage(); + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeZip.java b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeZip.java new file mode 100644 index 000000000000..cfd7bcf42049 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/OfficeZip.java @@ -0,0 +1,458 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import java.util.List; +import java.util.ListIterator; +import java.util.LinkedList; +import java.util.zip.ZipInputStream; +import java.util.zip.ZipOutputStream; +import java.util.zip.ZipEntry; +import java.util.zip.CRC32; +import java.io.InputStream; +import java.io.OutputStream; +import java.io.IOException; +import java.io.ByteArrayOutputStream; + +import org.openoffice.xmerge.util.Debug; + +/** + * Class used by {@link + * org.openoffice.xmerge.converter.OfficeDocument + * OfficeDocument} to handle reading and writing + * from a ZIP file, as well as storing ZIP entries. + * + * @author Herbie Ong + */ +class OfficeZip { + + /** File name of the XML file in a zipped document. */ + private final static String CONTENTXML = "content.xml"; + + private final static String STYLEXML = "styles.xml"; + private final static String METAXML = "meta.xml"; + private final static String SETTINGSXML = "settings.xml"; + private final static String MANIFESTXML = "META-INF/manifest.xml"; + + private final static int BUFFERSIZE = 1024; + + private List entryList = null; + + private int contentIndex = -1; + private int styleIndex = -1; + private int metaIndex = -1; + private int settingsIndex = -1; + private int manifestIndex = -1; + + /** Default constructor. */ + OfficeZip() { + + entryList = new LinkedList(); + } + + + /** + * <p>Read each zip entry in the <code>InputStream</code> object + * and store in entryList both the <code>ZipEntry</code> object + * as well as the bits of each entry. Call this method before + * calling the <code>getContentXMLBytes</code> method or the + * <code>getStyleXMLBytes</code> method.</p> + * + * <p>Keep track of the CONTENTXML and STYLEXML using + * contentIndex and styleIndex, respectively.</p> + * + * @param is <code>InputStream</code> object to read. + * + * @throws IOException If any I/O error occurs. + */ + void read(InputStream is) throws IOException { + + ZipInputStream zis = new ZipInputStream(is); + ZipEntry ze = null; + int i = -1; + + while ((ze = zis.getNextEntry()) != null) { + + String name = ze.getName(); + + Debug.log(Debug.TRACE, "reading entry: " + name); + + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + + int len = 0; + byte buffer[] = new byte[BUFFERSIZE]; + + while ((len = zis.read(buffer)) > 0) { + baos.write(buffer, 0, len); + } + + byte bytes[] = baos.toByteArray(); + Entry entry = new Entry(ze,bytes); + + entryList.add(entry); + + i++; + + if (name.equalsIgnoreCase(CONTENTXML)) { + contentIndex = i; + } + else if (name.equalsIgnoreCase(STYLEXML)) { + styleIndex = i; + } + else if (name.equalsIgnoreCase(METAXML)) { + metaIndex = i; + } + else if (name.equalsIgnoreCase(SETTINGSXML)) { + settingsIndex = i; + } + else if (name.equalsIgnoreCase(MANIFESTXML)) { + manifestIndex = i; + } + + } + + zis.close(); + } + + + /** + * This method returns the CONTENTXML file in a + * <code>byte</code> array. It returns null if there is no + * CONTENTXML in this zip file. + * + * @return CONTENTXML in a <code>byte</code> array. + */ + byte[] getContentXMLBytes() { + + return getEntryBytes(contentIndex); + } + + + /** + * This method returns the STYLEXML file in a + * <code>byte</code> array. It returns null if there is + * no STYLEXML in this zip file. + * + * @return STYLEXML in a <code>byte</code> array. + */ + byte[] getStyleXMLBytes() { + + return getEntryBytes(styleIndex); + } + + /** + * This method returns the METAXML file in a + * <code>byte</code> array. It returns null if there is + * no METAXML in this zip file. + * + * @return METAXML in a <code>byte</code> array. + */ + byte[] getMetaXMLBytes() { + return getEntryBytes(metaIndex); + } + + /** + * This method returns the SETTINGSXML file in a + * <code>byte</code> array. It returns null if there is + * no SETTINGSXML in this zip file. + * + * @return SETTINGSXML in a <code>byte</code> array. + */ + byte[] getSettingsXMLBytes() { + return getEntryBytes(settingsIndex); + } + + /** + * This method returns the MANIFESTXML file in a <code>byte</code> array. + * It returns null if there is no MANIFESTXML in this zip file. + * + * @return MANIFESTXML in a <code>byte</code> array. + */ + byte[] getManifestXMLBytes() { + return getEntryBytes(manifestIndex); + } + + /** + * This method returns the bytes corresponding to the entry named in the + * parameter. + * + * @param name The name of the entry in the Zip file to retrieve. + * + * @return The data for the named entry in a <code>byte</code> array or + * <code>null</code> if no entry is found. + */ + byte[] getNamedBytes(String name) { + + // The list is not sorted, and sorting it for a binary search would + // invalidate the indices stored for the main files. + + // Could improve performance by caching the name and index when + // iterating through the ZipFile in read(). + for (int i = 0; i < entryList.size(); i++) { + Entry e = (Entry)entryList.get(i); + + if (e.zipEntry.getName().equals(name)) { + return getEntryBytes(i); + } + } + + return null; + } + + + /** + * This method sets the bytes for the named entry. It searches for a + * matching entry in the LinkedList. If no entry is found, a new one is + * created. + * + * Writing of data is defferred to setEntryBytes(). + * + * @param name The name of the entry to search for. + * @param bytes The new data to write. + */ + void setNamedBytes(String name, byte[] bytes) { + for (int i = 0; i < entryList.size(); i++) { + Entry e = (Entry)entryList.get(i); + + if (e.zipEntry.getName().equals(name)) { + setEntryBytes(i, bytes, name); + return; + } + } + + // If we're here, no entry was found. Call setEntryBytes with an index + // of -1 to insert a new entry. + setEntryBytes(-1, bytes, name); + } + + /** + * Used by the <code>getContentXMLBytes</code> method and the + * <code>getStyleXMLBytes</code> method to return the + * <code>byte</code> array from the corresponding + * <code>entry</code> in the <code>entryList</code>. + * + * @param index Index of <code>Entry</code> object in + * <code>entryList</code>. + * + * @return <code>byte</code> array associated in that + * <code>Entry</code> object or null, if there is + * not such <code>Entry</code>. + */ + private byte[] getEntryBytes(int index) { + + byte[] bytes = null; + + if (index > -1) { + Entry entry = (Entry) entryList.get(index); + bytes = entry.bytes; + } + return bytes; + } + + + /** + * Set or replace the <code>byte</code> array for the + * CONTENTXML file. + * + * @param bytes <code>byte</code> array for the + * CONTENTXML file. + */ + void setContentXMLBytes(byte bytes[]) { + + contentIndex = setEntryBytes(contentIndex, bytes, CONTENTXML); + } + + + /** + * Set or replace the <code>byte</code> array for the + * STYLEXML file. + * + * @param bytes <code>byte</code> array for the + * STYLEXML file. + */ + void setStyleXMLBytes(byte bytes[]) { + + styleIndex = setEntryBytes(styleIndex, bytes, STYLEXML); + } + + + /** + * Set or replace the <code>byte</code> array for the + * METAXML file. + * + * @param bytes <code>byte</code> array for the + * METAXML file. + */ + void setMetaXMLBytes(byte bytes[]) { + + metaIndex = setEntryBytes(metaIndex, bytes, METAXML); + } + + + /** + * Set or replace the <code>byte</code> array for the + * SETTINGSXML file. + * + * @param bytes <code>byte</code> array for the + * SETTINGSXML file. + */ + void setSettingsXMLBytes(byte bytes[]) { + + settingsIndex = setEntryBytes(settingsIndex, bytes, SETTINGSXML); + } + + + /** + * Set or replace the <code>byte</code> array for the MANIFESTXML file. + * + * @param bytes <code>byte</code> array for the MANIFESTXML file. + */ + void setManifestXMLBytes(byte bytes[]) { + manifestIndex = setEntryBytes(manifestIndex, bytes, MANIFESTXML); + } + + /** + * <p>Used by the <code>setContentXMLBytes</code> method and + * the <code>setStyleXMLBytes</code> to either replace an + * existing <code>Entry</code>, or create a new entry in + * <code>entryList</code>.</p> + * + * <p>If there is an <code>Entry</code> object within + * entryList that corresponds to the index, replace the + * <code>ZipEntry</code> info.</p> + * + * @param index Index of <code>Entry</code> to modify. + * @param bytes <code>Entry</code> value. + * @param name Name of <code>Entry</code>. + * + * @return Index of value added or modified in entryList + */ + private int setEntryBytes(int index, byte bytes[], String name) { + + if (index > -1) { + + // replace existing entry in entryList + + Entry entry = (Entry) entryList.get(index); + name = entry.zipEntry.getName(); + int method = entry.zipEntry.getMethod(); + + ZipEntry ze = createZipEntry(name, bytes, method); + + entry.zipEntry = ze; + entry.bytes= bytes; + + } else { + + // add a new entry into entryList + ZipEntry ze = createZipEntry(name, bytes, ZipEntry.DEFLATED); + Entry entry = new Entry(ze, bytes); + entryList.add(entry); + index = entryList.size() - 1; + } + + return index; + } + + + /** + * Write out the ZIP entries into the <code>OutputStream</code> + * object. + * + * @param os <code>OutputStream</code> object to write ZIP. + * + * @throws IOException If any ZIP I/O error occurs. + */ + void write(OutputStream os) throws IOException { + + Debug.log(Debug.TRACE, "Writing out the following entries into zip."); + + ZipOutputStream zos = new ZipOutputStream(os); + + ListIterator iterator = entryList.listIterator(); + + while (iterator.hasNext()) { + + Entry entry = (Entry) iterator.next(); + ZipEntry ze = entry.zipEntry; + + String name = ze.getName(); + + Debug.log(Debug.TRACE, "... " + name); + + zos.putNextEntry(ze); + zos.write(entry.bytes); + } + + zos.close(); + } + + + /** + * Creates a <code>ZipEntry</code> object based on the given params. + * + * @param name Name for the <code>ZipEntry</code>. + * @param bytes <code>byte</code> array for <code>ZipEntry</code>. + * @param method ZIP method to be used for <code>ZipEntry</code>. + * + * @return A <code>ZipEntry</code> object. + */ + private ZipEntry createZipEntry(String name, byte bytes[], int method) { + + ZipEntry ze = new ZipEntry(name); + + ze.setMethod(method); + ze.setSize(bytes.length); + + CRC32 crc = new CRC32(); + crc.reset(); + crc.update(bytes); + ze.setCrc(crc.getValue()); + + ze.setTime(System.currentTimeMillis()); + + return ze; + } + + /** + * This inner class is used as a data structure for holding + * a <code>ZipEntry</code> info and its corresponding bytes. + * These are stored in entryList. + */ + private class Entry { + + ZipEntry zipEntry = null; + byte bytes[] = null; + + Entry(ZipEntry zipEntry, byte bytes[]) { + this.zipEntry = zipEntry; + this.bytes = bytes; + } + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/ParaStyle.java b/xmerge/java/org/openoffice/xmerge/converter/xml/ParaStyle.java new file mode 100644 index 000000000000..10a1dbaaaed1 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/ParaStyle.java @@ -0,0 +1,607 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import java.io.IOException; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import java.lang.reflect.Constructor; +import org.openoffice.xmerge.util.Debug; + + +abstract class conversionAlgorithm { + int I(String val) { + return 0; + } +} + + /* + * This algorithm expects only values in millimeters, e.g. "20.3mm". + */ +class horizSize extends conversionAlgorithm { + int I(String value) { + if (value.endsWith("mm")) { + float size = (float)0.0; + String num = value.substring(0, value.length() - 2); + try { + size = Float.parseFloat(num); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Error parsing " + value, e); + } + size *= 100; + return (int)size; + } else { + Debug.log(Debug.ERROR, "Unexpected value (" + value + + ") in horizSize.I()"); + return 0; + } + } +} + + +/* + * This algorithm does line height - can be either millimeters or + * a percentage. + */ +class lineHeight extends conversionAlgorithm { + int I(String value) { + if (value.endsWith("mm")) { + float size = (float)0.0; + String num = value.substring(0, value.length() - 2); + try { + size = Float.parseFloat(num); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Error parsing " + value, e); + } + size *= 100; + return (int)size; + } else if (value.endsWith("%")) { + float size = (float)0.0; + String num = value.substring(0, value.length() - 1); + try { + size = Float.parseFloat(num); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Error parsing " + value, e); + } + int retval = (int) size; + retval |= ParaStyle.LH_PCT; + return retval; + } + return 0; + } +} + + +/** + * This class converts alignment values. + */ +class alignment extends conversionAlgorithm { + int I(String value) { + if (value.equals("end")) + return ParaStyle.ALIGN_RIGHT; + if (value.equals("right")) + return ParaStyle.ALIGN_RIGHT; + if (value.equals("center")) + return ParaStyle.ALIGN_CENTER; + if (value.equals("justify")) + return ParaStyle.ALIGN_JUST; + if (value.equals("justified")) + return ParaStyle.ALIGN_JUST; + if (value.equals("start")) + return ParaStyle.ALIGN_LEFT; + if (value.equals("left")) + return ParaStyle.ALIGN_LEFT; + Debug.log(Debug.ERROR, "Unknown string (" + + value + ") in alignment.I()"); + return ParaStyle.ALIGN_LEFT; + } +} + + +/** + * <p>This class represents a paragraph <code>Style</code>.</p> + * + * <p><table border="1" cellpadding="1"><tr><td> + * Attribute </td><td>Value + * </td></tr><tr><td> + * MARGIN_LEFT </td><td>mm * 100 + * </td></tr><tr><td> + * MARGIN_RIGHT </td><td>mm * 100 + * </td></tr><tr><td> + * MARGIN_TOP </td><td>mm * 100 (space on top of paragraph) + * </td></tr><tr><td> + * MARGIN_BOTTOM </td><td>mm * 100 + * </td></tr><tr><td> + * TEXT_INDENT </td><td>mm * 100 (first line indent) + * </td></tr><tr><td> + * LINE_HEIGHT </td><td>mm * 100, unless or'ed with LH_PCT, in which + * case it is a percentage (e.g. 200% for double spacing) + * Can also be or'ed with LH_ATLEAST. Value is stored + * in bits indicated by LH_VALUEMASK. + * </td></tr><tr><td> + * TEXT_ALIGN </td><td>ALIGN_RIGHT, ALIGN_CENTER, ALIGN_JUST, ALIGN_LEFT + * </td></tr></table></p> + * + * @author David Proulx + */ +public class ParaStyle extends Style implements Cloneable { + + /** The left margin property. */ + public static final int MARGIN_LEFT = 0; + /** The right margin property. */ + public static final int MARGIN_RIGHT = 1; + /** The top margin property. */ + public static final int MARGIN_TOP = 2; + /** The bottom margin property. */ + public static final int MARGIN_BOTTOM = 3; + /** Indent left property. */ + public static final int TEXT_INDENT = 4; + /** Indent right property. */ + public static final int LINE_HEIGHT = 5; + /** Align text property. */ + public static final int TEXT_ALIGN = 6; + // This must always be one more than highest property + /** Total number of properties. */ + protected static final int NR_PROPERTIES = 7; + + /** + * Array of flags indicating which attributes are set for this + * paragraph <code>Style</code>. + */ + protected boolean isSet[] = new boolean[NR_PROPERTIES]; + /** Array of attribute values for this paragraph <code>tyle</code>. */ + protected int value[] = new int[NR_PROPERTIES]; + /** Array of attribute names for this paragraph <code>Style</code>. */ + protected String attrName[] = { + "fo:margin-left", + "fo:margin-right", + "fo:margin-top", + "fo:margin-bottom", + "fo:text-indent", + "fo:line-height", + "fo:text-align" + }; + + /** Array of attribute structures for this paragraph <code>Style</code>. */ + protected Class algor[] = { + horizSize.class, + horizSize.class, + horizSize.class, + horizSize.class, + horizSize.class, + lineHeight.class, + alignment.class + }; + + /** Align right. */ + public static final int ALIGN_RIGHT = 1; + /** Align center. */ + public static final int ALIGN_CENTER = 2; + /** Align justified. */ + public static final int ALIGN_JUST = 3; + /** Align left. */ + public static final int ALIGN_LEFT = 4; + + /** Line height percentage. */ + public static final int LH_PCT = 0x40000000; + /** Line height minimum value. */ + public static final int LH_ATLEAST = 0x20000000; + /** Line height mask. */ + public static final int LH_VALUEMASK = 0x00FFFFFF; + + /** Ignored tags. */ + private static String[] ignored = { + "style:font-name", "fo:font-size", "fo:font-weight", "fo:color", + "fo:language", "fo:country", "style:font-name-asian", + "style:font-size-asian", "style:language-asian", + "style:country-asian", "style:font-name-complex", + "style:font-size-complex", "style:language-complex", + "style:country-complex", "style:text-autospace", "style:punctuation-wrap", + "style:line-break", "fo:keep-with-next", "fo:font-style", + "text:number-lines", "text:line-number" + }; + + + /** + * Constructor for use when going from DOM to client device format. + * + * @param node A <i>style:style</i> <code>Node</code> which, which + * is assumed to have <i>family</i> attribute of + * <i>paragraph</i>. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public ParaStyle(Node node, StyleCatalog sc) { + + super(node, sc); + + // Look for children. Only ones we care about are "style:properties" + // nodes. If any are found, recursively traverse them, passing + // along the style element to add properties to. + // + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + for (int i = 0; i < len; i++) { + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:properties")) { + NamedNodeMap childAttrNodes = child.getAttributes(); + if (childAttrNodes != null) { + int nChildAttrNodes = childAttrNodes.getLength(); + for (int j = 0; j < nChildAttrNodes; j++) { + Node attr = childAttrNodes.item(j); + setAttribute(attr.getNodeName(), attr.getNodeValue()); + } + } + } + } + } + } + + + /** + * Constructor for use when going from client device format to DOM. + * + * @param name Name of the <code>Style</code>. Can be null. + * @param family Family of the <code>Style</code> - usually + * <i>paragraph</i>, <i>text</i>, etc. Can be null. + * @param parent Name of the parent <code>Style</code>, or null + * if none. + * @param attribs Array of attributes to set. + * @param values Array of values to set. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public ParaStyle(String name, String familyName, String parentName, + String attribs[], String values[], StyleCatalog sc) { + super(name, familyName, parentName, sc); + if (attribs != null) + for (int i = 0; i < attribs.length; i++) + setAttribute(attribs[i], values[i]); + } + + + /** + * Alternate constructor for use when going from client device + * format to DOM. + * + * @param name Name of the <code>Style</code>. Can be null. + * @param family Family of the <code>Style</code> - usually + * <i>paragraph</i>, <i>text</i>, etc. Can be null. + * @param parent Name of the parent <code>Style</code>, or + * null if none. + * @param attribs Array of attributes indices to set. + * @param values Array of values to set. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public ParaStyle(String name, String familyName, String parentName, + int attribs[], String values[], StyleCatalog lookup) { + super(name, familyName, parentName, lookup); + if (attribs != null) + for (int i = 0; i < attribs.length; i++) + setAttribute(attribs[i], values[i]); + } + + + /** + * This code checks whether an attribute is one that we + * intentionally ignore. + * + * @param attribute The attribute to check. + * + * @return true if attribute can be ignored, false otherwise. + */ + private boolean isIgnored(String attribute) { + for (int i = 0; i < ignored.length; i++) { + if (ignored[i].equals(attribute)) + return true; + } + return false; + } + + + /** + * Set an attribute for this paragraph <code>Style</code>. + * + * @param attr The attribute to set. + * @param value The attribute value to set. + */ + public void setAttribute(String attr, String value) { + for (int i = 0; i < NR_PROPERTIES; i++) { + if (attr.equals(attrName[i])) { + setAttribute(i, value); + return; + } + } + if (!isIgnored(attr)) + Debug.log(Debug.INFO, "ParaStyle Unhandled: " + attr + "=" + value); + } + + + /** + * Check whether an attribute is set in this <code>Style</code>. + * + * @param attrIndex The attribute index to check. + * + * @return true if the attribute at specified index is set, + * false otherwise. + */ + public boolean isAttributeSet(int attrIndex) { + return isSet[attrIndex]; + } + + + /** + * Get the value of an integer attribute. + * + * @param attrIndex Index of the attribute. + * + * @return Value of the attribute, 0 if not set. + */ + public int getAttribute(int attrIndex) { + if (isSet[attrIndex]) + return value[attrIndex]; + else return 0; + } + + + /** + * Set an attribute for this paragraph <code>Style</code>. + * + * @param attr The attribute index to set. + * @apram value The attribute value to set. + */ + public void setAttribute(int attr, String value) { + isSet[attr] = true; + try { + this.value[attr] = (((conversionAlgorithm)algor[attr].newInstance())).I(value); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Instantiation error", e); + } + } + + + /** + * Return the <code>Style</code> in use. + * + * @return The fully-resolved copy of the <code>Style</code> in use. + */ + public Style getResolved() { + ParaStyle resolved = null; + try { + resolved = (ParaStyle)this.clone(); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Can't clone", e); + } + + // Look up the parent style. (If there is no style catalog + // specified, we can't do any lookups). + ParaStyle parentStyle = null; + if (sc != null) { + if (parent != null) { + parentStyle = (ParaStyle)sc.lookup(parent, family, null, + this.getClass()); + if (parentStyle == null) + Debug.log(Debug.ERROR, "parent style lookup of " + + parent + " failed!"); + else + parentStyle = (ParaStyle)parentStyle.getResolved(); + } else if (!name.equals("DEFAULT_STYLE")) { + parentStyle = (ParaStyle)sc.lookup("DEFAULT_STYLE", null, null, + this.getClass()); + } + } + + // If we found a parent, for any attributes which we don't have + // set, try to get the values from the parent. + if (parentStyle != null) { + parentStyle = (ParaStyle)parentStyle.getResolved(); + for (int i = 0; i < NR_PROPERTIES; i++) { + if (!isSet[i] && parentStyle.isSet[i]) { + resolved.isSet[i] = true; + resolved.value[i] = parentStyle.value[i]; + } + } + } + return resolved; + } + + + /** + * Private function to return the value as an element in + * a Comma Separated Value (CSV) format. + * + * @param value The value to format. + * + * @return The formatted value. + */ + private static String toCSV(String value) { + if (value != null) + return "\"" + value + "\","; + else + return "\"\","; + } + + + /** + * Private function to return the value as a last element in + * a Comma Separated Value (CSV) format. + * + * @param value The value to format. + * + * @return The formatted value. + */ + private static String toLastCSV(String value) { + if (value != null) + return "\"" + value + "\""; + else + return "\"\""; + } + + + /** + * Print a Comma Separated Value (CSV) header line for the + * spreadsheet dump. + */ + public static void dumpHdr() { + System.out.println(toCSV("Name") + toCSV("Family") + toCSV("parent") + + toCSV("left mgn") + toCSV("right mgn") + + toCSV("top mgn") + toCSV("bottom mgn") + toCSV("txt indent") + + toCSV("line height") + toLastCSV("txt align")); + } + + + /** + * Dump this <code>Style</code> as a Comma Separated Value (CSV) + * line. + */ + public void dumpCSV() { + String attributes = ""; + for (int index = 0; index <= 6; index++) { + if (isSet[index]) { + attributes += toCSV("" + value[index]); + } + else + attributes += toCSV(null); // unspecified + } + System.out.println(toCSV(name) + toCSV(family) + toCSV(parent) + + attributes + toLastCSV(null)); + } + + + /** + * Create the <code>Node</code> with the specified elements. + * + * @parentDoc Parent <code>Document</code> of the + * <code>Node</code> to create. + * @param name Name of the <code>Node</code>. + * + * @return The created <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + Element node = parentDoc.createElement(name); + writeAttributes(node); + return node; + } + + + /** + * Return true if <code>style</code> is a subset of the + * <code>Style</code>. + * + * @param style <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Style style) { + + if (!super.isSubset(style)) + return false; + if (!this.getClass().isAssignableFrom(style.getClass())) + return false; + ParaStyle ps = (ParaStyle)style; + + for (int i = 0; i < NR_PROPERTIES; i++) { + if (ps.isSet[i]) { + // if (!isSet[i]) return false; + + if (i < NR_PROPERTIES - 1) { + // Compare the actual values. We allow a margin of error + // here because the conversion loses precision. + int diff; + if (value[i] > ps.value[i]) + diff = value[i] - ps.value[i]; + else + diff = ps.value[i] - value[i]; + if (diff > 32) + return false; + } else { + if (i == TEXT_ALIGN) + if ((value[i] == 0) && (ps.value[i] == 4)) + continue; + if (value[i] != ps.value[i]) + return false; + } + } + } + return true; + } + + + /** + * Add <code>Style</code> attributes to the given + * <code>Node</code>. This may involve writing child + * <code>Node</code> objects as well. + * + * @param node The <code>Node</code> to add <code>Style</code> + * attributes. + */ + public void writeAttributes(Element node) { + for (int i = 0; i <= TEXT_INDENT; i++) { + if (isSet[i]) { + double temp = value[i] / 100.0; + String stringVal = (new Double(temp)).toString() + "mm"; + node.setAttribute(attrName[i], stringVal); + } + } + + if (isSet[LINE_HEIGHT]) { + String stringVal; + if ((value[LINE_HEIGHT] & LH_PCT) != 0) + stringVal = (new Integer(value[LINE_HEIGHT] & LH_VALUEMASK)).toString() + "%"; + else { + double temp = (value[LINE_HEIGHT] & LH_VALUEMASK) / 100.0; + stringVal = (new Double(temp)).toString() + "mm"; + } + node.setAttribute(attrName[LINE_HEIGHT], stringVal); + } + + if (isSet[TEXT_ALIGN]) { + String val; + switch (value[TEXT_ALIGN]) { + case ALIGN_RIGHT: val = "end"; break; + case ALIGN_CENTER: val = "center"; break; + case ALIGN_JUST: val = "justify"; break; + case ALIGN_LEFT: val = "left"; break; + default: val = "unknown"; break; + } + node.setAttribute(attrName[TEXT_ALIGN], val); + } + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/Style.java b/xmerge/java/org/openoffice/xmerge/converter/xml/Style.java new file mode 100644 index 000000000000..cf8611f4e143 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/Style.java @@ -0,0 +1,235 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import java.io.IOException; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; + +/** + * An object of class <code>Style</code> represents a <i>style</i> + * in an OpenOffice document. In practice subclasses of this + * <code>Style</code>, such as <code>TextStyle</code>, + * <code>ParaStyle</code> are used. + * + * @author David Proulx + * @see <a href="TextStyle.html">TextStyle</a>, + * <a href="ParaStyle.html">ParaStyle</a> + */ +public class Style { + + /** Name of the <code>Style</code>. */ + protected String name = null; + /** Family of the <code>Style</code>. */ + protected String family = null; + /** Parent of the <code>Style</code>. */ + protected String parent = null; + + /** + * A reference to the <code>StyleCatalog</code> to be used for + * looking up ancestor <code>Style</code> objects. + */ + protected StyleCatalog sc; + + + /** + * Constructor for use when going from DOM to client device format. + * + * @param node A <i>style:style</i> or <i>style:default-style</i> + * <code>Node</code> from the document being parsed. + * No checking of <code>Node</code> is done, so if it + * is not of the proper type the results will be + * unpredictable. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public Style(Node node, StyleCatalog sc) { + + this.sc = sc; + + // Run through the attributes of this node, saving + // the ones we're interested in. + if (node.getNodeName().equals("style:default-style")) + name = "DEFAULT_STYLE"; + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + if (attr.getNodeName().equals("style:family")) + family = attr.getNodeValue(); + else if (attr.getNodeName().equals("style:name")) { + name = attr.getNodeValue(); + } else if (attr.getNodeName().equals("style:parent-style-name")) + parent = attr.getNodeValue(); + + } + } + } + + + /** + * Constructor for use when going from client device format to DOM. + * + * @param name Name of the <code>Style</code>. Can be null. + * @param family Family of the <code>Style</code> - usually + * <i>paragraph</i>, <i>text</i>, etc. Can be null. + * @param parent Name of the parent <code>Style</code>, or null if none. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public Style(String name, String family, String parent, StyleCatalog sc) { + this.sc = sc; + this.name = name; + this.family = family; + this.parent = parent; + } + + + /** + * Set the <code>StyleCatalog</code> to be used when looking up the + * <code>Style</code> parent. + * + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public void setCatalog(StyleCatalog sc) { + this.sc = sc; + } + + + /** + * Returns the name of this <code>Style</code>. + * + * @return The name of this <code>Style</code>. + */ + public String getName() { + return name; + } + + + /** + * Sets the name of this <code>Style</code>. + * + * @param newName The new name of this <code>Style</code>. + */ + public void setName(String newName) { + name = newName; + } + + + /** + * Return the family of this <code>Style</code>. + * + * @return The family of this <code>Style</code>. + */ + public String getFamily() { + return family; + } + + /** + * Return the name of the parent of this <code>Style</code>. + * + * @return The parent of this <code>Style</code>. + */ + public String getParent() { + return parent; + } + + + /** + * Return a <code>Style</code> object corresponding to this one, but with + * all of the inherited information from parent <code>Style</code> + * objects filled in. The object returned will be a new object, not a + * reference to this object, even if it does not need any information + * added. + * + * @return A resolved <code>Style</code> object in which to look up + * ancestors. + */ + public Style getResolved() { + return new Style(name, family, parent, sc); + } + + + /** + * Write a <code>Node</code> in <code>parentDoc</code> + * representing this <code>Style</code>. Note that the + * <code>Node</code> is returned unconnected. + * + * @param parentDoc Document to which new <code>Node</code> will + * belong. + * @param name Name to use for new <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + // DJP: write this! Should call writeAttributes() + return null; + } + + + /** + * Write this <code>Style</code> object's attributes to the given + * <code>Node</code>. This may involve writing child + * <code>Node</code> objects as well. This is similar to the + * <code>writeNode</code> method, but the <code>Node</code> + * already exists, and this does <b>not</b> write the name, + * family, and parent attributes, which are assumed to already + * exist in the <code>Node</code>. + * + * @param node The <code>Node</code> to add style attributes. + */ + public void writeAttributes(Node node) { + } + + + /** + * Return true if <code>Style</code> is a subset of this one. Note + * that this will return true even if <code>Style</code> is less + * specific than this <code>Style</code>, so long as it does not + * contradict this <code>Style</code> in any way. + * + * This always returns true since only subclasses of + * <code>Style</code> contain any actual <code>Style</code> + * information. + * + * @param style The <code>Style</code> to check + * + * @return true if the <code>Style</code> is a subset, false otherwise. + */ + public boolean isSubset(Style style) { + return true; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/StyleCatalog.java b/xmerge/java/org/openoffice/xmerge/converter/xml/StyleCatalog.java new file mode 100644 index 000000000000..689b5d47c5b4 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/StyleCatalog.java @@ -0,0 +1,397 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; +import org.openoffice.xmerge.util.*; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import java.io.IOException; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import java.util.Vector; +import java.lang.reflect.Constructor; +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; + + +/** + * A <code>StyleCatalog</code> holds a collection of <code>Style</code> + * objects. It is intended for use when parsing or building a DOM + * document. + * + * Each entry in the <code>StyleCatalog</code> represents a + * <code>Style</code>, and is an object which is a subclass of + * <code>Style</code>. + * + * @author David Proulx + * @see <a href="Style.html">Style</a> + */ +public class StyleCatalog { + + private Vector styles; // The actual styles + + /** + * Constructor + * + * @param initialEntries Expected number of entries to set + * for efficiency purposes. + */ + public StyleCatalog(int initialEntries) { + styles = new Vector(initialEntries); + } + + + /** + * <p>Parse the <code>Document</code> starting from <code>node</code> + * and working downward, and add all styles found, so long as their + * family name is listed in <code>families</code>. For each + * family name in <code>families</code> there must be a corresponding + * element in <code>classes</code>, which specifies the class type + * to use for that family. All of these classes must be + * subclasses of <code>Style</code>. There can be multiple + * classes specified for a particular family.</p> + * + * <p>If <code>defaultClass</code> is non-null, then all styles that + * are found will be added. Any <code>Style</code> whose family is + * not listed in <code>families</code> will be added using defaultClass, + * which, of course, must be a subclass of <code>Style</code>. + * If <code>alwaysCreateDefault</code> is true, then a class + * of type <code>defaultClass</code> will always be created, + * regardless of whether there was also a match in + * <code>families</code>.</p> + * + * <p>DJP Todo: make it recursive so that <code>node</code> can be + * higher up in the <code>Document</code> tree.</p> + * + * @param node The node to be searched for + * <code>Style</code> objects. + * @param families An array of <code>Style</code> families + * to add. + * @param classes An array of class types corresponding + * to the families array. + * @param defaultClass All <code>Style</code> objects that are + * found are added to this class. + * @param alwaysCreateDefault A class of type <code>defaultClass</code> + * will always be created, regardless of + * whether there is a match in the + * families array. + */ + public void add(Node node, String families[], Class classes[], + Class defaultClass, boolean alwaysCreateDefault) { + + if (node == null) + return; + + if (families == null) + families = new String[0]; + if (classes == null) + classes = new Class[0]; + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + + for (int i = 0; i < len; i++) { + boolean found = false; + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:default-style") || name.equals("style:style")) { + String familyName = getFamilyName(child); + if (familyName == null) { + Debug.log(Debug.ERROR, "familyName is null!"); + continue; + } + + for (int j = 0; j < families.length; j++) { + if (families[j].equals(familyName)) { + Class styleClass = classes[j]; + callConstructor(classes[j], child); + found = true; + } + } + if ((!found || alwaysCreateDefault) && (defaultClass != null)) + callConstructor(defaultClass, child); + } + } + } + } + + + /** + * Call the constructor of class <code>cls</code> with parameters + * <code>node</code>, and add the resulting <code>Style</code> to + * the catalog. + * + * @param cls The class whose constructor will be called. + * @param node The constructed class will be added to this node. + */ + private void callConstructor(Class cls, Node node) { + Class params[] = new Class[2]; + params[0] = Node.class; + params[1] = this.getClass(); + try { + Constructor c = cls.getConstructor(params); + Object p[] = new Object[2]; + p[0] = node; + p[1] = this; + styles.add(c.newInstance(p)); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Exception when calling constructor", e); + } + } + + + /** + * Add a <code>Style</code> to the catalog. + * + * @param s The <code>Style</code> to add. + */ + public void add(Style s) { + styles.addElement(s); + } + + + /** + * Return the first <code>Style</code> matching the specified names. + * + * @param name Name to match, null is considered + * <i>always match</i>. + * @param family Family to match, null is considered + * <i>always match</i>. + * @param parent Parent to match, null is considered + * <i>always match</i>. + * @param styleClass styleClass to match, null is considered + * <i>always match</i>. + * + * @return <code>Style</code> value if all parameters match, + * null otherwise + */ + public Style lookup(String name, String family, String parent, + Class styleClass) { + int nStyles = styles.size(); + for (int i = 0; i < nStyles; i++) { + Style s = (Style)styles.elementAt(i); + if ((name != null) && (s.getName() != null) + && (!s.getName().equals(name))) + continue; + if ((family != null) && (s.getFamily() != null) + && (!s.getFamily().equals(family))) + continue; + if ((parent != null) && (s.getParent() != null) + && (!s.getParent().equals(parent))) + continue; + if ((styleClass != null) && (s.getClass() != styleClass)) + continue; + if (s.getName() == null) continue; // DJP: workaround for "null name" problem + return s; + } + return null; // none found + } + + + /** + * Given a <code>Style</code> <code>s<code> return all + * <code>Style</code> objects that match. + * + * @param s <code>Style</code> to match. + * + * @return An array of <code>Style</code> objects that match, an + * empty array if none match. + */ + public Style[] getMatching(Style s) { + + // Run through and count the matching styles so we know how big of + // an array to allocate. + int matchCount = 0; + int nStyles = styles.size(); + for (int j = 0; j < nStyles; j++) { + Style p = ((Style)styles.elementAt(j)).getResolved(); + if (p.isSubset(s)) matchCount++; + } + + // Now allocate the array, and run through again, populating it. + Style[] matchArray = new Style[matchCount]; + matchCount = 0; + for (int j = 0; j < nStyles; j++) { + Style p = ((Style)styles.elementAt(j)).getResolved(); + if (p.isSubset(s)) matchArray[matchCount++] = p; + } + return matchArray; + } + + + /** + * Given a <code>Style</code> <code>s</code>, return the + * <code>style</code> that is the closest match. Not currently + * implemented. + * + * @param s <code>Style</code> to match. + * + * @return The <code>Style</code> that most closely matches. + */ + public Style getBestMatch(Style s) { + // DJP: is this needed? + // DJP ToDo: implement this + return null; + } + + + /** + * <p>Create a <code>Node</code> named <code>name</code> in + * <code>Document</code> <code>parentDoc</code>, and write the + * entire <code>StyleCatalog</code> to it.</p> + * + * <p>Note that the resulting node is returned, but is not connected + * into the document. Placing the output node in the document is + * left to the caller.</p> + * + * @param parentDoc The <code>Document</code> to add the + * <code>Node</code>. + * @param name The name of the <code>Node</code> to add. + * + * @return The <code>Element</code> that was created. + */ + public Element writeNode(org.w3c.dom.Document parentDoc, String name) { + Element rootNode = parentDoc.createElement(name); + + int len = styles.size(); + for (int j = 0; j < len; j++) { + Style s = (Style)styles.get(j); + + Element styleNode = parentDoc.createElement("style:style"); + + if (s.getName() != null) + styleNode.setAttribute("style:name", s.getName()); + if (s.getParent() != null) + styleNode.setAttribute("style:parent-style-name", s.getParent()); + if (s.getFamily() != null) + styleNode.setAttribute("style:family", s.getFamily()); + + Element propertiesNode = (Element) s.createNode(parentDoc, "style:properties"); + // if (propertiesNode.getFirstChild() != null) + // DJP: only add node if has children OR attributes + if (propertiesNode != null) + styleNode.appendChild(propertiesNode); + + rootNode.appendChild(styleNode); + } + + return rootNode; + } + + + /** + * Dump the <code>Style</code> table in Comma Separated Value (CSV) + * format + * + * @param para If true, dump in paragraph <code>Style</code>, + * otherwise dump in text style. + */ + public void dumpCSV(boolean para) { + if (!para) { + TextStyle.dumpHdr(); + int nStyles = styles.size(); + for (int i = 0; i < nStyles; i++) { + Style s = (Style)styles.get(i); + if (s.getClass().equals(TextStyle.class)) + ((TextStyle)s).dumpCSV(); + } + } else { + ParaStyle.dumpHdr(); + int nStyles = styles.size(); + for (int i = 0; i < nStyles; i++) { + Style s = (Style)styles.get(i); + if (s.getClass().equals(ParaStyle.class)) + ((ParaStyle)s).dumpCSV(); + } + } + + } + + + /** + * Check whether a given node represents a <code>Style</code> + * that should be added to the catalog, and if so, return the + * class type for it. If <code>Style</code> should not be added, + * or if node is not a <code>Style</code>, return null. + * + * @param node The <code>Node</code> to be checked. + * @param families An array of <code>Style</code> families. + * @param classes An array of class types corresponding to the + * families array. + * @param defaultClass The default class. + * + * @return The class that is appropriate for this node. + */ + private Class getClass(Node node, String[] families, Class[] classes, + Class defaultClass) { + NamedNodeMap attributes = node.getAttributes(); + if (attributes != null) { + int len = attributes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attributes.item(i); + if (attr.getNodeName().equals("style:family")) { + String familyName = attr.getNodeValue(); + for (int j = 0; j < families.length; j++) { + if (families[j].equals(familyName)) + return classes[j]; + } + return defaultClass; + } + } + } + return null; + } + + + /** + * Find the family attribute of a <code>Style</code> <code>Node</code>. + * + * @param node The <code>Node</code> to check. + * + * @return The family attribute, or null if one does not + * exist. + */ + private String getFamilyName(Node node) { + NamedNodeMap attributes = node.getAttributes(); + if (attributes != null) { + int len = attributes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attributes.item(i); + if (attr.getNodeName().equals("style:family")) { + return attr.getNodeValue(); + } + } + } + return null; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/StyleTest01.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/StyleTest01.xml new file mode 100644 index 000000000000..ac2652c49ee6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/StyleTest01.xml @@ -0,0 +1,169 @@ +<?xml version="1.0" encoding="UTF-8"?> + +<office:document office:class="text" office:version="0.9" xmlns:office="http://openoffice.org/2000/office" xmlns:style="http://openoffice.org/2000/style" xmlns:text="http://openoffice.org/2000/text" xmlns:table="http://openoffice.org/2000/table" xmlns:draw="http://openoffice.org/2000/drawing" xmlns:fo="http://www.w3.org/1999/XSL/Format" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="http://openoffice.org/2000/meta" xmlns:number="http://openoffice.org/2000/datastyle" xmlns:svg="http://www.w3.org/2000/svg" xmlns:chart="http://openoffice.org/2000/chart" xmlns:dr3d="http://openoffice.org/2000/dr3d" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="http://openoffice.org/2000/form" xmlns:script="http://openoffice.org/2000/script" xmlns:zensync="haha"> + + <!-- styles01 is four styles, named "TX01" through "TX04". Each is a + child of its predecessor. They define properties as follows: + fo:margin-right fo:margin-top fo:margin-bottom + TX01 100 300 + TX02 + TX03 200 + TX04 301 + When inheritance is considered, the properties look like this: + fo:margin-right fo:margin-top fo:margin-bottom + TX01 100 300 + TX02 100 300 + TX03 100 200 300 + TX04 100 200 301 + DJP: change prop1, prop2, prop3 to paragraph or text properties so + the actual classes can be tested. + --> + <zensync:styles01> + + <style:style style:name="TX01" style:family="text" + style:class="text"> + <style:properties fo:margin-right="100" fo:margin-bottom="300"/> + </style:style> + + <style:style style:name="TX02" style:family="text" + style:parent-style-name="TX01" style:class="text"> + </style:style> + + <style:style style:name="TX03" style:family="text" + style:parent-style-name="TX02" style:class="text"> + <style:properties fo:margin-top="200" /> + </style:style> + + <style:style style:name="TX04" style:family="text" + style:parent-style-name="TX03" style:class="text"> + <style:properties fo:margin-bottom="301" /> + </style:style> + + </zensync:styles01> + + + + <office:styles> + <style:default-style style:family="paragraph"> + <style:properties fo:color="#000000" style:font-name="Times New Roman" fo:font-size="12pt" fo:language="en" fo:country="US" style:font-name-asian="Andale WT UI" style:font-size-asian="12pt" style:language-asian="none" style:country-asian="none" style:font-name-complex="Simplified Arabic" style:font-size-complex="12pt" style:language-complex="none" style:country-complex="none" style:text-autospace="ideograph-alpha" style:punctuation-wrap="hanging" style:line-break="strict"> + <style:tab-stops> + <style:tab-stop style:position="22.05mm" style:type="default"/> + </style:tab-stops> + </style:properties> + </style:default-style> + <style:style style:name="Standard" style:family="paragraph" style:class="text"/> + <style:style style:name="Heading" style:family="paragraph" style:parent-style-name="Standard" style:next-style-name="Text body" style:class="text"> + <style:properties style:font-name="Arial" fo:font-size="14pt" fo:margin-top="4.23mm" fo:margin-bottom="2.12mm" fo:keep-with-next="true"/> + </style:style> + <style:style style:name="Text body" style:family="paragraph" style:parent-style-name="Standard" style:class="text"> + <style:properties fo:margin-top="0mm" fo:margin-bottom="2.12mm"/> + </style:style> + <style:style style:name="List" style:family="paragraph" style:parent-style-name="Text body" style:class="list"> + <style:properties style:font-name="Times New Roman"/> + </style:style> + <style:style style:name="Caption" style:family="paragraph" style:parent-style-name="Standard" style:class="extra"> + <style:properties style:font-name="Times New Roman" fo:font-size="10pt" fo:font-style="italic" fo:margin-top="2.12mm" fo:margin-bottom="2.12mm" text:number-lines="false" text:line-number="0"/> + </style:style> + <style:style style:name="Index" style:family="paragraph" style:parent-style-name="Standard" style:class="index"> + <style:properties style:font-name="Times New Roman" text:number-lines="false" text:line-number="0"/> + </style:style> + <style:style style:name="Heading 1" style:family="paragraph" style:parent-style-name="Heading" style:next-style-name="Text body" style:class="text"> + <style:properties fo:font-size="16pt" fo:font-weight="bold"/> + </style:style> + <style:style style:name="Heading 2" style:family="paragraph" style:parent-style-name="Heading" style:next-style-name="Text body" style:class="text"> + <style:properties fo:font-size="14pt" fo:font-style="italic" fo:font-weight="bold"/> + </style:style> + <style:style style:name="Heading 3" style:family="paragraph" style:parent-style-name="Heading" style:next-style-name="Text body" style:class="text"> + <style:properties fo:font-size="14pt" fo:font-weight="bold"/> + </style:style> + <style:style style:name="First line indent" style:family="paragraph" style:parent-style-name="Text body" style:class="text"> + <style:properties fo:margin-left="0mm" fo:margin-right="0mm" fo:text-indent="4.99mm"/> + </style:style> + <style:style style:name="Hanging indent" style:family="paragraph" style:parent-style-name="Text body" style:class="text"> + <style:properties fo:margin-left="10mm" fo:margin-right="0mm" fo:text-indent="-4.99mm"> + <style:tab-stops> + <style:tab-stop style:position="0mm"/> + </style:tab-stops> + </style:properties> + </style:style> + <style:style style:name="Marginalia" style:family="paragraph" style:parent-style-name="Text body" style:class="text"> + <style:properties fo:margin-left="40.01mm" fo:margin-right="0mm" fo:text-indent="0mm"/> + </style:style> + <style:style style:name="Salutation" style:family="paragraph" style:parent-style-name="Standard" style:class="text"> + <style:properties text:number-lines="false" text:line-number="0"/> + </style:style> + <style:style style:name="Strong Emphasis" style:family="text"> + <style:properties fo:font-weight="bold"/> + </style:style> + <style:style style:name="Example" style:family="text"> + <style:properties style:font-name="Courier"/> + </style:style> + <style:style style:name="Definition" style:family="text"/> + <style:style style:name="Line numbering" style:family="text"/> + <style:default-style style:family="graphics"> + <style:properties svg:width="0mm" svg:height="0mm" text:anchor-type="page" text:anchor-page-number="0" svg:x="0mm" svg:y="0mm" style:run-through="foreground" style:wrap="parallel" style:number-wrapped-paragraphs="no-limit" style:vertical-pos="from-top" style:vertical-rel="page-content" style:horizontal-pos="from-left" style:horizontal-rel="paragraph-content" fo:background-color="transparent" fo:padding="0mm" style:editable="false"/> + </style:default-style> + <style:style style:name="Frame" style:family="graphics"> + <style:properties text:anchor-type="paragraph" svg:x="0mm" svg:y="0mm" style:wrap="parallel" style:number-wrapped-paragraphs="no-limit" style:vertical-pos="top" style:vertical-rel="paragraph-content" style:horizontal-pos="center" style:horizontal-rel="paragraph-content" fo:padding="1.5mm" fo:border="0.02mm solid #000000"/> + </style:style> + <text:outline-style> + <text:outline-level-style text:level="1" style:num-format=""/> + <text:outline-level-style text:level="2" style:num-format=""/> + <text:outline-level-style text:level="3" style:num-format=""/> + <text:outline-level-style text:level="4" style:num-format=""/> + <text:outline-level-style text:level="5" style:num-format=""/> + <text:outline-level-style text:level="6" style:num-format=""/> + <text:outline-level-style text:level="7" style:num-format=""/> + <text:outline-level-style text:level="8" style:num-format=""/> + <text:outline-level-style text:level="9" style:num-format=""/> + <text:outline-level-style text:level="10" style:num-format=""/> + </text:outline-style> + <text:footnotes-configuration style:num-format="1" text:offset="0" text:footnotes-position="page" text:start-numbering-at="document"/> + <text:endnotes-configuration style:num-format="i" text:offset="0"/> + <text:bibliography-configuration text:prefix="[" text:suffix="]"/> + <text:linenumbering-configuration text:style-name="Line numbering" text:number-lines="false" text:offset="4.99mm" style:num-format="1" text:number-position="left" text:increment="5"/> + </office:styles> + <office:automatic-styles> + <style:style style:name="P1" style:family="paragraph" style:parent-style-name="Standard"> + <style:properties fo:font-style="normal" fo:font-weight="normal"/> + </style:style> + <style:style style:name="P2" style:family="paragraph" style:parent-style-name="Standard"> + <style:properties fo:line-height="200%" fo:margin-top="6mm" fo:margin-bottom="20mm"/> + </style:style> + <style:style style:name="T1" style:family="text"> + <style:properties fo:font-style="italic"/> + </style:style> + <style:style style:name="T2" style:family="text"> + <style:properties fo:font-style="normal"/> + </style:style> + <style:style style:name="T3" style:family="text"> + <style:properties fo:font-style="normal" fo:font-weight="bold"/> + </style:style> + <style:style style:name="T4" style:family="text"> + <style:properties fo:font-style="normal" fo:font-weight="normal"/> + </style:style> + <style:style style:name="T5" style:family="text"> + <style:properties style:text-underline="double" style:text-underline-color="#000000"/> + </style:style> + <style:style style:name="T6" style:family="text"> + <style:properties style:text-underline="single" style:text-underline-color="#000000"/> + </style:style> + <style:style style:name="T7" style:family="text" style:parent-style-name="Example"> + <style:properties fo:font-size="24pt"/> + </style:style> + <style:style style:name="T8" style:family="text" style:parent-style-name="Definition"> + <style:properties fo:font-size="24pt"/> + </style:style> + <style:page-master style:name="pm1"> + <style:properties fo:page-width="209.99mm" fo:page-height="296.99mm" style:num-format="1" style:print-orientation="portrait" fo:margin-top="25.4mm" fo:margin-bottom="25.4mm" fo:margin-left="31.75mm" fo:margin-right="31.75mm"/> + <style:header-style/> + <style:footer-style/> + </style:page-master> + </office:automatic-styles> + <office:master-styles> + <style:master-page style:name="Standard" style:page-master-name="pm1"/> + </office:master-styles> +</office:document> + + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/TextStyle.java b/xmerge/java/org/openoffice/xmerge/converter/xml/TextStyle.java new file mode 100644 index 000000000000..1652c12c6ac8 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/TextStyle.java @@ -0,0 +1,684 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +// DJP ToDo: need way of specifying fg/bg colors on ws->DOM + +package org.openoffice.xmerge.converter.xml; + +import java.awt.Color; +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.util.Debug; + +/** + * Represents a text <code>Style</code> in an OpenOffice document. + * + * @author David Proulx + */ +public class TextStyle extends Style implements Cloneable { + + final protected static int FIRST_ATTR = 0x01; + /** Indicates <i>bold</i> text. */ + final public static int BOLD = 0x01; + /** Indicates <i>italic</i> text. */ + final public static int ITALIC = 0x02; + /** Indicates <i>underlined</i> text. */ + final public static int UNDERLINE = 0x04; + /** Indicates <i>strike-through</i> in the text. */ + final public static int STRIKETHRU = 0x08; + /** Indicates <i>superscripted</i> text. */ + final public static int SUPERSCRIPT = 0x10; + /** Indicates <i>subscripted</i> text. */ + final public static int SUBSCRIPT = 0x20; + /** Indicates the last attribute. */ + final protected static int LAST_ATTR = 0x20; + + /** Values of text attributes. */ + protected int values = 0; + /** Bitwise mask of text attributes. */ + protected int mask = 0; + + /** Font size in points. */ + protected int sizeInPoints = 0; + /** Font name. */ + protected String fontName = null; + /** Font <code>Color</code>. */ + protected Color fontColor = null; + /** Background <code>Color</code>. */ + protected Color bgColor = null; + + /** + * Constructor for use when going from DOM to client device format. + * + * @param Node The <i>style:style</i> <code>Node</code> containing + * the <code>Style</code>. (This <code>Node</code> is + * assumed have a <i>family</i> attribute of <i>text</i>). + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public TextStyle(Node node, StyleCatalog sc) { + super(node, sc); + + // Run through the attributes of this node, saving + // the ones we're interested in. + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + handleAttribute(attr.getNodeName(), attr.getNodeValue()); + } + } + + // Look for children. Only ones we care about are "style:properties" + // nodes. If any are found, recursively traverse them, passing + // along the style element to add properties to. + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + for (int i = 0; i < len; i++) { + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:properties")) { + NamedNodeMap childAttrNodes = child.getAttributes(); + if (childAttrNodes != null) { + int nChildAttrNodes = childAttrNodes.getLength(); + for (int j = 0; j < nChildAttrNodes; j++) { + Node attr = childAttrNodes.item(j); + handleAttribute(attr.getNodeName(), + attr.getNodeValue()); + } + } + } + } + } + } + + + /** + * Constructor for use when going from client device format to DOM + * + * @param name Name of text <code>Style</code>. Can be null. + * @param family Family of text <code>Style</code> (usually + * <i>text</i>). Can be null. + * @param parent Name of parent text <code>Style</code>, or null + * for none. + * @param mask Bitwise mask of text attributes that this text + * <code>Style</code> will specify. Can be any + * combination of the following, or'ed together: + * {@link #BOLD}, {@link #ITALIC}, {@link #UNDERLINE}, + * {@link #STRIKETHRU}, {@link #SUPERSCRIPT}, + * {@link #SUBSCRIPT}. This parameter determines what + * attributes this <code>Style</code> will specify. + * When an attribute is specified in a + * <code>Style</code>, its value can be either + * <i>on</i> or <i>off</i>. The on/off value for + * each attribute is controlled by the + * <code>values</code> parameter. + * @param values Values of text attributes that this text + * <code>Style</code> will be setting. Any of the + * attributes ({@link #BOLD}, etc) listed for + * <code>mask</code> can be used for this. + * @param fontSize Font size in points. + * @param fontName Name of font. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public TextStyle(String name, String family, String parent, + int mask, int values, int fontSize, String fontName, StyleCatalog sc) { + super(name, family, parent, sc); + this.mask = mask; + this.values = values; + this.sizeInPoints = fontSize; + this.fontName = fontName; + } + + + /** + * Parse a color specification of the form <i>#rrggbb</i> + * + * @param value <code>Color</code> specification to parse. + * + * @returns The <code>Color</code> associated the value. + */ + private Color parseColorString(String value) { + // Assume color value is of form #rrggbb + String r = value.substring(1, 3); + String g = value.substring(3, 5); + String b = value.substring(5, 7); + int red = 0; + int green = 0; + int blue = 0; + try { + red = Integer.parseInt(r, 16); + green = Integer.parseInt(g, 16); + blue = Integer.parseInt(b, 16); + } catch (NumberFormatException e) { + Debug.log(Debug.ERROR, "Problem parsing a color string", e); + } + return new Color(red, green, blue); + } + + + /** + * Set an attribute. + * + * @param attr The attribute to set. + * @param value The attribute value to set. + */ + private void handleAttribute(String attr, String value) { + + if (attr.equals("fo:font-weight")) { + if (value.equals("bold")) turnAttributesOn(BOLD); + else if (value.equals("normal")) turnAttributesOff(BOLD); + } + + else if (attr.equals("fo:font-style")) { + if (value.equals("italic")) turnAttributesOn(ITALIC); + else if (value.equals("oblique")) turnAttributesOn(ITALIC); + else if (value.equals("normal")) turnAttributesOff(ITALIC); + } + + else if (attr.equals("style:text-underline")) { + if (value.equals("none")) + turnAttributesOff(UNDERLINE); + else + turnAttributesOn(UNDERLINE); + } + + else if (attr.equals("style:text-crossing-out")) { + if (value.equals("none")) + turnAttributesOff(STRIKETHRU); + else + turnAttributesOn(STRIKETHRU); + } + + else if (attr.equals("style:text-position")) { + if (value.startsWith("super ")) + turnAttributesOn(SUPERSCRIPT); + else if (value.startsWith("sub ")) + turnAttributesOn(SUBSCRIPT); + else if (value.startsWith("0% ")) + turnAttributesOff(SUPERSCRIPT | SUBSCRIPT); + else { + String firstPart = value.substring(0, value.indexOf(" ")); + if (firstPart.endsWith("%")) { + firstPart = firstPart.substring(0, value.indexOf("%")); + int amount; + try { + amount = Integer.parseInt(firstPart); + } catch (NumberFormatException e) { + amount = 0; + Debug.log(Debug.ERROR, "Problem with style:text-position tag", e); + } + if (amount < 0) turnAttributesOn(SUBSCRIPT); + else if (amount > 0) turnAttributesOn(SUPERSCRIPT); + } + } + } + + else if (attr.equals("fo:font-size")) { + if (value.endsWith("pt")) { + String num = value.substring(0, value.length() - 2); + sizeInPoints = Integer.parseInt(num); + } + } + + else if (attr.equals("style:font-name")) + fontName = value; + + else if (attr.equals("fo:color")) + fontColor = parseColorString(value); + + else if (attr.equals("style:text-background-color")) + bgColor = parseColorString(value); + + else if (isIgnored(attr)) {} + + else { + Debug.log(Debug.INFO, "TextStyle Unhandled: " + attr + "=" + value); + } + } + + + /** + * Return true if text <code>attribute</code> is set in this + * <code>Style</code>. An attribute that is set may have a + * value of <i>on</i> or <i>off</i>. + * + * @param attribute The attribute to check ({@link #BOLD}, + * {@link #ITALIC}, etc.). + * + * @return true if text <code>attribute</code> is set in this + * <code>Style</code>, false otherwise. + */ + public boolean isSet(int attribute) { + return (!((mask & attribute) == 0)); + } + + + /** + * Return true if the <code>attribute</code> is set to <i>on</i> + * + * @param attribute Attribute to check ({@link #BOLD}, + * {@link #ITALIC}, etc.) + * + * @return true if <code>attribute</code> is set to <i>on</i>, + * otherwise false. + */ + public boolean getAttribute(int attribute) { + if ((mask & attribute) == 0) + return false; + return (!((values & attribute) == 0)); + } + + + /** + * Return the font size for this <code>Style</code>. + * + * @return The font size in points + */ + public int getFontSize() { + return sizeInPoints; + } + + + /** + * Return the name of the font for this <code>Style</code>. + * + * @return Name of font, or null if no font is specified by + * this <code>Style</code>. + */ + public String getFontName() { + return fontName; + } + + + /** + * Return the font <code>Color</code> for this <code>Style</code>. + * Can be null if none was specified. + * + * @return <code>Color</code> value for this <code>Style</code>. + * Can be null. + */ + public Color getFontColor() { + return fontColor; + } + + + /** + * Return the background <code>Color</code> for this + * <code>Style</code>. Can be null if none was specified. + * + * @return Background <code>Color</code> value for this + * <code>Style</code>. Can be null. + */ + public Color getBackgroundColor() { + return bgColor; + } + + + /** + * Set the font and/or background <code>Color</code> for this + * <code>Style</code>. + * + * @param fontColor The font <code>Color</code> to set. + * @param backgroundColor The background <code>Color</code> to set. + */ + public void setColors(Color fontColor, Color backgroundColor) { + if (fontColor != null) + this.fontColor = fontColor; + if (backgroundColor != null) + this.bgColor = backgroundColor; + } + + + /** + * Return a <code>Style</code> object corresponding to this one, + * but with all of the inherited information from parent + * <code>Style</code> objects filled in. The object returned will + * be a new object, not a reference to this object, even if it does + * not need any information added. + * + * @return The <code>StyleCatalog</code> in which to look up + * ancestors. + */ + public Style getResolved() { + // Create a new object to return, which is a clone of this one. + TextStyle resolved = null; + try { + resolved = (TextStyle)this.clone(); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Can't clone", e); + } + + // Look up the parentStyle. (If there is no style catalog + // specified, we can't do any lookups.) + TextStyle parentStyle = null; + if (sc != null) { + if (parent != null) { + parentStyle = (TextStyle)sc.lookup(parent, family, null, + this.getClass()); + if (parentStyle == null) + Debug.log(Debug.ERROR, "parent style lookup of " + + parent + " failed!"); + else + parentStyle = (TextStyle)parentStyle.getResolved(); + + } else if (!name.equals("DEFAULT_STYLE")) { + parentStyle = (TextStyle)sc.lookup("DEFAULT_STYLE", null, + null, this.getClass()); + } + } + + // If we found a parent, for any attributes which we don't have + // set, try to get the values from the parent. + if (parentStyle != null) { + parentStyle = (TextStyle)parentStyle.getResolved(); + + if ((sizeInPoints == 0) && (parentStyle.sizeInPoints != 0)) + resolved.sizeInPoints = parentStyle.sizeInPoints; + if ((fontName == null) && (parentStyle.fontName != null)) + resolved.fontName = parentStyle.fontName; + if ((fontColor == null) && (parentStyle.fontColor != null)) + resolved.fontColor = parentStyle.fontColor; + if ((bgColor == null) && (parentStyle.bgColor != null)) + resolved.bgColor = parentStyle.bgColor; + for (int m = BOLD; m <= SUBSCRIPT; m = m << 1) { + if (((mask & m) == 0) && ((parentStyle.mask & m) != 0)) { + resolved.mask |= m; + resolved.values |= (parentStyle.mask & m); + } + } + + } + return resolved; + } + + + /** + * Set one or more text attributes to <i>on</i>. + * + * @param flags Flag values to set <i>on</i>. + */ + private void turnAttributesOn(int flags) { + mask |= flags; + values |= flags; + } + + + /** + * Set one or more text attributes to <i>off</i>. + * + * @param flags The flag values to set <i>off</i>. + */ + private void turnAttributesOff(int flags) { + mask |= flags; + values &= ~flags; + } + + + /** + * Private function to return the value as an element in + * a Comma Separated Value (CSV) format. + * + * @param The value to format. + * + * @return The formatted value. + */ + private static String toCSV(String value) { + if (value != null) + return "\"" + value + "\","; + else + return "\"\","; + } + + + /** + * Private function to return the value as a last element in + * a Comma Separated Value (CSV) format. + * + * @param value The value to format. + * + * @return The formatted value. + */ + private static String toLastCSV(String value) { + if (value != null) + return "\"" + value + "\""; + else + return "\"\""; + } + + + /** + * Print a Comma Separated Value (CSV) header line for the + * spreadsheet dump. + */ + public static void dumpHdr() { + System.out.println(toCSV("Name") + toCSV("Family") + toCSV("parent") + + toCSV("Font") + toCSV("Size") + + toCSV("Bold") + toCSV("Italic") + toCSV("Underline") + + toCSV("Strikethru") + toCSV("Superscript") + toLastCSV("Subscript")); + } + + + /** + * Dump this <code>Style</code> as a Comma Separated Value (CSV) line. + */ + public void dumpCSV() { + String attributes = ""; + for (int bitVal = 0x01; bitVal <= 0x20; bitVal = bitVal << 1) { + if ((bitVal & mask) != 0) { + attributes += toCSV(((bitVal & values) != 0) ? "yes" : "no"); + } else attributes += toCSV(null); // unspecified + } + System.out.println(toCSV(name) + toCSV(family) + toCSV(parent) + + toCSV(fontName) + toCSV("" + sizeInPoints) + attributes + toLastCSV(null)); + } + + + /** + * Create a new <code>Node</code> in the <code>Document</code>, and + * write this <code>Style</code> to it. + * + * @param parentDoc Parent <code>Document</code> of the + * <code>Node</code> to create. + * @param name Name to use for the new <code>Node</code> (e.g. + * <i>style:style</i>) + * + * @return Created <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + Element node = parentDoc.createElement(name); + writeAttributes(node); + return node; + } + + + /** + * Return true if <code>style</code> specifies as much or less + * than this <code>Style</code>, and nothing it specifies + * contradicts this <code>Style</code>. + * + * @param style The <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Style style) { + if (style.getClass() != this.getClass()) + return false; + TextStyle tStyle = (TextStyle)style; + + if (tStyle.values != values) + return false; + + if (tStyle.sizeInPoints != 0) { + if (sizeInPoints != tStyle.sizeInPoints) + return false; + } + + if (tStyle.fontName != null) { + if (fontName == null) + return false; + if (!fontName.equals(tStyle.fontName)) + return false; + } + + if (tStyle.fontColor != null) { + if (fontColor == null) + return false; + if (!fontColor.equals(tStyle.fontColor)) + return false; + } + + if (tStyle.bgColor != null) { + if (bgColor == null) + return false; + if (!bgColor.equals(tStyle.bgColor)) + return false; + } + + return true; + } + + + /** + * Write this <code>Style</code> object's attributes to a + * <code>Node</code> in the <code>Document</code>. + * + * @param node The <code>Node</code> to add <code>Style</code> + * attributes. + */ + public void writeAttributes(Element node) { + + if ((mask & BOLD) != 0) + if ((values & BOLD) != 0) + node.setAttribute("fo:font-weight", "bold"); + + if ((mask & ITALIC) != 0) + if ((values & ITALIC) != 0) + node.setAttribute("fo:font-style", "italic"); + + if ((mask & UNDERLINE) != 0) + if ((values & UNDERLINE) != 0) + node.setAttribute("style:text-underline", "single"); + + if ((mask & STRIKETHRU) != 0) + if ((values & STRIKETHRU) != 0) + node.setAttribute("style:text-crossing-out", "single-line"); + + if ((mask & SUPERSCRIPT) != 0) + if ((values & SUPERSCRIPT) != 0) + node.setAttribute("style:text-position", "super 58%"); + + if ((mask & SUBSCRIPT) != 0) + if ((values & SUBSCRIPT) != 0) + node.setAttribute("style:text-position", "sub 58%"); + + if (sizeInPoints != 0) { + Integer fs = new Integer(sizeInPoints); + node.setAttribute("fo:font-size", fs.toString() + "pt"); + } + + if (fontName != null) + node.setAttribute("style:font-name", fontName); + + if (fontColor != null) + node.setAttribute("fo:color", buildColorString(fontColor)); + + if (bgColor != null) + node.setAttribute("style:text-background-color", + buildColorString(bgColor)); + } + + + /** + * Given a <code>Color</code>, return a string of the form + * <i>#rrggbb</i>. + * + * @param c The <code>Color</code> value. + * + * @return The <code>Color</code> value in the form <i>#rrggbb</i>. + */ + private String buildColorString(Color c) { + int v[] = new int[3]; + v[0] = c.getRed(); + v[1] = c.getGreen(); + v[2] = c.getBlue(); + String colorString = new String("#"); + for (int i = 0; i <= 2; i++) { + String xx = Integer.toHexString(v[i]); + if (xx.length() < 2) + xx = "0" + xx; + colorString += xx; + } + return colorString; + } + + + private static String[] ignored = { + "style:text-autospace", "style:text-underline-color", + "fo:margin-left", "fo:margin-right", "fo:text-indent", + "fo:margin-top", "fo:margin-bottom", "text:line-number", + "text:number-lines", "style:country-asian", + "style:font-size-asian", "style:font-name-complex", + "style:language-complex", "style:country-complex", + "style:font-size-complex", "style:punctuation-wrap", + "fo:language", "fo:country", + "style:font-name-asian", "style:language-asian", + "style:line-break", "fo:keep-with-next" + }; + + + /* + * This code checks whether an attribute is one that we + * intentionally ignore. + * + * @param attribute The attribute to check. + * + * @return true if <code>attribute</code> can be ignored, + * otherwise false. + */ + private boolean isIgnored(String attribute) { + for (int i = 0; i < ignored.length; i++) { + if (ignored[i].equals(attribute)) + return true; + } + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/build.xml new file mode 100644 index 000000000000..25093212ca10 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/build.xml @@ -0,0 +1,137 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxc_xml" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxc_xml"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/EmbeddedObject.java"/> + <include name="${package}/EmbeddedBinaryObject.java"/> + <include name="${package}/EmbeddedXMLObject.java"/> + <include name="${package}/OfficeConstants.java"/> + <include name="${package}/OfficeZip.java"/> + <include name="${package}/OfficeDocument.java"/> + <include name="${package}/OfficeDocumentException.java"/> + <include name="${package}/ParaStyle.java"/> + <include name="${package}/StyleCatalog.java"/> + <include name="${package}/Style.java"/> + <include name="${package}/TextStyle.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/makefile.mk new file mode 100644 index 000000000000..89bf15133228 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxc_xml +PRJ=../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/package.html new file mode 100644 index 000000000000..392e85018dca --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/package.html @@ -0,0 +1,39 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.util package</title> +</head> + +<body bgcolor="white"> + +<p><code>Document</code> and <code>PluginFactory</code> implementations +for XML based formats. + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/BookSettings.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/BookSettings.java new file mode 100644 index 000000000000..0155224a5740 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/BookSettings.java @@ -0,0 +1,229 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.util.Vector; +import java.util.Enumeration; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import java.awt.Point; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.XmlUtil; + +/** + * This is a class representing the different attributes for a worksheet + * contained in settings.xml. + * + * @author Martin Maher + */ +public class BookSettings implements OfficeConstants { + + /** A w3c <code>Document</code>. */ + private org.w3c.dom.Document settings = null; + + private boolean hasColumnRowHeaders = true; + private String activeSheet = new String(); + private Vector worksheetSettings = new Vector(); + + /** + * Default Constructor for a <code>BookSettings</code> + * + * @param dimension if it's a row the height, a column the width + * @param repeated + */ + public BookSettings(Node root) { + readNode(root); + } + + /** + * Default Constructor for a <code>BookSettings</code> + * + * @param worksheetSettings if it's a row the height, a column the width + */ + public BookSettings(Vector worksheetSettings) { + this.worksheetSettings = worksheetSettings; + } + + /** + * + */ + public void setColumnRowHeaders(boolean hasColumnRowHeaders) { + this.hasColumnRowHeaders = hasColumnRowHeaders; + } + + /** + * + */ + public boolean hasColumnRowHeaders() { + return hasColumnRowHeaders; + } + + /** + * Gets the <code>Vector</code> of <code>SheetSettings</code> + * + * @return <code>Vector</code> of <code>SheetSettings</code> + */ + public Vector getSheetSettings() { + return worksheetSettings; + } + + /** + * Gets the active sheet name + * + * @return the active sheet name + */ + public String getActiveSheet() { + + return activeSheet; + } + + /** + * Sets the active sheet name + * + * @param activeSheet the active sheet name + */ + public void setActiveSheet(String activeSheet) { + + this.activeSheet = activeSheet; + } + + + /** + * Adds an XML entry for a particular setting + * + * @param root the root node at which to add the xml entry + * @param attriute the name of the attribute to add + * @param type the attribute type (int, short etc) + * @param value the value of the attribute + */ + private void addConfigItem(Node root, String attribute, String type, String value) { + + Element configItem = settings.createElement(TAG_CONFIG_ITEM); + configItem.setAttribute(ATTRIBUTE_CONFIG_NAME, attribute); + configItem.setAttribute(ATTRIBUTE_CONFIG_TYPE, type); + + configItem.appendChild(settings.createTextNode(value)); + + root.appendChild(configItem); + } + + /** + * Writes out a settings.xml entry for this BookSettings object + * + * @param settings a <code>Document</code> object representing the settings.xml + * @param root the root xml node to add to + */ + public void writeNode(org.w3c.dom.Document settings, Node root) { + + this.settings = settings; + Element configItemMapNamed = (Element) settings.createElement(TAG_CONFIG_ITEM_MAP_NAMED); + configItemMapNamed.setAttribute(ATTRIBUTE_CONFIG_NAME, "Tables"); + for(Enumeration e = worksheetSettings.elements();e.hasMoreElements();) { + SheetSettings s = (SheetSettings) e.nextElement(); + s.writeNode(settings, configItemMapNamed); + } + addConfigItem(root, "ActiveTable", "string", activeSheet); + String booleanValue = Boolean.toString(hasColumnRowHeaders); + addConfigItem(root, "HasColumnRowHeaders", "boolean", booleanValue); + root.appendChild(configItemMapNamed); + } + + /** + * Sets a variable based on a String value read from XML + * + * @param name xml name of the attribute to set + * @param value String value fo the attribute + */ + public void addAttribute(String name, String value) { + + if(name.equals("ActiveTable")) { + activeSheet = value; + } else if(name.equals("HasColumnRowHeaders")) { + Boolean b = Boolean.valueOf(value); + hasColumnRowHeaders = b.booleanValue(); + } + } + + /** + * Reads document settings from xml and inits SheetSettings variables + * + * @param root XML Node to read from + */ + public void readNode(Node root) { + + if (root.hasChildNodes()) { + + NodeList nodeList = root.getChildNodes(); + int len = nodeList.getLength(); + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_CONFIG_ITEM)) { + + NamedNodeMap cellAtt = child.getAttributes(); + + Node configNameNode = + cellAtt.getNamedItem(ATTRIBUTE_CONFIG_NAME); + + String name = configNameNode.getNodeValue(); + NodeList nodeList2 = child.getChildNodes(); + int len2 = nodeList2.getLength(); + String s = ""; + for (int j = 0; j < len2; j++) { + Node child2 = nodeList2.item(j); + if (child2.getNodeType() == Node.TEXT_NODE) { + s = child2.getNodeValue(); + } + } + addAttribute(name, s); + + } else if (nodeName.equals(TAG_CONFIG_ITEM_MAP_NAMED)) { + + readNode(child); + + } else if (nodeName.equals(TAG_CONFIG_ITEM_MAP_ENTRY)) { + + SheetSettings s = new SheetSettings(child); + worksheetSettings.add(s); + + } else { + + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/CellStyle.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/CellStyle.java new file mode 100644 index 000000000000..4882d7e09d80 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/CellStyle.java @@ -0,0 +1,515 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.awt.Color; +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.Style; +import org.openoffice.xmerge.converter.xml.StyleCatalog; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.util.Debug; + +/** + * Represents a text <code>Style</code> in an OpenOffice document. + * + * @author Martin Maher + */ +public class CellStyle extends Style implements Cloneable { + + private Format fmt = new Format(); + + /** + * Constructor for use when going from DOM to client device format. + * + * @param Node The <i>style:style</i> <code>Node</code> containing + * the <code>Style</code>. (This <code>Node</code> is + * assumed have a <i>family</i> attribute of <i>text</i>). + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public CellStyle(Node node, StyleCatalog sc) { + super(node, sc); + + // Run through the attributes of this node, saving + // the ones we're interested in. + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + handleAttribute(attr.getNodeName(), attr.getNodeValue()); + } + } + + // Look for children. Only ones we care about are "style:properties" + // nodes. If any are found, recursively traverse them, passing + // along the style element to add properties to. + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + for (int i = 0; i < len; i++) { + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:properties")) { + NamedNodeMap childAttrNodes = child.getAttributes(); + if (childAttrNodes != null) { + int nChildAttrNodes = childAttrNodes.getLength(); + for (int j = 0; j < nChildAttrNodes; j++) { + Node attr = childAttrNodes.item(j); + handleAttribute(attr.getNodeName(), + attr.getNodeValue()); + } + } + } + } + } + } + + + /** + * Constructor for use when going from client device format to DOM + * + * @param name Name of cell <code>Style</code>. Can be null. + * @param family Family of text <code>Style</code> (usually + * <i>text</i>). Can be null. + * @param parent Name of parent text <code>Style</code>, or null + * for none. + * @param fmt size in points. + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public CellStyle(String name, String family, String parent,Format fmt, StyleCatalog sc) { + super(name, family, parent, sc); + this.fmt = fmt; + } + + /** + * Returns the <code>Format</code> object for this particular style + * + * @return the <code>Format</code> object + */ + public Format getFormat() { + return fmt; + } + + /** + * Parse a color specification of the form <i>#rrggbb</i> + * + * @param value <code>Color</code> specification to parse. + * + * @return The <code>Color</code> associated the value. + */ + private Color parseColorString(String value) { + // Assume color value is of form #rrggbb + String r = value.substring(1, 3); + String g = value.substring(3, 5); + String b = value.substring(5, 7); + int red = 0; + int green = 0; + int blue = 0; + try { + red = Integer.parseInt(r, 16); + green = Integer.parseInt(g, 16); + blue = Integer.parseInt(b, 16); + } catch (NumberFormatException e) { + Debug.log(Debug.ERROR, "Problem parsing a color string", e); + } + return new Color(red, green, blue, 0); + } + + + /** + * Set an attribute. + * + * @param attr The attribute to set. + * @param value The attribute value to set. + */ + private void handleAttribute(String attr, String value) { + + if (attr.equals("fo:font-weight")) { + fmt.setAttribute(Format.BOLD, value.equals("bold")); + } + + else if (attr.equals("fo:font-style")) { + if (value.equals("italic") || value.equals("oblique")) + fmt.setAttribute(Format.ITALIC, true); + else if (value.equals("normal")) + fmt.setAttribute(Format.ITALIC, false); + } + + else if (attr.equals("style:text-underline")) { + fmt.setAttribute(Format.UNDERLINE, !value.equals("none")); + } + + else if (attr.equals("style:text-crossing-out")) { + fmt.setAttribute(Format.STRIKETHRU, !value.equals("none")); + } + + else if (attr.equals("style:text-position")) { + if (value.startsWith("super ")) + fmt.setAttribute(Format.SUPERSCRIPT, true); + else if (value.startsWith("sub ")) + fmt.setAttribute(Format.SUBSCRIPT, true); + else if (value.startsWith("0% ")) + fmt.setAttribute(Format.SUPERSCRIPT | Format.SUBSCRIPT, false); + else { + String firstPart = value.substring(0, value.indexOf(" ")); + if (firstPart.endsWith("%")) { + firstPart = firstPart.substring(0, value.indexOf("%")); + int amount; + try { + amount = Integer.parseInt(firstPart); + } catch (NumberFormatException e) { + amount = 0; + Debug.log(Debug.ERROR, "Problem with style:text-position tag", e); + } + if (amount < 0) fmt.setAttribute(Format.SUBSCRIPT, true); + else if (amount > 0) fmt.setAttribute(Format.SUPERSCRIPT, false); + } + } + } + + else if (attr.equals("fo:font-size")) { + if (value.endsWith("pt")) { + String num = value.substring(0, value.length() - 2); + fmt.setFontSize(Integer.parseInt(num)); + } + } + + else if (attr.equals("style:font-name")) + fmt.setFontName(value); + + else if (attr.equals("fo:color")) + fmt.setForeground(parseColorString(value)); + + else if (attr.equals("fo:background-color")) + fmt.setBackground(parseColorString(value)); + + else if (attr.equals("fo:text-align")) { + if(value.equals("center")) { + fmt.setAlign(Format.CENTER_ALIGN); + } else if(value.equals("end")) { + fmt.setAlign(Format.RIGHT_ALIGN); + } else if(value.equals("start")) { + fmt.setAlign(Format.LEFT_ALIGN); + } + } + + else if (attr.equals("fo:vertical-align")) { + if(value.equals("top")) { + fmt.setVertAlign(Format.TOP_ALIGN); + } else if(value.equals("middle")) { + fmt.setVertAlign(Format.MIDDLE_ALIGN); + } else if(value.equals("bottom")) { + fmt.setVertAlign(Format.BOTTOM_ALIGN); + } + } + + else if (attr.equals("fo:border")) { + fmt.setAttribute(Format.TOP_BORDER, !value.equals("none")); + fmt.setAttribute(Format.BOTTOM_BORDER, !value.equals("none")); + fmt.setAttribute(Format.LEFT_BORDER, !value.equals("none")); + fmt.setAttribute(Format.RIGHT_BORDER, !value.equals("none")); + } + else if (attr.equals("fo:border-top")) { + fmt.setAttribute(Format.TOP_BORDER, !value.equals("none")); + } + else if (attr.equals("fo:border-bottom")) { + fmt.setAttribute(Format.BOTTOM_BORDER, !value.equals("none")); + } + else if (attr.equals("fo:border-left")) { + fmt.setAttribute(Format.LEFT_BORDER, !value.equals("none")); + } + else if (attr.equals("fo:border-right")) { + fmt.setAttribute(Format.RIGHT_BORDER, !value.equals("none")); + } + else if (attr.equals("fo:wrap-option")) { + fmt.setAttribute(Format.WORD_WRAP, value.equals("wrap")); + } + + else if (isIgnored(attr)) {} + + else { + Debug.log(Debug.INFO, "CellStyle Unhandled: " + attr + "=" + value); + } + } + + + /** + * Return a <code>Style</code> object corresponding to this one, + * but with all of the inherited information from parent + * <code>Style</code> objects filled in. The object returned will + * be a new object, not a reference to this object, even if it does + * not need any information added. + * + * @return The <code>StyleCatalog</code> in which to look up + * ancestors. + */ + public Style getResolved() { + // Create a new object to return, which is a clone of this one. + CellStyle resolved = null; + try { + resolved = (CellStyle)this.clone(); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Can't clone", e); + } + + // Look up the parentStyle. (If there is no style catalog + // specified, we can't do any lookups.) + CellStyle parentStyle = null; + if (sc != null) { + if (parent != null) { + parentStyle = (CellStyle)sc.lookup(parent, family, null, + this.getClass()); + if (parentStyle == null) + Debug.log(Debug.ERROR, "parent style lookup of " + + parent + " failed!"); + else + parentStyle = (CellStyle)parentStyle.getResolved(); + + } else if (!name.equals("DEFAULT_STYLE")) { + parentStyle = (CellStyle)sc.lookup("DEFAULT_STYLE", null, + null, this.getClass()); + } + } + + // If we found a parent, for any attributes which we don't have + // set, try to get the values from the parent. + if (parentStyle != null) { + parentStyle = (CellStyle)parentStyle.getResolved(); + Format parentFormat = parentStyle.getFormat(); + Format resolvedFormat = resolved.getFormat(); + + if ((fmt.getAlign() == Format.LEFT_ALIGN) && (parentFormat.getAlign() != Format.LEFT_ALIGN)) + resolvedFormat.setAlign(parentFormat.getAlign()); + if ((fmt.getVertAlign() == Format.BOTTOM_ALIGN) && (parentFormat.getVertAlign() != Format.BOTTOM_ALIGN)) + resolvedFormat.setVertAlign(parentFormat.getVertAlign()); + if ((fmt.getFontSize() == 0) && (parentFormat.getFontSize() != 0)) + resolvedFormat.setFontSize(parentFormat.getFontSize()); + if ((fmt.getFontName() == null) && (parentFormat.getFontName() != null)) + resolvedFormat.setFontName(parentFormat.getFontName()); + if ((fmt.getForeground() == null) && (parentFormat.getForeground() != null)) + resolvedFormat.setForeground(parentFormat.getForeground()); + if ((fmt.getBackground() == null) && (parentFormat.getBackground() != null)) + resolvedFormat.setBackground(parentFormat.getBackground()); + for (int m = Format.BOLD; m <= Format.SUBSCRIPT; m = m << 1) { + if ((fmt.getAttribute(m)) && (parentFormat.getAttribute(m))) { + resolvedFormat.setAttribute(m, parentFormat.getAttribute(m)); + } + } + + } + return resolved; + } + + + /** + * Create a new <code>Node</code> in the <code>Document</code>, and + * write this <code>Style</code> to it. + * + * @param parentDoc Parent <code>Document</code> of the + * <code>Node</code> to create. + * @param name Name to use for the new <code>Node</code> (e.g. + * <i>style:style</i>) + * + * @return Created <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + Element node = parentDoc.createElement(name); + writeAttributes(node); + return node; + } + + + /** + * Return true if <code>style</code> specifies as much or less + * than this <code>Style</code>, and nothing it specifies + * contradicts this <code>Style</code>. + * + * @param style The <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Style style) { + if (style.getClass() != this.getClass()) + return false; + CellStyle tStyle = (CellStyle)style; + + Format rhs = tStyle.getFormat(); + + if(!fmt.isSubset(rhs)) + return false; + + return true; + } + + + /** + * Write this <code>Style</code> object's attributes to a + * <code>Node</code> in the <code>Document</code>. + * + * @param node The <code>Node</code> to add <code>Style</code> + * attributes. + */ + public void writeAttributes(Element node) { + + if (fmt.getAlign()==Format.RIGHT_ALIGN) + node.setAttribute("fo:text-align", "end"); + + if (fmt.getAlign()==Format.LEFT_ALIGN) + node.setAttribute("fo:text-align", "start"); + + if (fmt.getAlign()==Format.CENTER_ALIGN) + node.setAttribute("fo:text-align", "center"); + + if (fmt.getVertAlign()==Format.TOP_ALIGN) + node.setAttribute("fo:vertical-align", "top"); + + if (fmt.getVertAlign()==Format.MIDDLE_ALIGN) + node.setAttribute("fo:vertical-align", "middle"); + + if (fmt.getVertAlign()==Format.BOTTOM_ALIGN) + node.setAttribute("fo:vertical-align", "bottom"); + + if (fmt.getAttribute(Format.BOLD)) + node.setAttribute("fo:font-weight", "bold"); + + if (fmt.getAttribute(Format.ITALIC)) + node.setAttribute("fo:font-style", "italic"); + + if (fmt.getAttribute(Format.UNDERLINE)) + node.setAttribute("style:text-underline", "single"); + + if (fmt.getAttribute(Format.STRIKETHRU)) + node.setAttribute("style:text-crossing-out", "single-line"); + + if (fmt.getAttribute(Format.SUPERSCRIPT)) + node.setAttribute("style:text-position", "super 58%"); + + if (fmt.getAttribute(Format.SUBSCRIPT)) + node.setAttribute("style:text-position", "sub 58%"); + + if (fmt.getFontSize() != 0) { + Integer fs = new Integer(fmt.getFontSize()); + node.setAttribute("fo:font-size", fs.toString() + "pt"); + } + + if (fmt.getFontName() != null) + node.setAttribute("style:font-name", fmt.getFontName()); + + if (fmt.getForeground() != null) + node.setAttribute("fo:color", buildColorString(fmt.getForeground())); + + if (fmt.getBackground() != null) + node.setAttribute("fo:background-color", + buildColorString(fmt.getBackground())); + + if (fmt.getAttribute(Format.TOP_BORDER)) + node.setAttribute("fo:border-top", "0.0008inch solid #000000"); + + if (fmt.getAttribute(Format.BOTTOM_BORDER)) + node.setAttribute("fo:border-bottom", "0.0008inch solid #000000"); + + if (fmt.getAttribute(Format.RIGHT_BORDER)) + node.setAttribute("fo:border-right", "0.0008inch solid #000000"); + + if (fmt.getAttribute(Format.LEFT_BORDER)) + node.setAttribute("fo:border-left", "0.0008inch solid #000000"); + + if (fmt.getAttribute(Format.WORD_WRAP)) + node.setAttribute("fo:wrap-option", "wrap"); + + } + + + /** + * Given a <code>Color</code>, return a string of the form + * <i>#rrggbb</i>. + * + * @param c The <code>Color</code> value. + * + * @return The <code>Color</code> value in the form <i>#rrggbb</i>. + */ + private String buildColorString(Color c) { + int v[] = new int[3]; + v[0] = c.getRed(); + v[1] = c.getGreen(); + v[2] = c.getBlue(); + String colorString = new String("#"); + for (int i = 0; i <= 2; i++) { + String xx = Integer.toHexString(v[i]); + if (xx.length() < 2) + xx = "0" + xx; + colorString += xx; + } + return colorString; + } + + + private static String[] ignored = { + "style:text-autospace", "style:text-underline-color", + "fo:margin-left", "fo:margin-right", "fo:text-indent", + "fo:margin-top", "fo:margin-bottom", "text:line-number", + "text:number-lines", "style:country-asian", + "style:font-size-asian", "style:font-name-complex", + "style:language-complex", "style:country-complex", + "style:font-size-complex", "style:punctuation-wrap", + "fo:language", "fo:country", + "style:font-name-asian", "style:language-asian", + "style:line-break", "fo:keep-with-next" + }; + + + /* + * This code checks whether an attribute is one that we + * intentionally ignore. + * + * @param attribute The attribute to check. + * + * @return true if <code>attribute</code> can be ignored, + * otherwise false. + */ + private boolean isIgnored(String attribute) { + for (int i = 0; i < ignored.length; i++) { + if (ignored[i].equals(attribute)) + return true; + } + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnRowInfo.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnRowInfo.java new file mode 100644 index 000000000000..c8511ed81ef3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnRowInfo.java @@ -0,0 +1,195 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +/** + * This is a class to define a table-column structure. This can then be + * used by plugins to write or read their own column types. + * + * @author Martin Maher + */ +public class ColumnRowInfo { + + final public static int COLUMN = 0x01; + final public static int ROW = 0x02; + + final private static int DEFAULTROWSIZE_MIN = 250; + final private static int DEFAULTROWSIZE_MAX = 260; + + private int type; + private int dimension = 0; + private int repeated = 1; + private boolean userDefined = true; + private Format fmt = new Format(); + + /** + * Constructor for a <code>ColumnRowInfo</code> + * + * @param dimension if it's a row the height, a column the width + * @param repeated + */ + public ColumnRowInfo(int type) { + + this.type = type; + } + + /** + * Constructor for a <code>ColumnRowInfo</code> + * + * @param dimension if it's a row the height, a column the width + * @param repeated how many times it is repeated + * @param type whether Row or column record + */ + public ColumnRowInfo(int dimension, int repeated, int type) { + + this.dimension = dimension; + this.repeated = repeated; + this.type = type; + } + + /** + * Constructor that includes userDefined field + * + * @param userDefined whether the record is manually set + */ + public ColumnRowInfo(int dimension, int repeated, int type, boolean userDefined) { + + this(dimension, repeated, type); + this.userDefined = userDefined; + } + + /** + * sets the definition + * + * @param newDefinition sets the definition + */ + public void setFormat(Format fmt) { + + this.fmt = fmt; + } + + /** + * returns Name of the definition + * + * @return the name which identifies the definition + */ + public Format getFormat() { + + return fmt; + } + + /** + * returns Name of the definition + * + * @return the name which identifies the definition + */ + public int getSize() { + + return dimension; + } + + /** + * sets the definition + * + * @param newDefinition sets the definition + */ + public void setSize(int dimension) { + + this.dimension = dimension; + } + /** + * Returns the definition itself + * + * @return the definition + */ + public int getRepeated() { + + return repeated; + } + + /** + * Returns the base Cell address + * + * @return the base cell address + */ + public void setRepeated(int repeated) { + + this.repeated = repeated; + } + + /** + * Returns the definition itself + * + * @return the definition + */ + public boolean isRow() { + + if(type==ROW) + return true; + else + return false; + } + + /** + * Returns the base Cell address + * + * @return the base cell address + */ + public boolean isColumn() { + + if(type==COLUMN) + return true; + else + return false; + } + + /** + * Test if the row height as been set manually + * + * @return true if user defined otherwise false + */ + public boolean isUserDefined() { + + return userDefined; + } + + /** + * Test if the row height is default + * + * @return true if default otherwise false + */ + public boolean isDefaultSize() { + + if( type==ROW && + dimension>DEFAULTROWSIZE_MIN && + dimension<DEFAULTROWSIZE_MAX) + return true; + else + return false; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnStyle.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnStyle.java new file mode 100644 index 000000000000..bc730d6b880b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/ColumnStyle.java @@ -0,0 +1,306 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.awt.Color; +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.Style; +import org.openoffice.xmerge.converter.xml.StyleCatalog; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.TwipsConverter; + +/** + * Represents a text <code>Style</code> in an OpenOffice document. + * + * @author Martin Maher + */ +public class ColumnStyle extends Style implements Cloneable { + + private int colWidth = 0; + /** + * Constructor for use when going from DOM to client device format. + * + * @param Node The <i>style:style</i> <code>Node</code> containing + * the <code>Style</code>. (This <code>Node</code> is + * assumed have a <i>family</i> attribute of <i>text</i>). + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public ColumnStyle(Node node, StyleCatalog sc) { + super(node, sc); + + // Run through the attributes of this node, saving + // the ones we're interested in. + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + handleAttribute(attr.getNodeName(), attr.getNodeValue()); + } + } + + // Look for children. Only ones we care about are "style:properties" + // nodes. If any are found, recursively traverse them, passing + // along the style element to add properties to. + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + for (int i = 0; i < len; i++) { + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:properties")) { + NamedNodeMap childAttrNodes = child.getAttributes(); + if (childAttrNodes != null) { + int nChildAttrNodes = childAttrNodes.getLength(); + for (int j = 0; j < nChildAttrNodes; j++) { + Node attr = childAttrNodes.item(j); + handleAttribute(attr.getNodeName(), + attr.getNodeValue()); + } + } + } + } + } + } + + + /** + * Constructor for use when going from client device format to DOM + * + * @param name Name of text <code>Style</code>. Can be null. + * @param family Family of text <code>Style</code> (usually + * <i>text</i>). Can be null. + * @param parent Name of parent text <code>Style</code>, or null + * for none. + * @param mask the width of this column + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public ColumnStyle(String name, String family, String parent,int colWidth, StyleCatalog sc) { + super(name, family, parent, sc); + this.colWidth = colWidth; + } + + /** + * Returns the width of this column + * + * @return the <code>Format</code> object + */ + public int getColWidth() { + return colWidth; + } + + /** + * Sets the width of this column + * + * @return the <code>Format</code> object + */ + public void setColWidth(int colWidth) { + + this.colWidth = colWidth; + } + + /** + * Parse a colwidth in the form "1.234cm" to twips + * + * @param value <code>String</code> specification to parse. + * + * @return The twips equivalent. + */ + private int parseColWidth(String value) { + + int width = 255; // Default value + + if(value.indexOf("cm")!=-1) { + float widthCM = Float.parseFloat(value.substring(0,value.indexOf("c"))); + width = TwipsConverter.cm2twips(widthCM); + } else if(value.indexOf("inch")!=-1) { + float widthInch = Float.parseFloat(value.substring(0,value.indexOf("i"))); + width = TwipsConverter.inches2twips(widthInch); + } + + return (width); + } + + + /** + * Set an attribute. + * + * @param attr The attribute to set. + * @param value The attribute value to set. + */ + private void handleAttribute(String attr, String value) { + + if (attr.equals("style:column-width")) { + colWidth = parseColWidth(value); + } + else { + Debug.log(Debug.INFO, "ColumnStyle Unhandled: " + attr + "=" + value); + } + } + + + /** + * Return a <code>Style</code> object corresponding to this one, + * but with all of the inherited information from parent + * <code>Style</code> objects filled in. The object returned will + * be a new object, not a reference to this object, even if it does + * not need any information added. + * + * @return The <code>StyleCatalog</code> in which to look up + * ancestors. + */ + public Style getResolved() { + // Create a new object to return, which is a clone of this one. + ColumnStyle resolved = null; + try { + resolved = (ColumnStyle)this.clone(); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Can't clone", e); + } + + // Look up the parentStyle. (If there is no style catalog + // specified, we can't do any lookups.) + ColumnStyle parentStyle = null; + if (sc != null) { + if (parent != null) { + parentStyle = (ColumnStyle)sc.lookup(parent, family, null, + this.getClass()); + if (parentStyle == null) + Debug.log(Debug.ERROR, "parent style lookup of " + + parent + " failed!"); + else + parentStyle = (ColumnStyle)parentStyle.getResolved(); + + } else if (!name.equals("DEFAULT_STYLE")) { + parentStyle = (ColumnStyle)sc.lookup("DEFAULT_STYLE", null, + null, this.getClass()); + } + } + + // If we found a parent, for any attributes which we don't have + // set, try to get the values from the parent. + if (parentStyle != null) { + parentStyle = (ColumnStyle)parentStyle.getResolved(); + + if ((colWidth == 0) && (parentStyle.getColWidth() != 0)) + resolved.setColWidth(parentStyle.getColWidth()); + } + return resolved; + } + + + /** + * Create a new <code>Node</code> in the <code>Document</code>, and + * write this <code>Style</code> to it. + * + * @param parentDoc Parent <code>Document</code> of the + * <code>Node</code> to create. + * @param name Name to use for the new <code>Node</code> (e.g. + * <i>style:style</i>) + * + * @return Created <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + Element node = parentDoc.createElement(name); + writeAttributes(node); + return node; + } + + + /** + * Return true if <code>style</code> specifies as much or less + * than this <code>Style</code>, and nothing it specifies + * contradicts this <code>Style</code>. + * + * @param style The <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Style style) { + if (style.getClass() != this.getClass()) + return false; + ColumnStyle tStyle = (ColumnStyle)style; + + if(colWidth!=tStyle.getColWidth()) + return false; + + return true; + } + + + /** + * Write this <code>Style</code> object's attributes to a + * <code>Node</code> in the <code>Document</code>. + * + * @param node The <code>Node</code> to add <code>Style</code> + * attributes. + */ + public void writeAttributes(Element node) { + + if(colWidth!=0) { + String width = TwipsConverter.twips2cm(colWidth) + "cm"; + node.setAttribute("style:column-width", width); + } + } + + + private static String[] ignored = { + "fo:break-before", "fo:keep-with-next" + }; + + + /* + * This code checks whether an attribute is one that we + * intentionally ignore. + * + * @param attribute The attribute to check. + * + * @return true if <code>attribute</code> can be ignored, + * otherwise false. + */ + private boolean isIgnored(String attribute) { + for (int i = 0; i < ignored.length; i++) { + if (ignored[i].equals(attribute)) + return true; + } + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/DocumentMergerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/DocumentMergerImpl.java new file mode 100644 index 000000000000..eb4e03216fca --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/DocumentMergerImpl.java @@ -0,0 +1,199 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import org.w3c.dom.NodeList; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.MergeException; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.Difference; +import org.openoffice.xmerge.merger.Iterator; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.NodeMergeAlgorithm; +import org.openoffice.xmerge.merger.diff.IteratorRowCompare; +import org.openoffice.xmerge.merger.diff.RowIterator; +import org.openoffice.xmerge.merger.merge.SheetMerge; +import org.openoffice.xmerge.merger.merge.PositionBaseRowMerge; +import org.openoffice.xmerge.merger.MergeAlgorithm; +import org.openoffice.xmerge.util.XmlUtil; +import org.openoffice.xmerge.util.Debug; + + +/** + * Generic small device implementation of <code>DocumentMerger</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcPluginFactory + * SxcPluginFactory}. Used with SXC <code>Document</code> objects.</p> + */ +public class DocumentMergerImpl implements DocumentMerger { + + private ConverterCapabilities cc_; + private org.openoffice.xmerge.Document orig = null; + + /** + * Constructor + * + * @param doc The original "Office" <code>Document</code> + * to merge. + * @param cc The <code>ConverterCapabilities</code>. + */ + public DocumentMergerImpl(org.openoffice.xmerge.Document doc, ConverterCapabilities cc) { + cc_ = cc; + this.orig = doc; + } + + public void merge(Document modifiedDoc) throws MergeException { + + SxcDocument sdoc1 = (SxcDocument)orig; + SxcDocument sdoc2 = (SxcDocument)modifiedDoc; + + org.w3c.dom.Document doc1 = sdoc1.getContentDOM(); + org.w3c.dom.Document doc2 = sdoc2.getContentDOM(); + + Element elem1 = doc1.getDocumentElement(); + Element elem2 = doc2.getDocumentElement(); + + // get table name + NodeList workSheetList1 = + elem1.getElementsByTagName(OfficeConstants.TAG_TABLE); + NodeList workSheetList2 = + elem2.getElementsByTagName(OfficeConstants.TAG_TABLE); + + int numOfWorkSheet = workSheetList1.getLength(); + + for (int i=0; i < numOfWorkSheet; i++) { + Node workSheet = workSheetList1.item(i); + + // try to match the workSheet + Node matchingWorkSheet = matchWorkSheet(workSheet, workSheetList2); + + if (matchingWorkSheet != null) { + + // need to put it into a row Iterator + // use a straight comparsion algorithm then do a merge on it + Iterator i1 = new RowIterator(cc_, workSheet); + Iterator i2 = new RowIterator(cc_, matchingWorkSheet); + + // find out the diff + DiffAlgorithm diffAlgo = new IteratorRowCompare(); + + // find out the paragrah level diffs + Difference[] diffResult = diffAlgo.computeDiffs(i1, i2); + + if (Debug.isFlagSet(Debug.INFO)) { + Debug.log(Debug.INFO, "Diff Result: "); + + for (int j = 0; j < diffResult.length; j++) { + Debug.log(Debug.INFO, diffResult[j].debug()); + } + } + + // merge back the result + NodeMergeAlgorithm rowMerger = new PositionBaseRowMerge(cc_); + MergeAlgorithm merger = new SheetMerge(cc_, rowMerger); + + Iterator result = null; + + merger.applyDifference(i1, i2, diffResult); + } + } + + numOfWorkSheet = workSheetList2.getLength(); + + // for those workSheet from target don't have a matching one + // in the original workSheet list, we add it + + // find out the office body node first + NodeList officeBodyList = + elem1.getElementsByTagName(OfficeConstants.TAG_OFFICE_BODY); + + Node officeBody = officeBodyList.item(0); + + // for each WorkSheets, try to see whether we have it or not + for (int j=0; j < numOfWorkSheet; j++) { + Node workSheet= workSheetList2.item(j); + + // try to match the workSheet + // + Node matchingWorkSheet = matchWorkSheet(workSheet, workSheetList1); + + // add the new WorkSheet to the original document iff match not + // found + // + if (matchingWorkSheet == null) { + Node cloneNode = XmlUtil.deepClone(officeBody, workSheet); + officeBody.appendChild(cloneNode); + } + } + } + + /** + * Try to find a WorkSheet from the modified WorkSheetList that + * has a matching table name from the original WorkSheet. + * + * @param orgSheet The original WorkSheet. + * @param modSheetList The modified WorkSheet. + * + * @return The Node in modSheetList that matches the orgSheet. + */ + private Node matchWorkSheet(Node orgSheet, NodeList modSheetList) { + + Node matchSheet = null; + + String orgTableName = ((Element)orgSheet).getAttribute( + OfficeConstants.ATTRIBUTE_TABLE_NAME); + + if (orgTableName == null) + return null; + + int numOfWorkSheet = modSheetList.getLength(); + + String modTableName; + + for (int i=0; i < numOfWorkSheet; i++) { + modTableName = ((Element)modSheetList.item(i)).getAttribute( + OfficeConstants.ATTRIBUTE_TABLE_NAME); + if (modTableName == null) + continue; + + if (orgTableName.equals(modTableName)) { + matchSheet = modSheetList.item(i); + break; + } + } + + return matchSheet; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/Format.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/Format.java new file mode 100644 index 000000000000..7f6dee011253 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/Format.java @@ -0,0 +1,477 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.awt.Color; + +import org.openoffice.xmerge.util.Debug; + +/** + * This class specifies the format for a given spreadsheet cell. + * + * @author Mark Murnane + * @author Martin Maher (Extended Style Support) + */ +public class Format implements Cloneable { + + /** Horizontal Alignment Constants. */ + final public static int RIGHT_ALIGN = 0x01; + final public static int CENTER_ALIGN = 0x02; + final public static int LEFT_ALIGN = 0x03; + final public static int JUST_ALIGN = 0x04; + + /** Vertical Alignment Constants. */ + final public static int TOP_ALIGN = 0x01; + final public static int MIDDLE_ALIGN = 0x02; + final public static int BOTTOM_ALIGN = 0x03; + + /** Indicates <i>bold</i> text. */ + final public static int BOLD = 0x01; + /** Indicates <i>italic</i> text. */ + final public static int ITALIC = 0x02; + /** Indicates <i>underlined</i> text. */ + final public static int UNDERLINE = 0x04; + /** Indicates <i>strike-through</i> in the text. */ + final public static int STRIKETHRU = 0x08; + /** Indicates <i>superscripted</i> text. */ + final public static int SUPERSCRIPT = 0x10; + /** Indicates <i>subscripted</i> text. */ + final public static int SUBSCRIPT = 0x20; + + final public static int LEFT_BORDER = 0x40; + final public static int RIGHT_BORDER = 0x80; + final public static int TOP_BORDER = 0x100; + final public static int BOTTOM_BORDER = 0x200; + + final public static int WORD_WRAP = 0x400; + + private int align; + private int vertAlign; + private String category; + private String value; + private String formatSpecifier; + private int decimalPlaces; + + /** Font name. */ + private String fontName; + /** Font size in points. */ + protected int sizeInPoints; + + private Color foreground, background; + + /** Values of text attributes. */ + protected int attributes = 0; + /** Bitwise mask of text attributes. */ + protected int mask = 0; + + /** + * Constructor for creating a new <code>Format</code>. + */ + public Format() { + clearFormatting(); + } + + /** + * Constructor that creates a new <code>Format</code> object + * by setting all the format attributes. + * + */ + public Format(int attributes, int fontSize, String fontName) { + + this.attributes = attributes; + sizeInPoints = fontSize; + this.fontName = fontName; + } + + /** + * Constructor for creating a new <code>Format</code> object + * based on an existing one. + * + * @param fmt <code>Format</code> to copy. + */ + public Format(Format fmt) { + category = fmt.getCategory(); + value = fmt.getValue(); + formatSpecifier = fmt.getFormatSpecifier(); + decimalPlaces = fmt.getDecimalPlaces(); + + attributes = fmt.attributes; + mask = fmt.mask; + + fontName = fmt.getFontName(); + align = fmt.getAlign(); + vertAlign = fmt.getVertAlign(); + foreground = fmt.getForeground(); + background = fmt.getBackground(); + sizeInPoints = fmt.sizeInPoints; + } + + + /** + * Reset this <code>Format</code> description. + */ + public void clearFormatting() { + category = ""; + value = ""; + formatSpecifier = ""; + decimalPlaces = 0; + attributes = 0; + mask = 0; + sizeInPoints = 10; + align = LEFT_ALIGN; + vertAlign = BOTTOM_ALIGN; + fontName = ""; + foreground = null; + background = null; + } + + /** + * Set one or more text attributes to <i>on</i>. + * + * @param flags Flag attributes to set <i>on</i>. + */ + public void setAttribute(int flags, boolean toggle) { + mask |= flags; + if(toggle) { + attributes |= flags; + } else { + attributes &= ~flags; + } + } + + /** + * Return true if the <code>attribute</code> is set to <i>on</i> + * + * @param attribute Attribute to check ({@link #BOLD}, + * {@link #ITALIC}, etc.) + * + * @return true if <code>attribute</code> is set to <i>on</i>, + * otherwise false. + */ + public boolean getAttribute(int attribute) { + if ((mask & attribute) == 0) + return false; + return (!((attributes & attribute) == 0)); + } + + /** + * Return true if text <code>attribute</code> is set in this + * <code>Style</code>.An attribute that is set may have a + * value of <i>on</i> or <i>off</i>. + * + * @param attribute The attribute to check ({@link #BOLD}, + * {@link #ITALIC}, etc.). + * + * @return true if text <code>attribute</code> is set in this + * <code>Style</code>, false otherwise. + */ + public boolean isSet(int attribute) { + return (!((mask & attribute) == 0)); + } + + + /** + * Set the formatting category of this object, ie number, date, + * currency.The <code>OfficeConstants</code> class contains string + * constants for the category types. + * + * @see org.openoffice.xmerge.converter.xml.OfficeConstants + * + * @param newCategory The name of the category to be set. + */ + public void setCategory(String newCategory) { + category = newCategory; + } + + /** + * Return the formatting category of the object. + * + * @see org.openoffice.xmerge.converter.xml.OfficeConstants + * + * @return The formatting category of the object. + */ + public String getCategory() { + return category; + } + + /** + * In the case of Formula returns the value of the formula. + * + * @return The value of the formula + */ + public String getValue() { + return value; + } + + /** + * In the case of formula the contents are set as the formula string and + * the value of the formula is a formatting attribute. + * + * @param newValue the formuala value + */ + public void setValue(String newValue) { + value = newValue; + } + + + /** + * Set the <code>Format</code> specifier for this category. + * + * @param formatString The new <code>Format</code> specifier. + */ + public void setFormatSpecifier(String formatString) { + formatSpecifier = formatString; + } + + + /** + * Get the <code>Format</code> specifier for this category. + * + * @return <code>Format</code> specifier for this category. + */ + public String getFormatSpecifier() { + return formatSpecifier; + } + + + /** + * Set the precision of the number to be displayed. + * + * @param precision The number of decimal places to display. + */ + public void setDecimalPlaces(int precision) { + decimalPlaces = precision; + } + + + /** + * Get the number of decimal places displayed. + * + * @return Number of decimal places. + */ + public int getDecimalPlaces() { + return decimalPlaces; + } + + + /** + * Set the font used for this cell. + * + * @param fontName The name of the font. + */ + public void setFontName(String fontName) { + this.fontName = fontName; + } + + + /** + * Get the font used for this cell. + * + * @return The font name. + */ + public String getFontName() { + return fontName; + } + + /** + * Set the font used for this cell. + * + * @param fontName The name of the font. + */ + public void setFontSize(int fontSize) { + sizeInPoints = fontSize; + } + + + /** + * Get the font used for this cell. + * + * @return The font name. + */ + public int getFontSize() { + return sizeInPoints; + } + + /** + * Set the alignmen used for this cell. + * + * @param fontName The name of the font. + */ + public void setVertAlign(int vertAlign) { + this.vertAlign = vertAlign; + } + + + /** + * Get the alignment used for this cell. + * + * @return The font name. + */ + public int getVertAlign() { + return vertAlign; + } + + /** + * Set the alignmen used for this cell. + * + * @param fontName The name of the font. + */ + public void setAlign(int align) { + this.align = align; + } + + + /** + * Get the alignment used for this cell. + * + * @return The font name. + */ + public int getAlign() { + return align; + } + /** + * Set the Foreground <code>Color</code> for this cell. + * + * @param color A <code>Color</code> object representing the + * foreground color. + */ + public void setForeground(Color c) { + if(c!=null) + foreground = new Color(c.getRGB()); + } + + + /** + * Get the Foreground <code>Color</code> for this cell. + * + * @return Foreground <code>Color</code> value. + */ + public Color getForeground() { + return foreground; + } + + + /** + * Set the Background <code>Color</code> for this cell + * + * @param color A <code>Color</code> object representing + * the background color. + */ + public void setBackground(Color c) { + if(c!=null) + background = new Color(c.getRGB()); + } + + + /** + * Get the Foreground <code>Color</code> for this cell + * + * @return Background <code>Color</code> value + */ + public Color getBackground() { + return background; + } + + /** + * Get the Foreground <code>Color</code> for this cell + * + * @return Background <code>Color</code> value + */ + public String toString() { + return new String("Value : " + getValue() + " Category : " + getCategory()); + } + + /** + * Tests if the current <code>Format</code> object has default attribute + * values. + * + * @return true if it contains default value + */ + public boolean isDefault() { + + Format rhs = new Format(); + + if (rhs.attributes!= attributes) + return false; + + if (foreground!=rhs.foreground) + return false; + + if (background!=rhs.background) + return false; + + if (rhs.align!= align) + return false; + + if (rhs.vertAlign!= vertAlign) + return false; + + return true; + } + + /** + * Return true if <code>style</code> specifies as much or less + * than this <code>Style</code>, and nothing it specifies + * contradicts this <code>Style</code>. + * + * @param style The <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Format rhs) { + if (rhs.getClass() != this.getClass()) + return false; + + if (rhs.attributes!= attributes) + return false; + + if (rhs.sizeInPoints != 0) { + if (sizeInPoints != rhs.sizeInPoints) + return false; + } + + if (fontName!=rhs.fontName) + return false; + + if (foreground!=rhs.foreground) + return false; + + if (background!=rhs.background) + return false; + + if (rhs.align!= align) + return false; + + if (rhs.vertAlign!= vertAlign) + return false; + + return true; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/NameDefinition.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/NameDefinition.java new file mode 100644 index 000000000000..99aa3dd625ec --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/NameDefinition.java @@ -0,0 +1,216 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import org.w3c.dom.NamedNodeMap; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.XmlUtil; + +/** + * This is a class to define a Name Definition structure. This can then be + * used by plugins to write or read their own definition types. + * + * @author Martin Maher + */ +public class NameDefinition implements OfficeConstants { + + private String name; // name which identifies the definition + private String definition; // the definition itself + private String baseCellAddress; // the basecelladdress + private boolean rangeType = false; // true if definition of type range + private boolean expressionType = false; // true if definition of type expression + + /** + * Default Constructor for a <code>NameDefinition</code> + * + */ + public NameDefinition() { + + } + + /** + * Constructor that takes a <code>Node</code> to build a + * <code>NameDefinition</code> + * + * @param root XML Node to read from + */ + public NameDefinition(Node root) { + readNode(root); + } + + /** + * Default Constructor for a <code>NameDefinition</code> + * + */ + public NameDefinition(String name, String definition, String + baseCellAddress, boolean rangeType, boolean expressionType ) { + this.name = name; + this.definition = definition; + this.baseCellAddress = baseCellAddress; + this.rangeType = rangeType; + this.expressionType = expressionType; + } + + /** + * returns Name of the definition + * + * @return the name which identifies the definition + */ + public String getName() { + + return name; + } + /** + * sets the definition + * + * @param newDefinition sets the definition + */ + public void setDefinition(String newDefinition) { + + definition = newDefinition; + } + /** + * Returns the definition itself + * + * @return the definition + */ + public String getDefinition() { + + return definition; + } + + /** + * Returns the base Cell address + * + * @return the base cell address + */ + public String getBaseCellAddress() { + + return baseCellAddress; + } + + /** + * Tests if definition is of type expression + * + * @return whether or not this name definition is of type expression + */ + public boolean isExpressionType() { + return expressionType; + } + + /** + * Tests if definition is of type range + * + * @return whether or not this name definition is of type range + */ + public boolean isRangeType() { + return rangeType; + } + + /** + * Writes out a content.xml entry for this NameDefinition object + * + * @param settings a <code>Document</code> object representing the settings.xml + * @param root the root xml node to add to + */ + public void writeNode(org.w3c.dom.Document doc, Node root) { + + if(isRangeType()) { + + Debug.log(Debug.TRACE, "Found Range Name : " + getName()); + Element namedRangeElement = (Element) doc.createElement(TAG_TABLE_NAMED_RANGE); + namedRangeElement.setAttribute(ATTRIBUTE_TABLE_NAME, getName()); + namedRangeElement.setAttribute(ATTRIBUTE_TABLE_BASE_CELL_ADDRESS, getBaseCellAddress()); + namedRangeElement.setAttribute(ATTRIBUTE_TABLE_CELL_RANGE_ADDRESS, getDefinition()); + root.appendChild(namedRangeElement); + } else if (isExpressionType()) { + + Debug.log(Debug.TRACE, "Found Expression Name : " + getName()); + Element namedExpressionElement = (Element) doc.createElement(TAG_TABLE_NAMED_EXPRESSION); + namedExpressionElement.setAttribute(ATTRIBUTE_TABLE_NAME, getName()); + namedExpressionElement.setAttribute(ATTRIBUTE_TABLE_BASE_CELL_ADDRESS,getBaseCellAddress()); + namedExpressionElement.setAttribute(ATTRIBUTE_TABLE_EXPRESSION, getDefinition()); + root.appendChild(namedExpressionElement); + } else { + + Debug.log(Debug.TRACE, "Unknown Name Definition : " + getName()); + } + } + + /** + * Reads document settings from xml and inits Settings variables + * + * @param root XML Node to read from + */ + public void readNode(Node root) { + + String nodeName = root.getNodeName(); + NamedNodeMap cellAtt = root.getAttributes(); + + if (nodeName.equals(TAG_TABLE_NAMED_RANGE)) { + + Node tableNameNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_NAME); + Node tableBaseCellAddress = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_BASE_CELL_ADDRESS); + Node tableCellRangeAddress = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_CELL_RANGE_ADDRESS); + Debug.log(Debug.TRACE,"Named-range : " + tableNameNode.getNodeValue()); + // Create a named-range name definition + name = tableNameNode.getNodeValue(); + definition = tableCellRangeAddress.getNodeValue(); + baseCellAddress = tableBaseCellAddress.getNodeValue(); + expressionType = true; + rangeType = false; + + } else if (nodeName.equals(TAG_TABLE_NAMED_EXPRESSION)) { + + Node tableNameNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_NAME); + Node tableBaseCellAddress = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_BASE_CELL_ADDRESS); + Node tableExpression= + cellAtt.getNamedItem(ATTRIBUTE_TABLE_EXPRESSION); + Debug.log(Debug.TRACE,"Named-expression: " + tableNameNode.getNodeValue()); + // Create a named-range name definition + name = tableNameNode.getNodeValue(); + definition = tableExpression.getNodeValue(); + baseCellAddress = tableBaseCellAddress.getNodeValue(); + expressionType = false; + rangeType = true; + } else { + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(root) + " />"); + } + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/RowStyle.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/RowStyle.java new file mode 100644 index 000000000000..aecb3cec3001 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/RowStyle.java @@ -0,0 +1,305 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.Style; +import org.openoffice.xmerge.converter.xml.StyleCatalog; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.TwipsConverter; + +/** + * Represents a text <code>Style</code> in an OpenOffice document. + * + * @author Martin Maher + */ +public class RowStyle extends Style implements Cloneable { + + private int rowHeight = 255; + /** + * Constructor for use when going from DOM to client device format. + * + * @param Node The <i>style:style</i> <code>Node</code> containing + * the <code>Style</code>. (This <code>Node</code> is + * assumed have a <i>family</i> attribute of <i>text</i>). + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public RowStyle(Node node, StyleCatalog sc) { + super(node, sc); + + // Run through the attributes of this node, saving + // the ones we're interested in. + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + handleAttribute(attr.getNodeName(), attr.getNodeValue()); + } + } + + // Look for children. Only ones we care about are "style:properties" + // nodes. If any are found, recursively traverse them, passing + // along the style element to add properties to. + if (node.hasChildNodes()) { + NodeList children = node.getChildNodes(); + int len = children.getLength(); + for (int i = 0; i < len; i++) { + Node child = children.item(i); + String name = child.getNodeName(); + if (name.equals("style:properties")) { + NamedNodeMap childAttrNodes = child.getAttributes(); + if (childAttrNodes != null) { + int nChildAttrNodes = childAttrNodes.getLength(); + for (int j = 0; j < nChildAttrNodes; j++) { + Node attr = childAttrNodes.item(j); + handleAttribute(attr.getNodeName(), + attr.getNodeValue()); + } + } + } + } + } + } + + + /** + * Constructor for use when going from client device format to DOM + * + * @param name Name of text <code>Style</code>. Can be null. + * @param family Family of text <code>Style</code> (usually + * <i>text</i>). Can be null. + * @param parent Name of parent text <code>Style</code>, or null + * for none. + * @param mask The height of this row + * @param sc The <code>StyleCatalog</code>, which is used for + * looking up ancestor <code>Style</code> objects. + */ + public RowStyle(String name, String family, String parent,int rowHeight, StyleCatalog sc) { + super(name, family, parent, sc); + this.rowHeight=rowHeight; + } + + /** + * Returns the height of this row + * + * @return the <code>Format</code> object + */ + public int getRowHeight() { + return rowHeight; + } + + /** + * Sets the height of this row + * + * @return the <code>Format</code> object + */ + public void setRowHeight(int RowHeight) { + + this.rowHeight = rowHeight; + } + /** + * Parse a colheight in the form "1.234cm" to twips + * + * @param value <code>String</code> specification to parse. + * + * @return The twips equivalent. + */ + private int parseRowHeight(String value) { + + int height = 255; // Default value + + if(value.indexOf("cm")!=-1) { + float heightCM = Float.parseFloat(value.substring(0,value.indexOf("c"))); + height = TwipsConverter.cm2twips(heightCM); + } else if(value.indexOf("inch")!=-1) { + float heightInch = Float.parseFloat(value.substring(0,value.indexOf("i"))); + height = TwipsConverter.inches2twips(heightInch); + } + + return (height); + + } + + + /** + * Set an attribute. + * + * @param attr The attribute to set. + * @param value The attribute value to set. + */ + private void handleAttribute(String attr, String value) { + + if (attr.equals("style:row-height")) { + rowHeight = parseRowHeight(value); + } + else { + Debug.log(Debug.INFO, "RowStyle Unhandled: " + attr + "=" + value); + } + } + + + /** + * Return a <code>Style</code> object corresponding to this one, + * but with all of the inherited information from parent + * <code>Style</code> objects filled in. The object returned will + * be a new object, not a reference to this object, even if it does + * not need any information added. + * + * @return The <code>StyleCatalog</code> in which to look up + * ancestors. + */ + public Style getResolved() { + // Create a new object to return, which is a clone of this one. + RowStyle resolved = null; + try { + resolved = (RowStyle)this.clone(); + } catch (Exception e) { + Debug.log(Debug.ERROR, "Can't clone", e); + } + + // Look up the parentStyle. (If there is no style catalog + // specified, we can't do any lookups.) + RowStyle parentStyle = null; + if (sc != null) { + if (parent != null) { + parentStyle = (RowStyle)sc.lookup(parent, family, null, + this.getClass()); + if (parentStyle == null) + Debug.log(Debug.ERROR, "parent style lookup of " + + parent + " failed!"); + else + parentStyle = (RowStyle)parentStyle.getResolved(); + + } else if (!name.equals("DEFAULT_STYLE")) { + parentStyle = (RowStyle)sc.lookup("DEFAULT_STYLE", null, + null, this.getClass()); + } + } + + // If we found a parent, for any attributes which we don't have + // set, try to get the values from the parent. + if (parentStyle != null) { + parentStyle = (RowStyle)parentStyle.getResolved(); + + if ((rowHeight == 0) && (parentStyle.getRowHeight() != 0)) + resolved.setRowHeight(parentStyle.getRowHeight()); + } + return resolved; + } + + + /** + * Create a new <code>Node</code> in the <code>Document</code>, and + * write this <code>Style</code> to it. + * + * @param parentDoc Parent <code>Document</code> of the + * <code>Node</code> to create. + * @param name Name to use for the new <code>Node</code> (e.g. + * <i>style:style</i>) + * + * @return Created <code>Node</code>. + */ + public Node createNode(org.w3c.dom.Document parentDoc, String name) { + Element node = parentDoc.createElement(name); + writeAttributes(node); + return node; + } + + + /** + * Return true if <code>style</code> specifies as much or less + * than this <code>Style</code>, and nothing it specifies + * contradicts this <code>Style</code>. + * + * @param style The <code>Style</code> to check. + * + * @return true if <code>style</code> is a subset, false + * otherwise. + */ + public boolean isSubset(Style style) { + if (style.getClass() != this.getClass()) + return false; + RowStyle tStyle = (RowStyle)style; + + if(rowHeight!=tStyle.getRowHeight()) + return false; + + return true; + } + + + /** + * Write this <code>Style</code> object's attributes to a + * <code>Node</code> in the <code>Document</code>. + * + * @param node The <code>Node</code> to add <code>Style</code> + * attributes. + */ + public void writeAttributes(Element node) { + + if(rowHeight!=0) { + String height = TwipsConverter.twips2cm(rowHeight) + "cm"; + node.setAttribute("style:row-height", height); + } + } + + + private static String[] ignored = { + "fo:break-before", "fo:keep-with-next" + }; + + + /* + * This code checks whether an attribute is one that we + * intentionally ignore. + * + * @param attribute The attribute to check. + * + * @return true if <code>attribute</code> can be ignored, + * otherwise false. + */ + private boolean isIgnored(String attribute) { + for (int i = 0; i < ignored.length; i++) { + if (ignored[i].equals(attribute)) + return true; + } + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SheetSettings.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SheetSettings.java new file mode 100644 index 000000000000..08339773be30 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SheetSettings.java @@ -0,0 +1,374 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import java.awt.Point; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.util.Debug; + +/** + * This is a class representing the different attributes for a worksheet + * contained in settings.xml. + * + * @author Martin Maher + */ +public class SheetSettings implements OfficeConstants { + + /** A w3c <code>Document</code>. */ + private org.w3c.dom.Document settings = null; + + private String sheetName; + private int cursorX = 0; + private int cursorY = 0; + private int splitTypeX; + private int splitTypeY; + private int splitPointX = 0; + private int splitPointY = 0; + private int posLeft = 0; + private int posRight = 0; + private int posBottom = 0; + private int posTop = 0; + private int paneNumber = 2; + + final public static int NONE = 0x00; + final public static int SPLIT = 0x01; + final public static int FREEZE = 0x02; + + + /** + * Default Constructor for a <code>ColumnRowInfo</code> + * + */ + public SheetSettings() { + } + + /** + * Constructor that takes a <code>Node</code> to build a <code>SheetSettings</code> + * + * @param root XML Node to read from + */ + public SheetSettings(Node root) { + readNode(root); + } + + /** + * Constructor for a <code>ColumnRowInfo</code> + * + * @param dimension if it's a row the height, a column the width + * @param repeated + */ + public SheetSettings(String name) { + sheetName = name; + } + + /** + * sets the position of the acitve cell + * + * @param activeCell the current curor position + */ + public void setCursor(Point activeCell) { + + cursorX = (int) activeCell.getX(); + cursorY = (int) activeCell.getY(); + } + + /** + * Gets the position of the acitve cell + * + * @return The position as a <code>Point</code> + */ + public Point getCursor() { + + return (new Point(cursorX, cursorY)); + } + + /** + * Sets the position of the freeze + * + * @param splitPoint the point at where the split occurs + */ + public void setFreeze(Point splitPoint) { + + splitTypeX = FREEZE; + splitTypeY = FREEZE; + splitPointX = (int) splitPoint.getX(); + splitPointY = (int) splitPoint.getY(); + } + + /** + * Sets the position of the split + * + * @param splitPoint the point at where the split occurs + */ + public void setSplit(Point splitPoint) { + + splitTypeX = SPLIT; + splitTypeY = SPLIT; + splitPointX = (int) splitPoint.getX(); + splitPointY = (int) splitPoint.getY(); + } + + /** + * sets the position and type of the split + * + * @return The position as a <code>Point</code> where the split occurs + */ + public Point getSplit() { + + return (new Point(splitPointX, splitPointY)); + } + + /** + * sets the position and type of the split + * + * @return The position as a <code>Point</code> where the split occurs + */ + public Point getSplitType() { + + return (new Point(splitTypeX, splitTypeY)); + } + + /** + * Sets the top row visible in the lower pane and the leftmost column + * visibile in the right pane. + * + * @param top The top row visible in the lower pane + * @param left The leftmost column visibile in the right pane + */ + public void setTopLeft(int top, int left) { + + posLeft = left; + posTop = top; + } + + /** + * Gets the the leftmost column visibile in the right pane. + * + * @return the 0-based index to the column + */ + public int getLeft() { + + return posLeft; + } + /** + * Sets the top row visible in the lower pane and the leftmost column + * visibile in the right pane. + * + * @param top The top row visible in the lower pane + * @param left The leftmost column visibile in the right pane + */ + public int getTop() { + + return posTop; + } + + /** + * Gets the active Panel + * 0 - Bottom Right, 1 - Top Right + * 2 - Bottom Left, 3 - Top Left + * + * @return int representing the active panel + */ + public int getPaneNumber() { + + return paneNumber; + } + + /** + * Sets the sheetname this settings object applies to + * + * @param sheetName the name of the worksheet + */ + public void setSheetName(String sheetName) { + + this.sheetName = sheetName; + + } + + /** + * Sets the active pane number + * 0 - Bottom Right, 1 - Top Right + * 2 - Bottom Left, 3 - Top Left + * + * @param paneNumber the pane number + */ + public void setPaneNumber(int paneNumber) { + + this.paneNumber = paneNumber; + } + + /** + * Gets the name of the worksheet these <code>Settings</code> apply to + * + * @return the name of the worksheet + */ + public String getSheetName() { + + return sheetName; + } + + /** + * Adds an XML entry for a particular setting + * + * @param root the root node at which to add the xml entry + * @param attriute the name of the attribute to add + * @param type the attribute type (int, short etc) + * @param value the value of the attribute + */ + private void addConfigItem(Node root, String attribute, String type, String value) { + + Element configItem = settings.createElement(TAG_CONFIG_ITEM); + configItem.setAttribute(ATTRIBUTE_CONFIG_NAME, attribute); + configItem.setAttribute(ATTRIBUTE_CONFIG_TYPE, type); + + configItem.appendChild(settings.createTextNode(value)); + + root.appendChild(configItem); + } + + /** + * Writes out a settings.xml entry for this SheetSettings object + * + * @param settings a <code>Document</code> object representing the settings.xml + * @param root the root xml node to add to + */ + public void writeNode(org.w3c.dom.Document settings, Node root) { + + this.settings = settings; + Element configItemMapEntry = (Element) settings.createElement(TAG_CONFIG_ITEM_MAP_ENTRY); + configItemMapEntry.setAttribute(ATTRIBUTE_CONFIG_NAME, getSheetName()); + addConfigItem(configItemMapEntry, "CursorPositionX", "int", Integer.toString(cursorX)); + addConfigItem(configItemMapEntry, "CursorPositionY", "int", Integer.toString(cursorY)); + + String splitMode = Integer.toString(splitTypeX); + if(splitPointX==0) { + splitMode = "0"; + } + addConfigItem(configItemMapEntry, "HorizontalSplitMode", "short", splitMode); + + splitMode = Integer.toString(splitTypeY); + if(splitPointY==0) { + splitMode = "0"; + } + addConfigItem(configItemMapEntry, "VerticalSplitMode", "short", splitMode); + + addConfigItem(configItemMapEntry, "HorizontalSplitPosition", "int", Integer.toString(splitPointX)); + addConfigItem(configItemMapEntry, "VerticalSplitPosition", "int", Integer.toString(splitPointY)); + addConfigItem(configItemMapEntry, "ActiveSplitRange", "short", Integer.toString(paneNumber)); + + addConfigItem(configItemMapEntry, "PositionLeft", "int", "0"); + addConfigItem(configItemMapEntry, "PositionRight", "int", Integer.toString(posLeft)); + addConfigItem(configItemMapEntry, "PositionTop", "int", "0"); + addConfigItem(configItemMapEntry, "PositionBottom", "int", Integer.toString(posTop)); + root.appendChild(configItemMapEntry); + } + + /** + * Sets a variable based on a String value read from XML + * + * @param name xml name of the attribute to set + * @param value String value fo the attribute + */ + public void addAttribute(String name, String value) { + + if(name.equals("CursorPositionX")) { + cursorX = Integer.parseInt(value); + } else if(name.equals("CursorPositionY")) { + cursorY = Integer.parseInt(value); + + } else if(name.equals("HorizontalSplitPosition")) { + splitPointX = Integer.parseInt(value); + } else if(name.equals("VerticalSplitPosition")) { + splitPointY = Integer.parseInt(value); + } else if(name.equals("ActiveSplitRange")) { + paneNumber = Integer.parseInt(value); + + } else if(name.equals("PositionRight")) { + posLeft = Integer.parseInt(value); + } else if(name.equals("PositionBottom")) { + posTop = Integer.parseInt(value); + + } else if(name.equals("HorizontalSplitMode")) { + splitTypeX = Integer.parseInt(value); + } else if(name.equals("VerticalSplitMode")) { + splitTypeY = Integer.parseInt(value); + } + } + + /** + * Reads document settings from xml and inits SheetSettings variables + * + * @param root XML Node to read from + */ + public void readNode(Node root) { + + NamedNodeMap sheetAtt = root.getAttributes(); + + Node sheetNameNode = sheetAtt.getNamedItem(ATTRIBUTE_CONFIG_NAME); + + sheetName = sheetNameNode.getNodeValue(); + + if (root.hasChildNodes()) { + + NodeList nodeList = root.getChildNodes(); + int len = nodeList.getLength(); + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_CONFIG_ITEM)) { + + NamedNodeMap cellAtt = child.getAttributes(); + + Node configNameNode = + cellAtt.getNamedItem(ATTRIBUTE_CONFIG_NAME); + + String name = configNameNode.getNodeValue(); + NodeList nodeList2 = child.getChildNodes(); + int len2 = nodeList2.getLength(); + String s = ""; + for (int j = 0; j < len2; j++) { + Node child2 = nodeList2.item(j); + if (child2.getNodeType() == Node.TEXT_NODE) { + s = child2.getNodeValue(); + } + } + addAttribute(name, s); + } + } + } + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetDecoder.java new file mode 100644 index 000000000000..a0ec6cc305bd --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetDecoder.java @@ -0,0 +1,181 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.io.IOException; +import java.io.InputStream; +import java.util.Enumeration; + +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.ConvertData; + +/** + * This class is a abstract class for encoding a "Device" + * <code>Document</code> format into an alternative spreadsheet format. + * + * @author Mark Murnane + */ +public abstract class SpreadsheetDecoder { + + /** + * Constructor for creating new <code>SpreadsheetDecoder</code>. + */ + public SpreadsheetDecoder(String name, String password) throws IOException { + } + + /** + * Returns the total number of sheets in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public abstract int getNumberOfSheets(); + + /** + * Returns an Enumeration to a Vector of <code>NameDefinition</code>. + * + * @return The Enumeration + */ + public abstract Enumeration getNameDefinitions(); + + /** + * Returns an <code>BookSettings</code> + * + * @return The Enumeration + */ + public abstract BookSettings getSettings(); + + /** + * Returns an Enumeration to a Vector of <code>ColumnRowInfo</code>. + * + * @return The Enumeration + */ + public abstract Enumeration getColumnRowInfos(); + + /** + * Returns the number of populated rows in the current WorkSheet. + * + * @return the number of populated rows in the current WorkSheet. + */ + public abstract int getNumberOfRows(); + + + /** + * Returns the number of populated columns in the current WorkSheet. + * + * @return The number of populated columns in the current WorkSheet. + */ + public abstract int getNumberOfColumns(); + + + /** + * Returns the name of the current WorkSheet. + * + * @return Name of the current WorkSheet. + */ + public abstract String getSheetName(); + + + /** + * Returns the number of the active column. + * + * @return The number of the active column. + */ + public abstract int getColNumber(); + + + /** + * Returns the number of the active row. + * + * @return The number of the active row. + */ + public abstract int getRowNumber(); + + + /** + * Sets the active WorkSheet. + * + * @param sheetIndex The index of the sheet to be made active. + * + * @throws IOException If any I/O error occurs. + */ + public abstract void setWorksheet(int sheetIndex) throws IOException; + + + /** + * Move on the next populated cell in the current WorkSheet. + * + * @return true if successful, false otherwise. + * + * @throws IOException If any I/O error occurs. + */ + public abstract boolean goToNextCell() throws IOException; + + + /** + * Return the contents of the active cell. + * + * @return The cell contents. + */ + public abstract String getCellContents(); + + /** + * Return the value of the active cell. Used in the case of Formula where + * the cell contents and the cell value are not the same thing. + * + * @return The cell value. + */ + public abstract String getCellValue(); + + /** + * Return the data type of the active cell. + * + * @return The cell data type. + */ + public abstract String getCellDataType(); + + + /** + * Return a <code>Format</code> object describing the active cells + * formatting. + * + * @return <code>Format</code> object for the cell. + */ + public abstract Format getCellFormat(); + + + /** + * Add the contents of a <code>ConvertData</code> to the workbook. + * + * @param cd The <code>ConvertData</code> containing the + * content. + * + * @throws IOException If any I/O error occurs. + */ + public abstract void addDeviceContent(ConvertData cd) throws IOException; +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetEncoder.java new file mode 100644 index 000000000000..7d0d1f615849 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SpreadsheetEncoder.java @@ -0,0 +1,131 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.io.IOException; +import java.util.Vector; + +import org.openoffice.xmerge.util.IntArrayList; + +/** + * <p>This class is a abstract class for encoding an SXC into an + * alternative spreadsheet format.</p> + * + * <p>TODO - Add appropriate exceptions to each of the methods.</p> + * + * @author Mark Murnane + */ +public abstract class SpreadsheetEncoder { + + + /** + * Creates new SpreadsheetEncoder. + * + * @param name The name of the WorkBook to be created. + * @param password An optional password for the WorkBook. + * + * @throws IOException If any I/O error occurs. + */ + public SpreadsheetEncoder(String name, String password) throws IOException { }; + + + /** + * Create a new WorkSheet within the WorkBook. + * + * @param sheetName The name of the WorkSheet. + * + * @throws IOException If any I/O error occurs. + */ + public abstract void createWorksheet(String sheetName) throws IOException; + + + /** + * Set a cell's formatting options via a separately create + * <code>Format</code> object. + * + * @param row The row number of the cell to be changed + * @param column The column number of the cell to be changed + * @param fmt Object containing formatting settings for this cell. + */ + public abstract void setCellFormat(int row, int column, Format fmt); + + + /** + * Add a cell to the current WorkSheet. + * + * @param row The row number of the cell + * @param column The column number of the cell + * @param fmt The <code>Format</code> object describing the + * appearance of this cell. + * @param cellContents The text or formula of the cell's contents. + */ + public abstract void addCell(int row, int column, + Format fmt, String cellContents) throws IOException; + + + /** + * Get the number of sheets in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public abstract int getNumberOfSheets(); + + + /** + * Get the names of the sheets in the WorkBook. + * + * @param sheet The required sheet. + */ + public abstract String getSheetName(int sheet); + + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public abstract void setColumnRows(Vector columnRows) throws IOException; + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public abstract void setNameDefinition(NameDefinition nd) throws IOException; + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public abstract void addSettings(BookSettings s) throws IOException; +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcConstants.java new file mode 100644 index 000000000000..7c9fff61a2e6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcConstants.java @@ -0,0 +1,50 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc; + + +/** + * Interface defining constants for Sxc attributes. + * + * @author Martin Maher + */ +public interface SxcConstants { + + /** Family name for column styles. */ + public static final String COLUMN_STYLE_FAMILY = "table-column"; + + /** Family name for row styles. */ + public static final String ROW_STYLE_FAMILY = "table-row"; + + /** Family name for table-cell styles. */ + public static final String TABLE_CELL_STYLE_FAMILY = "table-cell"; + + /** Name of the default style. */ + public static final String DEFAULT_STYLE = "Default"; +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocument.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocument.java new file mode 100644 index 000000000000..d435479842c6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocument.java @@ -0,0 +1,93 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import org.w3c.dom.Document; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * This class is an implementation of <code>OfficeDocument</code> for + * the SXC format. + */ +public class SxcDocument extends OfficeDocument { + + /** + * Constructor with arguments to set <code>name</code>. + * + * @param name The name of the <code>Document</code> + */ + public SxcDocument(String name) { + super(name); + } + + + /** + * Constructor with arguments to set <code>name</code>, the + * <code>namespaceAware</code> flag, and the <code>validating</code> + * flag. + * + * @param name The name of the <code>Document</code>. + * @param namespaceAware The value of the <code>namespaceAware</code> + * flag. + * @param validating The value of the <code>validating</code> flag. + */ + public SxcDocument(String name, boolean namespaceAware, boolean validating) { + + super(name, namespaceAware, validating); + } + + /** + * Returns the Office file extension for the SXC format. + * + * @return The Office file extension for the SXC format. + */ + protected String getFileExtension() { + return OfficeConstants.SXC_FILE_EXTENSION; + } + + /** + * Returns the Office attribute for the SXC format. + * + * @return The Office attribute for the SXC format. + */ + protected String getOfficeClassAttribute() { + return OfficeConstants.SXC_TYPE; + } + + /** + * Method to return the MIME type of the document. + * + * @return String The document's MIME type. + */ + protected final String getDocumentMimeType() { + return OfficeConstants.SXC_MIME_TYPE; + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentDeserializer.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentDeserializer.java new file mode 100644 index 000000000000..2415c9385d62 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentDeserializer.java @@ -0,0 +1,794 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; + +import java.awt.Point; +import java.io.IOException; +import java.util.Enumeration; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocument; +import org.openoffice.xmerge.converter.xml.sxc.BookSettings; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; +import org.openoffice.xmerge.converter.xml.sxc.NameDefinition; +import org.openoffice.xmerge.converter.xml.sxc.CellStyle; +import org.openoffice.xmerge.converter.xml.Style; +import org.openoffice.xmerge.converter.xml.StyleCatalog; +import org.openoffice.xmerge.util.Debug; + +/** + * <p>General spreadsheet implementation of <code>DocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcPluginFactory + * SxcPluginFactory}. Used with SXC <code>Document</code> objects.</p> + * + * <p>The <code>deserialize</code> method uses a <code>DocDecoder</code> + * to read the device spreadsheet format into a <code>String</code> + * object, then it calls <code>buildDocument</code> to create a + * <code>SxcDocument</code> object from it.</p> + * + * @author Paul Rank + * @author Mark Murnane + * @author Martin Maher + */ +public abstract class SxcDocumentDeserializer implements OfficeConstants, + DocumentDeserializer { + + /** + * A <code>SpreadsheetDecoder</code> object for decoding from + * device formats. + */ + private SpreadsheetDecoder decoder = null; + + /** A w3c <code>Document</code>. */ + private org.w3c.dom.Document settings = null; + + /** A w3c <code>Document</code>. */ + private org.w3c.dom.Document doc = null; + + /** An <code>ConvertData</code> object assigned to this object. */ + private ConvertData cd = null; + + /** A style catalog for the workbook */ + private StyleCatalog styleCat = null; + + private int textStyles = 1; + private int colStyles = 1; + private int rowStyles = 1; + + /** + * Constructor. + * + * @param cd <code>ConvertData</code> consisting of a + * device content object. + */ + public SxcDocumentDeserializer(ConvertData cd) { + this.cd = cd; + } + + + /** + * This abstract method will be implemented by concrete subclasses + * and will return an application-specific Decoder. + * + * @param workbook The WorkBook to read. + * @param password The WorkBook password. + * + * @return The appropriate <code>SpreadSheetDecoder</code>. + * + * @throws IOException If any I/O error occurs. + */ + public abstract SpreadsheetDecoder createDecoder(String workbook, String[] worksheetNames, String password) + throws IOException; + + + /** + * <p>This method will return the name of the WorkBook from the + * <code>ConvertData</code>. Allows for situations where the + * WorkBook name differs from the Device Content name.</p> + * + * <p>Implemented in the Deserializer as the Decoder's constructor requires + * a name.</p> + * + * @param cd The <code>ConvertData</code> containing the Device + * content. + * + * @return The WorkBook name. + */ + protected abstract String getWorkbookName(ConvertData cd) throws IOException; + + + /** + * This method will return the name of the WorkSheet from the + * <code>ConvertData</code>. + * + * @param cd The <code>ConvertData</code> containing the Device + * content. + * + * @return The WorkSheet names. + */ + protected abstract String[] getWorksheetNames(ConvertData cd) throws IOException; + + + /** + * <p>Method to convert a set of "Device" + * <code>Document</code> objects into a <code>SxcDocument</code> + * object and returns it as a <code>Document</code>.</p> + * + * <p>This method is not thread safe for performance reasons. + * This method should not be called from within two threads. + * It would be best to call this method only once per object + * instance.</p> + * + * @return document An <code>SxcDocument</code> consisting + * of the data converted from the input + * stream. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public Document deserialize() throws ConvertException, + IOException { + + // Get the name of the WorkBook from the ConvertData. + String[] worksheetNames = getWorksheetNames(cd); + String workbookName = getWorkbookName(cd); + + // Create a document + SxcDocument sxcDoc = new SxcDocument(workbookName); + sxcDoc.initContentDOM(); + sxcDoc.initSettingsDOM(); + + // Default to an initial 5 entries in the catalog. + styleCat = new StyleCatalog(5); + + doc = sxcDoc.getContentDOM(); + settings = sxcDoc.getSettingsDOM(); + initFontTable(); + // Little fact for the curious reader: workbookName should + // be the name of the StarCalc file minus the file extension suffix. + + // Create a Decoder to decode the DeviceContent to a spreadsheet document + // TODO - we aren't using a password in StarCalc, so we can + // use any value for password here. If StarCalc XML supports + // passwords in the future, we should try to get the correct + // password value here. + // + decoder = createDecoder(workbookName, worksheetNames, "password"); + + Debug.log(Debug.TRACE, "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"); + Debug.log(Debug.TRACE, "<DEBUGLOG>"); + + decoder.addDeviceContent(cd); + decode(); + + Debug.log(Debug.TRACE, "</DEBUGLOG>"); + + return sxcDoc; + } + + /** + * This initializes a font table so we can imclude some basic font + * support for spreadsheets. + * + */ + private void initFontTable() { + + String fontTable[]= new String[] { "Tahoma", "Tahoma", "swiss", "variable", + "Courier New", "'Courier New'", "modern", "fixed"}; + // Traverse to the office:body element. + // There should only be one. + NodeList list = doc.getElementsByTagName(TAG_OFFICE_FONT_DECLS); + Node root = list.item(0); + + for(int i=0;i<fontTable.length;) { + + // Create an element node for the table + Element tableElement = (Element) doc.createElement(TAG_STYLE_FONT_DECL); + + tableElement.setAttribute(ATTRIBUTE_STYLE_NAME, fontTable[i++]); + tableElement.setAttribute(ATTRIBUTE_FO_FONT_FAMILY, fontTable[i++]); + tableElement.setAttribute(ATTRIBUTE_FO_FONT_FAMILY_GENERIC, fontTable[i++]); + tableElement.setAttribute(ATTRIBUTE_STYLE_FONT_PITCH, fontTable[i++]); + + root.appendChild(tableElement); + } + + } + + /** + * Outer level method used to decode a WorkBook + * into a <code>Document</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void decode() throws IOException { + + // Get number of worksheets + int numSheets = decoder.getNumberOfSheets(); + // #i33702# - check for an Empty InputStream. + if(numSheets == 0) + { + System.err.println("Error decoding invalid Input stream"); + return; + } + + // Traverse to the office:body element. + // There should only be one. + NodeList list = doc.getElementsByTagName(TAG_OFFICE_BODY); + Node node = list.item(0); + + for (int i = 0; i < numSheets; i++) { + + // Set the decoder to the correct worksheet + decoder.setWorksheet(i); + + int len = list.getLength(); + + if (len > 0) { + + // Process the spreadsheet + processTable(node); + } + } + + // Add the Defined Name table if there is one + Enumeration nameDefinitionTable = decoder.getNameDefinitions(); + if(nameDefinitionTable.hasMoreElements()) { + processNameDefinition(node, nameDefinitionTable); + } + + // add settings + NodeList settingsList = settings.getElementsByTagName(TAG_OFFICE_SETTINGS); + Node settingsNode = settingsList.item(0);; + processSettings(settingsNode); + + } + + + + /** + * This method process the settings portion + * of the <code>Document</code>. + * + * @param root The root <code>Node</code> of the + * <code>Document</code> we are building. This + * <code>Node</code> should be a TAG_OFFICE_SETTINGS + * tag. + */ + protected void processSettings(Node root) { + + Element configItemSetEntry = (Element) settings.createElement(TAG_CONFIG_ITEM_SET); + configItemSetEntry.setAttribute(ATTRIBUTE_CONFIG_NAME, "view-settings"); + Element configItemMapIndexed = (Element) settings.createElement(TAG_CONFIG_ITEM_MAP_INDEXED); + configItemMapIndexed.setAttribute(ATTRIBUTE_CONFIG_NAME, "Views"); + Element configItemMapEntry = (Element) settings.createElement(TAG_CONFIG_ITEM_MAP_ENTRY); + BookSettings bs = (BookSettings) decoder.getSettings(); + bs.writeNode(settings, configItemMapEntry); + + configItemMapIndexed.appendChild(configItemMapEntry); + configItemSetEntry.appendChild(configItemMapIndexed); + root.appendChild(configItemSetEntry); + } + + /** + * This method process a Name Definition Table and generates a portion + * of the <code>Document</code>. + * + * @param root The root <code>Node</code> of the + * <code>Document</code> we are building. This + * <code>Node</code> should be a TAG_OFFICE_BODY + * tag. + * + * @throws IOException If any I/O error occurs. + */ + protected void processNameDefinition(Node root, Enumeration eNameDefinitions) throws IOException { + + Debug.log(Debug.TRACE, "<NAMED-EXPRESSIONS>"); + + Element namedExpressionsElement = (Element) doc.createElement(TAG_NAMED_EXPRESSIONS); + + while(eNameDefinitions.hasMoreElements()) { + + NameDefinition tableEntry = (NameDefinition) eNameDefinitions.nextElement(); + tableEntry.writeNode(doc, namedExpressionsElement); + } + + root.appendChild(namedExpressionsElement); + + Debug.log(Debug.TRACE, "</NAMED-EXPRESSIONS>"); + } + + /** + * This method process a WorkSheet and generates a portion + * of the <code>Document</code>. A spreadsheet is represented + * as a table Node in StarOffice XML format. + * + * @param root The root <code>Node</code> of the + * <code>Document</code> we are building. This + * <code>Node</code> should be a TAG_OFFICE_BODY + * tag. + * + * @throws IOException If any I/O error occurs. + */ + protected void processTable(Node root) throws IOException { + + Debug.log(Debug.TRACE, "<TABLE>"); + + // Create an element node for the table + Element tableElement = (Element) doc.createElement(TAG_TABLE); + + // Get the sheet name + String sheetName = decoder.getSheetName(); + + // Set the table name attribute + tableElement.setAttribute(ATTRIBUTE_TABLE_NAME, sheetName); + + // TODO - style currently hardcoded - get real value + // Set table style-name attribute + tableElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, "Default"); + + // Append the table element to the root node + root.appendChild(tableElement); + + Debug.log(Debug.TRACE, "<SheetName>" + sheetName + "</SheetName>"); + + // add the various different table-columns + processColumns(tableElement); + + // Get each cell and add to doc + processCells(tableElement); + + Debug.log(Debug.TRACE, "</TABLE>"); + } + + /** + * <p>This method process the cells in a <code>Document</code> + * and generates a portion of the <code>Document</code>.</p> + * + * <p>This method assumes that records are sorted by + * row and then column.</p> + * + * @param root The <code>Node</code> of the <code>Document</code> + * we are building that we will append our cell + * <code>Node</code> objects. This <code>Node</code> + * should be a TAG_TABLE tag. + * + * @throws IOException If any I/O error occurs. + */ + protected void processColumns(Node root) throws IOException { + + for(Enumeration e = decoder.getColumnRowInfos();e.hasMoreElements();) { + + ColumnRowInfo ci = (ColumnRowInfo) e.nextElement(); + if(ci.isColumn()) { + ColumnStyle cStyle = new ColumnStyle("Default",SxcConstants.COLUMN_STYLE_FAMILY, + SxcConstants.DEFAULT_STYLE, ci.getSize(), null); + + Style result[] = (Style[]) styleCat.getMatching(cStyle); + String styleName; + if(result.length==0) { + + cStyle.setName("co" + colStyles++); + styleName = cStyle.getName(); + Debug.log(Debug.TRACE,"No existing style found, adding " + styleName); + styleCat.add(cStyle); + } else { + ColumnStyle existingStyle = (ColumnStyle) result[0]; + styleName = existingStyle.getName(); + Debug.log(Debug.TRACE,"Existing style found : " + styleName); + } + + // Create an element node for the new row + Element colElement = (Element) doc.createElement(TAG_TABLE_COLUMN); + colElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, styleName); + if(ci.getRepeated()!=1) { + String repeatStr = String.valueOf(ci.getRepeated()); + colElement.setAttribute(ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED, repeatStr); + } + root.appendChild(colElement); + } + } + } + + /** + * <p>This method process the cells in a <code>Document</code> + * and generates a portion of the <code>Document</code>.</p> + * + * <p>This method assumes that records are sorted by + * row and then column.</p> + * + * @param root The <code>Node</code> of the <code>Document</code> + * we are building that we will append our cell + * <code>Node</code> objects. This <code>Node</code> + * should be a TAG_TABLE tag. + * + * @throws IOException If any I/O error occurs. + */ + protected void processCells(Node root) throws IOException { + + // The current row element + Element rowElement = null; + + // The current cell element + Element cellElement = null; + + // The row number - we may not have any rows (empty sheet) + // so set to zero. + int row = 0; + + // The column number - This is the expected column number of + // the next cell we are reading. + int col = 1; + + // The number of columns in the spreadsheet + int lastColumn = decoder.getNumberOfColumns(); + + // + Node autoStylesNode = null; + + // Loop over all cells in the spreadsheet + while (decoder.goToNextCell()) { + + // Get the row number + int newRow = decoder.getRowNumber(); + + // Is the cell in a new row, or part of the current row? + if (newRow != row) { + + // Make sure that all the cells in the previous row + // have been entered. + if (col <= lastColumn && rowElement != null) { + int numSkippedCells = lastColumn - col + 1; + addEmptyCells(numSkippedCells, rowElement); + } + + // log an end row - if we already have a row + if (row != 0) { + Debug.log(Debug.TRACE, "</tr>"); + } + + // How far is the new row from the last row? + int deltaRows = newRow - row; + + // Check if we have skipped any rows + if (deltaRows > 1) { + // Add in empty rows + addEmptyRows(deltaRows-1, root, lastColumn); + } + + // Re-initialize column (since we are in a new row) + col = 1; + + // Create an element node for the new row + rowElement = (Element) doc.createElement(TAG_TABLE_ROW); + + + for(Enumeration e = decoder.getColumnRowInfos();e.hasMoreElements();) { + ColumnRowInfo cri = (ColumnRowInfo) e.nextElement(); + if(cri.isRow() && cri.getRepeated()==newRow-1) { + // We have the correct Row BIFFRecord for this row + RowStyle rStyle = new RowStyle("Default",SxcConstants.ROW_STYLE_FAMILY, + SxcConstants.DEFAULT_STYLE, cri.getSize(), null); + + Style result[] = (Style[]) styleCat.getMatching(rStyle); + String styleName; + if(result.length==0) { + + rStyle.setName("ro" + rowStyles++); + styleName = rStyle.getName(); + Debug.log(Debug.TRACE,"No existing style found, adding " + styleName); + styleCat.add(rStyle); + } else { + RowStyle existingStyle = (RowStyle) result[0]; + styleName = existingStyle.getName(); + Debug.log(Debug.TRACE,"Existing style found : " + styleName); + } + rowElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, styleName); + // For now we will not use the repeat column attribute + } + } + + // Append the row element to the root node + root.appendChild(rowElement); + + // Update row number + row = newRow; + + Debug.log(Debug.TRACE, "<tr>"); + } + + // Get the column number of the current cell + int newCol = decoder.getColNumber(); + + // Check to see if some columns were skipped + if (newCol != col) { + + // How many columns have we skipped? + int numColsSkipped = newCol - col; + + addEmptyCells(numColsSkipped, rowElement); + + // Update the column number to account for the + // skipped cells + col = newCol; + } + + // Lets start dealing with the cell data + Debug.log(Debug.TRACE, "<td>"); + + // Get the cell's contents + String cellContents = decoder.getCellContents(); + + // Get the type of the data in the cell + String cellType = decoder.getCellDataType(); + + // Get the cell format + Format fmt = decoder.getCellFormat(); + + // Create an element node for the cell + cellElement = (Element) doc.createElement(TAG_TABLE_CELL); + + Node bodyNode = doc.getElementsByTagName(TAG_OFFICE_BODY).item(0); + + // Not every document has an automatic style tag + autoStylesNode = doc.getElementsByTagName( + TAG_OFFICE_AUTOMATIC_STYLES).item(0); + + if (autoStylesNode == null) { + autoStylesNode = doc.createElement(TAG_OFFICE_AUTOMATIC_STYLES); + doc.insertBefore(autoStylesNode, bodyNode); + } + + CellStyle tStyle = new + CellStyle( "Default",SxcConstants.TABLE_CELL_STYLE_FAMILY, + SxcConstants.DEFAULT_STYLE, fmt, null); + String styleName; + Style result[] = (Style[]) styleCat.getMatching(tStyle); + if(result.length==0) { + + tStyle.setName("ce" + textStyles++); + styleName = tStyle.getName(); + Debug.log(Debug.TRACE,"No existing style found, adding " + styleName); + styleCat.add(tStyle); + } else { + CellStyle existingStyle = (CellStyle) result[0]; + styleName = existingStyle.getName(); + Debug.log(Debug.TRACE,"Existing style found : " + styleName); + } + + cellElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, styleName); + + // Store the cell data into the appropriate attributes + processCellData(cellElement, cellType, cellContents); + + // Append the cell element to the row node + rowElement.appendChild(cellElement); + + // Append the cellContents as a text node + Element textElement = (Element) doc.createElement(TAG_PARAGRAPH); + cellElement.appendChild(textElement); + textElement.appendChild(doc.createTextNode(cellContents)); + + Debug.log(Debug.TRACE, cellContents); + Debug.log(Debug.TRACE, "</td>"); + + // Increment to the column number of the next expected cell + col++; + } + + // Make sure that the last row is padded correctly + if (col <= lastColumn && rowElement != null) { + int numSkippedCells = lastColumn - col + 1; + addEmptyCells(numSkippedCells, rowElement); + } + + // Now write the style catalog to the document + if(autoStylesNode!=null) { + Debug.log(Debug.TRACE,"Well the autostyle node was found!!!"); + NodeList nl = styleCat.writeNode(doc, "dummy").getChildNodes(); + int nlLen = nl.getLength(); // nl.item reduces the length + for (int i = 0; i < nlLen; i++) { + autoStylesNode.appendChild(nl.item(0)); + } + } + + if (row != 0) { + + // The sheet does have rows, so write out a /tr + Debug.log(Debug.TRACE, "</tr>"); + } + } + + + /** + * This method will add empty rows to the <code>Document</code>. + * It is called when the conversion process encounters + * a row (or rows) that do not contain any data in its cells. + * + * @param numEmptyRows The number of empty rows that we + * need to add to the <code>Document</code>. + * @param root The <code>Node</code> of the + * <code>Document</code> we are building + * that we will append our empty row + * <code>Node</code> objects. This + * <code>Node</code> should be a TAG_TABLE + * tag. + * @param numEmptyCells The number of empty cells in the + * empty row. + */ + protected void addEmptyRows(int numEmptyRows, Node root, int numEmptyCells) { + + // Create an element node for the row + Element rowElement = (Element) doc.createElement(TAG_TABLE_ROW); + + // TODO - style currently hardcoded - get real value + // Set row style-name attribute + rowElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, "Default"); + + // Set cell number-rows-repeated attribute + rowElement.setAttribute(ATTRIBUTE_TABLE_NUM_ROWS_REPEATED, + Integer.toString(numEmptyRows)); + + // Append the row element to the root node + root.appendChild(rowElement); + + // Open Office requires the empty row to have an empty cell (or cells) + addEmptyCells(numEmptyCells, rowElement); + + // Write empty rows to the log + for (int i = 0; i < numEmptyRows; i++) { + Debug.log(Debug.TRACE, "<tr />"); + } + + } + + + /** + * This method will add empty cells to the <code>Document</code>. + * It is called when the conversion process encounters a row + * that contains some cells without data. + * + * @param numColsSkipped The number of empty cells + * that we need to add to the + * current row. + * @param row The <code>Node</code> of the + * <code>Document</code> we + * are building that we will + * append our empty cell + * <code>Node</code> objects. + * This <code>Node</code> should + * be a TAG_TABLE_ROW tag. + */ + protected void addEmptyCells(int numColsSkipped, Node row) { + + // Create an empty cellElement + Element cellElement = (Element) doc.createElement(TAG_TABLE_CELL); + + // TODO - style currently hardcoded - get real value + // Set cell style-name attribute + cellElement.setAttribute(ATTRIBUTE_TABLE_STYLE_NAME, "Default"); + + // If we skipped more than 1 cell, we must set the + // appropriate attribute + if (numColsSkipped > 1) { + + // Set cell number-columns-repeated attribute + cellElement.setAttribute(ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED, + Integer.toString(numColsSkipped)); + } + + // Append the empty cell element to the row node + row.appendChild(cellElement); + + // Write empty cells to the log + for (int i = 0; i < numColsSkipped; i++) { + Debug.log(Debug.TRACE, "<td />"); + } + } + + + /** + * This method process the data in a cell and sets + * the appropriate attributes on the cell <code>Element</code>. + * + * @param cellElement A TAG_TABLE_CELL <code>Element</code> + * that we will be adding attributes to + * based on the type of data in the cell. + * @param type The type of data contained in the cell. + * @param contents The contents of the data contained in + * the cell. + */ + protected void processCellData(Element cellElement, String type, + String contents) { + + // Set cell value-type attribute + cellElement.setAttribute(ATTRIBUTE_TABLE_VALUE_TYPE, type); + + // Does the cell contain a formula? + if (contents.startsWith("=")) { + + cellElement.setAttribute(ATTRIBUTE_TABLE_FORMULA, contents); + + cellElement.setAttribute(ATTRIBUTE_TABLE_VALUE, decoder.getCellValue()); + // String data does not require any additional attributes + } else if (!type.equals(CELLTYPE_STRING)) { + + if (type.equals(CELLTYPE_TIME)) { + + // Data returned in StarOffice XML format, so store in + // attribute + cellElement.setAttribute(ATTRIBUTE_TABLE_TIME_VALUE, + contents); + + } else if (type.equals(CELLTYPE_DATE)) { + + // Data returned in StarOffice XML format, so store in + // attribute + cellElement.setAttribute(ATTRIBUTE_TABLE_DATE_VALUE, + contents); + + } else if (type.equals(CELLTYPE_BOOLEAN)) { + + // StarOffice XML format requires stored boolean value + // to be in lower case + cellElement.setAttribute(ATTRIBUTE_TABLE_BOOLEAN_VALUE, + contents.toLowerCase()); + + } else if (type.equals(CELLTYPE_CURRENCY)) { + // TODO - StarOffice XML format requires a correct style to + // display currencies correctly. Need to implement styles. + // TODO - USD is for US currencies. Need to pick up + // the correct currency location from the source file. + cellElement.setAttribute(ATTRIBUTE_TABLE_CURRENCY, "USD"); + + // Data comes stripped of currency symbols + cellElement.setAttribute(ATTRIBUTE_TABLE_VALUE, contents); + + } else if (type.equals(CELLTYPE_PERCENT)) { + // Data comes stripped of percent signs + cellElement.setAttribute(ATTRIBUTE_TABLE_VALUE, contents); + + } else { + // Remaining data types use table-value attribute + + cellElement.setAttribute(ATTRIBUTE_TABLE_VALUE, contents); + } + } + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentSerializer.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentSerializer.java new file mode 100644 index 000000000000..9e0d30831d24 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcDocumentSerializer.java @@ -0,0 +1,992 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.awt.Color; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import java.io.IOException; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentSerializer; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocument; +import org.openoffice.xmerge.converter.xml.ParaStyle; +import org.openoffice.xmerge.converter.xml.sxc.CellStyle; +import org.openoffice.xmerge.converter.xml.StyleCatalog; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.XmlUtil; + +/** + * <p>General spreadsheet implementation of <code>DocumentSerializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcPluginFactory + * SxcPluginFactory}. Used with SXC <code>Document</code> objects.</p> + * + * <p>The <code>serialize</code> method traverses the DOM + * <code>Document</code> from the given <code>Document</code> object. + * It uses a <code>DocEncoder</code> object for the actual conversion + * of contents to the device spreadsheet format.</p> + * + * @author Paul Rank + * @author Mark Murnane + */ +public abstract class SxcDocumentSerializer implements OfficeConstants, + DocumentSerializer { + + /** The cell foreground <code>Color</code>. */ + private Color foreground = Color.black; + + /** The cell background <code>Color</code>. */ + private Color background = Color.white; + + /** The cell format. */ + private long format = 0; + + /** <code>Format</code> object describing the cell. */ + private Format fmt = null; + + /** The row number. */ + private int rowID = 1; + + /** The column number. */ + private int colID = 1; + + /** The number of times the current row is repeated. */ + private int rowsRepeated = 1; + + /** The number of times the current column is repeated. */ + private int colsRepeated = 1; + + /** The number of times the current column is repeated. */ + private StyleCatalog styleCat = null; + /** + * An array of column widths of the current worksheet. Width is + * measured in number of characters. + */ + private Vector ColumnRowList; + + /** Width, in characters, of the current cell display data. */ + private int displayWidth = 0; + + /** + * A <code>SpreadsheetEncoder</code> object for encoding to + * appropriate format. + */ + protected SpreadsheetEncoder encoder = null; + + /** <code>SxcDocument</code> object that this converter processes. */ + protected SxcDocument sxcDoc = null; + + + /** + * Constructor. + * + * @param document Input <code>SxcDocument</code> + * <code>Document</code>. + */ + public SxcDocumentSerializer(Document document) { + fmt = new Format(); + sxcDoc = (SxcDocument) document; + } + + + /** + * <p>Method to convert a DOM <code>Document</code> into + * "Device" <code>Document</code> objects.</p> + * + * <p>This method is not thread safe for performance reasons. + * This method should not be called from within two threads. + * It would be best to call this method only once per object + * instance.</p> + * + * @return <code>ConvertData</code> containing "Device" + * <code>Document</code> objects. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public abstract ConvertData serialize() throws ConvertException, + IOException; + + + /** + * This method traverses <i>office:settings</i> <code>Element</code>. + * + * @param node <i>office:settings</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + public void traverseSettings(Node node) throws IOException { + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_CONFIG_ITEM_SET)) { + + traverseSettings(child); + + } else if (nodeName.equals(TAG_CONFIG_ITEM_MAP_INDEXED)) { + + traverseSettings(child); + + } else if (nodeName.equals(TAG_CONFIG_ITEM_MAP_ENTRY)) { + + BookSettings bs = new BookSettings(child); + encoder.addSettings(bs); + + } else { + + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + } + + /* + * Handles the loading of defined styles from the style.xml file as well + * as automatic styles from the content.xml file. + * + * Any change to a defined style, such as a short bold section, falls into + * the latter category. + */ + protected void loadStyles(SxcDocument sxcDoc) { + + org.w3c.dom.Document contentDom = sxcDoc.getContentDOM(); + + styleCat = new StyleCatalog(25); + + NodeList nl = null; + String families[] = new String[] { SxcConstants.COLUMN_STYLE_FAMILY, + SxcConstants.ROW_STYLE_FAMILY, + SxcConstants.TABLE_CELL_STYLE_FAMILY }; + Class classes[] = new Class[] { ColumnStyle.class, + RowStyle.class, + CellStyle.class}; + + /* + * Process the content XML for any other style info. + * Should only be automatic types here. + */ + nl = contentDom.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + if (nl.getLength() != 0) { + styleCat.add(nl.item(0), families, classes, null, false); + } + } + + /** + * This method traverses <i>office:body</i> <code>Element</code>. + * + * @param node <i>office:body</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseBody(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"); + Debug.log(Debug.TRACE, "<DEBUGLOG>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + Node searchNode = nodeList.item(i); + if (searchNode.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = searchNode.getNodeName(); + + if (nodeName.equals(TAG_NAMED_EXPRESSIONS)) { + + traverseNamedExpressions(searchNode); + + } else { + + Debug.log(Debug.TRACE, "Skipping " + XmlUtil.getNodeInfo(searchNode) + " />"); + } + } + } + + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_TABLE)) { + + traverseTable(child); + + } else { + + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + Debug.log(Debug.TRACE, "</DEBUGLOG>"); + } + + + /** + * This method traverses the <i>table:table</i> element + * <code>Node</code>. + * + * @param node A <i>table:table</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseNamedExpressions(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<NAMED:EXPRESSIONS>"); + + NamedNodeMap att = node.getAttributes(); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + NameDefinition nd = new NameDefinition(child); + encoder.setNameDefinition(nd); + } + } + } + + Debug.log(Debug.TRACE, "</NAMED:EXPRESSIONS>"); + } + + /** + * This method traverses the <i>table:table</i> element + * <code>Node</code>. + * + * @param node A <i>table:table</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseTable(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<TABLE>"); + + ColumnRowList = new Vector(); + + // Get table attributes + // TODO - extract style from attribute + + NamedNodeMap att = node.getAttributes(); + + String tableName = + att.getNamedItem(ATTRIBUTE_TABLE_NAME).getNodeValue(); + + rowID = 1; + + encoder.createWorksheet(tableName); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_TABLE_ROW)) { + // TODO - handle all the possible rows + // spelled out in the entities + + traverseTableRow(child); + + } else if (nodeName.equals(TAG_TABLE_COLUMN)) { + + traverseTableColumn(child); + + } else if (nodeName.equals(TAG_TABLE_SCENARIO)) { + + // TODO + + } else { + + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + // Add column width info to the current sheet + encoder.setColumnRows(ColumnRowList); + + Debug.log(Debug.TRACE, "</TABLE>"); + } + + /** + * This method traverses the <i>table:table-row</i> element + * <code>Node</code>. + * + * @param node A <i>table:table-row</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseTableRow(Node node) throws IOException { + + // Get the attributes of the row + NamedNodeMap cellAtt = node.getAttributes(); + + if (cellAtt != null) { + + Node rowStyle = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_STYLE_NAME); + + Node tableNumRowRepeatingNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_NUM_ROWS_REPEATED); + int repeatedRows = 1; + + if(tableNumRowRepeatingNode!=null) { + String repeatStr = tableNumRowRepeatingNode.getNodeValue(); + Debug.log(Debug.TRACE, "traverseTableRow() repeated-rows : " + repeatStr); + repeatedRows = Integer.parseInt(repeatStr); + } + + String styleName = new String(""); + + if ( rowStyle != null) { + styleName = rowStyle.getNodeValue(); + } + if(styleName.equalsIgnoreCase("Default") || styleName.length()==0) { + + Debug.log(Debug.TRACE, "No defined Row Style Attribute was found"); + + } else { + + RowStyle rStyle = ( RowStyle)styleCat.lookup(styleName, + SxcConstants.ROW_STYLE_FAMILY, null, + RowStyle.class); + + int rowHeight = rStyle.getRowHeight(); + + Debug.log(Debug.TRACE, "traverseTableRow() Row Height : " + rowHeight); + ColumnRowInfo ri = new ColumnRowInfo( rowHeight, + repeatedRows, + ColumnRowInfo.ROW, + rowHeight!=0); + ColumnRowList.add(ri); + } + + // Get the attribute representing the number of rows repeated + Node rowsRepeatedNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_NUM_ROWS_REPEATED); + + // There is a number of rows repeated attribute: + if (rowsRepeatedNode != null) { + + // Get the number of times the row is repeated + String rowsRepeatedString = rowsRepeatedNode.getNodeValue(); + + Integer rowsRepeatedInt = new Integer(rowsRepeatedString); + + rowsRepeated = rowsRepeatedInt.intValue(); + + } else { + + // The row is not repeated + rowsRepeated = 1; + } + } + + Debug.log(Debug.TRACE, "<TR>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_TABLE_CELL)) { + + traverseCell(child); + + } else { + + Debug.log(Debug.TRACE, "<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + // Increase the row counter by the number of rows which are repeated + rowID += rowsRepeated; + + // Re-initialize number of rows repeated before processing the next + // row data. + rowsRepeated = 1; + + // When starting a new row, set the column counter back to the + // first column. + colID = 1; + + // Re-initialize number of columns repeated before processing + // the next row data. + colsRepeated = 1; + + Debug.log(Debug.TRACE, "</TR>"); + } + + + /** + * This method traverses the <i>table:table-column</i> + * <code>Node</code>. Not yet implemented. + * + * @param node A <i>table:table-column</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseTableColumn(Node node) throws IOException { + + Debug.log(Debug.TRACE, "traverseColumn() : "); + NamedNodeMap cellAtt = node.getAttributes(); + Node tableStyleNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_STYLE_NAME); + Node tableNumColRepeatingNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED); + Node tableDefaultCellStyle = cellAtt.getNamedItem(ATTRIBUTE_DEFAULT_CELL_STYLE); + + int repeatedColumns = 1; + int columnWidth = 0; + ColumnRowInfo col = new ColumnRowInfo(ColumnRowInfo.COLUMN); + + if(tableNumColRepeatingNode!=null) { + Debug.log(Debug.TRACE, "traverseColumn() repeated-cols : " + tableNumColRepeatingNode.getNodeValue()); + repeatedColumns = Integer.parseInt(tableNumColRepeatingNode.getNodeValue()); + col.setRepeated(repeatedColumns); + } + + String cellStyleName = new String(""); + + if(tableDefaultCellStyle!=null) { + cellStyleName = tableDefaultCellStyle.getNodeValue(); + + Debug.log(Debug.TRACE, "traverseColumn() default-cell-style : " + cellStyleName); + } + + if(cellStyleName.equalsIgnoreCase("Default") || cellStyleName.length()==0) { + + Debug.log(Debug.TRACE, "No default cell Style Attribute was found"); + + } else { + + CellStyle cellStyle = (CellStyle)styleCat.lookup(cellStyleName, + SxcConstants.TABLE_CELL_STYLE_FAMILY, null, + CellStyle.class); + Format defaultFmt = new Format(cellStyle.getFormat()); + col.setFormat(defaultFmt); + } + + String styleName = new String(""); + + if(tableStyleNode!=null) { + styleName = tableStyleNode.getNodeValue(); + } + + if(styleName.equalsIgnoreCase("Default") || styleName.length()==0) { + + Debug.log(Debug.TRACE, "No defined Style Attribute was found"); + + } else { + + ColumnStyle cStyle = (ColumnStyle)styleCat.lookup(styleName, + SxcConstants.COLUMN_STYLE_FAMILY, null, + ColumnStyle.class); + + columnWidth = cStyle.getColWidth(); + col.setSize(columnWidth); + Debug.log(Debug.TRACE, "traverseColumn() Column Width : " + columnWidth); + + } + ColumnRowList.add(col); + } + + /** + * This method traverses a <i>table:table-cell</i> element + * <code>Node</code>. + * + * @param node a <i>table:table-cell</i> <code>Node</code>. + * + * @throws IOException if any I/O error occurs. + */ + protected void traverseCell(Node node) throws IOException { + + NamedNodeMap cellAtt = node.getAttributes(); + + int debug_i=0; + Node debug_attrib = null; + fmt.clearFormatting(); + if (cellAtt == null || cellAtt.item(0) == null) + { + Debug.log(Debug.INFO, "No Cell Attributes\n"); + // return; + } + else + { + while ((debug_attrib = cellAtt.item(debug_i++)) != null) + { + Debug.log(Debug.INFO, "Cell Attribute " + debug_i + + ": " + debug_attrib.getNodeName() + " : " + + debug_attrib.getNodeValue() + "\n"); + } + } + + // Get the type of data in the cell + Node tableValueTypeNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_VALUE_TYPE); + + // Get the number of columns this cell is repeated + Node colsRepeatedNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED); + + // Get the style type + Node tableStyleNode = + cellAtt.getNamedItem(ATTRIBUTE_TABLE_STYLE_NAME); + + String styleName = new String(""); + + if(tableStyleNode!=null) { + styleName = tableStyleNode.getNodeValue(); + } + + if(styleName.equalsIgnoreCase("Default")) { + + Debug.log(Debug.TRACE, "No defined Style Attribute was found"); + + } else if(styleName.length()!=0) { + + CellStyle cStyle = (CellStyle)styleCat.lookup(styleName, + SxcConstants.TABLE_CELL_STYLE_FAMILY, null, + CellStyle.class); + + Format definedFormat = cStyle.getFormat(); + fmt = new Format(definedFormat); + } + + // There is a number of cols repeated attribute + if (colsRepeatedNode != null) { + + // Get the number of times the cell is repeated + String colsRepeatedString = colsRepeatedNode.getNodeValue(); + + Integer colsRepeatedInt = new Integer(colsRepeatedString); + colsRepeated = colsRepeatedInt.intValue(); + } else { + + // The cell is not repeated + colsRepeated = 1; + } + + + // if there is no style we need to check to see if there is a default + // cell style defined in the table-column's + + if (fmt.isDefault() && styleName.length()==0) { + int index = 1; + for(Enumeration e = ColumnRowList.elements();e.hasMoreElements();) { + ColumnRowInfo cri = (ColumnRowInfo) e.nextElement(); + if(cri.isColumn()) { + if(colID>=index && colID<(index+cri.getRepeated())) { + fmt = new Format(cri.getFormat()); + } + index += cri.getRepeated(); + } + } + } + + + // for (int j = 0; j < colsRepeated; j++) { + + + if (tableValueTypeNode != null) { + + // Make sure we initialize to 0 the width of the current cell + displayWidth = 0; + + String cellType = + tableValueTypeNode.getNodeValue(); + + if (cellType.equalsIgnoreCase(CELLTYPE_STRING)) { + + // has text:p tag + fmt.setCategory(CELLTYPE_STRING); + Node tableStringValueNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_STRING_VALUE); + Debug.log(Debug.TRACE,"Cell Type String : " + tableStringValueNode); + if(tableStringValueNode != null) { + fmt.setValue(tableStringValueNode.getNodeValue()); + } + + } else if (cellType.equalsIgnoreCase(CELLTYPE_FLOAT)) { + + // has table:value attribute + // has text:p tag + + // Determine the number of decimal places StarCalc + // is displaying for this floating point output. + fmt.setCategory(CELLTYPE_FLOAT); + fmt.setDecimalPlaces(getDecimalPlaces(node)); + Node tableValueNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_VALUE); + fmt.setValue(tableValueNode.getNodeValue()); + + + } else if (cellType.equalsIgnoreCase(CELLTYPE_TIME)) { + + // has table:time-value attribute + // has text:p tag - which is the value we convert + + fmt.setCategory(CELLTYPE_TIME); + Node tableTimeNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_TIME_VALUE); + fmt.setValue(tableTimeNode.getNodeValue()); + + } else if (cellType.equalsIgnoreCase(CELLTYPE_DATE)) { + + // has table:date-value attribute + // has text:p tag - which is the value we convert + + fmt.setCategory(CELLTYPE_DATE); + Node tableDateNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_DATE_VALUE); + fmt.setValue(tableDateNode.getNodeValue()); + + } else if (cellType.equalsIgnoreCase(CELLTYPE_CURRENCY)) { + + // has table:currency + // has table:value attribute + // has text:p tag + + fmt.setCategory(CELLTYPE_CURRENCY); + fmt.setDecimalPlaces(getDecimalPlaces(node)); + Node tableValueNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_VALUE); + fmt.setValue(tableValueNode.getNodeValue()); + + } else if (cellType.equalsIgnoreCase(CELLTYPE_BOOLEAN)) { + + // has table:boolean-value attribute + // has text:p tag - which is the value we convert + + fmt.setCategory(CELLTYPE_BOOLEAN); + Node tableBooleanNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_BOOLEAN_VALUE); + fmt.setValue(tableBooleanNode.getNodeValue()); + + } else if (cellType.equalsIgnoreCase(CELLTYPE_PERCENT)) { + + // has table:value attribute + // has text:p tag + + fmt.setCategory(CELLTYPE_PERCENT); + fmt.setDecimalPlaces(getDecimalPlaces(node)); + Node tableValueNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_VALUE); + fmt.setValue(tableValueNode.getNodeValue()); + + } else { + + Debug.log(Debug.TRACE,"No defined value type" + cellType); + // Should never get here + + } + } + + Node tableFormulaNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_FORMULA); + + if(tableFormulaNode != null) + { + if(tableValueTypeNode == null) { // If there is no value-type Node we must assume string-value + fmt.setCategory(CELLTYPE_STRING); + Node tableStringValueNode = cellAtt.getNamedItem(ATTRIBUTE_TABLE_STRING_VALUE); + fmt.setValue(tableStringValueNode.getNodeValue()); + } + String cellFormula = tableFormulaNode.getNodeValue(); + addCell(cellFormula); + } else { + + // Text node, Date node, or Time node + // + Debug.log(Debug.INFO, + "TextNode, DateNode, TimeNode or BooleanNode\n"); + // This handles the case where we have style information but no content + if (node.hasChildNodes()) { + NodeList childList = node.getChildNodes(); + int len = childList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = childList.item(i); + if (child.getNodeType() == Node.ELEMENT_NODE) { + String childName = child.getNodeName(); + if (childName.equals(TAG_PARAGRAPH)) { + traverseParagraph(child); + } + } + } + } else if(!fmt.isDefault()) { + addCell(""); + } + } + + // Clear out format for current cell after it is written + format = 0; + + // Increase the column counter by the number of times the + // last cell was repeated. + colID += colsRepeated; + + // Re-initialize the number of columns repeated before processing + // the next cell data. + colsRepeated = 1; + + } + + + /** + * This method traverses the <i>text:p</i> element <code>Node</code>. + * + * @param node A <i>text:p</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void traverseParagraph(Node node) throws IOException { + + NamedNodeMap cellAtt = node.getAttributes(); + + int debug_i=0; + Node debug_attrib = null; + if (cellAtt == null || cellAtt.item(0) == null) + { + Debug.log(Debug.INFO, "No Paragraph Attributes\n"); + } + else + { + while ((debug_attrib = cellAtt.item(debug_i++)) != null) + { + Debug.log(Debug.INFO, "Paragraph Attribute " + debug_i + + ": " + debug_attrib.getNodeName() + " : " + + debug_attrib.getNodeValue() + "\n"); + } + } + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + + int len = nodeList.getLength(); + + StringBuffer buffer = new StringBuffer(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + // TODO: need to handle space/tabs/newline nodes later + short nodeType = child.getNodeType(); + + switch (nodeType) { + + case Node.TEXT_NODE: + buffer.append(child.getNodeValue()); + break; + + case Node.ENTITY_REFERENCE_NODE: + + NodeList nodeList2 = child.getChildNodes(); + int len2 = nodeList2.getLength(); + + for (int j = 0; j < len2; j++) { + Node child2 = nodeList2.item(j); + + if (child2.getNodeType() == Node.TEXT_NODE) { + buffer.append(child2.getNodeValue()); + } + } + + break; + } + } + + String s = buffer.toString(); + // displayWidth = calculateContentWidth(s); + addCell(s); + + } + } + + + /** + * This method will take the input cell value and add + * it to the spreadsheet <code>Document</code> we are currently + * encoding. This method correctly handles cells that are + * repeated in either the row, cell, or both directions. + * + * @param cellValue The contents of the cell we want to add + * to the spreadsheet <code>Document</code>. + * + * @throws IOException If any I/O error occurs. + */ + protected void addCell(String cellValue) throws IOException { + + int col = colID; + int row = rowID; + + for (int i = 0; i < rowsRepeated; i++) { + + // Log the columns when there are rowsRepeated. + if (i > 0) { + Debug.log(Debug.TRACE, "</TR>"); + Debug.log(Debug.TRACE, "<TR>"); + } + + col = colID; + + for (int j = 0; j < colsRepeated; j++) { + + Debug.log(Debug.TRACE, "<TD>"); + + + // Add the cell data to the encoded spreadsheet document + encoder.addCell(row, col, fmt, cellValue); + + Debug.log(Debug.TRACE, cellValue); + Debug.log(Debug.TRACE, "</TD>"); + + col++; + } + + row++; + + } + + } + + + + /** + * This method takes a <i>table:table-cell</i> <code>Node</code> + * and traverses down to the <i>text:p</i> tag. The value is + * extracted from the <i>text:p</i> tag and the number of decimal + * places is calculated. + * + * @param node A <i>table:table-cell</i> <code>Node</code>. + * + * @return The number of decimal places in the display + * string of the data in the input <code>Node</code>. + */ + protected int getDecimalPlaces(Node node) { + + int decimals = 0; + + Element element = null; + + // cast org.w3c.dom.Node to org.w3c.dom.Element + if (node instanceof Element) { + element = (Element) node; + } else { + return decimals; + } + + // Traverse to the text:p element, there should only be one. + NodeList list = element.getElementsByTagName(TAG_PARAGRAPH); + + if (list.getLength() != 1) { + return decimals; + } + + Node paragraph = list.item(0); + + if (paragraph.hasChildNodes()) { + + NodeList nodeList = paragraph.getChildNodes(); + + int len = nodeList.getLength(); + + for (int j = 0; j < len; j++) { + + Node child = nodeList.item(j); + + if (child.getNodeType() == Node.TEXT_NODE) { + + String s = child.getNodeValue(); + + // displayWidth = calculateContentWidth(s); + + int k = s.lastIndexOf("."); + if (k > 0) { + s = s.substring(k+1); + decimals = s.length(); + } + } + } + } + + return decimals; + } + + /* + * Utility method to retrieve a Node attribute. + */ + private String getAttribute (Node node, String attribute) { + NamedNodeMap attrNodes = node.getAttributes(); + + if (attrNodes != null) { + Node attr = attrNodes.getNamedItem(attribute); + if (attr != null) { + return attr.getNodeValue(); + } + } + return null; + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcPluginFactory.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcPluginFactory.java new file mode 100644 index 000000000000..4bdaad8e009c --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/SxcPluginFactory.java @@ -0,0 +1,83 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc; + +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.registry.ConverterInfo; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.PluginFactory; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentMergerFactory; + + +/** + * General implementation of the <code>PluginFactory</code> interface + * for SXC <code>Document</code> objects. + * + * @see org.openoffice.xmerge.DocumentDeserializer + * @see org.openoffice.xmerge.DocumentMerger + * @see org.openoffice.xmerge.DocumentSerializer + */ +public abstract class SxcPluginFactory + extends PluginFactory implements DocumentMergerFactory { + + + /** + * Constructor that caches the <code>ConvertInfo</code> that + * corresponds to the registry information for this plug-in. + * + * @param ci <code>ConvertInfo</code> object. + */ + public SxcPluginFactory(ConverterInfo ci) { + super(ci); + } + + + public Document createOfficeDocument(String name, InputStream is) + throws IOException { + + // read zipped XML stream + // + SxcDocument doc = new SxcDocument(name); + doc.read(is); + return doc; + } + + public Document createOfficeDocument(String name, InputStream is,boolean isZip) + throws IOException { + + // read zipped XML stream + // + SxcDocument doc = new SxcDocument(name); + doc.read(is,isZip); + return doc; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/build.xml new file mode 100644 index 000000000000..5805a5253993 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/build.xml @@ -0,0 +1,143 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcx_sxc" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcx_sxc"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxc"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/CellStyle.java"/> + <include name="${package}/ColumnStyle.java"/> + <include name="${package}/ColumnRowInfo.java"/> + <include name="${package}/RowStyle.java"/> + <include name="${package}/SxcConstants.java"/> + <include name="${package}/SxcDocument.java"/> + <include name="${package}/Format.java"/> + <include name="${package}/BookSettings.java"/> + <include name="${package}/SheetSettings.java"/> + <include name="${package}/NameDefinition.java"/> + <include name="${package}/SpreadsheetDecoder.java"/> + <include name="${package}/SpreadsheetEncoder.java"/> + <include name="${package}/SxcDocumentDeserializer.java"/> + <include name="${package}/SxcDocumentSerializer.java"/> + <include name="${package}/DocumentMergerImpl.java"/> + <include name="${package}/SxcPluginFactory.java"/> + + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/makefile.mk new file mode 100644 index 000000000000..abc309279f0f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcx_sxc +PRJ=../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..07b0c751b93d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/ConverterCapabilitiesImpl.java @@ -0,0 +1,113 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + + +/** + * <p>MiniCalc implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxc.minicalc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarCalc SXC to/from MiniCalc conversions. The + * <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE_ROW.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE_COLUMN.equals(tag)) + return false; + // TODO - we currently do not handle the table column tag + else if (OfficeConstants.TAG_TABLE_SCENARIO.equals(tag)) + return false; + // TODO - we currently do not handle the table scenario tag + else if (OfficeConstants.TAG_TABLE_CELL.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_TABLE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_NAME.equals(attribute)) + return true; + + } else if (OfficeConstants.TAG_TABLE_CELL.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_VALUE_TYPE.equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_FORMULA. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_VALUE.equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_BOOLEAN_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_CURRENCY. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_TIME_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_DATE_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED. + equals(attribute)) + return true; + + } else if (OfficeConstants.TAG_TABLE_ROW.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_NUM_ROWS_REPEATED. + equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcConstants.java new file mode 100644 index 000000000000..07530013ea84 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcConstants.java @@ -0,0 +1,45 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import org.openoffice.xmerge.converter.palm.PdbUtil; + +/** + * Constants used for encoding and decoding the MiniCalc format. + * + * @author Herbie Ong + */ +interface MinicalcConstants { + + /** Creator ID. */ + public static final int CREATOR_ID = PdbUtil.intID("PiMC"); + + /** Type ID. */ + public static final int TYPE_ID = PdbUtil.intID("Data"); +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDataString.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDataString.java new file mode 100644 index 000000000000..140dfde1881b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDataString.java @@ -0,0 +1,545 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +/** + * This class is used by <code>MinicalcDecoder</code> to manipulate a + * <code>String</code> containing MiniCalc cell data. + * + * @author Paul Rank + */ +public class MinicalcDataString { + + /** The String representation of the MiniCalc data. */ + private String data = null; + + + /** + * Constructor stores the MiniCalc data <code>String</code>. + * + * @param data A <code>String</code> containing MiniCalc + * cell data. + */ + public MinicalcDataString(String data) { + this.data = data; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a <i>formula</i>. + * + * @return true if the MiniCalc data <code>String</code> is a + * <i>formula</i>, false if the MiniCalc data <code>String</code> + * is not a <i>formula</i>. + */ + public boolean isFormula() { + + if (data.startsWith("=")) { + return true; + } + + return false; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a <i>percentage</i>. + * + * @return true if the MiniCalc data <code>String</code> is a + * <i>percentage</i>, false if the MiniCalc data + * <code>String</code> is not a <i>percentage</i>. + */ + public boolean isPercent() { + + if (data.endsWith("%")) { + return true; + } + + return false; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a + * <i>boolean</i> value. + * + * @return true if the MiniCalc data <code>String</code> is + * a <i>boolean</i>, false if the MiniCalc data + * <code>String</code> is not a <i>boolean</i>. + */ + public boolean isBoolean() { + + if (data.equalsIgnoreCase("false") || + data.equalsIgnoreCase("true")) { + return true; + } + + return false; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a <i>date</i>. + * + * @return true if the MiniCalc data <code>String</code> is + * a <i>date</i>, false if the MiniCalc data <code>String</code> + * is not a <i>date</i>. + */ + public boolean isDate() { + + // Starting index into the date string - month + int start = 0; + + // Search for "/", which separates month from day + int end = data.indexOf("/"); + + // Separator was found + if (end > 0) { + + String monthString = data.substring(start, end); + + try { + Float f = Float.valueOf(monthString); + if ((f.intValue() < 0) || (f.intValue() > 12)) { + return false; + } + } + catch (NumberFormatException e) { + + // no, it is not a currency type + return false; + } + + // start is now the starting index of day + start = end+1; + + // Search for "/", which separates day from year + end = data.indexOf("/", start); + + // Separator was found + if (end > 0) { + + String dayString = data.substring(start, end); + + try { + Float f = Float.valueOf(dayString); + if ((f.intValue() < 0) || (f.intValue() > 31)) + return false; + } + catch (NumberFormatException e) { + // no, it is not a currency type + return false; + } + } else { + return false; + } + + // start is now at the starting index of the year + start = end + 1; + + String yearString = data.substring(start); + try { + Float f = Float.valueOf(yearString); + if (f.intValue() < 0) { + return false; + } + } + catch (NumberFormatException e) { + // no, it is not a currency type + return false; + } + + } else { + return false; + } + + return true; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a <i>time</i>. + * + * @return true if the MiniCalc data <code>String</code> + * is a <i>time</i>, false if the MiniCalc data + * <code>String</code> is not a <i>time</i>. + */ + public boolean isTime() { + + // Starting index into the time string - hour + int start = 0; + + // Search for ":", which separates hour from minute + int end = data.indexOf(":"); + + + // Separator was found + if (end > 0) { + + String hourString = data.substring(start, end); + try { + Float f = Float.valueOf(hourString); + if ((f.intValue() < 0) || (f.intValue() > 24)) + return false; + } + catch (NumberFormatException e) { + // no, it is not a time type + return false; + } + + // start is now the starting index of minute + start = end+1; + + // Search for ":", which separates minute from second + end = data.indexOf(":", start); + + // Separator was found + if (end > 0) { + + String minuteString = data.substring(start, end); + + try { + Float f = Float.valueOf(minuteString); + if ((f.intValue() < 0) || (f.intValue() > 60)) + return false; + } + catch (NumberFormatException e) { + // no, it is not a time type + return false; + } + + // start is now at the starting index of the seconds + start = end+1; + + // The seconds are in the string + if (data.length() > start) { + + String secondString = data.substring(start); + + + try { + Float f = Float.valueOf(secondString); + if ((f.intValue() < 0) || (f.intValue() > 60)) + return false; + } + catch (NumberFormatException e) { + // no, it is not a time type + return false; + } + } + + } + + return true; + + } + + return false; + } + + + /** + * Checks if the MiniCalc data <code>String</code> is a <i>currency</i> + * value. + * + * @return true if the MiniCalc data <code>String</code> is + * a <i>currency</i>, false if the MiniCalc data + * <code>String</code> is not a <i>currency</i>. + */ + public boolean isCurrency() { + + boolean result = false; + + // TODO - we currently only check for US currencies + + if (data.endsWith("$")) { + String number = data.substring(0, data.length()-1); + try { + Float f = Float.valueOf(number); + result = true; + } + catch (NumberFormatException e) { + // no, it is not a currency type + result = false; + } + } + + else if (data.startsWith("$")) { + String number = data.substring(1, data.length()); + try { + Float f = Float.valueOf(number); + result = true; + } + catch (NumberFormatException e) { + // no, it is not a currency type + result = false; + } + } + + return result; + + } + + + /** + * This method removes the percent sign from the MiniCalc data + * <code>String</code>. If the percent sign is not the last + * character of the MiniCalc data <code>String</code>, the + * MiniCalc data <code>String</code> is returned. + * + * @return The MiniCalc data <code>String</code> minus the + * percent sign. If the MiniCalc data <code>String</code> + * does not begin with a percent sign, the MiniCalc data + * <code>String</code> is returned. + */ + public String percentRemoveSign() { + + String number = data; + + if (data.endsWith("%")) { + // "%" is the last character, so remove + number = data.substring(0, data.length()-1); + + try { + Float f = Float.valueOf(number); + float f1 = f.floatValue()/100f; + Float f2 = new Float(f1); + number = f2.toString(); + } + catch (NumberFormatException e) { + // no, it is not a float type + } + } + + return number; + } + + + /** + * This method removes the currency sign from the MiniCalc data + * <code>String</code>. If the currency sign is not the first or + * last character of the MiniCalc data <code>String</code>, the + * MiniCalc data <code>String</code> is returned. + * + * @return The MiniCalc data <code>String</code> minus the currency + * sign. If the MiniCalc data <code>String</code> does not + * begin or end with a currency sign, the MiniCalc + * data <code>String</code> is returned. + */ + public String currencyRemoveSign() { + + String number = data; + + // TODO - only works with US currencies + + if (data.endsWith("$")) { + + number = data.substring(0, data.length()-1); + + } else if (data.startsWith("$")) { + + number = data.substring(1, data.length()); + } + + return number; + + } + + + /** + * <p>This method converts a MiniCalc date from MiniCalc + * format to StarOffice XML format.</p> + * + * <p>MiniCalc format:</p> + * + * <p><blockquote> + * MM/DD/YY or MM/DD/YYYY + * </blockquote></p> + * + * <p>StarOffice XML format:</p> + * + * <p><blockquote> + * YYYY-MM-DD + * </blockquote></p> + * + * @return The MiniCalc date converted to StarOffice XML + * format. + */ + public String convertToStarDate() { + + // The output date string + String out; + + String monthString = "01"; + String dayString = "01"; + String yearString = "1900"; + + // Starting index into the date string - month + int start = 0; + + // Search for "/", which separates month from day + int end = data.indexOf("/"); + + // Separator was found + if (end > 0) { + + monthString = data.substring(start, end); + + Integer monthInt = new Integer(monthString); + + // Make sure month is 2 digits + if (monthInt.intValue() < 10) { + monthString = "0" + monthString; + } + + // start is now the starting index of day + start = end+1; + + // Search for "/", which separates day from year + end = data.indexOf("/", start); + + // Separator was found + if (end > 0) { + + dayString = data.substring(start, end); + + Integer dayInt = new Integer(dayString); + + // Make sure day is 2 digits + if (dayInt.intValue() < 10) { + dayString = "0" + dayString; + } + + // start is now at the starting index of the year + start = end + 1; + + // The year is in the string + if (data.length() > start) { + + yearString = data.substring(start); + + Integer yearInt = new Integer(yearString); + int year = yearInt.intValue(); + + if (year < 31) { + + // MiniCalc years between 0 and 30 correspond to + // 2000 - 2030 + year += 2000; + + } else if (year < 100) { + + // MiniCalc years between 31 and 99 correspond + // to 1931 - 1999 + year += 1900; + } + + yearString = Integer.toString(year); + } + } + } + + // Set out to StarOffice XML date format + out = yearString + "-" + monthString + "-" + dayString; + + return out; + } + + + /** + * This method converts the MiniCalc time from MiniCalc + * format to StarOffice XML format. + * + * <p>MiniCalc format:</p> + * + * <p><blockquote> + * hh:mm:ss + * </blockquote></p> + * + * <p>StarOffice XML format:</p> + * + * <p><blockquote> + * PThhHmmMssS + * </blockquote></p> + * + * @return The MiniCalc time converted to StarOffice XML + * format. + */ + public String convertToStarTime() { + + // The output time string + String out; + + String hourString = "00"; + String minuteString = "00"; + String secondString = "00"; + + // Starting index into the time string - hour + int start = 0; + + // Search for ":", which separates hour from minute + int end = data.indexOf(":"); + + // Separator was found + if (end > 0) { + + hourString = data.substring(start, end); + + // start is now the starting index of minute + start = end+1; + + // Search for ":", which separates minute from second + end = data.indexOf(":", start); + + // Separator was found + if (end > 0) { + + minuteString = data.substring(start, end); + + // start is now at the starting index of the seconds + start = end+1; + + // The seconds are in the string + if (data.length() > start) { + + secondString = data.substring(start); + } + + } + } + + // TODO - PT is for pacific time, where can we get the + // localized value from? + + // Set to StarOffice XML time format + out = "PT"+hourString+"H"+minuteString+"M"+secondString+"S"; + + return out; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDecoder.java new file mode 100644 index 000000000000..a165a25f9fbf --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcDecoder.java @@ -0,0 +1,744 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import jmc.Workbook; +import jmc.Worksheet; +import jmc.CellAttributes; +import jmc.CellDescriptor; +import jmc.JMCconstants; +import jmc.JMCException; + +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.DataOutputStream; +import java.io.IOException; +import java.io.InputStream; +import java.util.Enumeration; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializer; +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetDecoder; +import org.openoffice.xmerge.converter.xml.sxc.Format; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializerImpl} + * SxcDocumentDeserializerImpl} to decode the MiniCalc format. + * + * @author Paul Rank + */ +final class MinicalcDecoder extends SpreadsheetDecoder { + + /** MiniCalc WorkBook to store sheets. */ + private Workbook wb; + + /** MiniCalc sheet - only one sheet can be open at a time. */ + private Worksheet ws; + + /** The current cell - only one cell can be active at a time. */ + private CellDescriptor cell = null; + + /** Format object describing the current cell. */ + private Format fmt = null; + + /** The password for the WorkBook. */ + private String password = null; + + /** The number of rows in the current WorkSheet. */ + private int maxRows = 0; + + /** The number of columns in the current WorkSheet. */ + private int maxCols = 0; + + /** The names of the worksheets. */ + private String[] worksheetNames = null; + + /** + * Constructor creates a MiniCalc WorkBook. + * + * @param name The name of the WorkBook. + * @param password The password for the workBook. + * + * @throws IOException If any I/O error occurs. + */ + MinicalcDecoder(String name, String[] worksheetNames, String password) throws IOException { + + super(name, password); + + fmt = new Format(); + + this.password = password; + this.worksheetNames = worksheetNames; + + try { + + wb = new Workbook(name, password); + + } + catch (JMCException e) { + + Debug.log(Debug.ERROR, "MinicalcDecoder.constructor:" + e.getMessage()); + + throw new IOException(e.getMessage()); + // e.printStackTrace(); + + } + } + + + /** + * This method takes a <code>ConvertData</code> as input and + * converts it into a MiniCalc WorkSheet. The WorkSheet is then + * added to the WorkBook. + * + * @param InputStream An <code>ConvertData</code> containing a + * MiniCalc WorkSheet. + * + * @throws IOException If any I/O error occurs. + */ + public void addDeviceContent(ConvertData cd) throws IOException { + + try { + PalmDocument palmDoc; + int j = 0; + + Enumeration e = cd.getDocumentEnumeration(); + while(e.hasMoreElements()) { + + palmDoc = (PalmDocument) e.nextElement(); + // Convert PDB to WorkBook/WorkSheet format + PalmDB pdb = palmDoc.getPdb(); + + // This will be done at least once + String sheetName = worksheetNames[j]; + + // Get number of records in the pdb + int numRecords = pdb.getRecordCount(); + + // sheetName does not contain the WorkBook name, but we need the + // full name. + String fullSheetName = new String(wb.getWorkbookName() + "-" + sheetName); + + // Create a new (empty) WorkSheet + ws = new Worksheet(); + + // Initialize the WorkSheet + ws.initWorksheet(fullSheetName, numRecords); + + // Loop over the number of records in the PDB + for (int i = 0; i < numRecords; i++) { + + // Read record i from the PDB + Record rec = pdb.getRecord(i); + + byte cBytes[] = rec.getBytes(); + + // Create an InputStream + ByteArrayInputStream bis = new ByteArrayInputStream(cBytes); + + // Get the size of the stream + int bisSize = cBytes.length; + + // Add each record to the WorkSheet + ws.readNextRecord(bis, bisSize); + } + + + // Add the WorkSheet to the WorkBook + wb.addWorksheet(ws); + j++; + } + } + catch (JMCException e) { + + Debug.log(Debug.ERROR, "MinicalcDecoder.addPDB:" + e.getMessage()); + + throw new IOException(e.getMessage()); + } + } + + + /** + * This method returns the number of spreadsheets + * stored in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public int getNumberOfSheets() { + + return wb.getNumberOfSheets(); + } + + + /** + * This method gets the requested WorkSheet from the + * WorkBook and sets it as the selected WorkSheet. All + * other "get" methods will now get data from this WorkSheet. + * + * @param sheetIndex The index number of the sheet to open. + * + * @throws IOException If any I/O error occurs. + */ + public void setWorksheet(int sheetIndex) throws IOException { + + try { + + ws = wb.getWorksheet(sheetIndex); + + // Initialize access to the WorkSheet so that we can calculate + // the number of rows and columns + ws.initAccess(password); + + maxRows = 0; + maxCols = 0; + + while (goToNextCell()) { + maxRows = Math.max(maxRows, cell.getRowNumber()); + maxCols = Math.max(maxCols, cell.getColNumber()); + } + + // Re-initialize access to the WorkSheet + ws.initAccess(password); + + } + catch (JMCException e) { + + Debug.log(Debug.ERROR, "MinicalcDecoder.setWorksheet:" + e.getMessage()); + + throw new IOException(e.getMessage()); + // e.printStackTrace(); + + } + } + + + /** + * This method returns the name of the current spreadsheet. + * + * @return The name of the current WorkSheet. + */ + public String getSheetName() { + + String sheetName = ws.getName(); + + return sheetName; + } + + + /** + * This method gets the next cell from the WorkSheet + * and sets it as the selected cell. All other "get" + * methods will now get data from this cell. + * + * @return True if we were able to go to another cell + * in the sheet, false if there were no cells + * left. + * + * @throws IOException If any I/O error occurs. + */ + public boolean goToNextCell() throws IOException { + + boolean gotCell = false; + + try { + cell = ws.getNextCell(); + + if (cell != null) { + gotCell = true; + } + + // As we read each cell, get its formatting info + readCellFormat(); + } + catch (JMCException e) { + + Debug.log(Debug.ERROR, "MinicalcDecoder.goToNextCell:" + e.getMessage()); + + throw new IOException(e.getMessage()); + // e.printStackTrace(); + + } + + return gotCell; + } + + + /** + * This method returns the row number of the current cell. + * + * @return The row number of the current cell. Returns + * -1 if no cell is currently selected. + */ + public int getRowNumber() { + + int row = -1; + + if (cell != null) { + + row = cell.getRowNumber(); + } + + return row; + } + + /** + * This method returns the number of rows in the current sheet. + * + * @return The number of rows in the current sheet. + */ + public int getNumberOfRows() { + + return maxRows; + } + + /** + * This method returns the number of columns in the current sheet. + * + * @return The number of columns in the current sheet. + */ + public int getNumberOfColumns() { + return maxCols; + } + + + /** + * This method returns the col number of the current cell. + * + * @return The col number of the current cell. Returns + * -1 if no cell is currently selected. + */ + public int getColNumber() { + + int col = -1; + + if (cell != null) { + + col = cell.getColNumber(); + } + + return col; + } + + + /** + * This method returns the contents of the current cell. + * + * @return The contents of the current cell. Returns + * null if no cell is currently selected. + */ + public String getCellContents() { + + String contents = null; + + if (cell != null) { + contents = cell.getCellContents(); + + // Active cell, but no content + if (contents == null) + return new String(""); + + // Does the cell contain a formula? + if (contents.startsWith("=")) { + contents = parseFormula(contents); + } + // Make sure that any MiniCalc peculiarities are stripped off + if (fmt.getCategory().equalsIgnoreCase(OfficeConstants.CELLTYPE_CURRENCY)) { + contents = currencyRemoveSign(contents); + } + else if (fmt.getCategory().equalsIgnoreCase(OfficeConstants.CELLTYPE_PERCENT)) { + contents = percentRemoveSign(contents); + } + else if (fmt.getCategory().equalsIgnoreCase(OfficeConstants.CELLTYPE_DATE)) { + contents = convertToStarDate(contents); + } + else if (fmt.getCategory().equalsIgnoreCase(OfficeConstants.CELLTYPE_TIME)) { + contents = convertToStarTime(contents); + } + } + + return contents; + } + + /** + * This method is meant to return the value of the formula cell. However + * in minicalc this value is not used so hence the stubbed function + * + * @return the value fo the formula cell + */ + public String getCellValue() { + return null; + } + + /** + * <p>This method takes a formula and parses it into + * StarOffice XML formula format.</p> + * + * <p>Many spreadsheets use ',' as a separator. + * StarOffice XML format uses ';' as a separator instead.</p> + * + * <p>Many spreadsheets use '!' as a separator when refencing + * a cell in a different sheet.</p> + * + * <blockquote> + * Example: =sheet1!A1 + * </blockquote> + * + * <p>StarOffice XML format uses '.' as a separator instead.</p> + * + * <blockquote> + * Example: =sheet1.A1 + * </blockquote> + * + * @param formula A formula string. + * + * @return A StarOffice XML format formula string. + */ + protected String parseFormula(String formula) { + + formula = formula.replace(',', ';'); + formula = formula.replace('!', '.'); + + return formula; + } + + /** + * <p>This method returns the type of the data in the current cell.</p> + * + * <p>Possible Data Types:</p> + * + * <ul><li> + * Percent - MiniCalc can store as a number or as a string. + * + * When stored as a string, the % sign is stored in the + * string . The MiniCalc format is "string". + * Example 10.1% is stored as the string "10.1%" + * + * When stored as a number, the decimal representation + * is stored. The MiniCalc format is "percentage". + * Example: 10.1% is stored as "0.101" + * </li><li> + * Currency - MiniCalc stores currency as a number with the format + * set to "currency". + * A user can also enter a value with a dollar sign + * (example $18.56) into MiniCalc and not set the format + * as currency. We treat this type of data as a + * currency data type. + * </li><li> + * Boolean - MiniCalc stores in a string as "true" or "false" + * </li><li> + * + * Date - MiniCalc stores a date in a string as either + * MM/DD/YY or MM/DD/YYYY. Any variation from the above + * format will not be considered a date. + * </li><li> + * Time - MiniCalc stores a time in a string as hh:mm:ss. Any + * variation from this format will not be considered a time. + * </li><li> + * Float - MiniCalc stores as a number and it is not percent + * or currency. + * </li><li> + * String - MiniCalc stores as a string (surprise). Doesn't parse + * to any of the other data types. + * </li><li> + * @return The type of the data in the current cell. + * </li></ul> + */ + public String getCellDataType() { + + boolean isNumber = false; + + // Get format value set on the cell in MiniCalc + String format = getCellFormatType(); + + // Initialize the data type to the format + String type = format; + + String contents = getCellContents(); + + if (contents != null) { + + MinicalcDataString data = new MinicalcDataString(contents); + + // Check if it is a formula + if (data.isFormula()) { + Debug.log(Debug.INFO, " " + contents + " Is a Function Format = " + + format + "\n"); + return type; + } + + try { + // Check to see if it is a number + Double d = Double.valueOf(contents); + isNumber = true; + Debug.log(Debug.INFO, " " + contents + " Is a Number Format = " + format); + + } catch (NumberFormatException e) { + Debug.log(Debug.INFO, " " + contents + " Not a Number Format= " + format); + // no, it is not a number + isNumber = false; + } + + + if (isNumber) { + + // Numbers are Float, Currency, and Percent + if (format.equals(OfficeConstants.CELLTYPE_CURRENCY)) { + + type = OfficeConstants.CELLTYPE_CURRENCY; + + } else if (format.equals(OfficeConstants.CELLTYPE_PERCENT)) { + + type = OfficeConstants.CELLTYPE_PERCENT; + + } else { + + type = OfficeConstants.CELLTYPE_FLOAT; + } + + } else if (data.isBoolean()) { + + // Data is a Boolean type + type = OfficeConstants.CELLTYPE_BOOLEAN; + + } else if (data.isDate()) { + + // Data is a Date type + type = OfficeConstants.CELLTYPE_DATE; + + } else if (data.isTime()) { + + // Data is a Time type + type = OfficeConstants.CELLTYPE_TIME; + + } else if (data.isPercent()) { + + // Data is percent + type = OfficeConstants.CELLTYPE_PERCENT; + + } else if (data.isCurrency()) { + + // Data is a Currency type + type = OfficeConstants.CELLTYPE_CURRENCY; + + } else { + + // Data can't be float, since it isn't a number + + // We've already tried parsing it as all other data + // types, the only remaining option is a string + type = OfficeConstants.CELLTYPE_STRING; + } + } + + Debug.log(Debug.INFO, " TYPE = " + type + "\n"); + + return type; + } + + + /** + * This method returns the format of the data in the current cell. + * + * @return The format of the data in the current cell. + */ + String getCellFormatType() { + + // Set type to default data type + String type = OfficeConstants.CELLTYPE_FLOAT; + + if (cell != null) { + + // Get the attributes for the current cell + CellAttributes att = cell.getCellAttributes(); + + if (att != null) { + + // Extract the format info from the attributes + long format = att.getFormat(); + + // The cell type is stored in bits 5-8 + long cellType = format & 0x000000F0L; + + // The number of decimal places is stored in bits 1-4 + long decimals = format & 0x0000000FL; + + if (cellType == JMCconstants.FF_FORMAT_GENERIC) { + + // MiniCalc stores both Strings and Booleans + // in the generic type. We must check the contents + // to differentiate between the two. + + // Get cell's contents + String contents = getCellContents(); + + if (contents.equalsIgnoreCase("false") || + contents.equalsIgnoreCase("true")) { + + type = OfficeConstants.CELLTYPE_BOOLEAN; + + + } else { + + type = OfficeConstants.CELLTYPE_STRING; + + } + + } else if (cellType == JMCconstants.FF_FORMAT_DECIMAL) { + + type = OfficeConstants.CELLTYPE_FLOAT; + + } else if (cellType == JMCconstants.FF_FORMAT_TIME) { + + type = OfficeConstants.CELLTYPE_TIME; + + } else if (cellType == JMCconstants.FF_FORMAT_DATE) { + + type = OfficeConstants.CELLTYPE_DATE; + + } else if (cellType == JMCconstants.FF_FORMAT_CURRENCY) { + + type = OfficeConstants.CELLTYPE_CURRENCY; + + } else if (cellType == JMCconstants.FF_FORMAT_PERCENT) { + + type = OfficeConstants.CELLTYPE_PERCENT; + } + + } + } + + return type; + } + + + /** + * This method takes a <code>String</code> that contains a + * currency value and removes the $ from the <code>String</code>. + * If the dollar sign is not the first or last character of the + * input <code>String</code>, the input <code>String</code> is + * simply returned. + * + * @param contents The input <code>String</code> from which to + * remove the dollar sign. + * + * @return The input <code>String</code> minus the dollar sign. + * If the input <code>String</code> did not begin or end + * with a dollar sign, contents is returned. + */ + private String currencyRemoveSign(String contents) { + MinicalcDataString mcString = new MinicalcDataString(contents); + String currencyString = mcString.currencyRemoveSign(); + return currencyString; + } + + + /** + * This method takes a <code>String</code> that contains a percent + * value and removes the % from the <code>String</code>. If the + * percent sign is not the last character of the input + * <code>String</code>, the input <code>String</code> is simply + * returned. + * + * @param contents The input String from which to remove the + * percent sign. + * + * @return The input <code>String</code> minus the percent sign. + * If the input <code>String</code> did not begin with + * a percent sign, contents is returned. + */ + private String percentRemoveSign(String contents) { + MinicalcDataString mcString = new MinicalcDataString(contents); + String percentString = mcString.percentRemoveSign(); + return percentString; + } + + + /** + * This method returns takes a <code>String</code> that contains + * a time value and converts it from MiniCalc format to StarOffice + * XML time format. + * + * @param contents The input <code>String</code> containing a + * MiniCalc time. + * + * @return The input <code>String</code> converted to StarOffice + * XML time format. + */ + private String convertToStarTime(String contents) { + MinicalcDataString mcString = new MinicalcDataString(contents); + String timeString = mcString.convertToStarTime(); + return timeString; + } + + /** + * This method returns takes a <code>String</code> that contains + * a date value and converts it from MiniCalc format to StarOffice + * XML date format. + * + * @param contents The input <code>String</code> containing a + * MiniCalc date. + * + * @return The input <code>String</code> converted to StarOffice + * XML date format. + */ + private String convertToStarDate(String contents) { + MinicalcDataString mcString = new MinicalcDataString(contents); + String dateString = mcString.convertToStarDate(); + return dateString; + } + + + /** + * Return the Format object describing the active cell formatting. + * + * @return The Format object describing the active cell formatting. + */ + public Format getCellFormat() { + return new Format(fmt); + } + + + /** + * Create the format data for the new cell. + */ + private void readCellFormat() { + // Make sure there are no remnants from the last time + fmt.clearFormatting(); + + fmt.setCategory(getCellFormatType()); + + // TODO - Get any more formatting data here + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcEncoder.java new file mode 100644 index 000000000000..70014a8af93e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/MinicalcEncoder.java @@ -0,0 +1,582 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import jmc.Workbook; +import jmc.Worksheet; +import jmc.CellAttributes; +import jmc.CellDescriptor; +import jmc.JMCconstants; +import jmc.JMCException; + +import java.awt.Color; + +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.DataOutputStream; +import java.io.IOException; + +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.IntArrayList; + +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetEncoder; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocumentSerializerImpl + * SxcDocumentSerializerImpl} to encode the MiniCalc format. + * + * @author Paul Rank + */ +final class MinicalcEncoder extends SpreadsheetEncoder { + + /** MiniCalc WorkBook to store sheets. */ + private Workbook wb; + + /** MiniCalc sheet - only one sheet can be open at a time. */ + private Worksheet ws; + + /** + * Estimate of the number of Palm pixels per character. Used for + * estimating the width of a cell on a Palm device. + */ + private final static int pixelsPerChar = 6; + + /** + * The minimum width (in pixels) that we allow a column to be set to + * on a Palm device. + */ + private final static int minWidth = 10; + + /** + * The maximum width (in pixels) that we allow a column to be set to + * on a Palm device. + */ + private final static int maxWidth = 80; + + + /** + * Constructor creates a MiniCalc WorkBook. + * + * @param log Log object for logging. + * @param name The name of the WorkBook. + * @param password The password for the WorkBook. + * + * @throws IOException If any I/O error occurs. + */ + MinicalcEncoder(String name, String password) throws IOException { + + super(name, password); + + try { + wb = new Workbook(name, password); + } + catch (JMCException e) { + Debug.log(Debug.ERROR, "new Workbook threw exception:" + e.getMessage()); + throw new IOException(e.getMessage()); + } + } + + + /** + * This method creates a WorkSheet belonging to the + * WorkBook. + * + * @param sheetName The name of the WorkSheet. + * + * @throws IOException If any I/O error occurs. + */ + public void createWorksheet(String sheetName) throws IOException { + + try { + ws = wb.createWorksheet(sheetName); + } + catch (JMCException e) { + Debug.log(Debug.ERROR, "wb.createWorksheet threw exception:" + e.getMessage()); + throw new IOException(e.getMessage()); + } + } + + + /** + * This method gets the number of sheets in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public int getNumberOfSheets() { + + int numSheets = wb.getNumberOfSheets(); + return numSheets; + } + + + /** + * This method encodes the MiniCalc WorkBook information + * into an palm <code>Record</code> array in MiniCalc + * database format. + * + * @return Array of <code>Record</code> holding MiniCalc + * contents. + * + * @throws IOException If any I/O error occurs. + */ + public Record[] getRecords(int sheetID) throws IOException { + + // Get the WorkSheet for the input sheetID + ws = wb.getWorksheet(sheetID); + + // Need to call ws.initWrite() before we start querying the WorkSheet + try { + ws.initWrite(); + } + catch (JMCException e) { + Debug.log(Debug.ERROR, "ws.initWrite in getRecords:" + e.getMessage()); + throw new IOException(e.getMessage()); + } + + // Get the number of records in the WorkSheet + int numRecords = ws.getNumberOfRecords(); + + // Create the Record array + Record[] allRecords = new Record[numRecords]; + + + // Get each record from the WorkSheet and store in allRecords[] + try { + for (int i = 0; i < allRecords.length; i++) { + + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + + int length = ws.writeNextRecord(bos); + + byte cBytes[] = bos.toByteArray(); + + allRecords[i] = new Record(cBytes); + } + } + catch (Exception e) { + Debug.log(Debug.ERROR, "ws.writeNextRecord in getRecords:" + e.getMessage()); + throw new IOException(e.getMessage()); + } + + return allRecords; + } + + + /** + * A cell reference in a StarOffice formula looks like + * [.C2] (for cell C2). MiniCalc is expecting cell references + * to look like C2. This method strips out the braces and + * the period. + * + * @param formula A StarOffice formula <code>String</code>. + * + * @return A MiniCalc formula <code>String</code>. + */ + protected String parseFormula(String formula) { + + StringBuffer inFormula = new StringBuffer(formula); + StringBuffer outFormula = new StringBuffer(); + + boolean inBrace = false; + boolean firstCharAfterBrace = false; + boolean firstCharAfterColon = false; + + int len = inFormula.length(); + + for (int in = 0; in < len; in++) { + switch (inFormula.charAt(in)) { + case '[': + // We are now inside a StarOffice cell reference. + // We also need to strip out the '[' + inBrace = true; + + // If the next character is a '.', we want to strip it out + firstCharAfterBrace = true; + break; + + case ']': + // We are exiting a StarOffice cell reference + // We are stripping out the ']' + inBrace = false; + break; + + case ':': + // We have a cell range reference. + // May need to strip out the leading '.' + if (inBrace) + firstCharAfterColon = true; + outFormula.append(inFormula.charAt(in)); + break; + + case '.': + if (inBrace == true) { + if (firstCharAfterBrace == false && + firstCharAfterColon == false) { + // Not the first character after the open brace. + // We have hit a separator between a sheet reference + // and a cell reference. MiniCalc uses a ! as + // this type of separator. + outFormula.append('!'); + } + else { + firstCharAfterBrace = false; + firstCharAfterColon = false; + // Since we are in a StarOffice cell reference, + // and we are the first character, we need to + // strip out the '.' + } + break; + } else { + // We hit valid data, lets add it to the formula string + outFormula.append(inFormula.charAt(in)); + break; + } + + case ';': + // StarOffice XML format uses ';' as a separator. MiniCalc (and + // many spreadsheets) use ',' as a separator instead. + outFormula.append(','); + break; + + default: + // We hit valid data, lets add it to the formula string + outFormula.append(inFormula.charAt(in)); + + // Need to make sure that firstCharAfterBrace is not true. + firstCharAfterBrace = false; + break; + } + } + + return outFormula.toString(); + } + + /** + * Add a cell to the current WorkSheet. + * + * @param row The row number of the cell. + * @param column The column number of the cell. + * @param fmt The <code>Format</code> object describing + * the appearance of this cell. + * @param cellContents The text or formula of the cell's contents. + * + * @throws IOException If any I/O error occurs. + */ + public void addCell(int row, int column, Format fmt, String cellContents) throws IOException { + + CellAttributes ca = new CellAttributes(getFormat(fmt), + fmt.getForeground(), + fmt.getBackground()); + if (cellContents.startsWith("=")) { + cellContents = parseFormula(cellContents); + Debug.log(Debug.INFO, "YAHOO Found Formula" + cellContents); + } + + CellDescriptor cellDes = new CellDescriptor(row, column, ca, cellContents); + + try { + ws.putCell(cellDes); + } + catch (JMCException jmce) { + Debug.log(Debug.ERROR, "ws.putCell threw exception: " + jmce.getMessage()); + throw new IOException(jmce.getMessage()); + } + } + + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public void setColumnWidths(IntArrayList columnWidths) throws IOException { + // Get the number of columns + int numColumns = columnWidths.size(); + + // Return if there are no columns in the listr + if (numColumns == 0) { + return; + } + + // Need to set the FORM_FLAGS_NONDEFAULT flag for the column widths + // to be used in MiniCalc + long format = JMCconstants.FORM_FLAGS_NONDEFAULT; + + CellAttributes ca = new CellAttributes(format); + + try { + for (int i = 0; i < numColumns; i++) { + // Get the column width in Palm pixels + int width = columnWidths.get(i) * pixelsPerChar; + + // Check limits on column width + if (width < minWidth) { + width = minWidth; + } else if (width > maxWidth) { + width = maxWidth; + } + + // Add the column descriptor to the WorkSheet + ws.putColumn(i + 1, width, ca); + } + } + catch (JMCException jmce) { + Debug.log(Debug.ERROR, "ws.putColumn threw exception: " + jmce.getMessage()); + throw new IOException(jmce.getMessage()); + } + } + + + /** + * This method sets the format of a cell to <i>string</i>. + * + * @param format The cell format-may already contain display info, + * such as alignment or font type. + * + * @return The updated format of the cell. + */ + private long setFormatString(long format) { + + format = clearCellFormatType(format); + + // Set format to generic, since MiniCalc does not have a string type. + format = format | JMCconstants.FF_FORMAT_GENERIC; + + return format; + } + + + /** + * This method sets the format of a cell to <i>floating point</i>. + * + * @param format The cell format. May already contain + * display info, such as alignment or + * font type. + * @param decimalPlaces The number of decimal places to + * set in the floating point number. + * + * @return The updated format of the cell. + */ + private long setFormatFloat(long format, int decimalPlaces) { + + format = clearCellFormatType(format); + + // Set format to floating point with correct number of decimal places + format = format | JMCconstants.FF_FORMAT_DECIMAL | decimalPlaces; + + return format; + } + + + /** + * This method sets the format of a cell to <i>time</i>. + * + * @param format The cell format-may already contain display info, + * such as alignment or font type. + * + * @return The updated format of the cell. + */ + private long setFormatTime(long format) { + + format = clearCellFormatType(format); + + // Set format to time. + format = format | JMCconstants.FF_FORMAT_TIME; + + return format; + } + + + /** + * This method sets the format of a cell to <i>date</i>. + * + * @param format The cell format-may already contain display info, + * such as alignment or font type. + * + * @return The updated format of the cell. + */ + private long setFormatDate(long format) { + + format = clearCellFormatType(format); + + // Set format to date. + format = format | JMCconstants.FF_FORMAT_DATE; + + return format; + } + + + /** + * This method sets the format of a cell to <i>currency</i>. + * + * @param format The cell format-may already contain + * display info, such as alignment or + * font type. + * @param decimalPlaces The number of decimal places to set. + * + * @return The updated format of the cell. + */ + private long setFormatCurrency(long format, int decimalPlaces) { + + format = clearCellFormatType(format); + + // Set format to Currency with correct number of decimal places + format = format | JMCconstants.FF_FORMAT_CURRENCY | decimalPlaces; + + return format; + } + + + /** + * This method sets the format of a cell to <i>boolean</i>. + * + * @param format The cell format-may already contain display info, + * such as alignment or font type. + * + * @return The updated format of the cell. + */ + private long setFormatBoolean(long format) { + + format = clearCellFormatType(format); + + // Set format to generic, since MiniCalc does not have a Boolean type. + format = format | JMCconstants.FF_FORMAT_GENERIC; + + return format; + } + + + /** + * This method sets the format of a cell to <i>percent</i>. + * + * @param format The cell format-may already contain + * display info, such as alignment or + * font type. + * @param decimalPlaces The number of decimal places to set. + * + * @return The updated format of the cell. + */ + private long setFormatPercent(long format, int decimalPlaces) { + + format = clearCellFormatType(format); + + // Set format to Percent with correct number of decimal places + format = format | JMCconstants.FF_FORMAT_PERCENT | decimalPlaces; + + return format; + } + + + /** + * This method clears out the format bits associated with + * the type of data (<i>float</i>, <i>time</i>, etc...) in + * a cell. + * + * @param format The original format for the cell. + * + * @return The updated cell format with the bits associated + * with the type of data (float, time, etc...) + * zeroed out. + */ + private long clearCellFormatType(long format) { + + // First 4 bits are for the number of decimal places + // bits 5-8 are for the data format (float, time, etc...) + + // Clear out first 8 bits + format = format & 0xFFFFFFFFFFFFFF00L; + + return format; + } + + + /** + * Set a cell's formatting options via a separately create + * <code>Format</code> object. + * + * @param row The row number of the cell to be changed. + * @param column The column number of the cell to be changed. + * @param fmt Object containing formatting settings for + * this cell. + */ + public void setCellFormat(int row, int column, Format fmt) { + } + + + /** + * Get the names of the sheets in the WorkBook. + * + * @param sheet The required sheet. + */ + public String getSheetName(int sheet) { + return wb.getWorksheet(sheet).getName(); + } + + + /* + * This method returns a MiniCalc style format from the + * <code>Format</code> object. + */ + private long getFormat(Format fmt) + { + String category = fmt.getCategory(); + + if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_BOOLEAN)) { + return setFormatBoolean(0); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_CURRENCY)) { + return setFormatCurrency(0, fmt.getDecimalPlaces()); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_DATE)) { + return setFormatDate(0); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_FLOAT)) { + return setFormatFloat(0, fmt.getDecimalPlaces()); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_PERCENT)) { + return setFormatPercent(0, fmt.getDecimalPlaces()); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_STRING)) { + return setFormatString(0); + } + else if (category.equalsIgnoreCase(OfficeConstants.CELLTYPE_TIME)) { + return setFormatTime(0); + } + else { + // Should never get here, but just in case + System.out.println("XXXXX Formatting information not found"); + return 0; + } + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/PluginFactoryImpl.java new file mode 100644 index 000000000000..82f39a8e60aa --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/PluginFactoryImpl.java @@ -0,0 +1,129 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxc.DocumentMergerImpl; +import org.openoffice.xmerge.converter.xml.sxc.SxcPluginFactory; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.registry.ConverterInfo; +import java.io.IOException; +import java.io.InputStream; + +/** + * <p>MiniCalc implementation of the <code>PluginFactory</code>. + * This encapsulates conversion of StarCalc XML format to and from + * MiniCalc format.</p> + * + * <p>The superclass produces a particular + * {@link org.openoffice.xmerge.Document Document} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocument + * SxcDocument} that the converters in this class works with. Thus, + * this class only implements the methods that produces the converters, + * i.e. {@link + * org.openoffice.xmerge.DocumentSerializer + * DocumentSerializer} and {@link + * org.openoffice.xmerge.DocumentDeserializer + * DocumentDeserializer}; + * as well as the {@link + * org.openoffice.xmerge.ConverterCapabilities + * ConverterCapabilities} object that is specific to this format + * conversion. That superclass also produces a {@link + * org.openoffice.xmerge.DocumentMerger DocumentMerger} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxc.DocumentMergerImpl + * DocumentMergerImpl} which this class derives the functionality.</p> + */ +public final class PluginFactoryImpl extends SxcPluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory { + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + public PluginFactoryImpl(ConverterInfo ci) { + super(ci); + } + + + /** + * Returns an instance of <code>DocumentSerializerImpl</code>, + * which is an implementation of <code>DocumentSerializer</code> + * interface. + * + * @param doc <code>Document</code> object to be + * converted/serialized. + * + * @return A <code>DocumentSerializerImpl</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + + return new SxcDocumentSerializerImpl(doc); + } + + + /** + * Returns an instance of <code>DocumentDeserializerImpl</code>, + * which is an implementation of <code>DocumentDeserializer</code> + * interface. + * + * @param cd <code>ConvertData</code> object for reading data + * which will be converted back to a + * <code>Document</code> object. + * + * @return A <code>DocumentDeserializerImpl</code> object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + + return new SxcDocumentDeserializerImpl(cd); + } + + + public Document createDeviceDocument(String name, InputStream is) + throws IOException { + + PalmDocument palmDoc = new PalmDocument(is); + return palmDoc; + } + + public DocumentMerger createDocumentMerger(Document doc) { + + DocumentMergerImpl merger = new DocumentMergerImpl(doc, converterCap); + return merger; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentDeserializerImpl.java new file mode 100644 index 000000000000..db3bcdeb91c5 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentDeserializerImpl.java @@ -0,0 +1,138 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializer; +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetDecoder; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.converter.palm.PalmDocument; + +import java.io.IOException; +import java.util.Enumeration; + +/** + * <p>MiniCalc implementation of <code>DocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.minicalc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts a set of files in MiniCalc PDB format to a StarOffice DOM.</p> + * + * @author Mark Murnane + */ +public final class SxcDocumentDeserializerImpl extends SxcDocumentDeserializer { + + /** + * Creates new <code>SxcDocumentDeserializerImpl</code>. + * + * @param cd <code>ConvertData</code> Input data to convert. + */ + public SxcDocumentDeserializerImpl(ConvertData cd) { + super(cd); + } + + + /** + * This method will be implemented by concrete subclasses and will + * return an application-specific decoder. + * + * @param workbook The WorkBook name. + * @param worksheetNames An array of WorkSheet names. + * @param password The password. + * + * @return An application-specific <code>SpreadsheetDecoder</code>. + */ + public SpreadsheetDecoder createDecoder(String workbook, + String[] worksheetNames, String password) throws IOException { + + return new MinicalcDecoder(workbook, worksheetNames, password); + } + + + /** + * This method will return the name of the WorkBook from the + * <code>ConvertData</code>. Allows for situations where the + * WorkBook name differs from the PDB name. + * + * Implemented in the Deserializer as the Decoder's constructor + * requires a name. + * + * @param cd The <code>ConvertData</code>. + * + * @return The name of the WorkBook. + */ + protected String getWorkbookName(ConvertData cd) + throws IOException { + + Enumeration e = cd.getDocumentEnumeration(); + PalmDocument palmDoc = (PalmDocument) e.nextElement(); + String workbookName = palmDoc.getName(); + + // Search for "-", which separates workbook from worksheet + int end = workbookName.indexOf("-"); + + if (end > 0) { + workbookName = workbookName.substring(0, end); + } + + return workbookName; + } + + + /** + * This method will return an array of WorkSheet names from the + * <code>ConvertData</code>. + * + * @param cd The <code>ConvertData</code>. + * + * @return The name of the WorkSheet. + */ + protected String[] getWorksheetNames(ConvertData cd) + throws IOException { + int numberOfPDBs = cd.getNumDocuments(); + String worksheetName[] = new String[numberOfPDBs]; + int i=0; + Enumeration e = cd.getDocumentEnumeration(); + while (e.hasMoreElements()) { + PalmDocument palmDoc = (PalmDocument) e.nextElement(); + worksheetName[i] = palmDoc.getName(); + + // Search for the "-", which seperates workbook from worksheet + int start = worksheetName[i].indexOf("-"); + + if (start != -1) { + worksheetName[i] = worksheetName[i].substring(start + 1); + } + i++; + } + + return worksheetName; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentSerializerImpl.java new file mode 100644 index 000000000000..1c1c8fe2e6bd --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/SxcDocumentSerializerImpl.java @@ -0,0 +1,141 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.minicalc; + +import java.awt.Color; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import java.io.IOException; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PalmDocument; + +import jmc.JMCconstants; + +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentSerializer; + +/** + * <p>MiniCalc implementation of <code>SxcDocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.minicalc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts StarOffice XML format to a set of files in + * MiniCalc PDB format.</p> + * + * @author Paul Rank + * @author Mark Murnane + */ +public final class SxcDocumentSerializerImpl extends SxcDocumentSerializer { + + + /** + * Constructor. + * + * @param document The <code>Document</code> to convert. + */ + public SxcDocumentSerializerImpl(Document document) { + super(document); + } + + + public ConvertData serialize() throws ConvertException, IOException { + + + // Get the server side document name. This value should not + // contain a path or the file extension. + String docName = sxcDoc.getName(); + + // TODO - get real values for password when implemnted in XML + // Passwords are not currently stored in StarCalc XML format. + String password = null; + + encoder = new MinicalcEncoder(docName, password); + + // get dom document + org.w3c.dom.Document domDoc = sxcDoc.getContentDOM(); + + // Traverse to the office:body element. + // There should only be one. + NodeList list = domDoc.getElementsByTagName(TAG_OFFICE_BODY); + int len = list.getLength(); + + if (len > 0) { + Node node = list.item(0); + traverseBody(node); + } + + // Get the number of sheets in the workbook + // This will equal the number of PDBs we need + ConvertData cd = new ConvertData(); + int numSheets = encoder.getNumberOfSheets(); + + for (int i = 0; i < numSheets; i++) { + + // Get records for sheet i + Record records[] = ((MinicalcEncoder) encoder).getRecords(i); + + // Get the sheet name for sheet i + String fullSheetName = new String(docName + + "-" + + encoder.getSheetName(i)); + + // Create a PalmDB object + PalmDocument palmDoc = new PalmDocument(fullSheetName, + MinicalcConstants.CREATOR_ID, + MinicalcConstants.TYPE_ID, JMCconstants.AppVersion, + PalmDB.PDB_HEADER_ATTR_BACKUP, records); + + cd.addDocument(palmDoc); + } + + + // OutputStream os = new FileOutputStream(docName); + + //pdbSet.write(os); + //os.flush(); + + //ConvertDataEntry cde = new ConvertDataOutputStream(os, docName); + //cd.addCDE(cde); + + return cd; + } + + + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/build.xml new file mode 100644 index 000000000000..6a4092250009 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/build.xml @@ -0,0 +1,135 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxs_minicalc" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxs_minicalc"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxc/minicalc"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + <pathelement location="${solar.jar}/jmc.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/MinicalcConstants.java"/> + <include name="${package}/MinicalcDecoder.java"/> + <include name="${package}/MinicalcEncoder.java"/> + <include name="${package}/MinicalcDataString.java"/> + <include name="${package}/SxcDocumentDeserializerImpl.java"/> + <include name="${package}/SxcDocumentSerializerImpl.java"/> + <include name="${package}/ConverterCapabilitiesImpl.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/converter.xml new file mode 100644 index 000000000000..39b28ffbf944 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/converter.xml @@ -0,0 +1,43 @@ +<?xml version="1.0"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<converters> + <converter type="staroffice/sxc" version="1.0"> + <converter-display-name> + Minicalc 6.4 + </converter-display-name> + <converter-description> + StarCalc XML to/from Minicalc 6.4 conversion + </converter-description> + <converter-vendor>OpenOffice.org</converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.sxc.minicalc.PluginFactoryImpl + </converter-class-impl> + <converter-target type="application/x-minicalc" /> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/makefile.mk new file mode 100644 index 000000000000..8d6716d32b74 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcxs_minicalc +PRJ=../../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/package.html new file mode 100644 index 000000000000..034af32e581b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/minicalc/package.html @@ -0,0 +1,51 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxc.minicalc package</title> +</head> + +<body bgcolor="white"> + +<p>Provides the tools for doing the conversion of StarWriter XML to +and from MiniCalc format.</p> + +<p>It follows the {@link org.openoffice.xmerge} framework for the conversion process.</p> + +<p>Since it converts to/from a Palm application format, these converters +follow the <a href=../../../../converter/palm/package-summary.html#streamformat> +PalmDB stream format</a> for writing out to the Palm sync client or reading +in from the Palm sync client.</p> + +<p>Note that <code>PluginFactoryImpl</code> also provides a +<code>DocumentMerger</code> object, i.e. {@link org.openoffice.xmerge.converter.xml.sxw.aportisdoc.DocumentMergerImpl DocumentMergerImpl}. +This functionality was derived from its superclass +{@link org.openoffice.xmerge.converter.xml.sxw.SxwPluginFactory SxwPluginFactory}.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/package.html new file mode 100644 index 000000000000..bfa0d5a53dbc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/package.html @@ -0,0 +1,38 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxc package</title> +</head> + +<body bgcolor="white"> +<p>Provides base implementation of StarCalc XML conversion to and from +different "Device" <code>Document</code> formats.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..c8de9e99b5da --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/ConverterCapabilitiesImpl.java @@ -0,0 +1,113 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + + +/** + * <p>Pocket Excel implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxc.pexcel.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarCalc SXC to/from Pocket Excel conversions. The + * <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE_ROW.equals(tag)) + return true; + else if (OfficeConstants.TAG_TABLE_COLUMN.equals(tag)) + return false; + // TODO - we currently do not handle the table column tag + else if (OfficeConstants.TAG_TABLE_SCENARIO.equals(tag)) + return false; + // TODO - we currently do not handle the table scenario tag + else if (OfficeConstants.TAG_TABLE_CELL.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_TABLE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_NAME.equals(attribute)) + return true; + + } else if (OfficeConstants.TAG_TABLE_CELL.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_VALUE_TYPE.equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_FORMULA. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_VALUE.equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_BOOLEAN_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_CURRENCY. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_TIME_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_DATE_VALUE. + equals(attribute)) + return true; + else if (OfficeConstants.ATTRIBUTE_TABLE_NUM_COLUMNS_REPEATED. + equals(attribute)) + return true; + + } else if (OfficeConstants.TAG_TABLE_ROW.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_TABLE_NUM_ROWS_REPEATED. + equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PluginFactoryImpl.java new file mode 100644 index 000000000000..e7b08e097614 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PluginFactoryImpl.java @@ -0,0 +1,130 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import java.io.IOException; +import java.io.InputStream; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxc.DocumentMergerImpl; +import org.openoffice.xmerge.converter.xml.sxc.SxcPluginFactory; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.util.registry.ConverterInfo; + +/** + * <p>Pocket Excel implementation of the <code>PluginFactory</code>. + * This encapsulates conversion of StarCalc XML format to and from + * Pocket Excel format.</p> + * + * <p>The superclass produces a particular + * {@link org.openoffice.xmerge.Document Document} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocument + * SxcDocument} that the converters in this class works with. Thus, + * this class only implements the methods that produces the converters, + * i.e. {@link + * org.openoffice.xmerge.DocumentSerializer + * DocumentSerializer} and {@link + * org.openoffice.xmerge.DocumentDeserializer + * DocumentDeserializer}; + * as well as the {@link + * org.openoffice.xmerge.ConverterCapabilities + * ConverterCapabilities} object that is specific to this format + * conversion. That superclass also produces a {@link + * org.openoffice.xmerge.DocumentMerger DocumentMerger} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxc.DocumentMergerImpl + * DocumentMergerImpl} which this class derives the functionality.</p> + */ +public final class PluginFactoryImpl extends SxcPluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory { + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + public PluginFactoryImpl(ConverterInfo ci) { + super(ci); + } + + + /** + * Returns an instance of <code>DocumentSerializerImpl</code>, + * which is an implementation of <code>DocumentSerializer</code> + * interface. + * + * @param doc <code>Document</code> object to be + * converted/serialized. + * + * @return A <code>DocumentSerializerImpl</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + + return new SxcDocumentSerializerImpl(doc); + } + + + /** + * Returns an instance of <code>DocumentDeserializerImpl</code>, + * which is an implementation of <code>DocumentDeserializer</code> + * interface. + * + * @param cd <code>ConvertData</code> object for reading data + * which will be converted back to a + * <code>Document</code> object. + * + * @return A <code>DocumentDeserializerImpl</code> object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + + return new SxcDocumentDeserializerImpl(cd); + } + + + public Document createDeviceDocument(String name, InputStream is) + throws IOException { + + Workbook wb = new Workbook(name, is); + return wb; + } + + public DocumentMerger createDocumentMerger(Document doc) { + + DocumentMergerImpl merger = new DocumentMergerImpl(doc, converterCap); + return merger; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelConstants.java new file mode 100644 index 000000000000..1e2abbf937cb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelConstants.java @@ -0,0 +1,68 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + + +/** + * Interface defining constants for Pocket Excel attributes. + * + * @author Martin Maher + */ +public interface PocketExcelConstants { + /** File extension for Pocket Word files. */ + public static final String FILE_EXTENSION = ".pxl"; + + /** Constants for pexcel BIFF records */ + public static final int BLANK_CELL = 0x01; + public static final int NUMBER_CELL = 0x03; + public static final int LABEL_CELL = 0x04; + public static final int BOOLERR_CELL = 0x05; + public static final int FORMULA_CELL = 0x06; + public static final int FORMULA_STRING = 0x07; + public static final int ROW_DESCRIPTION = 0x08; + public static final int BOF_RECORD = 0x09; + public static final int EOF_MARKER = 0x0A; + public static final int DEFINED_NAME = 0x18; + public static final int CURRENT_SELECTION = 0x1D; + public static final int NUMBER_FORMAT = 0x1E; + public static final int DEFAULT_ROW_HEIGHT = 0x25; + public static final int FONT_DESCRIPTION = 0x31; + public static final int WINDOW_INFO = 0x3D; + public static final int SHEET_WINDOW_INFO = 0x3E; + public static final int PANE_INFO = 0x41; + public static final int CODEPAGE = 0x42; + public static final int DEF_COL_WIDTH = 0x55; + public static final int COLINFO = 0x7D; + public static final int BOUND_SHEET = 0x85; + public static final int EXTENDED_FORMAT = 0xE0; + + /** Colour lookup table for mapping pexcel color values + (See util/ColourConverter.java */ + public short cLookup[] = { 0, 14, 15, 1, 2, 3, 4, 7, 6, 5, 8, 9, 10, 13, 12, 11 }; +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelDecoder.java new file mode 100644 index 000000000000..3e23a87aa20f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelDecoder.java @@ -0,0 +1,446 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.DataOutputStream; +import java.io.IOException; +import java.io.InputStream; +import java.util.Stack; +import java.util.LinkedList; +import java.util.Vector; +import java.util.Enumeration; +import java.util.NoSuchElementException; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; +import org.openoffice.xmerge.converter.xml.sxc.BookSettings; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializer; +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetDecoder; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.NameDefinition; +import org.openoffice.xmerge.converter.xml.sxc.ColumnRowInfo; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.*; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializerImpl} + * SxcDocumentDeserializerImpl} to decode the Pocket Excel format. + * + * @author Paul Rank + */ +final class PocketExcelDecoder extends SpreadsheetDecoder { + + private Workbook wb; + private Worksheet ws; + private CellValue cell; + private int maxRows = 0; + private int maxCols = 0; + private int wsIndex; + private Enumeration cellValue; + private Format fmt = null; + + /** + * Constructor creates a Pocket Excel WorkBook. + * + * @param name The name of the WorkBook. + * @param worksheetNames set of Strings equivalent to the worksheets + * contained in the workbook + * @param password The password for the workBook. + * + * @throws IOException If any I/O error occurs. + */ + PocketExcelDecoder(String name, String[] worksheetNames, String password) throws IOException { + super(name, password); + + fmt = new Format(); + } + + + /** + * This method takes a <code>ConvertData</code> as input and + * converts it into a PocketWord WorkSheet. The WorkSheet is then + * added to the WorkBook. + * + * @param InputStream An <code>ConvertData</code> containing a + * Pocket Excel WorkSheet. + * + * @throws IOException If any I/O error occurs. + */ + public void addDeviceContent(ConvertData cd) throws IOException { + + Enumeration e = cd.getDocumentEnumeration(); + wb = (Workbook) e.nextElement(); + } + + + /** + * This method returns the number of spreadsheets + * stored in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public int getNumberOfSheets() { + + Vector v = wb.getWorksheetNames(); + Debug.log(Debug.TRACE,"Total Number of Sheets : " + v.size()); + return (v.size()); + } + + /** + * This method returns the number of spreadsheets + * stored in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public Enumeration getNameDefinitions() { + + Enumeration e = wb.getDefinedNames(); + Vector nameDefinitionVector = new Vector(); + while(e.hasMoreElements()) { + DefinedName dn = (DefinedName)e.nextElement(); + NameDefinition nameDefinitionEntry = dn.getNameDefinition(); + nameDefinitionVector.add(nameDefinitionEntry); + } + Debug.log(Debug.TRACE,"Getting " + nameDefinitionVector.size() + " DefinedName records"); + return (nameDefinitionVector.elements()); + } + + /** + * This method returns an enumeration of Settings object(s), + * one for each worksheet + * + * @return An enumerattion of <code>Settings</code> + */ + public BookSettings getSettings() { + + return (wb.getSettings()); + } + /** + * This method returns the number of spreadsheets + * stored in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public Enumeration getColumnRowInfos() { + + Vector colRowVector = new Vector(); + + // Collect Columns from worksheet and add them to the vector + for(Enumeration e = ws.getColInfos();e.hasMoreElements();) { + ColInfo ci = (ColInfo)e.nextElement(); + int repeated = ci.getLast() - ci.getFirst() + 1; + ColumnRowInfo colInfo = new ColumnRowInfo( ci.getColWidth(), + repeated, + ColumnRowInfo.COLUMN); + colRowVector.add(colInfo); + } + + // Collect Rows from worksheet and add them to the vector + for(Enumeration e = ws.getRows();e.hasMoreElements();) { + Row rw = (Row)e.nextElement(); + // We will use the repeat field for number (unlike columns rows + // cannot be repeated, we have unique record for each row in pxl + int repeated = rw.getRowNumber(); + ColumnRowInfo rowInfo = new ColumnRowInfo( rw.getRowHeight(), + repeated, + ColumnRowInfo.ROW); + colRowVector.add(rowInfo); + } + Debug.log(Debug.TRACE,"Getting " + colRowVector.size() + " ColRowInfo records"); + return (colRowVector.elements()); + } + + /** + * This method gets the requested WorkSheet from the + * WorkBook and sets it as the selected WorkSheet. All + * other "get" methods will now get data from this WorkSheet. + * + * @param sheetIndex The index number of the sheet to open. + * + * @throws IOException If any I/O error occurs. + */ + public void setWorksheet(int sheetIndex) throws IOException { + Debug.log(Debug.TRACE,"Setting to worksheet : " + sheetIndex); + ws = wb.getWorksheet(sheetIndex); + cellValue = ws.getCellEnumerator(); + wsIndex = sheetIndex; + while(goToNextCell()) { + maxRows = Math.max(maxRows, cell.getRow()); + maxCols = Math.max(maxCols, cell.getCol()); + } + cellValue = ws.getCellEnumerator(); + Debug.log(Debug.TRACE,"Max Cols : " + maxCols + " MaxRows : " + maxRows); + } + + + /** + * This method returns the name of the current spreadsheet. + * + * @return The name of the current WorkSheet. + */ + public String getSheetName() { + + String wsName = wb.getSheetName(wsIndex); + Debug.log(Debug.TRACE,"The name of the current Worksheet is : " + wsName); + return wsName; + } + + + /** + * This method gets the next cell from the WorkSheet + * and sets it as the selected cell. All other "get" + * methods will now get data from this cell. + * + * @return True if we were able to go to another cell + * in the sheet, false if there were no cells + * left. + * + * @throws IOException If any I/O error occurs. + */ + public boolean goToNextCell() throws IOException { + + boolean success = false; + + try { + cell = (CellValue) cellValue.nextElement(); + Debug.log(Debug.TRACE,"Current Cell : " + cell.getString()); + readCellFormat(); + success = true; + } catch (NoSuchElementException e) { + Debug.log(Debug.TRACE,"Could't find current cell"); + } + + return success; + } + + + /** + * This method returns the row number of the current cell. + * + * @return The row number of the current cell. Returns + * -1 if no cell is currently selected. + */ + public int getRowNumber() { + + int row = -1; + + if (cell != null) { + row = cell.getRow(); + Debug.log(Debug.TRACE,"cell row is " + row); + } + return (row); + } + + /** + * This method returns the number of rows in the current sheet. + * + * @return The number of rows in the current sheet. + */ + public int getNumberOfRows() { + return maxRows; + } + + /** + * This method returns the number of columns in the current sheet. + * + * @return The number of columns in the current sheet. + */ + public int getNumberOfColumns() { + return maxCols; + } + + + /** + * This method returns the col number of the current cell. + * + * @return The col number of the current cell. Returns + * -1 if no cell is currently selected. + */ + public int getColNumber() { + + int col = -1; + + if (cell != null) { + col = cell.getCol(); + Debug.log(Debug.TRACE,"cell col is " + col); + } + return (col); + } + + /** + * This method returns the contents of the current cell. + * + * @return The contents of the current cell. Returns + * null if no cell is currently selected. + */ + public String getCellContents() { + + String contents = new String(""); + + if (cell != null) { + try { + contents = cell.getString(); + if (contents.startsWith("=")) { + contents = parseFormula(contents); + } + } + catch (IOException e) { + System.err.println("Could Not retrieve Cell contents"); + System.err.println("Setting contents of cell(" + cell.getRow() + + "," + cell.getCol() + ") to an empty string"); + System.err.println("Error msg: " + e.getMessage()); + } + } + + return contents; + } + + /** + * <p>This method takes a formula and parses it into + * StarOffice XML formula format.</p> + * + * <p>Many spreadsheets use ',' as a separator. + * StarOffice XML format uses ';' as a separator instead.</p> + * + * <p>Many spreadsheets use '!' as a separator when refencing + * a cell in a different sheet.</p> + * + * <blockquote> + * Example: =sheet1!A1 + * </blockquote> + * + * <p>StarOffice XML format uses '.' as a separator instead.</p> + * + * <blockquote> + * Example: =sheet1.A1 + * </blockquote> + * + * @param formula A formula string. + * + * @return A StarOffice XML format formula string. + */ + protected String parseFormula(String formula) { + + formula = formula.replace(',', ';'); + formula = formula.replace('!', '.'); + + return formula; + } + + /** + * This method returns the contents of the current cell. + * + * @return The contents of the current cell. Returns + * null if no cell is currently selected. + */ + public String getCellValue() { + + String contents = new String(""); + + if (cell != null) { + try { + contents = ((Formula)cell).getValue(); + } + catch (IOException e) { + System.err.println("Could Not retrieve Cell value"); + System.err.println("Setting value of cell(" + cell.getRow() + + "," + cell.getCol() + ") to an empty string"); + System.err.println("Error msg: " + e.getMessage()); + } + } + return contents; + } + + /** + * <p>This method returns the type of the data in the current cell. + * Currently the only type supported is String.</p> + * + * @return The type of the data in the current cell. + */ + public String getCellDataType() { + + String type = OfficeConstants.CELLTYPE_STRING; + + if(cell instanceof FloatNumber) + type = OfficeConstants.CELLTYPE_FLOAT; + if(cell instanceof Formula) + type = OfficeConstants.CELLTYPE_FLOAT; + + return type; + } + + + /** + * Return the Format object describing the active cell formatting. + * + * @return The Format object describing the active cell formatting. + */ + public Format getCellFormat() { + return new Format(fmt); + } + + + /** + * Create the format data for the new cell. + */ + private void readCellFormat() throws IOException { + + fmt.clearFormatting(); + + Debug.log(Debug.TRACE," ixfe for Current Cell " + cell.getIxfe()); + ExtendedFormat xf = wb.getExtendedFormat(cell.getIxfe()); + Debug.log(Debug.TRACE," ixfnt for Current Cell " + xf.getFontIndex()); + FontDescription fd = wb.getFontDescription(xf.getFontIndex()); + + fmt.setAttribute(Format.ITALIC, fd.isItalic()); + fmt.setAttribute(Format.BOLD, fd.isBold()); + fmt.setAttribute(Format.UNDERLINE, fd.isUnderline()); + fmt.setForeground(fd.getForeground()); + + fmt.setBackground(xf.getBackground()); + fmt.setAlign(xf.getAlign()); + fmt.setVertAlign(xf.getVertAlign()); + fmt.setAttribute(Format.WORD_WRAP, xf.isWordWrap()); + + fmt.setAttribute(Format.TOP_BORDER, xf.isBorder(ExtendedFormat.TOP_BORDER)); + fmt.setAttribute(Format.BOTTOM_BORDER, xf.isBorder(ExtendedFormat.BOTTOM_BORDER)); + fmt.setAttribute(Format.RIGHT_BORDER, xf.isBorder(ExtendedFormat.RIGHT_BORDER)); + fmt.setAttribute(Format.LEFT_BORDER, xf.isBorder(ExtendedFormat.LEFT_BORDER)); + + fmt.setFontName(fd.getFont()); + fmt.setFontSize(fd.getFontSize()); + + fmt.setCategory(getCellDataType()); + + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelEncoder.java new file mode 100644 index 000000000000..062260aa3664 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/PocketExcelEncoder.java @@ -0,0 +1,295 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.DataOutputStream; +import java.io.IOException; +import java.util.Vector; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.IntArrayList; + +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetEncoder; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.BookSettings; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; +import org.openoffice.xmerge.converter.xml.sxc.NameDefinition; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxc.SxcDocumentSerializerImpl + * SxcDocumentSerializerImpl} to encode the Pocket Excel format. + * + * @author Martin Maher + */ +final class PocketExcelEncoder extends SpreadsheetEncoder { + + private Workbook wb; + + /** + * Constructor creates a Pocket Excel WorkBook. + * + * @param name The name of the WorkBook. + * @param password The password for the WorkBook. + * + * @throws IOException If any I/O error occurs. + */ + PocketExcelEncoder(String name, String password) throws IOException { + + super(name, password); + wb = new Workbook(name); + + } + + + /** + * This method creates a WorkSheet belonging to the + * WorkBook. + * + * @param sheetName The name of the WorkSheet. + * + * @throws IOException If any I/O error occurs. + */ + public void createWorksheet(String sheetName) throws IOException { + + wb.addWorksheet(sheetName); + } + + + /** + * This method gets the number of sheets in the WorkBook. + * + * @return The number of sheets in the WorkBook. + */ + public int getNumberOfSheets() { + + Vector v = wb.getWorksheetNames(); + return (v.size()); + } + + + /** + * This method returns the Workbook created. + * + * @return Returns a <code>Workbook</code> + * + * @throws IOException If any I/O error occurs. + */ + public Workbook getWorkbook() throws IOException { + + return wb; + } + + /** + * This method converts a String containing a formula in infix notation + * to a String in Reverse Polish Notation (RPN) + * + * @return a parsed pexcel formula in RPN + */ + protected String parseFormula(String formula) { + + Debug.log(Debug.TRACE,"Strip Formula (Before) : " + formula); + + StringBuffer inFormula = new StringBuffer(formula); + StringBuffer outFormula = new StringBuffer(); + + boolean inBrace = false; + boolean firstCharAfterBrace = false; + boolean firstCharAfterColon = false; + + int len = inFormula.length(); + + for (int in = 0; in < len; in++) { + switch (inFormula.charAt(in)) { + case '[': + // We are now inside a StarOffice cell reference. + // We also need to strip out the '[' + Debug.log(Debug.TRACE,"brace Found"); + inBrace = true; + + // If the next character is a '.', we want to strip it out + firstCharAfterBrace = true; + break; + + case ']': + // We are exiting a StarOffice cell reference + // We are stripping out the ']' + inBrace = false; + break; + case '.': + if (inBrace == true && (firstCharAfterBrace == true || + firstCharAfterColon == true) ) { + + Debug.log(Debug.TRACE,"dot Found and in brace"); + // Since we are in a StarOffice cell reference, + // and we are the first character, we need to + // strip out the '.' + firstCharAfterBrace = false; + firstCharAfterColon = false; + + } else if(firstCharAfterColon == true) { + firstCharAfterColon = false; + } else { + outFormula.append(inFormula.charAt(in)); + } + break; + + case ':': + // We have a cell range reference. + // May need to strip out the leading '.' + firstCharAfterColon = true; + outFormula.append(inFormula.charAt(in)); + break; + + case ';': + // StarOffice XML format uses ';' as a separator. MiniCalc (and + // many spreadsheets) use ',' as a separator instead. + outFormula.append(','); + break; + + default: + // We hit valid data, lets add it to the formula string + outFormula.append(inFormula.charAt(in)); + + // Need to make sure that firstCharAfterBrace is not true. + firstCharAfterBrace = false; + break; + } + } + + Debug.log(Debug.TRACE,"Strip Formula (After) : " + outFormula); + return outFormula.toString(); + } + + /** + * Add a cell to the current WorkSheet. + * + * @param row The row number of the cell. + * @param column The column number of the cell. + * @param fmt The <code>Format</code> object describing + * the appearance of this cell. + * @param cellContents The text or formula of the cell's contents. + * + * @throws IOException If any I/O error occurs. + */ + public void addCell(int row, int column, Format fmt, String cellContents) throws IOException { + + if (cellContents.startsWith("=")) { + cellContents = parseFormula(cellContents); + Debug.log(Debug.TRACE,"Parsing Formula " + cellContents); + } + wb.addCell(row, column, fmt, cellContents); + } + + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public void setColumnRows(Vector columnRows) throws IOException { + + wb.addColInfo(columnRows); + } + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public void setNameDefinition(NameDefinition nd) throws IOException { + + String parsedName = nd.getDefinition(); + nd.setDefinition(parseFormula(parsedName)); + + wb.addNameDefinition(nd); + } + + /** + * Set the width of the columns in the WorkBook. + * + * @param columnWidths An <code>IntArrayList</code> of column + * widths. + */ + public void addSettings(BookSettings s) throws IOException { + + wb.addSettings(s); + } + + /** + * This method sets the format of a cell to <i>string</i>. + * + * @param format The cell format-may already contain display info, + * such as alignment or font type. + * + * @return The updated format of the cell. + */ + private long setFormatString(long format) { + + return 0; + } + + + /** + * Set a cell's formatting options via a separately create + * <code>Format</code> object. + * + * @param row The row number of the cell to be changed. + * @param column The column number of the cell to be changed. + * @param fmt Object containing formatting settings for + * this cell. + */ + public void setCellFormat(int row, int column, Format fmt) { + Debug.log(Debug.TRACE,"bold : " + fmt.getAttribute(Format.BOLD) + + ",Italic : " + fmt.getAttribute(Format.ITALIC) + + ",Underline : " + fmt.getAttribute(Format.UNDERLINE)); + } + + + /** + * Get the names of the sheets in the WorkBook. + * + * @param sheet The required sheet. + */ + public String getSheetName(int sheet) { + + Vector v = wb.getWorksheetNames(); + String wsName = (String) (v.elementAt(sheet)); + + return wsName; + } + + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentDeserializerImpl.java new file mode 100644 index 000000000000..777506515629 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentDeserializerImpl.java @@ -0,0 +1,129 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import java.io.IOException; +import java.util.Enumeration; +import java.util.Vector; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.converter.xml.sxc.SpreadsheetDecoder; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentDeserializer; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelDecoder; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; + + +/** + * <p>Pocket Excel implementation of <code>DocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.pexcel.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts a set of files in Pocket Excel PXL format to a StarOffice DOM.</p> + * + * @author Mark Murnane + */ +public final class SxcDocumentDeserializerImpl extends SxcDocumentDeserializer { + + /** + * Creates new <code>SxcDocumentDeserializerImpl</code>. + * + * @param cd <code>ConvertData</code> Input data to convert. + */ + public SxcDocumentDeserializerImpl(ConvertData cd) { + super(cd); + } + + + /** + * This method will be implemented by concrete subclasses and will + * return an application-specific decoder. + * + * @param workbook The WorkBook name. + * @param worksheetNames An array of WorkSheet names. + * @param password The password. + * + * @return An application-specific <code>SpreadsheetDecoder</code>. + */ + public SpreadsheetDecoder createDecoder(String workbook, + String[] worksheetNames, String password) throws IOException { + + return new PocketExcelDecoder(workbook, worksheetNames, password); + } + + + /** + * This method will return the name of the WorkBook from the + * <code>ConvertData</code>. Allows for situations where the + * WorkBook name differs from the PDB name. + * + * Implemented in the Deserializer as the Decoder's constructor + * requires a name. + * + * @param cd The <code>ConvertData</code>. + * + * @return The name of the WorkBook. + */ + protected String getWorkbookName(ConvertData cd) + throws IOException { + + Enumeration e = cd.getDocumentEnumeration(); + Workbook wb = (Workbook) e.nextElement(); + + String workbookName = wb.getName(); + return workbookName; + } + + + /** + * This method will return an array of WorkSheet names from the + * <code>ConvertData</code>. + * + * @param cd The <code>ConvertData</code>. + * + * @return The name of the WorkSheet. + */ + protected String[] getWorksheetNames(ConvertData cd) + throws IOException { + + Enumeration e = cd.getDocumentEnumeration(); + Workbook wb = (Workbook) e.nextElement(); + Vector v = wb.getWorksheetNames(); + e = v.elements(); + String worksheetNames[] = new String[v.size()]; + int i = 0; + while(e.hasMoreElements()) { + worksheetNames[i] = (String) e.nextElement(); + Debug.log(Debug.TRACE,"Worksheet Name : " + worksheetNames[i]); + i++; + } + return worksheetNames; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentSerializerImpl.java new file mode 100644 index 000000000000..df2d9c6befa1 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/SxcDocumentSerializerImpl.java @@ -0,0 +1,136 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel; + +import java.awt.Color; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import java.io.IOException; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.SxcDocumentSerializer; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.converter.xml.StyleCatalog; + +/** + * <p>Pocket Excel implementation of <code>SxcDocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxc.pexcel.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts StarOffice XML format to a set of files in + * Pocket Excel PXL format.</p> + * + * @author Paul Rank + * @author Mark Murnane + */ +public final class SxcDocumentSerializerImpl extends SxcDocumentSerializer { + + + /** + * Constructor. + * + * @param document The <code>Document</code> to convert. + */ + public SxcDocumentSerializerImpl(Document document) { + super(document); + } + + + public ConvertData serialize() throws ConvertException, IOException { + + // Get the server side document name. This value should not + // contain a path or the file extension. + String docName = sxcDoc.getName(); + + // TODO - get real values for password when implemnted in XML + // Passwords are not currently stored in StarCalc XML format. + String password = null; + + encoder = new PocketExcelEncoder(docName, password); + + // get dom document + org.w3c.dom.Document domDoc = sxcDoc.getContentDOM(); + + // load the styles + loadStyles(sxcDoc); + // Traverse to the office:body element. + // There should only be one. + NodeList list = domDoc.getElementsByTagName(TAG_OFFICE_BODY); + int len = list.getLength(); + + if (len > 0) { + Node node = list.item(0); + traverseBody(node); + } + + // get settings for this document + org.w3c.dom.Document settingsDoc = sxcDoc.getSettingsDOM(); + if(settingsDoc!=null) { + NodeList settingsList = settingsDoc.getElementsByTagName(TAG_OFFICE_SETTINGS); + int slen = settingsList.getLength(); + + if (slen > 0) { + Node settingsNode = settingsList.item(0); + traverseSettings(settingsNode); + } + } + + // Get the number of sheets in the workbook + // This will equal the number of PDBs we need + ConvertData cd = new ConvertData(); + Workbook wb = ((PocketExcelEncoder) encoder).getWorkbook(); + cd.addDocument(wb); + + return cd; + } + + + /** + * A cell reference in a StarOffice formula looks like + * [.C2] (for cell C2). MiniCalc is expecting cell references + * to look like C2. This method strips out the braces and + * the period. + * + * @param formula A StarOffice formula <code>String</code>. + * + * @return A MiniCalc formula <code>String</code>. + */ + protected String parseFormula(String formula) { + + return null; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/build.xml new file mode 100644 index 000000000000..d0b036da0454 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/build.xml @@ -0,0 +1,132 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxs_pexcel" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxs_pexcel"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxc/pexcel"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/PocketExcelConstants.java"/> + <include name="${package}/PocketExcelDecoder.java"/> + <include name="${package}/PocketExcelEncoder.java"/> + <include name="${package}/SxcDocumentDeserializerImpl.java"/> + <include name="${package}/SxcDocumentSerializerImpl.java"/> + <include name="${package}/ConverterCapabilitiesImpl.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/converter.xml new file mode 100644 index 000000000000..85efdab4f83d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/converter.xml @@ -0,0 +1,43 @@ +<?xml version="1.0"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<converters> + <converter type="staroffice/sxc" version="1.0"> + <converter-display-name> + Pocket Excel 2.0 + </converter-display-name> + <converter-description> + StarCalc XML to/from Pocket Excel 2.0 conversion + </converter-description> + <converter-vendor>OpenOffice.org</converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.sxc.pexcel.PluginFactoryImpl + </converter-class-impl> + <converter-target type="application/x-pocket-excel" /> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/makefile.mk new file mode 100644 index 000000000000..9e5308e04a11 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcxs_pexcel +PRJ=../../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/package.html new file mode 100644 index 000000000000..b13666af6920 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/package.html @@ -0,0 +1,41 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxc.pexcel package</title> +</head> + +<body bgcolor="white"> + +<p>Provides the tools for doing the conversion of StarWriter XML to +and from Pocket Excel format.</p> + +<p>It follows the {@link org.openoffice.xmerge} framework for the conversion process.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BIFFRecord.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BIFFRecord.java new file mode 100644 index 000000000000..e55778c8e04f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BIFFRecord.java @@ -0,0 +1,62 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + + public interface BIFFRecord { + + /** + * Get the type of the record. In the BIFF file format each record has a type + * designated with a byte value. See @link PocketExcelBiffConstants + * for a list of the BIFF constants and what they mean. + * + * @return byte The BIFF record value. + */ + public short getBiffType(); + + /** + * Read from the input stream <b>NB</b>The input stream is assumed to be in + * Little Endian format. The Biff identifier is expected to be in the stream. + * + * @param input The InputStream to read from. + * @return The number of bytes that were read in. + */ + public int read(InputStream input) throws IOException; + + /** + * Writes the record, including the BIFF record byte to the outputstream + * @param output The output stream to write to in LittleEndian format. + */ + public void write(OutputStream output) throws IOException; + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BeginningOfFile.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BeginningOfFile.java new file mode 100644 index 000000000000..fadaea5e30d7 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BeginningOfFile.java @@ -0,0 +1,116 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.InputStream; +import java.io.OutputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * This class describes the beginning of file. It is the + * the Biff record that marks the beginning of a a worbook + * or the beginning of worksheets in the workbook + * + */ +public class BeginningOfFile implements BIFFRecord { + + private byte[] version = new byte[2]; + private byte[] subStream = new byte[2]; + + /** + * Constructor that initializes the member values. + * + * @param ver Version Number + * Substream type (workbook = 0x05, worksheet = 0x10) + */ + public BeginningOfFile(boolean global) { + setVersion((short) 271); + if(global) + setSubStreamWBGlobal(); + else + setSubStreamWorkSheet(); + // this.subStream = EndianConverter.writeShort(dt); + } + + public BeginningOfFile(InputStream is) throws IOException { + read(is); + } + + private void setVersion(short version) { + this.version = EndianConverter.writeShort(version); + } + + int getVersion() { + return EndianConverter.readShort(version); + } + + private void setSubStreamWBGlobal() { + // subStream = new byte[] {0x05}; + subStream = EndianConverter.writeShort((short) 0x05); + } + + private void setSubStreamWorkSheet() { + // subStream = new byte[] {0x10}; + subStream = EndianConverter.writeShort((short) 0x10); + } + + int getSubStreamType() { + return EndianConverter.readShort(subStream); + } + + public int read(InputStream input) throws IOException { + int numBytesRead = input.read(version); + numBytesRead += input.read(subStream); + Debug.log(Debug.TRACE,"\tVersion : "+ EndianConverter.readShort(version) + + " Stream : " + EndianConverter.readShort(subStream)); + + return numBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(version); + output.write(subStream); + + Debug.log(Debug.TRACE, "Writing BeginningOfFile record"); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BeginningOfFile</code> + */ + public short getBiffType() { + return PocketExcelConstants.BOF_RECORD; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BlankCell.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BlankCell.java new file mode 100644 index 000000000000..5844f4a6b57b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BlankCell.java @@ -0,0 +1,116 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record that describes a blank cell + */ +public class BlankCell extends CellValue { + + /** + * Constructs a BlankCell <code>InputStream</code> + * + * @param is InputStream containing a BlankCell. + */ + public BlankCell(InputStream is) throws IOException { + read(is); + } + + /** + * Constructs a <code>BlankCell</code> using specified attributes + * + * @param row row number + * @param col column number + * @param cellContents contents of the cell + * @param ixfe font index + */ + public BlankCell(int row, int column, int ixfe) throws IOException { + + setRow(row); + setCol(column); + setIxfe(ixfe); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BlankCell</code> + */ + public short getBiffType() { + return PocketExcelConstants.BLANK_CELL; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(rw); + output.write(col); + output.write(ixfe); + + Debug.log(Debug.TRACE, "Writing BlankCell record"); + + } + + /** + * Reads a BlankCell <code>InputStream</code> + * + * @param is InputStream containing a BlankCell. + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(rw); + numOfBytesRead++; + col += input.read(); + numOfBytesRead += input.read(ixfe); + + Debug.log(Debug.TRACE, "\tRow : "+ EndianConverter.readShort(rw) + + " Column : " + col + + " ixfe : " + EndianConverter.readShort(ixfe)); + + return numOfBytesRead; + } + + /** + * Gets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + public String getString() throws IOException { + + return (new String("")); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoolErrCell.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoolErrCell.java new file mode 100644 index 000000000000..b9226885be2d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoolErrCell.java @@ -0,0 +1,127 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record that describes a Boolean or Error value + */ +public class BoolErrCell extends CellValue { + + private byte bBoolErr; + private byte fError; + + /** + * Constructs a BoolErrCell from arguments + * + * @param row row number + * @param col column number + * @param ixfe font index + * @param bBoolErr Boolean value or error value + * @param fError Boolean error flag + */ + public BoolErrCell(int row, int column, int ixfe, int bBoolErr, int fError) throws IOException { + + setIxfe(ixfe); + this.bBoolErr = (byte)bBoolErr; + this.fError = (byte)fError; + setRow(row); + setCol(column); + } + + /** + * Constructs a BoolErrCell from the <code>InputStream</code> + * + * @param is InputStream containing a BoolErrCell + */ + public BoolErrCell(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BoolErrCEll</code> + */ + public short getBiffType() { + return PocketExcelConstants.BOOLERR_CELL; + } + + /** + * Writes a <code>BoolErrCell</code> to the specified <code>Outputstream</code> + * + * @param os the <code>OutputStream</code> to write to + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + + super.write(output); + + output.write(bBoolErr); + output.write(fError); + + Debug.log(Debug.TRACE,"Writing BoolErrCell record"); + } + + /** + * Reads a BoolErrCell from the <code>InputStream</code> + * + * @param is InputStream containing a BoolErrCell + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = super.read(input); + + bBoolErr = (byte) input.read(); + fError = (byte) input.read(); + numOfBytesRead += 2; + + Debug.log(Debug.TRACE, " bBoolErr : " + bBoolErr + + " fError : " + fError); + return numOfBytesRead; + } + + /** + * Gets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + public String getString() throws IOException { + return ("Error Cell"); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoundSheet.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoundSheet.java new file mode 100644 index 000000000000..743853013ac6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/BoundSheet.java @@ -0,0 +1,137 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.io.OutputStream; +import java.io.InputStream; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BoundSheet Record which describes the name of a worksheet + */ +public class BoundSheet implements BIFFRecord { + + private byte reserved; + private byte cch; + private byte[] sheetName; + + /** + * Constructs a pocket Excel Document assigns it the document name passed in + * + * @param name name of the worksheet represented + */ + public BoundSheet(String name) throws IOException { + setSheetName(name); + reserved = 0; + } + + /** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public BoundSheet(InputStream is) throws IOException { + read(is); + } + + /** + * Sets the worksheet name. The sheetname length must be doubled as the + * String is stored in unicode format. + * + * @param sheetname worksheet name + */ + void setSheetName(String sheetName) throws IOException { + this.cch = (byte) sheetName.length(); + this.sheetName = new byte[cch*2]; + this.sheetName = sheetName.getBytes("UTF-16LE"); + } + + public String getSheetName() { + String name; + + try { + name = new String(sheetName, "UTF-16LE"); + } catch (UnsupportedEncodingException e){ + name = "unknown"; + } + return name; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BoundSheet</code> + */ + public short getBiffType() { + return PocketExcelConstants.BOUND_SHEET; + } + + /** + * Write this particular <code>BIFFRecord</code> to the <code>OutputStream</code> + * + * @param ouput the <code>OutputStream</code> + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(reserved); + output.write(cch); + output.write(sheetName); + + Debug.log(Debug.TRACE,"Writing BoundSheet record"); + } + + /** + * Reads a BoundSheet from the <code>InputStream</code> The byte array + * must be twice the size of the String as it uses unicode. + * + * @param is InputStream containing the record data + */ + public int read(InputStream input) throws IOException { + + reserved = (byte) input.read(); + cch = (byte) input.read(); + int numOfBytesRead = 2; + int strLen = cch*2; + sheetName = new byte[strLen]; + numOfBytesRead += input.read(sheetName, 0, strLen); + + Debug.log(Debug.TRACE,"\tReserved : "+ reserved + + " cch : " + cch + + " sheetName : " + new String(sheetName,"UTF-16LE")); + + return numOfBytesRead; + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CellValue.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CellValue.java new file mode 100644 index 000000000000..3c4d875a923a --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CellValue.java @@ -0,0 +1,138 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +public abstract class CellValue implements BIFFRecord { + + protected byte[] rw = new byte[2]; + protected byte col; + protected byte[] ixfe = new byte[2]; + + /** + * Get the row number of this cell + * + * @return the row number of this cell + */ + public int getRow() { + return EndianConverter.readShort(rw) + 1; + } + + /** + * Set the row number of this cell + * + * @param row sets the row number for this cell + */ + public void setRow(int row) { + this.rw = EndianConverter.writeShort((short) (row - 1)); + } + /** + * Get the Index to the <code>ExtendedFormat</code> + * + * @return the index number of this cell's <code>ExtendedFormat</code> + */ + public int getIxfe() { + return EndianConverter.readShort(ixfe); + } + + /** + * Sets the Index to the <code>ExtendedFormat</code> + * + * @param ixfe sets the index number for this cell's <code>ExtendedFormat</code> + */ + public void setIxfe(int ixfe) { + this.ixfe = EndianConverter.writeShort((short) (ixfe)); + } + + /** + * Get the column number of this cell + * + * @return the column number of this cell + */ + public int getCol() { + return col + 1; // The cols start at 1 + } + + /** + * Set the row number of this cell + * + * @param col sets the row number for this cell + */ + public void setCol(int col) { + this.col = (byte) (col - 1); // The cols start at 1 + } + + /** + * Writes basic cell value attributes to the specified <code>Outputstream</code> + * + * @param os the <code>OutputStream</code> to write to + */ + public void write(OutputStream output) throws IOException { + + output.write(rw); + output.write(col); + output.write(ixfe); + } + + /** + * Writes a<code>LabelCell</code> to the specified <code>Outputstream</code> + * + * @param os the <code>OutputStream</code> to write to + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(rw); + col += input.read(); + numOfBytesRead++; + numOfBytesRead += input.read(ixfe); + + Debug.log(Debug.TRACE, "\tRow : "+ EndianConverter.readShort(rw) + + " Column : " + col + + " ixfe : " + EndianConverter.readShort(ixfe)); + + return numOfBytesRead; + } + + + /** + * Returns the contents of the cell as a String + * + * @return the contents of the cell + */ + abstract public String getString() throws IOException; + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CodePage.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CodePage.java new file mode 100644 index 000000000000..34c2dccdfb10 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/CodePage.java @@ -0,0 +1,108 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents the codepage for the document. There is a number of unknown + * fields which are hardcoded at construction + */ +public class CodePage implements BIFFRecord { + + private byte[] codepage = new byte[2]; + private byte[] unknown1 = new byte[2]; + private byte[] unknown2 = new byte[2]; + private byte unknown3; + + /** + * Constructs a pocket Excel Codepage + */ + public CodePage() { + codepage = new byte[] {(byte)0xE4, (byte)0x04}; + unknown1 = new byte[] {(byte)0x8C, (byte)0x01}; + unknown2 = new byte[] {(byte)0x00, (byte)0x01}; + unknown3 = 0x00; + } + + /** + * Constructs a pocket Excel Codepage from the<code>InputStream</code> + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public CodePage(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BoundSheet</code> + */ + public short getBiffType() { + return PocketExcelConstants.CODEPAGE; + } + + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(codepage); + numOfBytesRead += input.read(unknown1); + numOfBytesRead += input.read(unknown2); + // numOfBytesRead += input.read(unknown3); + unknown3 = (byte) input.read(); + numOfBytesRead++; + + Debug.log(Debug.TRACE,"\tcodepage : "+ EndianConverter.readShort(codepage) + + " unknown1 : " + EndianConverter.readShort(unknown1) + + " unknown2 : " + EndianConverter.readShort(unknown2) + + " unknown3 : " + unknown3); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(codepage); + output.write(unknown1); + output.write(unknown2); + output.write(unknown3); + + Debug.log(Debug.TRACE,"Writing CodePage record"); + + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ColInfo.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ColInfo.java new file mode 100644 index 000000000000..fc2e9c5f7fbb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ColInfo.java @@ -0,0 +1,158 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.IOException; +import java.io.DataInputStream; +import java.io.InputStream; +import java.io.OutputStream; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * ColInfo describes the formatting for a column + * + */ +public class ColInfo implements BIFFRecord { + + private byte[] colFirst = new byte[2]; // first column this formatting applies to + private byte[] colLast = new byte[2]; // last column this formatting applies to + private byte[] colDX = new byte[2]; // column width + private byte[] ixfe = new byte[2]; // index for formatting + private byte grbit; // options flags + private float scale = (float) 2.5; // 1.798; + + /** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param colFirst the first column this formatting applies to + * @param colLast last column this formatting applies to + * @param coldx column width + * @param grbit options flags + */ + public ColInfo(int colFirst, int colLast, int colDX, int ixfe) { + this.colFirst = EndianConverter.writeShort((short)colFirst); + this.colLast = EndianConverter.writeShort((short)colLast); + colDX *= scale; + this.colDX = EndianConverter.writeShort((short)colDX); + this.ixfe = EndianConverter.writeShort((short)ixfe); + this.grbit = 0x00; + } + + /** + * Construct a ColInfo from the InputStream + * + * @param is the <code>Inputstream</code> to read from + */ + public ColInfo(InputStream is) throws IOException { + read(is); + } + + /** + * Reads ColInfo record from the InputStream + * + * @param input the InputStream to read from + * @return the number of bytes read + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(colFirst); + numOfBytesRead += input.read(colLast); + numOfBytesRead += input.read(colDX); + short scaledDX = (short) (EndianConverter.readShort(colDX) / scale); + colDX = EndianConverter.writeShort(scaledDX); + numOfBytesRead += input.read(ixfe); + grbit = (byte) input.read(); + numOfBytesRead ++; + + Debug.log(Debug.TRACE,"\tcolFirst : "+ EndianConverter.readShort(colFirst) + + " colLast : " + EndianConverter.readShort(colLast) + + " colDX : " + EndianConverter.readShort(colDX) + + " ixfe : " + EndianConverter.readShort(ixfe) + + " grbit : " + grbit); + + return numOfBytesRead; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>ColInfo</code> + */ + public short getBiffType() { + return PocketExcelConstants.COLINFO; + } + /** + * Get the width of this column + * + * @return the width of this column + */ + public short getColWidth() { + return EndianConverter.readShort(colDX); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>ColInfo</code> + */ + public short getFirst() { + return EndianConverter.readShort(colFirst); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>ColInfo</code> + */ + public short getLast() { + return EndianConverter.readShort(colLast); + } + + /** + * Writes a ColInfo to the specified <code>Outputstream</code> + * + * @param os the <code>OutputStream</code> to write to + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(colFirst); + output.write(colLast); + output.write(colDX); + output.write(ixfe); + output.write(grbit); + + Debug.log(Debug.TRACE,"Writing ColInfo record"); + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefColWidth.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefColWidth.java new file mode 100644 index 000000000000..35650f0278f3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefColWidth.java @@ -0,0 +1,95 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF record defiuning the defualt column width + */ +public class DefColWidth implements BIFFRecord { + + private byte[] grbit = new byte[2]; + private byte[] coldx = new byte[2]; + private byte[] ixfe = new byte[2]; + +/** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public DefColWidth() { + grbit = new byte[] {0x00, 0x00}; + coldx = new byte[] {0x00, 0x09}; + ixfe = new byte[] {0x00, 0x00}; + } + + public DefColWidth(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>DefColWidth</code> + */ + public short getBiffType() { + return PocketExcelConstants.DEF_COL_WIDTH; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(grbit); + output.write(coldx); + output.write(ixfe); + + Debug.log(Debug.TRACE, "Writing DefColWidth record"); + } + + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(grbit); + numOfBytesRead += input.read(coldx); + numOfBytesRead += input.read(ixfe); + + Debug.log(Debug.TRACE,"\tgrbit : "+ EndianConverter.readShort(grbit) + + " coldx : " + EndianConverter.readShort(coldx) + + " ixfe : " + EndianConverter.readShort(ixfe)); + return 0; + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefRowHeight.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefRowHeight.java new file mode 100644 index 000000000000..7e933d9b8978 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefRowHeight.java @@ -0,0 +1,97 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF record defiuning the default row height + */ +public class DefRowHeight implements BIFFRecord { + + private byte[] unknown1 = new byte[2]; + private byte[] unknown2 = new byte[2]; + + /** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public DefRowHeight() { + unknown1 = new byte[] {(byte)0x00, (byte)0x00}; + unknown2 = new byte[] {(byte)0xFF, (byte)0x00}; + } + + /** + * Constructs a DefRowHeight from the <code>InputStream</code> + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public DefRowHeight(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>DefRowHeight</code> + */ + public short getBiffType() { + return PocketExcelConstants.DEFAULT_ROW_HEIGHT; + } + + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(unknown1); + numOfBytesRead += input.read(unknown2); + + Debug.log(Debug.TRACE,"\tunknown1 : "+ EndianConverter.readShort(unknown1) + + " unknown2 : " + EndianConverter.readShort(unknown2)); + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(unknown1); + output.write(unknown2); + + Debug.log(Debug.TRACE,"Writing DefRowHeight record"); + + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefinedName.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefinedName.java new file mode 100644 index 000000000000..38d47b8adbc5 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/DefinedName.java @@ -0,0 +1,227 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.io.UnsupportedEncodingException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula.FormulaHelper; +import org.openoffice.xmerge.converter.xml.sxc.NameDefinition; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record representing a defined name in the workbook + */ +public class DefinedName implements BIFFRecord { + + private byte[] grbit = new byte[2]; + private byte cch; + private byte[] cce = new byte[2]; + private byte[] ixals = new byte[2]; + private byte[] rgch; + private byte[] rgce; + private FormulaHelper fh = new FormulaHelper(); + private String definition = new String(""); + private Workbook wb; + + /** + * Constructs a Defined Name from the <code>InputStream</code> + * + * @param is InputStream containing the record data + */ + public DefinedName(NameDefinition nd, Workbook wb) throws IOException { + + fh.setWorkbook(wb); + this.wb = wb; + String name = nd.getName(); + + // we have to insert an = to stop the formulaParser throwing an exception + definition = "=" + nd.getDefinition(); + + cch = (byte)name.length(); + rgch = new byte[cch*2]; + rgch = name.getBytes("UTF-16LE"); + grbit = EndianConverter.writeShort((short)0); + ixals[0] = (byte)0xFF;ixals[1] = (byte)0xFF; + } + /** + * Constructs a Defined Name from the <code>InputStream</code> + * + * @param is InputStream containing the record data + */ + public DefinedName(InputStream is, Workbook wb) throws IOException { + + read(is); + fh.setWorkbook(wb); + this.wb = wb; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>DefinedName</code> + */ + public short getBiffType() { + return PocketExcelConstants.DEFINED_NAME; + } + + /** + * Reads a Defined Name from the <code>InputStream</code> The byte array + * must be twice the size of the String as it uses unicode. + * + * @param is InputStream containing the record data + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(grbit); + cch = (byte) input.read(); + numOfBytesRead++; + numOfBytesRead += input.read(cce); + numOfBytesRead += input.read(ixals); + + rgch = new byte[cch*2]; + input.read(rgch, 0, cch*2); + + rgce = new byte[EndianConverter.readShort(cce)]; + input.read(rgce, 0, EndianConverter.readShort(cce)); + + + + Debug.log(Debug.TRACE, "\tgrbit : "+ EndianConverter.readShort(grbit) + + " cch : " + cch + + " cce : " + EndianConverter.readShort(cce) + + " ixals : " + EndianConverter.readShort(ixals) + + "\n\trgch : " + rgch + + " rgce : " + rgce); + + return numOfBytesRead; + } + + /** + * Write this particular <code>BIFFRecord</code> to the <code>OutputStream</code> + * + * @param ouput the <code>OutputStream</code> + */ + public void write(OutputStream output) throws IOException { + + try { + Debug.log(Debug.TRACE,"Writing out " + definition); + rgce = fh.convertCalcToPXL(definition); + cce = EndianConverter.writeShort((short) rgce.length); + } catch(Exception e) { + Debug.log(Debug.TRACE,"Error in Parsing Name Definition"); + cce = EndianConverter.writeShort((short) 0); + } + + + output.write(getBiffType()); + output.write(grbit); + output.write(cch); + output.write(cce); + output.write(ixals); + output.write(rgch); + if(rgce.length!=0) + output.write(rgce); + + Debug.log(Debug.TRACE,"Writing DefinedName record"); + } + + /** + * Returns definition name. This is public because the + * <code>TokenDecoder</code> has to substitue the Name token with this + * String when writing out to sxc + * + * @return the <code>String</code> containing the name + */ + public String getName() { + String name; + + try { + name = new String(rgch, "UTF-16LE"); + } catch (UnsupportedEncodingException e){ + name = "unknown"; + } + return name; + } + + /** + * Returns a definition table which can be used by the pocket excel + * decoder to build a complete definitions table for writing to the sxc + * document + */ + public NameDefinition getNameDefinition() { + + String baseCellAddress; + getDefinition(); // This must be called first so we know the type + + baseCellAddress = "$" + wb.getSheetName(0) + ".A1"; + + NameDefinition nd = new NameDefinition(getName(),definition, baseCellAddress, isRangeType(), isExpressionType()); + return nd; + } + + /** + * Returns the definition + * + * @return the <code>String</code> containing the definition + */ + private String getDefinition() { + // pexcel sometimes creates Name definition with no defintion, bug?? + if(EndianConverter.readShort(cce)!=0) { + definition = fh.convertPXLToCalc(rgce); + definition = definition.substring(1); // remove the '=' + definition = definition.replace(',', ';'); + } + return definition; + } + + /** + * Returns the defintion + * + * @return the <code>String</code> containing the definition + */ + private boolean isRangeType() { + + return fh.isRangeType(); + } + /** + * Returns the defintion + * + * @return the <code>String</code> containing the definition + */ + private boolean isExpressionType() { + + return fh.isExpressionType(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Eof.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Eof.java new file mode 100644 index 000000000000..fbb216caad08 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Eof.java @@ -0,0 +1,72 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record used to mark the end of a section of file + */ +public class Eof implements BIFFRecord { + + /** + * Constructor + */ + public Eof() { + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>BeginningOfFile</code> + */ + public short getBiffType() { + return PocketExcelConstants.EOF_MARKER; + } + + public int read(InputStream input) throws IOException { + return 0; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + + Debug.log(Debug.TRACE,"Writing Eof record"); + + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ExtendedFormat.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ExtendedFormat.java new file mode 100644 index 000000000000..dc4780de9efe --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/ExtendedFormat.java @@ -0,0 +1,385 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.awt.Color; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.util.ColourConverter; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record descibing extended formatting information + * + */ +public class ExtendedFormat implements BIFFRecord, +org.openoffice.xmerge.converter.xml.OfficeConstants { + + private byte[] ixfnt = new byte[2]; // Index to Font Record + private byte[] ixnf = new byte[2]; + private byte[] fattributes = new byte[4]; + private byte[] fBaseAttr = new byte[2]; // base attribute flags + private byte[] fTextAttr = new byte[2]; // text attribute flags + private byte[] icvFore = new byte[2]; // Background colour of the cell + private byte[] icvFill = new byte[2]; + private byte bRight; // Right border Style + private byte bTop; // Top border style + private byte bLeft; // Left border style + private byte bBottom; // Bottom border style + private byte backstyle; + private byte borderstyle; + + public static final int TOP_BORDER = 0x01; + public static final int LEFT_BORDER = 0x02; + public static final int BOTTOM_BORDER = 0x04; + public static final int RIGHT_BORDER = 0x08; + + // Horizontal Alignment Styles + public static final int NORMAL_ALIGN = 0x00; + public static final int LEFT_ALIGN = 0x01; + public static final int CENTER_ALIGN = 0x02; + public static final int RIGHT_ALIGN = 0x03; + + // Vertical Alignment Styles + public static final int TOP_ALIGN = 0x10; + public static final int MIDDLE_ALIGN = 0x20; + public static final int BOTTOM_ALIGN = 0x30; + + public static final int WORD_WRAP = 0x08; + + /** + * Constructs an <code>ExtendedFormat</code> from the + * <code>InputStream</code> + * + * @param is <code>InputStream</code> to read from + */ + public ExtendedFormat(InputStream is) throws IOException { + read(is); + } + + /** + * Constructs a pocket Excel Document using defualt values and sets the + * font index using the specified attribute + * + * @param ixfnt index of the font this format should use + */ + public ExtendedFormat(int ixfnt, Format fmt) { + + this.ixfnt = EndianConverter.writeShort((short)ixfnt); + String category = fmt.getCategory(); + if(category.equalsIgnoreCase(CELLTYPE_CURRENCY)) { + this.ixnf = EndianConverter.writeShort((short) 0); + } else if(category.equalsIgnoreCase(CELLTYPE_DATE)) { + this.ixnf = EndianConverter.writeShort((short) 0x12); + } else if(category.equalsIgnoreCase(CELLTYPE_TIME)) { + this.ixnf = EndianConverter.writeShort((short) 0x1E); + } else { + this.ixnf = EndianConverter.writeShort((short) 0); + } + this.fattributes = new byte[] {(byte)0xFF,(byte)0xFF,(byte)0xFF,(byte)0xFF}; + this.fBaseAttr = new byte[] {(byte)0x02,(byte)0x00}; + + this.fTextAttr = new byte[] {(byte)0x00, (byte)0x00}; + + int align = fmt.getAlign(); + + // Horizontal alignment + if(align==Format.CENTER_ALIGN) { + fTextAttr[0] |= CENTER_ALIGN; + } else if(align==Format.LEFT_ALIGN) { + fTextAttr[0] |= LEFT_ALIGN; + } else if(align==Format.RIGHT_ALIGN) { + fTextAttr[0] |= RIGHT_ALIGN; + } else { + fTextAttr[0] |= NORMAL_ALIGN; + } + + int vertAlign = fmt.getVertAlign(); + + // Vertical alignment + if(vertAlign==Format.TOP_ALIGN) { + fTextAttr[0] |= TOP_ALIGN; + } else if(vertAlign==Format.BOTTOM_ALIGN) { + fTextAttr[0] |= BOTTOM_ALIGN; + } else if(vertAlign==Format.MIDDLE_ALIGN) { + fTextAttr[0] |= MIDDLE_ALIGN; + } else { + fTextAttr[0] |= BOTTOM_ALIGN; + } + + if(fmt.getAttribute(Format.WORD_WRAP)) { + fTextAttr[0] |= WORD_WRAP; + } + + if(fmt.getAttribute(Format.LEFT_BORDER)) { + fTextAttr[1] |= LEFT_BORDER; + } + if(fmt.getAttribute(Format.RIGHT_BORDER)) { + fTextAttr[1] |= RIGHT_BORDER; + } + if(fmt.getAttribute(Format.TOP_BORDER)) { + fTextAttr[1] |= TOP_BORDER; + } + if(fmt.getAttribute(Format.BOTTOM_BORDER)) { + fTextAttr[1] |= BOTTOM_BORDER; + } + + Color background = fmt.getBackground(); + if( background != null ) { + ColourConverter cc = new ColourConverter(PocketExcelConstants.cLookup); + icvFill = EndianConverter.writeShort(cc.convertFromRGB(background)); + } else { + icvFill = new byte[] {(byte)0xFF,(byte)0x00}; + } + + icvFore = new byte[] {(byte)0xFF,(byte)0x00}; + + bRight = (byte) 0xFF; + bTop = (byte) 0xFF; + bLeft = (byte) 0xFF; + bBottom = (byte) 0xFF; + backstyle = (byte) 0x00; + borderstyle = (byte) 0x00; + + } + + /** + * Get the font index this format uses + * + * @return the font index + */ + public int getFontIndex() { + return EndianConverter.readShort(ixfnt); + } + + /** + * Get the font index this format uses + * + * @return the font index + */ + public int getFormatIndex() { + return EndianConverter.readShort(ixnf); + } + + /** + * Get the font index this format uses + * + * @return the font index + */ + public int getTextAttr() { + return EndianConverter.readShort(fTextAttr); + } + + /** + * Get the background color this format uses + * + * @return the background color + */ + public Color getBackground() { + short rgb = EndianConverter.readShort(icvFill); + Color c = null; + if(rgb!=0xFF) { + ColourConverter cc = new ColourConverter(PocketExcelConstants.cLookup); + c = cc.convertToRGB(rgb); + } + return c; + } + + /** + * Get the Vertical alignment for this Format + * + * @return the alignment + */ + public int getVertAlign() { + + int mask = MIDDLE_ALIGN | BOTTOM_ALIGN | TOP_ALIGN; + int masked = fTextAttr[0] & mask; + + if(masked == MIDDLE_ALIGN) + return Format.MIDDLE_ALIGN; + + if(masked == BOTTOM_ALIGN) + return Format.BOTTOM_ALIGN; + + if(masked == TOP_ALIGN) + return Format.TOP_ALIGN; + + return Format.BOTTOM_ALIGN; + } + + /** + * Get the alignment for this Format + * + * @return the alignment + */ + public int getAlign() { + + int mask = LEFT_ALIGN | CENTER_ALIGN | RIGHT_ALIGN; + int masked = fTextAttr[0] & mask; + + if(masked == MIDDLE_ALIGN) + return Format.LEFT_ALIGN; + + if(masked == CENTER_ALIGN) + return Format.CENTER_ALIGN; + + if(masked == RIGHT_ALIGN) + return Format.RIGHT_ALIGN; + + return Format.LEFT_ALIGN; + } + + /** + * Is the word wrap set + * + * @return true if it is selected + */ + public boolean isWordWrap() { + return (!((fTextAttr[0] & WORD_WRAP) == 0)); + } + /** + * Get the border style + * + * @param side the side to test + * @return true if it is selected + */ + public boolean isBorder(int side) { + return (!((fTextAttr[1] & side) == 0)); + } + + /** + * Compare two ExtendedFormat to see if the font index is the same + * + * @param the ExtendedFormat to be used in the comaprison + * @return boolean if the two are the same otherwise false + */ + public boolean compareTo(ExtendedFormat rhs) { + + if(EndianConverter.readShort(icvFill) != + EndianConverter.readShort(rhs.icvFill)) + return false; + + if(this.getTextAttr() != rhs.getTextAttr()) + return false; + + if(this.getVertAlign() != rhs.getVertAlign()) + return false; + + if(this.getAlign() != rhs.getAlign()) + return false; + + if (this.getFontIndex() != rhs.getFontIndex()) + return false; + + if (this.getFormatIndex() != rhs.getFormatIndex()) + return false; + + return true; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>ExtendedFormat</code> + */ + public short getBiffType() { + return PocketExcelConstants.EXTENDED_FORMAT; + } + + /** + * Reads the extended format from the <code>Inputstream</code> + * + * @param input the <code>Inputstream</code>to read + * @return toal number of bytes read + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(ixfnt); + numOfBytesRead += input.read(ixnf); + numOfBytesRead += input.read(fattributes); + numOfBytesRead += input.read(fBaseAttr); + numOfBytesRead += input.read(fTextAttr); + numOfBytesRead += input.read(icvFore); + numOfBytesRead += input.read(icvFill); + bRight = (byte) input.read(); + bTop = (byte) input.read(); + bLeft = (byte) input.read(); + bBottom = (byte) input.read(); + backstyle = (byte) input.read(); + borderstyle = (byte) input.read(); + numOfBytesRead += 6; + + Debug.log(Debug.TRACE,"\tixfnt : "+ EndianConverter.readShort(ixfnt) + + " ixnf : " + EndianConverter.readShort(ixnf) + + " fattributes : " + EndianConverter.readInt(fattributes) + + " fBaseAttr : " + EndianConverter.readShort(fBaseAttr) + + "\n\tfTextAttr : " + EndianConverter.readShort(fTextAttr) + + " icvFore : " + EndianConverter.readShort(icvFore) + + " icvFill : " + EndianConverter.readShort(icvFill) + + " bRight : " + bRight + + "\n\tbTop : " + bTop + + " bLeft : " + bLeft + + " bBottom : " + bBottom + + " backstyle : " + backstyle + + " borderstyle : " + borderstyle); + return numOfBytesRead; + } + + /** + * Writes the ExtendedFormat to the <code>Outputstream<code> + * + * @param output the <code>Outputstream</code>to write to + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(ixfnt); + output.write(ixnf); + output.write(fattributes); + output.write(fBaseAttr); + output.write(fTextAttr); + output.write(icvFore); + output.write(icvFill); + output.write(bRight); + output.write(bTop); + output.write(bLeft); + output.write(bBottom); + output.write(backstyle); + output.write(borderstyle); + + Debug.log(Debug.TRACE,"Writing ExtendedFormat record"); + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FloatNumber.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FloatNumber.java new file mode 100644 index 000000000000..9399b22fc6ad --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FloatNumber.java @@ -0,0 +1,121 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + +/** + * Represents a BIFF Record describing a floating point + */ +public class FloatNumber extends CellValue { + + protected byte[] num = new byte[8]; + + /** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public FloatNumber(InputStream is) throws IOException { + read(is); + } + + /** + * Constructs a <code>FloatNumber</code> using specified attributes + * + * @param row row number + * @param col column number + * @param cellContents contents of the cell + * @param ixfe font index + */ + public FloatNumber(int row, int column, String cellContents, int ixfe) throws IOException { + + setIxfe(ixfe); + setRow(row); + setCol(column); + double cellLong = (double) Double.parseDouble(cellContents); + num = EndianConverter.writeDouble(cellLong); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>FloatNumber</code> + */ + public short getBiffType() { + return PocketExcelConstants.NUMBER_CELL; + } + + /** + * Reads a<code>FloatNumber</code> from the specified <code>InputStream</code> + * + * @param input the <code>InputStram</code> to read from + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = super.read(input); + + numOfBytesRead += input.read(num); + + Debug.log(Debug.TRACE," num : " + getString()); + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + + super.write(output); + + output.write(num); + + Debug.log(Debug.TRACE,"Writing FloatNumber record"); + } + + + /** + * Gets the numerical value the cell represents + * + * @return the <code>String</code> representing a double value + */ + public String getString() throws IOException { + + double value = EndianConverter.readDouble(num); + Double myDo = new Double(value); + return myDo.toString(); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FontDescription.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FontDescription.java new file mode 100644 index 000000000000..559853206593 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/FontDescription.java @@ -0,0 +1,287 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.awt.Color; + +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.util.ColourConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF Record descibing a font used + */ +public class FontDescription implements BIFFRecord { + + private byte[] dwHeight = new byte[2]; + private byte[] grbit = new byte[2]; + private byte[] icvFore = new byte[2]; + private byte[] bls = new byte[2]; + private byte[] Reserved2 = new byte[2]; + private byte uls; + private byte bFamily; + private byte bCharSet; + private byte Reserved3; + private byte cch; + private byte[] rgch; + + public static final int UNDERLINE = 0x01; + public static final int ITALIC = 0x02; + + /** + * Constructs a FontDescription from the bold italic and undelrine attributes + * + * @param italic Italic attribute + * @param bold Bold attribute + * @param underline Underline attribute + */ + public FontDescription(Format fmt) throws IOException { + + Debug.log(Debug.TRACE,"Building FontDescriptor based on Format : " + fmt); + + this.dwHeight = EndianConverter.writeShort((short) (fmt.getFontSize()*20)); + + grbit = new byte[] {(byte)0x00, (byte)0x00}; + bls = EndianConverter.writeShort((short) 400); + uls = 0; + + if (fmt.getAttribute(Format.ITALIC)) + grbit[0] |= ITALIC; + + if (fmt.getAttribute(Format.BOLD)) + bls = EndianConverter.writeShort((short) 700); + + if (fmt.getAttribute(Format.UNDERLINE)) + uls |= UNDERLINE; + + + bFamily = 0; + bCharSet = 0; + + String fontName = fmt.getFontName(); + if( !fontName.equals("Tahoma") && + !fontName.equals("Courier New")) { + // We will set our default font to be Tahoma + fontName = new String("Tahoma"); + } + + cch = (byte) fontName.length(); + rgch = fontName.getBytes("UTF-16LE"); + + Color foreground = fmt.getForeground(); + if( foreground != null ) { + ColourConverter cc = new ColourConverter(PocketExcelConstants.cLookup); + icvFore = EndianConverter.writeShort(cc.convertFromRGB(foreground)); + } else { + icvFore = new byte[] {(byte)0xFF,(byte)0x00}; + } + + Reserved2 = EndianConverter.writeShort((short) 0); + Reserved3 = 0; + + } + + /** + * Tests if this font descriptor defines italic + * + * @return true if italic otherwise false + */ + public boolean isItalic() { + + return (EndianConverter.readShort(grbit) == 2); + } + + /** + * Tests if this font descriptor defines underline + * + * @return true if underline otherwise false + */ + public boolean isUnderline() { + + return (uls == 1); + } + + /** + * Tests if this font descriptor defines bold + * + * @return true if bold otherwise false + */ + public boolean isBold() { + + return (EndianConverter.readShort(bls) == 700); + } + + /** + * Get the background color this format uses + * + * @return the background color + */ + public Color getForeground() { + short rgb = EndianConverter.readShort(icvFore); + Color c = null; + if(rgb!=0xFF) { + ColourConverter cc = new ColourConverter(PocketExcelConstants.cLookup); + c = cc.convertToRGB(rgb); + } + return c; + } + + /** + * Compares current font descriptor against one passed in + * + * @return true if attrbitues are the same + */ + public boolean compareTo(FontDescription rhs) { + + if(EndianConverter.readShort(icvFore) != + EndianConverter.readShort(rhs.icvFore)) + return false; + + if (EndianConverter.readShort(dwHeight) != + EndianConverter.readShort(dwHeight)) + return false; + + if (this.getFont() != rhs.getFont()) + return false; + + if (this.isBold() != rhs.isBold()) + return false; + + if (this.isUnderline() != rhs.isUnderline()) + return false; + + if (this.isItalic() != rhs.isItalic()) + return false; + + return true; + } + + + /** + * Constructs a Font Description from the <code>InputStream</code> + * + * @param is InputStream containing a <code>FontDescription</code> + */ + public FontDescription(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>FontDescription</code> + */ + public short getBiffType() { + return PocketExcelConstants.FONT_DESCRIPTION; + } + + /** + * Get the Font size + * + */ + public int getFontSize() { + return EndianConverter.readShort(dwHeight)/20; + } + + /** + * Get the font name + * + */ + public String getFont() { + + String name; + + try { + name = new String(rgch, "UTF-16LE"); + } catch (UnsupportedEncodingException e){ + name = "Tahoma"; + } + return name; + } + + /** + * Constructs a Font Description from the <code>InputStream</code> + * + * @param is InputStream containing a <code>FontDescription</code> + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(dwHeight); + numOfBytesRead += input.read(grbit); + numOfBytesRead += input.read(icvFore); + numOfBytesRead += input.read(bls); + numOfBytesRead += input.read(Reserved2); + uls = (byte) input.read(); + bFamily = (byte) input.read(); + bCharSet = (byte) input.read(); + Reserved3 = (byte) input.read(); + cch = (byte) input.read(); + numOfBytesRead += 5; + + rgch = new byte[cch*2]; + input.read(rgch, 0, cch*2); + + Debug.log(Debug.TRACE,"\tdwHeight : "+ EndianConverter.readShort(dwHeight) + + " grbit : " + EndianConverter.readShort(grbit) + + " bls : " + EndianConverter.readShort(bls) + + " uls : " + uls + + "\n\tFamily : " + bFamily + + " bCharSet : " + bCharSet + + " cch : " + cch + + " rgch : " + new String(rgch,"UTF-16LE")); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(dwHeight); + output.write(grbit); + output.write(icvFore); + output.write(bls); + output.write(Reserved2); + output.write(uls); + output.write(bFamily); + output.write(bCharSet); + output.write(Reserved3); + output.write(cch); + output.write(rgch); + + Debug.log(Debug.TRACE,"Writing FontDescription record"); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Formula.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Formula.java new file mode 100644 index 000000000000..97bea77f0811 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Formula.java @@ -0,0 +1,263 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.util.Vector; +import java.util.Enumeration; +import java.util.Calendar; +import java.util.Date; +import java.text.DateFormat; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula.FormulaHelper; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF Record describing a formula + */ +public class Formula extends CellValue implements OfficeConstants { + + private byte[] num = new byte[8]; + private byte grbit; + private byte[] cce = new byte[2]; + private byte[] rgce; + private FormulaHelper fh = new FormulaHelper(); + + /** + * Constructs a <code>Formula</code> using specified attributes + * + * @param row row number + * @param col column number + * @param cellContents contents of the cell + * @param ixfe font index + * @param value the value of the cell + */ + public Formula(int row, int column, String cellContents, int ixfe, Format fmt, Workbook wb) + throws Exception { + + fh.setWorkbook(wb); + + setRow(row); + setCol(column); + setIxfe(ixfe); + setFormula(cellContents); + + String category = fmt.getCategory(); + String value = fmt.getValue(); + + if(category.equalsIgnoreCase(CELLTYPE_BOOLEAN)) { + num[0]=(byte)0x01; + num[1]=(byte)0x00; + if(value.equalsIgnoreCase("true")) { + num[2]=(byte)0x01; + } else { + num[2]=(byte)0x00; + } + num[3]=(byte)0x00;num[4]=(byte)0x00;num[5]=(byte)0x00; + num[6]=(byte)0xFF;num[7]=(byte)0xFF; + } else if(category.equalsIgnoreCase(CELLTYPE_DATE)) { + Debug.log(Debug.TRACE,"Date Formula"); + num = EndianConverter.writeDouble(toExcelSerialDate(fmt.getValue())); + } else if(category.equalsIgnoreCase(CELLTYPE_TIME)) { + Debug.log(Debug.TRACE,"Time Formula"); + num = EndianConverter.writeDouble(toExcelSerialTime(fmt.getValue())); + } else if(category.equalsIgnoreCase(CELLTYPE_PERCENT)) { + Debug.log(Debug.TRACE,"Percent Formula"); + double percent = (double) Double.parseDouble(fmt.getValue()); + num = EndianConverter.writeDouble(percent); + } else if(category.equalsIgnoreCase(CELLTYPE_CURRENCY)) { + Debug.log(Debug.TRACE,"Currency Formula"); + } else if(category.equalsIgnoreCase(CELLTYPE_STRING)) { + Debug.log(Debug.TRACE,"String Formula"); + num[0]=(byte)0x00; + num[1]=(byte)0x00; + num[2]=(byte)0x00; + num[3]=(byte)0x00; + num[4]=(byte)0x00; + num[5]=(byte)0x00; + num[6]=(byte)0xFF; + num[7]=(byte)0xFF; + } else { + Debug.log(Debug.TRACE,"Float Formula"); + double cellLong = (double) Double.parseDouble(fmt.getValue()); + num = EndianConverter.writeDouble(cellLong); + } + } + + /** + * Translates a <code>String</code> written in infix which represents a + * formula into a byte[] what can be written to pocket excel file. + * + * @param formula string + */ + public void setFormula(String inFormula) throws Exception { + + rgce = fh.convertCalcToPXL(inFormula); + cce = EndianConverter.writeShort((short) rgce.length); + } + + /** + * Constructs a pocket Excel formula from the + * <code>InputStream</code> + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public Formula(InputStream is, Workbook wb) throws IOException { + read(is); + fh.setWorkbook(wb); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Formula</code> + */ + public short getBiffType() { + return PocketExcelConstants.FORMULA_CELL; + } + + /** + * Reads the formula data members from the stream. Byte arrays for Strings + * are doubled as they are stored as unicode + * + * @return total number of bytes read + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = super.read(input); + + numOfBytesRead += input.read(num); + grbit = (byte) input.read(); + numOfBytesRead ++; + numOfBytesRead += input.read(cce); + + int strLen = EndianConverter.readShort(cce); + rgce = new byte[strLen]; + input.read(rgce, 0, strLen); + + Debug.log(Debug.TRACE, " num : " + num + + "\n\tgrbit : " + grbit + + " cce : " + EndianConverter.readShort(cce) + + " rgce : " + new String(rgce,"UTF-16LE") + + "\n" + numOfBytesRead + " Bytes Read"); + + return numOfBytesRead; + } + + /** + * Writes the Formula record to the <code>OutputStream</code> + * + * @param the <code>OutputStream</code> being written to + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + + super.write(output); + + output.write(num); + output.write(grbit); + output.write(cce); + output.write(rgce); + + Debug.log(Debug.TRACE,"Writing Formula record"); + } + + /** + * Gets the <code>String</code> representing the cell value + * + * @return the <code>String</code> representing the cell value + */ + public String getValue() throws IOException { + + double value = EndianConverter.readDouble(num); + Double myDo = new Double(value); + return myDo.toString(); + } + + /** + * Gets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + public String getString() throws IOException { + + return fh.convertPXLToCalc(rgce); + } + + /** + * Excel dates are the number of days since 1/1/1900. This method converts + * to this date. + * + * @param s String representing a date in the form YYYY-MM-DD + * @return The excel serial date + */ + public long toExcelSerialDate(String s) throws IOException { + + int year = Integer.parseInt(s.substring(0,4)); + int month = Integer.parseInt(s.substring(5,7)); + int day = Integer.parseInt(s.substring(8,10)); + + long serialDate = (1461 * (year + 4800 + (month - 14) / 12)) / 4 + + (367 * (month - 2 - 12 * ((month - 14) / 12))) / 12 - + (3 * ((year + 4900 + (month - 14) / 12)) / 100) / 4 + + day - 2415019 - 32075; + + return serialDate; + } + + /** + * Excel times are a fraction of a 24 hour day expressed in seconds. This method converts + * to this time. + * + * @param s String representing a time in the form ??HH?MM?SS? + * @return The excel serial time + */ + public double toExcelSerialTime(String s) throws IOException { + + int hours = Integer.parseInt(s.substring(2,4)); + int mins = Integer.parseInt(s.substring(5,7)); + int secs = Integer.parseInt(s.substring(8,10)); + + int timeSecs = (hours*3600) + (mins*60) + (secs); + + double d = (double) timeSecs / (24 * 3600); + + return d; + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/LabelCell.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/LabelCell.java new file mode 100644 index 000000000000..b398e1bf519c --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/LabelCell.java @@ -0,0 +1,140 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.InputStream; +import java.io.OutputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Reperesent a BIFF Record descibing a cell containing a string + */ +public class LabelCell extends CellValue { + + private byte[] cch = new byte[2]; + private byte[] rgch; + + /** + * Constructs a <code>LabelCell</code> using specified attributes + * + * @param row row number + * @param col column number + * @param cellContents contents of the cell + * @param ixfe font index + */ + public LabelCell(int row, int column, String cellContents, int ixfe) + throws IOException { + + setLabel(cellContents); + setRow(row); + setCol(column); + setIxfe(ixfe); + } + + /** + * Reads a LabelCell from the <code>InputStream</code> + * + * @param is the <code>Inputstream</code> to read from + */ + public LabelCell(InputStream is) throws IOException { + read(is); + } + + /** + * Writes a <code>LabelCell</code> to the specified <code>Outputstream</code> + * + * @param os the <code>OutputStream</code> to write to + */ + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + + super.write(output); + + output.write(cch); + output.write(rgch); + + Debug.log(Debug.TRACE,"Writing Label record"); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>LabelCell</code> + */ + public short getBiffType() { + return PocketExcelConstants.LABEL_CELL; + } + + /** + * Reads a<code>LabelCell</code> from the specified <code>InputStream</code> + * + * @param input the <code>InputStram</code> to read from + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = super.read(input); + + numOfBytesRead += input.read(cch); + + int strLen = EndianConverter.readShort(cch)*2; + rgch = new byte[strLen]; + input.read(rgch, 0, strLen); + + Debug.log(Debug.TRACE, " cch : " + EndianConverter.readShort(cch) + + " rgch : " + new String(rgch, "UTF-16LE")); + + return numOfBytesRead; + } + + + /** + * Gets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + public String getString() throws IOException { + return (new String(rgch,"UTF-16LE")); + } + + /** + * Sets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + private void setLabel(String cellContents) throws IOException { + rgch = cellContents.getBytes("UTF-16LE"); + cch = EndianConverter.writeShort((short)cellContents.length()); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/NumberFormat.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/NumberFormat.java new file mode 100644 index 000000000000..e226ebad0203 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/NumberFormat.java @@ -0,0 +1,95 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF Record describing a number format + */ +public class NumberFormat implements BIFFRecord { + + private byte cce; + private byte[] rgch; + + /** + * Constructs a NumberFormat Record from the <code>InputStream</code> + * + * @param is InputStream containing the record data + */ + public NumberFormat(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>NumberFormat</code> + */ + public short getBiffType() { + return PocketExcelConstants.NUMBER_FORMAT; + } + + /** + * Reads the NumberFormat from the <code>InputStream</code> Byte array + * containg strings are doubled in length becuse they use unicode + * + * @return the total number of bytes read + */ + public int read(InputStream input) throws IOException { + + cce = (byte) input.read(); + int numOfBytesRead = 1; + + rgch = new byte[cce*2]; + numOfBytesRead += input.read(rgch, 0, cce*2); + + Debug.log(Debug.TRACE, "\tcce : "+ cce + + " rgch : " + new String(rgch,"UTF-16LE")); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(cce); + output.write(rgch); + + Debug.log(Debug.TRACE,"Writing NumberFormat record"); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Pane.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Pane.java new file mode 100644 index 000000000000..7af0a11e800e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Pane.java @@ -0,0 +1,219 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.awt.Point; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; + +/** + * Represents a BIFF Record that describes the number and position of unfrozen + * panes. + */ +public class Pane implements BIFFRecord { + + private byte[] x = new byte[2]; + private byte[] y = new byte[2]; + private byte[] rwTop = new byte[2]; + private byte[] colLeft = new byte[2]; + private byte pnnAcct; + + /** + * Default Constructor + */ + public Pane() { + pnnAcct = (byte) 0x02; // Default setting + } + + /** + * Constructs a Pane Record from the <code>InputStream</code> + * + * @param is InputStream containing a Pane record + */ + public Pane(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Pane</code> + */ + public short getBiffType() { + return PocketExcelConstants.PANE_INFO; + } + + /** + * Gets the split point for this pane, in the case of splits this will be + * in twips. + * + * @return the split point + */ + public Point getSplitPoint() { + + int xTwips = EndianConverter.readShort(x)/11; + int yTwips = EndianConverter.readShort(y)/15; + return (new Point(xTwips, yTwips)); + } + + /** + * Gets the freeze point for this pane, in the case of freezes this will + * be a zero-based index to either the column or row. + * + * @return the freeze point + */ + public Point getFreezePoint() { + + return (new Point(EndianConverter.readShort(x), + EndianConverter.readShort(y))); + } + + /** + * Sets the split point for this pane, coordinates are in column row units + * if the split type is freeze or twips if split type is split. + * + * @param splitType contains the X and Y split types (freeze or split) + * @param p the split point + */ + public void setSplitPoint(Point splitType, Point p) { + + if(splitType.getX()==SheetSettings.SPLIT + || splitType.getY()==SheetSettings.SPLIT) { + int yTwips = (int) p.getY(); + short yPxl = (short) (yTwips * 15); + y = EndianConverter.writeShort(yPxl); + int xTwips = (int) p.getX(); + short xPxl = (short) (xTwips * 11); + x = EndianConverter.writeShort(xPxl); + } else { + y = EndianConverter.writeShort((short) p.getY()); + x = EndianConverter.writeShort((short) p.getX()); + } + + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Pane</code> + */ + public void setPaneNumber(int paneNumber) { + pnnAcct = (byte) paneNumber; + } + + /** + * Get the pane number of the active pane + * 0 - bottom right, 1 - top right + * 2 - bottom left, 3 - top left + * + * @return the hex code for <code>Pane</code> + */ + public int getPaneNumber() { + return pnnAcct; + } + + /** + * Set the top row visible in the lower pane + * + * @param top 0-based inex of the top row + */ + public void setTop(int top) { + rwTop = EndianConverter.writeShort((short)top); + } + + /** + * Set leftmost column visible in the right pane + * + * @param left 0-based index of the leftmost column + */ + public void setLeft(int left) { + colLeft = EndianConverter.writeShort((short)left); + } + + /** + * Get the top row visible in the lower pane + * + * @return the hex code for <code>Pane</code> + */ + public int getTop() { + return EndianConverter.readShort(rwTop); + } + + /** + * Get leftmost column visible in the right pane + * + * @return 0-based index of the column + */ + public int getLeft() { + return EndianConverter.readShort(colLeft); + } + + + /** + * Reads a <code>Pane</code> record from the <code>InputStream</code> + * + * @param input <code>InputStream</code> to read from + * @return the total number of bytes read + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(x); + numOfBytesRead += input.read(y); + numOfBytesRead += input.read(rwTop); + numOfBytesRead += input.read(colLeft); + pnnAcct = (byte) input.read(); + numOfBytesRead++; + + Debug.log(Debug.TRACE, "\tx : "+ EndianConverter.readShort(x) + + " y : " + EndianConverter.readShort(y) + + " rwTop : " + EndianConverter.readShort(rwTop) + + " colLeft : " + EndianConverter.readShort(colLeft) + + " pnnAcct : " + pnnAcct); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(x); + output.write(y); + output.write(rwTop); + output.write(colLeft); + output.write(pnnAcct); + + Debug.log(Debug.TRACE,"Writing Pane record"); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Row.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Row.java new file mode 100644 index 000000000000..5e5ce6ce74df --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Row.java @@ -0,0 +1,139 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents s BIFF Record that describes the format of a column + */ +public class Row implements BIFFRecord { + + private byte[] rw = new byte[2]; + private byte[] miyRw = new byte[2]; + private byte[] grbit = new byte[2]; + private byte[] ixfe = new byte[2]; + private float scale = (float) 1; + + /** + * Constructs a pocket Excel Document from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param rw Zero based row number + * @param miyRw row height + */ + public Row(int rw, int miyRw, boolean userDefined) { + this.rw = EndianConverter.writeShort((short) rw); + miyRw *= scale; + this.miyRw = EndianConverter.writeShort((short) miyRw); + if(userDefined) { + grbit = EndianConverter.writeShort((short) 2); + } else { + grbit = EndianConverter.writeShort((short) 0); + } + ixfe = EndianConverter.writeShort((short) 0); + } + + /** + * Constructs a Row fro man <code>InputStream</code> + * + * @param is InputStream containing a Pane Record + */ + public Row(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Row</code> + */ + public short getBiffType() { + return PocketExcelConstants.ROW_DESCRIPTION; + } + + /** + * Get the height of this row + * + * @return the height of this row + */ + public short getRowHeight() { + return EndianConverter.readShort(miyRw); + } + + /** + * Get the rown number for this style + * + * @return the row this style applies to + */ + public short getRowNumber() { + return EndianConverter.readShort(rw); + } + + /** + * Reads a Row from an <code>InputStream</code> + * + * @param is InputStream containing a Pane Record + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(rw); + numOfBytesRead += input.read(miyRw); + short scaledHeight = (short) (EndianConverter.readShort(miyRw) / scale); + miyRw = EndianConverter.writeShort(scaledHeight); + numOfBytesRead += input.read(grbit); + numOfBytesRead += input.read(ixfe); + + Debug.log(Debug.TRACE,"\trw : "+ EndianConverter.readShort(rw) + + " miyRw : " + EndianConverter.readShort(miyRw) + + " grbit : " + EndianConverter.readShort(grbit) + + " ixfe : " + EndianConverter.readShort(ixfe)); + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(rw); + output.write(miyRw); + output.write(grbit); + output.write(ixfe); + + Debug.log(Debug.TRACE,"Writing Row record"); + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Selection.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Selection.java new file mode 100644 index 000000000000..dac0c2986a14 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Selection.java @@ -0,0 +1,143 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.awt.Point; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF Record that describes the selected area of a worksheet + */ +public class Selection implements BIFFRecord { + + private byte[] rwTop = new byte[2]; + private byte colLeft; + private byte[] rwBottom = new byte[2]; + private byte colRight; + private byte[] rwActive = new byte[2]; + private byte colActive; + + /** + * Default Constructor + */ + public Selection() { + this.rwTop = EndianConverter.writeShort((short) 0); + this.colLeft = 0; + this.rwBottom = EndianConverter.writeShort((short) 0); + this.colRight = 0; + this.rwActive = EndianConverter.writeShort((short) 0); + this.colActive = 0; + + } + + /** + * Constructs a Selection Record from the <code>InputStream</code> + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public Selection(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Selection</code> + */ + public short getBiffType() { + return PocketExcelConstants.CURRENT_SELECTION; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Selection</code> + */ + public Point getActiveCell() { + Point p = new Point(colActive, EndianConverter.readShort(rwActive)); + return p; + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Selection</code> + */ + public void setActiveCell(Point p) { + + colActive = (byte) p.getX(); + rwActive = EndianConverter.writeShort((short) p.getY()); + } + + /** + * Reads a Selection Record from the <code>InputStream</code> + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(rwTop); + colLeft += (byte) input.read(); + numOfBytesRead += input.read(rwBottom); + colRight += (byte) input.read(); + numOfBytesRead += input.read(rwActive); + colActive += (byte) input.read(); + numOfBytesRead += 3; + + Debug.log(Debug.TRACE,"\trwTop : "+ EndianConverter.readShort(rwTop) + + " colLeft : " + colLeft + + " rwBottom : " + EndianConverter.readShort(rwBottom) + + " colRight : "+ colRight + + " rwActive : " + EndianConverter.readShort(rwActive) + + " colActive : " + colActive); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(rwTop); + output.write(colLeft); + output.write(rwBottom); + output.write(colRight); + output.write(rwActive); + output.write(colActive); + + Debug.log(Debug.TRACE,"Writing Selection record"); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/StringValue.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/StringValue.java new file mode 100644 index 000000000000..540d1d8e6ad1 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/StringValue.java @@ -0,0 +1,125 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.io.UnsupportedEncodingException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF Record that describes the value of a formula that + * evaluates to a string + */ +public class StringValue implements BIFFRecord { + + private byte[] cch = new byte[2]; + private byte[] rgch; + + /** + * Constructs a StringValue Record from an <code>InputStream</code> + * + * @param is InputStream containing a StringValue Record + */ + public StringValue(String str) throws IOException { + cch = EndianConverter.writeShort((short) str.length()); + rgch = new byte[str.length()]; + rgch = str.getBytes("UTF-16LE"); + } + + /** + * Constructs a StringValue Record from an <code>InputStream</code> + * + * @param is InputStream containing a StringValue Record + */ + public StringValue(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>StringValue</code> + */ + public short getBiffType() { + return PocketExcelConstants.FORMULA_STRING; + } + + /** + * Reads a StringVlaue Record from an <code>InputStream</code> + * + * @param is InputStream containing a StringValue Record + */ + public int read(InputStream input) throws IOException { + + cch[0] = (byte) input.read(); + cch[1] = (byte) input.read(); + int numOfBytesRead = 1; + + int strlen = EndianConverter.readShort(cch)*2; + rgch = new byte[strlen]; + numOfBytesRead += input.read(rgch, 0, strlen); + + Debug.log(Debug.TRACE,"\tcch : "+ cch + + " rgch : " + rgch); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(cch); + output.write(rgch); + + Debug.log(Debug.TRACE,"Writing StringValue record"); + } + + /** + * Gets the <code>String</code> representing the cells contents + * + * @return the <code>String</code> representing the cells contents + */ + public String getString() throws IOException { + String name; + + try { + name = new String(rgch, "UTF-16LE"); + } catch (UnsupportedEncodingException e){ + name = "unknown"; + } + return name; + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/UnsupportedFormulaException.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/UnsupportedFormulaException.java new file mode 100644 index 000000000000..3acfd9ec2011 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/UnsupportedFormulaException.java @@ -0,0 +1,43 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.lang.Exception; + +import org.openoffice.xmerge.util.Debug; + +/** + * At the moment any functions within a formula will result in this exception + * being thrown. + */ +public class UnsupportedFormulaException extends Exception { + + public UnsupportedFormulaException(String message){ + super(message); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window1.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window1.java new file mode 100644 index 000000000000..c1c1d6ba44c0 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window1.java @@ -0,0 +1,116 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * Represents a BIFF REcord that describes workbook window attributes + */ +public class Window1 implements BIFFRecord { + + private byte[] grbit = new byte[2]; + private byte[] itabCur = new byte[2]; // index of selected worksheet + + /** + * Constructor + */ + public Window1() { + grbit = EndianConverter.writeShort((short) 0); + itabCur = EndianConverter.writeShort((short) 0); + } + + /** + * Constructs a Window1 Record from an <code>InputStream</code> + * + * @param is InputStream containing a Window1 Record + */ + public Window1(InputStream is) throws IOException{ + read(is); + } + + /** + * Set the number of the active sheet + * + * @param activeSheet number of the active sheet + */ + public void setActiveSheet(int activeSheet) { + itabCur = EndianConverter.writeShort((short) activeSheet); + } + + /** + * Get the number of the active sheet + * + * @return number of the active sheet + */ + public int getActiveSheet() { + return EndianConverter.readShort(itabCur); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Window1</code> + */ + public short getBiffType() { + return PocketExcelConstants.WINDOW_INFO; + } + + /** + * Reads a Window1 Record from an <code>InputStream</code> + * + * @param is InputStream containing a Window1 Record + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(grbit); + numOfBytesRead += input.read(itabCur); + + Debug.log(Debug.TRACE,"\tgrbit : "+ EndianConverter.readShort(grbit) + + " itabCur : " + EndianConverter.readShort(itabCur)); + + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(grbit); + output.write(itabCur); + + Debug.log(Debug.TRACE,"Writing Window1 record"); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window2.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window2.java new file mode 100644 index 000000000000..3595c1b47d37 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Window2.java @@ -0,0 +1,155 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.DataInputStream; +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.awt.Point; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; + + +/** + * Represents a BIFF Record that describes worksheet window attributes + */ +public class Window2 implements BIFFRecord { + + private final static int FROZEN = 0x08; + private final static int NOSPLIT = 0x01; + + private byte[] rwTop = new byte[2]; + private byte colLeft; + private byte[] grbit = new byte[2]; + + /** + * Constructor + */ + public Window2() { + this.rwTop = EndianConverter.writeShort((short) 0); + this.colLeft = 0; + this.grbit = EndianConverter.writeShort((short) 0); + } + + /** + * Constructs a Window2 Record from an <code>InputStream</code> + * + * @param is InputStream containing a Window2 Record + */ + public Window2(InputStream is) throws IOException { + read(is); + } + + /** + * Get the hex code for this particular <code>BIFFRecord</code> + * + * @return the hex code for <code>Window2</code> + */ + public short getBiffType() { + return PocketExcelConstants.SHEET_WINDOW_INFO; + } + + /** + * Sets the split type for this pane, the split type is the same for both + * x and y so we only test against one. + * + * @param splitType the split type based on types defined in + * <code>sheetSettings</code> + */ + public void setSplitType(Point splitType) { + if(splitType.getX()==SheetSettings.SPLIT) { + grbit[0] &= ~FROZEN; + grbit[1] &= ~NOSPLIT; + } else { + grbit[0] |= FROZEN; + grbit[1] |= NOSPLIT; + } + } + + /** + * This method tests if this object describes a freeze + * + * @return true if freeze otherwise false + */ + public boolean isFrozen() { + if((grbit[0] & FROZEN) != FROZEN) + return false; + + if((grbit[1] & NOSPLIT) != NOSPLIT) + return false; + + return true; + } + + /** + * This method tests if this object describes a split + * + * @return true if split otherwise false + */ + public boolean isSplit() { + if((grbit[0] & FROZEN) == FROZEN) + return false; + + if((grbit[1] & NOSPLIT) == NOSPLIT) + return false; + + return true; + } + + /** + * Reads a Window2 Record from an <code>InputStream</code> + * + * @param is InputStream containing a Window2 Record + */ + public int read(InputStream input) throws IOException { + + int numOfBytesRead = input.read(rwTop); + colLeft = (byte) input.read(); + numOfBytesRead++; + numOfBytesRead += input.read(grbit); + + Debug.log(Debug.TRACE,"\trwTop : "+ EndianConverter.readShort(rwTop) + + " colLeft : " + colLeft + + " grbit : " + EndianConverter.readShort(grbit)); + return numOfBytesRead; + } + + public void write(OutputStream output) throws IOException { + + output.write(getBiffType()); + output.write(rwTop); + output.write(colLeft); + output.write(grbit); + + Debug.log(Debug.TRACE,"Writing Window2 record"); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Workbook.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Workbook.java new file mode 100644 index 000000000000..70068253f7cf --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Workbook.java @@ -0,0 +1,540 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxc.Format; +import org.openoffice.xmerge.converter.xml.sxc.NameDefinition; +import org.openoffice.xmerge.converter.xml.sxc.BookSettings; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.IntArrayList; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; +import org.openoffice.xmerge.converter.xml.sxc.ColumnRowInfo; + +/** + * This class is used by <code> PxlDocument</code> to maintain pexcel + * workbooks. + * + * @author Martin Maher + */ +public class Workbook implements org.openoffice.xmerge.Document, +OfficeConstants { + + private Vector fonts = new Vector(); + private Vector extendedFormats = new Vector(); + private Vector worksheets = new Vector(); + private Vector boundsheets = new Vector(); + private Vector definedNames = new Vector(); + private static final CodePage cp; + private static final Window1 win1; + private static final BeginningOfFile bof;; + private static final Eof eof; + private String fileName; + + static { + cp = new CodePage(); + win1 = new Window1(); + bof = new BeginningOfFile(true); + eof = new Eof(); + } + + + /** + * Constructs a pocket Excel Workbook with the name of the file passed in + * as an argument. Also fills out a basic header block containing the + * minimum number of objects that can be created at this time. + * + * @param name Name of the Pocket Excel Data file. (excluding the file + * extension) + */ + public Workbook(String name) throws IOException { + fileName = name + PocketExcelConstants.FILE_EXTENSION; + Format defaultFormat = new Format(); + FontDescription fd = new FontDescription(defaultFormat); + fonts.add(fd); + ExtendedFormat xf = new ExtendedFormat(0, defaultFormat); + extendedFormats.add(xf); + } + + /** + * Constructs a pocket Excel Workbook from the + * <code>InputStream</code> and assigns it the document name passed in + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public Workbook(String name, InputStream is) throws IOException { + read(is); + fileName = name; + } + + /** + * Writes the current workbook to the <code>Outputstream</code> + * + * @param os The destination outputstream + */ + public void write(OutputStream os) throws IOException { + bof.write(os); + cp.write(os); + for(Enumeration e = definedNames.elements();e.hasMoreElements();) { + DefinedName dn = (DefinedName) e.nextElement(); + dn.write(os); + } + win1.write(os); + for(Enumeration e = fonts.elements();e.hasMoreElements();) { + FontDescription fd = (FontDescription) e.nextElement(); + fd.write(os); + } + for(Enumeration e = extendedFormats.elements();e.hasMoreElements();) { + ExtendedFormat xf = (ExtendedFormat) e.nextElement(); + xf.write(os); + } + for(Enumeration e = boundsheets.elements();e.hasMoreElements();) { + BoundSheet bs = (BoundSheet) e.nextElement(); + bs.write(os); + } + eof.write(os); + + for(Enumeration e = worksheets.elements();e.hasMoreElements();) { + Worksheet ws = (Worksheet) e.nextElement(); + ws.write(os); + } + } + + /** + * Reads a workbook from the <code>InputStream</code> and contructs a + * workbook object from it + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public void read(InputStream is) throws IOException { + + boolean done = false; + + int b = 0; + while (!done) + { + b = is.read(); + if (b == -1) + { + Debug.log(Debug.TRACE,"End of file reached"); + break; + } + + switch (b) + { + case PocketExcelConstants.DEFINED_NAME: + Debug.log(Debug.TRACE,"NAME: Defined Name (18h)"); + DefinedName dn = new DefinedName(is, this); + definedNames.add(dn); + break; + + case PocketExcelConstants.BOF_RECORD: + Debug.log(Debug.TRACE,"BOF Record"); + bof.read(is); + break; + + case PocketExcelConstants.EOF_MARKER: + Debug.log(Debug.TRACE,"EOF Marker"); + eof.read(is); + Worksheet ws = new Worksheet(this); + while(ws.read(is)) { + worksheets.add(ws); + ws = new Worksheet(this); + } + break; + + case PocketExcelConstants.FONT_DESCRIPTION: + Debug.log(Debug.TRACE,"FONT: Font Description (31h)"); + FontDescription fd = new FontDescription(is); + fonts.add(fd); + break; + + case PocketExcelConstants.WINDOW_INFO: + Debug.log(Debug.TRACE,"WINDOW1: Window Information (3Dh) [PXL 2.0]"); + win1.read(is); + break; + + case PocketExcelConstants.CODEPAGE: + Debug.log(Debug.TRACE,"CODEPAGE : Codepage and unknown fields (42h)"); + cp.read(is); + break; + + case PocketExcelConstants.BOUND_SHEET: + Debug.log(Debug.TRACE,"BOUNDSHEET: Sheet Information (85h)"); + BoundSheet bs = new BoundSheet(is); + boundsheets.add(bs); + break; + + case PocketExcelConstants.EXTENDED_FORMAT: + Debug.log(Debug.TRACE,"XF: Extended Format (E0h) [PXL 2.0]"); + ExtendedFormat xf = new ExtendedFormat(is); + extendedFormats.add(xf); + break; + + default: + b = is.read(); + break; + } + + } + is.close(); + } + + /** + * Adds a font recrod to the workbook + * + * @param f the font record to add + */ + public int addFont(FontDescription f) { + + boolean alreadyExists = false; + int i = 0; + + for(Enumeration e = fonts.elements();e.hasMoreElements();) { + FontDescription fd = (FontDescription) e.nextElement(); + if(fd.compareTo(f)) { + alreadyExists = true; + break; + } else { + i++; + } + } + + if(!alreadyExists) + fonts.add(f); + + return i; + } + + /** + * Adds a ExtendedFormat record to the workbook + * + * @param f the font recrod to add + */ + public int addExtendedFormat(Format fmt) throws IOException { + + FontDescription fd = new FontDescription(fmt); + int ixfnt = addFont(fd); + ExtendedFormat xf = new ExtendedFormat(ixfnt, fmt); + + boolean alreadyExists = false; + int i = 0; + + for(Enumeration e = extendedFormats.elements();e.hasMoreElements();) { + ExtendedFormat currentXF = (ExtendedFormat) e.nextElement(); + if(xf.compareTo(currentXF)) { + alreadyExists = true; + break; + } else if(!alreadyExists) { + i++; + } + } + + if(!alreadyExists) + extendedFormats.add(xf); + + return i; + } + + /** + * Gets a worksheet at a particular index from mthe current workbook. + * + * @param index the index of the worksheet to retrieve + */ + public Worksheet getWorksheet(int index) { + + return ((Worksheet) worksheets.elementAt(index)); + } + + /** + * Returns a FontDescription indictated by the + * index parameter passed in to the method + * + * @param ixfnt index to the FontDescriptions, this is a 0 based index + * @return FontDescription indexed by ixfe + */ + public FontDescription getFontDescription(int ixfnt) { + + return (FontDescription) fonts.elementAt(ixfnt); + } + + /** + * Returns a ExtendedFormat indictated by the + * index parameter passed in to the method + * + * @param ixfe index to the FontDescriptions, this is a 0 based index + * @return FontDescription indexed by ixfe + */ + public ExtendedFormat getExtendedFormat(int ixfe) { + + return (ExtendedFormat) extendedFormats.elementAt(ixfe); + } + + /** + * Returns an enumeration of DefinedNames for this workbook + * + * @return Enumeration for the DefinedNames + */ + public Enumeration getDefinedNames() { + + return definedNames.elements(); + } + + /** + * Returns an enumeration of <code>Settings</code> for this workbook + * + * @return Enumeration of <code>Settings</code> + */ + public BookSettings getSettings() { + + Vector settingsVector = new Vector(); + int index = 0; + for(Enumeration e = worksheets.elements();e.hasMoreElements();) { + Worksheet ws = (Worksheet) e.nextElement(); + SheetSettings s = ws.getSettings(); + s.setSheetName(getSheetName(index++)); + settingsVector.add(s); + } + BookSettings bs = new BookSettings(settingsVector); + String activeSheetName = getSheetName(win1.getActiveSheet()); + bs.setActiveSheet(activeSheetName); + return bs; + } + + /** + * Returns a <code>Vector</code> containing all the worksheet Names + * + * @return a <code>Vector</code> containing all the worksheet Names + */ + public Vector getWorksheetNames() { + + Vector wsNames = new Vector(); + + for(int i = 0;i < boundsheets.size();i++) { + wsNames.add(getSheetName(i)); + } + + return wsNames; + } + + /** + * Returns the name of the worksheet at the specified index + * + * @return a <code>String</code> containing the name of the worksheet + */ + public String getSheetName(int index) { + BoundSheet bs = (BoundSheet) boundsheets.elementAt(index); + + return bs.getSheetName(); + } + + /** + * Adds a <code>Worksheet</code> to the workbook. + * + * @return name the name of the <code>Worksheet</code> to be added + */ + public void addWorksheet(String name) throws IOException { + + BoundSheet bs = new BoundSheet(name); + boundsheets.add(bs); + + Worksheet ws = new Worksheet(); + worksheets.add(ws); + } + + /** + * Adds a cell to the current worksheet. + * + * @return the name of the <code>Worksheet</code> to be added + */ + public void addCell(int row,int col, Format fmt, String cellContents) + throws IOException { + + Worksheet currentWS = (Worksheet) worksheets.elementAt(worksheets.size()-1); + int ixfe = addExtendedFormat(fmt); + + String category = fmt.getCategory(); + + // Now the formatting is out of the way add the cell + Debug.log(Debug.TRACE,"Cell Format: " + fmt); + Debug.log(Debug.TRACE,"Row : " + row); + Debug.log(Debug.TRACE,"Col : " + col); + if(cellContents.startsWith("=")) { + try { + Formula f = new Formula(row, col, cellContents, ixfe, fmt, this); + currentWS.addCell(f); + if(category.equalsIgnoreCase(CELLTYPE_STRING)) { + StringValue sv = new StringValue(fmt.getValue()); + currentWS.addCell(sv); + } + } catch(Exception e) { + Debug.log(Debug.TRACE, "Parsing Exception thrown : " + e.getMessage()); + BoolErrCell errorCell = new BoolErrCell(row, col, ixfe, 0x2A, 1); + currentWS.addCell(errorCell); + } + } else if(category.equalsIgnoreCase(OfficeConstants.CELLTYPE_FLOAT)) { + try { + FloatNumber num = new FloatNumber(row, col, cellContents, ixfe); + currentWS.addCell(num); + } catch(Exception e) { + Debug.log(Debug.TRACE,"Error could not parse Float " + cellContents); + LabelCell lc = new LabelCell(row, col, cellContents, ixfe); + currentWS.addCell(lc); + } + } else { + if(cellContents.length()==0) { + Debug.log(Debug.TRACE, "Blank Cell"); + BlankCell b = new BlankCell(row, col, ixfe); + currentWS.addCell(b); + } else { + Debug.log(Debug.TRACE, "Label Cell : " + cellContents); + LabelCell lc = new LabelCell(row, col, cellContents, ixfe); + currentWS.addCell(lc); // three because we assume the last three + // Records in any worksheet is the selection, + // window2 and eof Records + } + } + } + + /** + * Will create a number of ColInfo records based on the column widths + * based in. + * + * @param columnRows <code>Vector</code> of <code>ColumnRowInfo</code> + */ + public void addColInfo(Vector columnRows) throws IOException { + + Worksheet currentWS = (Worksheet) worksheets.elementAt(worksheets.size()-1); + + int nCols = 0; + int nRows = 0; + + Debug.log(Debug.TRACE,"Workbook: addColInfo()"); + for(Enumeration e = columnRows.elements();e.hasMoreElements();) { + ColumnRowInfo cri =(ColumnRowInfo) e.nextElement(); + int ixfe = 0; + int size = cri.getSize(); + int repeated = cri.getRepeated(); + if(cri.isColumn()) { + Debug.log(Debug.TRACE,"Workbook: adding ColInfo width = " + size); + ColInfo newColInfo = new ColInfo( nCols, + nCols+repeated-1, + size, ixfe); + currentWS.addCol(newColInfo); + nCols += repeated; + } else if(cri.isRow()) { + + Debug.log(Debug.TRACE,"Workbook: adding Row Height = " + size); + if(!cri.isDefaultSize()) { + for(int i=0;i<repeated;i++) { + Row newRow = new Row(nRows++, size, cri.isUserDefined()); + currentWS.addRow(newRow); + } + } else { + // If it is the Default Row we don't need to add it + nRows += repeated; + } + + } + } + } + + /** + * Will create a number of ColInfo recrods based on the column widths + * based in. + * + * @param an integer list representing the column widths + */ + public void addNameDefinition(NameDefinition nameDefinition) throws IOException { + + DefinedName dn = new DefinedName(nameDefinition, this); + definedNames.add(dn); + } + + /** + * Adds the <code>BookSettings</code> for this workbook. + * + * @param book the <code>BookSettings</code> to add + */ + public void addSettings(BookSettings book) throws IOException { + + int index = 0; + Vector sheetSettings = book.getSheetSettings(); + String activeSheetName = book.getActiveSheet(); + + for(Enumeration e = worksheets.elements();e.hasMoreElements();) { + Worksheet ws = (Worksheet) e.nextElement(); + String name = getSheetName(index++); + if(activeSheetName.equals(name)) { + win1.setActiveSheet(index-1); + } + for(Enumeration eSettings = sheetSettings.elements();eSettings.hasMoreElements();) { + SheetSettings s = (SheetSettings) eSettings.nextElement(); + if(name.equals(s.getSheetName())) { + ws.addSettings(s); + } + } + } + } + + /** + * Return the filename of the pxl document without the file extension + * + * @return filename without the file extension + */ + public String getName() { + + // We have to strip off the file extension + int end = fileName.lastIndexOf("."); + String name; + if( end >= 0) // check in case the filename is already stripped + name = fileName.substring(0, end); + else + name = fileName; + + return name; + } + + /** + * Returns the filename of the pxl document with the file extension + * + * @return filename with the file extension + */ + public String getFileName() { + + return fileName; + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Worksheet.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Worksheet.java new file mode 100644 index 000000000000..722cc7ccd0fb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/Worksheet.java @@ -0,0 +1,320 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records; + +import java.io.OutputStream; +import java.io.InputStream; +import java.io.IOException; +import java.util.Vector; +import java.util.Enumeration; +import java.awt.Point; + +import org.openoffice.xmerge.util.IntArrayList; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.converter.xml.sxc.SheetSettings; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.PocketExcelConstants; + + +/** + * This class is used by <code>PxlDocument</code> to maintain pexcel + * worksheets. + * + * @author Martin Maher + */ +public class Worksheet { + + private String name; + private Workbook wb; + private Vector rows = new Vector(); + private Vector colInfo = new Vector(); + private Vector cells = new Vector(); + private DefColWidth dcw = new DefColWidth(); + private DefRowHeight drh = new DefRowHeight(); + private Window2 win2 = new Window2(); + private Selection sel = new Selection(); + private Pane p = new Pane(); + private BeginningOfFile bof; + private Eof eof; + + /** + * Writes the current workbook to the <code>Outputstream</code> + * + * @param os The destination outputstream + */ + public Worksheet(Workbook wb) { + this.wb = wb; + } + + /** + * Default Contructor + * + * @param os The destination outputstream + */ + public Worksheet() { + } + + /** + * Writes the current workbook to the <code>Outputstream</code> + * + * @param os The destination outputstream + */ + public void write(OutputStream os) throws IOException { + + bof = new BeginningOfFile(false); + bof.write(os); + dcw.write(os); + for(Enumeration e = colInfo.elements();e.hasMoreElements();) { + ColInfo ci = (ColInfo) e.nextElement(); + ci.write(os); + } + drh.write(os); + for(Enumeration e = rows.elements();e.hasMoreElements();) { + Row rw = (Row) e.nextElement(); + rw.write(os); + } + for(Enumeration e = cells.elements();e.hasMoreElements();) { + BIFFRecord cv = (BIFFRecord) e.nextElement(); + cv.write(os); + } + win2.write(os); + p.write(os); + sel.write(os); + eof = new Eof(); + eof.write(os); + } + + /** + * Reads a worksheet from the <code>InputStream</code> and contructs a + * workbook object from it + * + * @param is InputStream containing a Pocket Excel Data file. + */ + public boolean read(InputStream is) throws IOException { + + int b = is.read(); + + if (b==-1) + return false; + + while(b!=-1) { + switch (b) + { + case PocketExcelConstants.BLANK_CELL: + Debug.log(Debug.TRACE,"Blank Cell (01h)"); + BlankCell bc = new BlankCell(is); + cells.add(bc); + break; + + case PocketExcelConstants.NUMBER_CELL: + Debug.log(Debug.TRACE,"NUMBER: Cell Value, Floating-Point Number (03h)"); + FloatNumber fn = new FloatNumber(is); + cells.add(fn); + break; + + case PocketExcelConstants.LABEL_CELL: + Debug.log(Debug.TRACE,"LABEL: Cell Value, String Constant (04h)"); + LabelCell lc = new LabelCell(is); + cells.add(lc); + break; + + case PocketExcelConstants.BOOLERR_CELL: + Debug.log(Debug.TRACE,"BOOLERR: Cell Value, Boolean or Error (05h)"); + BoolErrCell bec = new BoolErrCell(is); + break; + + case PocketExcelConstants.FORMULA_CELL: + Debug.log(Debug.TRACE,"FORMULA: Cell Formula (06h)"); + Formula f = new Formula(is, wb); + cells.add(f); + break; + + case PocketExcelConstants.FORMULA_STRING: + Debug.log(Debug.TRACE,"String Value of a Formula (07h)"); + StringValue sv = new StringValue(is); + break; + + case PocketExcelConstants.ROW_DESCRIPTION: + Debug.log(Debug.TRACE,"ROW: Describes a Row (08h)"); + Row rw = new Row(is); + rows.add(rw); + break; + + case PocketExcelConstants.BOF_RECORD: + Debug.log(Debug.TRACE,"BOF Record"); + bof = new BeginningOfFile(is); + break; + + case PocketExcelConstants.EOF_MARKER: + Debug.log(Debug.TRACE,"EOF Marker"); + eof = new Eof(); + return true; + + case PocketExcelConstants.CURRENT_SELECTION: + Debug.log(Debug.TRACE,"SELECTION: Current Selection (1Dh)"); + sel = new Selection(is); + break; + + case PocketExcelConstants.NUMBER_FORMAT: + Debug.log(Debug.TRACE,"FORMAT: Number Format (1Eh)"); + NumberFormat nf = new NumberFormat(is); + break; + + case PocketExcelConstants.DEFAULT_ROW_HEIGHT: + Debug.log(Debug.TRACE,"DEFAULTROWHEIGHT: Default Row Height (25h)"); + drh = new DefRowHeight(is); + break; + + case PocketExcelConstants.SHEET_WINDOW_INFO: + Debug.log(Debug.TRACE,"WINDOW2: Sheet Window Information (3Eh) [PXL 2.0]"); + win2 = new Window2(is); + break; + + case PocketExcelConstants.PANE_INFO: + Debug.log(Debug.TRACE,"PANE: Number of Panes and their Position (41h) [PXL 2.0]"); + p = new Pane(is); + break; + + case PocketExcelConstants.DEF_COL_WIDTH: + Debug.log(Debug.TRACE,"DEFCOLWIDTH: Default Column Width (55h) [PXL 2.0]"); + dcw = new DefColWidth(is); + break; + + case PocketExcelConstants.COLINFO: + Debug.log(Debug.TRACE,"COLINFO: Column Formatting Information (7Dh) [PXL 2.0]"); + ColInfo ci = new ColInfo(is); + colInfo.add(ci); + break; + + default: + break; + } + b = is.read(); + + } + Debug.log(Debug.TRACE,"Leaving Worksheet:"); + + return true; + } + + /** + * Returns an enumerator which will be used to access individual cells + * + * @return an enumerator to the worksheet cells + */ + public Enumeration getCellEnumerator() throws IOException { + return (cells.elements()); + } + + /** + * Adds a cell to this worksheet. Current valdid celltypes are + * <code>FloatNumber</code>, <code>LabelCell</code> or <code>Formula</code> + * + * @param f the font recrod to add + */ + public void addCell(BIFFRecord br) { + cells.add(br); + } + + /** + * Adds a number of ColInfo Records to the worksheet base on a list of + * clumnwidths passed in + * + * @param list of column widths + */ + public void addRow(Row r) { + rows.add(r); + } + + /** + * Adds a number of ColInfo Records to the worksheet base on a list of + * clumnwidths passed in + * + * @param list of column widths + */ + public void addCol(ColInfo c) { + colInfo.add(c); + } + /** + * Returns an <code>Enumeration</code> to the ColInfo's for this worksheet + * + * @return an <code>Enumeration</code> to the ColInfo's + */ + public void addSettings(SheetSettings s) { + + sel.setActiveCell(s.getCursor()); + p.setLeft(s.getLeft()); + p.setTop(s.getTop()); + p.setPaneNumber(s.getPaneNumber()); + Point split = s.getSplit(); + if(split.getX()!=0 || split.getY()!=0) { + p.setSplitPoint(s.getSplitType(), split); + win2.setSplitType(s.getSplitType()); + } + } + + /** + * Returns an <code>Enumeration</code> to the ColInfo's for this worksheet + * + * @return an <code>Enumeration</code> to the ColInfo's + */ + public Enumeration getColInfos() { + + return (colInfo.elements()); + } + + /** + * Returns a <code>SheetSettings</code> object containing a collection of data + * contained in <code>Pane</code>, <code>Window2</code> and + * <code>Selection</code> + * + * @return an <code>SheetSettings</code> + */ + public SheetSettings getSettings() { + + SheetSettings s = new SheetSettings(); + s.setCursor(sel.getActiveCell()); + if(win2.isFrozen()) { + s.setFreeze(p.getFreezePoint()); + } else if(win2.isSplit()) { + s.setSplit(p.getSplitPoint()); + } + s.setPaneNumber(p.getPaneNumber()); + s.setTopLeft(p.getTop(), p.getLeft()); + return s; + } + /** + * Returns an <code>Enumeration</code> to the Rows for this worksheet + * + * @return an <code>Enumeration</code> to the Rows + */ + public Enumeration getRows() { + + return (rows.elements()); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/build.xml new file mode 100644 index 000000000000..f57eb799491c --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/build.xml @@ -0,0 +1,152 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxsp_records" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxsp_records"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxc/pexcel/records"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/BIFFRecord.java"/> + <include name="${package}/CellValue.java"/> + <include name="${package}/Workbook.java"/> + <include name="${package}/Worksheet.java"/> + <include name="${package}/BeginningOfFile.java"/> + <include name="${package}/BlankCell.java"/> + <include name="${package}/BoolErrCell.java"/> + <include name="${package}/BoundSheet.java"/> + <include name="${package}/CodePage.java"/> + <include name="${package}/ColInfo.java"/> + <include name="${package}/DefColWidth.java"/> + <include name="${package}/DefRowHeight.java"/> + <include name="${package}/DefinedName.java"/> + <include name="${package}/Eof.java"/> + <include name="${package}/ExtendedFormat.java"/> + <include name="${package}/FloatNumber.java"/> + <include name="${package}/FontDescription.java"/> + <include name="${package}/UnsupportedFormulaException.java"/> + <include name="${package}/Formula.java"/> + <include name="${package}/LabelCell.java"/> + <include name="${package}/NumberFormat.java"/> + <include name="${package}/Pane.java"/> + <include name="${package}/Row.java"/> + <include name="${package}/Selection.java"/> + <include name="${package}/StringValue.java"/> + <include name="${package}/Window1.java"/> + <include name="${package}/Window2.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaCompiler.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaCompiler.java new file mode 100644 index 000000000000..aad14dae21b3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaCompiler.java @@ -0,0 +1,272 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.util.*; +import org.openoffice.xmerge.util.Debug; + +/** + * FormulaCompiler converts Calc formula string into PocketXL bytes + * and PocketXL formula bytes into Calc Formula strings + * + * For converting from infix to Reverse Polish (or Postfix) notation the string is + * converted into a vector of Tokens and then re-ordered based on a modified version + * of the standard Infix to RPN conversion algorithms. + * <pre> + * Infix2Rpn(tokens) + * while have more tokens + * if token is operand + * push to stack + * else if token is function, argument separater, or open bracket + * push token + * extract tokens to matching close bracket into param + * Infix2Rpn(param) + * else if token is close bracket + * pop from stack into result until close bracket or function + * else + * while stack.top.priority >= token.priority + * add stack.pop to result + * push token onto stack + * </pre> + * For converting from RPN to Infix the following algorithm is applied: + * <pre> + * while have more tokens + * if token is operand + * push token to stack + * else if token is function or operator + * pop from stack number of args required by token + * apply token to params to make expr + * push expr to stack + * return stack.pop + * </pre> + */ +public class FormulaCompiler { + /** + * Constructs a FormulaCompiler object + */ + public FormulaCompiler() { + } + + private boolean isPercent(Token pt) { + return pt.getTokenID() == TokenConstants.TPERCENT; + } + + private boolean isOpenBrace(Token pt) { + return pt.getTokenID() == TokenConstants.TPAREN; + } + + private boolean isCloseBrace(Token pt) { + return pt.getValue().compareTo(")") == 0; + } + + private boolean isParamDelimiter(Token pt) { + return pt.getTokenID() == TokenConstants.TARGSEP; + } + + private boolean isBinaryOperator(Token pt) { + return false; + } + + /** + * Re-order into Infix format + * @param tokens The tokens in RPN form + * @return The vector of tokens re-ordered in Infix notation + */ + public Vector RPN2Infix(Vector tokens) { + Vector infixExpr = new Vector(15); + ListIterator iter = tokens.listIterator(); + Stack evalStack = new Stack(); + Stack args = new Stack(); + + while (iter.hasNext()) { + Token pt = (Token)iter.next(); + if (pt.isOperand()) { + Vector expr = new Vector(5); + expr.add(pt); + evalStack.push(expr); + } else if (pt.isOperator() || pt.isFunction()) { + args.clear(); + for (int i=0; i< pt.getNumArgs(); i++) { + args.push(evalStack.pop()); + } + evalStack.push(makeExpression(pt, args)); + } + } + return (Vector)evalStack.elementAt(0); + } + + /** + * Convert the infix expression to RPN. Note that open brackets are saved onto the stack to preserve the users bracketing. + * <p>Also note that the open bracket following functions is not pushed onto the stack - it is always implied when + * writing out results + * + * @param tokens The vector of tokens in Infix form + * + * @return A vector of tokens for the expression in Reverse Polish Notation order + */ + public Vector infix2RPN(Vector tokens) { + Vector rpnExpr = new Vector(15); + Stack evalStack = new Stack(); + ListIterator iter = tokens.listIterator(); + while (iter.hasNext()) { + Token pt = (Token)iter.next(); + + if (pt.isOperand()) { //Operands are output immediately + rpnExpr.add(pt); + } else if (pt.isFunction() || isParamDelimiter(pt) || isOpenBrace(pt)) { //Extract parameters after afunction or comma + evalStack.push(pt); + if (pt.isFunction()) { + iter.next(); + } + Vector param = extractParameter(iter); + Debug.log(Debug.TRACE, "Extracted parameter " + param); + rpnExpr.addAll(infix2RPN(param)); + } else if (isCloseBrace(pt)) { //Pop off stack till you meet a function or an open bracket + Token tmpTok = null; + boolean bPop = true; + while (bPop) { + if (evalStack.isEmpty()) { + bPop = false; + } else { + tmpTok = (Token)evalStack.pop(); + //if (!(isOpenBrace(tmpTok) || isParamDelimiter(tmpTok))) { //Don't output brackets and commas + if (!isParamDelimiter(tmpTok)) { //Don't output commas + rpnExpr.add(tmpTok); + } + if (tmpTok.isFunction() || isOpenBrace(tmpTok)) { + bPop = false; + } + } + } + } else { + if (!evalStack.isEmpty()) { + while (!evalStack.isEmpty() && + (((Token)evalStack.peek()).getTokenPriority() >=pt.getTokenPriority())) { + Token topTok = (Token)evalStack.peek(); + if (topTok.isFunction() || isOpenBrace(topTok)) { + break; + } + rpnExpr.add(evalStack.pop()); + } + } + evalStack.push(pt); + } + } + + while (!evalStack.isEmpty()) { + Token topTok = (Token)evalStack.peek(); + if (!(isOpenBrace(topTok) || isParamDelimiter(topTok))) { //Don't output brackets and commas + rpnExpr.add(evalStack.pop()); + } + else + { + evalStack.pop(); + } + } + return rpnExpr; + } + + /** + * Extract a parameter or bracketed sub-expression + * @param iter an iterator into the list + * @return A complete sub-expression + */ + protected Vector extractParameter(ListIterator iter) { + Vector param = new Vector(5); + int subExprCount = 0; + + while (iter.hasNext()) { + Token pt = (Token)iter.next(); + Debug.log(Debug.TRACE, "Token is " + pt + " and subExprCount is " + subExprCount); + if (isOpenBrace(pt)) { + subExprCount++; + param.add(pt); + } else if (isCloseBrace(pt)) { + if (subExprCount == 0) { + iter.previous(); + return param; + } else { + subExprCount--; + param.add(pt); + } + } else if (isParamDelimiter(pt) && (subExprCount == 0)) { + iter.previous(); + return param; + } else { + param.add(pt); + } + } + return param; + } + + /** + * Given the operator and it's operators + * @param pt The operator token + * @param args The arguments for this operator + * @return A correctly ordered expression + */ + protected Vector makeExpression(Token pt, Stack args) { + Vector tmp = new Vector(5); + TokenFactory tf = new TokenFactory(); + if (pt.isOperator()) { + if (pt.getNumArgs()==2) { //Binary operator + tmp.addAll((Vector)args.pop()); + tmp.add(pt); + tmp.addAll((Vector)args.pop()); + } else if (pt.getNumArgs() == 1) { + if(isPercent(pt)) { + tmp.addAll((Vector)args.elementAt(0)); + tmp.add(pt); + } else { + tmp.add(pt); + tmp.addAll((Vector)args.elementAt(0)); + } + if (isOpenBrace(pt)) { + tmp.add(tf.getOperatorToken(")",1)); + } + } + } else if (pt.isFunction()) { + tmp.add(pt); + tmp.add(tf.getOperatorToken("(",1)); + if (!args.isEmpty()) { + Vector v = (Vector)args.pop(); + tmp.addAll(v); + } + while (!args.isEmpty()) { + tmp.add(tf.getOperatorToken(",",1)); + Vector v = (Vector)args.pop(); + tmp.addAll(v); + + } + tmp.add(tf.getOperatorToken(")",1)); + } + + return tmp; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaHelper.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaHelper.java new file mode 100644 index 000000000000..1752d0e6336e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaHelper.java @@ -0,0 +1,153 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.io.ByteArrayOutputStream; +import java.io.IOException; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; + +/** + * This Helper class provides a simplified interface to conversion between PocketXL formula representation + * and Calc formula representation.<p> + * The class is used by {@link org.openoffice.xmerge.converter.xml.sxc.pexcel.Records.Formula} + */ +public class FormulaHelper { + + private static FormulaParser parser; + private static FormulaCompiler compiler; + private static TokenEncoder encoder; + private static TokenDecoder decoder; + private boolean rangeType = false; + private boolean expressionType = false; + + static { + parser = new FormulaParser(); + compiler = new FormulaCompiler(); + encoder = new TokenEncoder(); + decoder = new TokenDecoder(); + } + + /** + * Sets the workbook cache so that global data such as + * <code>DefinedNames</code>, <code>Boundsheets</code> can be read + * + * @param wb Wrokbook object containing all the global data + */ + public void setWorkbook(Workbook wb) { + + encoder.setWorkbook(wb); + decoder.setWorkbook(wb); + parser.setWorkbook(wb); + } + + /** + * Convertes a string representation of a calc formula into an array of PocketXL bytes + * @param formula The Formula String (e.g. 1+SUM(A1,B1)) + * + * @throws UnsupportedFunctionException Thrown if a function in the formula is nto supported by Pocket Excel + * @throws FormulaParsingException Thrown when the formula is not well formed + * + */ + public byte[] convertCalcToPXL(String formula) throws UnsupportedFunctionException, FormulaParsingException { + + Vector parseTokens = parser.parse(formula); + Vector rpnTokens = compiler.infix2RPN(parseTokens); + + ByteArrayOutputStream bytes = null; + try { + bytes = new ByteArrayOutputStream(); + for (Enumeration e = rpnTokens.elements(); e.hasMoreElements();) { + Token t = (Token)e.nextElement(); + bytes.write(encoder.getByte(t)); + } + } catch (IOException e) { + } + + return bytes.toByteArray(); + } + + /** + * Converts a PocketXL byte array into a Calc function string + * @param formula A byte array that contains the PocketXL bytes for a formula + * + */ + public String convertPXLToCalc(byte[] formula) { + + Vector parseTokens = decoder.getTokenVector(formula); + Vector infixTokens = compiler.RPN2Infix(parseTokens); + + StringBuffer buff = new StringBuffer(); + for (Enumeration e = infixTokens.elements();e.hasMoreElements();) { + Token t = (Token)e.nextElement(); + buff.append(t.toString()); + // If we are parsing a Name definition we need to know if it is of + // type range or expression + if(!t.isOperand()) { + expressionType = true; + } + } + if(!expressionType) { + rangeType = true; + } + return "=" + buff.toString(); + } + + /** + * Returns a boolean indicating whether or not the byte[] parsed is of + * type range. This means it contains only a cell reference and no + * operators. This is necessry because the syntax for range and expression + * types differs. This is only of interest when dealing with + * <code>DefinedNames</code> and not <code>Formula</code> + * + * @return a boolean true if of type range otherwise false + * + */ + public boolean isRangeType() { + + return rangeType; + } + + /** + * Returns a boolean indicating whether or not the byte[] parsed is of + * type expression. This means it contains operators. This is necessry + * because the syntax for range and expression types differs. This is + * only of interest when dealing with <code>DefinedNames</code> and not + * <code>Formula</code> + * + * @return a boolean true if of type expression otherwise false + * + */ + public boolean isExpressionType() { + + return expressionType; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParser.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParser.java new file mode 100644 index 000000000000..ead9a974d23d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParser.java @@ -0,0 +1,564 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + + +import java.io.*; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.util.Debug; + +/** + * This is the Formula Parser based on an article written by Jack Crenshaw. It is a + * top down parser with some basic error handling. It handles + * +,-,*,/,>,<,>=,<=,=,<>, unary + and - as well as functions. + * The BNF notation for this parser is + * <pre> + * <expression> ::= <unary op> <term> [<addop>|<logop> <term>] + * <term> ::= <factor> [<mulop> <factor>] + * <factor> ::= <number>[%] | <CellRef> | <QuoteString> | <expression> + * </pre> + */ +public class FormulaParser { + + private char look; + private String formulaStr; + private int index = 1; + private TokenFactory tokenFactory; + private Vector tokenVector; + private Workbook wb; + + /** + * Default constructor + */ + public FormulaParser() { + + Debug.log(Debug.TRACE,"Creating a Formula Parser"); + tokenFactory = new TokenFactory(); + tokenVector = new Vector(); + } + + /** + * + */ + public void setWorkbook(Workbook wb) { + + this.wb = wb; + } + + /** + * Parse method for parsing from a String to a byte[] + * + * @param formula A <code>String</code> representation of a formula + * starting with the '=' character + * @return A <code>Vector</code> containing the parsed <code>Token</code>s + */ + public Vector parse(String formula) throws FormulaParsingException { + + index = 1; + look = ' '; + tokenVector.clear(); + if(formula.startsWith("=")) { + formulaStr = formula; + Debug.log(Debug.TRACE,"Creating a Formula Parser for " + formulaStr); + getChar(); + expression(); + } else { + throw new FormulaParsingException("No equals found!" + makeErrorString()); + } + return tokenVector; + } + + /** + * Identify + and - operators + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isAddOp(char c) { + return (c == '-') || (c == '+'); + } + + /** + * Determine if the current character is a multiop + * + * @return A boolean returning the result of the comparison + */ + private boolean isMultiOp() { + return look=='*' || look =='/' || look == '^' || look == '&'; + } + + /** + * Identify <, >, <=, >=, =, <> using the index to find the current character(s) + * + * @return A boolean returning the result of the comparison + */ + private boolean isLogicalOp() { + if (!isLogicalOpChar(look)) { + return false; + } else if ((index+1) >= formulaStr.length()) {//logical operators in their own right : if at end then return true + return true; + } else if (!isLogicalOpChar(formulaStr.charAt(index))) { // we have >, < or = on their own + return true; + } else if ((look == '<') && ((formulaStr.charAt(index) == '>') || formulaStr.charAt(index) == '=')) { // <>, or <= + return true; + } else if ((look == '>') && (formulaStr.charAt(index) == '=')) { // >= + return true; + } + + return false; + } + + /** + * Identify <, >, <=, >=, =, <> + * + * @param The <code>String</code> which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isLogicalOp(String op) { + return ((op.compareTo(">") == 0) || + (op.compareTo("<") == 0) || + (op.compareTo(">=") == 0) || + (op.compareTo("<=") == 0) || + (op.compareTo("=") == 0) || + (op.compareTo("<>") == 0)); + } + + + /** + * Identify characters that MAY be logical operator characters + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isLogicalOpChar(char c) { + return (c == '>') || (c == '<') || (c == '='); + } + + /** + * Identify special Cell Reference charaters + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isCellRefSpecialChar(char c) { + return (c == ':') || (c == '$') || (c == '.'); + } + + /** + * Identify letters + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isAlpha(char c) { + return(Character.isLetter(c)); + } + + /** + * Identify numbers + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isDigit(char c) { + return(Character.isDigit(c)); + } + + /** + * Identify numbers + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isPercent(char c) { + return (c == '%'); + } + + /** + * Identify letters or numbers + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isAlphaNum(char c) { + return(isAlpha(c) || isDigit(c)); + } + + /** + * Identify valid Characters for cell references + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isCellRefChar(char c) { + return(isAlpha(c) || isDigit(c) || isCellRefSpecialChar(c)); + } + + /** + * Test if current character is a match and move to next character + * + * @param c The character which is to be matched + */ + private void match(char c) throws FormulaParsingException { + + if(look==c) { + Debug.log(Debug.TRACE,"Operator Found : " + look); + getChar(); + skipWhite(); + } + else + throw new FormulaParsingException("Unexpected character '" + c + "'" + makeErrorString()); + } + + /** + * Test if current character is a match and move to next character + * + * @param symbol The <code>String</code> to be matched. + */ + private void match(String symbol) throws FormulaParsingException { + + int numChars = symbol.length(); + boolean bContinue = true; + for (int i=0;i<numChars && bContinue; i++) { + if (look == symbol.charAt(i)) { + bContinue = getChar(); + skipWhite(); + } else { + throw new FormulaParsingException("Unexpected character '" + symbol + "'" + makeErrorString()); + } + } + } + + /** + * Skip over whitespaces (ie. spaces and tabs) + */ + private void skipWhite() throws FormulaParsingException { + + boolean success = true; + + while(Character.isWhitespace(look) && success) { + success = getChar(); + } + } + + /** + * This is a factor for multiplication and division operators + */ + private void factor() throws FormulaParsingException { + if(isAddOp(look)) { // handle unary addop + Character ch = new Character(look); + match(look); + tokenVector.add(tokenFactory.getOperatorToken(ch.toString(), 1)); + } + if(look=='(') { + match('('); + tokenVector.add(tokenFactory.getOperatorToken("(", 1)); + expression(); + match(')'); + tokenVector.add(tokenFactory.getOperatorToken(")", 1)); + } else if(isDigit(look)){ + getNum(); + } else { + ident(); + } + } + + /** + * Pulls the next character from the <code>String</code> + * + * @return boolean false if the end if the statement + * is reached otherwise true + */ + private boolean getChar() throws FormulaParsingException { + + boolean success = true; + + if(index<formulaStr.length()) { + look = formulaStr.charAt(index); + index++; + if(look==',') + success = false; + } else { + success = false; + } + return success; + } + + /** + * Parses the number of arguments in a function + * + * @return The number of arguments + */ + private int arguments() throws FormulaParsingException { + int numArgs; + + skipWhite(); + if(look==')') + numArgs = 0; + else + numArgs = 1; + + while(look!=')') { + expression(); + if(look==',') { + numArgs++; + match(','); + tokenVector.add(tokenFactory.getOperatorToken(",", 1)); + } + } + return numArgs; + } + + /** + * Test to see if we have come across a cell reference or a Name + * Definition. + */ + private boolean isCellRef(String s) { + char c; + boolean result = false; + + for(int i = 0;i<s.length();i++) { + c = s.charAt(i); + if(isCellRefSpecialChar(c)) { + result = true; + break; + } + } + + // if it is a simple cell reference then there will not be a cell + // reference 'special char' so we should also look for a digit + if(!result) { + if(isDigit(s.charAt(1)) || isDigit(s.charAt(2))) { + result = true; + } + } + return result; + } + + /** + * Test to see if we have come across a cell reference or a function and + * add the resulting toek nto the tokenVector. + */ + private void ident() throws FormulaParsingException { + + String cell = getTokenString(); + if(look=='(') { + Debug.log(Debug.TRACE,"Found Function : " + cell); + + int index = tokenVector.size(); + match('('); + tokenVector.add(tokenFactory.getOperatorToken("(", 1)); + int numArgs = arguments(); + match(')'); + tokenVector.add(tokenFactory.getOperatorToken(")", 1)); + tokenVector.insertElementAt(tokenFactory.getFunctionToken(cell, numArgs), index); + } else { + + if(cell.indexOf('.')!=-1) { + String cellRef = cell.substring(cell.indexOf('.') + 1, cell.length()); + if(cellRef.indexOf(':')!=-1) { + tokenVector.add(tokenFactory.getOperandToken(cell, "3D_CELL_AREA_REFERENCE")); + } else { + tokenVector.add(tokenFactory.getOperandToken(cell, "3D_CELL_REFERENCE")); + } + } else if(cell.indexOf(':')!=-1) { + tokenVector.add(tokenFactory.getOperandToken(cell, "CELL_AREA_REFERENCE")); + } else if(isCellRef(cell)) { + tokenVector.add(tokenFactory.getOperandToken(cell, "CELL_REFERENCE")); + } else { + tokenVector.add(tokenFactory.getOperandToken(cell, "NAME")); + } + } + } + + /** + * Will keep pulling valid logical operators from the formula and return + * the resultant <code>String</code>. + * + * @return a <code>String<code> representing a logical operator + */ + private String getLogicalOperator() throws FormulaParsingException { + String op = new String(); + boolean status; + + do { + op += look; + status = getChar(); + } while(isLogicalOpChar(look) && status); + skipWhite(); + return op; + } + + /** + * Keeps pulling characters from the statement until we get an + * operator and returns the resulting string. + * + * @return A <code>String</code>representing the next token + */ + private String getTokenString() throws FormulaParsingException { + + if(!isAlpha(look) && look!='$') + throw new FormulaParsingException("Expected Cell Reference" + makeErrorString()); + else { + String cell = new String(); + boolean status; + do { + cell += look; + status = getChar(); + } while(isCellRefChar(look) && status); + skipWhite(); + return cell; + } + } + + /** + * Keeps pulling numbers from the statement and add the resulting integer + * token to the tokenVector. + */ + private void getNum() throws FormulaParsingException { + + Debug.log(Debug.TRACE,"getNum : "); + if(!isDigit(look)) + throw new FormulaParsingException("Expected Integer" + makeErrorString()); + else { + String num = new String(); + boolean status; + + do { + num += look; + status = getChar(); + } while((isDigit(look) || ((look == '.') && isDigit(formulaStr.charAt(index)))) && status); + skipWhite(); + tokenVector.add(tokenFactory.getOperandToken(num, "INTEGER")); + if(isPercent(look)) { + match(look); + tokenVector.add(tokenFactory.getOperatorToken("%", 1)); + Debug.log(Debug.TRACE,"Added Percent token to Vector: "); + } + Debug.log(Debug.TRACE,"Number parsed : " + num); + } + } + + + /** + * Term will parse multiplication/division expressions + */ + private void term() throws FormulaParsingException { + factor(); + while(isMultiOp()) { + multiOp(Character.toString(look)); + } + } + + /** + * Expression is the entry point for the parser. It is the code + * that parses addition/subtraction expressions. + */ + private void expression() throws FormulaParsingException { + + if (look == '"') { //Extract a quoted string... + StringBuffer buff = new StringBuffer(); + boolean success = true; + success = getChar(); + while (look != '"' && success) { + buff.append(look); + success = getChar(); + } + + if (look != '"') { //We've reached the end of the string without getting a closing quote + throw new FormulaParsingException("Expected closing quote." + makeErrorString()); + } else { + tokenVector.add(tokenFactory.getOperandToken(buff.toString(), "STRING")); + getChar(); //Move on to the next character + } + } else { + term(); + } + while(isAddOp(look) || isLogicalOp()) { + if (isAddOp(look)) { + addOp(Character.toString(look)); + } else if (isLogicalOp()) { + logicalOp(); + } + } + } + + /** + * Test to see if the next token (represented as a <code>String</code>) is + * the same as the String passed in. Move the index along to the end of + * that String and add that <code>Token</code> to the tokenVector. Then + * call <code>term</code> to parse the right hand side of the operator. + * + * @param op A <code>String</code> representing the operator + */ + private void addOp(String op) throws FormulaParsingException { + match(op); + tokenVector.add(tokenFactory.getOperatorToken(op, 2)); + term(); + } + + /** + * Test to see if the next token (represented as a <code>String</code>) is + * the same as the String passed in. Move the index along to the end of + * that String and add that <code>Token</code> to the tokenVector. Then + * call <code>factor</code> to parse the right hand side of the operator. + * + * @param op A <code>String</code> representing the operator + */ + private void multiOp(String op) throws FormulaParsingException { + match(op); + tokenVector.add(tokenFactory.getOperatorToken(op, 2)); + factor(); + } + + /** + * Pull a logical operator starting at the current index, add a token for + * that operator to the tokenVector and call <code>term<code> to parse the + * right hand side of the operator + */ + private void logicalOp() throws FormulaParsingException { + String op = getLogicalOperator(); + tokenVector.add(tokenFactory.getOperatorToken(op, 2)); + term(); + } + + private String makeErrorString() { + StringBuffer buff = new StringBuffer(); + for (int i=0; i<index-1; i++) { + buff.append(' '); + } + + buff.append('^'); + return "\n\t" + formulaStr + "\n\t" + buff.toString(); + } + } + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParsingException.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParsingException.java new file mode 100644 index 000000000000..631244ad0d96 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FormulaParsingException.java @@ -0,0 +1,46 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +/* + * If the formula failed to be parsed properly this exception will be thrown + * + * Martin Maher + */ + +import java.io.*; + +import org.openoffice.xmerge.util.Debug; + +public class FormulaParsingException extends Exception { + + public FormulaParsingException(String message) { + super(message); + } + } diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FunctionLookup.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FunctionLookup.java new file mode 100644 index 000000000000..b4f7dab3a681 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/FunctionLookup.java @@ -0,0 +1,207 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import org.openoffice.xmerge.util.Debug; + +import java.util.HashMap; + +public class FunctionLookup extends SymbolLookup { + + private HashMap stringToArgs = null; + + /** + * The default constructor - invokes {@link #initialize() initialize()} + */ + public FunctionLookup() { + initialize(); + } + + /** + * Initialize the lookup table for functions + */ + public void initialize() { + if ((stringToID != null) || (idToString != null) || (stringToArgs !=null)) { + return; + } + stringToID = new HashMap(); + idToString = new HashMap(); + stringToArgs = new HashMap(); + + // Functions with Variable number of Arguments + // Math and Trig + addEntry("SUM", TokenConstants.TSUM, -1); + addEntry("MIN", TokenConstants.TMIN, -1); + addEntry("PRODUCT", TokenConstants.TPRODUCT, -1); + addEntry("LOG", TokenConstants.TLOG, -1); + addEntry("SUMIF", TokenConstants.TSUMIF, -1); + addEntry("TRUNC", TokenConstants.TRUNC, -1); + // Financial + addEntry("DDB", TokenConstants.TDDB, -1); + addEntry("FV", TokenConstants.TFV, -1); + addEntry("IRR", TokenConstants.TIRR, -1); + addEntry("NPER", TokenConstants.TNPER, -1); + addEntry("NPV", TokenConstants.TNPV, -1); + addEntry("PMT", TokenConstants.TPMT, -1); + addEntry("PV", TokenConstants.TPV, -1); + addEntry("RATE", TokenConstants.TRATE, -1); + // Statistical + addEntry("AVERAGE", TokenConstants.TAVERAGE, -1); + addEntry("COUNT", TokenConstants.TCOUNT, -1); + addEntry("COUNTA", TokenConstants.TCOUNTA, -1); + addEntry("MAX", TokenConstants.TMAX, -1 ); + addEntry("MIN", TokenConstants.TMIN, -1); + addEntry("STDEV", TokenConstants.TSTDEV, -1 ); + addEntry("STDEVP", TokenConstants.TSTDEVP, -1 ); + addEntry("VAR", TokenConstants.TVAR, -1); + addEntry("VARP", TokenConstants.TVARP, -1); + // Lookup + addEntry("CHOOSE", TokenConstants.TCHOOSE, -1); + addEntry("HLOOKUP", TokenConstants.THLOOKUP, -1); + addEntry("INDEX", TokenConstants.TINDEX, -1); + addEntry("MATCH", TokenConstants.TMATCH, -1) ; + addEntry("VLOOKUP", TokenConstants.TVLOOKUP, -1); + // Text + addEntry("RIGHT", TokenConstants.TRIGHT, -1); + addEntry("SUBSTITUTE", TokenConstants.TSUBSTITUTE, -1); + addEntry("FIND", TokenConstants.TFIND, -1); + addEntry("LEFT", TokenConstants.TLEFT, -1); + // Logical + addEntry("AND", TokenConstants.TAND, -1 ); + addEntry("IF", TokenConstants.TIF, -1) ; + addEntry("OR", TokenConstants.TOR, -1); + + // Functions with Fixed number of Arguments + // Math and Trig + addEntry("ABS", TokenConstants.TABS, 1); + addEntry("ACOS", TokenConstants.TACOS, 1); + addEntry("ASIN", TokenConstants.TASIN, 1); + addEntry("ATAN", TokenConstants.TATAN, 1); + addEntry("ATAN2", TokenConstants.TATAN2, 1); + addEntry("COS", TokenConstants.TCOS, 1); + addEntry("COUNTIF", TokenConstants.TCOUNTIF, 1); + addEntry("DEGREES", TokenConstants.TDEGREES, 1); + addEntry("EXP", TokenConstants.TEXP, 1); + addEntry("FACT", TokenConstants.TFACT, 1); + addEntry("INT", TokenConstants.TINTE, 1); + addEntry("LN", TokenConstants.TLN, 1); + addEntry("LOG10", TokenConstants.TLOG10, 1); + addEntry("MOD", TokenConstants.TMOD, 1); + addEntry("PI", TokenConstants.TPI, 0); + addEntry("POWER", TokenConstants.TPOWERF, 2); + addEntry("RADIANS", TokenConstants.TRADIANS, 1); + addEntry("RAND", TokenConstants.TRAND, 1); + addEntry("ROUND", TokenConstants.TROUND, 1); + addEntry("SQRT", TokenConstants.TSQRT, 1); + addEntry("TAN", TokenConstants.TTAN, 1); + addEntry("SIN", TokenConstants.TSIN, 1); + // Financial + addEntry("SLN", TokenConstants.TSLN, 3); + addEntry("SYD", TokenConstants.TSYD, 4); + // Date and Time + addEntry("DATE", TokenConstants.TDATE, 3); + addEntry("DATEVALUE", TokenConstants.TDATEVALUE, 1); + addEntry("DAY", TokenConstants.TDAY, 1); + addEntry("HOUR", TokenConstants.THOUR, 1); + addEntry("MINUTE", TokenConstants.TMINUTE, 1 ); + addEntry("MONTH", TokenConstants.TMONTH, 1); + addEntry("NOW", TokenConstants.TNOW, 0); + addEntry("SECOND", TokenConstants.TSECOND, 1); + addEntry("TIME", TokenConstants.TTIME, 3); + addEntry("TIMEVALUE", TokenConstants.TTIMEVALUE, 1); + addEntry("YEAR", TokenConstants.TYEAR, 1); + // Statistical + addEntry("COUNTBLANK", TokenConstants.TCOUNTBLANK, 1); + // lookup + addEntry("COLUMNS", TokenConstants.TCOLUMNS, 1); + addEntry("ROWS", TokenConstants.TROWS, 1); + // Database + addEntry("DAVERAGE", TokenConstants.TDAVAERAGE, 3); + addEntry("DCOUNT", TokenConstants.TDCOUNT, 3); + addEntry("DCOUNTA", TokenConstants.TDCOUNTA, 2); + addEntry("DGET", TokenConstants.TDGET, 3); + addEntry("DMAX", TokenConstants.TDMAX, 3); + addEntry("DMIN", TokenConstants.TDMIN, 3); + addEntry("DPRODUCT", TokenConstants.TDPRODUCT, 3); + addEntry("DSTDEV", TokenConstants.TDSTDEV, 3); + addEntry("DSTDEVP", TokenConstants.TDSTDEVP, 3) ; + addEntry("DSUM", TokenConstants.TDSUM, 3); + addEntry("DVAR", TokenConstants.TDVAR, 3); + addEntry("DVARP", TokenConstants.TDVARP, 3); + // Text + addEntry("EXACT", TokenConstants.TEXACT, 2); + addEntry("LEN", TokenConstants.TLEN, 1); + addEntry("LOWER", TokenConstants.TLOWER, 1); + addEntry("MID", TokenConstants.TMID, 3); // ?????? + addEntry("PROPER", TokenConstants.TPROPER, 1); + addEntry("REPLACE", TokenConstants.TREPLACE, 4); + addEntry("REPT", TokenConstants.TREPT, 2); + addEntry("T", TokenConstants.TT, 1); + addEntry("TRIM", TokenConstants.TRIM, 1); + addEntry("UPPER", TokenConstants.TUPPER, 1); + addEntry("VALUE", TokenConstants.TVALUE, 1); + // Logical + addEntry("FALSE", TokenConstants.TFALSE, 0); + addEntry("NOT", TokenConstants.TNOT, 1); + addEntry("TRUE", TokenConstants.TTRUE, 0); + // Informational + addEntry("ERRORTYPE", TokenConstants.TERRORTYPE, 1); + addEntry("ISBLANK", TokenConstants.TISBLANK, 1); + addEntry("ISERR", TokenConstants.TISERR, 1); + addEntry("ISERROR", TokenConstants.TISERROR, 1); + addEntry("ISLOGICAL", TokenConstants.TISLOGICAL, 1); + addEntry("ISNA", TokenConstants.TISNA, 1); + addEntry("ISNONTEXT", TokenConstants.TISNONTEXT, 1); + addEntry("ISNUMBER", TokenConstants.TISNUMBER, 1); + addEntry("ISTEXT", TokenConstants.TISTEXT, 1); + addEntry("N", TokenConstants.TN, 1); + addEntry("NA", TokenConstants.TNA, 0); + + } + + /** + * Associate a function with an identifier and specifiy the number of arguments for that function + * @param symbol The function string that will act as the key in the lookup table + * @param id The identifier for the function + * @param args The number of arguments this function requires + */ + public void addEntry(String symbol, int id, int args) { + addEntry(symbol, id); + stringToArgs.put(symbol, new Integer(args)); + } + + /** + * Retrieve the number of arguments for this function + * @param symbol The function name + * @return The number of arguments required by this function + */ + public int getArgCountFromString(String symbol) { + return ((Integer)stringToArgs.get(symbol)).intValue(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperandLookup.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperandLookup.java new file mode 100644 index 000000000000..67f79c561234 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperandLookup.java @@ -0,0 +1,65 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; +import java.util.HashMap; + +import org.openoffice.xmerge.util.Debug; + +/** + * A lookup table containing information about operands + */ +public class OperandLookup extends SymbolLookup { + + /** + * The default constructor - invokes {@link #initialize() initialize()} + */ + public OperandLookup() { + initialize(); + } + + /** + * Initialize the lookup table for operands + */ + public void initialize() { + if ((stringToID != null) || (idToString != null)) { + return; + } + stringToID = new HashMap(); + idToString = new HashMap(); + addEntry("CELL_REFERENCE", TokenConstants.TREF); + addEntry("CELL_AREA_REFERENCE", TokenConstants.TAREA); + addEntry("INTEGER", TokenConstants.TNUM); + addEntry("NUMBER", TokenConstants.TNUM); + addEntry("STRING", TokenConstants.TSTRING); + addEntry("NAME", TokenConstants.TNAME); + addEntry("3D_CELL_REFERENCE", TokenConstants.TREF3D); + addEntry("3D_CELL_AREA_REFERENCE", TokenConstants.TAREA3D); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperatorLookup.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperatorLookup.java new file mode 100644 index 000000000000..03d09f917a18 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/OperatorLookup.java @@ -0,0 +1,76 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.util.HashMap; + +import org.openoffice.xmerge.util.Debug; + +/** + * A lookup table containing information about operators + */ +public class OperatorLookup extends SymbolLookup { + + /** + * The default constructor - invokes {@link #initialize() initialize()} + */ + public OperatorLookup() { + initialize(); + } + + /** + * Initialize the lookup table for operators + */ + public void initialize() { + if ((stringToID != null) || (idToString != null)) { + return; + } + stringToID = new HashMap(); + idToString = new HashMap(); + addEntry("UNARY_PLUS", TokenConstants.TUPLUS); + addEntry("UNARY_MINUS", TokenConstants.TUMINUS); + addEntry("%", TokenConstants.TPERCENT); + addEntry("+", TokenConstants.TADD); + addEntry("-", TokenConstants.TSUB); + addEntry("*", TokenConstants.TMUL); + addEntry("/", TokenConstants.TDIV); + addEntry(",", TokenConstants.TARGSEP); + addEntry("^", TokenConstants.TPOWER); + addEntry("&", TokenConstants.TCONCAT); + addEntry("(", TokenConstants.TPAREN); + addEntry(")", TokenConstants.TCLOSEPAREN); + addEntry("<", TokenConstants.TLESS); + addEntry(">", TokenConstants.TGREATER); + addEntry(">=", TokenConstants.TGTEQUALS); + addEntry("<=", TokenConstants.TLESSEQUALS); + addEntry("=", TokenConstants.TEQUALS); + addEntry("<>", TokenConstants.TNEQUALS); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/ParseToken.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/ParseToken.java new file mode 100644 index 000000000000..e78234ca1adc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/ParseToken.java @@ -0,0 +1,43 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +public interface ParseToken +{ + public boolean isOperand(); + public boolean isOperator(); + public int getTokenType(); + + //GENERIC TOKENS (MOSTLY UNUSED + public static final int TOKEN_OPERATOR = 1; + public static final int TOKEN_OPERAND = 2; + public static final int TOKEN_FUNCTION_FIXED = 3; + public static final int TOKEN_FUNCTION_VARIABLE = 4; + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/PrecedenceTable.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/PrecedenceTable.java new file mode 100644 index 000000000000..fbe24bb4fff2 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/PrecedenceTable.java @@ -0,0 +1,86 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.util.HashMap; + +/** + * This class defines the precedence applied to each operator when performing a conversion + * {@link org.openoffice.xmerge.converter.xml.sxc.pexcel.Records.formula.FormulaCompiler.infix2 from infix to RPN.}. + */ +public class PrecedenceTable { + public static final int DEFAULT_PRECEDENCE = 0; + public static final int EQNEQ_PRECEDENCE = 1; // =, <> + public static final int GTLTEQ_PRECEDENCE = 1; // >=, <= + public static final int GTLT_PRECEDENCE = 2; // >, < + public static final int ADDOP_PRECEDENCE = 4; // +, - + public static final int MULTOP_PRECEDENCE = 5; // *, / + public static final int FACTOR_PRECEDENCE = 6; // ^ + public static final int CONCAT_PRECEDENCE = 6; // & + public static final int UNARY_PRECEDENCE = 7; // !, Unary +, Unary - + public static final int PAREN_PRECEDENCE = 8; // (, ) + public static final int FUNCTION_PRECEDENCE = 8; + public static final int COMMA_PRECEDENCE = 8; + + private static HashMap map; + static { + map = new HashMap(); + + map.put("%", new Integer(UNARY_PRECEDENCE)); + map.put("+", new Integer(ADDOP_PRECEDENCE)); + map.put("-", new Integer(ADDOP_PRECEDENCE)); + map.put("*", new Integer(MULTOP_PRECEDENCE)); + map.put("/", new Integer(MULTOP_PRECEDENCE)); + map.put("(", new Integer(PAREN_PRECEDENCE)); + map.put(")", new Integer(PAREN_PRECEDENCE)); + map.put(",", new Integer(COMMA_PRECEDENCE)); + map.put(">", new Integer(GTLT_PRECEDENCE)); + map.put("<", new Integer(GTLT_PRECEDENCE)); + map.put("=", new Integer(EQNEQ_PRECEDENCE)); + map.put("&", new Integer(CONCAT_PRECEDENCE)); + map.put("^", new Integer(FACTOR_PRECEDENCE)); + map.put(">=", new Integer(GTLTEQ_PRECEDENCE)); + map.put("<=", new Integer(GTLTEQ_PRECEDENCE)); + map.put("<>", new Integer(EQNEQ_PRECEDENCE)); + map.put("FUNCTION", new Integer(FUNCTION_PRECEDENCE)); + } + + /** + * Retrieve the precedence value for a given operator. + * @param op Look up the precedence for this operator + * @return an integer representing the integer value of the operator + */ + public static int getPrecedence(String op) { + Object obj = map.get(op); + if (obj == null) { + return DEFAULT_PRECEDENCE; + } + return ((Integer)obj).intValue(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/SymbolLookup.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/SymbolLookup.java new file mode 100644 index 000000000000..1399c57d2875 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/SymbolLookup.java @@ -0,0 +1,82 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.util.HashMap; + +/** + * This interface defines the attributes of a lookup table for this plugin. + * Symbols will generally be either operators (_, -, *, etc) or funtion names. + */ +public abstract class SymbolLookup { + + protected HashMap stringToID = null; + protected HashMap idToString = null; + + /** + * Perform lookup table specific initialization. This would typically entail loading values into + * the lookup table. It is best to optimize this process so that data is loaded statically and shared + * across all instances of the lookup table. + */ + abstract public void initialize(); + + /** + * Associate a symbol with a numeric value in the lookup table + * @param symbol The symbol that will act as the key in the lookup table + * @param value The value to be associated with a given symbol + */ + public void addEntry(String symbol, int id) { + Integer iObj = new Integer(id); + stringToID.put(symbol, iObj); + idToString.put(iObj, symbol); + } + + /** + * Retrieve the symbol associated with a given identifier + * @param id The identfier for which we need to retieve the symbol string + * @return The string associated with this identifier in the lookup table. + */ + public String getStringFromID(int id) { + return (String)idToString.get(new Integer(id)); + } + + /** + * Retrieve the identifier associated with a given symbol + * @param symbol The symbol for which we need to retieve the identifier + * @throws UnsupportedFunctionException Thown when the symbol is not found in the lookup table + * @return The identifier associated with this string in the lookup table. + */ + public int getIDFromString(String symbol) throws UnsupportedFunctionException { + Integer i = (Integer)stringToID.get(symbol); + if (i == null) + throw new UnsupportedFunctionException("Token '" + symbol + "' not supported by Pocket Excel"); + + return ((Integer)stringToID.get(symbol)).intValue(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/Token.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/Token.java new file mode 100644 index 000000000000..bfd9933936f5 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/Token.java @@ -0,0 +1,154 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + + +import java.io.*; + +/** + * A Token is the basic building block of any formula. + * A Token can be of four types (Operator, Operand, Function with fixed + * arguments and function with a variable number of arguments. Each type can + * have numerous id's. Thetypes are define in <code>ParseToken</code> and the + * id's are defined in <code>TokenConstants</code>. The other member variables + * are priority which is returned from the <code>PrecedenceTable</code>, the + * value which is the String equivalent of the token (eg. "+", "$A$12", "SUM") + * and the number of arguments which is only valid for operators and functions. + * Tokens should never be created directly and instead are created by the + * <code>TokenFactory</code> + */ +public class Token implements ParseToken { + + private String value; + private int type; // operator, operand, function fixed, function variable + private int id; // cell reference, SUM, integer + private int priority; + private int numArgs=-1; + + public Token(String op, int type, int id, int args) { + this.value = op; + this.type = type; + this.id = id; + this.numArgs = args; + if(type==ParseToken.TOKEN_FUNCTION_VARIABLE) { + priority = PrecedenceTable.getPrecedence("FUNCTION"); + } else if(type==ParseToken.TOKEN_OPERATOR) { + priority = PrecedenceTable.getPrecedence(op); + } else { + priority = PrecedenceTable.getPrecedence("DEFAULT"); + } + } + + /** + * Checks if the current token is an operator + * + * @return A <code>boolean</code> result of the comaparison + */ + public boolean isOperator() { + return type == ParseToken.TOKEN_OPERATOR; + } + + /** + * Checks if the current token is an operand + * + * @return A <code>boolean</code> result of the comaparison + */ + public boolean isOperand() { + return type == ParseToken.TOKEN_OPERAND; + } + + /** + * Checks if the current token is a function + * + * @return A <code>boolean</code> result of the comaparison + */ + public boolean isFunction() { + return (type==ParseToken.TOKEN_FUNCTION_FIXED) || (type==ParseToken.TOKEN_FUNCTION_VARIABLE); + } + + /** + * Returns the token type. This can be one of four values (TOKEN_OPERATOR, + * TOKEN_OPERAND, TOKEN_FUNCTION_FIXED, TOKEN_FUNCTION_VARIABLE) defined in + * <code>ParseToken</code> + * + * @return A <code>boolean</code> result of the comparison + */ + public int getTokenType() { + + return type; + } + + /** + * Returns the ID of this token. This ID is equivalent to the pexcel hex + * value and is defined in <code>ParseToken</code> + * + * @return Returns the id of this token + */ + public int getTokenID() { + + return id; + } + + /** + * Returns the <code>String</code> equivalent of this token + * + * @return The <code>String</code> representing this Token + */ + public String getValue() { + return value; + } + + /** + * Returns the number of arguments if this token represents an operator or + * function. Otherwise returns -1. + * + * @return The number of arguments + */ + public int getNumArgs() { + return numArgs; + } + + /** + * Checks if the current token is an operator + * + * @return A <code>boolean</code> result of the comparison + */ + public int getTokenPriority() { + return priority; + } + + /** + * Returns the <code>String</code> equivalent of this token + * + * @return The <code>String</code> representing this Token + */ + public String toString() { + return getValue(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenConstants.java new file mode 100644 index 000000000000..4fd90c6a234e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenConstants.java @@ -0,0 +1,206 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.io.*; + +public interface TokenConstants { + + // Unary Operator Tokens + public static final int TUPLUS = 0x12; + public static final int TUMINUS = 0x13; + public static final int TPERCENT = 0x14; + public static final int TPAREN = 0x15; + // Binary Operator Tokens + public static final int TADD = 0x03; + public static final int TSUB = 0x04; + public static final int TMUL = 0x05; + public static final int TDIV = 0x06; + public static final int TPOWER = 0x07; + public static final int TCONCAT = 0x08; + + //Logical operators + public static final int TLESS = 0x09; + public static final int TLESSEQUALS = 0x0A; + public static final int TEQUALS = 0x0B; + public static final int TGTEQUALS = 0x0C; + public static final int TGREATER = 0x0D; + public static final int TNEQUALS = 0x0E; + + // Function Operator Tokens + public static final int TFUNC = 0x41; + public static final int TFUNCVAR = 0x42; + + // Constant Operand Tokens + public static final int TSTRING = 0x17; + public static final int TINT = 0x1E; + public static final int TNUM = 0x1F; + // Operand Tokens + public static final int TREF = 0x44; + public static final int TAREA = 0x25; + public static final int TNAME = 0x23; + public static final int TREF3D = 0x3A; + public static final int TAREA3D = 0x3B; + + // + public static final int TARGSEP = 0x1001; + public static final int TCLOSEPAREN = 0x1002; + + // Variable argument Functions + // Math and Trig + public static final int TSUM = 0x04; + public static final int TPRODUCT = 0xB7; + public static final int TSUMIF = 0x0159; + public static final int TLOG = 0x6D; + public static final int TRUNC = 0xC5; + // Financial + public static final int TDDB = 0x90; + public static final int TFV = 0x39; + public static final int TIRR = 0x3E; + public static final int TNPER = 0x3A; + public static final int TNPV = 0x0B; + public static final int TPMT = 0x3B; + public static final int TPV = 0x38; + public static final int TRATE = 0x3C; + // Statistical + public static final int TAVERAGE = 0x05; + public static final int TCOUNT = 0x00; + public static final int TCOUNTA = 0xA9; + public static final int TMAX = 0x07; + public static final int TMIN = 0x06; + public static final int TSTDEV = 0x0C; + public static final int TSTDEVP = 0xC1; + public static final int TVAR = 0x2E; + public static final int TVARP = 0xC2; + // Lookup + public static final int TCHOOSE = 0x64; + public static final int THLOOKUP = 0x65; + public static final int TINDEX = 0x1D; + public static final int TMATCH = 0x40; + public static final int TVLOOKUP = 0x66; + // Text + public static final int TRIGHT = 0x74; + public static final int TSUBSTITUTE = 0x78; + public static final int TFIND = 0x7c; + public static final int TLEFT = 0x73; + // Logical + public static final int TAND = 0x24; // 42 + public static final int TIF = 0x01; // 42 + public static final int TOR = 0x25; // 42 + + // Fixed argument Functions + // Math and Trig + public static final int TABS = 0x18; + public static final int TACOS = 0x63; + public static final int TASIN = 0x62; + public static final int TATAN = 0x12; + public static final int TATAN2 = 0x61; + public static final int TCOS = 0x10; + public static final int TSIN = 0x0F; + + public static final int TCOUNTIF = 0x015A; + public static final int TDEGREES = 0x0157; + public static final int TEXP = 0x15; + public static final int TFACT = 0xB8; + public static final int TINTE = 0x19; + public static final int TLN = 0x16; + + public static final int TLOG10 = 0x17; + public static final int TMOD = 0x27; + public static final int TPI = 0x13; + + public static final int TPOWERF = 0x0151; + public static final int TRADIANS = 0x0156; + public static final int TRAND = 0x3F; + public static final int TROUND = 0x1B; + public static final int TSQRT = 0x14; + public static final int TTAN = 0x11; + + public static final int TSLN = 0x8E; + public static final int TSYD = 0x8F; + + // Date and Time + public static final int TDATE = 0x41; + public static final int TDATEVALUE = 0x8C; + public static final int TDAY = 0x43; + public static final int THOUR = 0x47; + public static final int TMINUTE = 0x48; + public static final int TMONTH = 0x44; + public static final int TNOW = 0x4A; + public static final int TSECOND = 0x49; + public static final int TTIME = 0x42; + public static final int TTIMEVALUE = 0x8D; + public static final int TYEAR = 0x45; + // Statistical + public static final int TCOUNTBLANK = 0x015B ; + // lookup + public static final int TCOLUMNS = 0x4D; + public static final int TROWS = 0x4C; + // Database + public static final int TDAVAERAGE = 0x2A; + public static final int TDCOUNT = 0x28; + public static final int TDCOUNTA = 0xC7; + public static final int TDGET = 0xEB; + public static final int TDMAX = 0x2C; + public static final int TDMIN = 0x2B; + public static final int TDPRODUCT = 0xBD; + public static final int TDSTDEV = 0x2D; + public static final int TDSTDEVP = 0xC3; + public static final int TDSUM = 0x29; + public static final int TDVAR = 0x2F; + public static final int TDVARP = 0xC4; + // Text + public static final int TEXACT = 0x75; + public static final int TLEN = 0x20; + public static final int TLOWER = 0x70; + public static final int TMID = 0x1F; // ?????? + public static final int TPROPER = 0x72; + public static final int TREPLACE = 0x77; + public static final int TREPT = 0x1E; + public static final int TT = 0x82; + public static final int TRIM = 0x76; + public static final int TUPPER = 0x71; + public static final int TVALUE = 0x21; + // Logical + public static final int TFALSE = 0x23; + public static final int TNOT = 0x26; + public static final int TTRUE = 0x22; + // Informational + public static final int TERRORTYPE = 0x05; + public static final int TISBLANK = 0x81; + public static final int TISERR = 0x7E; + public static final int TISERROR = 0x03; + public static final int TISLOGICAL = 0xC6; + public static final int TISNA = 0x02; + public static final int TISNONTEXT = 0xBE; + public static final int TISNUMBER = 0x80; + public static final int TISTEXT = 0x7F; + public static final int TN = 0x83; + public static final int TNA = 0x0A; +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenDecoder.java new file mode 100644 index 000000000000..694e3b796710 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenDecoder.java @@ -0,0 +1,498 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.io.*; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.DefinedName; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; + +/** + * The TokenDecoder decodes a byte[] to an equivalent <code>String</code>. The only + * public method apart from the default constructor is the getTokenVector method. + * This method takes an entire formula as a pexcel byte[] and decodes it into + * a series of <code>Token</code>s. It adds these to a <code>Vector</code> which + * is returned once all the tokens have been decoded. The Decoder supports + * the following tokens.<br><br> + * + * Operands Floating point's, Cell references (absolute and relative), + * cell ranges<br> + * Operators +,-,*,/,<,>.<=,>=,<><br> + * Functions All pexcel fixed and varaible argument functions + * + */ +public class TokenDecoder { + + private TokenFactory tf; + private FunctionLookup fl; + private OperatorLookup operatorLookup; + private OperandLookup operandLookup; + private Workbook wb; + + /** + * Default Constructor initializes the <code>TokenFactory</code> for generating + * <code>Token</code> and the <code>SymbolLookup</code> for generating + * Strings from hex values. + */ + public TokenDecoder() { + tf = new TokenFactory(); + fl = new FunctionLookup(); + operatorLookup = new OperatorLookup(); + operandLookup = new OperandLookup(); + } + + /** + * Sets global workbook data needed for defined names + */ + public void setWorkbook(Workbook wb) { + + Debug.log(Debug.TRACE, "TokenDecoder : setWorkbook"); + this.wb = wb; + } + + /** + * Returns a <code>Vector</code> of <code>Token</code> decoded from a + * byte[]. The byte[] is first converted to a + * <code>ByteArrayInputStream</code> as this is the easiest way of reading + * bytes. + * + * @param formula A Pocket Excel Formula byte[] + * @return A <code>Vector</code> of deoded <code>Token</code> + */ + public Vector getTokenVector(byte[] formula) { + + Vector v = new Vector(); + + ByteArrayInputStream bis = new ByteArrayInputStream(formula); + int b = 0 ; + Token t; + + while (bis.available()!=0) + { + b = bis.read(); + + switch (b) { + + case TokenConstants.TAREA3D: + Debug.log(Debug.TRACE, "Decoded 3D Area Cell Reference: "); + v.add(read3DCellAreaRefToken(bis)); + Debug.log(Debug.TRACE, "Decoded 3D Area Cell Reference: " + v.lastElement()); + break; + case TokenConstants.TREF3D: + Debug.log(Debug.TRACE, "Decoded 3D Cell Reference: "); + v.add(read3DCellRefToken(bis)); + Debug.log(Debug.TRACE, "Decoded 3D Cell Reference: " + v.lastElement()); + break; + case TokenConstants.TREF : + v.add(readCellRefToken(bis)); + Debug.log(Debug.TRACE, "Decoded Cell Reference: " + v.lastElement()); + break; + case TokenConstants.TAREA : + v.add(readCellAreaRefToken(bis)); + Debug.log(Debug.TRACE, "Decoded Cell Area Reference: " + v.lastElement()); + break; + case TokenConstants.TNUM : + v.add(readNumToken(bis)); + Debug.log(Debug.TRACE, "Decoded number : " + v.lastElement()); + break; + case TokenConstants.TFUNCVAR : + v.add(readFunctionVarToken(bis)); + Debug.log(Debug.TRACE, "Decoded variable argument function: " + v.lastElement()); + break; + case TokenConstants.TFUNC : + v.add(readFunctionToken(bis)); + Debug.log(Debug.TRACE, "Decoded function: " + v.lastElement()); + break; + case TokenConstants.TSTRING : + v.add(readStringToken(bis)); + Debug.log(Debug.TRACE, "Decoded string: " + v.lastElement()); + break; + case TokenConstants.TNAME : + v.add(readNameToken(bis)); + Debug.log(Debug.TRACE, "Decoded defined name: " + v.lastElement()); + break; + case TokenConstants.TUPLUS: + case TokenConstants.TUMINUS: + case TokenConstants.TPERCENT: + v.add(readOperatorToken(b, 1)); + Debug.log(Debug.TRACE, "Decoded Unary operator : " + v.lastElement()); + break; + case TokenConstants.TADD : + case TokenConstants.TSUB : + case TokenConstants.TMUL : + case TokenConstants.TDIV : + case TokenConstants.TLESS : + case TokenConstants.TLESSEQUALS : + case TokenConstants.TEQUALS : + case TokenConstants.TGTEQUALS : + case TokenConstants.TGREATER : + case TokenConstants.TNEQUALS : + v.add(readOperatorToken(b, 2)); + Debug.log(Debug.TRACE, "Decoded Binary operator : " + v.lastElement()); + break; + + default : + Debug.log(Debug.TRACE, "Unrecognized byte : " + b); + } + } + return v; + } + + /** + * Converts a zero based integer to a char (eg. a=0, b=1). + * It assumes the integer is less than 26. + * + * @param i A 0 based index + * @return The equivalent character + */ + private char int2Char(int i) { + return (char) ('A' + i); + } + + /** + * Reads a Cell Reference token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded String <code>Token</code> + */ + private Token readStringToken(ByteArrayInputStream bis) { + + int len = ((int)bis.read())*2; + int options = (int)bis.read(); + Debug.log(Debug.TRACE,"String length is " + len + " and Options Flag is " + options); + byte [] stringBytes = new byte[len]; + int numRead =0; + if ((numRead = bis.read(stringBytes, 0, len)) != len) { + Debug.log(Debug.TRACE,"Expected " + len + " bytes. Could only read " + numRead + " bytes."); + //throw new IOException("Expected " + len + " bytes. Could only read " + numRead + " bytes."); + } + StringBuffer outputString = new StringBuffer(); + outputString.append('"'); + try { + Debug.log(Debug.TRACE,"Using LE encoding"); + outputString.append(new String(stringBytes, "UTF-16LE")); + } catch (IOException eIO) { + outputString.append(new String(stringBytes)); //fall back to default encoding + } + outputString.append('"'); + + return (tf.getOperandToken(outputString.toString(), "STRING")); + } + + /** + * Reads a Defined Name token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded Name <code>Token</code> + */ + private Token readNameToken(ByteArrayInputStream bis) { + byte buffer[] = new byte[2]; + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int nameIndex = EndianConverter.readShort(buffer); + bis.skip(12); // the next 12 bytes are unused + Enumeration e = wb.getDefinedNames(); + int i = 1; + while(i<nameIndex) { + e.nextElement(); + i++; + } + Debug.log(Debug.TRACE,"Name index is " + nameIndex); + DefinedName dn = (DefinedName)e.nextElement(); + Debug.log(Debug.TRACE,"DefinedName is " + dn.getName()); + return (tf.getOperandToken(dn.getName(), "NAME")); + } + + /** + * Reads a Cell Reference token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded Cell Reference <code>Token</code> + */ + private Token readCellRefToken(ByteArrayInputStream bis) { + + byte buffer[] = new byte[2]; + String outputString = new String(); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int formulaRow = EndianConverter.readShort(buffer); + int relativeFlags = (formulaRow & 0xC000)>>14; + formulaRow &= 0x3FFF; + int formulaCol = (byte) bis.read(); + + outputString = int2CellStr(formulaRow, formulaCol, relativeFlags); + + return (tf.getOperandToken(outputString,"CELL_REFERENCE")); + } + + /** + * Reads a Cell Reference token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded Cell Reference <code>Token</code> + */ + private Token read3DCellRefToken(ByteArrayInputStream bis) { + + byte buffer[] = new byte[2]; + String outputString = new String(); + + bis.skip(10); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int Sheet1 = EndianConverter.readShort(buffer); + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int Sheet2 = EndianConverter.readShort(buffer); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int formulaRow = EndianConverter.readShort(buffer); + int relativeFlags = (formulaRow & 0xC000)>>14; + formulaRow &= 0x3FFF; + int formulaCol = (byte) bis.read(); + String cellRef = "." + int2CellStr(formulaRow, formulaCol, relativeFlags); + if(Sheet1 == Sheet2) { + outputString = "$" + wb.getSheetName(Sheet1) + cellRef; + } else { + outputString = "$" + wb.getSheetName(Sheet1) + cellRef + ":$" + wb.getSheetName(Sheet2) + cellRef; + } + + return (tf.getOperandToken(outputString,"3D_CELL_REFERENCE")); + } + + /** + * Reads a Cell Reference token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded Cell Reference <code>Token</code> + */ + private Token read3DCellAreaRefToken(ByteArrayInputStream bis) { + + byte buffer[] = new byte[2]; + String outputString = new String(); + + bis.skip(10); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int Sheet1 = EndianConverter.readShort(buffer); + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int Sheet2 = EndianConverter.readShort(buffer); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int formulaRow1 = EndianConverter.readShort(buffer); + int relativeFlags1 = (formulaRow1 & 0xC000)>>14; + formulaRow1 &= 0x3FFF; + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int formulaRow2 = EndianConverter.readShort(buffer); + int relativeFlags2 = (formulaRow2 & 0xC000)>>14; + formulaRow2 &= 0x3FFF; + + int formulaCol1 = (byte) bis.read(); + int formulaCol2 = (byte) bis.read(); + + String cellRef1 = "." + int2CellStr(formulaRow1, formulaCol1, relativeFlags1); + String cellRef2 = int2CellStr(formulaRow2, formulaCol2, relativeFlags2); + + if(Sheet1 == Sheet2) { + outputString = "$" + wb.getSheetName(Sheet1) + cellRef1 + ":" + cellRef2; + } else { + outputString = "$" + wb.getSheetName(Sheet1) + cellRef1 + ":$" + wb.getSheetName(Sheet2) + "." + cellRef2; + } + + return (tf.getOperandToken(outputString,"3D_CELL_AREA_REFERENCE")); + } + + /** + * Converts a row and col 0 based index to a spreadsheet cell reference. + * It also has a relativeFlags which indicates whether or not the + * Cell Reference is relative or absolute (Absolute is denoted with '$') + * + * 00 = absolute row, absolute col + * 01 = absolute row, relative col + * 10 = relative row, absolute col + * 11 = relative row, relative col + * + * @param row The cell reference 0 based index to the row + * @param col The cell reference 0 based index to the row + * @param relativeFlags Flags indicating addressing of row and column + * @return A <code>String</code> representing a cell reference + */ + private String int2CellStr(int row, int col, int relativeFlags) { + String outputString = ""; + int firstChar = (col + 1) / 26; + + if((relativeFlags & 1) == 0) { + outputString += "$"; + } + + if(firstChar>0) { + int secondChar = (col + 1) % 26; + outputString += Character.toString(int2Char(firstChar - 1)) + Character.toString(int2Char(secondChar - 1)); + } else { + outputString += Character.toString(int2Char(col)); + } + if((relativeFlags & 2) == 0) { + outputString += "$"; + } + outputString += Integer.toString(row+1); + return outputString; + } + + /** + * Reads a Cell Area Reference (cell range) <code>Token</code> from + * the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The equivalent Cell Area Reference (cell range) + * <code>Token</code> + */ + private Token readCellAreaRefToken(ByteArrayInputStream bis) { + byte buffer[] = new byte[2]; + int formulaRow1, formulaRow2; + int formulaCol1, formulaCol2; + + String outputString = new String(); + + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + formulaRow1 = EndianConverter.readShort(buffer); + int relativeFlags1 = (formulaRow1 & 0xC000)>>14; + formulaRow1 &= 0x3FFF; + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + formulaRow2 = EndianConverter.readShort(buffer); + int relativeFlags2 = (formulaRow2 & 0xC000)>>14; + formulaRow2 &= 0x3FFF; + + formulaCol1 = (byte) bis.read(); + formulaCol2 = (byte) bis.read(); + + outputString = int2CellStr(formulaRow1, formulaCol1, relativeFlags1); + outputString += (":" + int2CellStr(formulaRow2, formulaCol2, relativeFlags2)); + + return (tf.getOperandToken(outputString,"CELL_AREA_REFERENCE")); + } + + + /** + * Reads a Number (floating point) token from the <code>ByteArrayInputStream</code> + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded Integer <code>Token</code> + */ + private Token readNumToken(ByteArrayInputStream bis) { + + byte numBuffer[] = new byte[8]; + + for(int j=0;j<8;j++) { + numBuffer[j]=(byte) bis.read(); + } + + return (tf.getOperandToken(Double.toString(EndianConverter.readDouble(numBuffer)),"NUMBER")); + } + + /** + * Read an Operator token from the <code>ByteArrayInputStream</code> + * + * @param b A Pocket Excel number representing an operator. + * @param args The number of arguments this operator takes. + * @return The decoded Operator <code>Token</code> + */ + private Token readOperatorToken(int b, int args) { + + Token t; + + if(b==TokenConstants.TUPLUS) { + t = tf.getOperatorToken("+", args); + } else if(b==TokenConstants.TUMINUS) { + t = tf.getOperatorToken("-", args); + } else { + t = tf.getOperatorToken(operatorLookup.getStringFromID(b), args); + } + return t; + } + + /** + * Read a Function token from the <code>ByteArrayInputStream</code> + * This function can have any number of arguments and this number is read + * in with the record + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded variable argument Function <code>Token</code> + */ + private Token readFunctionVarToken(ByteArrayInputStream bis) { + + int numArgs = 0; + numArgs = bis.read(); + byte buffer[] = new byte[2]; + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int functionID = EndianConverter.readShort(buffer); + return (tf.getFunctionToken(fl.getStringFromID(functionID),numArgs)); + } + + /** + * Read a Function token from the <code>ByteArrayInputStream</code> + * This function has a fixed number of arguments which it will get + * from <code>FunctionLookup</code>. + * + * @param bis The <code>ByteArrayInputStream</code> from which we read the + * bytes. + * @return The decoded fixed argument Function <code>Token</code> + */ + private Token readFunctionToken(ByteArrayInputStream bis) { + + byte buffer[] = new byte[2]; + buffer[0] = (byte) bis.read(); + buffer[1] = (byte) bis.read(); + int functionID = EndianConverter.readShort(buffer); + String functionName = fl.getStringFromID(functionID); + return (tf.getFunctionToken(functionName,fl.getArgCountFromString(functionName))); + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenEncoder.java new file mode 100644 index 000000000000..23af0689d040 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenEncoder.java @@ -0,0 +1,561 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.io.*; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.Workbook; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.BoundSheet; +import org.openoffice.xmerge.converter.xml.sxc.pexcel.records.DefinedName; + +/** + * The TokenEncoder encodes a Token to an equivalent pexcel byte[]. The only + * public method apart from the default constructor is the getByte method. + * This method picks an encoder based onthe Token's type or id field and uses + * that encoder to return a byte[] which it returns. This Encoder supports + * Operands Floating point's, Cell references (absolute and relative), + * cell ranges + * Operators +,-,*,/,<,>.<=,>=,<> + * Functions All pexcel fixed and varaible argument functions + * + */ +public class TokenEncoder { + + private FunctionLookup fl; + private String parseString; + private int index; + private Workbook wb; + + /** + * Default Constructor + */ + public TokenEncoder() { + + parseString = new String(); + fl = new FunctionLookup(); + } + + /** + * Sets global workbook data needed for defined names + */ + public void setWorkbook(Workbook wb) { + + this.wb = wb; + } + + + /** + * Return the byte[] equivalent of a <code>Token</code>. The various + * encoders return <code>Vector</code> of <code>Byte</code> instead + * of byte[] because the number of bytes returned varies with each + * <code>Token</code> encoded. After the encoding is finished the Vector + * in converted to a byte[]. + * + * @param t The <code>Token</code> to be encoded + * @return An equivalent Pocket Excel byte[] + */ + public byte[] getByte(Token t) throws IOException { + + Vector tmpByteArray = null; // we use this cause we don't know till after + // the encoding takes place how big the byte [] will be + //index=0; // This class is declared static in + // FormulaHelper so better make sure our index is 0 + if(t.getTokenType()==ParseToken.TOKEN_OPERATOR) { + tmpByteArray = operatorEncoder(t); + } else if (t.getTokenType()==ParseToken.TOKEN_FUNCTION_VARIABLE || t.getTokenType()==ParseToken.TOKEN_FUNCTION_FIXED){ + tmpByteArray = functionEncoder(t); + } else { // Operands and functions + switch(t.getTokenID()) { + case TokenConstants.TNAME : + tmpByteArray = nameDefinitionEncoder(t); + break; + case TokenConstants.TREF3D : + tmpByteArray = threeDCellRefEncoder(t); + break; + case TokenConstants.TAREA3D: + tmpByteArray = threeDAreaRefEncoder(t); + break; + case TokenConstants.TREF : + tmpByteArray = cellRefEncoder(t); + break; + case TokenConstants.TAREA : + tmpByteArray = areaRefEncoder(t); + break; + case TokenConstants.TNUM : + tmpByteArray = numEncoder(t); + break; + case TokenConstants.TSTRING : + tmpByteArray = stringEncoder(t); + break; + default : + Debug.log(Debug.ERROR, "Encoder found unrecognized Token"); + } + } + + byte cellRefArray[] = new byte[tmpByteArray.size()]; + int i = 0; + String s = new String(); + for(Enumeration e = tmpByteArray.elements();e.hasMoreElements();) { + Byte tmpByte = (Byte) e.nextElement(); + s = s + tmpByte + " "; + cellRefArray[i] = tmpByte.byteValue(); + i++; + } + Debug.log(Debug.TRACE, "Encoding Token " + t.getValue() + " as [" + s + "]"); + return cellRefArray; + } + + /** + * An Operator Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector operatorEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + return tmpByteArray; + } + + + /** + * A String Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector stringEncoder(Token t) throws IOException{ + + Vector tmpByteArray = new Vector(); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + tmpByteArray.add(new Byte((byte)(t.getValue().length()))); + tmpByteArray.add(new Byte((byte)0x01)); + byte [] stringBytes = t.getValue().getBytes("UTF-16LE"); + for (int i=0; i<stringBytes.length; i++) { + tmpByteArray.add(new Byte(stringBytes[i])); + } + return tmpByteArray; + } + + + /** + * An Integer Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector numEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + + double cellLong = (double) Double.parseDouble(t.getValue()); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + byte[] tempByte = EndianConverter.writeDouble(cellLong); + for(int byteIter=0;byteIter<tempByte.length;byteIter++) { + tmpByteArray.add(new Byte(tempByte[byteIter])); + } + return tmpByteArray; + } + + /** + * Converts a char to an int. It is zero based + * so a=0, b=1 etc. + * + * @param ch the character to be converted + * @return -1 if not a character otherwise a 0 based index + */ + private int char2int(char ch) { + if(!Character.isLetter(ch)) + return -1; + + ch = Character.toUpperCase(ch); + return ch-'A'; + } + + /** + * Identify letters + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isAlpha(char c) { + return(Character.isLetter(c)); + } + + /** + * Identify numbers + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isDigit(char c) { + return(Character.isDigit(c)); + } + + /** + * Identify letters or numbers + * + * @param c The character which is to be identified + * @return A boolean returning the result of the comparison + */ + private boolean isAlphaNum(char c) { + return(isAlpha(c) || isDigit(c)); + } + + /** + * Parses a column reference and returns it's integer equivalent. (eg. + * A=0, D=3, BA=27) + * + * @return an 0 based index to a column + */ + private int column() { + char ch = parseString.charAt(index); + String columnStr = new String(); + int col = 0; + + while(isAlpha(ch)) { + columnStr += ch; + index++; + ch = parseString.charAt(index); + } + + if(columnStr.length()==1) { + col = char2int(columnStr.charAt(0)); + } else if (columnStr.length()==2) { + col = char2int(columnStr.charAt(0)) + 1; + col = (col*26) + char2int(columnStr.charAt(1)); + } else { + Debug.log(Debug.ERROR, "Invalid Column Reference " + columnStr ); + } + + + return col; + } + + /** + * Parses a column reference and returns it's integer equivalent. (eg. + * A=0, D=3, BA=27) + * + * @return an 0 based index to a column + */ + private int row() { + char ch = parseString.charAt(index); + String rowStr = new String(); + int row = 0; + boolean status = true; + + do { + rowStr += ch; + index++; + if(index>=parseString.length()) { + status = false; + } else { + ch = parseString.charAt(index); + } + } while(isDigit(ch) && status); + return Integer.parseInt(rowStr)-1; // Pexcel uses a 0 based index + } + + /** + * A Cell Reference Encoder (It supports absolute and relative addressing) + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private byte[] encodeCellCoordinates(String cellCoordinates) { + int col = 0, row = 0; + int addressing = 0xC000; + + index = 0; + parseString = cellCoordinates; + Debug.log(Debug.TRACE,"Encoding cell coordinates " + cellCoordinates); + if(cellCoordinates.charAt(index)=='$') { + addressing &= 0x8000; + index++; + } + col = column(); + if(cellCoordinates.charAt(index)=='$') { + addressing &= 0x4000; + index++; + } + row = row(); // Pexcel uses a 0 based index + row |= addressing; + byte tokenBytes[] = new byte[3]; + tokenBytes[0] = (byte)row; + tokenBytes[1] = (byte)(row>>8); + tokenBytes[2] = (byte)col; + return tokenBytes; + } + + /** + * A name definition Encoder + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector nameDefinitionEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + + String nameString = t.getValue(); + Debug.log(Debug.TRACE,"NameDefinitionEncoder : " + nameString); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + Enumeration e = wb.getDefinedNames(); + DefinedName dn; + String name; + int definedNameIndex = 0; + do { + dn = (DefinedName)e.nextElement(); + name = dn.getName(); + Debug.log(Debug.TRACE,"Name pulled from DefinedName : " + name); + definedNameIndex++; + } while(!nameString.equalsIgnoreCase(name) && e.hasMoreElements()); + + tmpByteArray.add(new Byte((byte)definedNameIndex)); + tmpByteArray.add(new Byte((byte)0x00)); + + for(int i = 0;i < 12;i++) { + tmpByteArray.add(new Byte((byte)0x00)); + } + + return tmpByteArray; + } + /** + * A Cell Reference Encoder. It supports absolute and relative addressing + * but not sheetnames. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector cellRefEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + + tmpByteArray.add(new Byte((byte)t.getTokenID())); + byte cellRefBytes[] = encodeCellCoordinates(t.getValue()); + for(int i = 0;i < cellRefBytes.length;i++) { + tmpByteArray.add(new Byte(cellRefBytes[i])); + } + return tmpByteArray; + } + + /** + * This function will find the sheetname index for a given String + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private short findSheetIndex(String s) { + + short sheetIndex = 0; + String savedName; + String sheetName; + if (s.startsWith("$")) { + sheetName = s.substring(1,s.length()); // Remove $ + } else { + sheetName = s.substring(0,s.length()); + } + Debug.log(Debug.TRACE,"Searching for Worksheet : " + sheetName); + Vector names = wb.getWorksheetNames(); + Enumeration e = names.elements(); + do { + savedName = (String) e.nextElement(); + sheetIndex++; + } while(!savedName.equalsIgnoreCase(sheetName) && e.hasMoreElements()); + + Debug.log(Debug.TRACE,"Setting sheetindex to " + sheetIndex); + return (short)(sheetIndex-1); + } + + /** + * A 3D Cell reference encoder + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector threeDCellRefEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + parseString = t.getValue(); + Debug.log(Debug.TRACE,"Encoding 3D Cell reference " + t); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + tmpByteArray.add(new Byte((byte)0xFF)); + tmpByteArray.add(new Byte((byte)0xFF)); + for(int i = 0;i < 8;i++) { + tmpByteArray.add(new Byte((byte)0x00)); + } + + String sheetRef = parseString.substring(0, parseString.indexOf('.') + 1); + if (sheetRef.indexOf(':')!=-1) { + sheetRef = parseString.substring(0, parseString.indexOf(':')); + short sheetNum1 = findSheetIndex(sheetRef); + sheetRef = parseString.substring(parseString.indexOf(':') + 1, parseString.length()); + short sheetNum2 = findSheetIndex(sheetRef); + tmpByteArray.add(new Byte((byte)sheetNum1)); + tmpByteArray.add(new Byte((byte)0x00)); + tmpByteArray.add(new Byte((byte)sheetNum2)); + tmpByteArray.add(new Byte((byte)0x00)); + } else { + sheetRef = parseString.substring(0, parseString.indexOf('.')); + short sheetNum = findSheetIndex(sheetRef); + tmpByteArray.add(new Byte((byte)sheetNum)); + tmpByteArray.add(new Byte((byte)0x00)); + tmpByteArray.add(new Byte((byte)sheetNum)); + tmpByteArray.add(new Byte((byte)0x00)); + } + String s = parseString.substring(parseString.indexOf('.') + 1, parseString.length()); + Debug.log(Debug.TRACE,"Parsing : " + s); + byte cellRefBytes[] = encodeCellCoordinates(s); + for(int i = 0;i < cellRefBytes.length;i++) { + tmpByteArray.add(new Byte(cellRefBytes[i])); + } + return tmpByteArray; + } + /** + * A 3D Area Reference Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector threeDAreaRefEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + parseString = t.getValue(); + Debug.log(Debug.TRACE,"Encoding 3D Area reference " + t); + tmpByteArray.add(new Byte((byte)t.getTokenID())); + tmpByteArray.add(new Byte((byte)0xFF)); + tmpByteArray.add(new Byte((byte)0xFF)); + for(int i = 0;i < 8;i++) { + tmpByteArray.add(new Byte((byte)0x00)); + } + + String param1= parseString.substring(0, parseString.indexOf(':')); + String cellRef1 = param1.substring(parseString.indexOf('.') + 1, param1.length()); + String sheetRef1 = param1.substring(0, param1.indexOf('.')); + short sheetNum1 = findSheetIndex(sheetRef1); + + String param2 = parseString.substring(parseString.indexOf(':') + 1, parseString.length()); + Debug.log(Debug.TRACE,"param2: " + param2); + String cellRef2 = param2.substring(param2.indexOf('.') + 1, param2.length()); + Debug.log(Debug.TRACE,"cellRef2: " + cellRef2); + + if(param2.indexOf('.')==-1) { + tmpByteArray.add(new Byte((byte)sheetNum1)); + tmpByteArray.add(new Byte((byte)0x00)); + tmpByteArray.add(new Byte((byte)sheetNum1)); + tmpByteArray.add(new Byte((byte)0x00)); + } else { + String sheetRef2 = param2.substring(0, param2.indexOf('.')); + short sheetNum2 = findSheetIndex(sheetRef2); + tmpByteArray.add(new Byte((byte)sheetNum1)); + tmpByteArray.add(new Byte((byte)0x00)); + tmpByteArray.add(new Byte((byte)sheetNum2)); + tmpByteArray.add(new Byte((byte)0x00)); + } + + byte cellRefBytes1[] = encodeCellCoordinates(cellRef1); + byte cellRefBytes2[] = encodeCellCoordinates(cellRef2); + + tmpByteArray.add(new Byte(cellRefBytes1[0])); + tmpByteArray.add(new Byte(cellRefBytes1[1])); + + tmpByteArray.add(new Byte(cellRefBytes2[0])); + tmpByteArray.add(new Byte(cellRefBytes2[1])); + + tmpByteArray.add(new Byte(cellRefBytes1[2])); + tmpByteArray.add(new Byte(cellRefBytes2[2])); + + return tmpByteArray; + } + + /** + * A Cell Range Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector areaRefEncoder(Token t) { + + Vector tmpByteArray = new Vector(); + + tmpByteArray.add(new Byte((byte)t.getTokenID())); + String param = t.getValue(); + String cellRef1 = new String(); + String cellRef2 = new String(); + + if(param.indexOf(':')==-1) { + Debug.log(Debug.ERROR, "Invalid Cell Range, could not find :"); + } else { + cellRef1 = param.substring(0, param.indexOf(':')); + cellRef2 = param.substring(param.indexOf(':') + 1, param.length()); + } + byte cellRefBytes1[] = encodeCellCoordinates(cellRef1); + byte cellRefBytes2[] = encodeCellCoordinates(cellRef2); + + tmpByteArray.add(new Byte(cellRefBytes1[0])); + tmpByteArray.add(new Byte(cellRefBytes1[1])); + + tmpByteArray.add(new Byte(cellRefBytes2[0])); + tmpByteArray.add(new Byte(cellRefBytes2[1])); + + tmpByteArray.add(new Byte(cellRefBytes1[2])); + tmpByteArray.add(new Byte(cellRefBytes2[2])); + + return tmpByteArray; + } + + /** + * A Function Encoder. + * + * @param t <code>Token</code> to be encoded + * @return A <code>Vector</code> of pexcel <code>Byte</code> + */ + private Vector functionEncoder(Token t) { + Vector tmpByteArray = new Vector(); + + int id = t.getTokenID(); + if(t.getTokenType()==ParseToken.TOKEN_FUNCTION_VARIABLE) { + tmpByteArray.add(new Byte((byte)TokenConstants.TFUNCVAR)); + tmpByteArray.add(new Byte((byte)t.getNumArgs())); + } else { + tmpByteArray.add(new Byte((byte)TokenConstants.TFUNC)); + } + + tmpByteArray.add(new Byte((byte)id)); + tmpByteArray.add(new Byte((byte)(id>>8))); + return tmpByteArray; + } + + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenFactory.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenFactory.java new file mode 100644 index 000000000000..23efd62cd2ce --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/TokenFactory.java @@ -0,0 +1,123 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +import java.io.*; +import java.util.Vector; +import java.util.Enumeration; + +import org.openoffice.xmerge.util.Debug; + +/** + * This is the Factory class responsible for creating a <code>Token</code>. + * It has three methods for returning three different types of Tokens + * (Operator, Operand and Function). + * This utility class is used by either the <code>FormulaParser</code> or the + * <code>FormulaDecoder</code>. + */ +public class TokenFactory { + + private OperatorLookup operatorLookup; + private OperandLookup operandLookup; + private FunctionLookup fl; + + /** + * Default Constructor + */ + public TokenFactory() { + operatorLookup = new OperatorLookup(); + operandLookup = new OperandLookup(); + fl = new FunctionLookup(); + } + + /** + * The Factory method for creating function Tokens + * + * @return The created <code>Token</code> + */ + public Token getFunctionToken(String s, int args) { + Token t = null; + // We will have to fix this later to include fixed function tokens + // Also will need to handle errors where functions names are incorrect??? + Debug.log(Debug.TRACE,"TokenFactory creating function Token : " + s); + try { + t = new Token(s, ParseToken.TOKEN_FUNCTION_VARIABLE, fl.getIDFromString(s), args); + } catch (UnsupportedFunctionException eFn) { + + Debug.log(Debug.ERROR, eFn.getMessage()); + } + return t; + } + + /** + * The Factory method for creating operator Tokens + * + * @return The created <code>Token</code> + */ + public Token getOperatorToken(String s, int args) { + + Token t = null; + + Debug.log(Debug.TRACE,"TokenFactory creating operator Token : " + s); + try { + if(args==1) { + if(s.equals("+")) { + t = new Token(s, ParseToken.TOKEN_OPERATOR, operatorLookup.getIDFromString("UNARY_PLUS"), args); + } else if (s.equals("-")) { + t = new Token(s, ParseToken.TOKEN_OPERATOR, operatorLookup.getIDFromString("UNARY_MINUS"), args); + } else { + t = new Token(s, ParseToken.TOKEN_OPERATOR, operatorLookup.getIDFromString(s), args); + } + } else { + t = new Token(s, ParseToken.TOKEN_OPERATOR, operatorLookup.getIDFromString(s), args); + } + } catch (UnsupportedFunctionException eFn) { + Debug.log(Debug.ERROR, eFn.getMessage()); + } + return t; + } + + /** + * The Factory method for creating Operand Tokens + * + * @return The created <code>Token</code> + */ + public Token getOperandToken(String s, String type) { + Token t = null; + + Debug.log(Debug.TRACE,"TokenFactory creating operand (" + type + ") Token : " + s); + try { + t = new Token(s, ParseToken.TOKEN_OPERAND, operandLookup.getIDFromString(type), 0); + } catch (UnsupportedFunctionException eFn) { + Debug.log(Debug.ERROR, eFn.getMessage()); + } + + return t; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/UnsupportedFunctionException.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/UnsupportedFunctionException.java new file mode 100644 index 000000000000..dcd2bf61a0c4 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/UnsupportedFunctionException.java @@ -0,0 +1,41 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula; + +/* + * Exception thrown when a function specified in a calc formula has no equivalent in Pocket Excel + * + * @author : Mike Hayes + */ + +public class UnsupportedFunctionException extends Exception { + UnsupportedFunctionException(String message) { + super(message); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/build.xml new file mode 100644 index 000000000000..fa3737f9dc63 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/build.xml @@ -0,0 +1,141 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxspr_formula" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxspr_formula"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/FormulaCompiler.java"/> + <include name="${package}/FormulaHelper.java"/> + <include name="${package}/FormulaParser.java"/> + <include name="${package}/FormulaParsingException.java"/> + <include name="${package}/FunctionLookup.java"/> + <include name="${package}/OperandLookup.java"/> + <include name="${package}/Operatorookup.java"/> + <include name="${package}/ParseToken.java"/> + <include name="${package}/PrecedenceTable.java"/> + <include name="${package}/SymbolLookup.java"/> + <include name="${package}/Token.java"/> + <include name="${package}/TokenConstants.java"/> + <include name="${package}/TokenDecoder.java"/> + <include name="${package}/TokenEncoder.java"/> + <include name="${package}/TokenFactory.java"/> + <include name="${package}/UnsupportedFunctionException.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/makefile.mk new file mode 100644 index 000000000000..c549fec7ebeb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcxs_pexcel +PRJ=../../../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/package.html new file mode 100644 index 000000000000..649879a407f6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/formula/package.html @@ -0,0 +1,40 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<html> +<head> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + + <title>org.openoffice.xmerge.converter.xml.sxc.pexcel.records.formula package</title> + +</head> + <body bgcolor="white"> + +<p> This package contains the classes necessary for converting pexcel formula +to and from StarCalc Formula.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/package.html new file mode 100644 index 000000000000..7d803d1feba8 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxc/pexcel/records/package.html @@ -0,0 +1,45 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<html> +<head> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + + <title>org.openoffice.xmerge.converter.xml.sxc.pexcel.records package</title> + +</head> + <body bgcolor="white"> + +<p> This package contains the objects that represent BIFF Records for the +pocket excel format. Each one implements the BIFF Record abstract class which +contains three basic functions (read, write and getBiffType). BIFF Records +which are not used do not contain setter's or getter's for their member +variables as some records have a large number of variables. It should be up +to the implementer which attributes get set and which get set to default +values.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwDocument.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwDocument.java new file mode 100644 index 000000000000..839a63e8bec9 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwDocument.java @@ -0,0 +1,95 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw; + +import org.w3c.dom.Document; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * This class is an implementation of <code>OfficeDocument</code> for + * the SXW format. + */ +public class SxwDocument extends OfficeDocument { + + + /** + * Constructor with arguments to set <code>name</code>. + * + * @param name The name of the <code>Document</code> + */ + public SxwDocument(String name) { + super(name); + } + + + /** + * Constructor with arguments to set <code>name</code>, the + * <code>namespaceAware</code> flag, and the <code>validating</code> + * flag. + * + * @param name The name of the <code>Document</code>. + * @param namespaceAware The value of the namespaceAware flag. + * @param validating The value of the validating flag. + */ + public SxwDocument(String name, boolean namespaceAware, boolean validating) { + + super(name, namespaceAware, validating); + } + + + /** + * Returns the Office file extension for the SXW format. + * + * @return The Office file extension for the SXW format. + */ + protected String getFileExtension() { + return OfficeConstants.SXW_FILE_EXTENSION; + } + + + /** + * Returns the Office attribute for the SXW format. + * + * @return The Office attribute for the SXW format. + */ + protected String getOfficeClassAttribute() { + return OfficeConstants.SXW_TYPE; + } + + /** + * Method to return the MIME type of the document. + * + * @return String The document's MIME type. + */ + protected final String getDocumentMimeType() { + return OfficeConstants.SXW_MIME_TYPE; + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwPluginFactory.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwPluginFactory.java new file mode 100644 index 000000000000..23e2608c242e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/SxwPluginFactory.java @@ -0,0 +1,78 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw; + +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.PluginFactory; +import org.openoffice.xmerge.PluginFactory; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.util.registry.ConverterInfo; + +/** + * General implementation of the <code>PluginFactory</code> interface + * for SXW documents. + * + * @see org.openoffice.xmerge.DocumentDeserializer + * @see org.openoffice.xmerge.DocumentMerger + * @see org.openoffice.xmerge.DocumentSerializer + */ +public abstract class SxwPluginFactory extends PluginFactory { + + /** + * Constructor that caches the <code>ConvertInfo</code> that + * corresponds to the registry information for this plug-in. + * + * @param ci <code>ConvertInfo</code> object. + */ + public SxwPluginFactory (ConverterInfo ci) { + super(ci); + } + + + public Document createOfficeDocument(String name, InputStream is) + throws IOException { + + // read zipped XML stream + SxwDocument doc = new SxwDocument(name); + doc.read(is); + return doc; + } + + public Document createOfficeDocument(String name, InputStream is,boolean isZip) + throws IOException { + + // read XML stream + SxwDocument doc = new SxwDocument(name); + doc.read(is,isZip); + return doc; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..671ae420bcfc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/ConverterCapabilitiesImpl.java @@ -0,0 +1,93 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * <p>AportisDoc implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxw.aportisdoc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarWriter XML to/from AportisDoc conversions. The + * <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_DOCUMENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_DOCUMENT_CONTENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_HEADING.equals(tag)) + return true; + else if (OfficeConstants.TAG_ORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_UNORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_ITEM.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_HEADER.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPAN.equals(tag)) + return true; + else if (OfficeConstants.TAG_HYPERLINK.equals(tag)) + return true; + else if (OfficeConstants.TAG_LINE_BREAK.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPACE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TAB_STOP.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_SPACE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_SPACE_COUNT.equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocConstants.java new file mode 100644 index 000000000000..86627c6d7ed3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocConstants.java @@ -0,0 +1,69 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.openoffice.xmerge.converter.palm.PdbUtil; + +/** + * Constants used for encoding and decoding the AportisDoc format. + * + * @author Herbie Ong + */ +interface DocConstants { + + /** Creator id. */ + public static final int CREATOR_ID = PdbUtil.intID("REAd"); + + /** Type id. */ + public static final int TYPE_ID = PdbUtil.intID("TEXt"); + + /** Constant for uncompressed version. */ + public static final short UNCOMPRESSED = 1; + + /** Constant for compressed version. */ + public static final short COMPRESSED = 2; + + /** Constant used for spare fields. */ + public static final int SPARE = 0; + + /** AportisDoc record size. */ + public static final short TEXT_RECORD_SIZE = 4096; + + /** Constant for encoding scheme. */ + public static final String ENCODING = "8859_1"; + + /** Constant for TAB character. */ + public final static char TAB_CHAR = '\t'; + + /** Constant for EOL character. */ + public final static char EOL_CHAR = '\n'; + + /** Constant for SPACE character. */ + public final static char SPACE_CHAR = ' '; +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocDecoder.java new file mode 100644 index 000000000000..9651e5b10b4d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocDecoder.java @@ -0,0 +1,304 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import java.io.ByteArrayInputStream; +import java.io.DataInputStream; +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.util.List; +import java.util.ArrayList; + +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.util.Resources; +import org.openoffice.xmerge.util.Debug; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxw.DocumentDeserializerImpl} + * to decode the AportisDoc format. It currently decodes + * the text content into a single <code>String</code> object. + * + * @author Herbie Ong + */ +final class DocDecoder implements DocConstants { + + /** For decoding purposes. */ + private final static int COUNT_BITS = 3; + + /** Resources object for I18N. */ + private Resources res = null; + + + /** + * Default constructor creates a header and a text buffer + * for holding all the text in the AportisDoc database. + */ + DocDecoder() { + res = Resources.getInstance(); + } + + + /** + * Decode the text records into a single <code>String</code> + * of text content. + * + * @param Record <code>Record</code> array holding AportisDoc + * contents. + * + * @throws IOException If any I/O error occurs. + */ + String parseRecords(Record[] recs) throws IOException { + + // read the header record + HeaderInfo header = readHeader(recs[0].getBytes()); + + dumpHeader(header); + + // store all the characters in textBuffer + StringBuffer textBuffer = new StringBuffer(header.textLen); + + switch (header.version) { + + case COMPRESSED: + for (int i = 1; i <= header.textRecordCount; i++) { + + byte[] bytes = decompress(recs[i].getBytes(), + header.textRecordSize); + log("processing " + bytes.length + " bytes"); + String str = new String(bytes, ENCODING); + textBuffer.append(str); + } + + break; + + case UNCOMPRESSED: + for (int i = 1; i <= header.textRecordCount; i++) { + + byte[] bytes = recs[i].getBytes(); + log("processing " + bytes.length + " bytes"); + String str = new String(bytes, ENCODING); + textBuffer.append(str); + } + + break; + + default: + throw new IOException(res.getString("UNKNOWN_DOC_VERSION")); + + } + + return textBuffer.toString(); + } + + + /** + * <p>Decompress the <code>byte</code> array.</p> + * + * <p>The resulting uncompressed <code>byte</code> array should + * be within <code>textRecordSize</code> length, definitely + * within twice the size it claims, else treat it as a problem + * with the encoding of that PDB and throw + * <code>IOException</code>.</p> + * + * @param bytes Compressed <code>byte</code> array. + * @param textRecordSize Size of uncompressed + * <code>byte</code> array. + * + * @throws IOException If <code>textRecordSize</code> < + * <code>cBytes.length</code>. + */ + private byte[] decompress(byte[] cBytes, int textRecordSize) + throws IOException { + + // create byte array for storing uncompressed bytes + // it should be within textRecordSize range, definitely + // within twice of textRecordSize! if not, then + // an ArrayIndexOutOfBoundsException will get thrown, + // and it should be converted into an IOException, and + // treat it as a conversion error. + byte[] uBytes = new byte[textRecordSize*2]; + + int up = 0; + int cp = 0; + + try { + + while (cp < cBytes.length) { + + int c = cBytes[cp++] & 0xff; + + // codes 1...8 mean copy that many bytes + if (c > 0 && c < 9) { + + while (c-- > 0) + uBytes[up++] = cBytes[cp++]; + } + + // codes 0, 9...0x7F represent themselves + else if (c < 0x80) { + uBytes[up++] = (byte) c; + } + + // codes 0xC0...0xFF represent "space + ascii char" + else if (c >= 0xC0) { + uBytes[up++] = (byte) ' '; + uBytes[up++] = (byte) (c ^ 0x80); + } + + // codes 0x80...0xBf represent sequences + else { + c <<= 8; + c += cBytes[cp++] & 0xff; + int m = (c & 0x3fff) >> COUNT_BITS; + int n = c & ((1 << COUNT_BITS) - 1); + n += COUNT_BITS; + while (n-- > 0) { + uBytes[up] = uBytes[up - m]; + up++; + } + } + } + + } catch (ArrayIndexOutOfBoundsException e) { + + throw new IOException( + res.getString("DOC_TEXT_RECORD_SIZE_EXCEEDED")); + } + + // note that ubytes may be larger that the amount of + // uncompressed bytes, so trim it to another byte array + // with the exact size. + byte[] textBytes = new byte[up]; + System.arraycopy(uBytes, 0, textBytes, 0, up); + + return textBytes; + } + + + /** + * Read the header <code>byte</code> array. + * + * @param bytes <code>byte</code> array containing header + * record data. + * + * @return <code>HeaderInfo</code> object. + * + * @throws IOException If any I/O error occurs. + */ + private HeaderInfo readHeader(byte[] bytes) throws IOException { + + HeaderInfo header = new HeaderInfo(); + + ByteArrayInputStream bis = new ByteArrayInputStream(bytes); + DataInputStream dis = new DataInputStream(bis); + + // Normally the first 2 bytes comprised of the version + // which should either be COMPRESSED or UNCOMPRESSED + // SmartDoc/Quickword would add a 0x01 to the first + // byte, thus their version would be 0x0101 for UNCOMPRESSED + // instead of 0x0001 and 0x0102 for UNCOMPRESSED instead of + // 0x0002. + + dis.readByte(); + header.version = dis.readByte(); + + // read extra 2 unused bytes + dis.readShort(); + + // Read the text length, this should be unsigned 4 bytes. + // We could store the read value into a long, but then + // our current buffer limit is the max positive of an int. + // That is a large enough limit, thus we shall stay with + // storing the value in an int. If it exceeds, then + // an IOException should be thrown. + header.textLen = dis.readInt(); + if (header.textLen < 0) { + throw new IOException(res.getString("DOC_TEXT_LENGTH_EXCEEDED")); + } + + // read the number of records - unsigned 2 bytes + header.textRecordCount = ((int) dis.readShort()) & 0x0000ffff; + + // read the record size - unsigned 2 bytes + header.textRecordSize = ((int) dis.readShort()) & 0x0000ffff; + + // read extra 4 unused bytes + dis.readInt(); + + return header; + } + + + /** + * Prints out header info into log. Used for debugging purposes only. + * + * @param header <code>HeaderInfo</code> structure. + */ + private void dumpHeader(HeaderInfo header) { + + log("<DOC_INFO "); + log("version=\"" + header.version + "\" "); + log("text-length=\"" + header.textLen + "\" "); + log("number-of-records=\"" + header.textRecordCount + "\" "); + log("record-size=\"" + header.textRecordSize + "\" />"); + } + + + /** + * Sends message to the log object. + * + * @param str Debug string message. + */ + private void log(String str) { + Debug.log(Debug.TRACE, str); + } + + + /** + * Inner class to store AportisDoc header information. + */ + private class HeaderInfo { + + /** length of text section */ + int textLen = 0; + + /** number of text records */ + int textRecordCount = 0; + + /** + * size of a text record. This is normally the same as + * TEXT_RECORD_SIZE, but some applications may modify this. + */ + int textRecordSize = 0; + + /** compression type */ + int version = 0; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocEncoder.java new file mode 100644 index 000000000000..90cf0e5cd1f1 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocEncoder.java @@ -0,0 +1,214 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import java.io.ByteArrayOutputStream; +import java.io.DataOutputStream; +import java.io.IOException; +import java.io.UnsupportedEncodingException; +import java.util.List; +import java.util.ArrayList; + +import org.openoffice.xmerge.converter.palm.Record; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxw.DocumentSerializerImpl + * DocumentSerializerImpl} to encode the AportisDoc format. + * It does not deal with any XML tags. It only knows how to encode + * from <code>String</code>. + * + * @author Herbie Ong + */ +final class DocEncoder implements DocConstants { + + /** Text buffer to contain text section. */ + private StringBuffer textBuffer = null; + + /** Length of text section. */ + private int textLen = 0; + + /** Number of text records. */ + private int textRecCount = 0; + + + /** + * Default constructor creates a header and + * a text buffer for holding all the text in + * the AportisDoc database. + */ + DocEncoder() { + + textBuffer = new StringBuffer(TEXT_RECORD_SIZE); + } + + + /** + * This method appends text into the text section of + * the AportisDoc database. + * + * @param text <code>String</code> to append. + */ + void addText(String text) { + + textBuffer.append(text); + } + + + /** + * This method appends text into the text section of + * the AportisDoc database. + * + * @param text <code>char</code> array to append. + */ + void addText(char[] text) { + + textBuffer.append(text); + } + + + /** + * This method appends text character into the text + * section of the AportisDoc database. + * + * @param text <code>char</code> to append. + */ + void addText(char text) { + + textBuffer.append(text); + } + + + /** + * This method encodes the information given to a + * palm <code>Record</code> array in the AportisDoc + * database format. + * + * @return <code>Record</code> array holding AportisDoc + * contents. + * + * @throws IOException If any I/O error occurs. + */ + Record[] getRecords() throws IOException { + + byte textBytes[] = processTextBuffer(); + textLen = textBytes.length; + textRecCount = (short) (textBytes.length / TEXT_RECORD_SIZE); + + // recBytes to hold a record of bytes at a time + byte recBytes[] = new byte[TEXT_RECORD_SIZE]; + int pos = 0; + + List textRecords = new ArrayList(textRecCount + 1); + + // split textBytes into chunks of Record objects + // and store in textRecords object. + for (int i = 0; i < textRecCount; i++) { + + System.arraycopy(textBytes, pos, recBytes, 0, recBytes.length); + pos += recBytes.length; + Record zRec = new Record(recBytes); + textRecords.add(zRec); + } + + // there's more if ... + + if (pos < textLen) { + + textRecCount++; + + recBytes = new byte[textLen - pos]; + System.arraycopy(textBytes, pos, recBytes, 0, recBytes.length); + Record rec = new Record(recBytes); + textRecords.add(rec); + } + + // construct the Record array and copy + // references from textRecords. + + Record[] allRecords = new Record[textRecords.size() + 1]; + + allRecords[0] = new Record(getHeaderBytes()); + + for (int i = 1; i < allRecords.length; i++) { + + allRecords[i] = (Record) textRecords.get(i-1); + } + + return allRecords; + } + + + /** + * This method converts the text buffer into a <code>byte</code> + * array with the proper encoding of the text section of the + * AportisDoc format. + * + * TODO: do compression. + * + * @return byte[] Converted <code>byte</code> array of text + * section. + * + * @throws IOException If any I/O error occurs. + */ + private byte[] processTextBuffer() throws IOException + { + String str = textBuffer.toString(); + byte bytes[] = str.getBytes(ENCODING); + + return bytes; + } + + + /** + * This method produces the <code>byte</code> array for the header. + * + * @return <code>byte</code> array containing header record data. + * + * @throws IOException If any I/O error occurs. + */ + private byte[] getHeaderBytes() throws IOException + { + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + DataOutputStream dos = new DataOutputStream(bos); + + // TODO: for now, we shall use UNCOMPRESSED. + // later, we need to use COMPRESSED or a setting. + dos.writeShort(UNCOMPRESSED); + dos.writeShort(SPARE); + dos.writeInt(textLen); + dos.writeShort(textRecCount); + dos.writeShort(TEXT_RECORD_SIZE); + dos.writeInt(SPARE); + + byte[] bytes = bos.toByteArray(); + + return bytes; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentDeserializerImpl.java new file mode 100644 index 000000000000..98022bcf47d9 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentDeserializerImpl.java @@ -0,0 +1,313 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import org.w3c.dom.Text; + +import java.io.IOException; +import java.util.Enumeration; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.PdbDecoder; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.Debug; + +/** + * <p>AportisDoc implementation of <code>DocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.aportisdoc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts an file in AportisDoc PDB format to StarOffice + * XML format.</p> + * + * <p>The <code>deserialize</code> method uses a <code>DocDecoder</code> + * to read the AportisDoc format into a <code>String</code> object, then + * it calls <code>buildDocument</code> to create a <code>SxwDocument</code> + * object from it.</p> + * + * @author Herbie Ong + */ +public final class DocumentDeserializerImpl + implements OfficeConstants, DocConstants, DocumentDeserializer { + + /** A <code>ConvertData</code> object assigned to this object. */ + private ConvertData cd = null; + + + /** + * Constructor that assigns the given <code>ConvertData</code> + * to this object as input. + * + * @param cd A <code>ConvertData</code> object to read data for + * the conversion process by the <code>deserialize</code> + * method. + */ + public DocumentDeserializerImpl(ConvertData cd) { + this.cd = cd; + } + + + /** + * Convert the given <code>ConvertData</code> object + * into a <code>SxwDocument</code> object. + * + * @return Resulting <code>SxwDocument</code> object. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public Document deserialize() throws IOException, ConvertException { + + int numberOfPDBs = cd.getNumDocuments(); + Document doc = null; + int i=0; + ConvertData cdOut; + Enumeration e = cd.getDocumentEnumeration(); + while (e.hasMoreElements()) { + PalmDocument palmDoc = (PalmDocument) e.nextElement(); + PalmDB pdb = palmDoc.getPdb(); + + log("<?xml version=\"1.0\" encoding=\"UTF-8\"?>"); + log("<AportisDoc>"); + + Record[] recs = pdb.getRecords(); + String docName = palmDoc.getName(); + DocDecoder decoder = new DocDecoder(); + String text = decoder.parseRecords(recs); + doc = buildDocument(docName, text); + + log("</AportisDoc>"); + } + + return doc; + } + + + /** + * Parses the text content of an AportisDoc format and build a + * <code>SxwDocument</code>. + * + * @param docName Name of <code>Document</code>. + * @param str Text content of AportisDoc format. + * + * @return Resulting <code>SxwDocument</code> object. + * + * @throws IOException If any I/O error occurs. + */ + private SxwDocument buildDocument(String docName, String str) + throws IOException { + + // create minimum office xml document. + SxwDocument sxwDoc = new SxwDocument(docName); + sxwDoc.initContentDOM(); + + org.w3c.dom.Document doc = sxwDoc.getContentDOM(); + + // Grab hold of the office:body tag, + // Assume there should be one. + // This is where top level paragraphs will append to. + NodeList list = doc.getElementsByTagName(TAG_OFFICE_BODY); + Node bodyNode = list.item(0); + + // Store all the text in a character array. + char[] text = str.toCharArray(); + + // startIndex has 2 purposes: + // if value is -1, it means that there are no text characters + // needed to be processed for a Text node. if value >= 0, it + // is the index of the starting position of a text section + // for a Text node. + int startIndex = -1; + + // Create a paragraph node to start with. + Element paraNode = doc.createElement(TAG_PARAGRAPH); + + log("<PARA>"); + + for (int i = 0; i < text.length; i++) { + + switch (text[i]) { + + case TAB_CHAR: + + // Check if there are text to be processed first. + if (startIndex >= 0) { + addTextNode(doc, paraNode, text, startIndex, i - 1); + startIndex = -1; + } + + // Then, add tab element. + Element tabNode = doc.createElement(TAG_TAB_STOP); + paraNode.appendChild(tabNode); + + log("<TAB/>"); + break; + + case EOL_CHAR: + + // Check if there are text to be processed first. + if (startIndex >= 0) { + addTextNode(doc, paraNode, text, startIndex, i - 1); + startIndex = -1; + } + + // Then, add the current paragraph to body. + bodyNode.appendChild(paraNode); + + // Create another paragraph element. + paraNode = doc.createElement(TAG_PARAGRAPH); + + log("</PARA>"); + log("<PARA>"); + break; + + case SPACE_CHAR: + + // count is the number of space chars from i + int count = 0; + + // Do a look ahead and count the number of space chars + while (text[i + 1 + count] == SPACE_CHAR) { + count++; + } + + // Need to build a space node ONLY if count is > 1. + + if (count > 0) { + + // Check if there are text to be processed first + if (startIndex >= 0) { + addTextNode(doc, paraNode, text, + startIndex, i); + startIndex = -1; + } + + // Then, create a space element + // with the proper attribute. + Element spaceNode = doc.createElement(TAG_SPACE); + spaceNode.setAttribute(ATTRIBUTE_SPACE_COUNT, + Integer.toString(count)); + + paraNode.appendChild(spaceNode); + + // reposition i to the last space character. + i += count; + + log("<SPACE count=\"" + count + "\" />"); + + } else { + + // If there are no chars for text node yet, + // consider this one. + if (startIndex < 0) { + + startIndex = i; + log("<TEXT>"); + } + } + + break; + + default: + + // If there are no chars for text node yet, + // this should be the start. + if (startIndex < 0) { + + startIndex = i; + log("<TEXT>"); + } + + break; + } + } + + int lastIndex = text.length - 1; + + // Check if there are text to be processed first. + + if (startIndex >= 0) { + addTextNode(doc, paraNode, text, startIndex, lastIndex); + } + + // Then, add the last paragraph element if it is not added yet. + if (text[lastIndex] != EOL_CHAR) { + bodyNode.appendChild(paraNode); + } + + log("</PARA>"); + + return sxwDoc; + } + + + /** + * Add a Text <code>Node</code> to the given paragraph node with the + * text starting at the given <code>startPos</code> until + * <code>endPos</code>. + * + * @param doc <code>org.w3c.dom.Document</code> object for creating + * <code>Node</code> objects. + * @param para The current paragraph <code>Node</code> to append + * text <code>Node</code>. + * @param text Array of characters containing text. + * @param startPos Starting index position for text value. + * @param endPos End index position for text value. + */ + private void addTextNode(org.w3c.dom.Document doc, Node para, char text[], + int startPos, int endPos) { + + String str = new String(text, startPos, endPos - startPos + 1); + Text textNode = doc.createTextNode(str); + para.appendChild(textNode); + log(str); + log("</TEXT>"); + } + + /** + * Sends message to the log object. + * + * @param str Debug message. + */ + private void log(String str) { + + Debug.log(Debug.TRACE, str); + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentMergerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentMergerImpl.java new file mode 100644 index 000000000000..23b236b41e6a --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentMergerImpl.java @@ -0,0 +1,99 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.w3c.dom.Document; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.MergeException; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.Difference; +import org.openoffice.xmerge.merger.NodeMergeAlgorithm; +import org.openoffice.xmerge.merger.Iterator; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.diff.ParaNodeIterator; +import org.openoffice.xmerge.merger.diff.IteratorLCSAlgorithm; +import org.openoffice.xmerge.merger.merge.DocumentMerge; +import org.openoffice.xmerge.merger.merge.CharacterBaseParagraphMerge; +import org.openoffice.xmerge.util.Debug; + + +/** + * AportisDoc implementation of <code>DocumentMerger</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.aportisdoc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + */ +public class DocumentMergerImpl implements DocumentMerger { + + private ConverterCapabilities cc_; + private org.openoffice.xmerge.Document orig = null; + + public DocumentMergerImpl(org.openoffice.xmerge.Document doc, ConverterCapabilities cc) { + cc_ = cc; + this.orig = doc; + } + + public void merge(org.openoffice.xmerge.Document modifiedDoc) throws MergeException { + + SxwDocument wdoc1 = (SxwDocument) orig; + SxwDocument wdoc2 = (SxwDocument) modifiedDoc; + + Document doc1 = wdoc1.getContentDOM(); + Document doc2 = wdoc2.getContentDOM(); + + Iterator i1 = new ParaNodeIterator(cc_, doc1.getDocumentElement()); + Iterator i2 = new ParaNodeIterator(cc_, doc2.getDocumentElement()); + + DiffAlgorithm diffAlgo = new IteratorLCSAlgorithm(); + + // find out the paragrah level diffs + Difference[] diffTable = diffAlgo.computeDiffs(i1, i2); + + if (Debug.isFlagSet(Debug.INFO)) { + Debug.log(Debug.INFO, "Diff Result: "); + + for (int i = 0; i < diffTable.length; i++) { + Debug.log(Debug.INFO, diffTable[i].debug()); + } + } + + // merge the paragraphs + NodeMergeAlgorithm charMerge = new CharacterBaseParagraphMerge(); + DocumentMerge docMerge = new DocumentMerge(cc_, charMerge); + + Iterator result = null; + + docMerge.applyDifference(i1, i2, diffTable); + } +} + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentSerializerImpl.java new file mode 100644 index 000000000000..a2652df792b3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/DocumentSerializerImpl.java @@ -0,0 +1,532 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import java.io.IOException; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.palm.PdbEncoder; +import org.openoffice.xmerge.converter.palm.PdbDecoder; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.XmlUtil; + +/** + * <p>AportisDoc implementation of + * org.openoffice.xmerge.DocumentSerializer + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.aportisdoc.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>The <code>serialize</code> method traverses the DOM + * document from the given <code>Document</code> object. It uses a + * <code>DocEncoder</code> object for the actual conversion of + * contents to the AportisDoc format.</p> + * + * @author Herbie Ong + */ + + +public final class DocumentSerializerImpl + implements OfficeConstants, DocConstants, DocumentSerializer { + + /** A <code>DocEncoder</code> object for encoding to AportisDoc. */ + private DocEncoder encoder = null; + + /** SXW <code>Document</code> object that this converter processes. */ + private SxwDocument sxwDoc = null; + + + /** + * Constructor. + * + * @param doc A SXW <code>Document</code> to be converted. + */ + public DocumentSerializerImpl(Document doc) { + sxwDoc = (SxwDocument) doc; + } + + + /** + * <p>Method to convert a <code>Document</code> into a PDB. + * It passes back the converted data as a <code>ConvertData</code> + * object.</p> + * + * <p>This method is not thread safe for performance reasons. + * This method should not be called from within two threads. + * It would be best to call this method only once per object + * instance.</p> + * + * @return The <code>ConvertData</code> object containing the output. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public ConvertData serialize() throws ConvertException, IOException { + + + // get the server document name + + String docName = sxwDoc.getName(); + + // get DOM document + + org.w3c.dom.Document domDoc = sxwDoc.getContentDOM(); + + encoder = new DocEncoder(); + + // Traverse to the office:body element. + // There should only be one. + + NodeList list = domDoc.getElementsByTagName(TAG_OFFICE_BODY); + int len = list.getLength(); + + if (len > 0) { + Node node = list.item(0); + traverseBody(node); + } + + // create a ConvertData object. + // + Record records[] = encoder.getRecords(); + ConvertData cd = new ConvertData(); + + PalmDocument palmDoc = new PalmDocument(docName, + DocConstants.CREATOR_ID, DocConstants.TYPE_ID, + 0, PalmDB.PDB_HEADER_ATTR_BACKUP, records); + + cd.addDocument(palmDoc); + return cd; + } + + + /** + * This method traverses <i>office:body</i> element. + * + * @param node <i>office:body</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseBody(Node node) throws IOException { + + log("<?xml version=\"1.0\" encoding=\"UTF-8\"?>"); + log("<AportisDOC>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH) || + nodeName.equals(TAG_HEADING)) { + + traverseParagraph(child); + + } else if (nodeName.equals(TAG_UNORDERED_LIST)) { + + traverseList(child); + + } else if (nodeName.equals(TAG_ORDERED_LIST)) { + + traverseList(child); + + } else { + + log("<OTHERS " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + log("</AportisDOC>"); + } + + + /** + * This method traverses the <i>text:p</i> and <i>text:h</i> + * element <code>Node</code> objects. + * + * @param node A <i>text:p</i> or <i>text:h</i> + * <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseParagraph(Node node) throws IOException { + + log("<PARA>"); + traverseParaContents(node); + encoder.addText(EOL_CHAR); + log("</PARA>"); + } + + + /** + * This method traverses a paragraph content. + * It uses the <code>traverseParaElem</code> method to + * traverse into Element <code>Node</code> objects. + * + * @param node A paragraph or content <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseParaContents(Node node) throws IOException { + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + short nodeType = child.getNodeType(); + + switch (nodeType) { + + case Node.TEXT_NODE: + // this is for grabbing text nodes. + String s = child.getNodeValue(); + + if (s.length() > 0) { + encoder.addText(s); + } + + log("<TEXT>"); + log(s); + log("</TEXT>"); + + break; + + case Node.ELEMENT_NODE: + + traverseParaElem(child); + break; + + case Node.ENTITY_REFERENCE_NODE: + + log("<ENTITY_REFERENCE>"); + traverseParaContents(child); + log("<ENTITY_REFERENCE/>"); + break; + + default: + log("<OTHERS " + XmlUtil.getNodeInfo(node) + " />"); + } + } + } + } + + + /** + * This method traverses an <code>Element</code> <code>Node</code> + * within a paragraph. + * + * @param node <code>Element</code> <code>Node</code> within a + * paragraph. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseParaElem(Node node) throws IOException { + + String nodeName = node.getNodeName(); + + if (nodeName.equals(TAG_SPACE)) { + + // this is for text:s tags. + NamedNodeMap map = node.getAttributes(); + Node attr = map.getNamedItem(ATTRIBUTE_SPACE_COUNT); + StringBuffer space = new StringBuffer(SPACE_CHAR); + int count = 1; + + if (attr != null) { + + try { + + String countStr = attr.getNodeValue(); + count = Integer.parseInt(countStr.trim()); + + } catch (NumberFormatException e) { + + // TODO: for now, throw IOException. + // later, perhaps will have to throw + // some other conversion exception instead. + throw new IOException(e.getMessage()); + } + } + + for (int j = 0; j < count; j++) { + + space.append(SPACE_CHAR); + } + + encoder.addText(space.toString()); + + log("<SPACE count=\"" + count + "\" />"); + + } else if (nodeName.equals(TAG_TAB_STOP)) { + + // this is for text:tab-stop + encoder.addText(TAB_CHAR); + + log("<TAB/>"); + + } else if (nodeName.equals(TAG_LINE_BREAK)) { + + // commented out by Csaba: There is no point to convert a linebreak + // into a EOL, because it messes up the number of XML nodes and the + // merge won't work properly. Other solution would be to implement such + // nodemerger, which would be able to merge embedded tags in a paragraph + + // this is for text:line-break + // encoder.addText(EOL_CHAR); + + log("skipped <LINE-BREAK/>"); + + } else if (nodeName.equals(TAG_SPAN)) { + + // this is for text:span + log("<SPAN>"); + traverseParaContents(node); + log("</SPAN>"); + + } else if (nodeName.equals(TAG_HYPERLINK)) { + + // this is for text:a + log("<HYPERLINK>"); + traverseParaContents(node); + log("<HYPERLINK/>"); + + } else if (nodeName.equals(TAG_BOOKMARK) || + nodeName.equals(TAG_BOOKMARK_START)) { + + log("<BOOKMARK/>"); + + } else if (nodeName.equals(TAG_TEXT_VARIABLE_SET) + || nodeName.equals(TAG_TEXT_VARIABLE_GET) + || nodeName.equals(TAG_TEXT_EXPRESSION) + || nodeName.equals(TAG_TEXT_USER_FIELD_GET) + || nodeName.equals(TAG_TEXT_PAGE_VARIABLE_GET) + || nodeName.equals(TAG_TEXT_SEQUENCE) + || nodeName.equals( TAG_TEXT_VARIABLE_INPUT) + || nodeName.equals(TAG_TEXT_TIME) + || nodeName.equals( TAG_TEXT_PAGE_COUNT) + || nodeName.equals(TAG_TEXT_PAGE_NUMBER ) + || nodeName.equals(TAG_TEXT_SUBJECT) + || nodeName.equals(TAG_TEXT_TITLE) + || nodeName.equals(TAG_TEXT_CREATION_TIME) + || nodeName.equals(TAG_TEXT_DATE) + || nodeName.equals(TAG_TEXT_TEXT_INPUT) + || nodeName.equals(TAG_TEXT_AUTHOR_INITIALS)) { + log("<FIELD>"); + traverseParaContents(node); + log("</FIELD>"); + + }else if (nodeName.startsWith(TAG_TEXT)) { + log("<Unknown text Field>"); + traverseParaContents(node); + log("</Unknown text Field>"); + + }else { + + log("<OTHERS " + XmlUtil.getNodeInfo(node) + " />"); + } + } + + + /** + * This method traverses list tags <i>text:unordered-list</i> and + * <i>text:ordered-list</i>. A list can only contain one optional + * <i>text:list-header</i> and one or more <i>text:list-item</i> + * elements. + * + * @param node A list <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseList(Node node) throws IOException { + + log("<LIST>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_LIST_ITEM)) { + + traverseListItem(child); + + } else if (nodeName.equals(TAG_LIST_HEADER)) { + + traverseListHeader(child); + + } else { + + log("<INVALID-XML-BUG " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + log("</LIST>"); + } + + + /** + * This method traverses a <i>text:list-header</i> element. + * It contains one or more <i>text:p</i> elements. + * + * @param node A list header <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseListHeader(Node node) throws IOException { + + log("<LIST-HEADER>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH)) { + + traverseParagraph(child); + + } else { + + log("<INVALID-XML-BUG " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + log("</LIST-HEADER>"); + } + + + /** + * <p>This method will traverse a <i>text:list-item</i>. + * A list item may contain one or more of <i>text:p</i>, + * <i>text:h</i>, <i>text:section</i>, <i>text:ordered-list</i> + * and <i>text:unordered-list</i>.</p> + * + * <p>This method currently only implements grabbing <i>text:p</i>, + * <i>text:h</i>, <i>text:unordered-list</i> and + * <i>text:ordered-list</i>.</p> + * + * @param node The <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseListItem(Node node) throws IOException { + + log("<LIST-ITEM>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH)) { + + traverseParagraph(child); + + } else if (nodeName.equals(TAG_UNORDERED_LIST)) { + + traverseList(child); + + } else if (nodeName.equals(TAG_ORDERED_LIST)) { + + traverseList(child); + + } else { + + log("<INVALID-XML-BUG " + XmlUtil.getNodeInfo(child) + " />"); + } + } + } + } + + log("</LIST-ITEM>"); + } + + + /** + * Logs debug messages. + * + * @param str The debug message. + */ + private void log(String str) { + + Debug.log(Debug.TRACE, str); + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/PluginFactoryImpl.java new file mode 100644 index 000000000000..d1de0b19a6ab --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/PluginFactoryImpl.java @@ -0,0 +1,141 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.aportisdoc; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.DocumentMergerFactory; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxw.SxwPluginFactory; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.registry.ConverterInfo; +import java.io.IOException; +import java.io.InputStream; + +/** + * <p>AportisDoc implementation of the <code>PluginFactory</code>. + * This encapsulates conversion of StarWriter XML format to and from + * AportisDoc format.</p> + * + * <p>The superclass produces a particular + * {@link org.openoffice.xmerge.Document Document} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxw.SxwDocument + * SxwDocument} that the converters in this class works with. Thus, + * this class only implements the methods that produces the converters, + * i.e. {@link + * org.openoffice.xmerge.DocumentSerializer + * DocumentSerializer} and {@link + * org.openoffice.xmerge.DocumentDeserializer + * DocumentDeserializer}; + * as well as the {@link + * org.openoffice.xmerge.ConverterCapabilities + * ConverterCapabilities} object that is specific to this format + * conversion. That superclass also produces a {@link + * org.openoffice.xmerge.DocumentMerger DocumentMerger} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxw.aportisdoc.DocumentMergerImpl + * DocumentMergerImpl} which this class derives the functionality.</p> + * + * @author Herbie Ong + */ +public final class PluginFactoryImpl extends SxwPluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory, + DocumentMergerFactory { + + public PluginFactoryImpl (ConverterInfo ci) { + super(ci); + } + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + /** + * Returns an instance of <code>DocumentSerializerImpl</code>, + * which is an implementation of the <code>DocumentSerializer</code> + * interface. + * + * @param doc <code>Document</code> object to be + * converted/serialized. + * + * @return A <code>DocumentSerializerImpl</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + + return new DocumentSerializerImpl(doc); + } + + + /** + * Returns an instance of <code>DocumentDeserializerImpl</code>, + * which is an implementation of the <code>DocumentDeserializer</code> + * interface. + * + * @param cd <code>ConvertData</code> object for reading data + * which will be converted back to a + * <code>Document</code> object. + * + * @return A DocumentDeserializerImpl object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + + return new DocumentDeserializerImpl(cd); + } + + + /** + * Returns an instance of <code>DocumentMergerImpl</code>, + * which is an implementation of the <code>DocumentMerger</code> + * interface. + * + * @param doc <code>Document</code> to merge. + * + * @return A DocumentMergerImpl object. + */ + public DocumentMerger createDocumentMerger(Document doc) { + + ConverterCapabilities cc = converterCap; + DocumentMergerImpl merger = new DocumentMergerImpl(doc, cc); + return merger; + } + + public Document createDeviceDocument(String name, InputStream is) + throws IOException { + + PalmDocument palmDoc = new PalmDocument(is); + return palmDoc; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/build.xml new file mode 100644 index 000000000000..b6efd3e2bec3 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/build.xml @@ -0,0 +1,134 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxs_aportisdoc" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxs_aportisdoc"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxw/aportisdoc"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/DocConstants.java"/> + <include name="${package}/DocDecoder.java"/> + <include name="${package}/DocEncoder.java"/> + <include name="${package}/DocumentDeserializerImpl.java"/> + <include name="${package}/DocumentSerializerImpl.java"/> + <include name="${package}/DocumentMergerImpl.java"/> + <include name="${package}/ConverterCapabilitiesImpl.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/converter.xml new file mode 100644 index 000000000000..7942295c004a --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/converter.xml @@ -0,0 +1,43 @@ +<?xml version="1.0"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<converters> + <converter type="staroffice/sxw" version="1.0"> + <converter-display-name> + AportisDoc + </converter-display-name> + <converter-description> + StarWriter XML to/from AportisDoc conversion + </converter-description> + <converter-vendor>OpenOffice.org</converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.sxw.aportisdoc.PluginFactoryImpl + </converter-class-impl> + <converter-target type="application/x-aportisdoc" /> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/makefile.mk new file mode 100644 index 000000000000..5b3f3fea509d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcxs_aportisdoc +PRJ=../../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/package.html new file mode 100644 index 000000000000..78cfe79bfbbf --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/aportisdoc/package.html @@ -0,0 +1,237 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxw.aportisdoc package</title> +</head> + +<body bgcolor="white"> + +<p>Provides the tools for doing the conversion of StarWriter XML to +and from AportisDoc format.</p> + +<p>It follows the {@link org.openoffice.xmerge} framework for the conversion process.</p> + +<p>Since it converts to/from a Palm application format, these converters +follow the <a href=../../../../converter/palm/package-summary.html#streamformat> +<code>PalmDB</code> stream format</a> for writing out to the Palm sync client or +reading in from the Palm sync client.</p> + +<p>Note that <code>PluginFactoryImpl</code> also provides a +<code>DocumentMerger</code> object, i.e. {@link org.openoffice.xmerge.converter.xml.sxw.aportisdoc.DocumentMergerImpl DocumentMergerImpl}. +This functionality was derived from its superclass +{@link org.openoffice.xmerge.converter.xml.sxw.SxwPluginFactory +SxwPluginFactory}.</p> + +<h2>AportisDoc pdb format - Doc</h2> + +<p>The AportisDoc pdb format is widely used by different Palm applications, +e.g. QuickWord, AportisDoc Reader, MiniWrite, etc. Note that some +of these applications put tweaks into the format. The converters will only +support the default AportisDoc format, plus some very minor tweaks to accommodate +other applications.</p> + +<p>The text content of the format is plain text, i.e. there are no styles +or structures. There is no notion of lists, list items, paragraphs, +headings, etc. The format does have support for bookmarks.</p> + +<p>For most Doc applications, the default character encoding supported is +the extended ASCII character set, i.e. ISO-8859-1. StarWriter XML is in +UTF-8 encoding scheme. Since UTF-8 encoding scheme covers more characters, +converting UTF-8 strings into extended ASCII would mean that there can be +possible loss of character mappings.</p> + +<p>Using JAXP, XML files can be parsed and read in as Java <code>String</code>s +which is in Unicode format, there is no loss of character mapping from UTF-8 +to Java Strings. There is possible loss of character mapping in +converting Java <code>String</code>s to ASCII bytes. Java characters that +cannot be represented in extended ASCII are converted into the ASCII +character '?' or x3F in hex digit via the <code>String.getBytes(encoding)</code> +API.</p> + +<h2>SXW to DOC Conversion</h2> + +<p>The <code>DocumentSerializerImpl</code> class implements the +<code>org.openoffice.xmerge.DocumentSerializer</code>. +This class specifically provides the conversion process from a given +<code>SxwDocument</code> object to DOC formatted records, which are +then passed back to the client via the <code>ConvertData</code> object.</p> + +<p>The following XML tags are handled. [Note that some may not be implemented yet.]</p> +<ul> +<li> + <p>Paragraphs <tt><text:p></tt> and Headings <tt><text:h></tt></p> + + <p>Heading elements are classified the same as paragraph + elements since both have the same possible elements inside. + Their main difference is that they refer to different types + of style information, which is outside of their element tags. + Since there are no styles on the DOC format, headings should + be treated the same way a paragraph is converted.</p> + + <p>For paragraph elements, convert and transfer text nodes + that are essential. Text nodes directly contained within paragraph + nodes are such. There are also a number of elements that + a paragraph element may contain. These are explained in their + own context.</p> + + <p>At the end of the paragraph, an EOL character is added by + the converter to provide a separation for each paragraph, + since the Doc format does not have a notion of a paragraph.</p> +</li> +<li> + <p>White spaces <tt><text:s></tt> and Tabs <tt><text:tab-stop></tt></p> + + <p>In SXW, normally 2 or more white-space characters are collapsed into + a single space character. In order to make sure that the document + content really contains those white-space characters, there are special + elements assigned to them.</p> + + <p>The space element specifies the number of spaces are in it. + Thus, converting it just means providing the specific number of spaces + that the element requires.</p> + + <p>There is also the tab-stop element. This is a bit tricky. In a + StarWriter document, tab-stops are specified by a column position. + A tab is not an exact number of space, but rather a specific column + positioning. Say, regular tab-stops are set at every 5th column. + At column 4, if I hit a tab, it goes to column 5. At column 1, hitting + a tab would put the cursor at column 5 as well. SmartDoc and AporticDoc + applications goes by columns for the ASCII tab character. The only problem + is that in StarWriter, one could specify a different tab-stop, but not + in most of these Doc applications, at least I have not seen one. + Solution for this is just to go with the converting to the ASCII tab + character and not do anything for different tab-stop positioning.</p> +</li> +<li> + <p>Line breaks <tt><text:line-break></tt></p> + + <p>To represent line breaks, it is simpliest to just put an ASCII LF + character. Note that the side effect of this is that an end of paragraph + also contains an ASCII LF character. Thus, for the DOC to SXW conversion, + line breaks are not distinguishable from specifying the end of a + paragraph.</p> +</li> +<li> + <p>Text spans <tt><text:span></tt></p> + + <p>Text spans contain text that have different style attributes + from the paragraphs'. Text spans can be embedded within another + text span. Since it is purely for style tagging, we only needed + to convert and transfer the text elements within these.</p> +</li> +<li> + <p>Hyperlinks <tt><text:a></tt> + + <p>Convert and transfer the text portion.</p> +</li> +<li> + <p>Bookmarks <tt><text:bookmark></tt> <tt><text:bookmark-start></tt> + <tt><text:bookmark-end></tt> [Not implemented yet]</p> + + <p>In SXW, bookmark elements are embedded inside paragraph elements. + Bookmarks can either mark a text position or a text range. <tt><text:bookmark></tt> + marks a position while the pair <tt><text:bookmark-start></tt> and + <tt><text:bookmark-end></tt></p> marks a text range. The DOC format only + supports bookmarking a text position. Thus, for the conversion, + <tt><text:bookmark></tt> and <tt><text:bookmark-start></tt> will both mark + a text position.</p> +</li> +<li> + <p>Change Tracking <tt><text:tracked-changes></tt> + <tt><text:change*></tt> [Not implemented yet]</p> + + <p>Change tracking elements are not supported yet on the current + OpenOffice XML filters, will have to watch out on this. The text + within these elements have to be interpreted properly during the + conversion process.</p> +</li> +<li> + <p>Lists <tt><text:unordered-list></tt> and + <tt><text:ordered-lists></tt></p> + + <p>A list can only contain one optional <tt><text:list-header></tt> + and one or more <tt><text:list-item></tt> elements.</p> + + <p>A <tt><text:list-header></tt> contains one or more paragraph + elements. Since there are no styles, the conversion process does not + do anything special for list headers, conversion for the paragraphs + within list headers are the same as explained above.</p> + + <p>A <tt><text:list-item></tt> may contain one or more of paragraphs, + headings, list, etc. Since the Doc format does not support any list + structure, there will not be any special handling for this element. + Conversion for elements within it shall be applied according to the + element type. Thus, lists with paragraphs within it will result in just + plain paragraphs. Sublists will not be identifiable. Paragraphs in + sublists will still appear.</p> +</li> +<li> + <p><tt><text:section></tt></p> + + <p>I am not sure what this is yet, will need to investigate more on this.</p> +</li> +</ul> +<p>There may be other tags that will still need to be addressed for this conversion.</p> + +<p>Refer to {@link org.openoffice.xmerge.converter.xml.sxw.aportisdoc.DocumentSerializerImpl DocumentSerializerImpl} +for details of implementation. It uses <code>DocEncoder</code> class to do the encoding +part.</p> + +<h2>DOC to SXW Conversion</h2> + +<p>The <code>DocumentDeserializerImpl</code> class implements the +<code>org.openoffice.xmerge.DocumentDeserializer</code>. It is +passed the device document in the form of a <code>ConvertData</code> object. +It will then create a <code>SxwDocument</code> object from the conversion of +the DOC formatted records.</p> + +<p>The text content of the Doc format will be transferred as text. Paragraph +elements will be formed based on the existence of an ASCII LF character. There +will be at least one paragraph element.</p> + +<p>Bookmarks in the Doc format will be converted to the bookmark element +<tt><text:bookmark></tt> [Not implemented yet].</p> + + +<h2>Merging changes</h2> + +<p>As mentioned above, the <code>DocumentMerger</code> object produced by +<code>PluginFactoryImpl</code> is <code>DocumentMergerImpl</code>. +Refer to the javadocs for that package/class on its merging specifications. +</p> + +<h2>TODO list</h2> + +<p><ol> +<li>Investigate Palm's with different character encodings.</li> +<li>Investigate other StarWriter XML tags</li> +</ol></p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/build.xml new file mode 100644 index 000000000000..02936516e7c9 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/build.xml @@ -0,0 +1,128 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcx_sxw" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcx_sxw"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxw"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/SxwDocument.java"/> + <include name="${package}/SxwPluginFactory.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/makefile.mk new file mode 100644 index 000000000000..c4953812ef58 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcx_sxw +PRJ=../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/package.html new file mode 100644 index 000000000000..409f041fffb2 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/package.html @@ -0,0 +1,38 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxw package</title> +</head> + +<body bgcolor="white"> +<p>Provides base implementation of StarWriter XML conversion to and from +different "Device" <code>Document</code> formats.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..4e4aaf164e7a --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ConverterCapabilitiesImpl.java @@ -0,0 +1,93 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * <p>PocketWord implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxw.pocketword.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarWriter XML to/from PocketWord conversions. The + * <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_DOCUMENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_DOCUMENT_CONTENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_HEADING.equals(tag)) + return true; + else if (OfficeConstants.TAG_ORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_UNORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_ITEM.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_HEADER.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPAN.equals(tag)) + return true; + else if (OfficeConstants.TAG_HYPERLINK.equals(tag)) + return true; + else if (OfficeConstants.TAG_LINE_BREAK.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPACE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TAB_STOP.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_SPACE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_SPACE_COUNT.equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDescriptor.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDescriptor.java new file mode 100644 index 000000000000..3e5f6e6827ff --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDescriptor.java @@ -0,0 +1,236 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.openoffice.xmerge.util.EndianConverter; + +import java.io.ByteArrayOutputStream; +import java.io.OutputStream; +import java.io.IOException; + +import java.util.Vector; + + +/** + * This class to represent the data structure stored by a Pocket Word file that + * describes that file. + * + * The data structure is of variable length, beginning at the end of the + * font declarations and ending 10 bytes before the first instance of 0xFF 0xFF + * marking a paragraph block. + * + * The variable length component arises from an 8 byte structure describing each + * paragraph in the document. These paragraph descriptors appear at the end + * of the Document Descriptor. + * + * @author Mark Murnane + * @version 1.1 + */ +class DocumentDescriptor { + private short numParagraphs = 0; + private short length = 0; + private short numLines = 0; + + private Vector paragraphDesc = null; + + DocumentDescriptor() { + paragraphDesc = new Vector(0, 1); + } + + + + /** + * Updates the <code>DocumentDescriptor</code> to include details of another + * paragraph in the document. + * + * @param len The number of characters in the paragraph. + * @param lines The number of lines on screen that the paragraph uses. + */ + public void addParagraph(short len, short lines) { + ParagraphDescriptor pd = new ParagraphDescriptor(len, lines); + + paragraphDesc.add(pd); + numParagraphs++; + numLines += lines; + length += pd.length; + } + + + /** + * Retrieve the <code>DocumentDescriptor's</code> data. Due to the variable + * length nature of the descriptor, certain fields can only be + * calculated/written after the addition of all paragraphs. + * + * @return Byte array containing the Pocket Word representation of this + * <code>DocumentDescriptor</code>. + */ + public byte[] getDescriptor () { + ByteArrayOutputStream descStream = new ByteArrayOutputStream(); + + writeHeader(descStream); + + /* + * This value seems to increment by 0x02 for each paragraph. + * For a single paragraph doc, the value is 0x08, 0x0A for two, + * 0x0C for three ... + */ + try { + descStream.write(EndianConverter.writeShort((short)(6 + + (numParagraphs * 2)))); + + descStream.write(EndianConverter.writeShort(numParagraphs)); + descStream.write(EndianConverter.writeShort((short)0)); + descStream.write(EndianConverter.writeShort(numParagraphs)); + + descStream.write(EndianConverter.writeShort((short)0)); + descStream.write(EndianConverter.writeShort((short)length)); + descStream.write(EndianConverter.writeShort((short)0)); + + descStream.write(EndianConverter.writeShort(numLines)); + descStream.write(new byte[] { 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00 } ); + + for (int i = 0; i < paragraphDesc.size(); i++) { + ParagraphDescriptor pd = (ParagraphDescriptor)paragraphDesc.elementAt(i); + + descStream.write(pd.getDescriptor()); + } + + // Byte sequence marking the end of this DocumentDescriptor + descStream.write(EndianConverter.writeShort((short)0)); + descStream.write(EndianConverter.writeShort((short)0x41)); + } + catch (IOException ioe) { + // Should never happen as this is a memory based stream. + } + + return descStream.toByteArray(); + } + + + /* + * This method loads the intial fixed portion of the descriptor and the + * mid-section. The mid-section is variable but Pocket Word doesn't seem + * to mind default values. + */ + private void writeHeader(OutputStream descStream) { + + try { + descStream.write(new byte[] { 0x00, 0x00, 0x00, 0x00, + 0x07, 0x00, 0x06, 0x00, + 0x15, 0x00, 0x10, 0x00, + 0x01, 0x00, (byte)0xD0, 0x2F, + 0x00, 0x00, (byte)0xE0, 0x3D, + 0x00, 0x00, (byte)0xF0, 0x00, + 0x00, 0x00, (byte)0xA0, 0x05, + 0x00, 0x00, (byte)0xA0, 0x05, + 0x00, 0x00, (byte)0xA0, 0x05, + 0x00, 0x00, (byte)0xA0, 0x05, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x0A, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x04, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x0A, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x04, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x08, 0x00, + 0x07, 0x00, 0x10, 0x00, + 0x01, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x12, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x1F, 0x04, 0x00, 0x00 } ); + + /* + * The next four bytes are variable, but a pattern hasn't yet been + * established. Pocket Word seems to accept this constant value. + * + * The bytes are repeated after another 12 byte sequence which does + * not seem to change from one file to the next. + */ + descStream.write(new byte[] { (byte)0xE2, 0x02, 0x00, 0x00 } ); + descStream.write(new byte[] { 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x3D, 0x04, 0x00, 0x00 } ); + descStream.write(new byte[] { (byte)0xE2, 0x02, 0x00, 0x00 } ); + + descStream.write(new byte[] { 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x40, 0x00, 0x08, 0x00 } ); + } + catch (IOException ioe) { + /* Shouldn't happen with a ByteArrayOutputStream */ + } + } + + + /** + * <code>ParagraphDescriptor</code> represents the data structure used to + * describe individual paragraphs within a <code>DocumentDescriptor.</code> + * + * It is used solely by the <code>DocumentDescriptor<code> class. + */ + private class ParagraphDescriptor { + private short filler = 0; + private short lines = 0; + private short length = 0; + private short unknown = 0x23; + + public ParagraphDescriptor(short len, short numLines) { + lines = numLines; + length = (short)(len + 1); + } + + public byte[] getDescriptor() { + ByteArrayOutputStream desc = new ByteArrayOutputStream(); + + try { + desc.write(EndianConverter.writeShort(filler)); + desc.write(EndianConverter.writeShort(lines)); + desc.write(EndianConverter.writeShort(length)); + desc.write(EndianConverter.writeShort(unknown)); + } + catch (IOException ioe) { + /* Should never happen */ + } + + return desc.toByteArray(); + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDeserializerImpl.java new file mode 100644 index 000000000000..373df77886f8 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentDeserializerImpl.java @@ -0,0 +1,298 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentDeserializer; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; + +import org.openoffice.xmerge.converter.xml.ParaStyle; +import org.openoffice.xmerge.converter.xml.TextStyle; +import org.openoffice.xmerge.converter.xml.StyleCatalog; + +import org.openoffice.xmerge.util.OfficeUtil; + +import java.io.InputStream; +import java.io.IOException; +import java.io.FileInputStream; +import java.io.FileDescriptor; + +import java.util.Enumeration; +import java.util.Vector; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; + + +/** + * <p>Pocket Word implementation of <code>DocumentDeserializer</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.pocketword.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts a Pocket Word file to an OpenOffice Writer XML DOM.</p> + * + * @author Mark Murnane + * @version 1.1 + */ +public final class DocumentDeserializerImpl + implements DocumentDeserializer, OfficeConstants { + + private PocketWordDocument pswDoc = null; + private SxwDocument sxwDoc = null; + private String docName; + + private StyleCatalog styleCat = null; + + + /** + * Initialises a new <code>DocumentDeserializerImpl</code> using the + * supplied <code>ConvertData</code>.</p> + * + * <p>The <code>Document</code> objects in the <code>ConvertData</code> + * should be {@link + * org.openoffice.xmerge.converter.xml.sxw.pocketword.PocketWordDocument + * PocketWordDocument} objects.</p> + * + * @param cd ConvertData containing a <code>PocketWordDocument</code> + * for conversion. + */ + public DocumentDeserializerImpl(ConvertData cd) { + Enumeration e = cd.getDocumentEnumeration(); + + // A Pocket Word file is composed of one binary file + while (e.hasMoreElements()) { + pswDoc = (PocketWordDocument)e.nextElement(); + } + + docName = pswDoc.getName(); + } + + + /** + * <p>Convert the data passed into the <code>DocumentDeserializer</code> + * constructor into the OpenOffice Writer <code>Document</code> + * format.</p> + * + * <p>This method may or may not be thread-safe. It is expected + * that the user code does not call this method in more than one + * thread. And for most cases, this method is only done once.</p> + * + * @return The resulting <code>Document</code> object from conversion. + * + * @throws ConvertException If any Convert error occurs. + * @throws IOException If any I/O error occurs. + */ + public Document deserialize() throws IOException, ConvertException { + Enumeration pe = pswDoc.getParagraphEnumeration(); + + sxwDoc = new SxwDocument (docName); + sxwDoc.initContentDOM(); + + // Default to an initial 5 entries in the catalog. + styleCat = new StyleCatalog(5); + + try { + buildDocument(pe); + } + catch (Exception e) { + e.printStackTrace(); + throw new ConvertException("Error building OpenOffice Writer DOM: " + + e.toString()); + + } + + return sxwDoc; + } + + + /** + * This method actually takes care of the conversion. + * + * @param data An Enumeration of all Paragraphs in the Pocket Word doc. + * + * @return The OpenOffice Writer XML representation of the data. + * + * @throws IOException If any I/O errors occur. + */ + private void buildDocument(Enumeration data) throws IOException { + + org.w3c.dom.Document doc = sxwDoc.getContentDOM(); + + /* + * There should be only one each of office:body and + * office:automatic-styles in each document. + */ + Node bodyNode = doc.getElementsByTagName(TAG_OFFICE_BODY).item(0); + + // Not every document has an automatic style tag + Node autoStylesNode = doc.getElementsByTagName( + TAG_OFFICE_AUTOMATIC_STYLES).item(0); + if (autoStylesNode == null) { + autoStylesNode = doc.createElement(TAG_OFFICE_AUTOMATIC_STYLES); + doc.insertBefore(autoStylesNode, bodyNode); + } + + + // Needed for naming new styles + int paraStyles = 1; + int textStyles = 1; + + // Pocket Word has no concept of a list. + Element listNode = null; + + + // Down to business ... + while (data.hasMoreElements()) { + Paragraph p = (Paragraph)data.nextElement(); + Element paraNode = doc.createElement(TAG_PARAGRAPH); + + // Set paragraph style information here + ParaStyle pStyle = p.makeStyle(); + if (pStyle == null) { + paraNode.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, + PocketWordConstants.DEFAULT_STYLE); + } + else { + // Create paragraph style + pStyle.setName(new String("PS" + paraStyles++)); + paraNode.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, pStyle.getName()); + styleCat.add(pStyle); + } + + + /* + * For each of the paragraphs, process each segment. + * There will always be at least one. + */ + Enumeration paraData = p.getSegmentsEnumerator(); + Vector textSpans = new Vector(0, 1); + + do { + ParagraphTextSegment pts = (ParagraphTextSegment)paraData.nextElement(); + Element span = doc.createElement(OfficeConstants.TAG_SPAN); + + TextStyle ts = pts.getStyle(); + + if (ts != null) { + ts.setName(new String("TS" + textStyles++)); + span.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, ts.getName()); + styleCat.add(ts); + } + else { + span.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, + PocketWordConstants.DEFAULT_STYLE); + } + + // If this isn't a blank paragraph + if (pts.getText() != null && !pts.getText().equals("")) { + Node[] children = OfficeUtil.parseText(pts.getText(), doc); + + for (int j = 0; j < children.length; j++) { + span.appendChild(children[j]); + } + } + + textSpans.add(span); + + } while (paraData.hasMoreElements()); + + + /* + * Special case for the first span. If it has no style, then + * it shouldn't be a span, so just add its children with style + * set as standard. + */ + Element firstSpan = (Element)textSpans.elementAt(0); + String styleName = firstSpan.getAttribute(ATTRIBUTE_TEXT_STYLE_NAME); + if (styleName.equals(PocketWordConstants.DEFAULT_STYLE)) { + NodeList nl = firstSpan.getChildNodes(); + int len = nl.getLength(); + + for (int i = 0; i < len; i++) { + /* + * Always take item 0 as the DOM tree event model will + * cause the NodeList to shrink as each Node is reparented. + * + * By taking the first item from the list, we essentially + * traverse the list in order. + */ + paraNode.appendChild(nl.item(0)); + } + } + else { + paraNode.appendChild(firstSpan); + } + + // The rest are spans, so just add them + for (int i = 1; i < textSpans.size(); i++) { + paraNode.appendChild((Node)textSpans.elementAt(i)); + } + + + /* + * Pocket Word doesn't support lists, but it does have bulleted + * paragraphs that are essentially the same thing. + * + * Unlike OpenOffice Writer, a blank paragraph can be bulleted + * as well. This will be handled by inserting a blank paragraph + * into the unordered list, but OpenOffice Writer will not display + * an item at that point in the list. + */ + if (p.isBulleted()) { + if (listNode == null) { + listNode = doc.createElement(TAG_UNORDERED_LIST); + } + Element listItem = doc.createElement(TAG_LIST_ITEM); + listItem.appendChild(paraNode); + listNode.appendChild(listItem); + } + else { + if (listNode != null) { + bodyNode.appendChild(listNode); + listNode = null; + } + bodyNode.appendChild(paraNode); + } + } // End processing paragraphs + + + // Now write the style catalog to the document + NodeList nl = styleCat.writeNode(doc, "dummy").getChildNodes(); + int nlLen = nl.getLength(); // nl.item reduces the length + for (int i = 0; i < nlLen; i++) { + autoStylesNode.appendChild(nl.item(0)); + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentMergerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentMergerImpl.java new file mode 100644 index 000000000000..c6a14ba2877d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentMergerImpl.java @@ -0,0 +1,99 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.w3c.dom.Document; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.MergeException; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.Difference; +import org.openoffice.xmerge.merger.NodeMergeAlgorithm; +import org.openoffice.xmerge.merger.Iterator; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.diff.ParaNodeIterator; +import org.openoffice.xmerge.merger.diff.IteratorLCSAlgorithm; +import org.openoffice.xmerge.merger.merge.DocumentMerge; +import org.openoffice.xmerge.merger.merge.CharacterBaseParagraphMerge; +import org.openoffice.xmerge.util.Debug; + + +/** + * PocketWord implementation of <code>DocumentMerger</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.pocketword.PluginFactoryImpl + * PluginFactoryImpl}.</p> + */ +public class DocumentMergerImpl implements DocumentMerger { + + private ConverterCapabilities cc_; + private org.openoffice.xmerge.Document orig = null; + + public DocumentMergerImpl(org.openoffice.xmerge.Document doc, ConverterCapabilities cc) { + cc_ = cc; + this.orig = doc; + } + + public void merge(org.openoffice.xmerge.Document modifiedDoc) throws MergeException { + + SxwDocument wdoc1 = (SxwDocument) orig; + SxwDocument wdoc2 = (SxwDocument) modifiedDoc; + + Document doc1 = wdoc1.getContentDOM(); + Document doc2 = wdoc2.getContentDOM(); + + Iterator i1 = new ParaNodeIterator(cc_, doc1.getDocumentElement()); + Iterator i2 = new ParaNodeIterator(cc_, doc2.getDocumentElement()); + + DiffAlgorithm diffAlgo = new IteratorLCSAlgorithm(); + + // find out the paragrah level diffs + Difference[] diffTable = diffAlgo.computeDiffs(i1, i2); + + if (Debug.isFlagSet(Debug.INFO)) { + Debug.log(Debug.INFO, "Diff Result: "); + + for (int i = 0; i < diffTable.length; i++) { + Debug.log(Debug.INFO, diffTable[i].debug()); + } + } + + // merge the paragraphs + NodeMergeAlgorithm charMerge = new CharacterBaseParagraphMerge(); + DocumentMerge docMerge = new DocumentMerge(cc_, charMerge); + + Iterator result = null; + + docMerge.applyDifference(i1, i2, diffTable); + } +} + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentSerializerImpl.java new file mode 100644 index 000000000000..2604e903c564 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/DocumentSerializerImpl.java @@ -0,0 +1,437 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.w3c.dom.Node; +import org.w3c.dom.NodeList; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentSerializer; + +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; + +import org.openoffice.xmerge.converter.xml.ParaStyle; +import org.openoffice.xmerge.converter.xml.TextStyle; +import org.openoffice.xmerge.converter.xml.StyleCatalog; + +import java.io.OutputStream; +import java.io.ByteArrayOutputStream; +import java.io.IOException; + + +/** + * <p>Pocket Word implementation of <code>DocumentDeserializer</code> + * for use by {@link + * org.openoffice.xmerge.converter.xml.sxw.pocketword.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>This converts an OpenOffice Writer XML files to a Pocket Word file<.</p> + * + * @author Mark Murnane + * @version 1.1 + */ +public final class DocumentSerializerImpl + implements DocumentSerializer, OfficeConstants { + + private PocketWordDocument pswDoc; + private SxwDocument sxwDoc; + + private StyleCatalog styleCat = null; + + private boolean inList = false; + + + /** + * <p>Initialises a new <code>DocumentSerializerImpl</code> using the.<br> + * supplied <code>Document</code></p> + * + * <p>The supplied document should be an {@link + * org.openoffice.xmerge.converter.xml.sxw.SxwDocument SxwDocument} + * object.</p> + * + * @param document The <code>Document</code> to convert. + */ + public DocumentSerializerImpl(Document doc) { + sxwDoc = (SxwDocument)doc; + pswDoc = new PocketWordDocument(sxwDoc.getName()); + } + + + /** + * <p>Convert the data passed into the <code>DocumentSerializerImpl</code> + * constructor into Pocket Word format.</p> + * + * <p>This method may or may not be thread-safe. It is expected + * that the user code does not call this method in more than one + * thread. And for most cases, this method is only done once.</p> + * + * @return <code>ConvertData</code> object to pass back the + * converted data. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public ConvertData serialize() throws IOException, ConvertException { + ConvertData cd = new ConvertData(); + + org.w3c.dom.Document doc = sxwDoc.getContentDOM(); + + // Load any style info before traversing the document content tree + loadStyles(); + + NodeList list = doc.getElementsByTagName(TAG_OFFICE_BODY); + + int len = list.getLength(); + if (len > 0) { + Node node = list.item(0); + traverseBody(node); + } + + cd.addDocument(pswDoc); + + return cd; + } + + + /* + * Handles the loading of defined styles from the style.xml file as well + * as automatic styles from the content.xml file. + * + * Any change to a defined style, such as a short bold section, falls into + * the latter category. + */ + private void loadStyles() { + org.w3c.dom.Document contentDom = sxwDoc.getContentDOM(); + org.w3c.dom.Document styleDom = sxwDoc.getStyleDOM(); + + styleCat = new StyleCatalog(25); + + NodeList nl = null; + String families[] = new String[] { PocketWordConstants.TEXT_STYLE_FAMILY, + PocketWordConstants.PARAGRAPH_STYLE_FAMILY, + PocketWordConstants.PARAGRAPH_STYLE_FAMILY }; + Class classes[] = new Class[] { TextStyle.class, + ParaStyle.class, + TextStyle.class }; + + String[] styleTypes = new String[] { TAG_OFFICE_STYLES, + TAG_OFFICE_AUTOMATIC_STYLES, + TAG_OFFICE_MASTER_STYLES }; + + /* + * Documents converted from PSW -> SXW will not have a style.xml when + * being converted back to PSW. This would occur if a document was + * not modified within Writer between conversions. + * + * Any Writer modifications and saves create the style.xml and other + * portions of a complete Writer SXW file. + */ + if (styleDom != null) { + // Process the Style XML tree + for (int i = 0; i < styleTypes.length; i++ ) { + nl = styleDom.getElementsByTagName(styleTypes[i]); + if (nl.getLength() != 0) { + styleCat.add(nl.item(0), families, classes, null, false); + } + } + } + + /* + * Process the content XML for any other style info. + * Should only be automatic types here. + */ + for (int i = 0; i < styleTypes.length; i++ ) { + nl = contentDom.getElementsByTagName(styleTypes[i]); + if (nl.getLength() != 0) { + styleCat.add(nl.item(0), families, classes, null, false); + } + } + } + + + /* + * Process the office:body tag. + */ + private void traverseBody(Node node) throws IOException, ConvertException { + + if (node.hasChildNodes()) { + NodeList nList = node.getChildNodes(); + int len = nList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH) + || nodeName.equals(TAG_HEADING)) { + traverseParagraph(child); + } + + if (nodeName.equals(TAG_UNORDERED_LIST) || + nodeName.equals(TAG_ORDERED_LIST)) { + traverseList(child); + } + } + } + } + } + + + /* + * Process a text:p tag + */ + private void traverseParagraph(Node node) throws IOException, ConvertException { + String styleName = getAttribute(node, ATTRIBUTE_TEXT_STYLE_NAME); + + ParaStyle pstyle = (ParaStyle)styleCat.lookup(styleName, + PocketWordConstants.PARAGRAPH_STYLE_FAMILY, null, + ParaStyle.class); + if (pstyle != null) { + pstyle = (ParaStyle)pstyle.getResolved(); + } + + TextStyle tstyle = (TextStyle)styleCat.lookup(styleName, + PocketWordConstants.PARAGRAPH_STYLE_FAMILY, null, + TextStyle.class); + if (pstyle != null) { + tstyle = (TextStyle)tstyle.getResolved(); + } + + try { + pswDoc.addParagraph(pstyle, inList); + } + catch (Exception e) { + throw new ConvertException( + "Error adding paragraph to PocketWordDocument.\n" + + e.toString()); + } + + traverseParagraphContents(node, tstyle); + } + + + /* + * Process the contents of a paragraph. This method handles situations + * where the paragraph contains multiple children, each representing a + * differently formatted piece of text. + */ + private void traverseParagraphContents (Node node, TextStyle defTextStyle) + throws IOException, ConvertException { + // First up, get the style of this little bit + String styleName = getAttribute(node, ATTRIBUTE_TEXT_STYLE_NAME); + TextStyle tStyle = (TextStyle)styleCat.lookup(styleName, + PocketWordConstants.TEXT_STYLE_FAMILY, null, + TextStyle.class); + + if (tStyle == null) { + tStyle = defTextStyle; + } + + if (node.hasChildNodes()) { + NodeList nList = node.getChildNodes(); + int len = nList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nList.item(i); + short nodeType = child.getNodeType(); + + switch (nodeType) { + case Node.TEXT_NODE: + String s = child.getNodeValue(); + if (s.length() > 0) { + try { + pswDoc.addParagraphData(s, tStyle); + } + catch (Exception e) { + throw new ConvertException( + "Error adding data to paragraph in " + + "PocketWordDocument.\n" + e.toString()); + + } + } + break; + + case Node.ELEMENT_NODE: + if (child.getNodeName().equals(TAG_SPACE)) { + StringBuffer sb = new StringBuffer(""); + int count = 1; + + NamedNodeMap map = child.getAttributes(); + + if (map.getLength() > 0) { + Node attr = map.getNamedItem(ATTRIBUTE_SPACE_COUNT); + count = Integer.parseInt(attr.getNodeValue().trim()); + } + + for ( ; count > 0; count--) { + sb.append(" "); + } + + /* + * May want to look at style info for spaces. Could + * be important when calculating font metrics. + */ + try { + pswDoc.addParagraphData(sb.toString(), tStyle); + } + catch (Exception e) { + throw new ConvertException( + "Error adding data to paragraph in " + + "PocketWordDocument.\n" + e.toString()); + + } + } + else if (child.getNodeName().equals(TAG_TAB_STOP)) { + try { + pswDoc.addParagraphData("\t", tStyle); + } + catch (Exception e) { + throw new ConvertException( + "Error adding data to paragraph in " + + "PocketWordDocument.\n" + e.toString()); + + } + } + else if (child.getNodeName().equals(TAG_LINE_BREAK)) { + /* + * Pocket Word does not support soft line breaks. + * They are just new paragraphs. + */ + } + else if (child.getNodeName().equals(TAG_SPAN)) { + /* + * This is where the interesting ones, i.e. format + * changes occur. + */ + traverseParagraphContents (child, defTextStyle); + } + else if (child.getNodeName().equals(TAG_HYPERLINK)) { + traverseParagraphContents (child, defTextStyle); + } + else { + // Should maybe have a default in here. + } + break; + default: + // Do nothing + } + } + } + else { + /* + * If the node has no children, then it is a blank paragraph, but + * they still require an entry in the Paragraph class to make sense. + */ + pswDoc.addParagraphData("", tStyle); + } + } + + + /* + * Process a text:ordered-list or text:unordered-list tag. Pocket Word has + * no concept of a list so there is no need to differentiate between the + * two. + * + * Each item on the list contains a text:p node. + */ + private void traverseList (Node node) throws IOException, ConvertException { + inList = true; + + if (node.hasChildNodes()) { + NodeList nList = node.getChildNodes(); + int len = nList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_LIST_ITEM)) { + traverseListItem(child); + } + } + } + } + + inList = false; + } + + + /* + * Process a text:list-item node. They usually contain have a single + * text:p child but can also have sections or other lists. + * + * For this case, only paragraphs are supported. + */ + private void traverseListItem (Node node) throws IOException, ConvertException { + if (node.hasChildNodes()) { + NodeList nList = node.getChildNodes(); + int len = nList.getLength(); + + for (int i = 0; i < len; i++) { + Node child = nList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH)) { + traverseParagraph(child); + } + } + } + } + + } + + + /* + * Utility method to retrieve a Node attribute. + */ + private String getAttribute (Node node, String attribute) { + NamedNodeMap attrNodes = node.getAttributes(); + + if (attrNodes != null) { + Node attr = attrNodes.getNamedItem(attribute); + if (attr != null) { + return attr.getNodeValue(); + } + } + + return null; + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/Paragraph.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/Paragraph.java new file mode 100644 index 000000000000..c2249766b5e5 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/Paragraph.java @@ -0,0 +1,859 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.io.IOException; + +import java.util.Vector; +import java.util.Enumeration; + +import java.awt.Color; + +import org.openoffice.xmerge.util.EndianConverter; +import org.openoffice.xmerge.util.ColourConverter; +import org.openoffice.xmerge.converter.xml.ParaStyle; +import org.openoffice.xmerge.converter.xml.TextStyle; + + +/** + * Represents a paragraph data structure within a Pocket Word document. + * + * @author Mark Murnane + * @version 1.1 + */ +class Paragraph implements PocketWordConstants { + /* + * The data elements of a Paragraph. + * + * As the 'unknown' values are not calculated they are declared static. + * They are not declared final because they do have a calcuable value. + */ + private static short unknown1 = 0x23; + private short dataWords = 0; + private short textLength = 0; + private short lengthWithFormatting = 0; + private short lines = 0; + + private static final short marker = (short)0xFFFF; + private static int unknown2 = 0x22; // May be two short values + + private short specialIndentation = 0; + private short leftIndentation = 0; + private short rightIndentation = 0; + + private byte bullets = 0; + private byte alignment = 0; + + private static int unknown3 = 0; + + // Will always have at least these formatting settings in each paragraph + private short defaultFont = 2; // Courier New for the time being + private short defaultSize = 10; + + + /* + * Remaining elements assist in calculating correct values for the paragraph + * representation. + */ + + private Vector textSegments = null; + + private Vector lineDescriptors = null; + + private ParaStyle pStyle = null; + + private boolean isLastParagraph = false; + + + /* + * Private class constructor used by all constructors. Ensures the proper + * initialisation of the Vector storing the paragraph's text. + */ + private Paragraph () { + textSegments = new Vector(0, 1); + } + + + /** + * <p>Constructor for use when converting from SXW format to Pocket Word + * format.</p> + * + * @param style Paragraph style object describing the formatting style + * of this paragraph. + */ + public Paragraph (ParaStyle style) { + this(); + + lineDescriptors = new Vector(0, 1); + pStyle = style; + } + + + /** + * <p>Constructor for use when converting from Pocket Word format to SXW + * format.</p> + * + * @param data Byte array containing byte data describing this paragraph + * from the Pocket Word file. + */ + public Paragraph (byte[] data) { + this(); + + /* + * Read in all fixed data from the array + * + * unknown1 appears at data[0] and data[1] + */ + dataWords = EndianConverter.readShort(new byte[] { data[2], data[3] } ); + textLength = EndianConverter.readShort(new byte[] { data[4], data [5] } ); + lengthWithFormatting = EndianConverter.readShort( + new byte[] { data[6], data[7] } ); + lines = EndianConverter.readShort(new byte[] { data[8], data [9] } ); + + /* + * The marker appears at data[10] and data[11]. + * + * The value of unknown2 is at data[12], data[13], data[14] and data[15]. + */ + + specialIndentation = EndianConverter.readShort(new byte[] { data[16], data[17] } ); + leftIndentation = EndianConverter.readShort(new byte[] { data[18], data [19] } ); + rightIndentation = EndianConverter.readShort(new byte[] { data[20], data [21] } ); + + bullets = data[22]; + alignment = data[23]; + + // The value of unknown3 is at data[24], data[25], data[26] and data[27]. + + /* + * The actual paragraph data is in the remainder of the byte sequence. + * + * Only the actual text seqence with the embedded formatting tags is + * relevant to the conversion from Pocket Word to SXW format. + */ + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + bos.write(data, 28, lengthWithFormatting); + parseText(bos.toByteArray()); + } + + + /* + * Processes the text portion of the raw paragraph data from the Pocket Word + * file. This data also includes formatting settings for the text in the + * paragraph. + * + * Formatting changes appear like XML/HTML tags. Formatted blocks are + * preceded by a sequence of bytes switching on a formatting change and + * followed by a sequence switching off that formatting change. + */ + private void parseText (byte[] data) { + + int totalLength = data.length; + + StringBuffer sb = new StringBuffer(""); + + // Setup text style information + int mask = TextStyle.BOLD | TextStyle.ITALIC | TextStyle.UNDERLINE + | TextStyle.STRIKETHRU; + + + String fontName = null; + int fontSize = 0; + Color textColour = null; + Color backColour = null; + int modifiers = 0; + + TextStyle ts = null; + + int attrsSet = 0; // If this is 0, we have no extra style + boolean inSequence = false; + boolean sawText = false; + + String s = new String(); // For debugging + + // Start from the very beginning + for (int i = 0; i < totalLength; i++) { + // Will encounter at least two codes first + if ((byte)(data[i] & 0xF0) == FORMATTING_TAG) { + if (sawText) { + // Style change so dump previous segment and style info + addTextSegment(sb.toString(), ts); + sb = new StringBuffer(""); + sawText = false; + } + + switch (data[i]) { + case FONT_TAG: + int index = EndianConverter.readShort( + new byte[] { data[i + 1], data[i + 2] } ); + + /* + * Standard font. + * + * Should really be one, but as the only supported font + * currently is Courier New, want to leave it at Courier + * New for round trip conversions. + * + * Also need to account for the fact that Tahoma is the + * correct standard font. + */ + if (fontName == null || fontName.equals("2")) { + if (index != 2 && index != 1) { + fontName = String.valueOf(index); + attrsSet++; + } + } + else { + // Font is set, but not the default + if (index == 2 || index == 1) { + fontName = "2"; + attrsSet--; + } + else { + fontName = String.valueOf(index); + } + } + i += 2; + break; + + + case FONT_SIZE_TAG: + int size = EndianConverter.readShort( + new byte[] { data[i + 1], data[i + 2] } ); + + if (size == 0) { + // Flags the end of the last paragraph + isLastParagraph = true; + i += 2; + break; + } + + // Standard size + if (fontSize == 0 || fontSize == 10) { + if (size != 10) { + fontSize = size; + attrsSet++; + } + } + else { + // Font size is set, but not to standard + if (size == 10) { + fontSize = 10; + attrsSet--; + } + else { + fontSize = size; + } + } + i += 2; + break; + + + case COLOUR_TAG: + if (data[i + 1] != 0) { + ColourConverter cc = new ColourConverter(); + textColour = cc.convertToRGB( + EndianConverter.readShort(new byte[] { data[i + 1], + data[i + 2] } )); + attrsSet++; + } + else { + textColour = null; + attrsSet--; + } + i += 2; + break; + + + case FONT_WEIGHT_TAG: + if (data[i + 1] == FONT_WEIGHT_BOLD + || data[i + 1] == FONT_WEIGHT_THICK) { + modifiers |= TextStyle.BOLD; + attrsSet++; + } + else { + // Its a bit field so subtracting should work okay. + modifiers ^= TextStyle.BOLD; + attrsSet--; + } + i += 2; + break; + + + case ITALIC_TAG: + if (data[i + 1] == (byte)0x01) { + modifiers |= TextStyle.ITALIC; + attrsSet++; + } + else { + modifiers ^= TextStyle.ITALIC; + attrsSet--; + } + i++; + break; + + + case UNDERLINE_TAG: + if (data[i + 1] == (byte)0x01) { + modifiers |= TextStyle.UNDERLINE; + attrsSet++; + } + else { + modifiers ^= TextStyle.UNDERLINE; + attrsSet--; + } + i++; + break; + + + case STRIKETHROUGH_TAG: + if (data[i + 1] == (byte)0x01) { + modifiers |= TextStyle.STRIKETHRU; + attrsSet++; + } + else { + modifiers ^= TextStyle.STRIKETHRU; + attrsSet--; + } + i++; + break; + + case HIGHLIGHT_TAG: + /* + * Highlighting is treated by OpenOffice as a + * background colour. + */ + if (data[i + 1] == (byte)0x01) { + backColour = Color.yellow; + attrsSet++; + } + else { + backColour = null; + attrsSet--; + } + i++; + break; + } + + inSequence = true; + continue; + } + + if (inSequence) { + // Style information has been changed. Create new style here + + inSequence = false; + if (attrsSet > 0) { + ts = new TextStyle(null, TEXT_STYLE_FAMILY, DEFAULT_STYLE, + mask, modifiers, fontSize, fontName, null); + ts.setColors(textColour, backColour); + } + else { + ts = null; + } + } + + /* + * C4 xx seems to indicate a control code. C4 00 indicates the end + * of a paragraph; C4 04 indicates a tab space. Only these two + * have been seen so far. + */ + if (data[i] == (byte)0xC4) { + /* + * Redundant nodes are sometimes added to the last paragraph + * because a new sequence is being processed when the flag is + * set. + * + * To avoid this, do nothing with the last paragraph unless no + * text has been added for it already. In that case, add the + * empty text segment being process to ensure that all + * paragraphs have at least one text segment. + */ + if (data[i + 1] == (byte)0x00) { + if (isLastParagraph && textSegments.size() > 0) { + return; + } + addTextSegment(sb.toString(), ts); + return; + } + sb.append("\t"); + sawText = true; + i++; + continue; + } + + sb.append((char)data[i]); + sawText = true; + s = sb.toString(); + } + } + + + /** + * <p>Adds details of a new text block to the <code>Paragraph</code> object. + * </p> + * + * @param text The text of the new block. + * @param style Text style object describing the formatting attached + * to this block of text. + */ + public void addTextSegment(String text, TextStyle style) { + textLength += text.length(); + textSegments.add(new ParagraphTextSegment(text, style)); + } + + + /** + * <p>This method alters the state of the <code>Paragraph</code> object to + * indicate whether or not it is the final paragraph in the document.</p> + * + * <p>It is used during conversion from SXW format to Pocket Word format. + * In Pocket Word files, the last paragraph finishes with a different byte + * sequence to other paragraphs.</p> + * + * @param isLast true if the Paragraph is the last in the document, + * false otherwise. + */ + public void setLastParagraph(boolean isLast) { + isLastParagraph = isLast; + } + + + /** + * <p>Complementary method to {@link #setLastParagraph(boolean) + * setLastParagraph}. Returns the terminal status of this + * <code>Paragraph</code> within the Pocket Word document.</p> + * + * @return true if the Paragraph is the last in the document; false otherwise. + */ + public boolean getLastParagraph () { + return isLastParagraph; + } + + + /** + * <p>This method returns the Pocket Word representation of this + * <code>Paragraph</code> in Little Endian byte order.</p> + * + * <p>Used when converting from SXW format to Pocket Word format.</p> + * + * @return <code>byte</code> array containing the formatted representation + * of this Paragraph. + */ + public byte[] getParagraphData() { + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + + postProcessText(); + + /* + * Need information about the paragraph segments in two places + * so calculate them first. + * + * The stream contains the text wrapped in any formatting sequences that + * are necessary. + */ + ByteArrayOutputStream segs = new ByteArrayOutputStream(); + + try { + for (int i = 0; i < textSegments.size(); i++) { + ParagraphTextSegment pts = (ParagraphTextSegment)textSegments.elementAt(i); + segs.write(pts.getData()); + } + } + catch (IOException ioe) { + // Should never happen in a memory based stream + } + + /* + * Number of data words for this paragraph descriptor: + * + * 26 is the number of bytes prior to the start of the segment. + * 3 comes from the C4 00 00 termintating sequence. + */ + dataWords = (short)(26 + segs.size() + 3 + 4); + if (isLastParagraph) { + dataWords += 6; + } + if (dataWords % 4 != 0) { + dataWords += (4 - (dataWords % 4)); + } + dataWords /= 4; + + /* + * The 8 bytes are made up of E6 ?0 00 and E5 ?0 00 at the start of the + * text along with the C4 00 that terminates it. + * + * In the event that the paragraph is the last one E6 00 00 is also + * present at the end of the text. Also, as we currently use a font + * other than the first in the index (Tahoma) E5 01 00 is also present. + * + * Make sure this is accurate when font specifications change + */ + lengthWithFormatting = (short)(segs.size() + (isLastParagraph ? 14 : 8)); + + try { + bos.write(EndianConverter.writeShort(unknown1)); + bos.write(EndianConverter.writeShort(dataWords)); + bos.write(EndianConverter.writeShort((short)(textLength + 1))); + bos.write(EndianConverter.writeShort(lengthWithFormatting)); + bos.write(EndianConverter.writeShort(lines)); + + bos.write(EndianConverter.writeShort(marker)); + bos.write(EndianConverter.writeInt(unknown2)); + + bos.write(EndianConverter.writeShort(specialIndentation)); + bos.write(EndianConverter.writeShort(leftIndentation)); + bos.write(EndianConverter.writeShort(rightIndentation)); + + bos.write(bullets); + + if (pStyle != null && pStyle.isAttributeSet(ParaStyle.TEXT_ALIGN)) { + switch (pStyle.getAttribute(ParaStyle.TEXT_ALIGN)) { + + case ParaStyle.ALIGN_RIGHT: + bos.write(0x01); + break; + + case ParaStyle.ALIGN_CENTER: + bos.write(0x02); + break; + + default: + bos.write(0x00); // Left align in all other circumstances + break; + } + } + else { + bos.write(0x00); + } + + bos.write(EndianConverter.writeInt(unknown3)); + + + /* + * Write out font and size. + * + * If font support is added then this should change as the information + * will have to be calculated from a Font table. + */ + bos.write(FONT_TAG); + bos.write(EndianConverter.writeShort(defaultFont)); + bos.write(FONT_SIZE_TAG); + bos.write(EndianConverter.writeShort(defaultSize)); + + // Write out the text segments + bos.write(segs.toByteArray()); + + /* + * If this is the last paragraph in the document then we need to make + * sure that the paragraph text is terminated correctly with an E6 00 00 + * before the C4 00 00. + */ + if (isLastParagraph) { + if (defaultFont != 1) { + // Must always go back to the first font. + bos.write(FONT_TAG); + bos.write(EndianConverter.writeShort((short)0x01)); + } + bos.write(FONT_SIZE_TAG); + bos.write(EndianConverter.writeShort((short)0x00)); + } + + bos.write(new byte[] { (byte)0xC4, 0x00, 0x00 } ); + + int padding = 0; + if (bos.size() % 4 != 0) { + padding = 4 - (bos.size() % 4); + } + for (int i = 0; i < padding; i++) { + bos.write(0x00); + } + + // Third byte should match first byte after 0xFF 0xFF + bos.write(new byte[] { 0x42, 0x00, 0x22, 0x00} ); + + /* + * Meaning of last two bytes seems to be the number of words describing + * lines. This is calculated at 10 bytes per descriptor. + * + * May have two extra padding bytes that need to be accounted for too + * The division below may lose 2 bytes (integer result). + */ + int wordsRemaining = (lineDescriptors.size() * 10) / 4; + if ((lineDescriptors.size() * 10) % 4 != 0) { + wordsRemaining++; + } + bos.write(EndianConverter.writeShort((short)wordsRemaining)); + + + // Now write out the line descriptors + for (int i = 0; i < lineDescriptors.size(); i++) { + LineDescriptor ld = (LineDescriptor)lineDescriptors.elementAt(i); + + bos.write(ld.getDescriptorInfo()); + } + + + if (!isLastParagraph) { + /* + * There may be a need to pad this. Will be writing at + * either start of 4 byte block or 2 bytes into it. + */ + if (bos.size() % 4 != 2) { + bos.write(EndianConverter.writeShort((short)0)); + } + bos.write(EndianConverter.writeShort((short)0x41)); + } + } + catch (IOException ioe) { + // Should never occur for a memory based stream + } + + return bos.toByteArray(); + } + + + /* + * This method handles the calculation of correct values for line lengths + * in each individual descriptor and the number of lines in the document. + * + * TODO: Update to take account of different font metrics. + */ + private void postProcessText() { + /* + * The post-processing ... + * + * For each line, we need to add a line descriptor and increment + * the number of lines in the paragraph data structure. + * + * To do this, make sure that no sequence goes over the given screen + * width unless the last char is a whitespace character. + */ + + // In courier, can have no more than 29 chars per line + + int chunkStart = 0; + StringBuffer sb = new StringBuffer(""); + + // Line Descriptor info should be eliminated each time + lineDescriptors = new Vector(1, 1); + lines = 0; + + for (int i = 0; i < textSegments.size(); i++) { + ParagraphTextSegment pts = (ParagraphTextSegment)textSegments.elementAt(i); + sb.append(pts.getText()); + } + + if (sb.length() == 0) { + lines = 1; + lineDescriptors.add(new LineDescriptor((short)1, (short)0)); + return; + } + + while (chunkStart < sb.length()) { + String text = ""; + + try { + text = sb.substring(chunkStart, chunkStart + 30); + } + catch (StringIndexOutOfBoundsException sioobe) { + // We have less than one line left so just add it + text = sb.substring(chunkStart); + lineDescriptors.add(new LineDescriptor((short)(text.length() + 1), (short)(text.length() * 36))); + chunkStart += text.length(); + lines++; + continue; + } + + int lastWhitespace = -1; + + for (int i = 29; i >= 0; i--) { + if (Character.isWhitespace(text.charAt(i))) { + lastWhitespace = i; + break; + } + } + + if (lastWhitespace != -1) { + // The line can be split + lineDescriptors.add(new LineDescriptor((short)(lastWhitespace + 1), (short)(lastWhitespace * 36))); + chunkStart += lastWhitespace + 1; + lines++; + } + else { + // The line is completely occupied by a single word + lineDescriptors.add(new LineDescriptor((short)29, (short)(29 * 36))); + chunkStart += 29; + lines++; + } + } + } + + + /** + * <p>Returns the number of lines in the <code>Paragraph</code>.</p> + * + * @return The number of lines in the document. + */ + public short getLines() { + postProcessText(); + + return lines; + } + + + /** + * <p>Toggles the flag indicating that the <code>Paragraph</code> is a + * bulleted paragraph.</p> + * + * @param isBulleted true to enable bulleting for this paragraph, false + * otherwise. + */ + public void setBullets(boolean isBulleted) { + if (isBulleted) { + bullets = (byte)0xFF; + } + else { + bullets = 0; + } + } + + /** + * <p>Returns the bulleting status of the <code>Paragraph</code>.</p> + * + * @return true if the paragraph is bulleted, false otherwise. + */ + public boolean isBulleted() { + if (bullets != 0) { + return true; + } + return false; + } + + + /** + * <p>Returns the number of text characters in the <code>Paragraph</code>, + * excluding formatting.</p> + * + * @return The length of the paragraph. + */ + public int getTextLength () { + return textLength; + } + + + /** + * <p>Returns an <code>Enumeration</code> over the individual text segments + * of the <code>Paragraph</code>.</p> + * + * @return An <code>Enumeration</code> of the text segments. + */ + public Enumeration getSegmentsEnumerator () { + return textSegments.elements(); + } + + + /** + * <p>Returns a paragraph style object that describes any of the paragraph + * level formatting used by this <code>Paragraph</code>.</p> + * + * @return Paragraph style object describing the <code>Paragraph</code>. + */ + public ParaStyle makeStyle() { + int attrs[] = new int[] { ParaStyle.MARGIN_LEFT, ParaStyle.MARGIN_RIGHT, + ParaStyle.TEXT_ALIGN }; + String values[] = new String[attrs.length]; + + /* + * Not interested in left or right indents just yet. Don't know + * how to calculate them. + */ + + switch (alignment) { + case 2: + values[2] = "center"; + break; + + case 1: + values[2] = "right"; + break; + + case 0: + default: + values[2] = "left"; + return null; // Not interested if its the default. + } + + return new ParaStyle(null, PARAGRAPH_STYLE_FAMILY, null, attrs, + values, null); + } + + + /* + * Class describing the data structures which appear following the text + * of a Paragraph. For each line on screen that the Paragraph uses, a + * LineDescriptor details how many characters are on the line and how much + * screen space they occupy. + * + * The screen space and character breaks are calculated during post-processing + * of the paragraph. See postProcessText(). + * + * The unit of measurement used for screen space is currently unknown. + */ + private class LineDescriptor { + private short characters = 0; + private int filler = 0; + private short screen_space = 0; + private short marker = 0; + + private LineDescriptor(short chars, short space) { + characters = chars; + screen_space = space; + marker = (short)0x040C; // Not a constant. Depends on font used. + } + + + private byte[] getDescriptorInfo(){ + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + + try { + bos.write(EndianConverter.writeShort(characters)); + bos.write(EndianConverter.writeInt(filler)); + bos.write(EndianConverter.writeShort(screen_space)); + bos.write(EndianConverter.writeShort(marker)); + } + catch (IOException ioe) { + // Should never happen in a memory based stream. + } + + return bos.toByteArray(); + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ParagraphTextSegment.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ParagraphTextSegment.java new file mode 100644 index 000000000000..442cbf2f53dc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/ParagraphTextSegment.java @@ -0,0 +1,205 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.openoffice.xmerge.converter.xml.TextStyle; + +import org.openoffice.xmerge.util.EndianConverter; + +import org.openoffice.xmerge.util.ColourConverter; + +import java.io.ByteArrayOutputStream; +import java.io.IOException; + +import java.awt.Color; + +/** + * This class represents a portion of text with a particular formatting style. + * The style may differ from the default style of the paragraph of which it + * is part. + * + * @author Mark Murnane + * @version 1.1 + */ +class ParagraphTextSegment implements PocketWordConstants { + + private String pText; + private TextStyle pStyle; + + + /** + * <p>Initialise a new <code>ParagraphTextSegment</p>. + * <p>Both parameters may be <code>null</code>.</p> + * + * @param data The text of this segment. + * @param style The style describing this segment. + */ + public ParagraphTextSegment (String data, TextStyle style) { + pText = data; + pStyle = style; + } + + /** + * <p>Sets the text for this segment.</p> + * + * @param data The text of this segment. + */ + public void setText (String data) { + pText = data; + } + + /** + * <p>Gets the text for this segment.</p> + * + * @return The text of this segment. + */ + public String getText () { + return pText; + } + + + /** + * <p>Sets the style for this segment.</p> + * + * @param data The style describing this segment. + */ + public void setStyle (TextStyle style) { + pStyle = style; + } + + + /** + * <p>Gets the style for this segment.</p> + * + * @return The style describing this segment. + */ + public TextStyle getStyle () { + return pStyle; + } + + + /** + * <p>Returns the string data for this text segment wrapped with the + * appropriate byte codes for the formatting settings used.</p> + * + * @return <code>byte</code> array containing formatted text in Pocket Word + * format. + */ + public byte[] getData () { + ByteArrayOutputStream data = new ByteArrayOutputStream(); + + boolean colourSet = false; + boolean boldSet = false; + boolean italicSet = false; + boolean underlineSet = false; + boolean strikeSet = false; + boolean highlightSet = false; + + // TODO: Font changes need to be worked out here + + try { + if (pStyle != null) { + if (pStyle.getFontColor() != null) { + ColourConverter cc = new ColourConverter(); + short colourCode = cc.convertFromRGB(pStyle.getFontColor()); + if (colourCode != 0) { // not black + data.write(COLOUR_TAG); + data.write(EndianConverter.writeShort(colourCode)); + colourSet = true; + } + } + if (pStyle.isSet(TextStyle.BOLD) && pStyle.getAttribute(TextStyle.BOLD)) { + data.write(new byte[] { FONT_WEIGHT_TAG, FONT_WEIGHT_BOLD, 0x00 } ); + boldSet = true; + } + if (pStyle.isSet(TextStyle.ITALIC) && pStyle.getAttribute(TextStyle.ITALIC)) { + data.write(new byte[] { ITALIC_TAG, 0x01 } ); + italicSet = true; + } + if (pStyle.isSet(TextStyle.UNDERLINE) && pStyle.getAttribute(TextStyle.UNDERLINE)) { + data.write(new byte[] { UNDERLINE_TAG, 0x01 } ); + underlineSet = true; + } + if (pStyle.isSet(TextStyle.STRIKETHRU) && pStyle.getAttribute(TextStyle.STRIKETHRU)) { + data.write(new byte[] { STRIKETHROUGH_TAG, 0x01 } ); + strikeSet = true; + } + if (pStyle.getBackgroundColor() != null) { + data.write(new byte[] { HIGHLIGHT_TAG, 0x01 } ); + highlightSet = true; + } + } + + + // Now write out the data + if (!pText.equals("\t")) { + data.write(pText.getBytes()); + } + else { + /* + * Tabs are a special case. They are represented by Pocket Word + * as the LE sequence 0xC4 0x04. + */ + data.write(new byte[] { (byte)0xC4, 0x04 } ); + } + + + // Now close out any of the settings changes + if (colourSet) { + /* + * Colours may change without changing back to black, but + * without knowing what the previous colour was, the only + * way to ensure correct conversion is to restore to black and + * let the next segment change the colour again. + */ + data.write(new byte[] { COLOUR_TAG, 0x00, 0x00 } ); + } + if (boldSet) { + data.write(new byte[] { FONT_WEIGHT_TAG, FONT_WEIGHT_NORMAL, 0x00 } ); + } + if (italicSet) { + data.write(new byte[] { ITALIC_TAG, 0x00 } ); + } + if (underlineSet) { + data.write(new byte[] { UNDERLINE_TAG, 0x00 } ); + } + if (strikeSet) { + data.write(new byte[] { STRIKETHROUGH_TAG, 0x00 } ); + } + if (highlightSet) { + data.write(new byte[] { HIGHLIGHT_TAG, 0x00 } ); + } + } + catch (IOException ioe) { + // Should never occur in a memory based stream + } + + return data.toByteArray(); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PluginFactoryImpl.java new file mode 100644 index 000000000000..d02c9eeddf53 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PluginFactoryImpl.java @@ -0,0 +1,165 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + + +import java.io.InputStream; +import java.io.IOException; + +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.DocumentMergerFactory; +import org.openoffice.xmerge.ConverterCapabilities; + +import org.openoffice.xmerge.util.registry.ConverterInfo; + +import org.openoffice.xmerge.converter.xml.sxw.SxwPluginFactory; + + +/** + * Factory class used to create converters to/from the Pocket Word format. + * + * @author Mark Murnane + * @version 1.1 + */ +public final class PluginFactoryImpl extends SxwPluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory, + DocumentMergerFactory{ + + /** + * <p>Constructor that caches the <code>ConvertInfo</code> that + * corresponds to the registry information for this plug-in.</p> + * + * @param ci <code>ConvertInfo</code> object. + */ + public PluginFactoryImpl (ConverterInfo ci) { + super(ci); + } + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + /** + * <p>The <code>DocumentSerializer</code> is used to convert + * from the OpenOffice Writer <code>Document</code> format + * to the Pocket Word <code>Document</code> format.</p> + * + * <p>The <code>ConvertData</code> object is passed along to the + * created <code>DocumentSerializer</code> via its constructor. + * The <code>ConvertData</code> is read and converted when the + * the <code>DocumentSerializer</code> object's + * <code>serialize</code> method is called.</p> + * + * @param doc <code>Document</code> object that the created + * <code>DocumentSerializer</code> object uses + * as input. + * + * @return A <code>DocumentSerializer</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + return new DocumentSerializerImpl(doc); + } + + + /** + * The <code>DocumentDeserializer</code> is used to convert + * from the Pocket Word <code>Document</code> format to + * the OpenOffice Writer <code>Document</code> format.</p> + * + * The <code>ConvertData</code> object is passed along to the + * created <code>DocumentDeserializer</code> via its constructor. + * The <code>ConvertData</code> is read and converted when the + * the <code>DocumentDeserializer</code> object's + * <code>deserialize</code> method is called. + * </p> + * + * @param cd <code>ConvertData</code> object that the created + * <code>DocumentDeserializer</code> object uses as + * input. + * + * @return A <code>DocumentDeserializer</code> object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + return new DocumentDeserializerImpl(cd); + } + + + /** + * <p>Create a <code>Document</code> object that corresponds to + * the Pocket Word data passed in via the <code>InputStream</code> + * object. + * + * <p>This method will read from the given <code>InputStream</code> + * object. The returned <code>Document</code> object will contain + * the necessary data for the other objects created by the + * <code>PluginFactoryImpl</code> to process, like the + * <code>DocumentSerializerImpl</code> object and a + * <code>DocumentMerger</code> object.</p> + * + * @param name The <code>Document</code> name. + * @param is <code>InputStream</code> object corresponding + * to the <code>Document</code>. + * + * @return A <code>Document</code> object representing the + * Pocket Word format. + * + * @throws IOException If any I/O error occurs. + */ + + public Document createDeviceDocument(String name, InputStream is) + throws IOException { + PocketWordDocument pwd = new PocketWordDocument(name); + pwd.read(is); + return pwd; + } + + /** + * Returns an instance of <code>DocumentMergerImpl</code>, + * which is an implementation of the <code>DocumentMerger</code> + * interface. + * + * @param doc <code>Document</code> to merge. + * + * @return A DocumentMergerImpl object. + */ + public DocumentMerger createDocumentMerger(Document doc) { + ConverterCapabilities cc = converterCap; + DocumentMergerImpl merger = new DocumentMergerImpl(doc, cc); + return merger; + + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordConstants.java new file mode 100644 index 000000000000..de67eeec31a7 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordConstants.java @@ -0,0 +1,95 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + + +/** + * Interface defining constants for Pocket Word attributes. + * + * @author Mark Murnane + * @version 1.1 + */ +public interface PocketWordConstants { + /** File extension for Pocket Word files. */ + public static final String FILE_EXTENSION = ".psw"; + + /** Name of the default style. */ + public static final String DEFAULT_STYLE = "Standard"; + + /** Family name for Paragraph styles. */ + public static final String PARAGRAPH_STYLE_FAMILY = "paragraph"; + + /** Family name for Text styles. */ + public static final String TEXT_STYLE_FAMILY = "text"; + + + /** + * Generic Pocket Word formatting code. + * + * Formatting codes are 0xEz, where z indicates the specific format code. + */ + public static final byte FORMATTING_TAG = (byte)0xE0; + + /** Font specification tag. The two bytes following inidicate which font. */ + public static final byte FONT_TAG = (byte)0xE5; + + /** Font size tag. The two bytes following specify font size in points. */ + public static final byte FONT_SIZE_TAG = (byte)0xE6; + + /** Colour tag. Two bytes following index a 4-bit colour table. */ + public static final byte COLOUR_TAG = (byte)0xE7; + + /** Font weight tag. Two bytes following indicate weighting of font. */ + public static final byte FONT_WEIGHT_TAG = (byte)0xE8; + + /** Normal font weight value. */ + public static final byte FONT_WEIGHT_NORMAL = (byte)0x04; + + /** Fine font weight value. */ + public static final byte FONT_WEIGHT_FINE = (byte)0x01; + + /** Bold font weight value. */ + public static final byte FONT_WEIGHT_BOLD = (byte)0x07; + + /** Thick font weight value. */ + public static final byte FONT_WEIGHT_THICK = (byte)0x09; + + /** Italic tag. Single byte following indicates whether italic is on. */ + public static final byte ITALIC_TAG = (byte)0xE9; + + /** Underline tag. Single byte following indicates whether underline is on. */ + public static final byte UNDERLINE_TAG = (byte)0xEA; + + /** Strikethrough tag. Single byte following indicates whether strikethrough is on. */ + public static final byte STRIKETHROUGH_TAG = (byte)0XEB; + + /** Highlighting tag. Single byte following indicates whether highlighting is on. */ + public static final byte HIGHLIGHT_TAG = (byte)0xEC; + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordDocument.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordDocument.java new file mode 100644 index 000000000000..9026d8866113 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/PocketWordDocument.java @@ -0,0 +1,408 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + + +package org.openoffice.xmerge.converter.xml.sxw.pocketword; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.converter.xml.ParaStyle; +import org.openoffice.xmerge.converter.xml.TextStyle; + +import java.awt.Font; + +import java.io.InputStream; +import java.io.IOException; +import java.io.OutputStream; +import java.io.ByteArrayInputStream; +import java.io.ByteArrayOutputStream; +import java.io.DataOutputStream; + +import java.util.Enumeration; +import java.util.Vector; + + +/** + * <p>Class representing a Pocket Word Document.</p> + * + * <p><code>PocketWordDocument</code> is used to create new Pocket Word documents + * and to read existing data to allow for conversion to OpenOffice Writer + * format.</p> + * + * @author Mark Murnane + * @version 1.1 + */ +public class PocketWordDocument implements Document, PocketWordConstants { + private String docName; + + private byte[] preamble; + private Vector fonts; + private DocumentDescriptor descriptor; + private Vector paragraphs; + + private ParaStyle pStyle; + private Paragraph currentPara; + + /* + * The trailer currently appears to be constant, but if its found to + * have a variable component, then this initialisation should be moved + * to an initTrailer() method. + * + * Padding is sometimes needed before the trailer to ensure the file + * ends on a 4-byte boundary, but this is handled in write(). + */ + private static final byte[] trailer = new byte[] { (byte)0x82, 0x00, + 0x09, 0x00, + 0x03, 0x00, + (byte)0x82, 0x00, + 0x00, 0x00, + 0x00, 0x00, + 0x00, 0x00, + 0x00, 0x00, + 0x00, 0x00 }; + + + /** + * <p>Constructs a new Pocket Word Document.</p> + * + * <p>This new document does notcontain any information. Document data must + * either be added using appropriate methods, or an existing file can be + * {@link #read(InputStream) read} from an <code>InputStream</code>.</p> + * + * @param name The name of the <code>PocketWordDocument</code>. + */ + public PocketWordDocument(String name) { + + docName = trimDocumentName(name); + + preamble = new byte[52]; + fonts = new Vector(0, 1); + descriptor = new DocumentDescriptor(); + paragraphs = new Vector(0, 1); + } + + + /** + * <p>This method reads <code>byte</code> data from the InputStream and + * extracts font and paragraph data from the file.</p> + * + * @param is InputStream containing a Pocket Word data file. + * + * @throws IOException In case of any I/O errors. + */ + public void read(InputStream docData) throws IOException { + + if (docData == null) { + throw new IOException ("No input stream to convert"); + } + + // The preamble may become important for font declarations. + int readValue = docData.read(preamble); + // #i33702# check for an empty InputStream. + if(readValue == -1) { + System.err.println("Error:invalid input stream"); + return; + } + + byte[] font = new byte[80]; + int numfonts = 0; + do { + docData.read(font); + + String name = new String(font, 0, 64, "UTF-16LE"); + fonts.add(name.trim()); + + } while (!(font[76] == 5 && font[77] == 0 + && font[78] == 1 && font[79] == 0)); + + /* + * TODO: The document descriptor data that follows the fonts ends with + * a variable section containing data for each of the paragraphs. + * It may be possible to use this information to calculate staring + * positions for each paragraph rather than iterating through the + * entire byte stream. + */ + + int value; + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + while ((value = docData.read()) != -1) { + bos.write(value); + } + + + byte[] contentData = bos.toByteArray(); + int start = 0, end = 0; + boolean sawMarker = false; + + for (int i = 0; i < contentData.length; i += 4) { + if (contentData[i + 2] == (byte)0xFF + && contentData[i + 3] == (byte)0xFF && !sawMarker) { + start = i - 8; + sawMarker = true; + continue; + } + + if (contentData[i + 2] == (byte)0xFF + && contentData[i + 3] == (byte)0xFF && sawMarker) { + end = i - 8; + ByteArrayOutputStream paragraph = new ByteArrayOutputStream(); + paragraph.write(contentData, start, end - start); + paragraphs.add(new Paragraph(paragraph.toByteArray())); + + // Reset the markers + sawMarker = false; + i -= 4; // Skip back + } + + } + + /* + * Special case, the last paragraph + * If we got here, and the marker is set then we saw the start of the + * last paragraph, but no following paragraph + */ + ByteArrayOutputStream paragraph = new ByteArrayOutputStream(); + if (contentData[contentData.length - 19] == 0) { + paragraph.write(contentData, start, contentData.length - start - 20); + } + else { + paragraph.write(contentData, start, contentData.length - start - 18); + } + paragraphs.add(new Paragraph(paragraph.toByteArray())); + } + + + /* + * Utility method to make sure the document name is stripped of any file + * extensions before use. + */ + private String trimDocumentName(String name) { + String temp = name.toLowerCase(); + + if (temp.endsWith(FILE_EXTENSION)) { + // strip the extension + int nlen = name.length(); + int endIndex = nlen - FILE_EXTENSION.length(); + name = name.substring(0,endIndex); + } + + return name; + } + + + /** + * <p>Method to provide access to all of the <code>Paragraph</code> objects + * in the <code>Document</code>.</p> + * + * @return <code>Enumeration</code> over the paragraphs in the document. + */ + public Enumeration getParagraphEnumeration() { + return paragraphs.elements(); + } + + + /** + * <p>Returns the <code>Document</code> name with no file extension.</p> + * + * @return The <code>Document</code> name with no file extension. + */ + public String getName() { + return docName; + } + + + /** + * <p>Returns the <code>Document</code> name with file extension.</p> + * + * @return The <code>Document</code> name with file extension. + */ + public String getFileName() { + return new String(docName + FILE_EXTENSION); + } + + + /** + * <p>Writes out the <code>Document</code> content to the specified + * <code>OutputStream</code>.</p> + * + * <p>This method may not be thread-safe. + * Implementations may or may not synchronize this + * method. User code (i.e. caller) must make sure that + * calls to this method are thread-safe.</p> + * + * @param os <code>OutputStream</code> to write out the + * <code>Document</code> content. + * + * @throws IOException If any I/O error occurs. + */ + public void write(OutputStream os) throws IOException { + DataOutputStream dos = new DataOutputStream(os); + + initPreamble(); + dos.write(preamble); + + loadFonts(); + for (int i = 0; i < fonts.size(); i++ ) { + ByteArrayOutputStream fontData = (ByteArrayOutputStream)fonts.elementAt(i); + dos.write(fontData.toByteArray()); + } + + + for (int i = 0; i < paragraphs.size(); i++) { + Paragraph para = (Paragraph)paragraphs.elementAt(i); + descriptor.addParagraph((short)para.getTextLength(), para.getLines()); + } + dos.write(descriptor.getDescriptor()); + + for (int i = 0; i < paragraphs.size(); i++ ) { + Paragraph para = (Paragraph)paragraphs.elementAt(i); + + // Last paragraph has some extra data + if (i + 1 == paragraphs.size()) { + para.setLastParagraph(true); + } + dos.write(para.getParagraphData()); + } + + + /* + * Before we write out the trailer, we need to make sure that it will + * lead to the file ending on a 4 byte boundary. + */ + if (dos.size() % 4 == 0) { + dos.write((byte)0x00); + dos.write((byte)0x00); + } + + dos.write(trailer); + + dos.flush(); + dos.close(); + } + + + /** + * <p>This method adds a new paragraph element to the document. No string + * data is added to the paragraph.</p> + * + * <p><b>N.B.</b> The newly added paragraph becomes the current paragraph and + * is used as the target for all subsequent calls to addParagraphData().</p> + * + * @param style Paragraph Style object describing the formatting for + * the new paragraph. Can be null. + * @param listElement true if this paragraph is to be bulleted; + * false otherwise. + */ + public void addParagraph(ParaStyle style, boolean listElement) { + /* For the moment, only support basic text entry in a single paragraph */ + Paragraph para = new Paragraph(style); + + paragraphs.add(para); + + pStyle = style; + currentPara = para; + + if (listElement) { + para.setBullets(true); + } + } + + + /** + * <p>This method adds text to the current paragraph.</p> + * + * <p>If no paragraphs exist within the document, it creates one.</p> + * + * @param data The string data for this segment. + * @param style Text Style object describing the formatting of this + * segment. Can be null. + */ + public void addParagraphData(String data, TextStyle style) { + if (currentPara == null) { + addParagraph(null, false); + } + currentPara.addTextSegment(data, style); + } + + + /* + * Preamble is the portion before font specification which never + * seems to change from one file, or one saved version, to the next. + * + * Bytes 18h and 19h seem to contain the number of fonts and should + * be modified when all of the fonts have been specified. + * These bytes are the first two on the fourth line below. + */ + private void initPreamble() { + preamble = new byte[] { 0x7B, 0x5C, 0x70, 0x77, 0x69, 0x15, 0x00, 0x00, + 0x01, 0x01, 0x06, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x02, 0x00, 0x2C, 0x00, 0x01, 0x00, 0x0A, 0x00, // Bytes 3-4 Font?? + 0x02, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, // Bytes 1-2 # Fonts + 0x00, 0x00, 0x00, 0x00, 0x01, 0x00, 0x01, 0x00, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00 }; + } + + + /* + * This method writes the minimum font data that is used by the converter. + * Currently, all documents convert to 10 point Courier New. Tahoma is + * always mentioned in Pocket Word files, however, even if it is not used. + * + * TODO: Rewrite to allow for multiple fonts once font support issues + * have been resolved. + */ + private void loadFonts() { + ByteArrayOutputStream fontData = new ByteArrayOutputStream(); + + try { + fontData.write(new String("Tahoma").getBytes("UTF-16LE")); + fontData.write(new byte[52]); // Rest of font name? + fontData.write(new byte[] { 0x02, 0x00, 0x01, 0x00 } ); + fontData.write(new byte[] { 0x00, 0x00, 0x01, 0x00 } ); + fontData.write(new byte[] { 0x00, 0x00, 0x00, 0x00 } ); + fontData.write(new byte[] { 0x00, 0x00, 0x00, 0x00 } ); + + fonts.add(fontData); + + fontData = new ByteArrayOutputStream(); + + fontData.write(new String("Courier New").getBytes("UTF-16LE")); + fontData.write(new byte[42]); + fontData.write(new byte[] { 0x14, 0x00, 0x04, 0x00 } ); + fontData.write(new byte[] { 0x01, 0x00, 0x00, 0x00 } ); + fontData.write(new byte[] { 0x00, 0x00, 0x15, 0x00 } ); + + // Next part indicates that this is the last font + fontData.write(new byte[] { 0x05, 0x00, 0x01, 0x00 } ); + + fonts.add(fontData); + } + catch (IOException ioe) { + // Shouldn't happen as this is a memory based stream + } + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/build.xml new file mode 100644 index 000000000000..9253aa503359 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/build.xml @@ -0,0 +1,136 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxs_pocketword" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxs_pocketword"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxw/pocketword"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/DocumentDescriptor.java"/> + <include name="${package}/DocumentDeserializerImpl.java"/> + <include name="${package}/DocumentSerializerImpl.java"/> + <include name="${package}/Paragraph.java"/> + <include name="${package}/ParagraphTextSegment.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + <include name="${package}/PocketWordConstants.java"/> + <include name="${package}/PocketWordDocument.java"/> + <include name="${package}/DocumentMergerImpl.java"/> + <include name="${package}/ConverterCapabilitiesImpl.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/converter.xml new file mode 100644 index 000000000000..aaa0dcc32e0d --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/converter.xml @@ -0,0 +1,47 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + + +<converters> + <converter type="staroffice/sxw" version="1.1"> + <converter-display-name> + Pocket Word + </converter-display-name> + <converter-description> + OpenOffice Writer XML to/from Pocket Word conversion. + </converter-description> + <converter-vendor> + OpenOffice.org + </converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.sxw.pocketword.PluginFactoryImpl + </converter-class-impl> + <converter-target type="application/x-pocket-word"/> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/package.html new file mode 100644 index 000000000000..ecc7d6105d83 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/pocketword/package.html @@ -0,0 +1,56 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<html> +<head> +<title>org.openoffice.xmerge.converter.xml.sxw.pocketword package</title> +</head> + +<body bgcolor="white"> + +<p>Plugin for the conversion of documents between StarWriter XML and + Pocket Word format.</p> +<p>This plugin suports conversion of most features supported by Pocket Word.</p> +<ul> + <li>Bold, Italic, Underline</li> + <li>Strikethrough</li> + <li>Highlight</li> + <li>Colours</li> + <li>Lists</li> + <li>Alignments</li> +</ul> + +<p>Additionally, work on fonts is currently underway.</p> + +<p>This plugin is based on the Windows CE 3.0 version of Pocket Word.<br> + Testing was carried out using Pocket PC 2000 and Pocket PC 2002 devices.</p> + +<p>It follows the {@link org.openoffice.xmerge} framework +for the conversion process.</p> + +</body> +</html> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..510f983e8248 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/ConverterCapabilitiesImpl.java @@ -0,0 +1,93 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * <p>WordSmith implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarWriter XML to/from WordSmith conversions. + * The <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_DOCUMENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_DOCUMENT_CONTENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_HEADING.equals(tag)) + return true; + else if (OfficeConstants.TAG_ORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_UNORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_ITEM.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_HEADER.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPAN.equals(tag)) + return true; + else if (OfficeConstants.TAG_HYPERLINK.equals(tag)) + return true; + else if (OfficeConstants.TAG_LINE_BREAK.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPACE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TAB_STOP.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_SPACE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_SPACE_COUNT.equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DOCConstants.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DOCConstants.java new file mode 100644 index 000000000000..546d3060eb9b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DOCConstants.java @@ -0,0 +1,61 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +/** + * Constants used for encoding and decoding the WordSmith format. + * + * @author Herbie Ong, David Proulx + */ +interface DOCConstants { + + /** Constant for uncompressed version. */ + public static final short UNCOMPRESSED = 1; + + /** Constant for compressed version. */ + public static final short COMPRESSED = 2; + + /** Constant used for spare fields. */ + public static final int SPARE = 0; + + /** WordSmith record size. */ + public static final short TEXT_RECORD_SIZE = 4096; + + /** Constant for encoding scheme. */ + public static final String ENCODING = "8859_1"; + + /** Constant for TAB character. */ + public final static char TAB_CHAR = '\t'; + + /** Constant for EOL character. */ + public final static char EOL_CHAR = '\n'; + + /** Constant for SPACE character. */ + public final static char SPACE_CHAR = ' '; +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentDeserializerImpl.java new file mode 100644 index 000000000000..ad90541afbbb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentDeserializerImpl.java @@ -0,0 +1,565 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.w3c.dom.*; + +import java.io.IOException; +import java.util.Enumeration; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PdbDecoder; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; + +import java.util.Vector; +import java.io.ByteArrayInputStream; + +import org.openoffice.xmerge.converter.xml.*; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.XmlUtil; + +/** + * <p>WordSmith implementation of + * org.openoffice.xmerge.DocumentDeserializer + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * The <code>deserialize</code> method uses a + * <code>DocDecoder</code> to read the WordSmith format into a + * <code>String</code> object, then it calls <code>buildDocument</code> + * to create a <code>SxwDocument</code> object from it. + * + * @author Herbie Ong, David Proulx + */ +public final class DocumentDeserializerImpl +implements DOCConstants, OfficeConstants, DocumentDeserializer { + + /** A Decoder object for decoding WordSmith format. */ + private WSDecoder decoder = null; + + WseFontTable fontTable = null; + WseColorTable colorTable = null; + StyleCatalog styleCat = null; + StyleCatalog oldStyleCat = null; + + /** A <code>ConvertData</code> object assigned to this object. */ + private ConvertData cd = null; + + + /** + * Constructor that assigns the given <code>ConvertData</code> + * to the object. + * + * @param cd A <code>ConvertData</code> object to read data for + * the conversion process by the deserialize method. + */ + public DocumentDeserializerImpl(ConvertData cd) { + this.cd = cd; + } + + + /** + * Convert the given <code>ConvertData</code> into a + * <code>SxwDocument</code> object. + * + * @return Resulting <code>Document</code> object. + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public Document deserialize() throws ConvertException, + IOException { + return deserialize(null, cd); + } + + + public Document deserialize(Document origDoc, ConvertData cd) + throws IOException { + + Document doc = null; + PalmDocument palmDoc = null; + Enumeration e = cd.getDocumentEnumeration(); + + while(e.hasMoreElements()) { + palmDoc = (PalmDocument) e.nextElement(); + PalmDB pdb = palmDoc.getPdb(); + Record[] recs = pdb.getRecords(); + decoder = new WSDecoder(); + Wse[] b = decoder.parseDocument(recs); + String docName = palmDoc.getName(); + doc = buildDocument(docName, b, origDoc); + } + return doc; + } + + + /** + * Temporary method to read existing <code>StyleCatalog</code> + * as a starting point. + * + * @param parentDoc The parent <code>Document</code>. + */ + private void readStyleCatalog(Document parentDoc) { + Element rootNode = null; + try { + java.io.ByteArrayOutputStream bos = new java.io.ByteArrayOutputStream(); + parentDoc.write(bos); + SxwDocument sxwDoc = new SxwDocument("old"); + sxwDoc.read(new ByteArrayInputStream(bos.toByteArray())); + org.w3c.dom.Document domDoc = sxwDoc.getContentDOM(); + + String families[] = new String[3]; + families[0] = "text"; + families[1] = "paragraph"; + families[2] = "paragraph"; + Class classes[] = new Class[3]; + classes[0] = TextStyle.class; + classes[1] = ParaStyle.class; + classes[2] = TextStyle.class; + + NodeList nl = domDoc.getElementsByTagName(TAG_OFFICE_STYLES); + oldStyleCat.add(nl.item(0), families, classes, null, false); + nl = domDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + oldStyleCat.add(nl.item(0), families, classes, null, false); + nl = domDoc.getElementsByTagName(TAG_OFFICE_MASTER_STYLES); + oldStyleCat.add(nl.item(0), families, classes, null, false); + + } catch (Exception e) { + Debug.log(Debug.ERROR, "", e); + } + + } + + + /** + * Given an array of paragraph <code>Style</code> objects, see if + * there is exactly one which matches the text formatting + * <code>Style</code> of <code>tStyle</code>. + * + * @param paraStyles An array of paragraph <code>Style</code> + * objects. + * @param tStyle Text <code>Style</code> to match. + * + * @return The paragraph <code>Style</code> that matches. + */ + private ParaStyle matchParaByText(Style paraStyles[], TextStyle tStyle) { + int matchIndex = -1; + int matchCount = 0; + Style txtMatches[] = (Style[]) oldStyleCat.getMatching(tStyle); + if (txtMatches.length >= 1) { + for (int j = 0; j < txtMatches.length; j++) { + TextStyle t = (TextStyle)txtMatches[j]; + + if (!t.getFamily().equals("paragraph")) + continue; + + for (int k = 0; k < paraStyles.length; k++) { + if (t.getName().equals(paraStyles[k].getName())) { + matchCount++; + matchIndex = k; + } + } + } + } + if (matchCount == 1) + return (ParaStyle)paraStyles[matchIndex]; + else return null; + } + + + /** + * Take a <code>String</code> of text and turn it into a sequence + * of <code>Node</code> objects. + * + * @param text <code>String</code> of text. + * @param parentDoc Parent <code>Document</code>. + * + * @return Array of <code>Node</code> objects. + */ + private Node[] parseText(String text, org.w3c.dom.Document parentDoc) { + Vector nodeVec = new Vector(); + + // Break up the text from the WordSmith text run into Open + // Office text runs. There may be more runs in OO because + // runs of 2 or more spaces map to nodes. + while ((text.indexOf(" ") != -1) || (text.indexOf("\t") != 1)) { + + // Find the indices of tabs and multiple spaces, and + // figure out which of them occurs first in the string. + int spaceIndex = text.indexOf(" "); + int tabIndex = text.indexOf("\t"); + if ((spaceIndex == -1) && (tabIndex == -1)) + break; // DJP This should not be necessary. What is wrong + // with the while() stmt up above? + int closerIndex; // Index of the first of these + if (spaceIndex == -1) + closerIndex = tabIndex; + else if (tabIndex == -1) + closerIndex = spaceIndex; + else + closerIndex = (spaceIndex > tabIndex) ? tabIndex : spaceIndex; + + // If there is any text prior to the first occurrence of a + // tab or spaces, create a text node from it, then chop it + // off the string we're working with. + if (closerIndex > 0) { + String beginningText = text.substring(0, closerIndex); + Text textNode = parentDoc.createTextNode(beginningText); + nodeVec.addElement(textNode); + log("<TEXT>"); + log(beginningText); + log("</TEXT>"); + } + text = text.substring(closerIndex); + + // Handle either tab character or space sequence by creating + // an element for it, and then chopping out the text that + // represented it in "text". + if (closerIndex == tabIndex) { + Element tabNode = parentDoc.createElement(TAG_TAB_STOP); + nodeVec.add(tabNode); + text = text.substring(1); // tab is always a single character + log("<TAB/>"); + } else { + // Compute length of space sequence. + int nrSpaces = 2; + while ((nrSpaces < text.length()) + && text.substring(nrSpaces, nrSpaces + 1).equals(" ")) + nrSpaces++; + + Element spaceNode = parentDoc.createElement(TAG_SPACE); + spaceNode.setAttribute(ATTRIBUTE_SPACE_COUNT, new Integer(nrSpaces).toString()); + nodeVec.add(spaceNode); + text = text.substring(nrSpaces); + log("<SPACE count=\"" + nrSpaces + "\" />"); + } + } + + // No more tabs or space sequences. If there's any remaining + // text create a text node for it. + if (text.length() > 0) { + Text textNode = parentDoc.createTextNode(text); + nodeVec.add(textNode); + log("<TEXT>"); + log(text); + log("</TEXT>"); + } + + // Now create and populate an array to return the nodes in. + Node nodes[] = new Node[nodeVec.size()]; + for (int i = 0; i < nodeVec.size(); i++) + nodes[i] = (Node)nodeVec.elementAt(i); + return nodes; + } + + + /** + * Parses the text content of a WordSmith format and builds a + * <code>SXWDocument</code>. + * + * @param docName <code>Document</code> name + * @param str Text content of WordSmith format + * + * @return Resulting <code>SXWDocument</code> object. + * + * @throws IOException If any I/O error occurs. + */ + private SxwDocument buildDocument(String docName, Wse[] data, Document origDoc) + throws IOException { + + // create minimum office xml document. + SxwDocument sxwDoc = new SxwDocument(docName); + sxwDoc.initContentDOM(); + + org.w3c.dom.Document doc = sxwDoc.getContentDOM(); + + // Grab hold of the office:body tag, + // Assume there should be one. + // This is where top level paragraphs will append to. + NodeList list = doc.getElementsByTagName(TAG_OFFICE_BODY); + Node bodyNode = list.item(0); + + styleCat = new StyleCatalog(50); + oldStyleCat = new StyleCatalog(50); + if (origDoc != null) + readStyleCatalog(origDoc); + + Element currPara = null; + ParaStyle currParaStyle = null; + int newTextStyleNr = 0; + int newParaStyleNr = 0; + + // Now write out the document body by running through + // the list of WordSmith elements and processing each one + // in turn. + for (int i = 0; i < data.length; i++) { + + if (data[i].getClass() == WsePara.class) { + + currPara = doc.createElement(TAG_PARAGRAPH); + log("</PARA>"); + log("<PARA>"); + + WsePara p = (WsePara)data[i]; + + // Save info about the first text run, if there is one. + WseTextRun firstTextRun = null; + + if ((data.length >= i + 2) + && (data[i+1].getClass() == WseTextRun.class)) + firstTextRun = (WseTextRun)data[i+1]; + + Style matches[] = oldStyleCat.getMatching(p.makeStyle()); + + // See if we can find a unique match in the catalog + // of existing styles from the original document. + ParaStyle pStyle = null; + if (matches.length == 1) { + pStyle = (ParaStyle)matches[0]; + log("using an existing style"); + } else if ((matches.length > 1) && (firstTextRun != null)) { + pStyle = matchParaByText(matches, firstTextRun.makeStyle()); + log("resolved a para by looking @ text"); + } + + // If nothing found so far, try looking in the catalog + // of newly-created styles. + // DJP FIXME: if we need to add two para styles with the + // same para formatting info but different default text + // styles, this won't work! + if (pStyle == null) { + log("had " + matches.length + " matches in old catalog"); + matches = styleCat.getMatching(p.makeStyle()); + if (matches.length == 0) { + pStyle = p.makeStyle(); + String newName = new String("PPP" + ++newParaStyleNr); + pStyle.setName(newName); + styleCat.add(pStyle); + // DJP: write in the text format info here + log("created a new style"); + } else if (matches.length == 1) { + pStyle = (ParaStyle)matches[0]; + log("re-using a new style"); + } else if (firstTextRun != null) { + pStyle = matchParaByText(matches, firstTextRun.makeStyle()); + if (pStyle != null) { + log("resolved a (new) para by looking @ text"); + } else + log("Hey this shouldn't happen! - nr of matches is " + + matches.length); + } + } + + if (pStyle == null) + log("Unable to figure out a para style"); + + // Figured out a style to use. Specify the style in this + // paragraph's attributes. + currPara.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, pStyle.getName()); + + bodyNode.appendChild(currPara); + currParaStyle = pStyle; + } else if (data[i].getClass() == WseTextRun.class) { + WseTextRun tr = (WseTextRun)data[i]; + TextStyle trStyle = null; + Node trNodes[] = parseText(tr.getText(), doc); + + // First see if the formatting of this text run matches + // the default text formatting for this paragraph. If + // it does, then just make the text node(s) children of + // the current paragraph. + Style[] cps = new Style[1]; + cps[0] = currParaStyle; + if (matchParaByText(cps, tr.makeStyle()) != null) { + for (int ii = 0; ii < trNodes.length; ii++) { + currPara.appendChild(trNodes[ii]); + } + continue; + } + + // Check for existing, matching styles in the old style + // catalog. If exactly one is found, use it. Otherwise, + // check the new style catalog, and either use the style + // found or add this new one to it. + Style matches[] = oldStyleCat.getMatching(tr.makeStyle()); + if (matches.length == 1) + trStyle = (TextStyle)matches[0]; + else { + matches = styleCat.getMatching(tr.makeStyle()); + if (matches.length == 0) { + trStyle = tr.makeStyle(); + String newName = new String("TTT" + ++newTextStyleNr); + trStyle.setName(newName); + styleCat.add(trStyle); + } else if (matches.length == 1) + trStyle = (TextStyle)matches[0]; + else + log("multiple text style matches from new catalog"); + } + + // Create a text span node, set the style attribute, make the + // text node(s) its children, and append it to current paragraph's + // list of children. + Element textSpanNode = doc.createElement(TAG_SPAN); + textSpanNode.setAttribute(ATTRIBUTE_TEXT_STYLE_NAME, trStyle.getName()); + for (int ii = 0; ii < trNodes.length; ii++) { + textSpanNode.appendChild(trNodes[ii]); + } + currPara.appendChild(textSpanNode); + log("</SPAN>"); + } + + else if (data[i].getClass() == WseFontTable.class) { + fontTable = (WseFontTable)data[i]; + } + + else if (data[i].getClass() == WseColorTable.class) { + colorTable = (WseColorTable)data[i]; + } + } + + + //NodeList r = doc.getElementsByTagName(TAG_OFFICE_DOCUMENT); + NodeList r = doc.getElementsByTagName(TAG_OFFICE_DOCUMENT_CONTENT); + Node rootNode = r.item(0); + + // read the original document + org.w3c.dom.NodeList nl; + if (origDoc != null) { + java.io.ByteArrayOutputStream bos = new java.io.ByteArrayOutputStream(); + origDoc.write(bos); + SxwDocument origSxwDoc = new SxwDocument("old"); + origSxwDoc.read(new ByteArrayInputStream(bos.toByteArray())); + org.w3c.dom.Document origDomDoc = origSxwDoc.getContentDOM(); + + XmlUtil xu = new XmlUtil(); + org.w3c.dom.DocumentFragment df; + org.w3c.dom.Node newNode; + + // copy font declarations from original document to the new document + nl = origDomDoc.getElementsByTagName(TAG_OFFICE_FONT_DECLS); + df = doc.createDocumentFragment(); + newNode = xu.deepClone(df, nl.item(0)); + rootNode.insertBefore(newNode, bodyNode); + + // copy style catalog from original document to the new document + nl = origDomDoc.getElementsByTagName(TAG_OFFICE_STYLES); + df = doc.createDocumentFragment(); + newNode = xu.deepClone(df, nl.item(0)); + rootNode.insertBefore(newNode, bodyNode); + + nl = origDomDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + df = doc.createDocumentFragment(); + newNode = xu.deepClone(df, nl.item(0)); + rootNode.insertBefore(newNode, bodyNode); + + nl = origDomDoc.getElementsByTagName(TAG_OFFICE_MASTER_STYLES); + df = doc.createDocumentFragment(); + newNode = xu.deepClone(df, nl.item(0)); + rootNode.insertBefore(newNode, bodyNode); + } + + // Original document not specified. We need to add font declarations. + // DJP: this might just be for debugging. Merger will probably put + // the "real" ones in. + // DJP: if really doing it this way, do it right: gather font names + // from style catalog(s). + else { + org.w3c.dom.Node declNode; + + log("<FONT-DECLS/>"); + + declNode = doc.createElement(TAG_OFFICE_FONT_DECLS); + rootNode.insertBefore(declNode, bodyNode); + org.w3c.dom.Element fontNode; + + fontNode = doc.createElement(TAG_STYLE_FONT_DECL); + fontNode.setAttribute(ATTRIBUTE_STYLE_NAME, "Arial"); + fontNode.setAttribute(ATTRIBUTE_FO_FONT_FAMILY, "Arial"); + fontNode.setAttribute(ATTRIBUTE_STYLE_FONT_PITCH, "variable"); + declNode.appendChild(fontNode); + + fontNode = doc.createElement(TAG_STYLE_FONT_DECL); + fontNode.setAttribute(ATTRIBUTE_STYLE_NAME, "Arioso"); + fontNode.setAttribute(ATTRIBUTE_FO_FONT_FAMILY, "Arioso"); + fontNode.setAttribute(ATTRIBUTE_STYLE_FONT_PITCH, "variable"); + declNode.appendChild(fontNode); + } + + + // Now add any new styles we have created in this document. + nl = doc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + Node autoStylesNode = nl.item(0); + if (autoStylesNode == null) { + autoStylesNode = doc.createElement(TAG_OFFICE_AUTOMATIC_STYLES); + log("<OFFICE-AUTOMATIC-STYLES/>"); + rootNode.insertBefore(autoStylesNode, bodyNode); + } + + Node newStyleCatNode = styleCat.writeNode(doc, "dummy"); + nl = newStyleCatNode.getChildNodes(); + int nNodes = nl.getLength(); + for (int i = 0; i < nNodes; i++) { + autoStylesNode.appendChild(nl.item(0)); + } + + oldStyleCat.dumpCSV(true); + styleCat.dumpCSV(true); + return sxwDoc; + } + + + /** + * Sends message to the log object. + * + * @param str Debug message. + */ + private void log(String str) { + + Debug.log(Debug.TRACE, str); + } + + + /* + public static void main(String args[]) { + + // DocumentDeserializerImpl d = new DocumentDeserializerImpl(new InputStream()); + + Node nodes[] = parseText("Tab here:\tThen some more text"); + } +*/ +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentMergerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentMergerImpl.java new file mode 100644 index 000000000000..c6dd88589fe5 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentMergerImpl.java @@ -0,0 +1,99 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.w3c.dom.Document; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.MergeException; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.Difference; +import org.openoffice.xmerge.merger.NodeMergeAlgorithm; +import org.openoffice.xmerge.merger.Iterator; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.diff.ParaNodeIterator; +import org.openoffice.xmerge.merger.diff.IteratorLCSAlgorithm; +import org.openoffice.xmerge.merger.merge.DocumentMerge; +import org.openoffice.xmerge.merger.merge.CharacterBaseParagraphMerge; +import org.openoffice.xmerge.util.Debug; + + +/** + * Wordsmith implementation of <code>DocumentMerger</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.PluginFactoryImpl + * PluginFactoryImpl}.</p> + */ +public class DocumentMergerImpl implements DocumentMerger { + + private ConverterCapabilities cc_; + private org.openoffice.xmerge.Document orig = null; + + public DocumentMergerImpl(org.openoffice.xmerge.Document doc, ConverterCapabilities cc) { + cc_ = cc; + this.orig = doc; + } + + public void merge(org.openoffice.xmerge.Document modifiedDoc) throws MergeException { + + SxwDocument wdoc1 = (SxwDocument) orig; + SxwDocument wdoc2 = (SxwDocument) modifiedDoc; + + Document doc1 = wdoc1.getContentDOM(); + Document doc2 = wdoc2.getContentDOM(); + + Iterator i1 = new ParaNodeIterator(cc_, doc1.getDocumentElement()); + Iterator i2 = new ParaNodeIterator(cc_, doc2.getDocumentElement()); + + DiffAlgorithm diffAlgo = new IteratorLCSAlgorithm(); + + // find out the paragrah level diffs + Difference[] diffTable = diffAlgo.computeDiffs(i1, i2); + + if (Debug.isFlagSet(Debug.INFO)) { + Debug.log(Debug.INFO, "Diff Result: "); + + for (int i = 0; i < diffTable.length; i++) { + Debug.log(Debug.INFO, diffTable[i].debug()); + } + } + + // merge the paragraphs + NodeMergeAlgorithm charMerge = new CharacterBaseParagraphMerge(); + DocumentMerge docMerge = new DocumentMerge(cc_, charMerge); + + Iterator result = null; + + docMerge.applyDifference(i1, i2, diffTable); + } +} + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentSerializerImpl.java new file mode 100644 index 000000000000..edbf7f5b4370 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/DocumentSerializerImpl.java @@ -0,0 +1,536 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import java.io.IOException; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.palm.PalmDB; +import org.openoffice.xmerge.converter.palm.PdbEncoder; +import org.openoffice.xmerge.converter.palm.Record; +import org.openoffice.xmerge.converter.palm.PdbUtil; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.util.*; +import org.openoffice.xmerge.converter.xml.*; + +/** + * <p>WordSmith implementation of + * org.openoffice.xmerge.DocumentSerializer + * for the {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>The <code>serialize</code> method traverses the DOM + * document from the given <code>Document</code> object. It uses a + * <code>DocEncoder</code> object for the actual conversion of + * contents to the WordSmith format.</p> + * + * @author Herbie Ong, David Proulx + */ + +// DJP: take out "implements OfficeConstants" +public final class DocumentSerializerImpl +implements OfficeConstants, DocumentSerializer { + + /** A WSEncoder object for encoding to WordSmith. */ + private WSEncoder encoder = null; + + /** The <code>StyleCatalog</code>. */ + private StyleCatalog styleCat = null; + + private WseFontTable fontTable = new WseFontTable(); + private WseColorTable colorTable = new WseColorTable(); + + /** + * The <code>SxwDocument</code> object that this converter + * processes. + */ + private SxwDocument sxwDoc = null; + + /** + * Constructor. + * + * @param doc The <code>Document</code> to convert. + */ + public DocumentSerializerImpl(Document doc) { + sxwDoc = (SxwDocument) doc; + } + + + /** + * <p>Method to convert a <code>Document</code> into a + * <code>PalmDocument</code>.</p> + * + * <p>This method is not thread safe for performance reasons. + * This method should not be called from within two threads. + * It would be best to call this method only once per object + * instance.</p> + * + * <p>Note that the doc parameter needs to be an XML + * <code>Document</code>, else this method will throw a + * <code>ClassCastException</code>. I think this is a hack, + * but this is the only way to not modify most of the existing + * code right now.</p> + * + * @param doc Input should be an XML <code>Document</code> + * object + * @param os Output of <code>PalmDB</code> object + * + * @throws ConvertException If any conversion error occurs. + * @throws IOException If any I/O error occurs. + */ + public ConvertData serialize() + throws IOException { + + + // get the server document name + String docName = sxwDoc.getName(); + + // get DOM document + org.w3c.dom.Document domDoc = sxwDoc.getContentDOM(); + + // Create WordSmith encoder object. Add WordSmith header, + // empty font table to it. + encoder = new WSEncoder(); + encoder.addElement(fontTable); + encoder.addElement(colorTable); + + // Read the styles into the style catalog + String families[] = new String[3]; + families[0] = "text"; + families[1] = "paragraph"; + families[2] = "paragraph"; + Class classes[] = new Class[3]; + classes[0] = TextStyle.class; + classes[1] = ParaStyle.class; + classes[2] = TextStyle.class; + styleCat = new StyleCatalog(25); + + // Parse the input document + // DJP todo: eliminate multiple calls to add() when it can + // recurse properly. + NodeList nl = domDoc.getElementsByTagName(TAG_OFFICE_STYLES); + styleCat.add(nl.item(0), families, classes, null, false); + nl = domDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + styleCat.add(nl.item(0), families, classes, null, false); + nl = domDoc.getElementsByTagName(TAG_OFFICE_MASTER_STYLES); + styleCat.add(nl.item(0), families, classes, null, false); + + // Traverse to the office:body element. + // There should only be one. + NodeList list = domDoc.getElementsByTagName(TAG_OFFICE_BODY); + int len = list.getLength(); + if (len > 0) { + Node node = list.item(0); + traverseBody(node); + } + + // create a PalmDB object and ConvertData object. + // + Record records[] = encoder.getRecords(); + + ConvertData cd = new ConvertData(); + PalmDocument palmDoc = new PalmDocument(docName, + PdbUtil.intID("WrdS"), PdbUtil.intID("BDOC"), 0, + PalmDB.PDB_HEADER_ATTR_BACKUP, records); + cd.addDocument(palmDoc); + return cd; + } + + + /** + * This method traverses <i>office:body</i> element. + * + * @param node <i>office:body</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseBody(Node node) throws IOException { + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH) || + nodeName.equals(TAG_HEADING)) { + + traverseParagraph(child); + + } else if (nodeName.equals(TAG_UNORDERED_LIST)) { + + traverseList(child); + + } else if (nodeName.equals(TAG_ORDERED_LIST)) { + + traverseList(child); + + } else { + + Debug.log(Debug.INFO, "<OTHERS " /* + XmlDebug.nodeInfo(child) */ + " />"); + } + } + } + } + + } + + + /** + * This method traverses the <i>text:p</i> and <i>text:h</i> + * element <code>Node</code> objects. + * + * @param node A <i>text:p</i> or <i>text:h</i> <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseParagraph(Node node) throws IOException { + + String styleName = findAttribute(node, "text:style-name"); + ParaStyle pstyle = (ParaStyle)styleCat.lookup(styleName, "paragraph", + null, ParaStyle.class); + + // If the style does not exist in the style catalog for some reason, + // make up a default style and use it. We'll have to add this default + // style to the style catalog the first time it is used. + if (pstyle == null) { + styleName = "CONVERTER-DEFAULT"; + pstyle = (ParaStyle)styleCat.lookup(styleName, "paragraph", null, + ParaStyle.class); + if (pstyle == null) { + pstyle = new ParaStyle(styleName, "paragraph", null, + (String [])null, null, styleCat); + styleCat.add(pstyle); + styleCat.add(new TextStyle(styleName, "paragraph", null, + 0, 0, 12, "Times-Roman", styleCat)); + } + } + + pstyle = (ParaStyle)pstyle.getResolved(); + encoder.addElement(new WsePara(pstyle, styleCat)); + TextStyle defParaTextStyle = (TextStyle) + styleCat.lookup(styleName, "paragraph", null, TextStyle.class); + + traverseParaContents(node, defParaTextStyle); + } + + + /** + * This method traverses a paragraph content. Note that this + * method may recurse to call itself. + * + * @param node A paragraph or content <code>Node</code> + */ + private void traverseParaContents(Node node, TextStyle defTextStyle) { + + String styleName = findAttribute(node, "text:style-name"); + TextStyle style = (TextStyle) + styleCat.lookup(styleName, "text", null, TextStyle.class); + + if (node.hasChildNodes()) { + NodeList nodeList = node.getChildNodes(); + int nChildren = nodeList.getLength(); + + for (int i = 0; i < nChildren; i++) { + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.TEXT_NODE) { + + // this is for grabbing text nodes. + String s = child.getNodeValue(); + + if (s.length() > 0) { + if (style != null) + encoder.addElement(new WseTextRun(s, style, styleCat, + fontTable, colorTable)); + else + encoder.addElement(new WseTextRun(s, defTextStyle, + styleCat, fontTable, colorTable)); + } + + } else if (child.getNodeType() == Node.ELEMENT_NODE) { + + String childNodeName = child.getNodeName(); + + if (childNodeName.equals(TAG_SPACE)) { + + // this is for text:s tags. + NamedNodeMap map = child.getAttributes(); + Node attr = map.getNamedItem(ATTRIBUTE_SPACE_COUNT); + StringBuffer space = new StringBuffer(" "); + int count = 1; + + if (attr != null) { + try { + String countStr = attr.getNodeValue(); + count = Integer.parseInt(countStr.trim()); + } catch (NumberFormatException e) { + Debug.log(Debug.ERROR, "Problem parsing space tag", e); + } + } + + for (int j = 1; j < count; j++) + space.append(" "); + + encoder.addElement(new WseTextRun(space.toString(), + defTextStyle, + styleCat, fontTable, colorTable)); + Debug.log(Debug.INFO, "<SPACE count=\"" + count + "\" />"); + + } else if (childNodeName.equals(TAG_TAB_STOP)) { + + // this is for text:tab-stop + encoder.addElement(new WseTextRun("\t", defTextStyle, styleCat, + fontTable, colorTable)); + + Debug.log(Debug.INFO, "<TAB/>"); + + } else if (childNodeName.equals(TAG_LINE_BREAK)) { + + // this is for text:line-break + encoder.addElement(new WseTextRun("\n", defTextStyle, + styleCat, fontTable, colorTable)); + + Debug.log(Debug.INFO, "<LINE-BREAK/>"); + + } else if (childNodeName.equals(TAG_SPAN)) { + + // this is for text:span + Debug.log(Debug.INFO, "<SPAN>"); + traverseParaContents(child, defTextStyle); + Debug.log(Debug.INFO, "</SPAN>"); + + } else if (childNodeName.equals(TAG_HYPERLINK)) { + + // this is for text:a + Debug.log(Debug.INFO, "<HYPERLINK>"); + traverseParaContents(child, defTextStyle); + Debug.log(Debug.INFO, "<HYPERLINK/>"); + + } else if (childNodeName.equals(TAG_BOOKMARK) || + childNodeName.equals(TAG_BOOKMARK_START)) { + + Debug.log(Debug.INFO, "<BOOKMARK/>"); + + } else { + + Debug.log(Debug.INFO, "<OTHERS " /* + XmlDebug.nodeInfo(child) */ + " />"); + } + + } + + } + } + } + + + /** + * This method traverses list tags <i>text:unordered-list</i> and + * <i>text:ordered-list</i>. A list can only contain one optional + * <i>text:list-header</i> and one or more <i>text:list-item</i> + * elements. + * + * @param node A list <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseList(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<LIST>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_LIST_ITEM)) { + + traverseListItem(child); + + } else if (nodeName.equals(TAG_LIST_HEADER)) { + + traverseListHeader(child); + + } else { + + Debug.log(Debug.ERROR, "<INVALID-XML-BUG " + " />"); + } + } + } + } + + Debug.log(Debug.TRACE, "</LIST>"); + } + + + /** + * This method traverses a <i>text:list-header</i> element. + * It contains one or more <i>text:p</i> elements. + * + * @param node A list header <code>Node</code>. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseListHeader(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<LIST-HEADER>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH)) { + + traverseParagraph(child); + + } else { + + Debug.log(Debug.TRACE, "<INVALID-XML-BUG " + " />"); + } + } + } + } + + Debug.log(Debug.TRACE, "</LIST-HEADER>"); + } + + + /** + * This method will traverse a <i>text:list-item</i>. + * A list item may contain one or more of <i>text:p</i>, + * <i>text:h</i>, <i>text:section</i>, + * <i>text:ordered-list</i> and <i>text:unordered-list</i>. + * + * This method currently only implements grabbing <i>text:p</i>, + * <i>text:h</i>, <i>text:unordered-list</i> and + * <i>text:ordered-list</i>. + * + * @param Node <code>Node</code> to traverse. + * + * @throws IOException If any I/O error occurs. + */ + private void traverseListItem(Node node) throws IOException { + + Debug.log(Debug.TRACE, "<LIST-ITEM>"); + + if (node.hasChildNodes()) { + + NodeList nodeList = node.getChildNodes(); + int len = nodeList.getLength(); + + for (int i = 0; i < len; i++) { + + Node child = nodeList.item(i); + + if (child.getNodeType() == Node.ELEMENT_NODE) { + + String nodeName = child.getNodeName(); + + if (nodeName.equals(TAG_PARAGRAPH)) { + + traverseParagraph(child); + + } else if (nodeName.equals(TAG_UNORDERED_LIST)) { + + traverseList(child); + + } else if (nodeName.equals(TAG_ORDERED_LIST)) { + + traverseList(child); + + } else { + + Debug.log(Debug.ERROR, "<INVALID-XML-BUG " + " />"); + } + } + } + } + + Debug.log(Debug.TRACE, "</LIST-ITEM>"); + } + + + /** + * Look up a <code>Node</code> object's named attribute and return + * its value + * + * @param node The <code>Node</code>. + * @param name The attribute name. + * + * @return The value of the named attribute + */ + private String findAttribute(Node node, String name) { + NamedNodeMap attrNodes = node.getAttributes(); + if (attrNodes != null) { + int len = attrNodes.getLength(); + for (int i = 0; i < len; i++) { + Node attr = attrNodes.item(i); + if (attr.getNodeName().equals(name)) + return attr.getNodeValue(); + } + } + return null; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/PluginFactoryImpl.java new file mode 100644 index 000000000000..f8df638bd69f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/PluginFactoryImpl.java @@ -0,0 +1,149 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.DocumentMergerFactory; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.sxw.SxwPluginFactory; +import org.openoffice.xmerge.converter.palm.PalmDocument; +import org.openoffice.xmerge.util.registry.ConverterInfo; + +import java.io.InputStream; +import java.io.IOException; + + +/** + * <p>WordSmith implementation of a <code>PluginFactory</code> that + * encapsulates conversion of StarWriter XML format to and from + * WordSmith format.</p> + * + * The superclass produces a particular + * {@link org.openoffice.xmerge.Document Document} + * object, i.e. + * {@link org.openoffice.xmerge.converter.xml.sxw.SxwDocument + * SxwDocument} that the converters in this class works with. Thus, + * this class only implements the methods that produces the converters, + * i.e. {@link + * org.openoffice.xmerge.DocumentSerializer + * DocumentSerializer} and {@link + * org.openoffice.xmerge.DocumentDeserializer + * DocumentDeserializer}; + * as well as the {@link + * org.openoffice.xmerge.ConverterCapabilities + * ConverterCapabilities} object that is specific to this format + * conversion. That superclass also produces a {@link + * org.openoffice.xmerge.DocumentMerger DocumentMerger} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.DocumentMergerImpl + * DocumentMergerImpl} which this class derives the functionality.</p> + * + * @author Herbie Ong, Dave Proulx + */ +public final class PluginFactoryImpl extends SxwPluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory, + DocumentMergerFactory { + + public PluginFactoryImpl(ConverterInfo ci) { + super(ci); + } + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + /** + * Returns an instance of <code>DocumentSerializerImpl</code>, which is + * an implementation of <code>DocumentSerializer</code> interface. + * + * @param doc <code>Document</code> object to be converted/serialized. + * + * @return A <code>DocumentSerializerImpl</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + + return new DocumentSerializerImpl(doc); + } + + + /** + * Returns an instance of <code>DocumentDeserializerImpl</code>, + * which is an implementation of <code>DocumentDeserializer</code> + * interface. + * + * @param cd <code>ConvertData</code> object for reading data + * which will be converted back to a + * <code>Document</code> object. + * + * @return A <code>DocumentDeserializerImpl</code> object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + + return new DocumentDeserializerImpl(cd); + } + + /** + * Returns an instance of <code>DocumentMergerImpl</code>, + * which is an implementation of the <code>DocumentMerger</code> + * interface. + * + * @param doc <code>Document</code> to merge. + * + * @return A DocumentMergerImpl object. + */ + public DocumentMerger createDocumentMerger(Document doc) { + + ConverterCapabilities cc = converterCap; + DocumentMergerImpl merger = new DocumentMergerImpl(doc, cc); + return merger; + } + + /** + * Returns an instance of the DeviceDocument + * which is an implementation of the <code>DocumentMerger</code> + * interface. + * + * @param doc <code>Document</code> to merge. + * + * @return A Device Document object + */ + public Document createDeviceDocument(String name, InputStream is) + throws IOException { + + PalmDocument palmDoc = new PalmDocument(is); + return palmDoc; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSDecoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSDecoder.java new file mode 100644 index 000000000000..07e8ea97ea43 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSDecoder.java @@ -0,0 +1,352 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.ByteArrayInputStream; +import java.io.DataInputStream; +import java.io.IOException; +import java.io.FileInputStream; +import java.io.UnsupportedEncodingException; +import org.openoffice.xmerge.util.Debug; + +import org.openoffice.xmerge.converter.palm.*; +import org.openoffice.xmerge.util.Resources; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.DocumentDeserializerImpl + * DocumentDeserializerImpl} to decode a WordSmith format. It currently + * decodes the text content into a single <code>String</code> object. + * + * @author Herbie Ong, David Proulx + */ +final class WSDecoder implements DOCConstants { + + /** For decoding purposes. */ + private final static int COUNT_BITS = 3; + + /** Resources object for I18N. */ + private Resources res = null; + + /** + * Default constructor creates a header and + * a text buffer for holding all the text in + * the DOC db. + */ + WSDecoder() { + res = Resources.getInstance(); + } + + /** + * Decode the text records into a single <code>byte</code> array. + * + * @param Record <code>Record</code> array holding WordSmith + * contents. + * + * @throws IOException If any I/O error occurs. + */ + byte[] parseRecords(Record[] recs) throws IOException { + + // read the header record + HeaderInfo header = readHeader(recs[0].getBytes()); + dumpHeader(header); + byte[][] byteArrays = new byte[recs.length - 1][]; + for (int i = 0; i < recs.length - 1; i++) byteArrays[i] = null; + + switch (header.version & ~4) { // DJP: "4" indicates OOB data is present. + // Add a constant to handle this, might also need code to handle it. + + case COMPRESSED: + case 3: // DJP: determined this empirically. Are Herbie's constants wrong? + for (int i = 1; i < recs.length; i++) { + byteArrays[i-1] = decompress(recs[i].getBytes(), + header.textRecordSize); + Debug.log(Debug.INFO, "processing " + byteArrays[i-1].length + " bytes"); + } + + break; + + case UNCOMPRESSED: + for (int i = 1; i < recs.length; i++) { + byteArrays[i-1] = recs[i].getBytes(); + Debug.log(Debug.INFO, "processing " + byteArrays[i-1].length + " bytes"); + } + + break; + + default: + throw new IOException(res.getString("UNKNOWN_DOC_VERSION")); + + } + + // Concatenate byteArrays[][] into a single byte array. + int length = 0; + for (int i = 0; i < recs.length - 1; i++) + length += byteArrays[i].length; + byte bigArray[] = new byte[length]; + int offset = 0; + for (int i = 0; i < recs.length - 1; i++) { + System.arraycopy(byteArrays[i], 0, bigArray, offset, + byteArrays[i].length); + offset += byteArrays[i].length; + } + return bigArray; + } + + + /** + * Decode the text records into a <code>Wse</code> array. + * + * @param Record[] <code>Record</code> array holding DOC + * contents. + * + * @throws IOException If any I/O error occurs. + */ + Wse[] parseDocument(Record[] recs) throws IOException { + + java.util.Vector v = new java.util.Vector(20, 20); + WseFontTable fontTable = null; + WseColorTable colorTable = null; + + // rawData is the document data to be parsed. + byte rawData[] = parseRecords(recs); + + // beginning of document has some header information, including + // optional font and color tables. + // DJP: maybe should add a new WSelement (docHeader) to hold + // header info. + // DJP: finish code here to parse header + if (rawData[0] != 2) throw new IOException(); + int nParagraphs = util.intFrom4bytes(rawData, 2); + int nAtoms = util.intFrom4bytes(rawData, 6); + int nChars = util.intFrom4bytes(rawData, 10); + int miscSize = util.intFrom4bytes(rawData, 14); + int curIndex = 18; + + while (curIndex < rawData.length) { + if (WsePara.isValid(rawData, curIndex)) { + v.add(new WsePara(rawData, curIndex)); + curIndex = WsePara.computeNewIndex(rawData, curIndex); + } else if (WseTextRun.isValid(rawData, curIndex)) { + v.add(new WseTextRun(rawData, curIndex, fontTable, colorTable)); + curIndex = WseTextRun.computeNewIndex(rawData, curIndex); + } else if (WseFontTable.isValid(rawData, curIndex)) { + fontTable = new WseFontTable(rawData, curIndex); + v.add(fontTable); + curIndex = WseFontTable.computeNewIndex(rawData, curIndex); + } else if (WseColorTable.isValid(rawData, curIndex)) { + colorTable = new WseColorTable(rawData, curIndex); + v.add(colorTable); + curIndex = WseColorTable.computeNewIndex(rawData, curIndex); + } else { + Debug.log(Debug.ERROR, "Unknown code " + rawData[curIndex]); + throw new IOException(); + } + } + + return (Wse[])v.toArray(new Wse[2]); + } + + + /** + * <p>Decompress the <code>byte</code> array.</p> + * + * <p>The resulting uncompressed <code>byte</code> array + * should be within <code>textRecordSize</code> length, + * definitely within twice the size it claims, else treat + * it as a problem with the encoding of that PDB and + * throw <code>IOException</code>.</p> + * + * @param bytes Compressed <code>byte</code> array + * @param textRecordSize Size of uncompressed <code>byte</code> + * array + * + * @throws IOException If <code>textRecordSize</codeL < + * <code>cBytes.length</code>. + */ + private byte[] decompress(byte[] cBytes, int textRecordSize) + throws IOException { + + // create byte array for storing uncompressed bytes + // it should be within textRecordSize range, definitely + // within twice of textRecordSize! if not, then + // an ArrayIndexOutOfBoundsException will get thrown, + // and it should be converted into an IOException, and + // treat it as a conversion error. + byte[] uBytes = new byte[textRecordSize*2]; + + int up = 0; + int cp = 0; + + try { + + while (cp < cBytes.length) { + + int c = cBytes[cp++] & 0xff; + + // codes 1...8 mean copy that many bytes + if (c > 0 && c < 9) { + + while (c-- > 0) + uBytes[up++] = cBytes[cp++]; + } + + // codes 0, 9...0x7F represent themselves + else if (c < 0x80) { + uBytes[up++] = (byte) c; + } + + // codes 0xC0...0xFF represent "space + ascii char" + else if (c >= 0xC0) { + uBytes[up++] = (byte) ' '; + uBytes[up++] = (byte) (c ^ 0x80); + } + + // codes 0x80...0xBf represent sequences + else { + c <<= 8; + c += cBytes[cp++] & 0xff; + int m = (c & 0x3fff) >> COUNT_BITS; + int n = c & ((1 << COUNT_BITS) - 1); + n += COUNT_BITS; + while (n-- > 0) { + uBytes[up] = uBytes[up - m]; + up++; + } + } + } + + } catch (ArrayIndexOutOfBoundsException e) { + + throw new IOException( + res.getString("DOC_TEXT_RECORD_SIZE_EXCEEDED")); + } + + // note that ubytes may be larger that the amount of + // uncompressed bytes, so trim it to another byte array + // with the exact size. + byte[] textBytes = new byte[up]; + System.arraycopy(uBytes, 0, textBytes, 0, up); + + return textBytes; + } + + + /** + * Read the header <code>byte</code> array. + * + * @param bytes <code>byte</code> array containing header + * record data. + * + * @return <code>HeaderInfo</code> object. + * + * @throws IOException If any I/O error occurs. + */ + private HeaderInfo readHeader(byte[] bytes) throws IOException { + + HeaderInfo header = new HeaderInfo(); + + ByteArrayInputStream bis = new ByteArrayInputStream(bytes); + DataInputStream dis = new DataInputStream(bis); + + // Normally the first 2 bytes comprised of the version + // which should either be COMPRESSED or UNCOMPRESSED + // SmartDoc/Quickword would add a 0x01 to the first + // byte, thus their version would be 0x0101 for UNCOMPRESSED + // instead of 0x0001 and 0x0102 for UNCOMPRESSED instead of + // 0x0002. + + dis.readByte(); + header.version = dis.readByte(); + + // read extra 2 unused bytes + dis.readShort(); + + // Read the text length, this should be unsigned 4 bytes. + // We could store the read value into a long, but then + // our current buffer limit is the max positive of an int. + // That is a large enough limit, thus we shall stay with + // storing the value in an int. If it exceeds, then + // an IOException should be thrown. + header.textLen = dis.readInt(); + if (header.textLen < 0) { + throw new IOException(res.getString("DOC_TEXT_LENGTH_EXCEEDED")); + } + + // read the number of records - unsigned 2 bytes + header.textRecordCount = ((int) dis.readShort()) & 0x0000ffff; + + // read the record size - unsigned 2 bytes + header.textRecordSize = ((int) dis.readShort()) & 0x0000ffff; + + // read extra 4 unused bytes + dis.readInt(); + + return header; + } + + + /** + * Prints out header info into log. + * Used for debugging purposes only. + * + * @param header <code>HeaderInfo</code> structure. + */ + private void dumpHeader(HeaderInfo header) { + /* + log("<DOC_INFO "); + log("version=\"" + header.version + "\" "); + log("text-length=\"" + header.textLen + "\" "); + log("number-of-records=\"" + header.textRecordCount + "\" "); + log("record-size=\"" + header.textRecordSize + "\" />\n"); + */ + } + + + /** + * Inner class to store DOC header information. + */ + private class HeaderInfo { + + /** length of text section */ + int textLen = 0; + + /** number of text records */ + int textRecordCount = 0; + + /** + * size of a text record. This is normally the same as + * TEXT_RECORD_SIZE, but some applications may modify this. + */ + int textRecordSize = 0; + + /** compression type */ + int version = 0; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSEncoder.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSEncoder.java new file mode 100644 index 000000000000..476e34c72e1f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WSEncoder.java @@ -0,0 +1,212 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.ByteArrayOutputStream; +import java.io.DataOutputStream; +import java.io.*; +import java.io.UnsupportedEncodingException; +import java.util.List; +import java.util.ArrayList; +import java.util.Vector; + +import org.openoffice.xmerge.converter.palm.*; + +/** + * This class is used by {@link + * org.openoffice.xmerge.converter.xml.sxw.wordsmith.DocumentDeserializerImpl + * DocumentDeserializerImpl} to encode the WordSmith format. + * + * @author David Proulx + */ + +// DJP: replace 4096 w/ a defined constant + +final class WSEncoder { + + /* DJP: These should probably go somewhere else! */ + /** Constant for uncompressed version. */ + public static final short UNCOMPRESSED = 1; + + /** Constant for compressed version. */ + public static final short COMPRESSED = 2; + + /** Constant used for spare fields. */ + public static final int SPARE = 0; + + /* WordSmith Header information. */ + private short version; + private int textLen; + private short maxRecSize; + private int textRecCount = 0; + + + /* WordSmith document elements. */ + WseHeader header = null; + WseFontTable ft = null; + WseColorTable ct = null; + private Vector elements; // paragraphs & text runs + + /* Totals for the WordSmith document. */ + int nrParagraphs = 0; + int nrAtoms = 0; + int nrChars = 0; + + + /** + * Default constructor creates a header and + * a text buffer for holding all the text in + * the WordSmith database. + */ + WSEncoder() { + version = 1; + textLen = 0; + maxRecSize = 4096; + elements = new Vector(); + } + + + /** + * This method adds a new element to the WordSmith document. + * + * @param elem WordSmith document element to add + */ + void addElement(Wse elem) { + if (elem.getClass() == WseHeader.class) + header = (WseHeader)elem; + else if (elem.getClass() == WseFontTable.class) + ft = (WseFontTable)elem; + else if (elem.getClass() == WseColorTable.class) + ct = (WseColorTable)elem; + else + elements.addElement(elem); + } + + + /** + * This method encodes the information given to + * an array of palm Records in the WordSmith database format. + * + * @return <code>Record</code> array holding WordSmith contents. + * + * @throws IOException If any I/O error occurs. + */ + Record[] getRecords() throws IOException { + + Vector allRecs = new Vector(); + int nElements = elements.size(); + + // Count up the number of paragraphs, atoms, and characters. + int currElement = 0; + while (currElement < nElements) { + Wse e = (Wse)elements.elementAt(currElement++); + if (e.getClass() == WsePara.class) + nrParagraphs++; + if (e.getClass() == WseTextRun.class) { + nrAtoms++; + nrChars += ((WseTextRun)e).getText().length(); + } + } + + byte[] currRec = new byte[4096]; + int currRecLen = 0; + + // This code assumes that the WordSmith header, font table, + // and color table total less than 4096 bytes. + header = new WseHeader(nrParagraphs, nrAtoms, nrChars, ft, ct); + System.arraycopy(header.getBytes(), 0, + currRec, currRecLen, header.getByteCount()); + currRecLen += header.getByteCount(); + + if (ft != null) { + System.arraycopy(ft.getBytes(), 0, currRec, currRecLen, + ft.getByteCount()); + currRecLen += ft.getByteCount(); + } + if (ct != null) { + System.arraycopy(ct.getBytes(), 0, currRec, currRecLen, + ct.getByteCount()); + currRecLen += ct.getByteCount(); + } + + currElement = 0; + while (currElement < nElements) { + Wse e = (Wse)elements.elementAt(currElement++); + int length = e.getByteCount(); + if ((length + currRecLen) <= 4096) { + System.arraycopy(e.getBytes(), 0, currRec, currRecLen, length); + currRecLen += length; + } else { + // Copy in enough to get to full size, then create a + // new Record and add it to the Vector. + int firstPartLen = 4096 - currRecLen; + System.arraycopy(e.getBytes(), 0, currRec, currRecLen, + firstPartLen); + Record r = new Record(currRec); + allRecs.addElement(r); + + // Put the remainder at the beginning of the next record + currRecLen = 0; + System.arraycopy(e.getBytes(), firstPartLen, currRec, + currRecLen, length - firstPartLen); + currRecLen += length - firstPartLen; + } + } + + // Processed all the elements. Write out any remaining partial record. + if (currRecLen > 0) { + byte[] partial = new byte[currRecLen]; + System.arraycopy(currRec, 0, partial, 0, currRecLen); + Record rr = new Record(partial); + allRecs.addElement(rr); + } + + + // Record 0 is the WordSmith header. Do it last since it + // contains totals for the entire document. It goes + // before everything else. + ByteArrayOutputStream bos = new ByteArrayOutputStream(); + DataOutputStream dos = new DataOutputStream(bos); + dos.writeShort(version); + dos.writeShort(0); + dos.writeInt(textLen); + dos.writeShort(allRecs.size()); + dos.writeShort(maxRecSize); + dos.writeInt(0); + allRecs.insertElementAt(new Record(bos.toByteArray()), 0); + + // Convert Vector of Records to an array and return it. + int nRecs = allRecs.size(); + Record recs[] = new Record[nRecs]; + for (int i = 0; i < nRecs; i++) + recs[i] = (Record)allRecs.elementAt(i); + return recs; + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/Wse.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/Wse.java new file mode 100644 index 000000000000..778ff5d38f57 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/Wse.java @@ -0,0 +1,100 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.xml.*; + + +/** + * This is the superclass for all elements in a WordSmith document. + * Elements can be paragraphs, text runs, font tables, or color tables. + * + * @author David Proulx + */ +abstract class Wse { + + /** + * Return true if <code>dataArray[startIndex]</code> is the start + * of a valid element of this type. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return true if <code>dataArray[startIndex]</code> is the + * start of a valid element of this type, false otherwise. + */ + static boolean isValid(byte dataArray[], int startIndex) { + return false; + } + + + /** + * Compute and return the index of the first <code>byte</code> + * following this element. It is assumed that the element + * starting at <code>dataArray[startIndex]</code> is valid. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return The index of the first <code>byte</code> following + * this element. + */ + static int computeNewIndex(byte dataArray[], int startIndex) { + return 0; + } + + + /** + * Return the total number of bytes needed to represent this + * object. + * + * @return The total number of bytes needed to represent this + * object. + */ + abstract int getByteCount(); + + + /** + * Return an <code>byte</code> array representing this element. + * + * @return An <code>bytes</code> array representing this element. + */ + abstract byte[] getBytes(); +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseColorTable.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseColorTable.java new file mode 100644 index 000000000000..e5af0337283b --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseColorTable.java @@ -0,0 +1,247 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.IOException; +import java.awt.Color; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.xml.*; + +/** + * This class represents a color table in a WordSmith document. + * + * @author David Proulx + */ +class WseColorTable extends Wse { + + private Color fgColors[]; + private Color bgColors[]; + + /** + * Constructor to use when going from DOM to WordSmith + */ + public WseColorTable() { + fgColors = new Color[16]; + bgColors = new Color[16]; + + // Always need these two! + fgColors[0] = Color.black; + bgColors[0] = Color.white; + + } + + /** + * Constructor to use when going from WordSmith to DOM. + * + * @param dataArray <code>byte</code> array. + * @param i The index. + */ + public WseColorTable(byte dataArray[], int i) { + fgColors = new Color[16]; + bgColors = new Color[16]; + + i += 2; // Skip leading "64" and table length field. + for (int k = 0; k < 16; k++) { + fgColors[k] = new Color(((int)dataArray[i+1]) & 0xFF, + ((int)dataArray[i+2]) & 0xFF, + ((int)dataArray[i+3]) & 0xFF); + i += 4; + } + for (int k = 0; k < 16; k++) { + bgColors[k] = new Color(((int)dataArray[i+1]) & 0xFF, + ((int)dataArray[i+2]) & 0xFF, + ((int)dataArray[i+3]) & 0xFF); + i += 4; + } + + } + + + /** + * Compute the index of the first <code>byte</code> following the + * paragraph descriptor, assuming that + * <code>dataArray[startIndex]</code> is the beginning of a valid + * paragraph descriptor. + * + * @param dataArray <code>byte</code array. + * @param startIndex The start index. + * + * @return The index of the first <code>byte</code> following the + * paragraph description. + */ + static int computeNewIndex(byte dataArray[], int startIndex) { + int tableLen = dataArray[startIndex + 1]; + tableLen &= 0xFF; // eliminate problems with sign-extension + return startIndex + tableLen + 2; + } + + + /** + * Return true if <code>dataArray[startIndex]</code> is the start + * of a valid paragraph descriptor. + * + * @param dataArray <code>byte</code> array. + * @param startIndex Start index. + * + * @return true if <code>dataArray[startIndex]</code> is the start + * of a valid paragraph descriptor, false otherwise. + */ + static boolean isValid(byte dataArray[], int startIndex) { + try { + if (dataArray[startIndex] != 64) + return false; + int len = dataArray[startIndex + 1]; + len &= 0xFF; // eliminate problems with sign-extension + int temp = dataArray[startIndex + (int)len + 2]; // probe end of table + } catch (ArrayIndexOutOfBoundsException e) { + return false; + } + return true; + } + + + /** + * Return the number of bytes needed to represent this color table. + * + * @return The byte count. + */ + int getByteCount() { + return (32 * 4) + 1 + 1; + } + + + /** + * Return a <code>byte</code> array representing this color table. + * + * @return <code>bytes</code> array representing this color table. + */ + byte[] getBytes() { + byte[] b = new byte[(32 * 4) + 1 + 1]; + b[0] = 0x40; + b[1] = (byte)128; + int i = 2; + // int indVal = 0xd8; + int indVal = 0; + + for (int j = 0; j < 16; j++) { + b[i++] = (byte)indVal++; + if (fgColors[j] != null) { + b[i++] = (byte)fgColors[j].getRed(); + b[i++] = (byte)fgColors[j].getGreen(); + b[i++] = (byte)fgColors[j].getBlue(); + } else { + b[i++] = (byte)0; + b[i++] = (byte)0; + b[i++] = (byte)0; + } + } + + for (int j = 0; j < 16; j++) { + b[i++] = (byte)indVal++; + if (bgColors[j] != null) { + b[i++] = (byte)bgColors[j].getRed(); + b[i++] = (byte)bgColors[j].getGreen(); + b[i++] = (byte)bgColors[j].getBlue(); + } else { + b[i++] = (byte)0xFF; + b[i++] = (byte)0xFF; + b[i++] = (byte)0xFF; + } + } + + return b; + } + + + /** + * Return the index of the specified foreground or background + * <code>Color</code>. (If the color is not already in the table, + * it will be added.) + * + * Note that the implementation of this may include a "margin of + * error" to prevent the color table from being filled up too + * quickly. + * + * @param c The <code>Color</code>. + * @param foreground true if foreground color, false if background + * color + * + * @return The index of the specified foreground or background + * <code>Color</code>. + * + * DJP: how to handle table overflow? + */ + int findColor(Color c, boolean foreground) { + + Color colorArray[] = foreground ? fgColors : bgColors; + + for (int i = 0; i < 16; i++) { + if (colorArray[i] != null) { + if (colorArray[i].equals(c)) + return i; + } + else + break; // hit a null entry - no more colors in table! + } + + // Color was not found in the table. Add it. + for (int i = 0; i < 16; i++) { + if (colorArray[i] == null) { + colorArray[i] = c; + return i; + } + } + return 0; // Default - we should never get here though. + } + + + /** + * Given an index, return the <code>Color</code> from the table. + * + * @param index The index + * @param foreground true if foreground color, false if background + * color + * + * @return The <code>Color</code> at the specified index. + */ + Color getColor(int index, boolean foreground) { + + Color colorArray[] = foreground ? fgColors : bgColors; + return colorArray[index]; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseFontTable.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseFontTable.java new file mode 100644 index 000000000000..d5e7a84fb6bf --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseFontTable.java @@ -0,0 +1,218 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.IOException; + +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.xml.*; + +/** + * <p>This class represents a font table in a WordSmith document. + * A font table is represented as follows:</p> + * + * <p><blockquote> + * binary "3"<br> + * two-byte length of the table of strings which follows<br> + * string table (null-terminated strings) representing font names + * </blockquote></p> + * + * @author David Proulx + */ +class WseFontTable extends Wse { + + java.util.Vector fontNames = new java.util.Vector(10); + + + /** + * Constructor for use when going from DOM to WordSmith. + */ + public WseFontTable() { + } + + + /** + * Constructor for use when going from WordSmith to DOM. + * + * @param dataArray <code>byte</code> array. + * @param i The index. + */ + public WseFontTable(byte dataArray[], int i) { + i++; + int tableLen = ((dataArray[i] << 8) | (dataArray[i+1] & 0xFF)); + i += 2; + while (tableLen > 0) { + int j = 0; + while (dataArray[i + j] != 0) j++; + fontNames.add(new String(dataArray, i, j)); + tableLen -= (j + 1); + i += (j + 1); + } + } + + + /** + * Add a new font to the table. + * + * @param newFontName The new font name. + */ + public void add(String newFontName) { + if (newFontName != null) + fontNames.add(newFontName); + } + + + /** + * Return a font name from the table, or null if invalid index. + * + * @param index The font name index. + * + * @return The font name. + */ + public String getFontName(int index) { + try { + return (String)fontNames.elementAt(index); + } catch (ArrayIndexOutOfBoundsException e) { + return null; + } + } + + /** + * Return the index of a font name in the table, or -1 if not found. + * + * @param fontName The font name. + * + * @return The index of the font name, or -1 if not found. + */ + public int getFontIndex(String fontName) { + int len = fontNames.size(); + for (int i = 0; i < len; i++) { + String name = (String) fontNames.elementAt(i); + if (name.equals(fontName)) + return i; + } + return -1; + } + + + /** + * Compute the index of the first <code>byte</code> following the + * paragraph descriptor, assuming that + * <code>dataArray[startIndex]</code> is the beginning of a valid + * paragraph descriptor. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return The index of the first <code>byte</code> following the + * paragraph description. + */ + static int computeNewIndex(byte dataArray[], int startIndex) { + startIndex++; // Skip the leading "3" + int tableLen = ((dataArray[startIndex] << 8) | (dataArray[startIndex+1] & 0xFF)); + tableLen &= 0xFFFF; // eliminate problems with sign-extension + return startIndex + tableLen + 2; + } + + + /** + * Return true if <code>dataArray[startIndex]</code> is the start of a + * valid paragraph descriptor. + * + * @param dataArray <code>byte</code> string. + * @param startIndex Start index. + * + * @return true if <code>dataArray[startIndex]</code> is the start + * of a valid paragraph descriptor, false otherwise. + */ + static boolean isValid(byte dataArray[], int startIndex) { + try { + if (dataArray[startIndex] != 3) + return false; + int len = ((dataArray[startIndex+1] << 8) + | (dataArray[startIndex+2] & 0xFF)); + len &= 0xFFFF; // eliminate problems with sign-extension + + if (dataArray[startIndex + len + 2] != 0) + return false; + } catch (ArrayIndexOutOfBoundsException e) { + return false; + } + return true; + } + + + /** + * Return the number of bytes needed to represent this font table. + * + * @return The number of bytes needed to represent this font table. + */ + int getByteCount() { + + int length = 3; // leading "3" plus 2 bytes for length. + int nFonts = fontNames.size(); + for (int i = 0; i < nFonts; i++) { + String name = (String)fontNames.elementAt(i); + length += name.length() + 1; // extra byte is for trailing "0" + } + return length; + } + + /** + * Return a <code>byte</code> array representing this font table. + * + * @return An <code>byte</code> array representing this font table. + */ + byte[] getBytes() { + + int length = getByteCount(); + int nFonts = fontNames.size(); + byte b[] = new byte[length]; + b[0] = 3; + length -= 3; + b[1] = (byte)(length >> 8); + b[2] = (byte)(length & 0xFF); + int indx = 3; + for (int i = 0; i < nFonts; i++) { + String name = (String)fontNames.elementAt(i); + byte bname[] = name.getBytes(); + System.arraycopy(bname, 0, b, indx, bname.length); + indx += bname.length; + b[indx++] = 0; + } + return b; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseHeader.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseHeader.java new file mode 100644 index 000000000000..52fffba259a8 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseHeader.java @@ -0,0 +1,145 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.IOException; +import java.io.DataOutputStream; +import java.io.ByteArrayOutputStream; + +/** + * This class represents a WordSmith document header. + * + * @author David Proulx + */ +class WseHeader extends Wse { + + private int nParagraphs = 0; + private int nAtoms = 0; + private int nChars = 0; + private int miscSize = 0; + + /** + * Constructor for use when going from DOM to WordSmith. + * + * @param nPara The number of paragraphs. + * @param nAtoms The number of atoms. + * @param nChars The number of characters. + * @param ft The font table. + * @param ct The color table. + */ + public WseHeader(int nPara, int nAtoms, int nChars, WseFontTable ft, + WseColorTable ct) { + nParagraphs = nPara; + this.nAtoms = nAtoms; + this.nChars = nChars; + if (ft != null) miscSize += ft.getByteCount(); + if (ct != null) miscSize += ct.getByteCount(); + } + + + /** + * Constructor for use when going from WordSmith to DOM. + * + * @param dataArray <code>byte</code> array. + * @param i Index. + */ + public WseHeader(byte dataArray[], int i) { + // DJP: write this! + } + + /** + * Return true if <code>dataArray[startIndex]</code> is the start + * of a document header. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The index. + * + * @return true if <code>dataArray[startIndex]</code> is the start + * of a document header, false otherwise. + */ + static boolean isValid(byte dataArray[], int startIndex) { + return ((dataArray[startIndex] == 2) + && (dataArray[startIndex + 1] == 4)); + } + + + /** + * Compute and return the index of the first <code>byte</code> + * following this element. It is assumed that the element + * starting at <code>dataArray[startIndex]</code> is valid. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return The first <code>byte</code> following this element. + */ + static int computeNewIndex(byte dataArray[], int startIndex) { + return startIndex + 18; + } + + + /** + * Return the total number of bytes needed to represent this. + * + * @return The total number of bytes needed to represent this. + */ + int getByteCount() { + return 18; + } + + + /** + * Return a <code>byte</code> array representing this element. + * + * @return A <code>byte</code> array representing this element. + */ + byte[] getBytes() { + DataOutputStream os; // Used for storing the data + ByteArrayOutputStream bs = null; // Used for storing the data + + try { + bs = new ByteArrayOutputStream(); + os = new DataOutputStream(bs); + os.write(2); // binary doc indicator + os.write(4); // binary header indicator + + os.writeInt(nParagraphs); + os.writeInt(nAtoms); + os.writeInt(nChars); + os.writeInt(miscSize); + + } catch (IOException e) { + e.printStackTrace(); + } + + if (bs != null) { + return bs.toByteArray(); + } else return null; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WsePara.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WsePara.java new file mode 100644 index 000000000000..91530174211f --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WsePara.java @@ -0,0 +1,299 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import java.io.IOException; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.NamedNodeMap; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.xml.*; + + +/** + * This class represents a paragraph in a WordSmith document. + * (A paragraph is "5" followed by 12 bytes of attributes.) + * + * @author David Proulx + */ +class WsePara extends Wse { + + private byte spaceBefore = 0; + private byte spaceAfter = 0; + private byte leftIndent = 0; + private byte firstIndent = 0; + private byte rightIndent = 0; + private byte misc = 0; + private byte style = 0; + private byte lineSpace = 0; + private byte outline = 0; + private byte reserved = 0; + + private static final byte LS_EXACTLY = (byte)0xC0; + private static final byte LS_ATLEAST = (byte)0x80; + private static final byte LS_MULTIPLE = (byte)0x40; + private static final byte LS_VALUEMASK = (byte)0x3F; + + private static final byte ALIGN_RIGHT = (byte)2; + private static final byte ALIGN_LEFT = (byte)0; + private static final byte ALIGN_CENTER = (byte)1; + private static final byte ALIGN_JUST = (byte)3; + + private StyleCatalog sc = null; + + + /** + * Constructor for use when going from DOM to WordSmith. + * + * @param p The paragraph style. + * @param sc The <code>StyleCatalog</code>. + */ + public WsePara(ParaStyle p, StyleCatalog sc) { + this.sc = sc; + ParaStyle ps = (ParaStyle)p.getResolved(); + + if (ps.isAttributeSet(ParaStyle.MARGIN_LEFT)) { + double temp = ps.getAttribute(ParaStyle.MARGIN_LEFT) * 1.6 / 100; + leftIndent = (byte) temp; + if ((temp - leftIndent) > 0.5) leftIndent++; + } + + if (ps.isAttributeSet(ParaStyle.MARGIN_RIGHT)) { + double temp = ps.getAttribute(ParaStyle.MARGIN_RIGHT) * 1.6 / 100; + rightIndent = (byte) temp; + if ((temp - rightIndent) > 0.5) rightIndent++; + } + + if (ps.isAttributeSet(ParaStyle.TEXT_INDENT)) { + double temp = ps.getAttribute(ParaStyle.TEXT_INDENT) * 1.6 / 100; + firstIndent = (byte) temp; + if ((temp - firstIndent) > 0.5) firstIndent++; + } + + if (ps.isAttributeSet(ParaStyle.MARGIN_TOP)) { + double temp = ps.getAttribute(ParaStyle.MARGIN_TOP) * 1.6 / 100; + spaceBefore = (byte) temp; + if ((temp - spaceBefore) > 0.5) spaceBefore++; + } + + if (ps.isAttributeSet(ParaStyle.MARGIN_BOTTOM)) { + double temp = ps.getAttribute(ParaStyle.MARGIN_BOTTOM) * 1.6 / 100; + spaceAfter = (byte) temp; + if ((temp - spaceAfter) > 0.5) spaceAfter++; + } + + if (ps.isAttributeSet(ParaStyle.LINE_HEIGHT)) { + int lh = ps.getAttribute(ParaStyle.LINE_HEIGHT); + if ((lh & ~ParaStyle.LH_VALUEMASK) == 0) + lineSpace = (byte)(LS_MULTIPLE | (lh * 2)); + else if ((lh & ParaStyle.LH_PCT) != 0) { + lh = (lh & ParaStyle.LH_VALUEMASK) / 100; + lineSpace = (byte)(LS_MULTIPLE | (lh * 2)); + } + // DJP: handle other cases.... + } + + if (ps.isAttributeSet(ParaStyle.TEXT_ALIGN)) { + + int val = ps.getAttribute(ParaStyle.TEXT_ALIGN); + + switch (val) { + case ParaStyle.ALIGN_RIGHT: + misc = ALIGN_RIGHT; + break; + case ParaStyle.ALIGN_LEFT: + misc = ALIGN_LEFT; + break; + case ParaStyle.ALIGN_CENTER: + misc = ALIGN_CENTER; + break; + case ParaStyle.ALIGN_JUST: + misc = ALIGN_JUST; + break; + } + } + + } + + + /** + * Constructor for use when going from WordSmith to DOM. + * Assumes <code>dataArray[startIndex]</code> is the first + * <code>byte</code> of a valid WordSmith paragraph descriptor. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + */ + public WsePara(byte dataArray[], int startIndex) { + spaceBefore = dataArray[startIndex + 1]; + spaceAfter = dataArray[startIndex + 2]; + leftIndent = dataArray[startIndex + 3]; + firstIndent = dataArray[startIndex + 4]; + rightIndent = dataArray[startIndex + 5]; + misc = dataArray[startIndex + 6]; + style = dataArray[startIndex + 7]; + lineSpace = dataArray[startIndex + 8]; + outline = dataArray[startIndex + 9]; + } + + + /** + * Compute the index of the first <code>byte</code> following the + * paragraph descriptor, assuming that + * <code>dataArray[startIndex]</code> is the beginning of a valid + * paragraph descriptor. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return The index of the first <code>byte</code> following the + * paragraph description. + */ + static int computeNewIndex(byte dataArray[], int startIndex) { + return startIndex + 13; + } + + + /** + * Return true if <code>dataArray[startIndex]</code> is the start + * of a valid paragraph descriptor. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return true if <code>dataArray[startIndex]</code> is the start + * of a valid paragraph descriptor, false otherwise. + */ + static boolean isValid(byte dataArray[], int startIndex) { + return (dataArray[startIndex] == 5); + } + + /** + * Return the number of bytes needed to represent this paragraph. + * + * @return The number of bytes needed to represent this paragraph. + */ + int getByteCount() { + return 13; + } + + /** + * Return an <code>byte</code> array representing this paragraph. + * + * @return An <code>byte</code> array representing this paragraph. + */ + byte[] getBytes() { + byte b[] = new byte[13]; + + b[0] = 5; + b[1] = spaceBefore; + b[2] = spaceAfter; + b[3] = leftIndent; + b[4] = firstIndent; + b[5] = rightIndent; + b[6] = misc; + b[7] = style; + b[8] = lineSpace; + b[9] = outline; + b[10] = reserved; + b[11] = 0; + b[12] = 0; + + return b; + } + + /** + * Return a <code>ParaStyle</code> that reflects the formatting of + * this run. + * + * @return A <code>ParaStyle</code> that reflects the formatting + * of this run. + */ + ParaStyle makeStyle() { + /* Csaba: Commented out the LINE_HEIGHT syle, because there was no + incoming data for that style. It was resulting a zero line + height in the xml document, ie. the doc looked empty. + */ + int attrs[] = { ParaStyle.MARGIN_LEFT, ParaStyle.MARGIN_RIGHT, + ParaStyle.TEXT_INDENT, //ParaStyle.LINE_HEIGHT, + ParaStyle.MARGIN_TOP, ParaStyle.MARGIN_BOTTOM, + ParaStyle.TEXT_ALIGN }; + String values[] = new String[attrs.length]; + double temp; + + temp = leftIndent / 1.6; + values[0] = (new Double(temp)).toString() + "mm"; + + temp = rightIndent / 1.6; + values[1] = (new Double(temp)).toString() + "mm"; + + temp = firstIndent / 1.6; + values[2] = (new Double(temp)).toString() + "mm"; + +/* if ((lineSpace & LS_MULTIPLE) != 0) { + temp = (lineSpace & LS_VALUEMASK) / 2; + temp *= 100; + values[3] = (new Double(temp)).toString() + "%"; + } else { + values[3] = (new Double(temp)).toString() + "mm"; + // DJP: handle other cases + } +*/ + temp = spaceBefore / 1.6; +// values[4] = (new Double(temp)).toString() + "mm"; + values[3] = (new Double(temp)).toString() + "mm"; + + temp = spaceAfter / 1.6; +// values[5] = (new Double(temp)).toString() + "mm"; + values[4] = (new Double(temp)).toString() + "mm"; + + switch (misc) { + +// case ALIGN_RIGHT: values[6] = "right"; break; +// case ALIGN_LEFT: values[6] = "left"; break; +// case ALIGN_CENTER:values[6] = "center"; break; +// case ALIGN_JUST: values[6] = "justified"; break; + + case ALIGN_RIGHT: values[5] = "right"; break; + case ALIGN_LEFT: values[5] = "left"; break; + case ALIGN_CENTER:values[5] = "center"; break; + case ALIGN_JUST: values[5] = "justified"; break; + } + ParaStyle x = new ParaStyle(null, "paragraph", null, attrs, + values, sc); + + return x; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseTextRun.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseTextRun.java new file mode 100644 index 000000000000..86626dd4d2c7 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/WseTextRun.java @@ -0,0 +1,324 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.openoffice.xmerge.converter.xml.TextStyle; +import org.openoffice.xmerge.converter.xml.StyleCatalog; +import java.awt.Color; + +/** + * <p>This class represents a text run (aka text atom) in a WordSmith + * document.</p> + * + * <p>WordSmith represents a text run as follows:</p> + * + * <p><ul><li> + * 1 byte Value of "1", indicating beginning of a text atom + * </li><li> + * 2 bytes Length of text (does not include attributes, this length field, + * etc) + * </li><li> + * 1 byte Font index - Index in the font table of font to be used + * </li><li> + * 1 byte Font size (DJP: get details of representation) + * </li><li> + * 1 byte Color index - Index in the color table of font color to be used + * </li><li> + * 1 byte Modifiers - bit flags for bold, italic, etc + * </li><li> + * n bytes Text - the actual text + * </li></ul></p> + * + * @author David Proulx + */ +class WseTextRun extends Wse { + + /** Font specifier. This is an index into the font table. */ + private byte fontIndex = 0; + private String fontName = null; + + /** Size of the font. */ + private byte fontSize = 0; + + /** + * Color of the font. This is an index into the color table. + * High nibble is background color index, low nibble is font color + * index. + */ + private byte colorIndex = 0; + + /** + * Reference to color table for color lookups. + */ + private WseColorTable ct; + + /** + * The modifiers for the text run. (Mostly) Bitwise flags. The "_TOKEN" + * values are not yet implemented in this converter. They may not even + * be implemented in WordSmith yet. + */ + private byte modifiers = 0; + final public static int BOLD = 0x01; + final public static int ITALIC = 0x02; + final public static int UNDERLINE = 0x04; + final public static int STRIKETHRU = 0x08; + final public static int SUPERSCRIPT = 0x10; + final public static int SUBSCRIPT = 0x20; + final public static int LINK = 0x40; + final public static int CUSTOM_TOKEN = 0x80; + final public static int IMAGE_TOKEN = 0x80; + final public static int BOOKMARK_TOKEN = 0x81; + final public static int ANNOTATION_TOKEN = 0x82; + final public static int LINK_TOKEN = 0x83; + + /** The actual text. */ + private String text; + + StyleCatalog sc; + + + /** + * Constructor for use when going from DOM to WordSmith. + * + * @param txt The text. + * @param t The text style. + * @param sc The <code>StyleCatalog</code>. + * @param ft The font table. + * @param ct The color Table. + */ + public WseTextRun(String txt, TextStyle t, StyleCatalog sc, + WseFontTable ft, WseColorTable ct) { + + this.sc = sc; + this.ct = ct; + + TextStyle ts = (TextStyle)t.getResolved(); + + if (ts.isSet(TextStyle.BOLD) && ts.getAttribute(TextStyle.BOLD)) + modifiers |= BOLD; + if (ts.isSet(TextStyle.ITALIC) && ts.getAttribute(TextStyle.ITALIC)) + modifiers |= ITALIC; + if (ts.isSet(TextStyle.UNDERLINE) && ts.getAttribute(TextStyle.UNDERLINE)) + modifiers |= UNDERLINE; + if (ts.isSet(TextStyle.STRIKETHRU) && ts.getAttribute(TextStyle.STRIKETHRU)) + modifiers |= STRIKETHRU; + if (ts.isSet(TextStyle.SUPERSCRIPT) && ts.getAttribute(TextStyle.SUPERSCRIPT)) + modifiers |= SUPERSCRIPT; + if (ts.isSet(TextStyle.SUBSCRIPT) && ts.getAttribute(TextStyle.SUBSCRIPT)) + modifiers |= SUBSCRIPT; + + fontSize = (byte)(ts.getFontSize() * 2); + fontName = ts.getFontName(); + fontIndex = (byte)ft.getFontIndex(fontName); + if (fontIndex == -1) { + ft.add(fontName); + fontIndex = (byte)ft.getFontIndex(fontName); + } + + // Figure out the color index. + Color c = t.getFontColor(); + if (c == null) + c = Color.black; + colorIndex = (byte)ct.findColor(c, true); + c = t.getBackgroundColor(); + if (c == null) + c = Color.white; + colorIndex |= (byte)(ct.findColor(c, false) << 4); + + text = txt; + } + + + /** + * Standard constructor for use when going from WordSmith to DOM. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * @param ft The font table. + * @param ct The color table. + */ + public WseTextRun(byte dataArray[], int startIndex, WseFontTable ft, + WseColorTable ct) { + + this.ct = ct; + + startIndex++; // Skip the leading "1" + + int textLen = ((dataArray[startIndex] << 8) + | (dataArray[startIndex+1] & 0xFF)); + startIndex += 2; + + fontIndex = dataArray[startIndex++]; + if (ft != null) + fontName = ft.getFontName(fontIndex); + + fontSize = dataArray[startIndex++]; + + colorIndex = dataArray[startIndex++]; + modifiers = dataArray[startIndex++]; + + text = new String(dataArray, startIndex, textLen); + startIndex += textLen; // skip the text + } + + + /** + * Given a <code>byte</code> sequence, assumed to be a text run, + * compute the index of the first byte past the text run. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index + * + * @return The index of the first <code>byte</code> past the + * text run. + */ + public static int computeNewIndex(byte dataArray[], int startIndex) { + + startIndex++; // Skip the leading "1" + + int textLen = ((dataArray[startIndex] << 8) + | (dataArray[startIndex+1] & 0xFF)); + startIndex += 2; + + startIndex += 4; // skip attributes + // text = new String(dataArray, startIndex, textLen); + startIndex += textLen; // skip the text + return startIndex; + } + + + /** + * Return true if the sequence starting at + * <code>dataArray[startIndex]</code> is a valid text run. + * + * @param dataArray <code>byte</code> array. + * @param startIndex The start index. + * + * @return true if the sequence starting at + * <code>dataArray[startIndex]</code> is a valid + * text run, false otherwise. + */ + public static boolean isValid(byte dataArray[], int startIndex) { + return (dataArray[startIndex] == 1); + } + + /** + * Return the number of bytes needed to represent this text run. + * + * @return The number of bytes needed to represent this text run. + */ + int getByteCount() { + return text.length() + 7; + } + + + /** + * Return an <code>byte</code> array representing this text run. + * + * @return An <code>byte</code> array representing this text run. + */ + byte[] getBytes() { + short textLen = (short)text.length(); + byte b[] = new byte[textLen + 7]; + b[0] = 1; + b[1] = (byte)(textLen >> 8); + b[2] = (byte)(textLen & 0xFF); + b[3] = fontIndex; + b[4] = fontSize; + b[5] = colorIndex; + b[6] = modifiers; + byte[] txtBytes = text.getBytes(); + System.arraycopy(txtBytes, 0, b, 7, textLen); + return b; + } + + + /** + * Return the text of this run. + * + * @return The text of this run. + */ + public String getText() { + return text; + } + + + /** + * Return a <code>TextStyle</code> that reflects the formatting + * of this run. + * + * @return A <code>TextStyle</code> that reflects the formatting + * of this run. + */ + public TextStyle makeStyle() { + int mod = 0; + if ((modifiers & BOLD) != 0) mod |= TextStyle.BOLD; + if ((modifiers & ITALIC) != 0) mod |= TextStyle.ITALIC; + if ((modifiers & UNDERLINE) != 0) mod |= TextStyle.UNDERLINE; + if ((modifiers & STRIKETHRU) != 0) + mod |= TextStyle.STRIKETHRU; + if ((modifiers & SUPERSCRIPT) != 0) mod |= TextStyle.SUPERSCRIPT; + if ((modifiers & SUBSCRIPT) != 0) mod |= TextStyle.SUBSCRIPT; + + int mask = TextStyle.BOLD | TextStyle.ITALIC + | TextStyle.UNDERLINE + | TextStyle.STRIKETHRU | TextStyle.SUPERSCRIPT + | TextStyle.SUBSCRIPT; + + TextStyle x = new TextStyle(null, "text", null, mask, + mod, (int)(fontSize/2), fontName, sc); + + // If color table is available, set the colors. + if (ct != null) { + Color fc = ct.getColor(colorIndex & 0xF, true); + Color bc = ct.getColor(colorIndex >> 4, false); + x.setColors(fc, bc); + } + + return x; + } + + + /** + * Display debug information. + */ + public void dump() { + System.out.print("TEXT RUN: fontIndex = " + fontIndex + + " fontsize = " + fontSize + + " colorIndex = " + colorIndex + + " "); + if ((modifiers & BOLD) != 0) System.out.print("BOLD,"); + if ((modifiers & ITALIC) != 0) System.out.print("ITALIC,"); + if ((modifiers & UNDERLINE) != 0) System.out.print("UNDERLINE,"); + if ((modifiers & STRIKETHRU) != 0) System.out.print("STRIKETHRU,"); + if ((modifiers & SUPERSCRIPT) != 0) System.out.print("SUPERSCRIPT,"); + if ((modifiers & SUBSCRIPT) != 0) System.out.print("SUBSCRIPT,"); + System.out.println("\n" + text); + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/build.xml new file mode 100644 index 000000000000..aa889d4d3f2e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/build.xml @@ -0,0 +1,141 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcxs_wordsmith" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcxs_wordsmith"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../.."/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/sxw/wordsmith"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/DOCConstants.java"/> + <include name="${package}/textRecord.java"/> + <include name="${package}/util.java"/> + <include name="${package}/WSDecoder.java"/> + <include name="${package}/WseColorTable.java"/> + <include name="${package}/WseFontTable.java"/> + <include name="${package}/Wse.java"/> + <include name="${package}/WseHeader.java"/> + <include name="${package}/WSEncoder.java"/> + <include name="${package}/WsePara.java"/> + <include name="${package}/WseTextRun.java"/> + <include name="${package}/DocumentMergerImpl.java"/> + <include name="${package}/DocumentSerializerImpl.java"/> + <include name="${package}/DocumentDeserializerImpl.java"/> + <include name="${package}/ConverterCapabilitiesImpl.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + </javac> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/converter.xml new file mode 100644 index 000000000000..9285730569db --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/converter.xml @@ -0,0 +1,17 @@ +<?xml version="1.0"?> +<converters> + <converter type="staroffice/sxw" version="1.0"> + <converter-display-name> + WordSmith + </converter-display-name> + <converter-description> + StarWriter XML to/from WordSmith conversion + </converter-description> + <converter-vendor>OpenOffice.org</converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.sxw.wordsmith.PluginFactoryImpl + </converter-class-impl> + <converter-target type="application/x-wordsmith" /> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/makefile.mk new file mode 100644 index 000000000000..c64e26894dac --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/makefile.mk @@ -0,0 +1,32 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* +PRJNAME=converter +TARGET=cv_jcsscdcxs_wordsmith +PRJ=../../../../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/textRecord.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/textRecord.java new file mode 100644 index 000000000000..7651767920fc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/textRecord.java @@ -0,0 +1,115 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +import org.openoffice.xmerge.util.Debug; +import java.io.IOException; +import java.io.DataOutputStream; +import java.io.ByteArrayOutputStream; + +/** + * This class represents a single text record in a WordSmith document. + * A record is composed of one or more "WordSmith elements", which + * include: WordSmith header, font table, color table, paragraphs, + * and text runs. + * + * @author David Proulx + */ + +class textRecord { + + java.util.Vector elements; + + + /** + * Default constructor + */ + textRecord() { + elements = new java.util.Vector(10); + } + + + /** + * Add an element + * + * @param elem The element to add + */ + void addElement(Wse elem) { + elements.add(elem); + } + + + /** + * Return the number of bytes needed to represent the current + * contents of this text record. + * + * @return The number of bytes needed to represent the current + * contents of this text record. + */ + int getByteCount() { + int totalBytes = 0; + int nElements = elements.size(); + for (int i = 0; i < nElements; i++) { + Wse e = (Wse)elements.elementAt(i); + totalBytes += e.getByteCount(); + } + return totalBytes; + } + + + /** + * Return the contents of this record as a <code>byte</code> array. + * + * @return the contents of this record as a <code>byte</code> array. + */ + byte[] getBytes() { + DataOutputStream os = null; // Used for storing the data + ByteArrayOutputStream bs = null; // Used for storing the data + byte ftBytes[] = null; + byte ctBytes[] = null; + + try { + bs = new ByteArrayOutputStream(); + os = new DataOutputStream(bs); + int nElements = elements.size(); + for (int i = 0; i < nElements; i++) { + Wse e = (Wse)elements.get(i); + os.write(e.getBytes()); + } + + } catch (IOException e) { + e.printStackTrace(); + } + + if (bs != null) + return bs.toByteArray(); + else + return null; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/util.java b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/util.java new file mode 100644 index 000000000000..0c1af8d5a8ec --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/sxw/wordsmith/util.java @@ -0,0 +1,68 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.sxw.wordsmith; + +/** + * WordSmith utility class. + * + * @author David Proulx + */ +class util { + + /** + * Convert 2 bytes to an integer. + * + * @param data <code>byte</code> data to convert. + * @param index Index to convert. + * + * @return Converted integer. + */ + static int intFrom2bytes(byte[] data, int index) { + return (((data[index] & 0xFF) << 8) + | (data[index+1] & 0xFF)); + + } + + + /** + * Convert 4 bytes to an integer. + * + * @param data <code>byte</code> data to convert. + * @param index Index to convert. + * + * @return Converted integer. + */ + static int intFrom4bytes(byte[] data, int index) { + return (((data[index] & 0xFF) << 24) + | ((data[index + 1] & 0xFF) << 16) + | ((data[index + 2] & 0xFF) << 8) + | (data[index+3] & 0xFF)); + + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/ConverterCapabilitiesImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/ConverterCapabilitiesImpl.java new file mode 100644 index 000000000000..079437336f8e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/ConverterCapabilitiesImpl.java @@ -0,0 +1,93 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * <p>Xslt implementation of <code>ConverterCapabilities</code> for + * the {@link + * org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>Used with StarWriter XML to/from XSLT supported formats conversions. The + * <code>ConverterCapibilies</code> specify which "Office" + * <code>Document</code> tags and attributes are supported on the + * "Device" <code>Document</code> format.</p> + */ +public final class ConverterCapabilitiesImpl + implements ConverterCapabilities { + + public boolean canConvertTag(String tag) { + + if (OfficeConstants.TAG_OFFICE_DOCUMENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_DOCUMENT_CONTENT.equals(tag)) + return true; + else if (OfficeConstants.TAG_OFFICE_BODY.equals(tag)) + return true; + else if (OfficeConstants.TAG_PARAGRAPH.equals(tag)) + return true; + else if (OfficeConstants.TAG_HEADING.equals(tag)) + return true; + else if (OfficeConstants.TAG_ORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_UNORDERED_LIST.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_ITEM.equals(tag)) + return true; + else if (OfficeConstants.TAG_LIST_HEADER.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPAN.equals(tag)) + return true; + else if (OfficeConstants.TAG_HYPERLINK.equals(tag)) + return true; + else if (OfficeConstants.TAG_LINE_BREAK.equals(tag)) + return true; + else if (OfficeConstants.TAG_SPACE.equals(tag)) + return true; + else if (OfficeConstants.TAG_TAB_STOP.equals(tag)) + return true; + + return false; + } + + public boolean canConvertAttribute(String tag, + String attribute) { + + if (OfficeConstants.TAG_SPACE.equals(tag)) { + + if (OfficeConstants.ATTRIBUTE_SPACE_COUNT.equals(attribute)) + return true; + } + + return false; + } +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentDeserializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentDeserializerImpl.java new file mode 100644 index 000000000000..08d294982537 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentDeserializerImpl.java @@ -0,0 +1,254 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; + +import java.io.InputStream; +import java.io.IOException; +import java.util.Enumeration; +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; + + + + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.converter.dom.DOMDocument; +//import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +import org.openoffice.xmerge.converter.xml.xslt.GenericOfficeDocument; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.registry.ConverterInfo; + +// Imported TraX classes +import javax.xml.transform.TransformerFactory; +import javax.xml.transform.Transformer; +import javax.xml.transform.dom.DOMSource; +//import javax.xml.transform.dom.DOMResult; +import javax.xml.transform.TransformerException; +import javax.xml.transform.TransformerConfigurationException; +import javax.xml.transform.stream.StreamResult; +import javax.xml.transform.stream.StreamSource; +import javax.xml.transform.URIResolver; +import javax.xml.transform.Source; + + +// +//import org.apache.xalan.serialize.Serializer; +//import org.apache.xalan.serialize.SerializerFactory; +//import org.apache.xalan.templates.OutputProperties; + +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.DocumentBuilderFactory; + +// Imported java classes +import java.io.FileNotFoundException; + + +/** + * <p>Xslt implementation of + * org.openoffice.xmerge.DocumentSerializer + * for the {@link + * org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>The <code>serialize</code> method transforms the DOM + * document from the given <code>Document</code> object by + * means of a supplied Xsl Stylesheet.</p> + * + * @author Aidan Butler + */ +public final class DocumentDeserializerImpl + implements DocumentDeserializer,URIResolver { + + /** A <code>ConvertData</code> object assigned to this object. */ + private InputStream is = null; + private ConvertData cd = null; + private PluginFactoryImpl pluginFactory = null; + + /** + * Constructor that assigns the given <code>ConvertData</code> + * to this object. + * + * @param pf A <code>PluginFactoryImpl</code> object. + * + * @param cd A <code>ConvertData</code> object to read data for + * the conversion process by the <code>deserialize</code> + * method. + */ + public DocumentDeserializerImpl(PluginFactoryImpl pf,ConvertData cd) { + this.cd = cd; + pluginFactory = pf; + } + + + + /* + * This method performs the xslt transformation on the supplied <code> + * Document</code> and returns a <code>ByteArrayOutputStream</code> object. + * + * Xslt transformation code + * + * @returns baos A <code>ByteArrayOutputStream</code> object containing + * the result of the Xslt transformation. + * @throws TransformerException,TransformerConfigurationException + * , FileNotFoundException,IOException + * + */ + public Document deserialize() throws ConvertException, IOException { + log("\nFound the XSLT deserializer"); + Enumeration enumer = cd.getDocumentEnumeration(); + org.w3c.dom.Document domDoc=null; + DOMDocument docOut=null; + GenericOfficeDocument doc = null; + ByteArrayOutputStream baos =null; + GenericOfficeDocument sxwDoc = new GenericOfficeDocument("output"); + while (enumer.hasMoreElements()) { + docOut = (DOMDocument) enumer.nextElement(); + } + domDoc = docOut.getContentDOM(); + try{ + baos = transform(domDoc); + sxwDoc.initContentDOM(); + DocumentBuilderFactory dFactory = DocumentBuilderFactory.newInstance(); + dFactory.setNamespaceAware(true); + DocumentBuilder dBuilder = dFactory.newDocumentBuilder(); + sxwDoc.setContentDOM(dBuilder.parse(new ByteArrayInputStream(baos.toByteArray()))); + + } + catch(Exception e){ + System.out.println("The following error occurred:"+e); + } + return sxwDoc; + } + + public Source resolve(String href,String base) + throws TransformerException{ + //System.out.println("\nhref "+href+"\nbase "+base); + if (href !=null){ + if(href.equals("javax.xml.transform.dom.DOMSource")|| href.equals("")) + return null; + try{ + ConverterInfo ci = pluginFactory.getConverterInfo(); + String newhRef ="jar:"+ci.getJarName()+"!/"+href; + //System.out.println("\n Looking For "+ newhRef); + StreamSource sheetFile= new StreamSource(newhRef); + return sheetFile; + } + catch (Exception e){ + System.out.println("\nException in Xslt Resolver " +e); + return null; + } + } + else + return null; + } + + /* + * This method performs the xslt transformation on the supplied Dom Tree. + * + * Xslt transformation code + * + * @throws TransformerException,TransformerConfigurationException + * , FileNotFoundException,IOException + * + */ + private ByteArrayOutputStream transform(org.w3c.dom.Document xmlDoc) + throws TransformerException,TransformerConfigurationException + , FileNotFoundException,IOException{ + + log("\nTransforming..."); + ConverterInfo ci = pluginFactory.getConverterInfo(); + ByteArrayOutputStream baos= new ByteArrayOutputStream(); + try{ + DocumentBuilderFactory dFactory = DocumentBuilderFactory.newInstance(); + dFactory.setNamespaceAware(true); + DocumentBuilder dBuilder = dFactory.newDocumentBuilder(); + + String teststr = ci.getXsltDeserial(); + teststr= teststr.substring(0,6); + org.w3c.dom.Document xslDoc=null; + if ((teststr.equals("http:/"))||(teststr.equals("file:/")) + ||(teststr.equals("jar://"))){ + log(ci.getXsltDeserial()); + xslDoc= dBuilder.parse(ci.getXsltDeserial()); + + } + else{ + log(ci.getJarName()+"!/"+ci.getXsltDeserial()); + xslDoc = dBuilder.parse( + "jar:"+ci.getJarName()+"!/"+ci.getXsltDeserial()); + } + + + DOMSource xslDomSource = new DOMSource(xslDoc); + DOMSource xmlDomSource = new DOMSource(xmlDoc); + + //call the tranformer using the XSL, Source and Result dom. + TransformerFactory tFactory = TransformerFactory.newInstance(); + tFactory.setURIResolver(this); + Transformer transformer = tFactory.newTransformer(xslDomSource); + transformer.transform(xmlDomSource,new StreamResult(baos)); + /* + // Serialize for output to standard out + Serializer serializer = SerializerFactory.getSerializer + (OutputProperties.getDefaultMethodProperties("xml")); + serializer.setOutputStream(System.out); + serializer.asDOMSerializer().serialize(xmlDomResult.getNode()); + */ + + log("\n** Transform Complete ***"); + + } + catch (StackOverflowError sOE){ + System.out.println("\nERROR : Stack Overflow Error During Transformation\n Try increasing the stack size by passing the -Xss1m option to the JRE."); + throw sOE; + } + catch(Exception e){ + System.out.println("An error occured in the transformation : "+e); + } + return baos; + } + + /** + * Sends message to the log object. + * + * @param str Debug message. + */ + private void log(String str) { + + Debug.log(Debug.TRACE, str); + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentMergerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentMergerImpl.java new file mode 100644 index 000000000000..a320080a43cb --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentMergerImpl.java @@ -0,0 +1,99 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.w3c.dom.Document; +import org.w3c.dom.Element; + +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.MergeException; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.converter.xml.xslt.GenericOfficeDocument; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.Difference; +import org.openoffice.xmerge.merger.NodeMergeAlgorithm; +import org.openoffice.xmerge.merger.Iterator; +import org.openoffice.xmerge.merger.DiffAlgorithm; +import org.openoffice.xmerge.merger.diff.ParaNodeIterator; +import org.openoffice.xmerge.merger.diff.IteratorLCSAlgorithm; +import org.openoffice.xmerge.merger.merge.DocumentMerge; +import org.openoffice.xmerge.merger.merge.CharacterBaseParagraphMerge; +import org.openoffice.xmerge.util.Debug; + + +/** + * Xslt implementation of <code>DocumentMerger</code> + * for the {@link + * org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl + * PluginFactoryImpl}.</p> + */ +public class DocumentMergerImpl implements DocumentMerger { + + private ConverterCapabilities cc_; + private org.openoffice.xmerge.Document orig = null; + + public DocumentMergerImpl(org.openoffice.xmerge.Document doc, ConverterCapabilities cc) { + cc_ = cc; + this.orig = doc; + } + + public void merge(org.openoffice.xmerge.Document modifiedDoc) throws MergeException { + + GenericOfficeDocument wdoc1 = (GenericOfficeDocument) orig; + GenericOfficeDocument wdoc2 = (GenericOfficeDocument) modifiedDoc; + + Document doc1 = wdoc1.getContentDOM(); + Document doc2 = wdoc2.getContentDOM(); + + Iterator i1 = new ParaNodeIterator(cc_, doc1.getDocumentElement()); + Iterator i2 = new ParaNodeIterator(cc_, doc2.getDocumentElement()); + + DiffAlgorithm diffAlgo = new IteratorLCSAlgorithm(); + + // find out the paragrah level diffs + Difference[] diffTable = diffAlgo.computeDiffs(i1, i2); + + if (Debug.isFlagSet(Debug.INFO)) { + Debug.log(Debug.INFO, "Diff Result: "); + + for (int i = 0; i < diffTable.length; i++) { + Debug.log(Debug.INFO, diffTable[i].debug()); + } + } + + // merge the paragraphs + NodeMergeAlgorithm charMerge = new CharacterBaseParagraphMerge(); + DocumentMerge docMerge = new DocumentMerge(cc_, charMerge); + + Iterator result = null; + + docMerge.applyDifference(i1, i2, diffTable); + } +} + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentSerializerImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentSerializerImpl.java new file mode 100644 index 000000000000..b4b1650f97f6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/DocumentSerializerImpl.java @@ -0,0 +1,309 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.w3c.dom.NodeList; +import org.w3c.dom.Node; +import org.w3c.dom.Element; +import org.w3c.dom.*; + +import java.io.IOException; +import java.io.InputStream; +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import java.util.Enumeration; +import java.util.Properties; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.ConvertException; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.converter.xml.xslt.GenericOfficeDocument; +import org.openoffice.xmerge.converter.dom.DOMDocument; +import org.openoffice.xmerge.util.Debug; +import org.openoffice.xmerge.util.registry.ConverterInfo; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +// Imported TraX classes +import javax.xml.transform.TransformerFactory; +import javax.xml.transform.Transformer; +import javax.xml.transform.stream.StreamSource; +import javax.xml.transform.stream.StreamResult; +import javax.xml.transform.dom.DOMSource; +import javax.xml.transform.dom.DOMResult; +import javax.xml.transform.TransformerException; +import javax.xml.transform.TransformerConfigurationException; +import javax.xml.transform.URIResolver; +import javax.xml.transform.Source; + +// +import org.apache.xalan.serialize.Serializer; +import org.apache.xalan.serialize.SerializerFactory; +import org.apache.xalan.templates.OutputProperties; + +import javax.xml.parsers.DocumentBuilder; +import javax.xml.parsers.DocumentBuilderFactory; + +// Imported java classes +import java.io.FileNotFoundException; +import java.io.File; +import java.net.URI; + +/** + * <p>Xslt implementation of + * org.openoffice.xmerge.DocumentSerializer + * for the {@link + * org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl + * PluginFactoryImpl}.</p> + * + * <p>The <code>serialize</code> method transforms the DOM + * document from the given <code>Document</code> object by + * means of a supplied Xsl Stylesheet.</p> + * + * @author Aidan Butler + */ + + +public final class DocumentSerializerImpl + implements DocumentSerializer,OfficeConstants,URIResolver { + + + /** SXW <code>Document</code> object that this converter processes. */ + private GenericOfficeDocument sxwDoc = null; + + private PluginFactoryImpl pluginFactory = null; + + /** + * Constructor. + * + * @param pf A <code>PluginFactoryImpl</code> + * @param doc A SXW <code>Document</code> to be converted. + */ + public DocumentSerializerImpl(PluginFactoryImpl pf,Document doc) { + pluginFactory=pf; + sxwDoc = (GenericOfficeDocument) doc; + } + + + /** + * Method to convert a <code>Document</code> with an xsl stylesheet. + * It creates a <code>Document</code> object, which is then transformed + * with the Xslt processer. A <code>ConvertData </code> object is + * constructed and returned. + * + * @returns cd A <code>ConvertData</code> object. + * @throws ConvertException If any I/O error occurs. + * @throws IOException If any I/O error occurs. + */ + public ConvertData serialize() throws ConvertException, IOException { + String docName = sxwDoc.getName(); + org.w3c.dom.Document domDoc = sxwDoc.getContentDOM(); + org.w3c.dom.Document metaDoc = sxwDoc.getMetaDOM(); + org.w3c.dom.Document styleDoc = sxwDoc.getStyleDOM(); + ByteArrayOutputStream baos= new ByteArrayOutputStream(); + ConvertData cd = new ConvertData(); + Node offnode = (Node)domDoc.getDocumentElement(); + if (!(offnode.getNodeName()).equals("office:document")){ + try{ + DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance(); + DocumentBuilder builder= builderFactory.newDocumentBuilder(); + DOMImplementation domImpl = builder.getDOMImplementation(); + DocumentType docType =domImpl.createDocumentType("office:document","-//OpenOffice.org//DTD OfficeDocument 1.0//EN",null); + org.w3c.dom.Document newDoc = domImpl.createDocument("http://openoffice.org/2000/office","office:document",docType); + + + Element rootElement=newDoc.getDocumentElement(); + rootElement.setAttribute("xmlns:office","http://openoffice.org/2000/office"); + rootElement.setAttribute("xmlns:style","http://openoffice.org/2000/style" ); + rootElement.setAttribute("xmlns:text","http://openoffice.org/2000/text"); + rootElement.setAttribute("xmlns:table","http://openoffice.org/2000/table"); + + rootElement.setAttribute("xmlns:draw","http://openoffice.org/2000/drawing"); + rootElement.setAttribute("xmlns:fo","http://www.w3.org/1999/XSL/Format" ); + rootElement.setAttribute("xmlns:xlink","http://www.w3.org/1999/xlink" ); + rootElement.setAttribute("xmlns:dc","http://purl.org/dc/elements/1.1/" ); + rootElement.setAttribute("xmlns:meta","http://openoffice.org/2000/meta" ); + rootElement.setAttribute("xmlns:number","http://openoffice.org/2000/datastyle" ); + rootElement.setAttribute("xmlns:svg","http://www.w3.org/2000/svg" ); + rootElement.setAttribute("xmlns:chart","http://openoffice.org/2000/chart" ); + rootElement.setAttribute("xmlns:dr3d","http://openoffice.org/2000/dr3d" ); + rootElement.setAttribute("xmlns:math","http://www.w3.org/1998/Math/MathML" ); + rootElement.setAttribute("xmlns:form","http://openoffice.org/2000/form" ); + rootElement.setAttribute("xmlns:script","http://openoffice.org/2000/script" ); + rootElement.setAttribute("xmlns:config","http://openoffice.org/2001/config" ); + rootElement.setAttribute("office:class","text" ); + rootElement.setAttribute("office:version","1.0"); + + + NodeList nodeList; + Node tmpNode; + Node rootNode = (Node)rootElement; + if (metaDoc !=null){ + nodeList= metaDoc.getElementsByTagName(TAG_OFFICE_META); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + } if (styleDoc !=null){ + nodeList= styleDoc.getElementsByTagName(TAG_OFFICE_STYLES); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + }if (domDoc !=null){ + nodeList= domDoc.getElementsByTagName(TAG_OFFICE_AUTOMATIC_STYLES); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + nodeList= domDoc.getElementsByTagName(TAG_OFFICE_BODY); + if (nodeList.getLength()>0){ + tmpNode = newDoc.importNode(nodeList.item(0),true); + rootNode.appendChild(tmpNode); + } + } + domDoc=newDoc; + }catch(Exception e){ + System.out.println("\nAn Exception occurred with Xslt Serializer"+e); + } + + } + + try{ + baos=transform(domDoc); + } + catch (Exception e){ + System.out.println("\n Error with Xslt\n"); + } + + String ext = pluginFactory.getDeviceFileExtension(); + DOMDocument resultDomDoc=(DOMDocument)pluginFactory.createDeviceDocument(docName,new ByteArrayInputStream(baos.toByteArray())); + cd.addDocument (resultDomDoc); + return cd; + } + + public Source resolve(String href,String base) + throws TransformerException{ + //System.out.println("\nhref "+href+"\nbase "+base); + if (href !=null){ + if(href.equals("javax.xml.transform.dom.DOMSource")|| href.equals("")) + return null; + try{ + ConverterInfo ci = pluginFactory.getConverterInfo(); + String newhRef ="jar:"+ci.getJarName()+"!/"+href; + //System.out.println("\n Looking For "+ newhRef); + StreamSource sheetFile= new StreamSource(newhRef); + return sheetFile; + } + catch (Exception e){ + System.out.println("\nException in Xslt Resolver " +e); + return null; + } + } + else + return null; + } + + + /* + * This method performs the sxl transformation on the supplied <code> + * Document</code> and returns a <code>DOMResult</code> object. + * + * Xslt transformation code + * + * @returns baos A <code>ByteArrayOutputStream</code> object containing + * the result of the Xslt transformation. + * @throws TransformerException,TransformerConfigurationException + * , FileNotFoundException,IOException + * + */ + + + private ByteArrayOutputStream transform(org.w3c.dom.Document domDoc) + throws TransformerException,TransformerConfigurationException + , FileNotFoundException,IOException{ + //System.out.println("\nTransforming..."); + ConverterInfo ci = pluginFactory.getConverterInfo(); + //DOMResult xmlDomResult = new DOMResult(); + ByteArrayOutputStream baos= new ByteArrayOutputStream(); + try{ + + DocumentBuilderFactory dFactory = DocumentBuilderFactory.newInstance(); + dFactory.setNamespaceAware(true); + + DocumentBuilder dBuilder = dFactory.newDocumentBuilder(); + String teststr = ci.getXsltSerial(); + + teststr= teststr.substring(0,6); + org.w3c.dom.Document xslDoc=null; + if ((teststr.equals("http:/"))||(teststr.equals("file:/")) + ||(teststr.equals("jar://"))){ + System.out.println(ci.getXsltSerial()); + xslDoc= dBuilder.parse(ci.getXsltSerial()); + + } + else{ + //System.out.println(ci.getJarName()+"!/"+ci.getXsltSerial()); + xslDoc = dBuilder.parse( + "jar:"+ci.getJarName()+"!/"+ci.getXsltSerial()); + } + + DOMSource xslDomSource = new DOMSource(xslDoc); + DOMSource xmlDomSource = new DOMSource(domDoc); + + //call the tranformer using the XSL, Source and Result. + TransformerFactory tFactory = TransformerFactory.newInstance(); + tFactory.setURIResolver(this); + Transformer transformer = tFactory.newTransformer(xslDomSource); + + transformer.transform(xmlDomSource, new StreamResult(baos)); + + /* + transformer.transform(xmlDomSource, xmlDomResult); //Removed this impl because the DocType was not being written out + + // Serialize for output to standard out + Serializer serializer = SerializerFactory.getSerializer + (OutputProperties.getDefaultMethodProperties("xml")); + //serializer.setOutputStream(System.out); + serializer.setOutputStream(baos); + serializer.asDOMSerializer().serialize(xmlDomResult.getNode()); + //serializer.asDOMSerializer().serialize(xmlDomSource.getNode()); + + + //System.out.println("\n** Transform Complete ***"); + */ + } + catch(Exception e){ + System.out.println("An error occured in the transformation : "+e); + } + return baos; + } + + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/GenericOfficeDocument.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/GenericOfficeDocument.java new file mode 100644 index 000000000000..d2b98819c87a --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/GenericOfficeDocument.java @@ -0,0 +1,95 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.w3c.dom.Document; +import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.OfficeConstants; + +/** + * This class is an implementation of <code>OfficeDocument</code> for + * the generic office format. + */ +public class GenericOfficeDocument extends OfficeDocument { + + /** + * Constructor with arguments to set <code>name</code>. + * + * @param name The name of the <code>Document</code> + */ + public GenericOfficeDocument(String name) { + super(name); + } + + + /** + * Constructor with arguments to set <code>name</code>, the + * <code>namespaceAware</code> flag, and the <code>validating</code> + * flag. + * + * @param name The name of the <code>Document</code>. + * @param namespaceAware The value of the <code>namespaceAware</code> + * flag. + * @param validating The value of the <code>validating</code> flag. + */ + public GenericOfficeDocument(String name, boolean namespaceAware, boolean validating) { + + super(name, namespaceAware, validating); + } + + /** + * Returns the Office file extension for the generic format. + * + * @return The Office file extension for the generic format. + */ + protected String getFileExtension() { + return ""; + } + + /** + * Returns the Office attribute for the generic format. + * + * @return The Office attribute for the generic format. + */ + protected String getOfficeClassAttribute() { + + return ""; + } + + /** + * Method to return the MIME type of the document. + * + * @return String The document's MIME type. + */ + protected String getDocumentMimeType() { + /* TODO: Determine the MIME-type from the input. */ + return ""; + } + +} + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/PluginFactoryImpl.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/PluginFactoryImpl.java new file mode 100644 index 000000000000..cb3a9c507b82 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/PluginFactoryImpl.java @@ -0,0 +1,204 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +package org.openoffice.xmerge.converter.xml.xslt; + +import org.openoffice.xmerge.Document; +import org.openoffice.xmerge.ConvertData; +import org.openoffice.xmerge.DocumentSerializer; +import org.openoffice.xmerge.DocumentSerializerFactory; +import org.openoffice.xmerge.DocumentDeserializer; +import org.openoffice.xmerge.DocumentDeserializerFactory; +import org.openoffice.xmerge.PluginFactory; +import org.openoffice.xmerge.converter.dom.DOMDocument; +//import org.openoffice.xmerge.converter.xml.sxw.SxwDocument; +//import org.openoffice.xmerge.converter.xml.OfficeDocument; +import org.openoffice.xmerge.converter.xml.xslt.GenericOfficeDocument; +import org.openoffice.xmerge.util.registry.ConverterInfo; +import org.openoffice.xmerge.DocumentMerger; +import org.openoffice.xmerge.DocumentMergerFactory; +import org.openoffice.xmerge.ConverterCapabilities; +import org.openoffice.xmerge.util.registry.ConverterInfo; + +import java.io.InputStream; +import java.util.Enumeration; +import java.io.InputStream; +import java.io.IOException; +import java.util.Properties; + +/** + * <p>Xslt implementation of the <code>PluginFactory</code>. + * This encapsulates conversion of StarWriter XML format to and from + * a supported format.</p> + * + * <p>The superclass produces a particular + * {@link org.openoffice.xmerge.Document Document} + * object, i.e. {@link + * org.openoffice.xmerge.converter.xml.sxw.SxwDocument + * SxwDocument} that the converters in this class work with. Thus, + * this class only implements the methods that produces the converters, + * i.e. {@link + * org.openoffice.xmerge.DocumentSerializer + * DocumentSerializer} and {@link + * org.openoffice.xmerge.DocumentDeserializer + * DocumentDeserializer}</p> + * + * @author Aidan Butler + */ +public final class PluginFactoryImpl extends PluginFactory + implements DocumentDeserializerFactory, DocumentSerializerFactory, DocumentMergerFactory +{ + + public PluginFactoryImpl (ConverterInfo ci) { + super(ci); + } + + /** ConverterCapabilities object for this type of conversion. */ + private final static ConverterCapabilities converterCap = + new ConverterCapabilitiesImpl(); + + + /** + * Returns an instance of <code>DocumentSerializerImpl</code>, + * which is an implementation of the <code>DocumentSerializer</code> + * interface. + * + * @param doc <code>Document</code> object to be + * converted/serialized. + * + * @return A <code>DocumentSerializerImpl</code> object. + */ + public DocumentSerializer createDocumentSerializer(Document doc) { + return new DocumentSerializerImpl(this,doc); + } + + + /** + * Returns an instance of <code>DocumentDeserializerImpl</code>, + * which is an implementation of the <code>DocumentDeserializer</code> + * interface. + * + * @param is <code>ConvertData</code> object. + * + * @return A DocumentDeserializerImpl object. + */ + public DocumentDeserializer createDocumentDeserializer(ConvertData cd) { + + return new DocumentDeserializerImpl(this,cd); + } + + public org.openoffice.xmerge.Document createDeviceDocument(java.lang.String str, java.io.InputStream inputStream) throws java.io.IOException { + String ext = this.getDeviceFileExtension(); + DOMDocument domDoc = new DOMDocument(str,ext); + domDoc.read(inputStream); + return domDoc; + } + + + public Document createOfficeDocument(String name, InputStream is) + throws IOException { + + // read zipped XML stream + GenericOfficeDocument doc = new GenericOfficeDocument(name); + doc.read(is); + return doc; + } + + public Document createOfficeDocument(String name, InputStream is,boolean isZip) + throws IOException { + + // read zipped XML stream + GenericOfficeDocument doc = new GenericOfficeDocument(name); + doc.read(is,isZip); + return doc; + } + + /** + * Returns a <code>String</code> containing the file extension of a + * <code>Document</code>. This method uses a properties file to determine + * a mapping from the device mime in the <code>ConverterInfo</code> to a + * particular file extension. If a mapping is not specified, the default + * is ".txt". + * + * @return <code>String</code>. + */ + + + public String getDeviceFileExtension(){ + Class c = this.getClass(); + InputStream is = c.getResourceAsStream("XsltPlugin.properties"); + Properties props = new Properties(); + String ext= ".txt"; + String mimeType = null; + ConverterInfo ci = this.getConverterInfo(); + Enumeration enumer = ci.getDeviceMime(); + while (enumer.hasMoreElements()) { + mimeType= (String) enumer.nextElement(); + } + try { + props.load(is); + + String info = props.getProperty(mimeType); + if (info != null) { + ext = info; + } + } catch (Exception e) { + + // It is okay for the property file to not exist. + // + } + return ext; + } + + /** + * Returns an instance of <code>DocumentMergerImpl</code>, + * which is an implementation of the <code>DocumentMerger</code> + * interface. + * + * @param doc <code>Document</code> to merge. + * + * @return A DocumentMergerImpl object. + */ + public DocumentMerger createDocumentMerger(Document doc) { + ConverterCapabilities cc = converterCap; + DocumentMergerImpl merger = new DocumentMergerImpl(doc, cc); + return merger; + + } + +} + + + + + + + + + + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/XsltPlugin.properties b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/XsltPlugin.properties new file mode 100644 index 000000000000..32f3771fc492 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/XsltPlugin.properties @@ -0,0 +1,36 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* + + +# +# XsltPlugin.properties +# + +#This file allows users to specify the mime-type to file extension mappings + +# e.g text/html=.html +text/html=.html diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/build.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/build.xml new file mode 100644 index 000000000000..43db663b2820 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/build.xml @@ -0,0 +1,136 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<project name="xmrg_jooxcx_xslt" default="main" basedir="."> + + <!-- ================================================================= --> + <!-- settings --> + <!-- ================================================================= --> + + <!-- project prefix, used for targets and build.lst --> + <property name="prj.prefix" value="xmrg"/> + + <!-- name of this sub target used in recursive builds --> + <property name="target" value="xmrg_jooxcx_xslt"/> + + <!-- relative path to project directory --> + <property name="prj" value="../../../../../../../"/> + + <!-- start of java source code package structure --> + <property name="java.dir" value="${prj}/java"/> + + <!-- path component for current java package --> + <property name="package" + value="org/openoffice/xmerge/converter/xml/xslt/"/> + + <!-- define how to handle CLASSPATH environment --> + <property name="build.sysclasspath" value="ignore"/> + + <!-- classpath settings for javac tasks --> + <path id="classpath"> + <pathelement location="${build.class}"/> + <pathelement location="${solar.jar}/xalan.jar"/> + <pathelement location="${solar.jar}/parser.jar"/> + <pathelement location="${solar.jar}/jaxp.jar"/> + <pathelement location="${solar.jar}/xerces.jar"/> + </path> + + <!-- set wether we want to compile with or without deprecation --> + <property name="deprecation" value="on"/> + + <!-- ================================================================= --> + <!-- solar build environment targets --> + <!-- ================================================================= --> + + <target name="build_dir" unless="build.dir"> + <property name="build.dir" value="${out}"/> + </target> + + <target name="solar" depends="build_dir" if="solar.update"> + <property name="solar.properties" + value="${solar.bin}/solar.properties"/> + </target> + + <target name="init" depends="solar"> + <property name="build.compiler" value="classic"/> + <property file="${solar.properties}"/> + <property file="${build.dir}/class/solar.properties"/> + </target> + + <target name="info"> + <echo message="--------------------"/> + <echo message="${target}"/> + <echo message="--------------------"/> + </target> + + + <!-- ================================================================= --> + <!-- custom targets --> + <!-- ================================================================= --> + + <!-- the main target, called in recursive builds --> + <target name="main" depends="info,prepare,compile"/> + + <!-- prepare output directories --> + <target name="prepare" depends="init" if="build.class"> + <mkdir dir="${build.dir}"/> + <mkdir dir="${build.class}"/> + </target> + + <!-- compile java sources in ${package} --> + <target name="compile" depends="prepare" if="build.class"> + <javac srcdir="${java.dir}" + destdir="${build.class}" + debug="${debug}" + deprecation="${deprecation}" + optimize="${optimize}"> + <classpath refid="classpath"/> + <include name="${package}/DocumentDeserializerImpl.java"/> + <include name="${package}/DocumentSerializerImpl.java"/> + <include name="${package}/GenericOfficeDocument.java"/> + <include name="${package}/PluginFactoryImpl.java"/> + </javac> + <copy todir="${build.class}/${package}"> + <fileset dir="."> + <include name="*.properties"/> + </fileset> + </copy> + </target> + + <!-- clean up --> + <target name="clean" depends="prepare"> + <delete includeEmptyDirs="true"> + <fileset dir="${build.class}"> + <patternset> + <include name="${package}/*.class"/> + </patternset> + </fileset> + </delete> + </target> + +</project> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/converter.xml b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/converter.xml new file mode 100644 index 000000000000..3baf857406ca --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/converter.xml @@ -0,0 +1,50 @@ +<?xml version="1.0"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<!--<!DOCTYPE converters SYSTEM "converter.dtd">--> +<converters> + <converter type="staroffice/sxw" version="1.0"> + <converter-display-name> + XSLT Transformation + </converter-display-name> + <converter-description> + Converter which performs xslt transformations + </converter-description> + <converter-vendor>OpenOffice.org</converter-vendor> + <converter-class-impl> + org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl + </converter-class-impl> + <converter-xslt-serialize> + sofftohtml.xsl + </converter-xslt-serialize> + <converter-xslt-deserialize> + htmltosoff.xsl + </converter-xslt-deserialize> + <converter-target type="text/html" /> + </converter> +</converters> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/DBFilter.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/DBFilter.java new file mode 100644 index 000000000000..eae4a03c5bc6 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/DBFilter.java @@ -0,0 +1,570 @@ +/************************************************************************ + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ + +//Standard Java classes +import java.util.Enumeration; +import java.util.Vector; +import java.io.InputStream; +import java.io.FileInputStream; +import java.io.FileOutputStream; +import java.io.ByteArrayOutputStream; +import java.io.ByteArrayInputStream; +import com.sun.star.xml.XImportFilter; +import com.sun.star.xml.XExportFilter; +import java.io.*; +import java.util.regex.*; + +// Imported TraX classes +import javax.xml.transform.TransformerFactory; +import javax.xml.transform.Transformer; +import javax.xml.transform.dom.DOMSource; +import javax.xml.transform.TransformerException; +import javax.xml.transform.TransformerConfigurationException; +import javax.xml.transform.stream.StreamResult; +import javax.xml.transform.stream.StreamSource; +import javax.xml.transform.URIResolver; +import javax.xml.transform.Source; +import javax.xml.transform.TransformerException; +import javax.xml.transform.TransformerConfigurationException; +import javax.xml.transform.OutputKeys; + +//StarOffice Interfaces and UNO +import com.sun.star.uno.AnyConverter; +import com.sun.star.lang.XInitialization; +import com.sun.star.lang.XMultiServiceFactory; +import com.sun.star.lang.XServiceInfo; +import com.sun.star.lang.XTypeProvider; +import com.sun.star.uno.Type; +import com.sun.star.uno.UnoRuntime; +import com.sun.star.comp.loader.FactoryHelper; +import com.sun.star.lang.XServiceName; +import com.sun.star.lang.XSingleServiceFactory; +import com.sun.star.registry.XRegistryKey; +import com.sun.star.frame.XConfigManager; +import com.sun.star.xml.sax.InputSource; +import com.sun.star.xml.sax.XParser; +import com.sun.star.io.XInputStream; +import com.sun.star.io.XOutputStream; +import com.sun.star.xml.sax.XDocumentHandler; + +//Uno to java Adaptor +import com.sun.star.lib.uno.adapter.*; + +/** This outer class provides an inner class to implement the service + * description, a method to instantiate the + * component on demand (__getServiceFactory()), and a method to give + * information about the component (__writeRegistryServiceInfo()). + */ +public class DBFilter { + + + private static XMultiServiceFactory xMSF; + + /** This inner class provides the component as a concrete implementation + * of the service description. It implements the needed interfaces. + * @implements XTypeProvider + */ + public static class _DBFilter implements + XImportFilter, + XExportFilter, + XServiceName, + XServiceInfo, + XDocumentHandler, + XTypeProvider { + + private boolean indent; + private XInputStream xInStream; + private XOutputStream xOutStream; + private XOutputStream xos; + private String sExportStyleSheet; + private String doctype_public; + private String doctype_system; + + public _DBFilter() + { + indent = false; + xInStream = null; + xOutStream = null; + xos = null; + sExportStyleSheet = null; + doctype_public = null; + doctype_system = null; + } + + /** The component will be registered under this name. + */ + static private final String __serviceName = "com.sun.star.documentconversion.DBFilter"; + + public com.sun.star.uno.Type[] getTypes() { + Type[] typeReturn = {}; + + try { + typeReturn = new Type[] { + new Type( XTypeProvider.class ), + new Type( XExportFilter.class ), + new Type( XImportFilter.class ), + new Type( XServiceName.class ), + new Type( XServiceInfo.class ) }; + } + catch( Exception exception ) { + + } + + return( typeReturn ); + } + + + public boolean importer(com.sun.star.beans.PropertyValue[] aSourceData, + com.sun.star.xml.sax.XDocumentHandler xDocHandler, + java.lang.String[] msUserData) throws com.sun.star.uno.RuntimeException,com.sun.star.lang.IllegalArgumentException { + /* + System.out.println("\nFound the Java Importer!\n"); + + System.out.println("\n"+msUserData[0]); + System.out.println("\n"+msUserData[1]); + System.out.println("\n"+msUserData[2]); + System.out.println("\n"+msUserData[3]); + System.out.println("\n"+xDocHandler); + System.out.println("\n"+msUserData[4]); + System.out.println("\n"+msUserData[5]); + */ + String sFileName=null; + String udImport =msUserData[2]; + String sImportStyleSheet =msUserData[4]; + sExportStyleSheet =msUserData[5]; + com.sun.star.io.XInputStream xis=null; + com.sun.star.beans.PropertyValue[] pValue = aSourceData; + + for (int i = 0 ; i < pValue.length; i++) + { + try{ + //System.out.println("\n"+pValue[i].Name+" "+pValue[i].Value); + if (pValue[i].Name.compareTo("InputStream")==0){ + xis=(com.sun.star.io.XInputStream)AnyConverter.toObject(new Type(com.sun.star.io.XInputStream.class), pValue[i].Value); + } + else if (pValue[i].Name.compareTo("FileName")==0){ + sFileName=(String)AnyConverter.toObject(new Type(java.lang.String.class), pValue[i].Value); + } + else if (pValue[i].Name.compareTo("Indent")==0){ //to be changed to new value for indentation from XSLT UI + indent=(boolean)AnyConverter.toBoolean(pValue[i].Value); + } + else if (pValue[i].Name.compareTo("DocType_Public")==0){ + doctype_public = AnyConverter.toString(pValue[i].Value); + } + else if (pValue[i].Name.compareTo("DocType_System")==0){ + doctype_system = AnyConverter.toString(pValue[i].Value); + } } + catch(com.sun.star.lang.IllegalArgumentException AnyExec){ + System.out.println("\nIllegalArgumentException "+AnyExec); + } + + } + + try{ + + Object xCfgMgrObj=xMSF.createInstance("com.sun.star.config.SpecialConfigManager"); + XConfigManager xCfgMgr = (XConfigManager) UnoRuntime.queryInterface( + XConfigManager.class , xCfgMgrObj ); + String PathString=xCfgMgr.substituteVariables("$(progurl)" ); + PathString= PathString.concat("/"); + Object xPipeObj=xMSF.createInstance("com.sun.star.io.Pipe"); + xInStream = (XInputStream) UnoRuntime.queryInterface( + XInputStream.class , xPipeObj ); + xOutStream = (XOutputStream) UnoRuntime.queryInterface( + XOutputStream.class , xPipeObj ); + if (!sImportStyleSheet.equals("")){ + if (!sImportStyleSheet.startsWith("file:")&&!sImportStyleSheet.startsWith("http:") + &&!sExportStyleSheet.startsWith("shttp:") + &&!sExportStyleSheet.startsWith("jar:")){ + sImportStyleSheet=PathString.concat(sImportStyleSheet); + } + } + convert (xis,xOutStream,sImportStyleSheet,true); + xOutStream.closeOutput(); + Object xSaxParserObj=xMSF.createInstance("com.sun.star.xml.sax.Parser"); + XParser xParser = (XParser) UnoRuntime.queryInterface( + XParser.class , xSaxParserObj ); + InputSource aInput = new InputSource(); + if (sFileName==null) + sFileName=" "; + aInput.sSystemId = sFileName; + aInput.aInputStream =xInStream; + xParser.setDocumentHandler ( xDocHandler ); + xParser.parseStream ( aInput ); + xInStream.closeInput(); + + } + catch (Exception AnyExec){ + //e.printStackTrace(); + System.out.println("\nException "+AnyExec); + throw new com.sun.star.uno.RuntimeException(AnyExec.getMessage()); + } + return true; + } + + + + public boolean exporter(com.sun.star.beans.PropertyValue[] aSourceData, + java.lang.String[] msUserData) throws com.sun.star.uno.RuntimeException,com.sun.star.lang.IllegalArgumentException { + /* + System.out.println("\nFound the Exporter!\n"); + + System.out.println("\n0"+msUserData[0]); + System.out.println("\n1"+msUserData[1]); + System.out.println("\n2"+msUserData[2]); + System.out.println("\n3"+msUserData[3]); + + System.out.println("\n4"+msUserData[4]); + System.out.println("\n5"+msUserData[5]); + */ + String udImport =msUserData[2]; + sExportStyleSheet =msUserData[5]; + com.sun.star.beans.PropertyValue[] pValue = aSourceData; + for (int i = 0 ; i < pValue.length; i++) + { + try{ + //System.out.println("\n"+pValue[i].Name+" "+pValue[i].Value); + if (pValue[i].Name.compareTo("OutputStream")==0){ + xos=(com.sun.star.io.XOutputStream)AnyConverter.toObject(new Type(com.sun.star.io.XOutputStream.class), pValue[i].Value); + // System.out.println(pValue[i].Name+" "+xos); + } + else if (pValue[i].Name.compareTo("Indent")==0){ //to be changed to new value for indentation from XSLT UI + indent=(boolean)AnyConverter.toBoolean(pValue[i].Value); + } + else if (pValue[i].Name.compareTo("DocType_Public")==0){ + doctype_public = AnyConverter.toString(pValue[i].Value); + } + else if (pValue[i].Name.compareTo("DocType_System")==0){ + doctype_system = AnyConverter.toString(pValue[i].Value); + } + + } + catch(com.sun.star.lang.IllegalArgumentException AnyExec){ + System.out.println("\nIllegalArgumentException "+AnyExec); + } + } + + + try{ + + Object xCfgMgrObj=xMSF.createInstance("com.sun.star.config.SpecialConfigManager"); + XConfigManager xCfgMgr = (XConfigManager) UnoRuntime.queryInterface( + XConfigManager.class , xCfgMgrObj ); + + String PathString=xCfgMgr.substituteVariables("$(progurl)" ); + PathString= PathString.concat("/"); + Object xPipeObj=xMSF.createInstance("com.sun.star.io.Pipe"); + xInStream = (XInputStream) UnoRuntime.queryInterface( + XInputStream.class , xPipeObj ); + xOutStream = (XOutputStream) UnoRuntime.queryInterface( + XOutputStream.class , xPipeObj ); + if (!sExportStyleSheet.equals("")){ + if (!sExportStyleSheet.startsWith("file:")&&!sExportStyleSheet.startsWith("http:") + &&!sExportStyleSheet.startsWith("shttp:") + &&!sExportStyleSheet.startsWith("jar:")){ + sExportStyleSheet=PathString.concat(sExportStyleSheet); + } + } + } + catch (Exception AnyExec){ + System.out.println("Exception "+AnyExec); + throw new com.sun.star.uno.RuntimeException(AnyExec.getMessage()); + } + return true; + } + + public String replace(String origString, String origChar, String replaceChar){ + String tmp=""; + int index=origString.indexOf(origChar); + if(index !=-1){ + while (index !=-1){ + String first =origString.substring(0,index); + first=first.concat(replaceChar); + tmp=tmp.concat(first); + origString=origString.substring(index+1,origString.length()); + index=origString.indexOf(origChar); + if(index==-1) { + tmp=tmp.concat(origString); + } + } + } + return tmp; + } + + public String needsMask(String origString){ + + if (origString.indexOf("&")!=-1){ + origString=replace(origString,"&","&"); + } + if (origString.indexOf("\"")!=-1){ + origString=replace(origString,"\"","""); + } + if (origString.indexOf("<")!=-1){ + origString=replace(origString,"<","<"); + } + if (origString.indexOf(">")!=-1){ + origString=replace(origString,">",">"); + } + return origString; + } + + + + public void startDocument (){ + } + + public void endDocument() + { + convert (xInStream,xos,sExportStyleSheet,false); + } + + public void startElement (String str, com.sun.star.xml.sax.XAttributeList xattribs) + { + + str="<".concat(str); + if (xattribs !=null) + { + str= str.concat(" "); + int len=xattribs.getLength(); + for (short i=0;i<len;i++) + { + str=str.concat(xattribs.getNameByIndex(i)); + str=str.concat("=\""); + //str=str.concat(xattribs.getValueByIndex(i)); + str=str.concat(needsMask(xattribs.getValueByIndex(i))); + str=str.concat("\" "); + } + } + str=str.concat(">"); + //System.out.println(str); + try{ + //xOutStream.writeBytes(str.getBytes()); + xOutStream.writeBytes(str.getBytes("UTF-8")); + } + catch (Exception e){ + System.out.println("\n"+e); + } + + } + + public void endElement(String str){ + str="</".concat(str); + str=str.concat(">"); + str=str.concat("\n"); + try{ + xOutStream.writeBytes(str.getBytes("UTF-8")); + } + catch (Exception e){ + System.out.println("\n"+e); + } + // System.out.println(str); + + } + public void characters(String str){ + str=needsMask(str); + try{ + xOutStream.writeBytes(str.getBytes("UTF-8")); + } + catch (Exception e){ + System.out.println("\n"+e); + } + + } + + public void ignorableWhitespace(String str){ + + + } + public void processingInstruction(String aTarget, String aData){ + + } + + public void setDocumentLocator(com.sun.star.xml.sax.XLocator xLocator){ + + } + + private String maskEntities(String xmlString){ + Pattern testpattern = Pattern.compile("<!ENTITY [a-zA-Z0-9#]* "); + Matcher testmatch= testpattern.matcher(xmlString); + //System.out.println("\nStarting replace"); + int offset=0; + while (testmatch.find(offset)){ + String newstring = xmlString.substring(testmatch.start()+9,testmatch.end()-1); + offset= testmatch.end(); + //System.out.println("\nReplacing " +newstring); + + xmlString=xmlString.replaceAll("&"+newstring+";","<entity name=\""+newstring+"\">"+"&"+newstring+";"+"</entity>"); + testmatch = testmatch.reset(); + testmatch= testpattern.matcher(xmlString); + //System.out.println("\nFound Pattern "+testmatch.replaceFirst("<entity>"+newstring+"</entity>")); + newstring= ""; + } + return xmlString; + } + + public void convert (com.sun.star.io.XInputStream xml, + com.sun.star.io.XOutputStream device,String sStyleSheet,boolean importing ) throws com.sun.star.uno.RuntimeException { + XInputStreamToInputStreamAdapter xis =new XInputStreamToInputStreamAdapter(xml); + XOutputStreamToOutputStreamAdapter xos = + new XOutputStreamToOutputStreamAdapter(device); + ByteArrayOutputStream baos = new ByteArrayOutputStream(); + String xmlFile=null; + try{ + //call the tranformer using the XSL, Source and Result dom. + TransformerFactory tFactory = TransformerFactory.newInstance(); + //tFactory.setURIResolver(this); + Transformer transformer =null; + transformer = tFactory.newTransformer( new StreamSource(sStyleSheet)); + if(indent){ // required for displaying XML correctly in XSLT UI + transformer.setOutputProperty("indent", "yes"); + transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "1"); + } + if(null != doctype_public){ + transformer.setOutputProperty(OutputKeys.DOCTYPE_PUBLIC, doctype_public); + } + if(null != doctype_system){ + transformer.setOutputProperty(OutputKeys.DOCTYPE_SYSTEM, doctype_system); + } + if (importing) + { + byte tmpArr[]=new byte[1000]; + while (xis.available()>0){ + int read = xis.read(tmpArr); + baos.write(tmpArr,0,read); + tmpArr =new byte[1000]; + } + xmlFile = maskEntities(baos.toString("UTF-8")); + + //xmlFile = baos.toString("UTF-8"); + if (xmlFile.indexOf("<!DOCTYPE")!=-1){ + String tag= xmlFile.substring(xmlFile.lastIndexOf("/")+1,xmlFile.lastIndexOf(">")); + String entities = ""; + if(xmlFile.indexOf("[",xmlFile.indexOf("<!DOCTYPE"))!=-1){ + if(xmlFile.indexOf("[",xmlFile.indexOf("<!DOCTYPE")) < xmlFile.indexOf(">",xmlFile.indexOf("<!DOCTYPE"))){ + entities = xmlFile.substring(xmlFile.indexOf("[",xmlFile.indexOf("<!DOCTYPE")),xmlFile.indexOf("]",xmlFile.indexOf("<!DOCTYPE"))+1); + } + } + String newDocType = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<!DOCTYPE "+tag+" "+entities+">"; + xmlFile= xmlFile.substring(xmlFile.indexOf("<"+tag,0), xmlFile.lastIndexOf(">")+1); + xmlFile= newDocType.concat(xmlFile); + //throw new com.sun.star.uno.RuntimeException(xmlFile); + } + ByteArrayInputStream bais = new ByteArrayInputStream(xmlFile.getBytes("UTF-8")); + transformer.transform(new StreamSource(bais),new StreamResult(xos)); + } + else + transformer.transform(new StreamSource(xis),new StreamResult(xos)); + } + catch (TransformerConfigurationException transConfExc) + { + throw new com.sun.star.uno.RuntimeException(transConfExc.getMessage()); + } + catch (TransformerException transExc){ + //System.out.println("\nException "+ e); + throw new com.sun.star.uno.RuntimeException(transExc.getMessage()); + } + catch (Exception e){ + System.out.println("\nException "+ e); + throw new com.sun.star.uno.RuntimeException(e.getMessage()); + } + } + + + + + // Implement methods from interface XTypeProvider + public byte[] getImplementationId() { + byte[] byteReturn = {}; + + byteReturn = new String( "" + this.hashCode() ).getBytes(); + + return( byteReturn ); + } + + // Implement method from interface XServiceName + public String getServiceName() { + return( __serviceName ); + } + + // Implement methods from interface XServiceInfo + public boolean supportsService(String stringServiceName) { + return( stringServiceName.equals( __serviceName ) ); + } + + public String getImplementationName() { + return( _DBFilter.class.getName() ); + } + + public String[] getSupportedServiceNames() { + String[] stringSupportedServiceNames = { __serviceName }; + return( stringSupportedServiceNames ); + } + } + + /** + * Returns a factory for creating the service. + * This method is called by the <code>JavaLoader</code> + * + * @return returns a <code>XSingleServiceFactory</code> for creating the + * component + * + * @param implName the name of the implementation for which a + * service is desired + * @param multiFactory the service manager to be used if needed + * @param regKey the registryKey + * + * @see com.sun.star.comp.loader.JavaLoader + */ + public static XSingleServiceFactory __getServiceFactory(String implName, + XMultiServiceFactory multiFactory, + XRegistryKey regKey) { + XSingleServiceFactory xSingleServiceFactory = null; + xMSF= multiFactory; + if (implName.equals(_DBFilter.class.getName()) ) { + xSingleServiceFactory = FactoryHelper.getServiceFactory(_DBFilter.class, + _DBFilter.__serviceName, + multiFactory, + regKey); + } + + return xSingleServiceFactory; + } + + /** + * Writes the service information into the given registry key. + * This method is called by the <code>JavaLoader</code> + * <p> + * @return returns true if the operation succeeded + * @param regKey the registryKey + * @see com.sun.star.comp.loader.JavaLoader + */ + public static boolean __writeRegistryServiceInfo(XRegistryKey regKey) { + + return FactoryHelper.writeRegistryServiceInfo(_DBFilter.class.getName(), + _DBFilter.__serviceName, regKey); + } +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Manifest b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Manifest new file mode 100644 index 000000000000..108fba617702 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Manifest @@ -0,0 +1 @@ +RegistrationClassName: DBFilter diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Readme.txt b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Readme.txt new file mode 100644 index 000000000000..d67b2aaeeac9 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/Readme.txt @@ -0,0 +1,14 @@ +DBFilter Readme +=============== + +The DocBook filter (DBFilter) is essentially teh XSLTFilter that is +delivered with Openoffice, except that it contains an extra routine +for Masking DOCTYPE Entity declarations. In this way, Entities +which are referenced inside the XML Document to be imported, +are converted into an <entity name="ent_name"> tag. In this way, +the entities can be imported into OOo as "set" and "get" variables. + +On Export, these variables can be written out once again as correct +Enity decls and Entity references. + +
\ No newline at end of file diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/makefile.mk new file mode 100644 index 000000000000..9f5a92570565 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbookfilter/makefile.mk @@ -0,0 +1,60 @@ +#************************************************************************* +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#************************************************************************* +PRJ = ..$/.. +PRJNAME = filter +#PACKAGE = com$/sun$/star$/documentconversion$/DBFilter +TARGET =DBFilter +# --- Settings ----------------------------------------------------- +.INCLUDE: settings.mk +CLASSDIR!:=$(CLASSDIR)$/$(TARGET) +#USE_UDK_EXTENDED_MANIFESTFILE=TRUE +#USE_EXTENDED_MANIFESTFILE=TRUE +JARFILES = ridl.jar unoil.jar jurt.jar juh.jar +JAVAFILES = $(subst,$(CLASSDIR)$/, $(subst,.class,.java $(JAVACLASSFILES))) +CUSTOMMANIFESTFILE = Manifest +#JARMANIFEST = Manifest + +#JARDIR=$(CLASSDIR) + +JARCOMPRESS = TRUE +JARCLASSDIRS = DBFilter*.class +JARTARGET = $(TARGET).jar + + +# --- Files -------------------------------------------------------- +JAVACLASSFILES=$(CLASSDIR)$/DBFilter.class +#---Manifest ------------------------------------------------------- +#$(OUT)$/class$/$(TARGET)$/META-INF: META-INF +# + $(COPY) $(COPYRECURSE) META-INF $(OUT)$/class$/DBFilter$/META-INF +# --- Targets ------------------------------------------------------ +.INCLUDE : target.mk +$(JAVACLASSFILES) : $(CLASSDIR) + +$(CLASSDIR) : + $(MKDIR) $(CLASSDIR) + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbooktosoffheadings.xsl b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbooktosoffheadings.xsl new file mode 100644 index 000000000000..7bb99da2f735 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/docbooktosoffheadings.xsl @@ -0,0 +1,1725 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + +<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:fo="http://www.w3.org/1999/XSL/Format" xmlns:office="http://openoffice.org/2000/office" xmlns:style="http://openoffice.org/2000/style" xmlns:text="http://openoffice.org/2000/text" xmlns:table="http://openoffice.org/2000/table" xmlns:draw="http://openoffice.org/2000/drawing" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="http://openoffice.org/2000/meta" xmlns:number="http://openoffice.org/2000/datastyle" xmlns:svg="http://www.w3.org/2000/svg" xmlns:chart="http://openoffice.org/2000/chart" xmlns:dr3d="http://openoffice.org/2000/dr3d" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="http://openoffice.org/2000/form" xmlns:script="http://openoffice.org/2000/script" xmlns:config="http://openoffice.org/2001/config" version="1.0" office:class="text" office:version="1.0"> + <xsl:output method="xml" indent="yes" omit-xml-declaration="no"/> + <!--<xsl:output method="xml" version="1.0" encoding="UTF-8" doctype-public="-//OASIS//DTD DocBook XML V4.1.2//EN" doctype-system="http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd"/>--> + <xsl:decimal-format name="staff" digit="D"/> + + <xsl:variable name="doc_type"> + <xsl:choose> + <xsl:when test="/article"> + <xsl:text>article</xsl:text> + </xsl:when> + <xsl:when test="/chapter"> + <xsl:text>chapter</xsl:text> + </xsl:when> + </xsl:choose> + </xsl:variable> + + + <xsl:template match="/"> + <xsl:element name="office:document"> + <office:meta> + <meta:generator>StarOffice 6.1 (Solaris Sparc)</meta:generator> + <dc:title> + <xsl:choose> + <xsl:when test="contains( $doc_type, 'chapter' )"> + <xsl:value-of select="/chapter/chapterinfo/title"/> + </xsl:when> + <xsl:when test="contains( $doc_type, 'article' )"> + <xsl:value-of select="/article/articleinfo/title"/> + </xsl:when> + </xsl:choose> + <!--<xsl:value-of select="$doc_type"/>--> + <!--<xsl:value-of select="/article/articleinfo/title"/>--> + + </dc:title> + <dc:description/> + <dc:subject/> + <meta:creation-date>2002-07-15T12:38:53</meta:creation-date> + <dc:date> + <xsl:choose> + <xsl:when test="contains( $doc_type, 'chapter' )"> + <xsl:value-of select="/chapter/chapterinfo/pubdate"/> + </xsl:when> + <xsl:when test="contains( $doc_type, 'article' )"> + <xsl:value-of select="/article/articleinfo/pubdate"/> + </xsl:when> + </xsl:choose> + <!--<xsl:value-of select="article/articleinfo/pubdate"/>--> + + </dc:date> + <dc:language> + <xsl:choose> + <xsl:when test="contains( $doc_type, 'chapter' )"> + <xsl:value-of select="chapter/@lang"/> + </xsl:when> + <xsl:when test="contains( $doc_type, 'article' )"> + <xsl:value-of select="article/@lang"/> + </xsl:when> + </xsl:choose> + <!--<xsl:value-of select="article/@lang"/>--> + + </dc:language> + <meta:editing-cycles>21</meta:editing-cycles> + <meta:editing-duration>P1DT0H11M54S</meta:editing-duration> + <meta:user-defined meta:name="Info 1"/> + <meta:user-defined meta:name="Info 2"/> + <meta:user-defined meta:name="Info 3"/> + <meta:user-defined meta:name="Info 4"/> + <meta:document-statistic meta:table-count="1" meta:image-count="0" meta:object-count="0" meta:page-count="1" meta:paragraph-count="42" meta:word-count="144" meta:character-count="820"/> + </office:meta> + <office:automatic-styles> + <style:style style:name="fr1" style:family="graphics" style:parent-style-name="Graphics"> + <style:properties style:horizontal-pos="center" style:horizontal-rel="paragraph" style:mirror="none" fo:clip="rect(0cm 0cm 0cm 0cm)" draw:luminance="0%" draw:contrast="0%" draw:red="0%" draw:green="0%" draw:blue="0%" draw:gamma="1" draw:color-inversion="false" draw:transparency="-100%" draw:color-mode="standard"/> + </style:style> + <style:style style:name="Table1" style:family="table"> + <style:properties style:width="14.649cm" table:align="margins"/> + </style:style> + <style:style style:name="Table1.A" style:family="table-column"> + <style:properties style:column-width="2.93cm" style:rel-column-width="13107*"/> + </style:style> + <style:style style:name="Table1.A1" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="none" fo:border-top="0.002cm solid #000000" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.E1" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.A2" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="none" fo:border-top="none" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.E2" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="0.002cm solid #000000" fo:border-top="none" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="P1" style:family="paragraph" style:parent-style-name="Text body" style:list-style-name="Ordered List"/> + <style:style style:name="T1" style:family="text" style:parent-style-name="Source Text"> + <style:properties fo:font-style="normal"/> + </style:style> + <style:page-master style:name="pm1"> + <style:properties fo:page-width="20.999cm" fo:page-height="29.699cm" style:num-format="1" style:print-orientation="portrait" fo:margin-top="2.54cm" fo:margin-bottom="2.54cm" fo:margin-left="3.175cm" fo:margin-right="3.175cm" style:writing-mode="lr-tb" style:footnote-max-height="0cm"> + <style:footnote-sep style:width="0.018cm" style:distance-before-sep="0.101cm" style:distance-after-sep="0.101cm" style:adjustment="left" style:rel-width="25%" style:color="#000000"/> + </style:properties> + <style:header-style/> + <style:footer-style/> + </style:page-master> + </office:automatic-styles> + <office:master-styles> + <style:master-page style:name="Standard" style:page-master-name="pm1"/> + </office:master-styles> + <office:body> + <xsl:call-template name="entities"/> + <xsl:apply-templates/> + </office:body> + </xsl:element> + </xsl:template> + + +<xsl:template name="entities"> + <xsl:element name="text:variable-decls"> + <xsl:for-each select="/descendant::entity"> + <xsl:variable name="entname"><xsl:value-of select="@name"/></xsl:variable> + <xsl:if test="not(preceding::entity[@name = $entname])"> + <xsl:element name="text:variable-decl"> + <xsl:attribute name="text:value-type"> + <xsl:text>string</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text>entitydecl_</xsl:text><xsl:value-of select="@name"/> + </xsl:attribute> + </xsl:element> + </xsl:if> + </xsl:for-each> + </xsl:element> +</xsl:template> + + + +<xsl:template match="entity"> + <xsl:variable name="entname"><xsl:value-of select="@name"/></xsl:variable> + <xsl:choose> + <xsl:when test="not(preceding::entity[@name = $entname])"> + <xsl:element name="text:variable-set"> + <xsl:attribute name="text:value-type"> + <xsl:text>string</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text>entitydecl_</xsl:text><xsl:value-of select="@name"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:element name="text:variable-get"> + <xsl:attribute name="text:value-type"> + <xsl:text>string</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text>entitydecl_</xsl:text><xsl:value-of select="@name"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + +</xsl:template> + + + + <!-- table start --> + + <xsl:template match="table"> + <xsl:variable name="tabletitle"> + <xsl:value-of select="title"/> + </xsl:variable> + <xsl:element name="table:table"> + <xsl:attribute name="table:name"/> + <xsl:attribute name="table:style-name">Table1</xsl:attribute> + <xsl:attribute name="table:name"> + <xsl:value-of select="@id"/> + </xsl:attribute> + <blah>blah</blah> + <xsl:apply-templates/> + </xsl:element> + <xsl:if test="not($tabletitle='')"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Table</xsl:attribute> + <xsl:value-of select="$tabletitle"/> + </xsl:element> + </xsl:if> + </xsl:template> + + + <xsl:template match="tgroup"> + <xsl:element name="table:table-column"> + <xsl:attribute name="table:style-name">Table1.A</xsl:attribute> + <xsl:choose> + <xsl:when test="@cols >0"> + <xsl:attribute name="table:number-columns-repeated"> + <xsl:value-of select="@cols"/> + </xsl:attribute> + </xsl:when> + <xsl:otherwise> + <xsl:attribute name="table:number-columns-repeated"> + <xsl:value-of select="count(child::tbody/row/entry) div count(child::tbody/row) "/> + </xsl:attribute> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="thead"> + <xsl:element name="table:table-header-rows"> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="tbody"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="row"> + <xsl:element name="table:table-row"> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="entry"> + <xsl:element name="table:table-cell"> + <xsl:if test="ancestor-or-self::thead"> + <xsl:attribute name="table:style-name">Table1.A1</xsl:attribute> + </xsl:if> + <xsl:if test="not(ancestor-or-self::thead)"> + <xsl:attribute name="table:style-name">Table1.A2</xsl:attribute> + </xsl:if> + <xsl:choose> + <xsl:when test="@spanname"> + <!--<xsl:if test="@spanname">--> + + <xsl:variable name="sname"> + <xsl:value-of select="@spanname"/> + </xsl:variable> + <xsl:attribute name="table:number-columns-spanned"> + <xsl:variable name="colnamestart"> + <xsl:value-of select="ancestor::tgroup/spanspec[@spanname=$sname]/@namest"/> + </xsl:variable> + <xsl:variable name="colnameend"> + <xsl:value-of select="ancestor::tgroup/spanspec[@spanname=$sname]/@nameend"/> + </xsl:variable> + <xsl:variable name="colnumstart"> + <xsl:value-of select="ancestor::tgroup/colspec[@colname=$colnamestart]/@colnum"/> + </xsl:variable> + <xsl:variable name="colnumend"> + <xsl:value-of select="ancestor::tgroup/colspec[@colname=$colnameend]/@colnum"/> + </xsl:variable> + <xsl:value-of select="$colnumend - $colnumstart + 1"/> + </xsl:attribute> + </xsl:when> + <xsl:when test="@namest and @nameend"> + <!--<xsl:if test="@namest and @nameend">--> + + <xsl:variable name="colnamestart"> + <xsl:value-of select="@namest"/> + </xsl:variable> + <xsl:variable name="colnameend"> + <xsl:value-of select="@nameend"/> + </xsl:variable> + <xsl:attribute name="table:number-columns-spanned"> + <xsl:variable name="colnumstart"> + <xsl:value-of select="ancestor::tgroup/colspec[@colname=$colnamestart]/@colnum"/> + </xsl:variable> + <xsl:variable name="colnumend"> + <xsl:value-of select="ancestor::tgroup/colspec[@colname=$colnameend]/@colnum"/> + </xsl:variable> + <xsl:value-of select="$colnumend - $colnumstart + 1"/> + </xsl:attribute> + </xsl:when> + </xsl:choose> + <!-- + <xsl:if test="not(@namest = '' ) "> + <xsl:attribute name="table:number-columns-spanned"> + <xsl:value-of select="(substring-after(@nameend,'c')-substring-after(@namest,'c'))+1"/> + + </xsl:attribute> + </xsl:if> + --> + + <xsl:choose> + <xsl:when test="not(child::para)"> + <xsl:element name="text:p"> + <xsl:if test="ancestor-or-self::thead"> + <xsl:attribute name="text:style-name">Table Heading</xsl:attribute> + </xsl:if> + <xsl:if test="ancestor-or-self::tbody"> + <xsl:attribute name="text:style-name">Table Contents</xsl:attribute> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + </xsl:template> + + + <xsl:template match="subtitle"> + <xsl:choose> + <xsl:when test="parent::table"> + <xsl:apply-templates/> + </xsl:when> + <xsl:when test="parent::informaltable"> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Section SubTitle</xsl:attribute> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="title"> + <xsl:choose> + <xsl:when test="parent::figure"/> + <xsl:when test="parent::table"/> + <xsl:when test="parent::sect1"/> + <xsl:when test="parent::sect2"/> + <xsl:when test="parent::sect3"/> + <xsl:when test="parent::sect4"/> + <xsl:when test="parent::sect5"/> + <xsl:when test="parent::informaltable"> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <xsl:element name="text:p"> + <xsl:choose> + <xsl:when test="parent::appendix"> + <xsl:attribute name="text:style-name">Appendix Title</xsl:attribute> + </xsl:when> + </xsl:choose> + <xsl:apply-templates/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="articleinfo"> + <xsl:element name="text:section"> + <xsl:attribute name="text:style-name">ArticleInfo</xsl:attribute> + <xsl:attribute name="text:name">ArticleInfo</xsl:attribute> + <xsl:if test="/article/articleinfo/subtitle !=''"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Document SubTitle</xsl:attribute> + <xsl:value-of select="/article/articleinfo/subtitle"/> + </xsl:element> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="chapterinfo"> + <xsl:element name="text:section"> + <xsl:attribute name="text:style-name">ChapterInfo</xsl:attribute> + <xsl:attribute name="text:name">ChapterInfo</xsl:attribute> + <xsl:if test="/chapter/chapterinfo/title !='' "> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Document Title</xsl:attribute> + <xsl:value-of select="/chapter/chapterinfo/title"/> + </xsl:element> + <xsl:if test="/chapter/chapterinfo/subtitle !=''"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Document SubTitle</xsl:attribute> + <xsl:value-of select="/chapter/chapterinfo/subtitle"/> + </xsl:element> + </xsl:if> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="appendix"> + <xsl:element name="text:section"> + <xsl:attribute name="text:style-name">Appendix</xsl:attribute> + <xsl:attribute name="text:name">Appendix</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + <!-- +<xsl:template match="author"> + <xsl:apply-templates/> +</xsl:template> + +<xsl:template match="firstname"> + <xsl:element name="text:variable-set"> + <xsl:attribute name="text:name"> + <xsl:if test="ancestor::articleinfo/author"> + <xsl:text disable-output-escaping="yes">articleinfo.author</xsl:text><xsl:value-of select="count(parent::author[preceding-sibling::author])"/><xsl:text disable-output-escaping="yes">.firstname</xsl:text><xsl:value-of select="count(preceding-sibling::firstname)"/> + </xsl:if> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> +</xsl:template> +--> + + <xsl:template match="articleinfo/title | chapterinfo/title"> + <!-- <xsl:element name="text:variable-decls"> + <xsl:element name="text:variable-decl"> + <xsl:attribute name="text:value-type"> + <xsl:text>string</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text disable-output-escaping="yes">articleinfo.title</xsl:text> + </xsl:attribute> + </xsl:element> + + </xsl:element> + <xsl:element name="text:p"> + <xsl:element name="text:variable-set"> + <xsl:attribute name="text:value-type"> + <xsl:text>string</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text disable-output-escaping="yes">articleinfo.title</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:element> + --> + </xsl:template> + + + <xsl:template match="articleinfo/title"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">Document Title</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> +</xsl:template> + +<xsl:template match="date"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>date_</xsl:text><xsl:value-of select="count(preceding::date)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>date_</xsl:text><xsl:value-of select="count(preceding::date)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="revision"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>revision_</xsl:text><xsl:value-of select="count(preceding::revision)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>revision_</xsl:text><xsl:value-of select="count(preceding::revision)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="revnumber"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>revnumber_</xsl:text><xsl:value-of select="count(preceding::revnumber)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>revnumber_</xsl:text><xsl:value-of select="count(preceding::revnumber)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="revdescription"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>revdescription_</xsl:text><xsl:value-of select="count(preceding::revdescription)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>revdescription_</xsl:text><xsl:value-of select="count(preceding::revdescription)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="revhistory"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>revhistory_</xsl:text><xsl:value-of select="count(preceding::revhistory)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>revhistory_</xsl:text><xsl:value-of select="count(preceding::revhistory)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:line-break"/> + </xsl:element> +</xsl:template> + +<xsl:template match="legalnotice"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>legalnotice_</xsl:text><xsl:value-of select="count(preceding::legalnotice)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>legalnotice_</xsl:text><xsl:value-of select="count(preceding::legalnotice)"/> + </xsl:attribute> + </xsl:element> + </xsl:element> +</xsl:template> + +<xsl:template match="legalnotice/title"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>title_</xsl:text><xsl:value-of select="count(preceding::legalnotice/title)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>title_</xsl:text><xsl:value-of select="count(preceding::legalnotice/title)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="para[ancestor::articleinfo]"> + <xsl:element name="text:s"/> + + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>para_</xsl:text><xsl:value-of select="count(preceding::para[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>para_</xsl:text><xsl:value-of select="count(preceding::para[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + + +<xsl:template match="articleinfo/subtitle"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>subtitle_</xsl:text><xsl:value-of select="count(preceding::articleinfo/subtitle)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>subtitle_</xsl:text><xsl:value-of select="count(preceding::articleinfo/subtitle)"/> + </xsl:attribute> + </xsl:element> + </xsl:element> +</xsl:template> + +<xsl:template match="articleinfo/edition"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>edition_</xsl:text><xsl:value-of select="count(preceding::articleinfo/edition)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>edition_</xsl:text><xsl:value-of select="count(preceding::articleinfo/edition)"/> + </xsl:attribute> + </xsl:element> + </xsl:element> +</xsl:template> + +<xsl:template match="articleinfo/releaseinfo"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>releaseinfo_</xsl:text><xsl:value-of select="count(preceding::articleinfo/releaseinfo)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>releaseinfo_</xsl:text><xsl:value-of select="count(preceding::articleinfo/releaseinfo)"/> + </xsl:attribute> + </xsl:element> + </xsl:element> +</xsl:template> + + +<xsl:template match="author/firstname"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>firstname_</xsl:text><xsl:value-of select="count(preceding::author/firstname)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>firstname_</xsl:text><xsl:value-of select="count(preceding::author/firstname)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + +</xsl:template> + + + +<xsl:template match="year[ancestor::articleinfo]"> + <xsl:element name="text:s"/> + + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>year_</xsl:text><xsl:value-of select="count(preceding::year[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>year_</xsl:text><xsl:value-of select="count(preceding::year[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + +</xsl:template> + +<xsl:template match="authorgroup"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>authorgroup_</xsl:text><xsl:value-of select="count(preceding::authorgroup)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>authorgroup_</xsl:text><xsl:value-of select="count(preceding::authorgroup)"/> + </xsl:attribute> + </xsl:element> + </xsl:element> +</xsl:template> + +<xsl:template match="articleinfo/copyright/holder"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>holder_</xsl:text><xsl:value-of select="count(preceding::articleinfo/copyright/holder)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>holder_</xsl:text><xsl:value-of select="count(preceding::articleinfo/copyright/holder)"/> + </xsl:attribute> + </xsl:element> + <!--<xsl:element name="text:s"/>--> + <xsl:element name="text:line-break"/> +</xsl:template> + +<xsl:template match="articleinfo/copyright"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>copyright_</xsl:text><xsl:value-of select="count(preceding::articleinfo/copyright)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>copyright_</xsl:text><xsl:value-of select="count(preceding::articleinfo/copyright)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + </xsl:element> +</xsl:template> + + +<xsl:template name="affiliation"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>affiliation_</xsl:text><xsl:value-of select="count(preceding::affiliation)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>affiliation_</xsl:text><xsl:value-of select="count(preceding::affiliation)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="author/affiliation/address"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>address_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/address)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>address_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/address)"/> + </xsl:attribute> + </xsl:element> +</xsl:element> +</xsl:template> + +<xsl:template match="authorgroup"> + <xsl:element name="text:p"> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>authorgroup_</xsl:text><xsl:value-of select="count(preceding::authorgroup)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>authorgroup_</xsl:text><xsl:value-of select="count(preceding::authorgroup)"/> + </xsl:attribute> + </xsl:element> +</xsl:element> +</xsl:template> + + +<xsl:template match="author"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>author_</xsl:text><xsl:value-of select="count(preceding::author)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>author_</xsl:text><xsl:value-of select="count(preceding::author)"/> + </xsl:attribute> + </xsl:element> + <!--<xsl:element name="text:s"/>--> + <xsl:element name="text:line-break"/> +</xsl:template> + +<xsl:template match="author/affiliation"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>affiliation_</xsl:text><xsl:value-of select="count(preceding::author/affiliation)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>affiliation_</xsl:text><xsl:value-of select="count(preceding::author/affiliation)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + +<xsl:template match="author/affiliation/address"> + <xsl:element name="text:s"/> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>address_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/address)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>address_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/address)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> +</xsl:template> + + +<xsl:template match="email[ancestor::articleinfo]"> + <xsl:element name="text:s"/> + + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>email_</xsl:text><xsl:value-of select="count(preceding::email[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>email_</xsl:text><xsl:value-of select="count(preceding::email[ancestor::articleinfo])"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + +</xsl:template> + +<xsl:template match="author/affiliation/orgname"> + <xsl:element name="text:s"/> + + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>orgname_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/orgname)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>orgname_</xsl:text><xsl:value-of select="count(preceding::author/affiliation/orgname)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + +</xsl:template> + + +<xsl:template match="author/surname"> + <xsl:element name="text:s"/> + + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>surname_</xsl:text><xsl:value-of select="count(preceding::author/surname)"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>surname_</xsl:text><xsl:value-of select="count(preceding::author/surname)"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="text:s"/> + + +</xsl:template> + + + + <xsl:template match="para"> + <xsl:choose> + <xsl:when test="ancestor::varlistentry"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">VarList Term</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:element name="text:p"> + <xsl:choose> + <xsl:when test="ancestor-or-self::footnote"> + <xsl:attribute name="text:style-name"> + <xsl:text>Footnote</xsl:text> + </xsl:attribute> + </xsl:when> + <xsl:when test="ancestor-or-self::informaltable"> + <xsl:if test="ancestor-or-self::informaltable"> + <xsl:attribute name="text:style-name">Table Contents</xsl:attribute> + </xsl:if> + <xsl:if test="ancestor-or-self::thead "> + <xsl:attribute name="text:style-name">Table Heading</xsl:attribute> + </xsl:if> + </xsl:when> + <xsl:when test="ancestor-or-self::table"> + <xsl:if test="ancestor-or-self::table"> + <xsl:attribute name="text:style-name">Table Contents</xsl:attribute> + </xsl:if> + <xsl:if test="ancestor-or-self::thead "> + <xsl:attribute name="text:style-name">Table Heading</xsl:attribute> + </xsl:if> + </xsl:when> + <xsl:otherwise> + <xsl:attribute name="text:style-name">Text body</xsl:attribute> + </xsl:otherwise> + </xsl:choose> + <xsl:choose> + <xsl:when test="@id"> + <xsl:call-template name="test.id"/> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="section"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level"> + <xsl:value-of select="count(ancestor-or-self::section) "/> + </xsl:attribute> + <xsl:value-of select="child::title"/> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="abstract"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">1</xsl:attribute> + <xsl:text>abstract</xsl:text> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="appendix"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">1</xsl:attribute> + <xsl:text>appendix</xsl:text> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="sect1"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">1</xsl:attribute> + <xsl:choose> + <xsl:when test="@id"> + <xsl:call-template name="test.id"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="child::title"/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="sect2"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">2</xsl:attribute> + <xsl:choose> + <xsl:when test="@id"> + <xsl:call-template name="test.id"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="child::title"/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="sect3"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">3</xsl:attribute> + <xsl:choose> + <xsl:when test="@id"> + <xsl:call-template name="test.id"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="child::title"/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="sect4"> + <xsl:element name="text:h"> + <xsl:attribute name="text:level">4</xsl:attribute> + <xsl:choose> + <xsl:when test="@id"> + <xsl:call-template name="test.id"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="child::title"/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + <xsl:apply-templates/> + </xsl:template> + <!--<xsl:template match="sect5"> + <xsl:element name="text:section"> + <xsl:attribute name="text:style-name">Sect1</xsl:attribute> + <xsl:attribute name="text:name"><xsl:value-of select="@id"/></xsl:attribute> + <xsl:apply-templates/> + </xsl:element> +</xsl:template>--> + + <xsl:template match="informaltable"> + <xsl:element name="table:table"> + <xsl:attribute name="table:name"/> + <xsl:attribute name="table:style-name">Table1</xsl:attribute> + <xsl:attribute name="table:name"> + <xsl:value-of select="@id"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + <xsl:template match="indexterm"/> + + + <xsl:template match="figure"> + <xsl:apply-templates/> + </xsl:template> + <!-- lists Section --> + + <xsl:template match="itemizedlist"> + <xsl:element name="text:unordered-list"> + <xsl:attribute name="text:style-name">UnOrdered List</xsl:attribute> + <xsl:attribute name="text:continue-numbering">false</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="variablelist"> + <xsl:element name="text:unordered-list"> + <xsl:attribute name="text:style-name">Var List</xsl:attribute> + <xsl:attribute name="text:continue-numbering">false</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="orderedlist"> + <xsl:element name="text:ordered-list"> + <xsl:attribute name="text:style-name">Ordered List</xsl:attribute> + <xsl:attribute name="text:continue-numbering">false</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="term"> + <xsl:if test="parent::varlistentry"> + <text:list-item> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">VarList Term</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </text:list-item> + </xsl:if> + </xsl:template> + + + <xsl:template match="listitem"> + <xsl:choose> + <xsl:when test="parent::varlistentry"> + <text:list-item> + <xsl:apply-templates/> + </text:list-item> + </xsl:when> + <xsl:otherwise> + <text:list-item> + <xsl:apply-templates/> + </text:list-item> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + <!-- end of lists--> + + <xsl:template match="menuchoice"> + <xsl:variable name="pos"><xsl:value-of select="count(preceding::menuchoice)"/></xsl:variable> + <xsl:element name="text:bookmark-start"> + <xsl:attribute name="text:name"> + <xsl:text>menuchoice_</xsl:text><xsl:value-of select="$pos"/> + </xsl:attribute> + </xsl:element> + <xsl:apply-templates/> + <xsl:element name="text:bookmark-end"> + <xsl:attribute name="text:name"> + <xsl:text>menuchoice_</xsl:text><xsl:value-of select="$pos"/> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="guimenuitem"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiMenuItem</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="guibutton"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiButton</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="guisubmenu"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiSubMenu</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 4th, 2003 --> + <xsl:template match="emphasis"> + <xsl:element name="text:span"> + <xsl:choose> + <xsl:when test="@role"> + <xsl:attribute name="text:style-name">Emphasis Bold</xsl:attribute> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <xsl:attribute name="text:style-name">Emphasis</xsl:attribute> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </xsl:element> + </xsl:template> + +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 16th, 2003 --> + <xsl:template match="quote"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">Citation</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + <xsl:template match="guimenu"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiMenu</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="guisubmenu"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiSubMenu</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="guilabel"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiLabel</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="guibutton"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">GuiButton</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="keycap"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">KeyCap</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="keysym"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">KeySym</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="keycombo"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">KeyCombo</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="command"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">Command</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="application"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">Application</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="filename"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">FileName</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="systemitem"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">SystemItem</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="computeroutput"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name">ComputerOutput</xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="inlinegraphic"> + <xsl:element name="draw:image"> + <xsl:attribute name="draw:style-name"> + <xsl:text>fr1</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:name"/> + <xsl:attribute name="text:anchor-type"/> + <xsl:attribute name="draw:z-index"/> + <xsl:attribute name="xlink:href"> + <xsl:value-of select="@fileref"/> + </xsl:attribute> + <xsl:attribute name="xlink:type"/> + <xsl:attribute name="svg:width"> + <!--<xsl:value-of select="@width"/>--> + + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="svg:height"> + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:show"> + <xsl:text>embed</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:actuate"> + <xsl:text>onLoad</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:filter-name"> + <xsl:text disable-output-escaping="yes"><All formats></xsl:text> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="footnote"> + <xsl:element name="text:footnote"> + <!--<xsl:element name="text:footnote-citation">Aidan</xsl:element>--> + + <xsl:element name="text:footnote-body"> + <xsl:apply-templates/> + </xsl:element> + </xsl:element> + </xsl:template> + + + <xsl:template match="highlight"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name"> + <xsl:text>Highlight</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="ulink"> + <xsl:element name="text:a"> + <xsl:attribute name="xlink:type"> + <xsl:text>simple</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:href"> + <xsl:value-of select="@url"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="link"> + <xsl:element name="text:a"> + <xsl:attribute name="xlink:type"> + <xsl:text>simple</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:href"> + <xsl:text>#</xsl:text> + <xsl:value-of select="@linkend"/> + <xsl:text>%7Cregion</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="olink"> + <xsl:element name="text:a"> + <xsl:attribute name="xlink:type"> + <xsl:text>simple</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:href"> + <xsl:value-of select="@targetdocent"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + <!-- xref maps to reference-ref i.e an OOo insert reference + xref is an empty element, reference-ref spans the object to be referenced --> + <xsl:template match="xref"> + <xsl:element name="text:reference-ref"> + <xsl:attribute name="text:reference-format"> + <xsl:text>text</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:ref-name"> + <xsl:value-of select="@linkend"/> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <!-- the DocBook elements that have been "xreffed" contain an ID attribute that is linked to by an xref @linkend or @endterm --> + <!-- the @id can also be pointed to by an indexterm --> + + <xsl:template name="test.id"> + <xsl:if test="@id"> + <xsl:variable name="id.val"> + <xsl:value-of select="@id"/> + </xsl:variable> + + <xsl:element name="text:reference-mark-start"> + <xsl:attribute name="text:name"> + <xsl:value-of select="@id"/> + </xsl:attribute> + </xsl:element> + + <xsl:choose> + <xsl:when test="self::para"> + <xsl:apply-templates/> + </xsl:when> + <xsl:otherwise> + <!-- sect* --> + <xsl:value-of select="child::title"/> + </xsl:otherwise> + </xsl:choose> + + <xsl:element name="text:reference-mark-end"> + <xsl:attribute name="text:name"> + <xsl:value-of select="@id"/> + </xsl:attribute> + </xsl:element> + + </xsl:if> + </xsl:template> + + + <xsl:template match="indexterm"> + <xsl:if test="@class = 'startofrange'"> + <xsl:element name="text:alphabetical-index-mark-start"> + <xsl:attribute name="text:id"> + <xsl:value-of select="@id"/> + </xsl:attribute> + <!--<xsl:if test="primary">--> + + <xsl:attribute name="text:key1"> + <xsl:value-of select="primary"/> + </xsl:attribute> + <!--</xsl:if>--> + + <xsl:if test="secondary">--> + <xsl:attribute name="text:key2"> + <xsl:value-of select="secondary"/> + </xsl:attribute> + </xsl:if> + </xsl:element> + </xsl:if> + <xsl:if test="@class = 'endofrange'"> + <xsl:element name="text:alphabetical-index-mark-end"> + <xsl:attribute name="text:id"> + <xsl:value-of select="@startref"/> + </xsl:attribute> + </xsl:element> + </xsl:if> + </xsl:template> + + + <xsl:template match="index"> + <xsl:element name="text:alphabetical-index"> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Sect1</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:protected"> + <xsl:text disable-output-escaping="yes">true</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:value-of select="title"/> + </xsl:attribute> + <xsl:element name="text:alphabetical-index-source"> + <xsl:attribute name="text:main-entry-style-name"> + <xsl:text disable-output-escaping="yes">Main index entry</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:sort-algorithm"> + <xsl:text disable-output-escaping="yes">alphanumeric</xsl:text> + </xsl:attribute> + <xsl:attribute name="fo:language"> + <xsl:text disable-output-escaping="yes">en</xsl:text> + </xsl:attribute> + <xsl:attribute name="fo:country"> + <xsl:text disable-output-escaping="yes">IE</xsl:text> + </xsl:attribute> + <xsl:element name="text:index-title-template"> + <xsl:attribute name="text:style-name">Index Heading</xsl:attribute> + <xsl:value-of select="title"/> + </xsl:element> + <xsl:element name="text:alphabetical-index-entry-template"> + <xsl:attribute name="text:outline-level"> + <xsl:text disable-output-escaping="yes">separator</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index Separator</xsl:text> + </xsl:attribute> + <xsl:element name="text:index-entry-text"/> + </xsl:element> + <xsl:element name="text:alphabetical-index-entry-template"> + <xsl:attribute name="text:outline-level"> + <xsl:text disable-output-escaping="yes">1</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index 1</xsl:text> + </xsl:attribute> + <xsl:element name="text:index-entry-text"/> + <xsl:element name="text:index-entry-tab-stop"> + <xsl:attribute name="style:type"> + <xsl:text disable-output-escaping="yes">left</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:position"> + <xsl:text disable-output-escaping="yes">0cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:leader-char"> + <xsl:text disable-output-escaping="yes"/> + </xsl:attribute> + </xsl:element> + </xsl:element> + <xsl:element name="text:alphabetical-index-entry-template"> + <xsl:attribute name="text:outline-level"> + <xsl:text disable-output-escaping="yes">2</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index 2</xsl:text> + </xsl:attribute> + <xsl:element name="text:index-entry-text"/> + <xsl:element name="text:index-entry-tab-stop"> + <xsl:attribute name="style:type"> + <xsl:text disable-output-escaping="yes">left</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:position"> + <xsl:text disable-output-escaping="yes">0cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:leader-char"> + <xsl:text disable-output-escaping="yes"/> + </xsl:attribute> + </xsl:element> + </xsl:element> + <xsl:element name="text:alphabetical-index-entry-template"> + <xsl:attribute name="text:outline-level"> + <xsl:text disable-output-escaping="yes">3</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index 3</xsl:text> + </xsl:attribute> + <xsl:element name="text:index-entry-text"/> + <xsl:element name="text:index-entry-tab-stop"> + <xsl:attribute name="style:type"> + <xsl:text disable-output-escaping="yes">left</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:position"> + <xsl:text disable-output-escaping="yes">0cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="style:leader-char"> + <xsl:text disable-output-escaping="yes"/> + </xsl:attribute> + </xsl:element> + </xsl:element> + </xsl:element> + + <xsl:element name="text:index-body"> + <xsl:element name="text:index-title"> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Sect1</xsl:text> + </xsl:attribute> + <xsl:attribute name="text:name"> + <xsl:text disable-output-escaping="yes">Alphabetical Index1_Head</xsl:text> + </xsl:attribute> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index Heading</xsl:text> + </xsl:attribute> + <xsl:value-of select="title"/> + </xsl:element> + </xsl:element> + <xsl:apply-templates select="indexentry"/> + </xsl:element> + </xsl:element> + </xsl:template> + + + <xsl:template match="indexentry"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index 1</xsl:text> + </xsl:attribute> + <xsl:value-of select="primaryie"/> + <xsl:element name="text:tab-stop"/> + </xsl:element> + <xsl:if test="secondaryie"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name"> + <xsl:text disable-output-escaping="yes">Index 2</xsl:text> + </xsl:attribute> + <xsl:value-of select="secondaryie"/> + <xsl:element name="text:tab-stop"/> + </xsl:element> + </xsl:if> + </xsl:template> + + + <xsl:template match="note"> + <office:annotation> + <text:p> + <xsl:apply-templates/> + </text:p> + </office:annotation> + </xsl:template> + + + <xsl:template match="imageobject"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="textobject"/> + + + <xsl:template match="caption"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="imagedata"> + <xsl:element name="draw:image"> + <xsl:attribute name="draw:style-name"> + <xsl:text>fr1</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:name"/> + <xsl:attribute name="text:anchor-type"/> + <xsl:attribute name="draw:z-index"/> + <xsl:attribute name="xlink:href"> + <xsl:value-of select="@fileref"/> + </xsl:attribute> + <xsl:attribute name="xlink:type"/> + <xsl:attribute name="svg:width"> + <!--<xsl:value-of select="@width"/>--> + + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="svg:height"> + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:show"> + <xsl:text>embed</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:actuate"> + <xsl:text>onLoad</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:filter-name"> + <xsl:text disable-output-escaping="yes"><All formats></xsl:text> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="audioobject"> + <xsl:element name="draw:plugin"> + <xsl:attribute name="draw:style-name"> + <xsl:text>fr1</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:name"/> + <xsl:attribute name="text:anchor-type"/> + <xsl:attribute name="draw:z-index"/> + <xsl:attribute name="xlink:href"> + <xsl:value-of select="@fileref"/> + </xsl:attribute> + <xsl:attribute name="xlink:type"/> + <xsl:attribute name="svg:width"> + <!--<xsl:value-of select="@width"/>--> + + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="svg:height"> + <xsl:text>1cm</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:show"> + <xsl:text>embed</xsl:text> + </xsl:attribute> + <xsl:attribute name="xlink:actuate"> + <xsl:text>onLoad</xsl:text> + </xsl:attribute> + <xsl:attribute name="draw:filter-name"> + <xsl:text disable-output-escaping="yes"><All formats></xsl:text> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="remark"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="mediaobject"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name"> + <xsl:text>Mediaobject</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="superscript"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name"> + <xsl:text>SuperScript</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="subscript"> + <xsl:element name="text:span"> + <xsl:attribute name="text:style-name"> + <xsl:text>SubScript</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="comment()"> + <xsl:element name="text:p"> + <xsl:attribute name="text:style-name">XMLComment</xsl:attribute> + <xsl:value-of select="."/> + </xsl:element> + </xsl:template> +</xsl:stylesheet> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/literallayout.java b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/literallayout.java new file mode 100644 index 000000000000..c2dbc2396d94 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/literallayout.java @@ -0,0 +1,135 @@ +/************************************************************************* + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * Copyright 2000, 2010 Oracle and/or its affiliates. + * + * OpenOffice.org - a multi-platform office productivity suite + * + * This file is part of OpenOffice.org. + * + * OpenOffice.org is free software: you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License version 3 + * only, as published by the Free Software Foundation. + * + * OpenOffice.org is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU Lesser General Public License version 3 for more details + * (a copy is included in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU Lesser General Public License + * version 3 along with OpenOffice.org. If not, see + * <http://www.openoffice.org/license.html> + * for a copy of the LGPLv3 License. + * + ************************************************************************/ +package org.openoffice.xmerge.converter.xml.xslt.docbook; +import java.lang.String; + + +public class literallayout{ + + public static String RemoveSpaces(String test){ + System.out.println("\nWorking... Length=" +test.length()); + int i=0; + int paraBreak=10000; + String result=""; + char data[]={10}; + char tab[]={13}; + if(test!=null){ + String strArr[]= test.split(new String(data)); + test=""; + + while (i< strArr.length ){ + //System.out.println("Trying "+ i); + + if (test.length()+strArr[i].length()> paraBreak){ + test=test.concat("</text:p><text:p text:style-name=\"Preformatted Text\" text:name=\"Preformatted Text\">"); + paraBreak+=10000; + } + strArr[i]=needsMask(strArr[i]).concat("<text:line-break/>"); + strArr[i]=needsSecondMask(strArr[i]); + test=test.concat(strArr[i]); + i++; + } + + System.out.println(test.length()); + + } + else{ + test=""; + } + System.out.println("\nDone"); + return test; + } + + public static String needsMask(String origString){ + if (origString.indexOf("&")!=-1){ + origString=replaceStr(origString,"&","&"); + } + if (origString.indexOf("\"")!=-1){ + origString=replaceStr(origString,"\"","""); + } + if (origString.indexOf("<")!=-1){ + origString=replaceStr(origString,"<","<"); + } + if (origString.indexOf(">")!=-1){ + origString=replaceStr(origString,">",">"); + } + return origString; + + } + + public static String needsSecondMask(String origString){ + char data[]={10}; + char tab[]={9}; + if (origString.indexOf(" ")!=-1){ + origString=replaceStr(origString," "," <text:s/>"); + } + if (origString.indexOf(new String(tab))!=-1){ + origString=replaceStr(origString,new String(tab),"<text:tab-stop/>"); + } + + return origString; + + } + + public static String replaceStr(String origString, String origChar, String replaceChar){ + String tmp=""; + int index=origString.indexOf(origChar); + if(index !=-1){ + while (index !=-1){ + String first =origString.substring(0,index); + first=first.concat(replaceChar); + tmp=tmp.concat(first); + origString=origString.substring(index+1,origString.length()); + index=origString.indexOf(origChar); + if(index==-1) { + tmp=tmp.concat(origString); + } + + } + + } + return tmp; + } + + + private static String replace(String test){ + int i=0; + String result=""; + if (test.indexOf(" ",i)!=-1){ + while (test.indexOf(" ",i)!=-1){ + result=result.concat(test.substring(0,test.indexOf(" ",i))); + result=result.concat(" <text:s/>"); + i=test.indexOf(" ",i)+2; + } + return result; + } + else{ + return test; + } + } + +} diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_article.xsl b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_article.xsl new file mode 100644 index 000000000000..649869eca225 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_article.xsl @@ -0,0 +1,848 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + +<xsl:stylesheet version="1.0" xmlns:style="http://openoffice.org/2000/style" xmlns:text="http://openoffice.org/2000/text" xmlns:office="http://openoffice.org/2000/office" xmlns:table="http://openoffice.org/2000/table" xmlns:draw="http://openoffice.org/2000/drawing" xmlns:fo="http://www.w3.org/1999/XSL/Format" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="http://openoffice.org/2000/meta" xmlns:number="http://openoffice.org/2000/datastyle" xmlns:svg="http://www.w3.org/2000/svg" xmlns:chart="http://openoffice.org/2000/chart" xmlns:dr3d="http://openoffice.org/2000/dr3d" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="http://openoffice.org/2000/form" xmlns:script="http://openoffice.org/2000/script" xmlns:config="http://openoffice.org/2001/config" office:class="text" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" exclude-result-prefixes="office meta table number dc fo xlink chart math script xsl draw svg dr3d form config text style"> + + <xsl:key name='headchildren' match="text:p | text:alphabetical-index | table:table | text:span | text:ordered-list | office:annotation | text:unordered-list | text:footnote | text:a | text:list-item | draw:plugin | draw:text-box | text:footnote-body | text:section" + use="generate-id((..|preceding-sibling::text:h[@text:level='1']|preceding-sibling::text:h[@text:level='2']|preceding-sibling::text:h[@text:level='3']|preceding-sibling::text:h[@text:level='4']|preceding-sibling::text:h[@text:level='5'])[last()])"/> + + <xsl:key name="children" match="text:h[@text:level='2']" + use="generate-id(preceding-sibling::text:h[@text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='3']" + use="generate-id(preceding-sibling::text:h[@text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='4']" + use="generate-id(preceding-sibling::text:h[@text:level='3' or @text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='5']" + use="generate-id(preceding-sibling::text:h[@text:level='4' or @text:level='3' or @text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="secondary_children" match="text:p[@text:style-name = 'Index 2']" + use="generate-id(preceding-sibling::text:p[@text:style-name = 'Index 1'][1])"/> + +<!-- --> + <xsl:template match="/office:document"> + <xsl:text disable-output-escaping="yes"><!DOCTYPE article PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN" "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" [ + </xsl:text> + <xsl:for-each select="descendant::text:variable-decl"> + <xsl:variable name="name"><xsl:value-of select="@text:name"/></xsl:variable> + <xsl:if test="contains(@text:name,'entitydecl')"> + <xsl:text disable-output-escaping="yes"><!ENTITY </xsl:text><xsl:value-of select="substring-after(@text:name,'entitydecl_')"/><xsl:text> "</xsl:text><xsl:value-of select="/descendant::text:variable-set[@text:name= $name][1]"/><xsl:text disable-output-escaping="yes">"></xsl:text> + </xsl:if> + </xsl:for-each> + + <xsl:text disable-output-escaping="yes">]></xsl:text> + <article> + <xsl:attribute name="lang"> + <xsl:value-of select="/office:document/office:meta/dc:language"/> + </xsl:attribute> + <xsl:apply-templates/> + </article> + </xsl:template> + + + <xsl:template match="text:section"> + <xsl:choose> + <xsl:when test="@text:name='ArticleInfo'"> + <articleinfo> + <xsl:apply-templates/> + </articleinfo> + </xsl:when> + <xsl:when test="@text:name='Abstract'"> + <abstract> + <xsl:apply-templates/> + </abstract> + </xsl:when> + <xsl:when test="@text:name='Appendix'"> + <appendix> + <xsl:apply-templates/> + </appendix> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="sectvar"><xsl:text>sect</xsl:text><xsl:value-of select="count(ancestor::text:section)+1"/></xsl:variable> + <xsl:variable name="idvar"><xsl:text> id="</xsl:text><xsl:value-of select="@text:name"/><xsl:text>"</xsl:text></xsl:variable> + <xsl:text disable-output-escaping="yes"><</xsl:text><xsl:value-of select="$sectvar"/><xsl:value-of select="$idvar"/><xsl:text disable-output-escaping="yes">></xsl:text> + <xsl:apply-templates/> + <xsl:text disable-output-escaping="yes"></</xsl:text><xsl:value-of select="$sectvar"/><xsl:text disable-output-escaping="yes">></xsl:text> + </xsl:otherwise> +</xsl:choose> + + </xsl:template> + + <xsl:template match="text:h[@text:level='1']"> + <xsl:choose> + <xsl:when test=".='Abstract'"> + <abstract> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + </abstract> + </xsl:when> + <xsl:otherwise> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="@text:level"/> + <xsl:with-param name="prev" select="1"/> + </xsl:call-template> + <!--<sect1> + <title> + <xsl:apply-templates/> + </title> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + </sect1>--> + + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:h[@text:level='2'] | text:h[@text:level='3']| text:h[@text:level='4'] | text:h[@text:level='5']"> + <xsl:variable name="level" select="@text:level"/> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="$level"/> + <xsl:with-param name="prev" select="preceding-sibling::text:h[@text:level < $level][1]/@text:level "/> + </xsl:call-template> + </xsl:template> + + + <xsl:template name="make-section"> + <xsl:param name="current"/> + <xsl:param name="prev"/> + <xsl:choose> + <xsl:when test="$current > $prev+1"> + <xsl:variable name="sect.element"> + <xsl:text disable-output-escaping="yes">sect</xsl:text> + <xsl:value-of select="$prev +1"/> + </xsl:variable> + <!--<xsl:text disable-output-escaping="yes"><sect</xsl:text><xsl:value-of select="$prev +1"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + <xsl:element name="{$sect.element}"> + <xsl:call-template name="id.attribute"/> + <title/> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="$current"/> + <xsl:with-param name="prev" select="$prev +1"/> + </xsl:call-template> + <!--<xsl:text disable-output-escaping="yes"></sect</xsl:text><xsl:value-of select="$prev +1 "/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="sect.element"> + <xsl:text disable-output-escaping="yes">sect</xsl:text> + <xsl:value-of select="$current"/> + </xsl:variable> + <!--<xsl:text disable-output-escaping="yes"><sect</xsl:text><xsl:value-of select="$current"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + <xsl:element name="{$sect.element}"> + <xsl:call-template name="id.attribute"/> + <title> + <xsl:apply-templates/> + </title> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + <!--<xsl:text disable-output-escaping="yes"></sect</xsl:text><xsl:value-of select="$current"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + <xsl:template match="text:variable-set|text:variable-get"> + <xsl:choose> + <xsl:when test="contains(@text:name,'entitydecl')"> + <xsl:text disable-output-escaping="yes">&</xsl:text><xsl:value-of select="substring-after(@text:name,'entitydecl_')"/><xsl:text disable-output-escaping="yes">;</xsl:text> + </xsl:when> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='XMLComment']"> + <xsl:comment> + <xsl:value-of select="."/> + </xsl:comment> + </xsl:template> + + <xsl:template match="text:section[@text:name = 'ArticleInfo']/text:p[not(@text:style-name='XMLComment')]"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="text:p"> + <!--text:span text:style-name="XrefLabel" --> + <!--<xsl:if test="not( child::text:span[@text:style-name = 'XrefLabel'] )"> --> + + <xsl:element name="para"> + <xsl:if test="child::text:reference-mark-start"> + <xsl:value-of select="."/> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + <!-- </xsl:if> --> + + </xsl:template> + + + <xsl:template match="office:meta"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:ordered-list"> + <orderedlist> + <xsl:apply-templates/> + </orderedlist> + </xsl:template> + + <xsl:template match="meta:editing-cycles"/> + + <xsl:template match="meta:user-defined"/> + + <xsl:template match="meta:editing-duration"/> + + <xsl:template match="dc:language"/> + + <xsl:template match="dc:date"> + <!--<pubdate> + <xsl:value-of select="substring-before(.,'T')"/> + </pubdate>--> + </xsl:template> + + <xsl:template match="meta:creation-date"/> + + <xsl:template match="office:body"> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="text:h[@text:level='1']"/> + <!--<xsl:apply-templates/>--> + </xsl:template> + + <xsl:template match="office:styles"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="office:script"/> + + <xsl:template match="office:settings"/> + + <xsl:template match="office:font-decls"/> + + <xsl:template match="text:bookmark-start"> + <xsl:text disable-output-escaping="yes"><</xsl:text><xsl:value-of select="substring-before(@text:name,'_')"/><xsl:text disable-output-escaping="yes">></xsl:text><xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:bookmark-end"> + <xsl:text disable-output-escaping="yes"></</xsl:text><xsl:value-of select="substring-before(@text:name,'_')"/><xsl:text disable-output-escaping="yes">></xsl:text><xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Document Title']"> + <xsl:element name="title"> + <xsl:apply-templates /> + </xsl:element> + </xsl:template> + +<xsl:template match="text:p[@text:style-name='Document SubTitle']"> +</xsl:template> + + <xsl:template match="text:p[@text:style-name='Document SubTitle']"/> + + <xsl:template match="text:p[@text:style-name='Section Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + <xsl:template match="text:p[@text:style-name='Appendix Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='VarList Item']"> + <xsl:if test="not(preceding-sibling::text:p[@text:style-name='VarList Item'])"> + <xsl:text disable-output-escaping="yes"><listitem></xsl:text> + </xsl:if> + <para> + <xsl:apply-templates/> + </para> + <xsl:if test="not(following-sibling::text:p[@text:style-name='VarList Item'])"> + <xsl:text disable-output-escaping="yes"></listitem></xsl:text> + </xsl:if> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='VarList Term']"> + <term> + <xsl:apply-templates/> + </term> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section1 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section2 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section3 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:footnote-citation"/> + + + <xsl:template match="text:p[@text:style-name='Mediaobject']"> + <mediaobject> + <xsl:apply-templates/> + </mediaobject> + </xsl:template> + + + <xsl:template match="office:annotation/text:p"> + <note> + <remark> + <xsl:apply-templates/> + </remark> + </note> + </xsl:template> + <!--<xsl:template match="meta:initial-creator"> + <author> + <xsl:apply-templates /> + </author> + </xsl:template>--> + + <xsl:template match="table:table"> + <xsl:choose> + <xsl:when test="following-sibling::text:p[@text:style-name='Table']"> + <table frame="all"> + <xsl:attribute name="id"> + <xsl:value-of select="@table:name"/> + </xsl:attribute> + <title> + <xsl:value-of select="following-sibling::text:p[@text:style-name='Table']"/> + </title> + <xsl:call-template name="generictable"/> + </table> + </xsl:when> + <xsl:otherwise> + <informaltable frame="all"> + <xsl:call-template name="generictable"/> + </informaltable> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template name="generictable"> + <xsl:variable name="cells" select="count(descendant::table:table-cell)"/> + <xsl:variable name="rows"> + <xsl:value-of select="count(descendant::table:table-row) "/> + </xsl:variable> + <xsl:variable name="cols"> + <xsl:value-of select="$cells div $rows"/> + </xsl:variable> + <xsl:variable name="numcols"> + <xsl:choose> + <xsl:when test="child::table:table-column/@table:number-columns-repeated"> + <xsl:value-of select="number(table:table-column/@table:number-columns-repeated+1)"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$cols"/> + </xsl:otherwise> + </xsl:choose> + </xsl:variable> + <xsl:element name="tgroup"> + <xsl:attribute name="cols"> + <xsl:value-of select="$numcols"/> + </xsl:attribute> + <xsl:call-template name="colspec"> + <xsl:with-param name="left" select="1"/> + </xsl:call-template> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template name="colspec"> + <xsl:param name="left"/> + <xsl:if test="number($left < ( table:table-column/@table:number-columns-repeated +2) )"> + <xsl:element name="colspec"> + <xsl:attribute name="colnum"> + <xsl:value-of select="$left"/> + </xsl:attribute> + <xsl:attribute name="colname">c + <xsl:value-of select="$left"/> + </xsl:attribute> + </xsl:element> + <xsl:call-template name="colspec"> + <xsl:with-param name="left" select="$left+1"/> + </xsl:call-template> + </xsl:if> + </xsl:template> + + + <xsl:template match="table:table-column"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="table:table-header-rows"> + <thead> + <xsl:apply-templates/> + </thead> + </xsl:template> + + + <xsl:template match="table:table-header-rows/table:table-row"> + <row> + <xsl:apply-templates/> + </row> + </xsl:template> + + + <xsl:template match="table:table/table:table-row"> + <xsl:if test="not(preceding-sibling::table:table-row)"> + <xsl:text disable-output-escaping="yes"><tbody></xsl:text> + </xsl:if> + <row> + <xsl:apply-templates/> + </row> + <xsl:if test="not(following-sibling::table:table-row)"> + <xsl:text disable-output-escaping="yes"></tbody></xsl:text> + </xsl:if> + </xsl:template> + + + <xsl:template match="table:table-cell"> + <xsl:element name="entry"> + <xsl:if test="@table:number-columns-spanned >'1'"> + <xsl:attribute name="namest"> + <xsl:value-of select="concat('c',count(preceding-sibling::table:table-cell[not(@table:number-columns-spanned)]) +sum(preceding-sibling::table:table-cell/@table:number-columns-spanned)+1)"/> + </xsl:attribute> + <xsl:attribute name="nameend"> + <xsl:value-of select="concat('c',count(preceding-sibling::table:table-cell[not(@table:number-columns-spanned)]) +sum(preceding-sibling::table:table-cell/@table:number-columns-spanned)+ @table:number-columns-spanned)"/> + </xsl:attribute> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:p"> + <xsl:choose> + <xsl:when test="@text:style-name='Table'"/> + <xsl:otherwise> + <xsl:if test="not( child::text:span[@text:style-name = 'XrefLabel'] )"> + <para> + <xsl:call-template name="id.attribute"/> + <xsl:apply-templates/> + </para> + </xsl:if> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:unordered-list"> + <xsl:choose> + <xsl:when test="@text:style-name='Var List'"> + <variablelist> + <xsl:apply-templates/> + </variablelist> + </xsl:when> + <xsl:when test="@text:style-name='UnOrdered List'"> + <variablelist> + <xsl:apply-templates/> + </variablelist> + </xsl:when> + <xsl:otherwise> + <itemizedlist> + <title/> + <xsl:apply-templates/> + </itemizedlist> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:list-item"> + <xsl:if test="parent::text:unordered-list/@text:style-name='Var List'"> + <varlistentry> + <xsl:for-each select="text:p[@text:style-name='VarList Term']"> + <xsl:apply-templates select="."/> + </xsl:for-each> + </varlistentry> + </xsl:if> + <xsl:if test="not(parent::text:unordered-list/@text:style-name='Var List')"> + <listitem> + <xsl:apply-templates/> + </listitem> + </xsl:if> + </xsl:template> + + + <xsl:template match="dc:title"/> + + + <xsl:template match="dc:description"> + <abstract> + <para> + <xsl:apply-templates/> + </para> + </abstract> + </xsl:template> + + + <xsl:template match="dc:subject"/> + + <xsl:template match="meta:generator"/> + + <xsl:template match="draw:plugin"> + <xsl:element name="audioobject"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:attribute name="width"/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:footnote"> + <footnote> + <xsl:apply-templates/> + </footnote> + </xsl:template> + + + <xsl:template match="text:footnote-body"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="draw:text-box"/> + + <xsl:template match="draw:image"> + <xsl:choose> + <xsl:when test="parent::text:p[@text:style-name='Mediaobject']"> + <xsl:element name="imageobject"> + <xsl:element name="imagedata"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="caption"> + <xsl:value-of select="."/> + </xsl:element> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:element name="inlinegraphic"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:attribute name="width"/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:span"> + <xsl:choose> + <xsl:when test="./@text:style-name='GuiMenu'"> + <xsl:element name="guimenu"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="./@text:style-name='GuiSubMenu'"> + <xsl:element name="guisubmenu"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiMenuItem'"> + <xsl:element name="guimenuitem"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiButton'"> + <xsl:element name="guibutton"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiButton'"> + <xsl:element name="guibutton"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiLabel'"> + <xsl:element name="guilabel"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Emphasis'"> + <xsl:element name="emphasis"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 4th, 2003 --> + <xsl:when test="@text:style-name='Emphasis Bold'"> + <xsl:element name="emphasis"> + <xsl:attribute name = "role" > + <xsl:text>bold</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 16th, 2003 --> + <xsl:when test="@text:style-name='Citation'"> + <xsl:element name="quote"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='FileName'"> + <xsl:element name="filename"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Application'"> + <xsl:element name="application"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Command'"> + <command> + <xsl:apply-templates/> + </command> + </xsl:when> + <xsl:when test="@text:style-name='SubScript'"> + <subscript> + <xsl:apply-templates/> + </subscript> + </xsl:when> + <xsl:when test="@text:style-name='SuperScript'"> + <superscript> + <xsl:apply-templates/> + </superscript> + </xsl:when> + <xsl:when test="@text:style-name='SystemItem'"> + <systemitem> + <xsl:apply-templates/> + </systemitem> + </xsl:when> + <xsl:when test="@text:style-name='ComputerOutput'"> + <computeroutput> + <xsl:apply-templates/> + </computeroutput> + </xsl:when> + <xsl:when test="@text:style-name='Highlight'"> + <highlight> + <xsl:apply-templates/> + </highlight> + </xsl:when> + <xsl:when test="@text:style-name='KeyCap'"> + <keycap> + <xsl:apply-templates/> + </keycap> + </xsl:when> + <xsl:when test="@text:style-name='KeySym'"> + <xsl:element name="keysym"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='KeyCombo'"> + <keycombo> + <xsl:apply-templates/> + </keycombo> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:a"> + <xsl:choose> + <xsl:when test="contains(@xlink:href,'://')"> + <xsl:element name="ulink"> + <xsl:attribute name="url"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="not(contains(@xlink:href,'#'))"> + <xsl:element name="olink"> + <xsl:attribute name="targetdocent"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="linkvar" select="substring-after(@xlink:href,'#')"/> + <xsl:element name="link"> + <xsl:attribute name="linkend"> + <xsl:value-of select="substring-before($linkvar,'%')"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:line-break"> + <xsl:text disable-output-escaping="yes"/> + </xsl:template> + + + <xsl:template match="text:tab-stop"> + <xsl:text disable-output-escaping="yes"/> + </xsl:template> + <!-- @endterm not retained due to problems with OOo method of displaying text in the reference-ref --> + + <xsl:template match="text:reference-ref"> + <xsl:element name="xref"> + <xsl:attribute name="linkend"> + <xsl:value-of select="@text:ref-name"/> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template name="id.attribute"> + <xsl:if test="child::text:reference-mark-start"> + <xsl:attribute name="id"> + <xsl:value-of select="child::text:reference-mark-start/@text:name"/> + </xsl:attribute> + </xsl:if> + <!-- Constraints imposed by OOo method of displaying reference-ref text means that xreflabel and endterm are lost --> + <!--<xsl:if test="child::text:p/text:span[@text:style-name = 'XrefLabel']"> + <xsl:attribute name="xreflabel"> + <xsl:value-of select="text:p/text:span"/> + </xsl:attribute> + </xsl:if> --> + + </xsl:template> + <!-- + <text:h text:level="1">Part One Title + <text:reference-mark-start text:name="part"/> + <text:p text:style-name="Text body"> + <text:span text:style-name="XrefLabel">xreflabel_part</text:span> + </text:p> + <text:reference-mark-end text:name="part"/> + </text:h> +--> + <!--<xsl:template match="text:p/text:span[@text:style-name = 'XrefLabel']"/>--> + + <xsl:template match="text:reference-mark-start"/> + + <xsl:template match="text:reference-mark-end"/> + + <xsl:template match="comment"> + <xsl:comment> + <xsl:value-of select="."/> + </xsl:comment> + </xsl:template> + + + <xsl:template match="text:alphabetical-index-mark-start"> + <xsl:element name="indexterm"> + <xsl:attribute name="class"> + <xsl:text disable-output-escaping="yes">startofrange</xsl:text> + </xsl:attribute> + <xsl:attribute name="id"> + <xsl:value-of select="@text:id"/> + </xsl:attribute> + <!--<xsl:if test="@text:key1">--> + + <xsl:element name="primary"> + <xsl:value-of select="@text:key1"/> + </xsl:element> + <!--</xsl:if>--> + + <xsl:if test="@text:key2"> + <xsl:element name="secondary"> + <xsl:value-of select="@text:key2"/> + </xsl:element> + </xsl:if> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:alphabetical-index-mark-end"> + <xsl:element name="indexterm"> + <xsl:attribute name="startref"> + <xsl:value-of select="@text:id"/> + </xsl:attribute> + <xsl:attribute name="class"> + <xsl:text disable-output-escaping="yes">endofrange</xsl:text> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:alphabetical-index"> + <xsl:element name="index"> + <xsl:element name="title"> + <xsl:value-of select="text:index-body/text:index-title/text:p"/> + </xsl:element> + <xsl:apply-templates select="text:index-body"/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:index-body"> + <xsl:for-each select="text:p[@text:style-name = 'Index 1']"> + <xsl:element name="indexentry"> + <xsl:element name="primaryie"> + <xsl:value-of select="."/> + </xsl:element> + <xsl:if test="key('secondary_children', generate-id())"> + <xsl:element name="secondaryie"> + <xsl:value-of select="key('secondary_children', generate-id())"/> + </xsl:element> + </xsl:if> + </xsl:element> + </xsl:for-each> + </xsl:template> + +</xsl:stylesheet> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_chapter.xsl b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_chapter.xsl new file mode 100644 index 000000000000..efb03f0a741c --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/docbook/sofftodocbookheadings_chapter.xsl @@ -0,0 +1,858 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> + +<xsl:stylesheet version="1.0" xmlns:style="http://openoffice.org/2000/style" xmlns:text="http://openoffice.org/2000/text" xmlns:office="http://openoffice.org/2000/office" xmlns:table="http://openoffice.org/2000/table" xmlns:draw="http://openoffice.org/2000/drawing" xmlns:fo="http://www.w3.org/1999/XSL/Format" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:meta="http://openoffice.org/2000/meta" xmlns:number="http://openoffice.org/2000/datastyle" xmlns:svg="http://www.w3.org/2000/svg" xmlns:chart="http://openoffice.org/2000/chart" xmlns:dr3d="http://openoffice.org/2000/dr3d" xmlns:math="http://www.w3.org/1998/Math/MathML" xmlns:form="http://openoffice.org/2000/form" xmlns:script="http://openoffice.org/2000/script" xmlns:config="http://openoffice.org/2001/config" office:class="text" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" exclude-result-prefixes="office meta table number dc fo xlink chart math script xsl draw svg dr3d form config text style"> + + <xsl:key name='headchildren' match="text:p | text:alphabetical-index | table:table | text:span | text:ordered-list | office:annotation | text:unordered-list | text:footnote | text:a | text:list-item | draw:plugin | draw:text-box | text:footnote-body | text:section" + use="generate-id((..|preceding-sibling::text:h[@text:level='1']|preceding-sibling::text:h[@text:level='2']|preceding-sibling::text:h[@text:level='3']|preceding-sibling::text:h[@text:level='4']|preceding-sibling::text:h[@text:level='5'])[last()])"/> + + <xsl:key name="children" match="text:h[@text:level='2']" + use="generate-id(preceding-sibling::text:h[@text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='3']" + use="generate-id(preceding-sibling::text:h[@text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='4']" + use="generate-id(preceding-sibling::text:h[@text:level='3' or @text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="children" match="text:h[@text:level='5']" + use="generate-id(preceding-sibling::text:h[@text:level='4' or @text:level='3' or @text:level='2' or @text:level='1'][1])"/> + + <xsl:key name="secondary_children" match="text:p[@text:style-name = 'Index 2']" + use="generate-id(preceding-sibling::text:p[@text:style-name = 'Index 1'][1])"/> + +<!-- --> + <xsl:template match="/office:document"> + <xsl:text disable-output-escaping="yes"><!DOCTYPE chapter PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN" "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" [ + </xsl:text> + <xsl:for-each select="descendant::text:variable-decl"> + <xsl:variable name="name"><xsl:value-of select="@text:name"/></xsl:variable> + <xsl:if test="contains(@text:name,'entitydecl')"> + <xsl:text disable-output-escaping="yes"><!ENTITY </xsl:text><xsl:value-of select="substring-after(@text:name,'entitydecl_')"/><xsl:text> "</xsl:text><xsl:value-of select="/descendant::text:variable-set[@text:name= $name][1]"/><xsl:text disable-output-escaping="yes">"></xsl:text> + </xsl:if> + </xsl:for-each> + + <xsl:text disable-output-escaping="yes">]></xsl:text> + <chapter> + <xsl:attribute name="lang"> + <xsl:value-of select="/office:document/office:meta/dc:language"/> + </xsl:attribute> + <xsl:apply-templates/> + </chapter> + </xsl:template> + + + <xsl:template match="text:section"> + <xsl:choose> + <xsl:when test="@text:name='ChapterInfo'"> + <chapterinfo> + <xsl:apply-templates/> + </chapterinfo> + </xsl:when> + <xsl:when test="@text:name='Abstract'"> + <abstract> + <xsl:apply-templates/> + </abstract> + </xsl:when> + <xsl:when test="@text:name='Appendix'"> + <appendix> + <xsl:apply-templates/> + </appendix> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="sectvar"><xsl:text>sect</xsl:text><xsl:value-of select="count(ancestor::text:section)+1"/></xsl:variable> + <xsl:variable name="idvar"><xsl:text> id="</xsl:text><xsl:value-of select="@text:name"/><xsl:text>"</xsl:text></xsl:variable> + <xsl:text disable-output-escaping="yes"><</xsl:text><xsl:value-of select="$sectvar"/><xsl:value-of select="$idvar"/><xsl:text disable-output-escaping="yes">></xsl:text> + <xsl:apply-templates/> + <xsl:text disable-output-escaping="yes"></</xsl:text><xsl:value-of select="$sectvar"/><xsl:text disable-output-escaping="yes">></xsl:text> + </xsl:otherwise> +</xsl:choose> + + </xsl:template> + + <xsl:template match="text:h[@text:level='1']"> + <xsl:choose> + <xsl:when test=".='Abstract'"> + <abstract> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + </abstract> + </xsl:when> + <xsl:otherwise> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="@text:level"/> + <xsl:with-param name="prev" select="1"/> + </xsl:call-template> + <!--<sect1> + <title> + <xsl:apply-templates/> + </title> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + </sect1>--> + + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:h[@text:level='2'] | text:h[@text:level='3']| text:h[@text:level='4'] | text:h[@text:level='5']"> + <xsl:variable name="level" select="@text:level"/> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="$level"/> + <xsl:with-param name="prev" select="preceding-sibling::text:h[@text:level < $level][1]/@text:level "/> + </xsl:call-template> + </xsl:template> + + + <xsl:template name="make-section"> + <xsl:param name="current"/> + <xsl:param name="prev"/> + <xsl:choose> + <xsl:when test="$current > $prev+1"> + <xsl:variable name="sect.element"> + <xsl:text disable-output-escaping="yes">sect</xsl:text> + <xsl:value-of select="$prev +1"/> + </xsl:variable> + <!--<xsl:text disable-output-escaping="yes"><sect</xsl:text><xsl:value-of select="$prev +1"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + <xsl:element name="{$sect.element}"> + <xsl:call-template name="id.attribute"/> + <title/> + <xsl:call-template name="make-section"> + <xsl:with-param name="current" select="$current"/> + <xsl:with-param name="prev" select="$prev +1"/> + </xsl:call-template> + <!--<xsl:text disable-output-escaping="yes"></sect</xsl:text><xsl:value-of select="$prev +1 "/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="sect.element"> + <xsl:text disable-output-escaping="yes">sect</xsl:text> + <xsl:value-of select="$current"/> + </xsl:variable> + <!--<xsl:text disable-output-escaping="yes"><sect</xsl:text><xsl:value-of select="$current"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + <xsl:element name="{$sect.element}"> + <xsl:call-template name="id.attribute"/> + <title> + <xsl:apply-templates/> + </title> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="key('children', generate-id())"/> + <!--<xsl:text disable-output-escaping="yes"></sect</xsl:text><xsl:value-of select="$current"/><xsl:text disable-output-escaping="yes">></xsl:text>--> + + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + <xsl:template match="text:variable-set"> + <xsl:choose> + <xsl:when test="contains(@text:name,'entitydecl')"> + <xsl:text disable-output-escaping="yes">&</xsl:text><xsl:value-of select="substring-after(@text:name,'entitydecl_')"/><xsl:text disable-output-escaping="yes">;</xsl:text> + </xsl:when> + </xsl:choose> + </xsl:template> + + <xsl:template match="text:variable-get"> + <xsl:choose> + <xsl:when test="contains(@text:name,'entitydecl')"> + <xsl:text disable-output-escaping="yes">&</xsl:text><xsl:value-of select="substring-after(@text:name,'entitydecl_')"/><xsl:text disable-output-escaping="yes">;</xsl:text> + </xsl:when> + </xsl:choose> + </xsl:template> + + + + + <xsl:template match="text:p[@text:style-name='XMLComment']"> + <xsl:comment> + <xsl:value-of select="."/> + </xsl:comment> + </xsl:template> + + <xsl:template match="text:section[@text:name = 'ChapterInfo']/text:p[not(@text:style-name='XMLComment')]"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="text:p"> + <!--text:span text:style-name="XrefLabel" --> + <!--<xsl:if test="not( child::text:span[@text:style-name = 'XrefLabel'] )"> --> + + <xsl:element name="para"> + <xsl:if test="child::text:reference-mark-start"> + <xsl:value-of select="."/> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + <!-- </xsl:if> --> + + </xsl:template> + + + <xsl:template match="office:meta"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:ordered-list"> + <orderedlist> + <xsl:apply-templates/> + </orderedlist> + </xsl:template> + + <xsl:template match="meta:editing-cycles"/> + + <xsl:template match="meta:user-defined"/> + + <xsl:template match="meta:editing-duration"/> + + <xsl:template match="dc:language"/> + + <xsl:template match="dc:date"> + <!--<pubdate> + <xsl:value-of select="substring-before(.,'T')"/> + </pubdate>--> + </xsl:template> + + <xsl:template match="meta:creation-date"/> + + <xsl:template match="office:body"> + <xsl:apply-templates select="key('headchildren', generate-id())"/> + <xsl:apply-templates select="text:h[@text:level='1']"/> + <!--<xsl:apply-templates/>--> + </xsl:template> + + <xsl:template match="office:styles"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="office:script"/> + + <xsl:template match="office:settings"/> + + <xsl:template match="office:font-decls"/> + + <xsl:template match="text:bookmark-start"> + <xsl:text disable-output-escaping="yes"><</xsl:text><xsl:value-of select="substring-before(@text:name,'_')"/><xsl:text disable-output-escaping="yes">></xsl:text><xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:bookmark-end"> + <xsl:text disable-output-escaping="yes"></</xsl:text><xsl:value-of select="substring-before(@text:name,'_')"/><xsl:text disable-output-escaping="yes">></xsl:text><xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Document Title']"> + <xsl:element name="title"> + <xsl:apply-templates /> + </xsl:element> + </xsl:template> + +<xsl:template match="text:p[@text:style-name='Document SubTitle']"> +</xsl:template> + + <xsl:template match="text:p[@text:style-name='Document SubTitle']"/> + + <xsl:template match="text:p[@text:style-name='Section Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + <xsl:template match="text:p[@text:style-name='Appendix Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='VarList Item']"> + <xsl:if test="not(preceding-sibling::text:p[@text:style-name='VarList Item'])"> + <xsl:text disable-output-escaping="yes"><listitem></xsl:text> + </xsl:if> + <para> + <xsl:apply-templates/> + </para> + <xsl:if test="not(following-sibling::text:p[@text:style-name='VarList Item'])"> + <xsl:text disable-output-escaping="yes"></listitem></xsl:text> + </xsl:if> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='VarList Term']"> + <term> + <xsl:apply-templates/> + </term> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section1 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section2 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:p[@text:style-name='Section3 Title']"> + <title> + <xsl:apply-templates/> + </title> + </xsl:template> + + + <xsl:template match="text:footnote-citation"/> + + + <xsl:template match="text:p[@text:style-name='Mediaobject']"> + <mediaobject> + <xsl:apply-templates/> + </mediaobject> + </xsl:template> + + + <xsl:template match="office:annotation/text:p"> + <note> + <remark> + <xsl:apply-templates/> + </remark> + </note> + </xsl:template> + <!--<xsl:template match="meta:initial-creator"> + <author> + <xsl:apply-templates /> + </author> + </xsl:template>--> + + <xsl:template match="table:table"> + <xsl:choose> + <xsl:when test="following-sibling::text:p[@text:style-name='Table']"> + <table frame="all"> + <xsl:attribute name="id"> + <xsl:value-of select="@table:name"/> + </xsl:attribute> + <title> + <xsl:value-of select="following-sibling::text:p[@text:style-name='Table']"/> + </title> + <xsl:call-template name="generictable"/> + </table> + </xsl:when> + <xsl:otherwise> + <informaltable frame="all"> + <xsl:call-template name="generictable"/> + </informaltable> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template name="generictable"> + <xsl:variable name="cells" select="count(descendant::table:table-cell)"/> + <xsl:variable name="rows"> + <xsl:value-of select="count(descendant::table:table-row) "/> + </xsl:variable> + <xsl:variable name="cols"> + <xsl:value-of select="$cells div $rows"/> + </xsl:variable> + <xsl:variable name="numcols"> + <xsl:choose> + <xsl:when test="child::table:table-column/@table:number-columns-repeated"> + <xsl:value-of select="number(table:table-column/@table:number-columns-repeated+1)"/> + </xsl:when> + <xsl:otherwise> + <xsl:value-of select="$cols"/> + </xsl:otherwise> + </xsl:choose> + </xsl:variable> + <xsl:element name="tgroup"> + <xsl:attribute name="cols"> + <xsl:value-of select="$numcols"/> + </xsl:attribute> + <xsl:call-template name="colspec"> + <xsl:with-param name="left" select="1"/> + </xsl:call-template> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template name="colspec"> + <xsl:param name="left"/> + <xsl:if test="number($left < ( table:table-column/@table:number-columns-repeated +2) )"> + <xsl:element name="colspec"> + <xsl:attribute name="colnum"> + <xsl:value-of select="$left"/> + </xsl:attribute> + <xsl:attribute name="colname">c + <xsl:value-of select="$left"/> + </xsl:attribute> + </xsl:element> + <xsl:call-template name="colspec"> + <xsl:with-param name="left" select="$left+1"/> + </xsl:call-template> + </xsl:if> + </xsl:template> + + + <xsl:template match="table:table-column"> + <xsl:apply-templates/> + </xsl:template> + + + <xsl:template match="table:table-header-rows"> + <thead> + <xsl:apply-templates/> + </thead> + </xsl:template> + + + <xsl:template match="table:table-header-rows/table:table-row"> + <row> + <xsl:apply-templates/> + </row> + </xsl:template> + + + <xsl:template match="table:table/table:table-row"> + <xsl:if test="not(preceding-sibling::table:table-row)"> + <xsl:text disable-output-escaping="yes"><tbody></xsl:text> + </xsl:if> + <row> + <xsl:apply-templates/> + </row> + <xsl:if test="not(following-sibling::table:table-row)"> + <xsl:text disable-output-escaping="yes"></tbody></xsl:text> + </xsl:if> + </xsl:template> + + + <xsl:template match="table:table-cell"> + <xsl:element name="entry"> + <xsl:if test="@table:number-columns-spanned >'1'"> + <xsl:attribute name="namest"> + <xsl:value-of select="concat('c',count(preceding-sibling::table:table-cell[not(@table:number-columns-spanned)]) +sum(preceding-sibling::table:table-cell/@table:number-columns-spanned)+1)"/> + </xsl:attribute> + <xsl:attribute name="nameend"> + <xsl:value-of select="concat('c',count(preceding-sibling::table:table-cell[not(@table:number-columns-spanned)]) +sum(preceding-sibling::table:table-cell/@table:number-columns-spanned)+ @table:number-columns-spanned)"/> + </xsl:attribute> + </xsl:if> + <xsl:apply-templates/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:p"> + <xsl:choose> + <xsl:when test="@text:style-name='Table'"/> + <xsl:otherwise> + <xsl:if test="not( child::text:span[@text:style-name = 'XrefLabel'] )"> + <para> + <xsl:call-template name="id.attribute"/> + <xsl:apply-templates/> + </para> + </xsl:if> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:unordered-list"> + <xsl:choose> + <xsl:when test="@text:style-name='Var List'"> + <variablelist> + <xsl:apply-templates/> + </variablelist> + </xsl:when> + <xsl:when test="@text:style-name='UnOrdered List'"> + <variablelist> + <xsl:apply-templates/> + </variablelist> + </xsl:when> + <xsl:otherwise> + <itemizedlist> + <title/> + <xsl:apply-templates/> + </itemizedlist> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:list-item"> + <xsl:if test="parent::text:unordered-list/@text:style-name='Var List'"> + <varlistentry> + <xsl:for-each select="text:p[@text:style-name='VarList Term']"> + <xsl:apply-templates select="."/> + </xsl:for-each> + </varlistentry> + </xsl:if> + <xsl:if test="not(parent::text:unordered-list/@text:style-name='Var List')"> + <listitem> + <xsl:apply-templates/> + </listitem> + </xsl:if> + </xsl:template> + + + <xsl:template match="dc:title"/> + + + <xsl:template match="dc:description"> + <abstract> + <para> + <xsl:apply-templates/> + </para> + </abstract> + </xsl:template> + + + <xsl:template match="dc:subject"/> + + <xsl:template match="meta:generator"/> + + <xsl:template match="draw:plugin"> + <xsl:element name="audioobject"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:attribute name="width"/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:footnote"> + <footnote> + <xsl:apply-templates/> + </footnote> + </xsl:template> + + + <xsl:template match="text:footnote-body"> + <xsl:apply-templates/> + </xsl:template> + + <xsl:template match="draw:text-box"/> + + <xsl:template match="draw:image"> + <xsl:choose> + <xsl:when test="parent::text:p[@text:style-name='Mediaobject']"> + <xsl:element name="imageobject"> + <xsl:element name="imagedata"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + </xsl:element> + <xsl:element name="caption"> + <xsl:value-of select="."/> + </xsl:element> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:element name="inlinegraphic"> + <xsl:attribute name="fileref"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:attribute name="width"/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:span"> + <xsl:choose> + <xsl:when test="./@text:style-name='GuiMenu'"> + <xsl:element name="guimenu"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="./@text:style-name='GuiSubMenu'"> + <xsl:element name="guisubmenu"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiMenuItem'"> + <xsl:element name="guimenuitem"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiButton'"> + <xsl:element name="guibutton"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiButton'"> + <xsl:element name="guibutton"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='GuiLabel'"> + <xsl:element name="guilabel"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Emphasis'"> + <xsl:element name="emphasis"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 4th, 2003 --> + <xsl:when test="@text:style-name='Emphasis Bold'"> + <xsl:element name="emphasis"> + <xsl:attribute name = "role" > + <xsl:text >bold</xsl:text> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> +<!-- Change Made By Kevin Fowlks (fowlks@msu.edu) June 16th, 2003 --> + <xsl:when test="@text:style-name='Citation'"> + <xsl:element name="quote"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='FileName'"> + <xsl:element name="filename"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Application'"> + <xsl:element name="application"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='Command'"> + <command> + <xsl:apply-templates/> + </command> + </xsl:when> + <xsl:when test="@text:style-name='SubScript'"> + <subscript> + <xsl:apply-templates/> + </subscript> + </xsl:when> + <xsl:when test="@text:style-name='SuperScript'"> + <superscript> + <xsl:apply-templates/> + </superscript> + </xsl:when> + <xsl:when test="@text:style-name='SystemItem'"> + <systemitem> + <xsl:apply-templates/> + </systemitem> + </xsl:when> + <xsl:when test="@text:style-name='ComputerOutput'"> + <computeroutput> + <xsl:apply-templates/> + </computeroutput> + </xsl:when> + <xsl:when test="@text:style-name='Highlight'"> + <highlight> + <xsl:apply-templates/> + </highlight> + </xsl:when> + <xsl:when test="@text:style-name='KeyCap'"> + <keycap> + <xsl:apply-templates/> + </keycap> + </xsl:when> + <xsl:when test="@text:style-name='KeySym'"> + <xsl:element name="keysym"> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="@text:style-name='KeyCombo'"> + <keycombo> + <xsl:apply-templates/> + </keycombo> + </xsl:when> + <xsl:otherwise> + <xsl:apply-templates/> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:a"> + <xsl:choose> + <xsl:when test="contains(@xlink:href,'://')"> + <xsl:element name="ulink"> + <xsl:attribute name="url"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:when test="not(contains(@xlink:href,'#'))"> + <xsl:element name="olink"> + <xsl:attribute name="targetdocent"> + <xsl:value-of select="@xlink:href"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:when> + <xsl:otherwise> + <xsl:variable name="linkvar" select="substring-after(@xlink:href,'#')"/> + <xsl:element name="link"> + <xsl:attribute name="linkend"> + <xsl:value-of select="substring-before($linkvar,'%')"/> + </xsl:attribute> + <xsl:apply-templates/> + </xsl:element> + </xsl:otherwise> + </xsl:choose> + </xsl:template> + + + <xsl:template match="text:line-break"> + <xsl:text disable-output-escaping="yes"/> + </xsl:template> + + + <xsl:template match="text:tab-stop"> + <xsl:text disable-output-escaping="yes"/> + </xsl:template> + <!-- @endterm not retained due to problems with OOo method of displaying text in the reference-ref --> + + <xsl:template match="text:reference-ref"> + <xsl:element name="xref"> + <xsl:attribute name="linkend"> + <xsl:value-of select="@text:ref-name"/> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template name="id.attribute"> + <xsl:if test="child::text:reference-mark-start"> + <xsl:attribute name="id"> + <xsl:value-of select="child::text:reference-mark-start/@text:name"/> + </xsl:attribute> + </xsl:if> + <!-- Constraints imposed by OOo method of displaying reference-ref text means that xreflabel and endterm are lost --> + <!--<xsl:if test="child::text:p/text:span[@text:style-name = 'XrefLabel']"> + <xsl:attribute name="xreflabel"> + <xsl:value-of select="text:p/text:span"/> + </xsl:attribute> + </xsl:if> --> + + </xsl:template> + <!-- + <text:h text:level="1">Part One Title + <text:reference-mark-start text:name="part"/> + <text:p text:style-name="Text body"> + <text:span text:style-name="XrefLabel">xreflabel_part</text:span> + </text:p> + <text:reference-mark-end text:name="part"/> + </text:h> +--> + <!--<xsl:template match="text:p/text:span[@text:style-name = 'XrefLabel']"/>--> + + <xsl:template match="text:reference-mark-start"/> + + <xsl:template match="text:reference-mark-end"/> + + <xsl:template match="comment"> + <xsl:comment> + <xsl:value-of select="."/> + </xsl:comment> + </xsl:template> + + + <xsl:template match="text:alphabetical-index-mark-start"> + <xsl:element name="indexterm"> + <xsl:attribute name="class"> + <xsl:text disable-output-escaping="yes">startofrange</xsl:text> + </xsl:attribute> + <xsl:attribute name="id"> + <xsl:value-of select="@text:id"/> + </xsl:attribute> + <!--<xsl:if test="@text:key1">--> + + <xsl:element name="primary"> + <xsl:value-of select="@text:key1"/> + </xsl:element> + <!--</xsl:if>--> + + <xsl:if test="@text:key2"> + <xsl:element name="secondary"> + <xsl:value-of select="@text:key2"/> + </xsl:element> + </xsl:if> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:alphabetical-index-mark-end"> + <xsl:element name="indexterm"> + <xsl:attribute name="startref"> + <xsl:value-of select="@text:id"/> + </xsl:attribute> + <xsl:attribute name="class"> + <xsl:text disable-output-escaping="yes">endofrange</xsl:text> + </xsl:attribute> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:alphabetical-index"> + <xsl:element name="index"> + <xsl:element name="title"> + <xsl:value-of select="text:index-body/text:index-title/text:p"/> + </xsl:element> + <xsl:apply-templates select="text:index-body"/> + </xsl:element> + </xsl:template> + + + <xsl:template match="text:index-body"> + <xsl:for-each select="text:p[@text:style-name = 'Index 1']"> + <xsl:element name="indexentry"> + <xsl:element name="primaryie"> + <xsl:value-of select="."/> + </xsl:element> + <xsl:if test="key('secondary_children', generate-id())"> + <xsl:element name="secondaryie"> + <xsl:value-of select="key('secondary_children', generate-id())"/> + </xsl:element> + </xsl:if> + </xsl:element> + </xsl:for-each> + </xsl:template> + +</xsl:stylesheet> + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/htmltosoff.xsl b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/htmltosoff.xsl new file mode 100644 index 000000000000..baf160c1449e --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/htmltosoff.xsl @@ -0,0 +1,174 @@ +<?xml version='1.0' encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" + xmlns:office="http://openoffice.org/2000/office" + xmlns:style="http://openoffice.org/2000/style" + xmlns:text="http://openoffice.org/2000/text" + xmlns:table="http://openoffice.org/2000/table" + xmlns:draw="http://openoffice.org/2000/drawing" + xmlns:fo="http://www.w3.org/1999/XSL/Format" + xmlns:xlink="http://www.w3.org/1999/xlink" + xmlns:number="http://openoffice.org/2000/datastyle" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns:chart="http://openoffice.org/2000/chart" + xmlns:dr3d="http://openoffice.org/2000/dr3d" + xmlns:math="http://www.w3.org/1998/Math/MathML" + xmlns:form="http://openoffice.org/2000/form" + xmlns:script="http://openoffice.org/2000/script" + > +<xsl:output method="xml" /> + + +<xsl:template match="/"> + <xsl:apply-templates /> +</xsl:template> + +<xsl:template match="html"> + + <office:document-content xmlns:office="http://openoffice.org/2000/office" + xmlns:style="http://openoffice.org/2000/style" + xmlns:text="http://openoffice.org/2000/text" + xmlns:table="http://openoffice.org/2000/table" + xmlns:draw="http://openoffice.org/2000/drawing" + xmlns:fo="http://www.w3.org/1999/XSL/Format" + xmlns:xlink="http://www.w3.org/1999/xlink" + xmlns:number="http://openoffice.org/2000/datastyle" + xmlns:svg="http://www.w3.org/2000/svg" + xmlns:chart="http://openoffice.org/2000/chart" + xmlns:dr3d="http://openoffice.org/2000/dr3d" + xmlns:math="http://www.w3.org/1998/Math/MathML" + xmlns:form="http://openoffice.org/2000/form" + xmlns:script="http://openoffice.org/2000/script" + office:class="text" office:version="1.0"> + +<office:script/> + <office:font-decls> + <style:font-decl style:name="Letter Gothic" fo:font-family="'Letter Gothic'" style:font-family-generic="modern" style:font-pitch="fixed"/> + <style:font-decl style:name="Arial Unicode MS" fo:font-family="'Arial Unicode MS'" style:font-pitch="variable"/> + <style:font-decl style:name="HG Mincho Light J" fo:font-family="'HG Mincho Light J'" style:font-pitch="variable"/> + <style:font-decl style:name="CG Times" fo:font-family="'CG Times'" style:font-family-generic="roman" style:font-pitch="variable"/> + <style:font-decl style:name="Thorndale" fo:font-family="Thorndale" style:font-family-generic="roman" style:font-pitch="variable"/> + <style:font-decl style:name="Antique Olive" fo:font-family="'Antique Olive'" style:font-family-generic="swiss" style:font-pitch="variable"/> + <style:font-decl style:name="Arial Black" fo:font-family="'Arial Black'" style:font-family-generic="swiss" style:font-pitch="variable"/> + </office:font-decls> + <office:automatic-styles> + <style:style style:name="Table1" style:family="table"> + <style:properties style:width="16.999cm" table:align="margins"/> + </style:style> + <style:style style:name="Table1.A" style:family="table-column"> + <style:properties style:column-width="3.399cm" style:rel-column-width="13107*"/> + </style:style> + <style:style style:name="Table1.A1" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="none" fo:border-top="0.002cm solid #000000" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.E1" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.A2" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="none" fo:border-top="none" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="Table1.E2" style:family="table-cell"> + <style:properties fo:padding="0.097cm" fo:border-left="0.002cm solid #000000" fo:border-right="0.002cm solid #000000" fo:border-top="none" fo:border-bottom="0.002cm solid #000000"/> + </style:style> + <style:style style:name="P1" style:family="paragraph" style:parent-style-name="Standard"> + <style:properties fo:margin-left="0cm" fo:margin-right="0cm" fo:text-indent="0cm" style:auto-text-indent="false"/> + </style:style> + <style:style style:name="P2" style:family="paragraph" style:parent-style-name="Table Contents"> + <style:properties style:font-name="Arial Black" fo:font-size="20pt"/> + </style:style> + </office:automatic-styles> + + + + + + <office:body> + <text:sequence-decls> + <text:sequence-decl text:display-outline-level="0" text:name="Illustration"/> + <text:sequence-decl text:display-outline-level="0" text:name="Table"/> + <text:sequence-decl text:display-outline-level="0" text:name="Text"/> + <text:sequence-decl text:display-outline-level="0" text:name="Drawing"/> + </text:sequence-decls> + + <xsl:apply-templates/> + </office:body> + </office:document-content> + +</xsl:template> + +<xsl:template match="body"> + <xsl:apply-templates /> +</xsl:template> + + + +<xsl:template match="p"> + <xsl:for-each select="."> + <text:p text:style-name="P1"> + <!--<xsl:value-of select="."/>--> + <xsl:apply-templates /> + </text:p> + </xsl:for-each> +</xsl:template> + +<xsl:template match="br"> + <xsl:if test="ancestor::p"> + <xsl:text disable-output-escaping="yes"></text:p> <text:p text:style-name="P1"></xsl:text> + </xsl:if> +</xsl:template> + +<xsl:template match="table"> + <xsl:for-each select="."> + <table:table table:name="Table1" table:style-name="Table1"> + <table:table-column table:style-name="Table1.A" table:number-columns-repeated="5"/> + <xsl:apply-templates/> + </table:table> + </xsl:for-each> +</xsl:template> + +<xsl:template match="tr"> + <xsl:for-each select="."> + <table:table-row> + <xsl:apply-templates/> + </table:table-row> + </xsl:for-each> +</xsl:template> + +<xsl:template match="td"> + <xsl:for-each select="."> + <table:table-cell table:style-name="Table1.A1" table:value-type="string"> + <text:p text:style-name="P1"> + <xsl:value-of select="."/> + </text:p> + </table:table-cell> + </xsl:for-each> +</xsl:template> + + + +</xsl:stylesheet> diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/makefile.mk b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/makefile.mk new file mode 100644 index 000000000000..06e0d14909dc --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/makefile.mk @@ -0,0 +1,32 @@ +#*************************************************************************** +# +# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. +# +# Copyright 2000, 2010 Oracle and/or its affiliates. +# +# OpenOffice.org - a multi-platform office productivity suite +# +# This file is part of OpenOffice.org. +# +# OpenOffice.org is free software: you can redistribute it and/or modify +# it under the terms of the GNU Lesser General Public License version 3 +# only, as published by the Free Software Foundation. +# +# OpenOffice.org is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU Lesser General Public License version 3 for more details +# (a copy is included in the LICENSE file that accompanied this code). +# +# You should have received a copy of the GNU Lesser General Public License +# version 3 along with OpenOffice.org. If not, see +# <http://www.openoffice.org/license.html> +# for a copy of the LGPLv3 License. +# +#*************************************************************************** + +TARGET=xmrg_jooxcx_xslt +PRJ=../../../../../../.. + +.INCLUDE : ant.mk +ALLTAR: ANTBUILD diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/package.html b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/package.html new file mode 100644 index 000000000000..0a689fb47cda --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/package.html @@ -0,0 +1,65 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN"> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<HTML> +<HEAD> + <TITLE>org.openoffice.xmerge.converter.xml.xslt package</TITLE> +</HEAD> +<BODY> +<P>Provides the tools for doing the conversion of StarWriter XML to +and from supported formats, through the use of an XSLT +transformation.</P> +<P>It follows the {@link org.openoffice.xmerge} +framework for the conversion process.</P> +<P>This converter does not currently support merge.</P> +<P><FONT FACE="Times New Roman, serif"><FONT SIZE=5><B>XSLT +Transformation</B></FONT></FONT></P> +<p>The converter makes use +of one or more XSLT style sheets, which are used in the +DocumentSerializer and DocumentDeserializer, to perform the actual +translations. The location of these stylesheets is extracted from the {@link org.openoffice.xmerge.util.registry.ConverterInfo ConverterInfo} data structure, and are specified using the optional converter-xslt-serialize and converter-xsltdeserialize tags in a plugins converter.xml file. Please refer to the SDK document for more information about how to implement a Plugin Configuration XML File for a specific plugin. +A sample OpenOffice to Html stylesheet and Html to +Openffice stylesheet, has been provided as a sample implementation. +The converter also makes use of an XsltPlugin.properties file, which may be edited by the user to provide MIME-TYPE to file extension mappings. This file is used by the {@link org.openoffice.xmerge.converter.xml.xslt.PluginFactoryImpl getDeviceFileExtension} method. +</p> + +<H2>TODO list</H2> + +<p><ol> +<li>Expand XSLT style sheets to support more office/html + capabilities</li> +<li>Add support for certain character codes, such as &nbsp + which currently causes the transformer to break.</li> +<li>Change the DocumentDeserializer transformer, so that the DOMResult is serialized using the xalan serializer and create an SxwDocument from the result</li> +</ol></p> + +@see org.openoffice.xmerge.util.registry + +</BODY> +</HTML> + + diff --git a/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/sofftohtml.xsl b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/sofftohtml.xsl new file mode 100644 index 000000000000..761a66a3f6e4 --- /dev/null +++ b/xmerge/java/org/openoffice/xmerge/converter/xml/xslt/sofftohtml.xsl @@ -0,0 +1,28 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + + DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + + Copyright 2000, 2010 Oracle and/or its affiliates. + + OpenOffice.org - a multi-platform office productivity suite + + This file is part of OpenOffice.org. + + OpenOffice.org is free software: you can redistribute it and/or modify + it under the terms of the GNU Lesser General Public License version 3 + only, as published by the Free Software Foundation. + + OpenOffice.org is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Lesser General Public License version 3 for more details + (a copy is included in the LICENSE file that accompanied this code). + + You should have received a copy of the GNU Lesser General Public License + version 3 along with OpenOffice.org. If not, see + <http://www.openoffice.org/license.html> + for a copy of the LGPLv3 License. + +--> +<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform" xmlns:style="http://openoffice.org/2000/style" xmlns:table="http://openoffice.org/2000/table" xmlns:text="http://openoffice.org/2000/text" xmlns:office="http://openoffice.org/2000/office" xmlns:fo="http://www.w3.org/1999/XSL/Format"> <xsl:output method="xml" omit-xml-declaration="yes" indent="yes" encoding="ISO-8859-1"/> <!--doctype-system=[<!ENTITY acirc "">] --> <xsl:strip-space elements="tokens"/> <xsl:template match="office:document"> <html> <xsl:apply-templates /> </html> </xsl:template> <xsl:template match="office:document-content"> <html> <xsl:apply-templates /> </html> </xsl:template> <xsl:template match="office:automatic-styles"> <style type="text/css"> p.Table-Heading{font-weight :bold;} <xsl:apply-templates /> </style> </xsl:template> <xsl:template match="office:styles"> </xsl:template> <xsl:template match="office:meta"> </xsl:template> <xsl:template match="office:settings"> </xsl:template> <xsl:template match="style:style"> <xsl:if test="@style:family ='paragraph'"> p.<xsl:value-of select="@style:name"/>{ <xsl:apply-templates />} </xsl:if> <xsl:if test="@style:family ='paragraph'"> p.<xsl:value-of select="@style:name"/>{ <xsl:if test="@style:parent-style-name='Table Heading'"> font-weight :bold;font-style:italic; </xsl:if> <xsl:apply-templates />} </xsl:if> <xsl:if test="@style:family ='table-cell'"> td.<xsl:value-of select="@style:name"/>{ <xsl:if test="@style:parent-style-name='Table Heading'"> font-weight :bold;font-style:italic; </xsl:if> <xsl:apply-templates />} </xsl:if> </xsl:template> <xsl:template match="style:properties"> <!--<xsl:param name="style" select="@fo:font-weight"/>--> <xsl:if test="@fo:font-weight"> font-weight :<xsl:value-of select="@fo:font-weight"/>; </xsl:if> <xsl:if test="@fo:font-style"> font-style :<xsl:value-of select="@fo:font-style"/>; </xsl:if> <xsl:if test="@style:font-name"> font-family :<xsl:value-of select="@style:font-name"/>; </xsl:if> <xsl:if test="@fo:font-size"> font-size : <xsl:value-of select="@fo:font-size"/>; </xsl:if> <xsl:if test="@style:text-underline='single'"> text-decoration :underline; </xsl:if> <xsl:if test="@style:text-crossing-out='single-line'"> text-decoration:line-through; </xsl:if> <xsl:if test="@fo:text-align='start'"> text-align :left </xsl:if> <xsl:if test="@fo:text-align='center'"> text-align :center </xsl:if> <xsl:if test="@fo:text-align='end'"> text-align :right </xsl:if> <!--<xsl:value-of select="$style"/>--> </xsl:template> <xsl:template match="office:body"> <xsl:apply-templates /> </xsl:template> <xsl:template match="table:table"> <table border="1" cellpadding="2" width="100%"> <xsl:apply-templates /> </table> </xsl:template> <xsl:template match="table:table-header-rows"> <th> <xsl:apply-templates /> </th> </xsl:template> <xsl:template match="table:table-row"> <tr> <xsl:apply-templates /> </tr> </xsl:template> <xsl:template match="table:table-cell"> <xsl:text disable-output-escaping="yes"><td class="</xsl:text> <xsl:value-of select="@table:style-name"/> <xsl:text disable-output-escaping="yes">"></xsl:text> <!--<xsl:value-of select="."/>--> <xsl:apply-templates /> <xsl:text disable-output-escaping="yes"></td></xsl:text> <!--<td width="20%"> <xsl:apply-templates /> </td>--> </xsl:template> <xsl:template match="text:p"> <xsl:if test="ancestor-or-self::table:table-cell"> <xsl:if test=".=''"> <br/> </xsl:if> </xsl:if> <xsl:text disable-output-escaping="yes"><p class="</xsl:text> <xsl:choose> <xsl:when test="@text:style-name ='Table Heading'"> Table-Heading </xsl:when> <xsl:otherwise> <xsl:value-of select="@text:style-name"/> </xsl:otherwise> </xsl:choose> <xsl:text disable-output-escaping="yes">"></xsl:text> <xsl:apply-templates/> <xsl:text disable-output-escaping="yes"></p></xsl:text> <!--<xsl:value-of select="."/>--> <!--<xsl:text disable-output-escaping="yes">&nbsp;</xsl:text>--> <!--<br/>--> </xsl:template> </xsl:stylesheet> |