summaryrefslogtreecommitdiff
path: root/setup_native/source/ulfconv
diff options
context:
space:
mode:
authorOliver Bolte <obo@openoffice.org>2004-10-18 13:08:04 +0000
committerOliver Bolte <obo@openoffice.org>2004-10-18 13:08:04 +0000
commit29a93687ec4942b7f507ee114042e45ef3f8da01 (patch)
treeee3528f6681b012f9b6cf1482005f4966550a5e5 /setup_native/source/ulfconv
parent319fbe258bf2ba1fa7a182c8add996a96932f07e (diff)
INTEGRATION: CWS langsupporter (1.1.2); FILE ADDED
2004/09/22 07:24:46 obr 1.1.2.2: #i33873# replace fprintf with fputs 2004/09/22 06:52:43 obr 1.1.2.1: #i33873# ulf file converter tool
Diffstat (limited to 'setup_native/source/ulfconv')
-rw-r--r--setup_native/source/ulfconv/ulfconv.cxx387
1 files changed, 387 insertions, 0 deletions
diff --git a/setup_native/source/ulfconv/ulfconv.cxx b/setup_native/source/ulfconv/ulfconv.cxx
new file mode 100644
index 000000000000..6d50227b4c2a
--- /dev/null
+++ b/setup_native/source/ulfconv/ulfconv.cxx
@@ -0,0 +1,387 @@
+/*************************************************************************
+ *
+ * $RCSfile: ulfconv.cxx,v $
+ *
+ * $Revision: 1.2 $
+ *
+ * last change: $Author: obo $ $Date: 2004-10-18 14:08:04 $
+ *
+ * The Contents of this file are made available subject to the terms of
+ * either of the following licenses
+ *
+ * - GNU Lesser General Public License Version 2.1
+ * - Sun Industry Standards Source License Version 1.1
+ *
+ * Sun Microsystems Inc., October, 2000
+ *
+ * GNU Lesser General Public License Version 2.1
+ * =============================================
+ * Copyright 2000 by Sun Microsystems, Inc.
+ * 901 San Antonio Road, Palo Alto, CA 94303, USA
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1, as published by the Free Software Foundation.
+ *
+ * This library 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 for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston,
+ * MA 02111-1307 USA
+ *
+ *
+ * Sun Industry Standards Source License Version 1.1
+ * =================================================
+ * The contents of this file are subject to the Sun Industry Standards
+ * Source License Version 1.1 (the "License"); You may not use this file
+ * except in compliance with the License. You may obtain a copy of the
+ * License at http://www.openoffice.org/license.html.
+ *
+ * Software provided under this License is provided on an "AS IS" basis,
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * WITHOUT LIMITATION, WARRANTIES THAT THE SOFTWARE IS FREE OF DEFECTS,
+ * MERCHANTABLE, FIT FOR A PARTICULAR PURPOSE, OR NON-INFRINGING.
+ * See the License for the specific provisions governing your rights and
+ * obligations concerning the Software.
+ *
+ * The Initial Developer of the Original Code is: Sun Microsystems, Inc.
+ *
+ * Copyright: 2000 by Sun Microsystems, Inc.
+ *
+ * All Rights Reserved.
+ *
+ * Contributor(s): _______________________________________
+ *
+ *
+ ************************************************************************/
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <string.h>
+#include <unistd.h>
+#include <ctype.h>
+
+#if !(defined NETBSD || defined FREEBSD || defined MACOSX || WNT)
+#include <alloca.h>
+#endif
+
+#ifdef WNT
+#include <malloc.h>
+#define alloca _alloca
+#endif
+
+#include <rtl/ustring.hxx>
+
+#include <map>
+#include <string>
+
+/*****************************************************************************/
+/* typedefs
+/*****************************************************************************/
+
+typedef std::map< const std::string, rtl_TextEncoding > EncodingMap;
+
+typedef struct {
+ const char *key;
+ const rtl_TextEncoding value;
+} _pair;
+
+static int _pair_compare (const char *key, const _pair *pair);
+static const _pair* _pair_search (const char *key, const _pair *base, unsigned int member );
+
+
+const _pair _ms_encoding_list[] = {
+ { "0", RTL_TEXTENCODING_UTF8 },
+ { "1250", RTL_TEXTENCODING_MS_1250 },
+ { "1251", RTL_TEXTENCODING_MS_1251 },
+ { "1252", RTL_TEXTENCODING_MS_1252 },
+ { "1253", RTL_TEXTENCODING_MS_1253 },
+ { "1254", RTL_TEXTENCODING_MS_1254 },
+ { "1255", RTL_TEXTENCODING_MS_1255 },
+ { "1256", RTL_TEXTENCODING_MS_1256 },
+ { "1257", RTL_TEXTENCODING_MS_1257 },
+ { "1258", RTL_TEXTENCODING_MS_1258 },
+ { "874", RTL_TEXTENCODING_MS_874 },
+ { "932", RTL_TEXTENCODING_MS_932 },
+ { "936", RTL_TEXTENCODING_MS_936 },
+ { "949", RTL_TEXTENCODING_MS_949 },
+ { "950", RTL_TEXTENCODING_MS_950 }
+};
+
+
+/*****************************************************************************/
+/* fgets that work with unix line ends on Windows
+/*****************************************************************************/
+
+char * my_fgets(char *s, int n, FILE *fp)
+{
+ int i;
+ for( i=0; i < n-1; i++ )
+ {
+ int c = getc(fp);
+
+ if( c == EOF )
+ break;
+
+ s[i] = (char) c;
+
+ if( s[i] == '\n' )
+ {
+ i++;
+ break;
+ }
+ }
+
+ if( i>0 )
+ {
+ s[i] = '\0';
+ return s;
+ }
+ else
+ {
+ return NULL;
+ }
+}
+
+/*****************************************************************************/
+/* compare function for binary search
+/*****************************************************************************/
+
+static int
+_pair_compare (const char *key, const _pair *pair)
+{
+ int result = rtl_str_compareIgnoreAsciiCase( key, pair->key );
+ return result;
+}
+
+/*****************************************************************************/
+/* binary search on encoding tables
+/*****************************************************************************/
+
+static const _pair*
+_pair_search (const char *key, const _pair *base, unsigned int member )
+{
+ unsigned int lower = 0;
+ unsigned int upper = member;
+ unsigned int current;
+ int comparison;
+
+ /* check for validity of input */
+ if ( (key == NULL) || (base == NULL) || (member == 0) )
+ return NULL;
+
+ /* binary search */
+ while ( lower < upper )
+ {
+ current = (lower + upper) / 2;
+ comparison = _pair_compare( key, base + current );
+ if (comparison < 0)
+ upper = current;
+ else
+ if (comparison > 0)
+ lower = current + 1;
+ else
+ return base + current;
+ }
+
+ return NULL;
+}
+
+
+/************************************************************************
+ * read_encoding_table
+ ************************************************************************/
+
+void read_encoding_table(char * file, EncodingMap& aEncodingMap)
+{
+ int nlang = 0;
+
+ FILE * fp = fopen(file, "r");
+ if ( ! fp ) {
+ fprintf(stderr, "ulfconv: %s %s\n", file, strerror(errno));
+ exit(2);
+ }
+
+ char buffer[512];
+ while ( NULL != my_fgets(buffer, sizeof(buffer), fp) ) {
+
+ // strip comment lines
+ if ( buffer[0] == '#' )
+ continue;
+
+ // find end of language string
+ char * cp;
+ for ( cp = buffer; ! isspace(*cp); cp++ )
+ ;
+ *cp = '\0';
+
+ // find start of codepage string
+ for ( ++cp; isspace(*cp); ++cp )
+ ;
+ char * codepage = cp;
+
+ // find end of codepage string
+ for ( ++cp; ! isspace(*cp); ++cp )
+ ;
+ *cp = '\0';
+
+ // find the correct mapping for codepage
+ const unsigned int members = sizeof( _ms_encoding_list ) / sizeof( _pair );
+ const _pair *encoding = _pair_search( codepage, _ms_encoding_list, members );
+
+ if ( encoding != NULL ) {
+ const std::string language(buffer);
+ aEncodingMap.insert( EncodingMap::value_type(language, encoding->value) );
+ }
+ }
+}
+
+/************************************************************************
+ * print_legacy_mixed
+ ************************************************************************/
+
+void print_legacy_mixed(
+ FILE * ostream,
+ const rtl::OUString& aString,
+ const std::string& language,
+ EncodingMap& aEncodingMap)
+{
+ EncodingMap::iterator iter = aEncodingMap.find(language);
+
+ if ( iter != aEncodingMap.end() ) {
+ fputs(OUStringToOString(aString, iter->second).getStr(), ostream);
+ } else {
+ fprintf(stderr, "ulfconv: WARNING: no legacy encoding found for %s\n", language.c_str());
+ }
+}
+
+/************************************************************************
+ * print_java_style
+ ************************************************************************/
+
+void print_java_style(FILE * ostream, const rtl::OUString& aString)
+{
+ int imax = aString.getLength();
+ for (int i = 0; i < imax; i++) {
+ sal_Unicode uc = aString[i];
+ if ( uc < 128 ) {
+ fprintf(ostream, "%c", (char) uc);
+ } else {
+ fprintf(ostream, "\\u%2.2x%2.2x", uc >> 8, uc & 0xFF );
+ }
+ }
+}
+
+/************************************************************************
+ * main
+ ************************************************************************/
+
+int main( int argc, char * const argv[] )
+{
+ EncodingMap aEncodingMap;
+
+ FILE *istream = stdin;
+ FILE *ostream = stdout;
+
+ int errflg = 0;
+ int argi;
+
+ for( argi=1; argi < argc; argi++ )
+ {
+ if( argv[argi][0] == '-' && argv[argi][2] == '\0' )
+ {
+ switch(argv[argi][1]) {
+ case 'o':
+ if (argi+1 >= argc || argv[argi+1][0] == '-')
+ {
+ fprintf(stderr, "Option -%c requires an operand\n", argv[argi]);
+ errflg++;
+ break;
+ }
+
+ ++argi;
+ ostream = fopen(argv[argi], "w");
+ if ( ostream == NULL ) {
+ fprintf(stderr, "ulfconv: %s : %s\n", argv[argi], strerror(errno));
+ exit(2);
+ }
+ break;
+ case 't':
+ if (argi+1 >= argc || argv[argi+1][0] == '-')
+ {
+ fprintf(stderr, "Option -%c requires an operand\n", argv[argi][1]);
+ errflg++;
+ break;
+ }
+
+ read_encoding_table(argv[++argi], aEncodingMap);
+ break;
+ default:
+ fprintf(stderr, "Unrecognized option: -%c\n", argv[argi]);
+ errflg++;
+ }
+ }
+ else
+ {
+ break;
+ }
+ }
+
+ if (errflg) {
+ fprintf(stderr, "Usage: ulfconv [-o <output file>] [-t <encoding table>] [<ulf file>]\n");
+ exit(2);
+ }
+
+ /* assign input file to stdin */
+ if ( argi < argc ) {
+
+ istream = fopen(argv[argi], "r");
+ if ( istream == NULL ) {
+ fprintf(stderr, "ulfconv: %s : %s\n", argv[argi], strerror(errno));
+ exit(2);
+ }
+ }
+
+ /* read line by line from stdin */
+ char buffer[512];
+ while ( NULL != fgets(buffer, sizeof(buffer), istream) ) {
+
+ /* only handle lines containing " = " */
+ char * cp = strstr(buffer, " = \"");
+ if ( cp ) {
+ rtl::OUString aString;
+
+ /* find end of lang string */
+ int n;
+ for ( n=0; ! isspace(buffer[n]); n++ )
+ ;
+
+ std::string line = buffer;
+ std::string lang(line, 0, n);
+
+ cp += 4;
+ rtl_string2UString( &aString.pData, cp, strrchr(cp, '\"') - cp,
+ RTL_TEXTENCODING_UTF8, OSTRING_TO_OUSTRING_CVTFLAGS );
+
+ fprintf(ostream, "%s = \"", lang.c_str());
+
+ if ( aEncodingMap.empty() ) {
+ print_java_style(ostream, aString);
+ } else {
+ print_legacy_mixed(ostream, aString, lang, aEncodingMap);
+ }
+
+ fprintf(ostream, "\"\n");
+
+
+ } else {
+ fprintf(ostream, buffer);
+ }
+ }
+}