tdf#132599 cui offapi sw xmloff: implement hyphenate-keep

Both parts of a hyphenated word shall lie within a single
page with ODF paragraph setting fo:hyphenation-keep="page".
The implementation follows the default page layout of
MSO 2016 and newer by shifting the bottom hyphenated line
to the next page (and to the next column, see last note).

Note: this is a MSO DOCX interoperability feature, used
also in DTP software, XSL and CSS.

* Add checkbox/combobox to Text Flow in paragraph dialog
* Store property in paragraph model (com::sun::star::style::ParagraphProperties::ParaHyphenationKeep)
* Add ODF import/export
* Add ODF unit tests

New constants of com::sun::star::text::ParagraphHyphenationKeepType,
containing ODF AUTO and PAGE (borrowed from XSL), and for the
planned extension ParaHyphenationKeepType of ParagraphProperties:

– COLUMN (standard XSL value, defined in
  https://www.w3.org/TR/2001/REC-xsl-20011015/slice7.html#hyphenation-keep)

– SPREAD and ALWAYS (CSS 4 values of hyphenate-limit-last,
  equivalent of hyphenation-keep, defined in
  https://www.w3.org/TR/css-text-4/#hyphenate-line-limits).

Note: the implementation truncates only a single hyphenated
line, like MSO does: the pages can end in hyphenated
lines (i.e. in the case of consecutive hyphenated lines),
but less often, than before.

Clean-up hyphenation dialog by collecting "Don't hyphenate"
options at the end of the hyphenation settings, and negating them
(similar to MSO and DTP), adding also the new option
"Hyphenate across column and page":

[x] Hyphenate words in CAPS
[x] Hyphenate last word
[x] Hyphenate across column and page

Note: ODF fo:hyphenation-keep has got only "auto" and
"page" attributes, while XSL defines also "column".
Because of the interoperability with MSO and DTP,
fo:hyphenation-keep="page" is interpreted as
XSL "column", avoiding hyphenation at the end
of column, not only at the end of page.

Change-Id: I5c6b7adc0671a5a790568e7bf1d33256e607f85f
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/164158
Tested-by: László Németh <nemeth@numbertext.org>
Reviewed-by: László Németh <nemeth@numbertext.org>

3 files changed, 125 insertions, 0 deletions

diff --git a/sw/qa/extras/odfexport/data/tdf132599_auto.fodt b/sw/qa/extras/odfexport/data/tdf132599_auto.fodt
new file mode 100644
index 000000000000..65b6ddccc295
--- /dev/null
+++ b/sw/qa/extras/odfexport/data/tdf132599_auto.fodt
@@ -0,0 +1,49 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<office:document xmlns:css3t="http://www.w3.org/TR/css3-text/" xmlns:grddl="http://www.w3.org/2003/g/data-view#" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:ooo="http://openoffice.org/2004/office" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:config="urn:oasis:names:tc:opendocument:xmlns:config:1.0" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:drawooo="http://openoffice.org/2010/draw" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:calcext="urn:org:documentfoundation:names:experimental:calc:xmlns:calcext:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:of="urn:oasis:names:tc:opendocument:xmlns:of:1.2" xmlns:tableooo="http://openoffice.org/2009/table" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:rpt="http://openoffice.org/2005/report" xmlns:formx="urn:openoffice:names:experimental:ooxml-odf-interop:xmlns:form:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:officeooo="http://openoffice.org/2009/office" office:version="1.3" office:mimetype="application/vnd.oasis.opendocument.text">
+ <office:font-face-decls>
+  <style:font-face style:name="Times New Roman" svg:font-family="&apos;Times New Roman&apos;" style:font-family-generic="swiss"/>
+ </office:font-face-decls>
+ <office:styles>
+  <style:default-style style:family="paragraph">
+   <style:paragraph-properties fo:hyphenation-ladder-count="no-limit"/>
+   <style:text-properties style:use-window-font-color="true" style:font-name="Times New Roman" fo:font-size="12pt" fo:language="en" fo:country="US" style:letter-kerning="true" fo:hyphenate="false" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:default-style>
+  <style:style style:name="Standard" style:family="paragraph" style:class="text">
+   <style:paragraph-properties fo:margin-top="0pt" fo:margin-bottom="0pt" style:contextual-spacing="false" fo:text-align="start" style:justify-single-word="false" fo:orphans="2" fo:widows="2" fo:hyphenation-ladder-count="no-limit"/>
+   <style:text-properties fo:hyphenate="true" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:style>
+  <style:style style:name="Text_20_body" style:display-name="Text body" style:family="paragraph" style:parent-style-name="Standard" style:class="text">
+   <style:paragraph-properties fo:margin-top="0pt" fo:margin-bottom="7pt" style:contextual-spacing="false" fo:line-height="115%" fo:text-align="justify" style:justify-single-word="false"/>
+  </style:style>
+  <style:style style:name="Heading_20_1" style:display-name="Heading 1" style:family="paragraph" style:parent-style-name="Heading" style:next-style-name="Text_20_body" style:class="text">
+   <style:text-properties fo:font-size="18pt" fo:font-weight="bold"/>
+  </style:style>
+ </office:styles>
+ <office:automatic-styles>
+  <style:style style:name="P1" style:family="paragraph" style:parent-style-name="Standard" style:master-page-name="">
+   <style:paragraph-properties fo:hyphenation-ladder-count="no-limit" fo:hyphenation-keep="auto" style:page-number="auto"/>
+   <style:text-properties fo:hyphenate="true" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:style>
+  <style:style style:name="P3" style:family="paragraph" style:parent-style-name="Heading_20_1"/>
+  <style:style style:name="T1" style:family="text">
+   <style:text-properties fo:font-size="49pt"/>
+  </style:style>
+  <style:style style:name="T2" style:family="text">
+   <style:text-properties fo:font-size="49pt"/>
+  </style:style>
+  <style:page-layout style:name="pm1">
+   <style:page-layout-properties fo:page-width="590pt" fo:page-height="792pt" style:num-format="1" style:print-orientation="portrait" fo:margin-top="56.69pt" fo:margin-bottom="56.69pt" fo:margin-left="56.69pt" fo:margin-right="56.69pt">
+   </style:page-layout-properties>
+  </style:page-layout>
+ </office:automatic-styles>
+ <office:master-styles>
+  <style:master-page style:name="Standard" style:page-layout-name="pm1" draw:style-name="dp1"/>
+ </office:master-styles>
+ <office:body>
+  <office:text text:use-soft-page-breaks="true">
+   <text:h text:style-name="P3" text:outline-level="1"><text:span text:style-name="T2">Hyphenate last word of the page</text:span><text:span text:style-name="T2"/></text:h>
+   <text:p text:style-name="P1"><text:span text:style-name="T1">The Earth is no different to any other celestial body out there in space. It merely moves along in space inertially. Even just one inch above the surface of the Earth is space, </text:span><text:soft-page-break/><text:span text:style-name="T1">except that it has an atmosphere. The Earth is no different to any other celestial body out there in space. It merely moves along in space inertially. Even just one inch above the surface of the Earth is space, except that it has an atmosphere. The Earth is </text:span><text:soft-page-break/><text:span text:style-name="T1">no different to any other celestial body out…</text:span></text:p>
+  </office:text>
+ </office:body>
+</office:document>
diff --git a/sw/qa/extras/odfexport/data/tdf132599_page.fodt b/sw/qa/extras/odfexport/data/tdf132599_page.fodt
new file mode 100644
index 000000000000..45393ad7dc43
--- /dev/null
+++ b/sw/qa/extras/odfexport/data/tdf132599_page.fodt
@@ -0,0 +1,49 @@
+<?xml version="1.0" encoding="UTF-8"?>
+
+<office:document xmlns:css3t="http://www.w3.org/TR/css3-text/" xmlns:grddl="http://www.w3.org/2003/g/data-view#" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:dom="http://www.w3.org/2001/xml-events" xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office:1.0" xmlns:ooo="http://openoffice.org/2004/office" xmlns:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:config="urn:oasis:names:tc:opendocument:xmlns:config:1.0" xmlns:ooow="http://openoffice.org/2004/writer" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:drawooo="http://openoffice.org/2010/draw" xmlns:oooc="http://openoffice.org/2004/calc" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:calcext="urn:org:documentfoundation:names:experimental:calc:xmlns:calcext:1.0" xmlns:style="urn:oasis:names:tc:opendocument:xmlns:style:1.0" xmlns:text="urn:oasis:names:tc:opendocument:xmlns:text:1.0" xmlns:of="urn:oasis:names:tc:opendocument:xmlns:of:1.2" xmlns:tableooo="http://openoffice.org/2009/table" xmlns:draw="urn:oasis:names:tc:opendocument:xmlns:drawing:1.0" xmlns:dr3d="urn:oasis:names:tc:opendocument:xmlns:dr3d:1.0" xmlns:rpt="http://openoffice.org/2005/report" xmlns:formx="urn:openoffice:names:experimental:ooxml-odf-interop:xmlns:form:1.0" xmlns:svg="urn:oasis:names:tc:opendocument:xmlns:svg-compatible:1.0" xmlns:chart="urn:oasis:names:tc:opendocument:xmlns:chart:1.0" xmlns:officeooo="http://openoffice.org/2009/office" office:version="1.3" office:mimetype="application/vnd.oasis.opendocument.text">
+ <office:font-face-decls>
+  <style:font-face style:name="Times New Roman" svg:font-family="&apos;Times New Roman&apos;" style:font-family-generic="swiss"/>
+ </office:font-face-decls>
+ <office:styles>
+  <style:default-style style:family="paragraph">
+   <style:paragraph-properties fo:hyphenation-ladder-count="no-limit"/>
+   <style:text-properties style:use-window-font-color="true" style:font-name="Times New Roman" fo:font-size="12pt" fo:language="en" fo:country="US" style:letter-kerning="true" fo:hyphenate="false" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:default-style>
+  <style:style style:name="Standard" style:family="paragraph" style:class="text">
+   <style:paragraph-properties fo:margin-top="0pt" fo:margin-bottom="0pt" style:contextual-spacing="false" fo:text-align="start" style:justify-single-word="false" fo:orphans="2" fo:widows="2" fo:hyphenation-ladder-count="no-limit"/>
+   <style:text-properties fo:hyphenate="true" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:style>
+  <style:style style:name="Text_20_body" style:display-name="Text body" style:family="paragraph" style:parent-style-name="Standard" style:class="text">
+   <style:paragraph-properties fo:margin-top="0pt" fo:margin-bottom="7pt" style:contextual-spacing="false" fo:line-height="115%" fo:text-align="justify" style:justify-single-word="false"/>
+  </style:style>
+  <style:style style:name="Heading_20_1" style:display-name="Heading 1" style:family="paragraph" style:parent-style-name="Heading" style:next-style-name="Text_20_body" style:class="text">
+   <style:text-properties fo:font-size="18pt" fo:font-weight="bold"/>
+  </style:style>
+ </office:styles>
+ <office:automatic-styles>
+  <style:style style:name="P1" style:family="paragraph" style:parent-style-name="Standard" style:master-page-name="">
+   <style:paragraph-properties fo:hyphenation-ladder-count="no-limit" fo:hyphenation-keep="page" style:page-number="auto"/>
+   <style:text-properties fo:hyphenate="true" fo:hyphenation-remain-char-count="2" fo:hyphenation-push-char-count="2"/>
+  </style:style>
+  <style:style style:name="P3" style:family="paragraph" style:parent-style-name="Heading_20_1"/>
+  <style:style style:name="T1" style:family="text">
+   <style:text-properties fo:font-size="49pt"/>
+  </style:style>
+  <style:style style:name="T2" style:family="text">
+   <style:text-properties fo:font-size="49pt"/>
+  </style:style>
+  <style:page-layout style:name="pm1">
+   <style:page-layout-properties fo:page-width="590pt" fo:page-height="792pt" style:num-format="1" style:print-orientation="portrait" fo:margin-top="56.69pt" fo:margin-bottom="56.69pt" fo:margin-left="56.69pt" fo:margin-right="56.69pt">
+   </style:page-layout-properties>
+  </style:page-layout>
+ </office:automatic-styles>
+ <office:master-styles>
+  <style:master-page style:name="Standard" style:page-layout-name="pm1" draw:style-name="dp1"/>
+ </office:master-styles>
+ <office:body>
+  <office:text text:use-soft-page-breaks="true">
+   <text:h text:style-name="P3" text:outline-level="1"><text:span text:style-name="T2">Hyphenate last word of the page</text:span><text:span text:style-name="T2"/></text:h>
+   <text:p text:style-name="P1"><text:span text:style-name="T1">The Earth is no different to any other celestial body out there in space. It merely moves along in space inertially. Even just one inch above the surface of the Earth is space, </text:span><text:soft-page-break/><text:span text:style-name="T1">except that it has an atmosphere. The Earth is no different to any other celestial body out there in space. It merely moves along in space inertially. Even just one inch above the surface of the Earth is space, except that it has an atmosphere. The Earth is </text:span><text:soft-page-break/><text:span text:style-name="T1">no different to any other celestial body out…</text:span></text:p>
+  </office:text>
+ </office:body>
+</office:document>
diff --git a/sw/qa/extras/odfexport/odfexport2.cxx b/sw/qa/extras/odfexport/odfexport2.cxx
index 53431d985e1a..eea133b1d274 100644
--- a/sw/qa/extras/odfexport/odfexport2.cxx
+++ b/sw/qa/extras/odfexport/odfexport2.cxx
@@ -14,6 +14,7 @@
 #include <com/sun/star/drawing/GraphicExportFilter.hpp>
 #include <com/sun/star/drawing/XGraphicExportFilter.hpp>
 #include <com/sun/star/io/XOutputStream.hpp>
+#include <com/sun/star/linguistic2/XHyphenator.hpp>
 #include <com/sun/star/style/VerticalAlignment.hpp>
 #include <com/sun/star/text/ColumnSeparatorStyle.hpp>
 #include <com/sun/star/text/XBookmarksSupplier.hpp>
@@ -31,6 +32,7 @@
 #include <comphelper/processfactory.hxx>
 #include <comphelper/propertysequence.hxx>
 #include <comphelper/sequenceashashmap.hxx>
+#include <editeng/unolingu.hxx>
 #include <officecfg/Office/Common.hxx>
 #include <unoprnms.hxx>
 #include <unotxdoc.hxx>
@@ -126,6 +128,31 @@ CPPUNIT_TEST_FIXTURE(Test, testTdf106733)
         "hyphenate"_ostr, "false");
 }
 
+
+CPPUNIT_TEST_FIXTURE(Test, testTdf132599_page)
+{
+    uno::Reference<linguistic2::XHyphenator> xHyphenator = LinguMgr::GetHyphenator();
+    if (!xHyphenator->hasLocale(lang::Locale("en", "US", OUString())))
+        return;
+
+    // fo:hyphenation-keep="page"
+    loadAndReload("tdf132599_page.fodt");
+    // This was 2 (not truncated hyphenated line)
+    CPPUNIT_ASSERT_EQUAL(3, getPages());
+}
+
+CPPUNIT_TEST_FIXTURE(Test, testTdf132599_auto)
+{
+    uno::Reference<linguistic2::XHyphenator> xHyphenator = LinguMgr::GetHyphenator();
+    if (!xHyphenator->hasLocale(lang::Locale("en", "US", OUString())))
+        return;
+
+    // fo:hyphenation-keep="auto"
+    loadAndReload("tdf132599_auto.fodt");
+    // not truncated hyphenated line
+    CPPUNIT_ASSERT_EQUAL(2, getPages());
+}
+
 DECLARE_ODFEXPORT_TEST(testReferenceLanguage, "referencelanguage.odt")
 {
     CPPUNIT_ASSERT_EQUAL(2, getPages());