EPUB export: fix double escaped NBSP
The EPUB package interface already XML-escapes characters, avoid a double
escape.
And once that works, handle NBSP/tabs.
Change-Id: I8b7bbdc2592096bdd46fbdb29b48b723ef5cf990
Reviewed-on: https://gerrit.libreoffice.org/42098
Reviewed-by: Miklos Vajna <vmiklos@collabora.co.uk>
Tested-by: Jenkins <ci@libreoffice.org>
diff --git a/external/libepubgen/libepubgen-epub3.patch.1 b/external/libepubgen/libepubgen-epub3.patch.1
index 0415bf3..8e62660 100644
--- a/external/libepubgen/libepubgen-epub3.patch.1
+++ b/external/libepubgen/libepubgen-epub3.patch.1
@@ -1906,3 +1906,32 @@ index 1661064..3340643 100644
--
2.12.3
From bce7c05a18a4c5089d5ac77bc61b9f6978e7224b Mon Sep 17 00:00:00 2001
From: Miklos Vajna <vmiklos@collabora.co.uk>
Date: Fri, 8 Sep 2017 11:21:32 +0200
Subject: [PATCH] EPUBHTMLGenerator: write un-escaped NBSP
Package implementations are supposed to take care of escaping, like it
was already a requirement for normal text.
---
src/lib/EPUBHTMLGenerator.cpp | 3 ++-
src/test/EPUBTextGeneratorTest.cpp | 18 ++++++++++++++++++
2 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/src/lib/EPUBHTMLGenerator.cpp b/src/lib/EPUBHTMLGenerator.cpp
index aa09332..ed968bf 100644
--- a/src/lib/EPUBHTMLGenerator.cpp
+++ b/src/lib/EPUBHTMLGenerator.cpp
@@ -681,7 +681,8 @@ void EPUBHTMLGenerator::insertSpace()
{
if (m_impl->m_ignore)
return;
- m_impl->output().insertCharacters(" ");
+ // NBSP.
+ m_impl->output().insertCharacters("\xc2\xa0");
}
void EPUBHTMLGenerator::openOrderedListLevel(const RVNGPropertyList &propList)
--
2.12.3
diff --git a/writerperfect/qa/unit/EPUBExportTest.cxx b/writerperfect/qa/unit/EPUBExportTest.cxx
index 0d86973..10fd5eb 100644
--- a/writerperfect/qa/unit/EPUBExportTest.cxx
+++ b/writerperfect/qa/unit/EPUBExportTest.cxx
@@ -63,6 +63,7 @@ public:
void testNamedStyleInheritance();
void testNestedSpan();
void testLineBreak();
void testEscape();
CPPUNIT_TEST_SUITE(EPUBExportTest);
CPPUNIT_TEST(testOutlineLevel);
@@ -77,6 +78,7 @@ public:
CPPUNIT_TEST(testNamedStyleInheritance);
CPPUNIT_TEST(testNestedSpan);
CPPUNIT_TEST(testLineBreak);
CPPUNIT_TEST(testEscape);
CPPUNIT_TEST_SUITE_END();
};
@@ -330,6 +332,19 @@ void EPUBExportTest::testLineBreak()
assertXPath(mpXmlDoc, "//xhtml:p[2]/xhtml:br", 1);
}
void EPUBExportTest::testEscape()
{
createDoc("escape.fodt", {});
mpXmlDoc = parseExport("OEBPS/sections/section0001.xhtml");
// This was lost.
assertXPathContent(mpXmlDoc, "//xhtml:p[1]/xhtml:span[1]", OUString::fromUtf8("\xc2\xa0"));
// Make sure escaping happens only once.
assertXPathContent(mpXmlDoc, "//xhtml:p[1]/xhtml:span[2]", "a&b");
// This was also lost.
assertXPathContent(mpXmlDoc, "//xhtml:p[1]/xhtml:span[3]", "\t");
}
CPPUNIT_TEST_SUITE_REGISTRATION(EPUBExportTest);
}
diff --git a/writerperfect/qa/unit/data/writer/epubexport/escape.fodt b/writerperfect/qa/unit/data/writer/epubexport/escape.fodt
new file mode 100644
index 0000000..8d23fb3
--- /dev/null
+++ b/writerperfect/qa/unit/data/writer/epubexport/escape.fodt
@@ -0,0 +1,16 @@
<?xml version="1.0" encoding="UTF-8"?>
<office:document xmlns:office="urn:oasis:names:tc:opendocument:xmlns:office: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:fo="urn:oasis:names:tc:opendocument:xmlns:xsl-fo-compatible:1.0" xmlns:officeooo="http://openoffice.org/2009/office" office:version="1.2" office:mimetype="application/vnd.oasis.opendocument.text">
<office:automatic-styles>
<style:style style:name="T1" style:family="text">
<style:text-properties officeooo:rsid="0006b966"/>
</style:style>
<style:style style:name="T2" style:family="text">
<style:text-properties fo:font-weight="bold" officeooo:rsid="0006b966" style:font-weight-asian="bold" style:font-weight-complex="bold"/>
</style:style>
</office:automatic-styles>
<office:body>
<office:text>
<text:p><text:s/><text:span text:style-name="T1">a&b</text:span><text:span text:style-name="T2"><text:tab/></text:span></text:p>
</office:text>
</office:body>
</office:document>
diff --git a/writerperfect/source/writer/exp/txtparai.cxx b/writerperfect/source/writer/exp/txtparai.cxx
index b085537..e660a34 100644
--- a/writerperfect/source/writer/exp/txtparai.cxx
+++ b/writerperfect/source/writer/exp/txtparai.cxx
@@ -152,6 +152,48 @@ void XMLLineBreakContext::startElement(const OUString &/*rName*/, const css::uno
mrImport.GetGenerator().insertLineBreak();
}
/// Handler for <text:s>.
class XMLSpaceContext : public XMLImportContext
{
public:
XMLSpaceContext(XMLImport &rImport);
void SAL_CALL startElement(const OUString &rName, const css::uno::Reference<css::xml::sax::XAttributeList> &xAttribs) override;
};
XMLSpaceContext::XMLSpaceContext(XMLImport &rImport)
: XMLImportContext(rImport)
{
}
void XMLSpaceContext::startElement(const OUString &/*rName*/, const css::uno::Reference<css::xml::sax::XAttributeList> &/*xAttribs*/)
{
mrImport.GetGenerator().openSpan(librevenge::RVNGPropertyList());
mrImport.GetGenerator().insertSpace();
mrImport.GetGenerator().closeSpan();
}
/// Handler for <text:tab>.
class XMLTabContext : public XMLImportContext
{
public:
XMLTabContext(XMLImport &rImport);
void SAL_CALL startElement(const OUString &rName, const css::uno::Reference<css::xml::sax::XAttributeList> &xAttribs) override;
};
XMLTabContext::XMLTabContext(XMLImport &rImport)
: XMLImportContext(rImport)
{
}
void XMLTabContext::startElement(const OUString &/*rName*/, const css::uno::Reference<css::xml::sax::XAttributeList> &/*xAttribs*/)
{
mrImport.GetGenerator().openSpan(librevenge::RVNGPropertyList());
mrImport.GetGenerator().insertTab();
mrImport.GetGenerator().closeSpan();
}
/// Handler for <text:a>.
class XMLHyperlinkContext : public XMLImportContext
{
@@ -255,6 +297,10 @@ XMLImportContext *CreateChildContext(XMLImport &rImport, const OUString &rName)
{
if (rName == "text:line-break")
return new XMLLineBreakContext(rImport);
if (rName == "text:s")
return new XMLSpaceContext(rImport);
if (rName == "text:tab")
return new XMLTabContext(rImport);
return nullptr;
}
