tdf#108995: take xml:space attribute into account

See paragraph 2.10 of XML 1.0 specification and 17.3.3.31 of ECMA-376-1:2016

Change-Id: I7f19d3b9cf2ccce88a5fa03022beeb99facc04fe
Reviewed-on: https://gerrit.libreoffice.org/39682
Tested-by: Jenkins <ci@libreoffice.org>
Reviewed-by: Mike Kaganski <mike.kaganski@collabora.com>
(cherry picked from commit 7c1a51516aaf2767e43b393259a1ad21570df5fb)
Reviewed-on: https://gerrit.libreoffice.org/39688
Tested-by: Mike Kaganski <mike.kaganski@collabora.com>

4 files changed, 53 insertions, 2 deletions

diff --git a/sw/qa/extras/ooxmlimport/data/xml_space.docx b/sw/qa/extras/ooxmlimport/data/xml_space.docx
new file mode 100644
index 000000000000..305c135fdd75
--- /dev/null
+++ b/sw/qa/extras/ooxmlimport/data/xml_space.docx
diff --git a/sw/qa/extras/ooxmlimport/ooxmlimport.cxx b/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
index 767f908ab6fb..a46a09d32bf3 100644
--- a/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
+++ b/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
@@ -1466,6 +1466,16 @@ DECLARE_OOXMLIMPORT_TEST(testTdf108714, "tdf108714.docx")
     CPPUNIT_ASSERT_EQUAL(style::BreakType_PAGE_BEFORE, breakType);
 }
 
+DECLARE_OOXMLIMPORT_TEST(testTdf108995, "xml_space.docx")
+{
+    CPPUNIT_ASSERT_EQUAL(1, getParagraphs());
+    // We need to take xml:space attribute into account
+    uno::Reference< text::XTextRange > paragraph = getParagraph(1);
+    CPPUNIT_ASSERT_EQUAL(OUString("\tA\t\tline  with\txml:space=\"preserve\" \n"
+                                  "A  line  without xml:space"),
+                         paragraph->getString());
+}
+
 // tests should only be added to ooxmlIMPORT *if* they fail round-tripping in ooxmlEXPORT
 
 CPPUNIT_PLUGIN_IMPLEMENT();
diff --git a/writerfilter/source/ooxml/OOXMLFastContextHandler.cxx b/writerfilter/source/ooxml/OOXMLFastContextHandler.cxx
index 84d2a65ad6e0..bb59ed9bebdc 100644
--- a/writerfilter/source/ooxml/OOXMLFastContextHandler.cxx
+++ b/writerfilter/source/ooxml/OOXMLFastContextHandler.cxx
@@ -627,6 +627,12 @@ void OOXMLFastContextHandler::text(const OUString & sText)
         // tdf#108806: CRLFs in XML were converted to \n before this point.
         // These must be converted to spaces before further processing.
         OUString sNormalizedText = sText.replaceAll("\n", " ");
+        // tdf#108995: by default, leading and trailing white space is ignored;
+        // tabs are converted to spaces
+        if (!IsPreserveSpace())
+        {
+            sNormalizedText = sNormalizedText.trim().replaceAll("\t", " ");
+        }
         mpStream->utext(reinterpret_cast < const sal_uInt8 * >
                         (sNormalizedText.getStr()),
                         sNormalizedText.getLength());
@@ -889,6 +895,15 @@ void OOXMLFastContextHandler::sendPropertiesToParent()
     }
 }
 
+bool OOXMLFastContextHandler::IsPreserveSpace() const
+{
+    // xml:space attribute applies to all elements within the content of the element where it is specified,
+    // unless overridden with another instance of the xml:space attribute
+    if (mpParent)
+        return mpParent->IsPreserveSpace();
+    return false; // default value
+}
+
 /*
   class OOXMLFastContextHandlerStream
  */
@@ -896,7 +911,9 @@ void OOXMLFastContextHandler::sendPropertiesToParent()
 OOXMLFastContextHandlerStream::OOXMLFastContextHandlerStream
 (OOXMLFastContextHandler * pContext)
 : OOXMLFastContextHandler(pContext),
-  mpPropertySetAttrs(new OOXMLPropertySet)
+  mpPropertySetAttrs(new OOXMLPropertySet),
+  mbPreserveSpace(false),
+  mbPreserveSpaceSet(false)
 {
 }
 
@@ -907,7 +924,14 @@ OOXMLFastContextHandlerStream::~OOXMLFastContextHandlerStream()
 void OOXMLFastContextHandlerStream::newProperty(Id nId,
                                                 const OOXMLValue::Pointer_t& pVal)
 {
-    if (nId != 0x0)
+    if (nId == NS_ooxml::LN_CT_Text_space)
+    {
+        // Set <xml:space> value early, to allow
+        // child contexts use it when dealing with strings
+        mbPreserveSpace = pVal->getString() == "preserve";
+        mbPreserveSpaceSet = true;
+    }
+    else if (nId != 0x0)
     {
         OOXMLProperty::Pointer_t pProperty(new OOXMLProperty(nId, pVal, OOXMLProperty::ATTRIBUTE));
 
@@ -938,6 +962,15 @@ void OOXMLFastContextHandlerStream::handleHyperlink()
     getPropertySetAttrs()->resolve(aHyperlinkHandler);
 }
 
+bool OOXMLFastContextHandlerStream::IsPreserveSpace() const
+{
+    // xml:space attribute applies to all elements within the content of the element where it is specified,
+    // unless overridden with another instance of the xml:space attribute
+    if (mbPreserveSpaceSet)
+        return mbPreserveSpace;
+    return OOXMLFastContextHandler::IsPreserveSpace();
+}
+
 /*
   class OOXMLFastContextHandlerProperties
  */
diff --git a/writerfilter/source/ooxml/OOXMLFastContextHandler.hxx b/writerfilter/source/ooxml/OOXMLFastContextHandler.hxx
index e4e3e563fad5..eaf40e27f47b 100644
--- a/writerfilter/source/ooxml/OOXMLFastContextHandler.hxx
+++ b/writerfilter/source/ooxml/OOXMLFastContextHandler.hxx
@@ -224,6 +224,9 @@ protected:
     void startAction(Token_t Element);
     void endAction(Token_t Element);
 
+    // 2.10 of XML 1.0 specification
+    virtual bool IsPreserveSpace() const;
+
     const css::uno::Reference< css::uno::XComponentContext >& getComponentContext() { return m_xContext;}
 
     bool inPositionV;
@@ -258,8 +261,13 @@ public:
 
     void handleHyperlink();
 
+protected:
+    virtual bool IsPreserveSpace() const override;
+
 private:
     mutable OOXMLPropertySet::Pointer_t mpPropertySetAttrs;
+    bool mbPreserveSpace    : 1;
+    bool mbPreserveSpaceSet : 1;
 };
 
 class OOXMLFastContextHandlerProperties : public OOXMLFastContextHandler