DOCX import: handle <w:smartTag>

These can be sort of arbitrary key-value pairs around one or multiple
runs, handle the following subset:

- when they appear at a paragraph context -> we assume they are
  annotations on the paragraph
- when the smart tag's URI/element is RDF -> we map these to RDF
  metadata statements on paragraphs
- when the attribute name's namespace is known, because in ODF we need
  to specify both a path and a type (namespace) for the RDF graph, and
  OOXML only provides a namespace

As a start, recognize the TSCP BAF namespace from
<https://www.tscp.org/wp-content/uploads/2013/08/TSCP_BAFv1.pdf>.

Change-Id: Ib188b1395e7ec7e0441b4f12f86cfef99fb9f096

3 files changed, 41 insertions, 0 deletions

diff --git a/sw/CppunitTest_sw_ooxmlimport.mk b/sw/CppunitTest_sw_ooxmlimport.mk
index 5aae15d8a6b4..4074255a7cf3 100644
--- a/sw/CppunitTest_sw_ooxmlimport.mk
+++ b/sw/CppunitTest_sw_ooxmlimport.mk
@@ -95,6 +95,7 @@ $(eval $(call gb_CppunitTest_use_components,sw_ooxmlimport,\
     ucb/source/ucp/file/ucpfile1 \
     unotools/util/utl \
     unoxml/source/service/unoxml \
+    unoxml/source/rdf/unordf \
     writerfilter/util/writerfilter \
     xmloff/util/xo \
 ))
diff --git a/sw/qa/extras/ooxmlimport/data/tscp.docx b/sw/qa/extras/ooxmlimport/data/tscp.docx
new file mode 100644
index 000000000000..3cda72de572e
--- /dev/null
+++ b/sw/qa/extras/ooxmlimport/data/tscp.docx
diff --git a/sw/qa/extras/ooxmlimport/ooxmlimport.cxx b/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
index e19d1ba4c91e..a4bb78b8d81c 100644
--- a/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
+++ b/sw/qa/extras/ooxmlimport/ooxmlimport.cxx
@@ -79,6 +79,8 @@
 #include <unotools/streamwrap.hxx>
 #include <comphelper/propertysequence.hxx>
 #include <com/sun/star/drawing/HomogenMatrix3.hpp>
+#include <com/sun/star/rdf/URI.hpp>
+#include <com/sun/star/rdf/Statement.hpp>
 
 #include <bordertest.hxx>
 
@@ -2841,6 +2843,44 @@ DECLARE_OOXMLIMPORT_TEST(testIndents, "indents.docx")
     } while (xParaEnum->hasMoreElements());
 }
 
+DECLARE_OOXMLIMPORT_TEST(testTscp, "tscp.docx")
+{
+    uno::Reference<uno::XComponentContext> xComponentContext(comphelper::getProcessComponentContext());
+    uno::Reference<rdf::XURI> xType = rdf::URI::create(xComponentContext, "urn:tscp:names:baf:1.1");
+    uno::Reference<rdf::XDocumentMetadataAccess> xDocumentMetadataAccess(mxComponent, uno::UNO_QUERY);
+    uno::Sequence< uno::Reference<rdf::XURI> > aGraphNames = xDocumentMetadataAccess->getMetadataGraphsWithType(xType);
+    // This failed, no graphs had the urn:tscp:names:baf:1.1 type.
+    CPPUNIT_ASSERT_EQUAL(static_cast<sal_Int32>(1), aGraphNames.getLength());
+    uno::Reference<rdf::XURI> xGraphName = aGraphNames[0];
+    uno::Reference<rdf::XNamedGraph> xGraph = xDocumentMetadataAccess->getRDFRepository()->getGraph(xGraphName);
+
+    // No RDF statement on the first paragraph.
+    uno::Reference<rdf::XResource> xParagraph(getParagraph(1), uno::UNO_QUERY);
+    uno::Reference<container::XEnumeration> xStatements = xGraph->getStatements(xParagraph, uno::Reference<rdf::XURI>(), uno::Reference<rdf::XURI>());
+    CPPUNIT_ASSERT_EQUAL(false, static_cast<bool>(xStatements->hasMoreElements()));
+
+    // 3 RDF statements on the second paragraph.
+    xParagraph.set(getParagraph(2), uno::UNO_QUERY);
+    std::map<OUString, OUString> aExpectedStatements = {
+        {"urn:tscp:names:baf:1.1#BusinessAuthorization", "urn:example:tscp:1"},
+        {"urn:tscp:names:baf:1.1#BusinessAuthorizationCategory", "urn:example:tscp:1:confidential"},
+        {"urn:tscp:names:baf:1.1#BusinessAuthorizationDate", "2015-11-27T11:45:00"}
+    };
+    std::map<OUString, OUString> aActualStatements;
+    xStatements = xGraph->getStatements(xParagraph, uno::Reference<rdf::XURI>(), uno::Reference<rdf::XURI>());
+    while (xStatements->hasMoreElements())
+    {
+        rdf::Statement aStatement = xStatements->nextElement().get<rdf::Statement>();
+        aActualStatements[aStatement.Predicate->getNamespace() + aStatement.Predicate->getLocalName()] = aStatement.Object->getStringValue();
+    }
+    CPPUNIT_ASSERT(aExpectedStatements == aActualStatements);
+
+    // No RDF statement on the third paragraph.
+    xParagraph.set(getParagraph(3), uno::UNO_QUERY);
+    xStatements = xGraph->getStatements(xParagraph, uno::Reference<rdf::XURI>(), uno::Reference<rdf::XURI>());
+    CPPUNIT_ASSERT_EQUAL(false, static_cast<bool>(xStatements->hasMoreElements()));
+}
+
 DECLARE_OOXMLIMPORT_TEST(testTdf92454, "tdf92454.docx")
 {
     // The first paragraph had a large indentation / left margin as inheritance