fix Graphic duplication in import and add GraphicMapper

When importing writerfilter, we change to oox when
importing images. This transition doesn't store any
previous contexts and all instances are reset. The
problem occurs when we have identical images because
the transition erases all caches we have to determine
if an image has already been imported or not, which
causes that we import the same image multiple times
which create unnecessary copies.

This introduces the XGraphicMapper, which can be used
to store the XGraphic for a key and can be transferred
between writerfilter to oox. With this we can remember
which images were already imported and don't create
unnecessary internal copies which decreases memory.

This also includes a test which checks that the import
and export doesn't produce unnecessary copies of
identical images. The test checks that for OOXML, ODF
and MS Binary formats.

Reviewed-on: https://gerrit.libreoffice.org/c/core/+/103283
Tested-by: Jenkins
Reviewed-by: Tomaž Vajngerl <quikee@gmail.com>
(cherry picked from commit d0efd878dc41e3913a2d91ff4b5c335c1d71a85c)

Change-Id: I33dc19218c565937fab77e132b3a996c51358b6e
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/103407
Tested-by: Jenkins CollaboraOffice <jenkinscollaboraoffice@gmail.com>
Reviewed-by: Tomaž Vajngerl <quikee@gmail.com>

2 files changed, 83 insertions, 0 deletions

diff --git a/sw/qa/extras/globalfilter/data/multiple_identical_graphics.odt b/sw/qa/extras/globalfilter/data/multiple_identical_graphics.odt
new file mode 100644
index 000000000000..20f40798edfe
--- /dev/null
+++ b/sw/qa/extras/globalfilter/data/multiple_identical_graphics.odt
diff --git a/sw/qa/extras/globalfilter/globalfilter.cxx b/sw/qa/extras/globalfilter/globalfilter.cxx
index f0d61355ea86..fe9b58e16413 100644
--- a/sw/qa/extras/globalfilter/globalfilter.cxx
+++ b/sw/qa/extras/globalfilter/globalfilter.cxx
@@ -40,6 +40,7 @@ public:
     void testLinkedGraphicRT();
     void testImageWithSpecialID();
     void testGraphicShape();
+    void testMultipleIdenticalGraphics();
     void testCharHighlight();
     void testCharHighlightODF();
     void testCharHighlightBody();
@@ -62,6 +63,7 @@ public:
     CPPUNIT_TEST(testLinkedGraphicRT);
     CPPUNIT_TEST(testImageWithSpecialID);
     CPPUNIT_TEST(testGraphicShape);
+    CPPUNIT_TEST(testMultipleIdenticalGraphics);
     CPPUNIT_TEST(testCharHighlight);
     CPPUNIT_TEST(testCharHighlightODF);
     CPPUNIT_TEST(testMSCharBackgroundEditing);
@@ -396,6 +398,87 @@ void Test::testGraphicShape()
     }
 }
 
+namespace
+{
+
+std::vector<uno::Reference<graphic::XGraphic>>
+    lcl_getGraphics(const uno::Reference<lang::XComponent>& xComponent)
+{
+    std::vector<uno::Reference<graphic::XGraphic>> aGraphics;
+    uno::Reference<drawing::XShape> xShape;
+
+    uno::Reference<drawing::XDrawPageSupplier> xDrawPageSupplier(xComponent, uno::UNO_QUERY);
+    uno::Reference<drawing::XDrawPage> xDrawPage = xDrawPageSupplier->getDrawPage();
+    for (sal_Int32 i = 0; i < xDrawPage->getCount(); ++i)
+    {
+        uno::Reference<beans::XPropertySet> xShapeProperties(xDrawPage->getByIndex(i), uno::UNO_QUERY);
+        uno::Reference<graphic::XGraphic> xGraphic;
+        xShapeProperties->getPropertyValue("Graphic") >>= xGraphic;
+        if (xGraphic.is())
+        {
+            aGraphics.push_back(xGraphic);
+        }
+    }
+
+    return aGraphics;
+}
+
+}
+
+void Test::testMultipleIdenticalGraphics()
+{
+    // We have multiple identical graphics. When we save them we want
+    // them to be saved de-duplicated and the same should still be true
+    // after loading them again. This test check that the de-duplication
+    // works as expected.
+
+    const OUString aFilterNames[] {
+        "writer8",
+        //"Rich Text Format", // doesn't work correctly for now
+        "MS Word 97",
+        "Office Open XML Text",
+    };
+
+    for (OUString const & rFilterName : aFilterNames)
+    {
+        if (mxComponent.is())
+            mxComponent->dispose();
+
+        mxComponent = loadFromDesktop(m_directories.getURLFromSrc("/sw/qa/extras/globalfilter/data/multiple_identical_graphics.odt"), "com.sun.star.text.TextDocument");
+
+        // Export the document and import again for a check
+        utl::MediaDescriptor aMediaDescriptor;
+        aMediaDescriptor["FilterName"] <<= rFilterName;
+        utl::TempFile aTempFile;
+        aTempFile.EnableKillingFile();
+        uno::Reference<frame::XStorable> xStorable(mxComponent, uno::UNO_QUERY);
+        xStorable->storeToURL(aTempFile.GetURL(), aMediaDescriptor.getAsConstPropertyValueList());
+        mxComponent->dispose();
+
+        mxComponent = loadFromDesktop(aTempFile.GetURL(), "com.sun.star.text.TextDocument");
+
+        // Check whether graphic exported well
+        const OString sFailedMessage = OStringLiteral("Failed on filter: ") + rFilterName.toUtf8();
+        auto aGraphics = lcl_getGraphics(mxComponent);
+
+        CPPUNIT_ASSERT_EQUAL_MESSAGE(sFailedMessage.getStr(), size_t(5), aGraphics.size());
+
+        // Get all GfxLink addresses, we expect all of them to be the same
+        // indicating we use the same graphic instance for all shapes
+        std::vector<sal_Int64> aGfxLinkAddresses;
+        for (auto const & rxGraphic : aGraphics)
+        {
+            GfxLink* pLink = Graphic(rxGraphic).GetSharedGfxLink().get();
+            aGfxLinkAddresses.emplace_back(reinterpret_cast<sal_Int64>(pLink));
+        }
+
+        // Check all addresses are the same
+        bool bResult = std::equal(aGfxLinkAddresses.begin() + 1, aGfxLinkAddresses.end(), aGfxLinkAddresses.begin());
+        const OString sGraphicNotTheSameFailedMessage = OStringLiteral("Graphics not the same for filter: '") + rFilterName.toUtf8() + OStringLiteral("'");
+        CPPUNIT_ASSERT_EQUAL_MESSAGE(sGraphicNotTheSameFailedMessage.getStr(), true, bResult);
+    }
+}
+
 void Test::testCharHighlightBody()
 {
     // MS Word has two kind of character backgrounds called character shading and highlighting