fdo#72031 RTF import: bogus call to getBestTextEncodingFromLocale()

There were two problems here. First, commit
bbe3627eece0c3486e7ea11f2f13377aaa3a8fed (rtftok: stop sending
sprm:CRgFtc{0,1,2} tokens, 2014-03-05) broke the use-case when the font
encoding is 0, but it's present. Before that commit, we parsed the font
encoding instantly; after that commit we parse it once we have a font
name. If we do that, then we have to have an idea if we have a font
encoding. Given that 0 is a valid encoding, use -1 for the "have no
encoding" case instead.

Second, commit 7839633fb356285652ed96f4bf3f85bcd5b561a4 (fdo#85889
handle pc, pca and mac rtf keywords in writerfilter, 2014-11-24) abused
m_nCurrentEncoding, which is meant to be used within the font table
only. The problem with this is that this way only the first font will
get the encoding, while the spec says it should be used in every context
where there is no other explicit encoding. Fix this by setting the
default encoding for those 3 control words instead -- and consider the
default encoding in getEncoding().

Change-Id: Ia1d71f8ce70f2a53a3770b4840e21362d082e71f
(cherry picked from commit fa15d039e3a553da8500c17190d27169a9477cf2)
Signed-off-by: Andras Timar <andras.timar@collabora.com>

3 files changed, 24 insertions, 12 deletions

diff --git a/sw/qa/extras/rtfimport/data/fdo72031.rtf b/sw/qa/extras/rtfimport/data/fdo72031.rtf
new file mode 100644
index 000000000000..ee589dab7d6b
--- /dev/null
+++ b/sw/qa/extras/rtfimport/data/fdo72031.rtf
@@ -0,0 +1 @@
+{\rtf1\ansi\ansicpg1250\deff0\deflang1038{\fonttbl{\f0\fnil\fcharset2 Symbol;}{\f1\fnil\fcharset238 MS Shell Dlg 2;}}\viewkind4\uc1\pard\f0\fs23\'c5\f1\fs17\par}
diff --git a/sw/qa/extras/rtfimport/rtfimport.cxx b/sw/qa/extras/rtfimport/rtfimport.cxx
index bf4b176f51ca..e3fddac5dd99 100644
--- a/sw/qa/extras/rtfimport/rtfimport.cxx
+++ b/sw/qa/extras/rtfimport/rtfimport.cxx
@@ -64,7 +64,7 @@ public:
     virtual void preTest(const char* filename) SAL_OVERRIDE
     {
         m_aSavedSettings = Application::GetSettings();
-        if (OString(filename) == "fdo48023.rtf")
+        if (OString(filename) == "fdo48023.rtf" || OString(filename) == "fdo72031.rtf")
         {
             AllSettings aSettings(m_aSavedSettings);
             aSettings.SetLanguageTag(LanguageTag("ru"));
@@ -80,7 +80,7 @@ public:
 
     virtual void postTest(const char* filename) SAL_OVERRIDE
     {
-        if (OString(filename) == "fdo48023.rtf" || OString(filename) == "fdo44211.rtf")
+        if (OString(filename) == "fdo48023.rtf" || OString(filename) == "fdo72031.rtf" || OString(filename) == "fdo44211.rtf")
             Application::SetSettings(m_aSavedSettings);
     }
 
@@ -2048,6 +2048,11 @@ DECLARE_RTFIMPORT_TEST(testFdo85889mac, "fdo85889-mac.rtf")
     CPPUNIT_ASSERT_EQUAL(aExpected, xTextRange->getString());
 }
 
+DECLARE_RTFIMPORT_TEST(testFdo72031, "fdo72031.rtf")
+{
+    OUString aExpected("\xc3\x85", 2, RTL_TEXTENCODING_UTF8);
+    CPPUNIT_ASSERT_EQUAL(aExpected, getRun(getParagraph(1), 1)->getString());
+}
 
 CPPUNIT_PLUGIN_IMPLEMENT();
 
diff --git a/writerfilter/source/rtftok/rtfdocumentimpl.cxx b/writerfilter/source/rtftok/rtfdocumentimpl.cxx
index 27e0ab227452..b61f5a764074 100644
--- a/writerfilter/source/rtftok/rtfdocumentimpl.cxx
+++ b/writerfilter/source/rtftok/rtfdocumentimpl.cxx
@@ -276,7 +276,7 @@ RTFDocumentImpl::RTFDocumentImpl(uno::Reference<uno::XComponentContext> const& x
       m_bObject(false),
       m_aFontTableEntries(),
       m_nCurrentFontIndex(0),
-      m_nCurrentEncoding(0),
+      m_nCurrentEncoding(-1),
       m_nDefaultFontIndex(-1),
       m_aStyleTableEntries(),
       m_nCurrentStyleIndex(0),
@@ -639,8 +639,14 @@ rtl_TextEncoding RTFDocumentImpl::getEncoding(int nFontIndex)
     {
         std::map<int, rtl_TextEncoding>::iterator it = m_aFontEncodings.find(nFontIndex);
         if (it != m_aFontEncodings.end())
+            // We have a font encoding associated to this font.
             return it->second;
-        return msfilter::util::getBestTextEncodingFromLocale(Application::GetSettings().GetLanguageTag().getLocale());
+        else if (m_aDefaultState.nCurrentEncoding != rtl_getTextEncodingFromWindowsCharset(0))
+            // We have a default encoding.
+            return m_aDefaultState.nCurrentEncoding;
+        else
+            // Guess based on locale.
+            return msfilter::util::getBestTextEncodingFromLocale(Application::GetSettings().GetLanguageTag().getLocale());
     }
     else
         return m_pSuperstream->getEncoding(nFontIndex);
@@ -1154,10 +1160,10 @@ void RTFDocumentImpl::text(OUString& rString)
             case DESTINATION_FONTENTRY:
             {
                 m_aFontNames[m_nCurrentFontIndex] = aName;
-                if (m_nCurrentEncoding > 0)
+                if (m_nCurrentEncoding >= 0)
                 {
                     m_aFontEncodings[m_nCurrentFontIndex] = m_nCurrentEncoding;
-                    m_nCurrentEncoding = 0;
+                    m_nCurrentEncoding = -1;
                 }
                 m_aStates.top().aTableAttributes.set(NS_ooxml::LN_CT_Font_name, RTFValue::Pointer_t(new RTFValue(aName)));
 
@@ -2831,16 +2837,16 @@ int RTFDocumentImpl::dispatchFlag(RTFKeyword nKeyword)
         m_aStates.top().nCurrentEncoding = RTL_TEXTENCODING_MS_1252;
         break;
     case RTF_MAC:
-        m_nCurrentEncoding = RTL_TEXTENCODING_APPLE_ROMAN;
-        m_aStates.top().nCurrentEncoding = m_nCurrentEncoding;
+        m_aDefaultState.nCurrentEncoding = RTL_TEXTENCODING_APPLE_ROMAN;
+        m_aStates.top().nCurrentEncoding = m_aDefaultState.nCurrentEncoding;
         break;
     case RTF_PC:
-        m_nCurrentEncoding = RTL_TEXTENCODING_IBM_437;
-        m_aStates.top().nCurrentEncoding = m_nCurrentEncoding;
+        m_aDefaultState.nCurrentEncoding = RTL_TEXTENCODING_IBM_437;
+        m_aStates.top().nCurrentEncoding = m_aDefaultState.nCurrentEncoding;
         break;
     case RTF_PCA:
-        m_nCurrentEncoding = RTL_TEXTENCODING_IBM_850;
-        m_aStates.top().nCurrentEncoding = m_nCurrentEncoding;
+        m_aDefaultState.nCurrentEncoding = RTL_TEXTENCODING_IBM_850;
+        m_aStates.top().nCurrentEncoding = m_aDefaultState.nCurrentEncoding;
         break;
     case RTF_PLAIN:
     {