[REVIEW] fdo#45543 fix RTF import of ms932-encoded characters

Hi,

There were a number of problems with the RTF import of stateful
encodings (i.e. where we can't process the characters one by one) - see
commits:

http://cgit.freedesktop.org/libreoffice/core/commit/?id=d7baacd81bbcfaa35b7fbf9981fa3fa7c9fb1cb4
http://cgit.freedesktop.org/libreoffice/core/commit/?id=0915f1b3d77afa694a2ca692aec307846827da99
http://cgit.freedesktop.org/libreoffice/core/commit/?id=00859026749e005759ce4e7115b746b064cd902b

I'm attaching a backport of these patches for -3-5: the first commit
fixes the real problem, the two later amends are correcting two issues
with the original fix.

Thanks,

Miklos

From c419aa5bfdff4041132520d2d39b3b1571376fd1 Mon Sep 17 00:00:00 2001
From: Miklos Vajna <vmiklos@suse.cz>
Date: Mon, 13 Feb 2012 18:42:56 +0100
Subject: [PATCH] fdo#45543 fix RTF import of ms932-encoded characters

(cherry picked from commits d7baacd81bbcfaa35b7fbf9981fa3fa7c9fb1cb4,
0915f1b3d77afa694a2ca692aec307846827da99 and
00859026749e005759ce4e7115b746b064cd902b)
---
 writerfilter/source/rtftok/rtfdocumentimpl.cxx |   32 +++++++++++++++++++----
 writerfilter/source/rtftok/rtfdocumentimpl.hxx |    6 +++-
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/writerfilter/source/rtftok/rtfdocumentimpl.cxx 
b/writerfilter/source/rtftok/rtfdocumentimpl.cxx
index 737350b..824615d 100644
--- a/writerfilter/source/rtftok/rtfdocumentimpl.cxx
+++ b/writerfilter/source/rtftok/rtfdocumentimpl.cxx
@@ -305,7 +305,8 @@ RTFDocumentImpl::RTFDocumentImpl(uno::Reference<uno::XComponentContext> const& x
     m_bWasInFrame(false),
     m_bIsInFrame(false),
     m_bHasPage(false),
-    m_aUnicodeBuffer()
+    m_aUnicodeBuffer(),
+    m_aHexBuffer()
 {
     OSL_ASSERT(xInputStream.is());
     m_pInStream.reset(utl::UcbStreamHelper::CreateStream(xInputStream, sal_True));
@@ -738,9 +739,13 @@ int RTFDocumentImpl::resolvePict(bool bInline)
 
 int RTFDocumentImpl::resolveChars(char ch)
 {
+    if (m_aStates.top().nInternalState != INTERNAL_HEX)
+        checkUnicode(false, true);
+
     OStringBuffer aBuf;
 
     bool bUnicodeChecked = false;
+    bool bSkipped = false;
     while(!Strm().IsEof() && ch != '{' && ch != '}' && ch != '\\')
     {
         if (ch != 0x0d && ch != 0x0a)
@@ -749,13 +754,16 @@ int RTFDocumentImpl::resolveChars(char ch)
             {
                 if (!bUnicodeChecked)
                 {
-                    checkUnicode();
+                    checkUnicode(true, false);
                     bUnicodeChecked = true;
                 }
                 aBuf.append(ch);
             }
             else
+            {
+                bSkipped = true;
                 m_aStates.top().nCharsToSkip--;
+            }
         }
         // read a single char if we're in hex mode
         if (m_aStates.top().nInternalState == INTERNAL_HEX)
@@ -764,6 +772,14 @@ int RTFDocumentImpl::resolveChars(char ch)
     }
     if (m_aStates.top().nInternalState != INTERNAL_HEX && !Strm().IsEof())
         Strm().SeekRel(-1);
+
+    if (m_aStates.top().nInternalState == INTERNAL_HEX && m_aStates.top().nDestinationState != 
DESTINATION_LEVELNUMBERS)
+    {
+        if (!bSkipped)
+            m_aHexBuffer.append(ch);
+        return 0;
+    }
+
     if (m_aStates.top().nDestinationState == DESTINATION_SKIP)
         return 0;
     OString aStr = aBuf.makeStringAndClear();
@@ -2031,8 +2047,7 @@ int RTFDocumentImpl::dispatchFlag(RTFKeyword nKeyword)
 
 int RTFDocumentImpl::dispatchValue(RTFKeyword nKeyword, int nParam)
 {
-    if (nKeyword != RTF_U)
-        checkUnicode();
+    checkUnicode(nKeyword != RTF_U, true);
     RTFSkipDestination aSkip(*this);
     int nSprm = 0;
     RTFValue::Pointer_t pIntValue(new RTFValue(nParam));
@@ -3370,13 +3385,18 @@ void RTFDocumentImpl::setSkipUnknown(bool bSkipUnknown)
     m_bSkipUnknown = bSkipUnknown;
 }
 
-void RTFDocumentImpl::checkUnicode()
+void RTFDocumentImpl::checkUnicode(bool bUnicode, bool bHex)
 {
-    if (m_aUnicodeBuffer.getLength() > 0)
+    if (bUnicode && m_aUnicodeBuffer.getLength() > 0)
     {
         OUString aString = m_aUnicodeBuffer.makeStringAndClear();
         text(aString);
     }
+    if (bHex && m_aHexBuffer.getLength() > 0)
+    {
+        OUString aString = OStringToOUString(m_aHexBuffer.makeStringAndClear(), 
m_aStates.top().nCurrentEncoding);
+        text(aString);
+    }
 }
 
 RTFParserState::RTFParserState()
diff --git a/writerfilter/source/rtftok/rtfdocumentimpl.hxx 
b/writerfilter/source/rtftok/rtfdocumentimpl.hxx
index 713fd7d..3644375 100644
--- a/writerfilter/source/rtftok/rtfdocumentimpl.hxx
+++ b/writerfilter/source/rtftok/rtfdocumentimpl.hxx
@@ -364,8 +364,8 @@ namespace writerfilter {
                 void replayBuffer(RTFBuffer_t& rBuffer);
                 /// If we got tokens indicating we're in a frame.
                 bool inFrame();
-                /// If we have some unicode characters to send.
-                void checkUnicode();
+                /// If we have some unicode or hex characters to send.
+                void checkUnicode(bool bUnicode = true, bool bHex = true);
 
                 uno::Reference<uno::XComponentContext> const& m_xContext;
                 uno::Reference<io::XInputStream> const& m_xInputStream;
@@ -454,6 +454,8 @@ namespace writerfilter {
                 bool m_bHasPage;
                 // Unicode characters are collected here so we don't have to send them one by one.
                 rtl::OUStringBuffer m_aUnicodeBuffer;
+                /// Same for hex characters.
+                rtl::OStringBuffer m_aHexBuffer;
         };
     } // namespace rtftok
 } // namespace writerfilter
-- 
1.7.7