Some character conversion rework + some debug messages

4 files changed, 429 insertions, 150 deletions

diff --git a/src/lib/VSDXContentCollector.cpp b/src/lib/VSDXContentCollector.cpp
index 5342736..2cef0f5 100644
--- a/src/lib/VSDXContentCollector.cpp
+++ b/src/lib/VSDXContentCollector.cpp
@@ -28,6 +28,7 @@
  * instead of those above.
  */
 
+#include <string.h> // for memcpy
 #include <stack>
 #include <boost/spirit/include/classic.hpp>
 
@@ -93,6 +94,10 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     m_fillType = "solid";
     if (colourIndexFG < m_colours.size())
       m_styleProps.insert("draw:fill-color", getColourString(m_colours[colourIndexFG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexFG out of bonds\n"));
+#endif
     if (m_fillFGTransparency > 0)
       m_styleProps.insert("draw:opacity", (double)(1 - m_fillFGTransparency/255.0), WPX_PERCENT);
     else
@@ -104,8 +109,16 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     m_styleProps.insert("draw:style", "axial");
     if (colourIndexFG < m_colours.size())
       m_styleProps.insert("draw:start-color", getColourString(m_colours[colourIndexFG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexFG out of bonds\n"));
+#endif
     if (colourIndexBG < m_colours.size())
       m_styleProps.insert("draw:end-color", getColourString(m_colours[colourIndexBG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexBG out of bonds\n"));
+#endif
     m_styleProps.remove("draw:opacity");
     if (m_fillBGTransparency > 0)
       m_styleProps.insert("libwpg:start-opacity", (double)(1 - m_fillBGTransparency/255.0), WPX_PERCENT);
@@ -128,8 +141,16 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     m_styleProps.insert("draw:style", "linear");
     if (colourIndexBG < m_colours.size())
       m_styleProps.insert("draw:start-color", getColourString(m_colours[colourIndexBG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexBG out of bonds\n"));
+#endif
     if (colourIndexFG < m_colours.size())
       m_styleProps.insert("draw:end-color", getColourString(m_colours[colourIndexFG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexFG out of bonds\n"));
+#endif
     m_styleProps.remove("draw:opacity");
     if (m_fillBGTransparency > 0)
       m_styleProps.insert("libwpg:start-opacity", (double)(1 - m_fillBGTransparency/255.0), WPX_PERCENT);
@@ -177,8 +198,16 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     m_styleProps.insert("svg:cy", 0.5, WPX_PERCENT);
     if (colourIndexBG < m_colours.size())
       m_styleProps.insert("draw:start-color", getColourString(m_colours[colourIndexBG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexBG out of bonds\n"));
+#endif
     if (colourIndexFG < m_colours.size())
       m_styleProps.insert("draw:end-color", getColourString(m_colours[colourIndexFG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexFG out of bonds\n"));
+#endif
     m_styleProps.remove("draw:opacity");
     if (m_fillBGTransparency > 0)
       m_styleProps.insert("libwpg:start-opacity", (double)(1 - m_fillBGTransparency/255.0), WPX_PERCENT);
@@ -197,8 +226,16 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     m_styleProps.insert("draw:style", "radial");
     if (colourIndexBG < m_colours.size())
       m_styleProps.insert("draw:start-color", getColourString(m_colours[colourIndexBG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexBG out of bonds\n"));
+#endif
     if (colourIndexFG < m_colours.size())
       m_styleProps.insert("draw:end-color", getColourString(m_colours[colourIndexFG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexFG out of bonds\n"));
+#endif
     m_styleProps.remove("draw:opacity");
     if (m_fillBGTransparency > 0)
       m_styleProps.insert("libwpg:start-opacity", (double)(1 - m_fillBGTransparency/255.0), WPX_PERCENT);
@@ -238,7 +275,12 @@ void libvisio::VSDXContentCollector::_fillAndShadowProperties(unsigned colourInd
     // fill types we don't handle right, but let us approximate with solid fill
   {
     m_fillType = "solid";
-    m_styleProps.insert("draw:fill-color", getColourString(m_colours[colourIndexBG]));
+    if (colourIndexBG < m_colours.size())
+      m_styleProps.insert("draw:fill-color", getColourString(m_colours[colourIndexBG]));
+#ifdef DEBUG
+    else
+      VSD_DEBUG_MSG(("_fillAndShadowProperties: colourIndexBG out of bonds\n"));
+#endif
   }
 
   if (shadowPattern != 0)
@@ -792,30 +834,18 @@ void libvisio::VSDXContentCollector::_flushText()
         VSD_DEBUG_MSG(("Charcount: %d, max: %lu, stream size: %lu\n", m_charFormats[charIndex].charCount, max, (unsigned long)m_textStream.size()));
         max = (m_charFormats[charIndex].charCount == 0 && m_textStream.size()) ? m_textStream.size()/2 : max;
         VSD_DEBUG_MSG(("Charcount: %d, max: %lu, stream size: %lu\n", m_charFormats[charIndex].charCount, max, (unsigned long)m_textStream.size()));
-        VSDInternalStream tmpStream(&pTextBuffer[textBufferPosition], max*2);
-        _appendUTF16LE(text, &tmpStream);
+        std::vector<unsigned char> tmpBuffer(max*2);
+        memcpy(&tmpBuffer[0], &pTextBuffer[textBufferPosition], max*2);
+        appendCharacters(text, tmpBuffer);
         textBufferPosition += max*2;
       }
       else
       {
         unsigned long max = m_charFormats[charIndex].charCount <= m_textStream.size() ? m_charFormats[charIndex].charCount : m_textStream.size();
         max = (m_charFormats[charIndex].charCount == 0 && m_textStream.size()) ? m_textStream.size() : max;
-        VSDInternalStream tmpStream(&pTextBuffer[textBufferPosition], max);
-        while (!tmpStream.atEOS())
-        {
-          unsigned char character = readU8(&tmpStream);
-          if (character == 0x1e)
-          {
-            if (m_fieldIndex < m_fields.size())
-              text.append(m_fields[m_fieldIndex++].cstr());
-            else
-              m_fieldIndex++;
-          }
-          else if (character <= 0x20)
-            _appendUCS4(text, (unsigned) 0x20);
-          else
-            _appendUCS4(text, (unsigned) character);
-        }
+        std::vector<unsigned char> tmpBuffer(max);
+        memcpy(&tmpBuffer[0], &pTextBuffer[textBufferPosition], max);
+        appendCharacters(text, tmpBuffer, 0);
         textBufferPosition += max;
       }
       WPXPropertyList textProps;
@@ -2079,24 +2109,12 @@ void libvisio::VSDXContentCollector::_convertDataToString(WPXString &result, con
 {
   if (!data.size())
     return;
-  WPXInputStream *pStream = const_cast<WPXInputStream *>(data.getDataStream());
-  if (!pStream)
-    return;
+  std::vector<unsigned char> tmpData(data.size());
+  memcpy(&tmpData[0], data.getDataBuffer(), data.size());
   if (format == VSD_TEXT_ANSI)
-  {
-    while (!pStream->atEOS())
-    {
-      unsigned char character = readU8(pStream);
-      if (character <= 0x20)
-        _appendUCS4(result, (unsigned) 0x20);
-      else
-        _appendUCS4(result, (unsigned) character);
-    }
-  }
+    appendCharacters(result, tmpData, 0);
   else if (format == VSD_TEXT_UTF16)
-  {
-    _appendUTF16LE(result, pStream);
-  }
+    appendCharacters(result, tmpData);
 }
 
 void libvisio::VSDXContentCollector::collectName(unsigned id, unsigned level, const WPXBinaryData &name, TextFormat format)
@@ -2278,7 +2296,6 @@ void libvisio::VSDXContentCollector::_handleLevelChange(unsigned level)
   m_currentLevel = level;
 }
 
-
 void libvisio::VSDXContentCollector::startPage()
 {
   if (m_isShapeStarted)
@@ -2323,118 +2340,6 @@ void libvisio::VSDXContentCollector::endPages(const std::vector<unsigned> &pageO
   m_pages.draw(m_painter);
 }
 
-#define SURROGATE_VALUE(h,l) (((h) - 0xd800) * 0x400 + (l) - 0xdc00 + 0x10000)
-
-void libvisio::VSDXContentCollector::_appendUTF16LE(WPXString &text, WPXInputStream *input)
-{
-  if (!input)
-    return;
-  while (!input->atEOS())
-  {
-    uint16_t high_surrogate = 0;
-    bool fail = false;
-    uint32_t ucs4Character = 0;
-    uint16_t character = 0;
-    while (true)
-    {
-      if (input->atEOS())
-      {
-        fail = true;
-        break;
-      }
-      character = readU16(input);
-      if (character == 0xfffc)
-      {
-        if (m_fieldIndex < m_fields.size())
-          text.append(m_fields[m_fieldIndex++].cstr());
-        else
-          m_fieldIndex++;
-      }
-      else if (character >= 0xdc00 && character < 0xe000) /* low surrogate */
-      {
-        if (high_surrogate)
-        {
-          ucs4Character = SURROGATE_VALUE(high_surrogate, character);
-          high_surrogate = 0;
-          break;
-        }
-        else
-        {
-          fail = true;
-          break;
-        }
-      }
-      else
-      {
-        if (high_surrogate)
-        {
-          fail = true;
-          break;
-        }
-        if (character >= 0xd800 && character < 0xdc00) /* high surrogate */
-          high_surrogate = character;
-        else
-        {
-          ucs4Character = character;
-          break;
-        }
-      }
-    }
-    if (fail)
-      throw GenericException();
-
-    _appendUCS4(text, ucs4Character);
-  }
-}
-
-void libvisio::VSDXContentCollector::_appendUCS4(WPXString &text, unsigned ucs4Character)
-{
-  unsigned char first;
-  int len;
-  if (ucs4Character < 0x80)
-  {
-    first = 0;
-    len = 1;
-  }
-  else if (ucs4Character < 0x800)
-  {
-    first = 0xc0;
-    len = 2;
-  }
-  else if (ucs4Character < 0x10000)
-  {
-    first = 0xe0;
-    len = 3;
-  }
-  else if (ucs4Character < 0x200000)
-  {
-    first = 0xf0;
-    len = 4;
-  }
-  else if (ucs4Character < 0x4000000)
-  {
-    first = 0xf8;
-    len = 5;
-  }
-  else
-  {
-    first = 0xfc;
-    len = 6;
-  }
-
-  unsigned char outbuf[6] = { 0, 0, 0, 0, 0, 0 };
-  int i;
-  for (i = len - 1; i > 0; --i)
-  {
-    outbuf[i] = (ucs4Character & 0x3f) | 0x80;
-    ucs4Character >>= 6;
-  }
-  outbuf[0] = (ucs4Character & 0xff) | first;
-
-  for (i = 0; i < len; i++)
-    text.append(outbuf[i]);
-}
-
 bool libvisio::VSDXContentCollector::parseFormatId( const char *formatString, unsigned short &result )
 {
   using namespace ::boost::spirit::classic;
diff --git a/src/lib/VSDXContentCollector.h b/src/lib/VSDXContentCollector.h
index c381610..99be8da 100644
--- a/src/lib/VSDXContentCollector.h
+++ b/src/lib/VSDXContentCollector.h
@@ -161,8 +161,6 @@ private:
   void _flushCurrentPage();
 
   void _handleLevelChange(unsigned level);
-  void _appendUTF16LE(WPXString &text, WPXInputStream *input);
-  void _appendUCS4(WPXString &text, unsigned ucs4Character);
 
   void _handleForeignData(const WPXBinaryData &data);
 
diff --git a/src/lib/libvisio_utils.cpp b/src/lib/libvisio_utils.cpp
index 05e04cf..5ac2e92 100644
--- a/src/lib/libvisio_utils.cpp
+++ b/src/lib/libvisio_utils.cpp
@@ -32,6 +32,61 @@
 
 #define VSD_NUM_ELEMENTS(array) sizeof(array)/sizeof(array[0])
 
+#define SURROGATE_VALUE(h,l) (((h) - 0xd800) * 0x400 + (l) - 0xdc00 + 0x10000)
+
+namespace
+{
+
+static void _appendUCS4(WPXString &text, unsigned ucs4Character)
+{
+  unsigned char first;
+  int len;
+  if (ucs4Character < 0x80)
+  {
+    first = 0;
+    len = 1;
+  }
+  else if (ucs4Character < 0x800)
+  {
+    first = 0xc0;
+    len = 2;
+  }
+  else if (ucs4Character < 0x10000)
+  {
+    first = 0xe0;
+    len = 3;
+  }
+  else if (ucs4Character < 0x200000)
+  {
+    first = 0xf0;
+    len = 4;
+  }
+  else if (ucs4Character < 0x4000000)
+  {
+    first = 0xf8;
+    len = 5;
+  }
+  else
+  {
+    first = 0xfc;
+    len = 6;
+  }
+
+  unsigned char outbuf[6] = { 0, 0, 0, 0, 0, 0 };
+  int i;
+  for (i = len - 1; i > 0; --i)
+  {
+    outbuf[i] = (ucs4Character & 0x3f) | 0x80;
+    ucs4Character >>= 6;
+  }
+  outbuf[0] = (ucs4Character & 0xff) | first;
+
+  for (i = 0; i < len; i++)
+    text.append(outbuf[i]);
+}
+
+} // anonymous namespace
+
 uint8_t libvisio::readU8(WPXInputStream *input)
 {
   if (!input || input->atEOS())
@@ -108,4 +163,320 @@ double libvisio::readDouble(WPXInputStream *input)
 
   return tmpUnion.d;
 }
+
+void libvisio::appendCharacters(WPXString &text, const std::vector<unsigned char> &characters, unsigned short charset)
+{
+  static const unsigned short cp874map[] =
+  {
+    0x20AC, 0x0020, 0x0020, 0x0020, 0x0020, 0x2026, 0x0020, 0x0020,
+    0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x00A0, 0x0E01, 0x0E02, 0x0E03, 0x0E04, 0x0E05, 0x0E06, 0x0E07,
+    0x0E08, 0x0E09, 0x0E0A, 0x0E0B, 0x0E0C, 0x0E0D, 0x0E0E, 0x0E0F,
+    0x0E10, 0x0E11, 0x0E12, 0x0E13, 0x0E14, 0x0E15, 0x0E16, 0x0E17,
+    0x0E18, 0x0E19, 0x0E1A, 0x0E1B, 0x0E1C, 0x0E1D, 0x0E1E, 0x0E1F,
+    0x0E20, 0x0E21, 0x0E22, 0x0E23, 0x0E24, 0x0E25, 0x0E26, 0x0E27,
+    0x0E28, 0x0E29, 0x0E2A, 0x0E2B, 0x0E2C, 0x0E2D, 0x0E2E, 0x0E2F,
+    0x0E30, 0x0E31, 0x0E32, 0x0E33, 0x0E34, 0x0E35, 0x0E36, 0x0E37,
+    0x0E38, 0x0E39, 0x0E3A, 0x0020, 0x0020, 0x0020, 0x0020, 0x0E3F,
+    0x0E40, 0x0E41, 0x0E42, 0x0E43, 0x0E44, 0x0E45, 0x0E46, 0x0E47,
+    0x0E48, 0x0E49, 0x0E4A, 0x0E4B, 0x0E4C, 0x0E4D, 0x0E4E, 0x0E4F,
+    0x0E50, 0x0E51, 0x0E52, 0x0E53, 0x0E54, 0x0E55, 0x0E56, 0x0E57,
+    0x0E58, 0x0E59, 0x0E5A, 0x0E5B, 0x0020, 0x0020, 0x0020, 0x0020
+  };
+
+  static const unsigned short cp1250map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0020, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x0020, 0x2030, 0x0160, 0x2039, 0x015A, 0x0164, 0x017D, 0x0179,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x0020, 0x2122, 0x0161, 0x203A, 0x015B, 0x0165, 0x017E, 0x017A,
+    0x00A0, 0x02C7, 0x02D8, 0x0141, 0x00A4, 0x0104, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x015E, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x017B,
+    0x00B0, 0x00B1, 0x02DB, 0x0142, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x0105, 0x015F, 0x00BB, 0x013D, 0x02DD, 0x013E, 0x017C,
+    0x0154, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x0139, 0x0106, 0x00C7,
+    0x010C, 0x00C9, 0x0118, 0x00CB, 0x011A, 0x00CD, 0x00CE, 0x010E,
+    0x0110, 0x0143, 0x0147, 0x00D3, 0x00D4, 0x0150, 0x00D6, 0x00D7,
+    0x0158, 0x016E, 0x00DA, 0x0170, 0x00DC, 0x00DD, 0x0162, 0x00DF,
+    0x0155, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x013A, 0x0107, 0x00E7,
+    0x010D, 0x00E9, 0x0119, 0x00EB, 0x011B, 0x00ED, 0x00EE, 0x010F,
+    0x0111, 0x0144, 0x0148, 0x00F3, 0x00F4, 0x0151, 0x00F6, 0x00F7,
+    0x0159, 0x016F, 0x00FA, 0x0171, 0x00FC, 0x00FD, 0x0163, 0x02D9
+  };
+
+  static const unsigned short cp1251map[] =
+  {
+    0x0402, 0x0403, 0x201A, 0x0453, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x20AC, 0x2030, 0x0409, 0x2039, 0x040A, 0x040C, 0x040B, 0x040F,
+    0x0452, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x0020, 0x2122, 0x0459, 0x203A, 0x045A, 0x045C, 0x045B, 0x045F,
+    0x00A0, 0x040E, 0x045E, 0x0408, 0x00A4, 0x0490, 0x00A6, 0x00A7,
+    0x0401, 0x00A9, 0x0404, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x0407,
+    0x00B0, 0x00B1, 0x0406, 0x0456, 0x0491, 0x00B5, 0x00B6, 0x00B7,
+    0x0451, 0x2116, 0x0454, 0x00BB, 0x0458, 0x0405, 0x0455, 0x0457,
+    0x0410, 0x0411, 0x0412, 0x0413, 0x0414, 0x0415, 0x0416, 0x0417,
+    0x0418, 0x0419, 0x041A, 0x041B, 0x041C, 0x041D, 0x041E, 0x041F,
+    0x0420, 0x0421, 0x0422, 0x0423, 0x0424, 0x0425, 0x0426, 0x0427,
+    0x0428, 0x0429, 0x042A, 0x042B, 0x042C, 0x042D, 0x042E, 0x042F,
+    0x0430, 0x0431, 0x0432, 0x0433, 0x0434, 0x0435, 0x0436, 0x0437,
+    0x0438, 0x0439, 0x043A, 0x043B, 0x043C, 0x043D, 0x043E, 0x043F,
+    0x0440, 0x0441, 0x0442, 0x0443, 0x0444, 0x0445, 0x0446, 0x0447,
+    0x0448, 0x0449, 0x044A, 0x044B, 0x044C, 0x044D, 0x044E, 0x044F
+  };
+
+  static const unsigned short cp1252map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x0020, 0x017D, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x0020, 0x017E, 0x0178,
+    0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+    0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
+    0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
+    0x00D0, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
+    0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x00DD, 0x00DE, 0x00DF,
+    0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
+    0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
+    0x00F0, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
+    0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x00FD, 0x00FE, 0x00FF
+  };
+
+  static const unsigned short cp1253map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x0020, 0x2030, 0x0020, 0x2039, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x0020, 0x2122, 0x0020, 0x203A, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x00A0, 0x0385, 0x0386, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x0020, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x2015,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x0384, 0x00B5, 0x00B6, 0x00B7,
+    0x0388, 0x0389, 0x038A, 0x00BB, 0x038C, 0x00BD, 0x038E, 0x038F,
+    0x0390, 0x0391, 0x0392, 0x0393, 0x0394, 0x0395, 0x0396, 0x0397,
+    0x0398, 0x0399, 0x039A, 0x039B, 0x039C, 0x039D, 0x039E, 0x039F,
+    0x03A0, 0x03A1, 0x0020, 0x03A3, 0x03A4, 0x03A5, 0x03A6, 0x03A7,
+    0x03A8, 0x03A9, 0x03AA, 0x03AB, 0x03AC, 0x03AD, 0x03AE, 0x03AF,
+    0x03B0, 0x03B1, 0x03B2, 0x03B3, 0x03B4, 0x03B5, 0x03B6, 0x03B7,
+    0x03B8, 0x03B9, 0x03BA, 0x03BB, 0x03BC, 0x03BD, 0x03BE, 0x03BF,
+    0x03C0, 0x03C1, 0x03C2, 0x03C3, 0x03C4, 0x03C5, 0x03C6, 0x03C7,
+    0x03C8, 0x03C9, 0x03CA, 0x03CB, 0x03CC, 0x03CD, 0x03CE, 0x0020
+  };
+
+  static const unsigned short cp1254map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x02C6, 0x2030, 0x0160, 0x2039, 0x0152, 0x0020, 0x0020, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x02DC, 0x2122, 0x0161, 0x203A, 0x0153, 0x0020, 0x0020, 0x0178,
+    0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+    0x00C0, 0x00C1, 0x00C2, 0x00C3, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
+    0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x00CC, 0x00CD, 0x00CE, 0x00CF,
+    0x011E, 0x00D1, 0x00D2, 0x00D3, 0x00D4, 0x00D5, 0x00D6, 0x00D7,
+    0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x0130, 0x015E, 0x00DF,
+    0x00E0, 0x00E1, 0x00E2, 0x00E3, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
+    0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x00EC, 0x00ED, 0x00EE, 0x00EF,
+    0x011F, 0x00F1, 0x00F2, 0x00F3, 0x00F4, 0x00F5, 0x00F6, 0x00F7,
+    0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x0131, 0x015F, 0x00FF
+  };
+
+  static const unsigned short cp1255map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x02C6, 0x2030, 0x0020, 0x2039, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x02DC, 0x2122, 0x0020, 0x203A, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x20AA, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x00D7, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x00B9, 0x00F7, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+    0x05B0, 0x05B1, 0x05B2, 0x05B3, 0x05B4, 0x05B5, 0x05B6, 0x05B7,
+    0x05B8, 0x05B9, 0x0020, 0x05BB, 0x05BC, 0x05BD, 0x05BE, 0x05BF,
+    0x05C0, 0x05C1, 0x05C2, 0x05C3, 0x05F0, 0x05F1, 0x05F2, 0x05F3,
+    0x05F4, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020, 0x0020,
+    0x05D0, 0x05D1, 0x05D2, 0x05D3, 0x05D4, 0x05D5, 0x05D6, 0x05D7,
+    0x05D8, 0x05D9, 0x05DA, 0x05DB, 0x05DC, 0x05DD, 0x05DE, 0x05DF,
+    0x05E0, 0x05E1, 0x05E2, 0x05E3, 0x05E4, 0x05E5, 0x05E6, 0x05E7,
+    0x05E8, 0x05E9, 0x05EA, 0x0020, 0x0020, 0x200E, 0x200F, 0x0020
+  };
+
+  static const unsigned short cp1256map[] =
+  {
+    0x20AC, 0x067E, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x02C6, 0x2030, 0x0679, 0x2039, 0x0152, 0x0686, 0x0698, 0x0688,
+    0x06AF, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x06A9, 0x2122, 0x0691, 0x203A, 0x0153, 0x200C, 0x200D, 0x06BA,
+    0x00A0, 0x060C, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x06BE, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x00B9, 0x061B, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x061F,
+    0x06C1, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627,
+    0x0628, 0x0629, 0x062A, 0x062B, 0x062C, 0x062D, 0x062E, 0x062F,
+    0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x00D7,
+    0x0637, 0x0638, 0x0639, 0x063A, 0x0640, 0x0641, 0x0642, 0x0643,
+    0x00E0, 0x0644, 0x00E2, 0x0645, 0x0646, 0x0647, 0x0648, 0x00E7,
+    0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x0649, 0x064A, 0x00EE, 0x00EF,
+    0x064B, 0x064C, 0x064D, 0x064E, 0x00F4, 0x064F, 0x0650, 0x00F7,
+    0x0651, 0x00F9, 0x0652, 0x00FB, 0x00FC, 0x200E, 0x200F, 0x06D2
+  };
+
+  static const unsigned short cp1257map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0020, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x0020, 0x2030, 0x0020, 0x2039, 0x0020, 0x00A8, 0x02C7, 0x00B8,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x0020, 0x2122, 0x0020, 0x203A, 0x0020, 0x00AF, 0x02DB, 0x0020,
+    0x00A0, 0x0020, 0x00A2, 0x00A3, 0x00A4, 0x0020, 0x00A6, 0x00A7,
+    0x00D8, 0x00A9, 0x0156, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00C6,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00F8, 0x00B9, 0x0157, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00E6,
+    0x0104, 0x012E, 0x0100, 0x0106, 0x00C4, 0x00C5, 0x0118, 0x0112,
+    0x010C, 0x00C9, 0x0179, 0x0116, 0x0122, 0x0136, 0x012A, 0x013B,
+    0x0160, 0x0143, 0x0145, 0x00D3, 0x014C, 0x00D5, 0x00D6, 0x00D7,
+    0x0172, 0x0141, 0x015A, 0x016A, 0x00DC, 0x017B, 0x017D, 0x00DF,
+    0x0105, 0x012F, 0x0101, 0x0107, 0x00E4, 0x00E5, 0x0119, 0x0113,
+    0x010D, 0x00E9, 0x017A, 0x0117, 0x0123, 0x0137, 0x012B, 0x013C,
+    0x0161, 0x0144, 0x0146, 0x00F3, 0x014D, 0x00F5, 0x00F6, 0x00F7,
+    0x0173, 0x0142, 0x015B, 0x016B, 0x00FC, 0x017C, 0x017E, 0x02D9
+  };
+
+  static const unsigned short cp1258map[] =
+  {
+    0x20AC, 0x0020, 0x201A, 0x0192, 0x201E, 0x2026, 0x2020, 0x2021,
+    0x02C6, 0x2030, 0x0020, 0x2039, 0x0152, 0x0020, 0x0020, 0x0020,
+    0x0020, 0x2018, 0x2019, 0x201C, 0x201D, 0x2022, 0x2013, 0x2014,
+    0x02DC, 0x2122, 0x0020, 0x203A, 0x0153, 0x0020, 0x0020, 0x0178,
+    0x00A0, 0x00A1, 0x00A2, 0x00A3, 0x00A4, 0x00A5, 0x00A6, 0x00A7,
+    0x00A8, 0x00A9, 0x00AA, 0x00AB, 0x00AC, 0x00AD, 0x00AE, 0x00AF,
+    0x00B0, 0x00B1, 0x00B2, 0x00B3, 0x00B4, 0x00B5, 0x00B6, 0x00B7,
+    0x00B8, 0x00B9, 0x00BA, 0x00BB, 0x00BC, 0x00BD, 0x00BE, 0x00BF,
+    0x00C0, 0x00C1, 0x00C2, 0x0102, 0x00C4, 0x00C5, 0x00C6, 0x00C7,
+    0x00C8, 0x00C9, 0x00CA, 0x00CB, 0x0300, 0x00CD, 0x00CE, 0x00CF,
+    0x0110, 0x00D1, 0x0309, 0x00D3, 0x00D4, 0x01A0, 0x00D6, 0x00D7,
+    0x00D8, 0x00D9, 0x00DA, 0x00DB, 0x00DC, 0x01AF, 0x0303, 0x00DF,
+    0x00E0, 0x00E1, 0x00E2, 0x0103, 0x00E4, 0x00E5, 0x00E6, 0x00E7,
+    0x00E8, 0x00E9, 0x00EA, 0x00EB, 0x0301, 0x00ED, 0x00EE, 0x00EF,
+    0x0111, 0x00F1, 0x0323, 0x00F3, 0x00F4, 0x01A1, 0x00F6, 0x00F7,
+    0x00F8, 0x00F9, 0x00FA, 0x00FB, 0x00FC, 0x01B0, 0x20AB, 0x00FF
+  };
+  std::vector<unsigned char>::const_iterator iter = characters.begin();
+  while (iter != characters.end())
+  {
+    uint32_t ucs4Character = 0;
+    if (*iter < 0x20)
+    {
+      ucs4Character = 0x20;
+      iter++;
+    }
+    else if (*iter >= 0x20 && *iter < 0x7f)
+      ucs4Character = *iter++;
+    else if (*iter == 0x7f)
+    {
+      ucs4Character = 0x20;
+      iter++;
+    }
+    else
+    {
+      switch (charset)
+      {
+      case 0: // ANSI
+        ucs4Character = cp1252map[*iter++ - 0x80];
+        break;
+      case 0xa1: // GREEEK
+        ucs4Character = cp1253map[*iter++ - 0x80];
+        break;
+      case 0xa2: // TURKISH
+        ucs4Character = cp1254map[*iter++ - 0x80];
+        break;
+      case 0xa3: // VIETNAMESE
+        ucs4Character = cp1258map[*iter++ - 0x80];
+        break;
+      case 0xb1: // HEBREW
+        ucs4Character = cp1255map[*iter++ - 0x80];
+        break;
+      case 0xb2: // ARABIC
+        ucs4Character = cp1256map[*iter++ - 0x80];
+        break;
+      case 0xba: // BALTIC
+        ucs4Character = cp1257map[*iter++ - 0x80];
+        break;
+      case 0xcc: // RUSSIAN
+        ucs4Character = cp1251map[*iter++ - 0x80];
+        break;
+      case 0xde: // THAI
+        ucs4Character = cp874map[*iter++ - 0x80];
+        break;
+      case 0xee: // CENTRAL EUROPE
+        ucs4Character = cp1250map[*iter++ - 0x80];
+        break;
+      default:
+        ucs4Character = *iter++;
+        break;
+      }
+    }
+    _appendUCS4(text, ucs4Character);
+  }
+}
+
+void libvisio::appendCharacters(WPXString &text, const std::vector<unsigned char> &characters)
+{
+  std::vector<unsigned char>::const_iterator iter = characters.begin();
+  while (iter != characters.end())
+  {
+    uint16_t high_surrogate = 0;
+    bool fail = false;
+    uint32_t ucs4Character = 0;
+    uint16_t character = 0;
+    while (true)
+    {
+      if (iter == characters.end())
+      {
+        fail = true;
+        break;
+      }
+      character = *iter++;
+      character = (uint16_t)(*iter++) << 8;
+      if (character >= 0xdc00 && character < 0xe000) /* low surrogate */
+      {
+        if (high_surrogate)
+        {
+          ucs4Character = SURROGATE_VALUE(high_surrogate, character);
+          high_surrogate = 0;
+          break;
+        }
+        else
+        {
+          fail = true;
+          break;
+        }
+      }
+      else
+      {
+        if (high_surrogate)
+        {
+          fail = true;
+          break;
+        }
+        if (character >= 0xd800 && character < 0xdc00) /* high surrogate */
+          high_surrogate = character;
+        else
+        {
+          ucs4Character = character;
+          break;
+        }
+      }
+    }
+    if (fail)
+      throw libvisio::GenericException();
+
+    _appendUCS4(text, ucs4Character);
+  }
+}
+
 /* vim:set shiftwidth=2 softtabstop=2 expandtab: */
diff --git a/src/lib/libvisio_utils.h b/src/lib/libvisio_utils.h
index 23dd559..030a46e 100644
--- a/src/lib/libvisio_utils.h
+++ b/src/lib/libvisio_utils.h
@@ -31,7 +31,9 @@
 #ifndef __LIBVISIO_UTILS_H__
 #define __LIBVISIO_UTILS_H__
 
+#include <vector>
 #include <stdio.h>
+#include <libwpd/libwpd.h>
 
 #ifdef _MSC_VER
 
@@ -92,6 +94,9 @@ uint64_t readU64(WPXInputStream *input);
 
 double readDouble(WPXInputStream *input);
 
+void appendCharacters(WPXString &text, const std::vector<unsigned char> &characters, unsigned short charset);
+void appendCharacters(WPXString &text, const std::vector<unsigned char> &characters);
+
 class EndOfStreamException
 {
 };