Fix hebrew character highlight issue in a special document

core/src/fpdftext/fpdf_text.cpp

 // Copyright 2014 PDFium Authors. All rights reserved.
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
  
 // Original code copyright 2014 Foxit Software Inc. http://www.foxitsoftware.com
 
 #include "../../include/fpdfapi/fpdf_page.h"
 #include "../../include/fpdfapi/fpdf_pageobj.h"
 #include "../../include/fpdftext/fpdf_text.h"
 #include "txtproc.h"
@@ skipping 166 matching lines @@
             pBaseLine->m_BaseLine = basey;
             m_BaseLines.InsertAt(i, pBaseLine);
         }
     }
     CFX_WideString text;
     FX_LPCSTR pStr = str;
     int len = str.GetLength(), offset = 0;
     while (offset < len) {
         FX_DWORD ch = pFont->GetNextChar(pStr, offset);
         CFX_WideString unicode_str = pFont->UnicodeFromCharCode(ch);
-        text += unicode_str;
+        if (unicode_str.IsEmpty()) {
+            text += (FX_WCHAR)ch;

[jbreiden, 2014/08/18 19:10:49]

The example PDF file for this bug contains a
mapping between character codes and Unicode.
Is this mapping not being used?

====================

5 0 obj
<< /Length 353 >>
stream
/CIDInit /ProcSet findresource begin
12 dict begin
begincmap
/CIDSystemInfo
<<
  /Registry (Adobe)
  /Ordering (UCS)
  /Supplement 0
/CMapName /Adobe-Identify-UCS def
/CMapType 2 def
1 begincodespacerange
<0000> <FFFF>
endcodespacerange
1 beginbfrange
<0000> <FFFF> <0000>
endbfrange
endcmap
CMapName currentdict /CMap defineresource pop
end
end
endstream
endobj

+        }
+        else {
+            text += unicode_str;
+        }
     }
     pBaseLine->InsertTextBox(leftx, rightx, topy, bottomy, spacew, fontsize_v, text);
     return pBaseLine;
 }
 void CTextPage::WriteOutput(CFX_WideStringArray& lines, int iMinWidth)
 {
     FX_FLOAT lastheight = -1;
     FX_FLOAT lastbaseline = -1;
     FX_FLOAT MinLeftX = 1000000;
     FX_FLOAT MaxRightX = 0;
@@ skipping 580 matching lines @@
 {
     buffer.EstimateSize(0, 10240);
     CPDF_Page page;
     page.Load(pDoc, pPage);
     CPDF_ParseOptions options;
     options.m_bTextOnly = TRUE;
     options.m_bSeparateForm = FALSE;
     page.ParseContent(&options);
     _PDF_GetTextStream_Unicode(buffer, &page, TRUE, NULL);
 }