# --- T2-COPYRIGHT-NOTE-BEGIN ---
# This copyright note is auto-generated by ./scripts/Create-CopyPatch.
# 
# T2 SDE: package/.../exact-image/no-utf8-pdf.patch
# Copyright (C) 2009 The T2 SDE Project
# 
# More information can be found in the files COPYING and README.
# 
# This patch file is dual-licensed. It is available under the license the
# patched project is licensed under, as long as it is an OpenSource license
# as defined at http://www.opensource.org/ (e.g. BSD, X11) or under the terms
# of the GNU General Public License as published by the Free Software
# Foundation; either version 2 of the License, or (at your option) any later
# version.
# --- T2-COPYRIGHT-NOTE-END ---

No half-way hocr 2 pdf writing in utf8, yet.

Index: codecs/pdf.cc
===================================================================
--- ./codecs/pdf.cc	(revision 1516)
+++ ./codecs/pdf.cc	(revision 1515)
@@ -711,12 +711,10 @@
   c <<  "(";
   
   // parse string and use proper escape
+  // TODO: UTF-8 input parsing
   // TODO: Unicode mappings
   bool first_newline = true;
-  
-  // decode utf8, locally
-  std::vector<uint32_t> utf8 = DecodeUtf8(text.c_str(), text.size());
-  for (std::vector<uint32_t>::const_iterator it = utf8.begin(); it != utf8.end(); ++it)
+  for (std::string::const_iterator it = text.begin(); it != text.end(); ++it)
     {
       switch (*it)
 	{
@@ -739,7 +737,7 @@
 	  
 	  // just copy by default:
 	default:
-	  c << (char)*it;
+	  c << *it;
 	}
     }