encoding_convert.h

   1 /*
   2 Project: J-Ben
   3 Author:  Paul Goins
   4 Website: http://www.vultaire.net/software/jben/
   5 License: GNU General Public License (GPL) version 2
   6          (http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt)
   7
   8 File: encoding_convert.h
   9
  10 This program is free software; you can redistribute it and/or modify
  11 it under the terms of the GNU General Public License as published by
  12 the Free Software Foundation; either version 2 of the License, or
  13 (at your option) any later version.
  14
  15 This program is distributed in the hope that it will be useful,
  16 but WITHOUT ANY WARRANTY; without even the implied warranty of
  17 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  18 GNU General Public License for more details.
  19
  20 You should have received a copy of the GNU General Public License
  21 along with this program.  If not, see <http://www.gnu.org/licenses/>
  22 */
  23
  24 #ifndef encoding_convert_h
  25 #define encoding_convert_h
  26
  27 #include "errorlog.h"
  28 #include <iconv.h>
  29 #include <cerrno>
  30 #include <sstream>
  31 #include <iomanip>
  32 #include <string>
  33 using namespace std;
  34
  35 extern string wcType;
  36
  37 bool InitUTFConv();
  38 void DestroyUTFConv();
  39 #define utfconv_wm(data) ConvertString<wchar_t, char>(data, wcType.c_str(), "UTF-8")
  40 #define utfconv_mw(data) ConvertString<char, wchar_t>(data, "UTF-8", wcType.c_str())
  41
  42 /* This is the core converter function. */
  43 template <class tsrc, class tdest>
  44 basic_string<tdest> ConvertString
  45 (const basic_string<tsrc>& sourceData, const iconv_t& converter)  {
  46         basic_string<tdest> result;
  47         int sLen = sourceData.length()+1;
  48         size_t inputBytesLeft  = sLen * sizeof(tsrc);
  49         size_t outputBytesLeft = sLen * 4;
  50         char *buffer = new char[outputBytesLeft];
  51         memset((void*)buffer, 0, outputBytesLeft);
  52         /* The libc iconv function takes a char* source, while the libiconv iconv
  53            takes a const char* source. */
  54 #ifdef __WXMSW__
  55         const char *srcData = (char *)sourceData.c_str();
  56 #else
  57         char *srcData = (char *)sourceData.c_str();
  58 #endif
  59
  60         char *destData = buffer;
  61
  62         /* libiconv stuff */
  63         size_t retcode
  64                 = iconv(converter, &srcData, &inputBytesLeft,
  65                                 &destData, &outputBytesLeft);
  66         if(retcode==(size_t)-1) {
  67                 /* If we put in error reporting later, we'll want this to return
  68                    conversion errors.  For now though, we'll do nothing and simply
  69                    bail. */
  70                 ostringstream oss;
  71                 oss << "Converting encoding using converter 0x"
  72                         << setw(8) << setfill('0') << hex << converter << dec
  73                         << ": error code = " << errno;
  74                 el.Push(EL_Error, oss.str());
  75                 goto exit_now;
  76         }
  77
  78         /* Copy result data to the string or wstring */
  79         result = (tdest*) buffer;
  80
  81 exit_now:
  82         delete[] buffer;
  83         return result;
  84 }
  85
  86 /* The below is for "on-the-fly" iconv conversions.  It creates a converter
  87    object, and then passes everything into the core converter function. */
  88 template <class tsrc, class tdest>
  89 basic_string<tdest> ConvertString
  90 (const basic_string<tsrc>& sourceData,
  91  const char* sourceEncoding,
  92  const char* targetEncoding)  {
  93         basic_string<tdest> result;
  94         iconv_t conv = iconv_open(targetEncoding, sourceEncoding);
  95         if(conv == (iconv_t)-1) return basic_string<tdest>();
  96         result = ConvertString<tsrc,tdest>(sourceData, conv);
  97         iconv_close(conv);
  98         return result;
  99 }
 100
 101 #endif