utf8.c

   1 /*
   2  * utf8.c
   3  *
   4  * Part of gwm, the Gratuitous Window Manager,
   5  *     by Gary Wong, <gtw@gnu.org>.
   6  *
   7  * Copyright (C) 2009  Gary Wong
   8  *
   9  *  This program is free software: you can redistribute it and/or modify
  10  *  it under the terms of version 3 of the GNU General Public License as
  11  *  published by the Free Software Foundation.
  12  *
  13  *  This program is distributed in the hope that it will be useful,
  14  *  but WITHOUT ANY WARRANTY; without even the implied warranty of
  15  *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  16  *  GNU General Public License for more details.
  17  *
  18  *  You should have received a copy of the GNU General Public License
  19  *  along with this program.  If not, see <http://www.gnu.org/licenses/>.
  20  *
  21  * $Id$
  22  */
  23
  24 #include <config.h>
  25
  26 #if HAVE_ICONV_H
  27 #include <iconv.h>
  28 #endif
  29 #include <string.h>
  30 #include <xcb/xcb.h>
  31
  32 #include "gwm.h"
  33
  34 #include "utf8.h"
  35
  36 #if HAVE_ICONV
  37 iconv_t iso2022;
  38 int tried_iso2022;
  39 #endif
  40
  41 extern char *to_utf8( enum gwm_encoding encoding, const char *in,
  42                       size_t len ) {
  43
  44     size_t outlen;
  45     char *out, *outp;
  46
  47     if( len < 0 )
  48         len = strlen( in );
  49
  50 #if HAVE_ICONV
  51     outlen = len << ( encoding == ENCODING_COMPOUND ? 2 : 1 );
  52 #else
  53     outlen = len << 1;
  54 #endif
  55
  56     outp = out = xmalloc( outlen + 1 );
  57
  58 #if HAVE_ICONV
  59     if( encoding == ENCODING_COMPOUND ) {
  60         if( !tried_iso2022 ) {
  61             iso2022 = iconv_open( "UTF-8", "ISO-2022-JP-2" );
  62             tried_iso2022 = TRUE;
  63         }
  64
  65         if( iso2022 != (iconv_t) -1 ) {
  66             static const char resetseq[ 3 ] = "\x1B\x2D\x41";
  67             const char *inp;
  68             size_t resetlen = 3;
  69
  70             /* Reset the decoder to the Compound Text initial state
  71                (G1 = ASCII, G3 = ISO 8859-1). */
  72             inp = resetseq;
  73             iconv( iso2022, NULL, NULL, NULL, NULL );
  74             /* Bah.  Several old implementations of iconv() declared
  75                the inbuf parameter as (const char **), but SUS says
  76                it's simply (char **).  We cast the thing to (void *),
  77                which will keep them both happy. */
  78             iconv( iso2022, (void *) &inp, &resetlen, &outp, &outlen );
  79
  80             iconv( iso2022, (void *) &in, &len, &outp, &outlen );
  81
  82             *outp++ = 0;
  83
  84             return xrealloc( out, outp - out );
  85         }
  86     }
  87 #endif
  88
  89     for( ; len; len-- )
  90         if( *in & 0x80 ) {
  91             *outp++ = 0xC0 | ( *in >> 6 );
  92             *outp++ = 0x80 | ( *in & 0x3F );
  93         } else
  94             *outp++ = *in++;
  95
  96     *outp++ = 0;
  97
  98     return xrealloc( out, outp - out );
  99 }
 100
 101 extern void cleanup_utf8( void ) {
 102
 103 #if HAVE_ICONV
 104     if( tried_iso2022 && iso2022 != (iconv_t) -1 )
 105         iconv_close( iso2022 );
 106 #endif
 107 }