wsutil/unicode-utils.c

   1 /* unicode-utils.c
   2  * Unicode utility routines
   3  *
   4  * $Id$
   5  *
   6  * Wireshark - Network traffic analyzer
   7  * By Gerald Combs <gerald@wireshark.org>
   8  * Copyright 2006 Gerald Combs
   9  *
  10  * This program is free software; you can redistribute it and/or
  11  * modify it under the terms of the GNU General Public License
  12  * as published by the Free Software Foundation; either version 2
  13  * of the License, or (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, write to the Free Software
  22  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  23  */
  24
  25 #ifndef _WIN32
  26 #error "This is only for Windows"
  27 #endif
  28
  29 #include "unicode-utils.h"
  30
  31 #include <shellapi.h>
  32
  33 /** @file
  34  * Unicode utilities (internal interface)
  35  *
  36  * We define UNICODE and _UNICODE under Windows.  This means that
  37  * Windows SDK routines expect UTF-16 strings, in contrast to newer
  38  * versions of Glib and GTK+ which expect UTF-8.  This module provides
  39  * convenience routines for converting between UTF-8 and UTF-16.
  40  */
  41
  42 #define INITIAL_UTFBUF_SIZE 128
  43
  44 /*
  45  * XXX - Should we use g_utf8_to_utf16() and g_utf16_to_utf8()
  46  * instead?  The goal of the functions below was to provide simple
  47  * wrappers for UTF-8 <-> UTF-16 conversion without making the
  48  * caller worry about freeing up memory afterward.
  49  */
  50
  51 /* Convert from UTF-8 to UTF-16. */
  52 wchar_t *
  53 utf_8to16(const char *utf8str)
  54 {
  55   static wchar_t *utf16buf[3];
  56   static int utf16buf_len[3];
  57   static int idx;
  58
  59   if (utf8str == NULL)
  60     return NULL;
  61
  62   idx = (idx + 1) % 3;
  63
  64   /*
  65    * Allocate the buffer if it's not already allocated.
  66    */
  67   if (utf16buf[idx] == NULL) {
  68     utf16buf_len[idx] = INITIAL_UTFBUF_SIZE;
  69     utf16buf[idx] = g_malloc(utf16buf_len[idx] * sizeof(wchar_t));
  70   }
  71
  72   while (MultiByteToWideChar(CP_UTF8, 0, utf8str,
  73       -1, NULL, 0) >= utf16buf_len[idx]) {
  74     /*
  75      * Double the buffer's size if it's not big enough.
  76      * The size of the buffer starts at 128, so doubling its size
  77      * adds at least another 128 bytes, which is more than enough
  78      * for one more character plus a terminating '\0'.
  79      */
  80     utf16buf_len[idx] *= 2;
  81     utf16buf[idx] = g_realloc(utf16buf[idx], utf16buf_len[idx] * sizeof(wchar_t));
  82   }
  83
  84   if (MultiByteToWideChar(CP_UTF8, 0, utf8str,
  85       -1, utf16buf[idx], utf16buf_len[idx]) == 0)
  86     return NULL;
  87
  88   return utf16buf[idx];
  89 }
  90
  91 void
  92 utf_8to16_snprintf(TCHAR *utf16buf, gint utf16buf_len, const gchar* fmt, ...)
  93 {
  94     va_list ap;
  95     gchar* dst;
  96
  97     va_start(ap,fmt);
  98     dst = g_strdup_vprintf(fmt, ap);
  99     va_end(ap);
 100
 101     _snwprintf(utf16buf, utf16buf_len, _T("%s"), utf_8to16(dst));
 102
 103     g_free(dst);
 104 }
 105
 106 /* Convert from UTF-16 to UTF-8. */
 107 gchar *
 108 utf_16to8(const wchar_t *utf16str)
 109 {
 110   static gchar *utf8buf[3];
 111   static int utf8buf_len[3];
 112   static int idx;
 113
 114   if (utf16str == NULL)
 115     return NULL;
 116
 117   idx = (idx + 1) % 3;
 118
 119   /*
 120    * Allocate the buffer if it's not already allocated.
 121    */
 122   if (utf8buf[idx] == NULL) {
 123     utf8buf_len[idx] = INITIAL_UTFBUF_SIZE;
 124     utf8buf[idx] = g_malloc(utf8buf_len[idx]);
 125   }
 126
 127   while (WideCharToMultiByte(CP_UTF8, 0, utf16str, -1,
 128       NULL, 0, NULL, NULL) >= utf8buf_len[idx]) {
 129     /*
 130      * Double the buffer's size if it's not big enough.
 131      * The size of the buffer starts at 128, so doubling its size
 132      * adds at least another 128 bytes, which is more than enough
 133      * for one more character plus a terminating '\0'.
 134      */
 135     utf8buf_len[idx] *= 2;
 136     utf8buf[idx] = g_realloc(utf8buf[idx], utf8buf_len[idx]);
 137   }
 138
 139   if (WideCharToMultiByte(CP_UTF8, 0, utf16str, -1,
 140       utf8buf[idx], utf8buf_len[idx], NULL, NULL) == 0)
 141     return NULL;
 142
 143   return utf8buf[idx];
 144 }
 145
 146 /* Convert our argument list from UTF-16 to UTF-8. */
 147 void
 148 arg_list_utf_16to8(int argc, char *argv[]) {
 149   LPWSTR              *wc_argv;
 150   int                  wc_argc, i;
 151
 152   /* Convert our arg list to UTF-8. */
 153   wc_argv = CommandLineToArgvW(GetCommandLineW(), &wc_argc);
 154   if (wc_argv && wc_argc == argc) {
 155     for (i = 0; i < argc; i++) {
 156       argv[i] = g_utf16_to_utf8(wc_argv[i], -1, NULL, NULL, NULL);
 157     }
 158   } /* XXX else bail because something is horribly, horribly wrong? */
 159 }