2 * Unicode utility routines
6 * Wireshark - Network traffic analyzer
7 * By Gerald Combs <gerald@wireshark.org>
8 * Copyright 2006 Gerald Combs
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.
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.
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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
28 #include "unicode-utils.h"
35 * Unicode utilities (internal interface)
37 * We define UNICODE and _UNICODE under Windows. This means that
38 * Windows SDK routines expect UTF-16 strings, in contrast to newer
39 * versions of Glib and GTK+ which expect UTF-8. This module provides
40 * convenience routines for converting between UTF-8 and UTF-16.
43 #define INITIAL_UTFBUF_SIZE 128
46 * XXX - Should we use g_utf8_to_utf16() and g_utf16_to_utf8()
47 * instead? The goal of the functions below was to provide simple
48 * wrappers for UTF-8 <-> UTF-16 conversion without making the
49 * caller worry about freeing up memory afterward.
52 /* Convert from UTF-8 to UTF-16. */
53 wchar_t * utf_8to16(const char *utf8str) {
54 static wchar_t *utf16buf[3];
55 static int utf16buf_len[3];
64 * Allocate the buffer if it's not already allocated.
66 if (utf16buf[idx] == NULL) {
67 utf16buf_len[idx] = INITIAL_UTFBUF_SIZE;
68 utf16buf[idx] = g_malloc(utf16buf_len[idx] * sizeof(wchar_t));
71 while (MultiByteToWideChar(CP_UTF8, 0, utf8str,
72 -1, NULL, 0) >= utf16buf_len[idx]) {
74 * Double the buffer's size if it's not big enough.
75 * The size of the buffer starts at 128, so doubling its size
76 * adds at least another 128 bytes, which is more than enough
77 * for one more character plus a terminating '\0'.
79 utf16buf_len[idx] *= 2;
80 utf16buf[idx] = g_realloc(utf16buf[idx], utf16buf_len[idx] * sizeof(wchar_t));
83 if (MultiByteToWideChar(CP_UTF8, 0, utf8str,
84 -1, utf16buf[idx], utf16buf_len[idx]) == 0)
90 /* Convert from UTF-16 to UTF-8. */
91 gchar * utf_16to8(const wchar_t *utf16str) {
92 static gchar *utf8buf[3];
93 static int utf8buf_len[3];
102 * Allocate the buffer if it's not already allocated.
104 if (utf8buf[idx] == NULL) {
105 utf8buf_len[idx] = INITIAL_UTFBUF_SIZE;
106 utf8buf[idx] = g_malloc(utf8buf_len[idx]);
109 while (WideCharToMultiByte(CP_UTF8, 0, utf16str, -1,
110 NULL, 0, NULL, NULL) >= utf8buf_len[idx]) {
112 * Double the buffer's size if it's not big enough.
113 * The size of the buffer starts at 128, so doubling its size
114 * adds at least another 128 bytes, which is more than enough
115 * for one more character plus a terminating '\0'.
117 utf8buf_len[idx] *= 2;
118 utf8buf[idx] = g_realloc(utf8buf[idx], utf8buf_len[idx]);
121 if (WideCharToMultiByte(CP_UTF8, 0, utf16str, -1,
122 utf8buf[idx], utf8buf_len[idx], NULL, NULL) == 0)