2
|
1 |
/*
|
|
2 |
* Copyright 2004 Sun Microsystems, Inc. All Rights Reserved.
|
|
3 |
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
|
|
4 |
*
|
|
5 |
* This code is free software; you can redistribute it and/or modify it
|
|
6 |
* under the terms of the GNU General Public License version 2 only, as
|
|
7 |
* published by the Free Software Foundation. Sun designates this
|
|
8 |
* particular file as subject to the "Classpath" exception as provided
|
|
9 |
* by Sun in the LICENSE file that accompanied this code.
|
|
10 |
*
|
|
11 |
* This code is distributed in the hope that it will be useful, but WITHOUT
|
|
12 |
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
13 |
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
14 |
* version 2 for more details (a copy is included in the LICENSE file that
|
|
15 |
* accompanied this code).
|
|
16 |
*
|
|
17 |
* You should have received a copy of the GNU General Public License version
|
|
18 |
* 2 along with this work; if not, write to the Free Software Foundation,
|
|
19 |
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
20 |
*
|
|
21 |
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
|
|
22 |
* CA 95054 USA or visit www.sun.com if you need additional information or
|
|
23 |
* have any questions.
|
|
24 |
*/
|
|
25 |
#include <stdio.h>
|
|
26 |
#include <stddef.h>
|
|
27 |
#include <stdlib.h>
|
|
28 |
#include <string.h>
|
|
29 |
#include <ctype.h>
|
|
30 |
#include <locale.h>
|
|
31 |
#include <langinfo.h>
|
|
32 |
#include <iconv.h>
|
|
33 |
|
|
34 |
/* Routines to convert back and forth between Platform Encoding and UTF-8 */
|
|
35 |
|
|
36 |
/* Error and assert macros */
|
|
37 |
#define UTF_ERROR(m) utfError(__FILE__, __LINE__, m)
|
|
38 |
#define UTF_ASSERT(x) ( (x)==0 ? UTF_ERROR("ASSERT ERROR " #x) : (void)0 )
|
|
39 |
#define UTF_DEBUG(x)
|
|
40 |
|
|
41 |
/* Global variables */
|
|
42 |
static iconv_t iconvToPlatform = (iconv_t)-1;
|
|
43 |
static iconv_t iconvFromPlatform = (iconv_t)-1;
|
|
44 |
|
|
45 |
/*
|
|
46 |
* Error handler
|
|
47 |
*/
|
|
48 |
static void
|
|
49 |
utfError(char *file, int line, char *message)
|
|
50 |
{
|
|
51 |
(void)fprintf(stderr, "UTF ERROR [\"%s\":%d]: %s\n", file, line, message);
|
|
52 |
abort();
|
|
53 |
}
|
|
54 |
|
|
55 |
/*
|
|
56 |
* Initialize all utf processing.
|
|
57 |
*/
|
|
58 |
static void
|
|
59 |
utfInitialize(void)
|
|
60 |
{
|
|
61 |
char *codeset;
|
|
62 |
|
|
63 |
/* Set the locale from the environment */
|
|
64 |
(void)setlocale(LC_ALL, "");
|
|
65 |
|
|
66 |
/* Get the codeset name */
|
|
67 |
codeset = (char*)nl_langinfo(CODESET);
|
|
68 |
if ( codeset == NULL || codeset[0] == 0 ) {
|
|
69 |
UTF_DEBUG(("NO codeset returned by nl_langinfo(CODESET)\n"));
|
|
70 |
return;
|
|
71 |
}
|
|
72 |
|
|
73 |
UTF_DEBUG(("Codeset = %s\n", codeset));
|
|
74 |
|
|
75 |
/* If we don't need this, skip it */
|
|
76 |
if (strcmp(codeset, "UTF-8") == 0 || strcmp(codeset, "utf8") == 0 ) {
|
|
77 |
UTF_DEBUG(("NO iconv() being used because it is not needed\n"));
|
|
78 |
return;
|
|
79 |
}
|
|
80 |
|
|
81 |
/* Open conversion descriptors */
|
|
82 |
iconvToPlatform = iconv_open(codeset, "UTF-8");
|
|
83 |
if ( iconvToPlatform == (iconv_t)-1 ) {
|
|
84 |
UTF_ERROR("Failed to complete iconv_open() setup");
|
|
85 |
}
|
|
86 |
iconvFromPlatform = iconv_open("UTF-8", codeset);
|
|
87 |
if ( iconvFromPlatform == (iconv_t)-1 ) {
|
|
88 |
UTF_ERROR("Failed to complete iconv_open() setup");
|
|
89 |
}
|
|
90 |
}
|
|
91 |
|
|
92 |
/*
|
|
93 |
* Terminate all utf processing
|
|
94 |
*/
|
|
95 |
static void
|
|
96 |
utfTerminate(void)
|
|
97 |
{
|
|
98 |
if ( iconvFromPlatform!=(iconv_t)-1 ) {
|
|
99 |
(void)iconv_close(iconvFromPlatform);
|
|
100 |
}
|
|
101 |
if ( iconvToPlatform!=(iconv_t)-1 ) {
|
|
102 |
(void)iconv_close(iconvToPlatform);
|
|
103 |
}
|
|
104 |
iconvToPlatform = (iconv_t)-1;
|
|
105 |
iconvFromPlatform = (iconv_t)-1;
|
|
106 |
}
|
|
107 |
|
|
108 |
/*
|
|
109 |
* Do iconv() conversion.
|
|
110 |
* Returns length or -1 if output overflows.
|
|
111 |
*/
|
|
112 |
static int
|
|
113 |
iconvConvert(iconv_t ic, char *bytes, int len, char *output, int outputMaxLen)
|
|
114 |
{
|
|
115 |
int outputLen = 0;
|
|
116 |
|
|
117 |
UTF_ASSERT(bytes);
|
|
118 |
UTF_ASSERT(len>=0);
|
|
119 |
UTF_ASSERT(output);
|
|
120 |
UTF_ASSERT(outputMaxLen>len);
|
|
121 |
|
|
122 |
output[0] = 0;
|
|
123 |
outputLen = 0;
|
|
124 |
|
|
125 |
if ( ic != (iconv_t)-1 ) {
|
|
126 |
int returnValue;
|
|
127 |
size_t inLeft;
|
|
128 |
size_t outLeft;
|
|
129 |
char *inbuf;
|
|
130 |
char *outbuf;
|
|
131 |
|
|
132 |
inbuf = bytes;
|
|
133 |
outbuf = output;
|
|
134 |
inLeft = len;
|
|
135 |
outLeft = outputMaxLen;
|
|
136 |
returnValue = iconv(ic, (void*)&inbuf, &inLeft, &outbuf, &outLeft);
|
|
137 |
if ( returnValue >= 0 && inLeft==0 ) {
|
|
138 |
outputLen = outputMaxLen-outLeft;
|
|
139 |
output[outputLen] = 0;
|
|
140 |
return outputLen;
|
|
141 |
}
|
|
142 |
|
|
143 |
/* Failed to do the conversion */
|
|
144 |
return -1;
|
|
145 |
}
|
|
146 |
|
|
147 |
/* Just copy bytes */
|
|
148 |
outputLen = len;
|
|
149 |
(void)memcpy(output, bytes, len);
|
|
150 |
output[len] = 0;
|
|
151 |
return outputLen;
|
|
152 |
}
|
|
153 |
|
|
154 |
/*
|
|
155 |
* Convert UTF-8 to Platform Encoding.
|
|
156 |
* Returns length or -1 if output overflows.
|
|
157 |
*/
|
|
158 |
static int
|
|
159 |
utf8ToPlatform(char *utf8, int len, char *output, int outputMaxLen)
|
|
160 |
{
|
|
161 |
return iconvConvert(iconvToPlatform, utf8, len, output, outputMaxLen);
|
|
162 |
}
|
|
163 |
|
|
164 |
/*
|
|
165 |
* Convert Platform Encoding to UTF-8.
|
|
166 |
* Returns length or -1 if output overflows.
|
|
167 |
*/
|
|
168 |
static int
|
|
169 |
platformToUtf8(char *str, int len, char *output, int outputMaxLen)
|
|
170 |
{
|
|
171 |
return iconvConvert(iconvFromPlatform, str, len, output, outputMaxLen);
|
|
172 |
}
|
|
173 |
|
|
174 |
int
|
|
175 |
convertUft8ToPlatformString(char* utf8_str, int utf8_len, char* platform_str, int platform_len) {
|
|
176 |
if (iconvToPlatform == (iconv_t)-1) {
|
|
177 |
utfInitialize();
|
|
178 |
}
|
|
179 |
return utf8ToPlatform(utf8_str, utf8_len, platform_str, platform_len);
|
|
180 |
}
|