1 /*
2 * Copyright (c) 2004, 2018, Oracle and/or its affiliates. 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. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle 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 Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * 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 /* Use THIS_FILE when it is available. */
37 #ifndef THIS_FILE
38 #define THIS_FILE __FILE__
39 #endif
40
41 /* Error and assert macros */
42 #define UTF_ERROR(m) utfError(THIS_FILE, __LINE__, m)
43 #define UTF_ASSERT(x) ( (x)==0 ? UTF_ERROR("ASSERT ERROR " #x) : (void)0 )
44 #define UTF_DEBUG(x)
45
46 /* Global variables */
47 static iconv_t iconvToPlatform = (iconv_t)-1;
48 static iconv_t iconvFromPlatform = (iconv_t)-1;
49
50 /*
51 * Error handler
52 */
53 static void
54 utfError(char *file, int line, char *message)
55 {
56 (void)fprintf(stderr, "UTF ERROR [\"%s\":%d]: %s\n", file, line, message);
57 abort();
58 }
59
60 /*
61 * Initialize all utf processing.
62 */
63 static void
64 utfInitialize(void)
65 {
66 const char* codeset;
67
68 /* Set the locale from the environment */
69 (void)setlocale(LC_ALL, "");
70
71 /* Get the codeset name */
72 codeset = (char*)nl_langinfo(CODESET);
73 if ( codeset == NULL || codeset[0] == 0 ) {
74 UTF_DEBUG(("NO codeset returned by nl_langinfo(CODESET)\n"));
75 return;
76 }
77
78 UTF_DEBUG(("Codeset = %s\n", codeset));
79
80 #ifdef MACOSX
81 /* On Mac, if US-ASCII, but with no env hints, use UTF-8 */
82 const char* env_lang = getenv("LANG");
83 const char* env_lc_all = getenv("LC_ALL");
84 const char* env_lc_ctype = getenv("LC_CTYPE");
85
86 if (strcmp(codeset,"US-ASCII") == 0 &&
87 (env_lang == NULL || strlen(env_lang) == 0) &&
88 (env_lc_all == NULL || strlen(env_lc_all) == 0) &&
89 (env_lc_ctype == NULL || strlen(env_lc_ctype) == 0)) {
90 codeset = "UTF-8";
91 }
92 #endif
93
94 /* If we don't need this, skip it */
95 if (strcmp(codeset, "UTF-8") == 0 || strcmp(codeset, "utf8") == 0 ) {
96 UTF_DEBUG(("NO iconv() being used because it is not needed\n"));
97 return;
98 }
99
100 /* Open conversion descriptors */
101 iconvToPlatform = iconv_open(codeset, "UTF-8");
102 if ( iconvToPlatform == (iconv_t)-1 ) {
103 UTF_ERROR("Failed to complete iconv_open() setup");
104 }
105 iconvFromPlatform = iconv_open("UTF-8", codeset);
106 if ( iconvFromPlatform == (iconv_t)-1 ) {
107 UTF_ERROR("Failed to complete iconv_open() setup");
108 }
109 }
110
111 /*
112 * Terminate all utf processing
113 */
114 static void
115 utfTerminate(void)
116 {
117 if ( iconvFromPlatform!=(iconv_t)-1 ) {
118 (void)iconv_close(iconvFromPlatform);
119 }
120 if ( iconvToPlatform!=(iconv_t)-1 ) {
121 (void)iconv_close(iconvToPlatform);
122 }
123 iconvToPlatform = (iconv_t)-1;
124 iconvFromPlatform = (iconv_t)-1;
125 }
126
127 /*
128 * Do iconv() conversion.
129 * Returns length or -1 if output overflows.
130 */
131 static int
132 iconvConvert(iconv_t ic, char *bytes, int len, char *output, int outputMaxLen)
133 {
134 int outputLen = 0;
135
136 UTF_ASSERT(bytes);
137 UTF_ASSERT(len>=0);
138 UTF_ASSERT(output);
139 UTF_ASSERT(outputMaxLen>len);
140
141 output[0] = 0;
142 outputLen = 0;
143
144 if ( ic != (iconv_t)-1 ) {
145 int returnValue;
146 size_t inLeft;
147 size_t outLeft;
148 char *inbuf;
149 char *outbuf;
150
151 inbuf = bytes;
152 outbuf = output;
153 inLeft = len;
154 outLeft = outputMaxLen;
155 returnValue = iconv(ic, (void*)&inbuf, &inLeft, &outbuf, &outLeft);
156 if ( returnValue >= 0 && inLeft==0 ) {
157 outputLen = outputMaxLen-outLeft;
158 output[outputLen] = 0;
159 return outputLen;
160 }
161
162 /* Failed to do the conversion */
163 UTF_DEBUG(("iconv() failed to do the conversion\n"));
164 return -1;
165 }
166
167 /* Just copy bytes */
168 outputLen = len;
169 (void)memcpy(output, bytes, len);
170 output[len] = 0;
171 return outputLen;
172 }
173
174 /*
175 * Convert UTF-8 to Platform Encoding.
176 * Returns length or -1 if output overflows.
177 */
178 static int
179 utf8ToPlatform(char *utf8, int len, char *output, int outputMaxLen)
180 {
181 return iconvConvert(iconvToPlatform, utf8, len, output, outputMaxLen);
182 }
183
184 /*
185 * Convert Platform Encoding to UTF-8.
186 * Returns length or -1 if output overflows.
187 */
188 static int
189 platformToUtf8(char *str, int len, char *output, int outputMaxLen)
190 {
191 return iconvConvert(iconvFromPlatform, str, len, output, outputMaxLen);
192 }
193
194 int
195 convertUft8ToPlatformString(char* utf8_str, int utf8_len, char* platform_str, int platform_len) {
196 if (iconvToPlatform == (iconv_t)-1) {
197 utfInitialize();
198 }
199 return utf8ToPlatform(utf8_str, utf8_len, platform_str, platform_len);
200 }