about summary refs log tree commit diff
path: root/libidn/toutf8.c
blob: 262f252d5ffb09f3b2f3733e8d20716774e87cde (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
/* toutf8.c	Convert strings from system locale into UTF-8.
 * Copyright (C) 2002, 2003, 2004  Simon Josefsson
 *
 * This file is part of GNU Libidn.
 *
 * GNU Libidn is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * GNU Libidn is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with GNU Libidn; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */

#if HAVE_CONFIG_H
# include "config.h"
#endif

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <errno.h>
#include <sys/param.h>

#include "stringprep.h"

#ifdef _LIBC
# define HAVE_ICONV 1
# define LOCALE_WORKS 1
# define ICONV_CONST
#endif

#ifdef HAVE_ICONV
# include <iconv.h>

# if LOCALE_WORKS
#  include <langinfo.h>
#  include <locale.h>
# endif

# ifdef _LIBC
#  define stringprep_locale_charset() nl_langinfo (CODESET)
# else
/**
 * stringprep_locale_charset:
 *
 * Find out current locale charset.  The function respect the CHARSET
 * environment variable, but typically uses nl_langinfo(CODESET) when
 * it is supported.  It fall back on "ASCII" if CHARSET isn't set and
 * nl_langinfo isn't supported or return anything.
 *
 * Note that this function return the application's locale's preferred
 * charset (or thread's locale's preffered charset, if your system
 * support thread-specific locales).  It does not return what the
 * system may be using.  Thus, if you receive data from external
 * sources you cannot in general use this function to guess what
 * charset it is encoded in.  Use stringprep_convert from the external
 * representation into the charset returned by this function, to have
 * data in the locale encoding.
 *
 * Return value: Return the character set used by the current locale.
 *   It will never return NULL, but use "ASCII" as a fallback.
 **/
const char *
stringprep_locale_charset (void)
{
  const char *charset = getenv ("CHARSET");	/* flawfinder: ignore */

  if (charset && *charset)
    return charset;

#  ifdef LOCALE_WORKS
  charset = nl_langinfo (CODESET);

  if (charset && *charset)
    return charset;
#  endif

  return "ASCII";
}
# endif

/**
 * stringprep_convert:
 * @str: input zero-terminated string.
 * @to_codeset: name of destination character set.
 * @from_codeset: name of origin character set, as used by @str.
 *
 * Convert the string from one character set to another using the
 * system's iconv() function.
 *
 * Return value: Returns newly allocated zero-terminated string which
 *   is @str transcoded into to_codeset.
 **/
char *
stringprep_convert (const char *str,
		    const char *to_codeset, const char *from_codeset)
{
  iconv_t cd;
  char *dest;
  char *outp;
  ICONV_CONST char *p;
  size_t inbytes_remaining;
  size_t outbytes_remaining;
  size_t err;
  size_t outbuf_size;
  int have_error = 0;

  if (strcmp (to_codeset, from_codeset) == 0)
    {
#if defined HAVE_STRDUP || defined _LIBC
      return strdup (str);
#else
      char *p;
      p = malloc (strlen (str) + 1);
      if (!p)
	return NULL;
      return strcpy (p, str);
#endif
    }

  cd = iconv_open (to_codeset, from_codeset);

  if (cd == (iconv_t) - 1)
    return NULL;

  p = (ICONV_CONST char *) str;

  inbytes_remaining = strlen (p);
  /* Guess the maximum length the output string can have.  */
  outbuf_size = (inbytes_remaining + 1) * MAX (7, MB_CUR_MAX);

  outp = dest = malloc (outbuf_size);
  if (dest == NULL)
    goto out;
  outbytes_remaining = outbuf_size - 1;	/* -1 for NUL */

again:

  err = iconv (cd, (ICONV_CONST char **) &p, &inbytes_remaining,
	       &outp, &outbytes_remaining);

  if (err == (size_t) - 1)
    {
      switch (errno)
	{
	case EINVAL:
	  /* Incomplete text, do not report an error */
	  break;

	case E2BIG:
	  {
	    size_t used = outp - dest;
	    char *newdest;

	    outbuf_size *= 2;
	    newdest = realloc (dest, outbuf_size);
	    if (newdest == NULL)
	      {
		have_error = 1;
		goto out;
	      }
	    dest = newdest;

	    outp = dest + used;
	    outbytes_remaining = outbuf_size - used - 1; /* -1 for NUL */

	    goto again;
	  }
	  break;

	case EILSEQ:
	  have_error = 1;
	  break;

	default:
	  have_error = 1;
	  break;
	}
    }

  *outp = '\0';

  if (*p != '\0')
    have_error = 1;

 out:
  iconv_close (cd);

  if (have_error)
    {
      free (dest);
      dest = NULL;
    }

  return dest;
}

#else /* HAVE_ICONV */

const char *
stringprep_locale_charset ()
{
  return "ASCII";
}

char *
stringprep_convert (const char *str,
		    const char *to_codeset, const char *from_codeset)
{
  char *p;
  fprintf (stderr, "libidn: warning: libiconv not installed, cannot "
	   "convert data to UTF-8\n");
  p = malloc (strlen (str) + 1);
  if (!p)
    return NULL;
  strcpy (p, str);
  return p;
}

#endif /* HAVE_ICONV */

/**
 * stringprep_locale_to_utf8:
 * @str: input zero terminated string.
 *
 * Convert string encoded in the locale's character set into UTF-8 by
 * using stringprep_convert().
 *
 * Return value: Returns newly allocated zero-terminated string which
 *   is @str transcoded into UTF-8.
 **/
char *
stringprep_locale_to_utf8 (const char *str)
{
  return stringprep_convert (str, "UTF-8", stringprep_locale_charset ());
}

/**
 * stringprep_utf8_to_locale:
 * @str: input zero terminated string.
 *
 * Convert string encoded in UTF-8 into the locale's character set by
 * using stringprep_convert().
 *
 * Return value: Returns newly allocated zero-terminated string which
 *   is @str transcoded into the locale's character set.
 **/
char *
stringprep_utf8_to_locale (const char *str)
{
  return stringprep_convert (str, stringprep_locale_charset (), "UTF-8");
}