1 /* IRI related functions.
2 Copyright (C) 2008 Free Software Foundation, Inc.
4 This file is part of GNU Wget.
6 GNU Wget is free software; you can redistribute it and/or modify
7 it under the terms of the GNU General Public License as published by
8 the Free Software Foundation; either version 3 of the License, or (at
9 your option) any later version.
11 GNU Wget is distributed in the hope that it will be useful,
12 but WITHOUT ANY WARRANTY; without even the implied warranty of
13 MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 GNU General Public License for more details.
16 You should have received a copy of the GNU General Public License
17 along with Wget. If not, see <http://www.gnu.org/licenses/>.
19 Additional permission under GNU GPL version 3 section 7
21 If you modify this program, or any covered work, by linking or
22 combining it with the OpenSSL project's OpenSSL library (or a
23 modified version of that library), containing parts covered by the
24 terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
25 grants you additional permission to convey the resulting work.
26 Corresponding Source for a non-source form of such a combination
27 shall include the source code for the parts of OpenSSL used as well
28 as that of the covered work. */
37 #include <stringprep.h>
43 /* RFC3987 section 3.1 mandates STD3 ASCII RULES */
44 #define IDNA_FLAGS IDNA_USE_STD3_ASCII_RULES
46 /* Note: locale encoding is kept in options struct (opt.locale) */
48 static bool do_conversion (iconv_t cd, char *in, size_t inlen, char **out);
51 /* Given a string containing "charset=XXX", return the encoding if found,
54 parse_charset (char *str)
61 str = strcasestr (str, "charset=");
68 /* sXXXav: which chars should be banned ??? */
69 while (*charset && !c_isspace (*charset))
72 /* sXXXav: could strdupdelim return NULL ? */
73 charset = strdupdelim (str, charset);
75 /* Do a minimum check on the charset value */
76 if (!check_encoding_name (charset))
82 /*logprintf (LOG_VERBOSE, "parse_charset: %s\n", quote (charset));*/
87 /* Find the locale used, or fall back on a default value */
91 return (char *) stringprep_locale_charset ();
94 /* Basic check of an encoding name. */
96 check_encoding_name (char *encoding)
102 if (!c_isascii (*s) || c_isspace (*s))
104 logprintf (LOG_VERBOSE, _("Encoding %s isn't valid\n"), quote (encoding));
114 /* Try opening an iconv_t descriptor for conversion from locale to UTF-8 */
116 open_locale_to_utf8 (void)
121 /* Try converting string str from locale to UTF-8. Return a new string
122 on success, or str on error or if conversion isn't needed. */
124 locale_to_utf8 (const char *str)
129 /* That shouldn't happen, just in case */
132 logprintf (LOG_VERBOSE, _("locale_to_utf8: locale is unset\n"));
133 opt.locale = find_locale ();
136 if (!opt.locale || !strcasecmp (opt.locale, "utf-8"))
139 l2u = iconv_open ("UTF-8", opt.locale);
140 if (l2u != (iconv_t)(-1))
142 logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"),
143 quote (opt.locale), quote ("UTF-8"));
147 if (do_conversion (l2u, (char *) str, strlen ((char *) str), &new))
148 return (const char *) new;
153 /* Do the conversion according to the passed conversion descriptor cd. *out
154 will contain the transcoded string on success. *out content is
155 unspecified otherwise. */
157 do_conversion (iconv_t cd, char *in, size_t inlen, char **out)
159 /* sXXXav : hummm hard to guess... */
160 size_t len, done, outlen = inlen * 2;
161 int invalid = 0, tooshort = 0;
164 s = xmalloc (outlen + 1);
171 if (iconv (cd, &in, &inlen, out, &outlen) != (size_t)(-1))
174 *(s + len - outlen - done) = '\0';
178 /* Incomplete or invalid multibyte sequence */
179 if (errno == EINVAL || errno == EILSEQ)
182 logprintf (LOG_VERBOSE,
183 _("Incomplete or invalid multibyte sequence encountered\n"));
192 else if (errno == E2BIG) /* Output buffer full */
198 outlen = done + inlen * 2;
199 new = xmalloc (outlen + 1);
200 memcpy (new, s, done);
206 else /* Weird, we got an unspecified error */
208 logprintf (LOG_VERBOSE, _("Unhandled errno %d\n"), errno);
216 /* Try to "ASCII encode" UTF-8 host. Return the new domain on success or NULL
219 idn_encode (struct iri *i, char *host)
224 /* Encode to UTF-8 if not done */
227 if (!remote_to_utf8 (i, (const char *) host, (const char **) &new))
228 return NULL; /* Nothing to encode or an error occured */
232 /* toASCII UTF-8 NULL terminated string */
233 ret = idna_to_ascii_8z (host, &new, IDNA_FLAGS);
234 if (ret != IDNA_SUCCESS)
236 /* sXXXav : free new when needed ! */
237 logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), ret,
238 quote (idna_strerror (ret)));
245 /* Try to decode an "ASCII encoded" host. Return the new domain in the locale
246 on success or NULL on error. */
248 idn_decode (char *host)
253 ret = idna_to_unicode_8zlz (host, &new, IDNA_FLAGS);
254 if (ret != IDNA_SUCCESS)
256 logprintf (LOG_VERBOSE, _("idn_decode failed (%d): %s\n"), ret,
257 quote (idna_strerror (ret)));
264 /* Try to transcode string str from remote encoding to UTF-8. On success, *new
265 contains the transcoded string. *new content is unspecified otherwise. */
267 remote_to_utf8 (struct iri *i, const char *str, const char **new)
272 if (!i->uri_encoding)
275 cd = iconv_open ("UTF-8", i->uri_encoding);
276 if (cd == (iconv_t)(-1))
279 if (do_conversion (cd, (char *) str, strlen ((char *) str), (char **) new))
284 /* Test if something was converted */
285 if (!strcmp (str, *new))
287 xfree ((char *) *new);
294 /* Allocate a new iri structure and return a pointer to it. */
298 struct iri *i = xmalloc (sizeof *i);
299 i->uri_encoding = opt.encoding_remote ? xstrdup (opt.encoding_remote) : NULL;
300 i->content_encoding = NULL;
302 i->utf8_encode = opt.enable_iri;
306 struct iri *iri_dup (const struct iri *src)
308 struct iri *i = xmalloc (sizeof *i);
309 i->uri_encoding = src->uri_encoding ? xstrdup (src->uri_encoding) : NULL;
310 i->content_encoding = (src->content_encoding ?
311 xstrdup (src->content_encoding) : NULL);
312 i->orig_url = src->orig_url ? xstrdup (src->orig_url) : NULL;
313 i->utf8_encode = src->utf8_encode;
317 /* Completely free an iri structure. */
319 iri_free (struct iri *i)
321 xfree_null (i->uri_encoding);
322 xfree_null (i->content_encoding);
323 xfree_null (i->orig_url);
327 /* Set uri_encoding of struct iri i. If a remote encoding was specified, use
328 it unless force is true. */
330 set_uri_encoding (struct iri *i, char *charset, bool force)
332 DEBUGP (("URI encoding = %s\n", charset ? quote (charset) : "None"));
333 if (!force && opt.encoding_remote)
337 if (charset && !strcasecmp (i->uri_encoding, charset))
339 xfree (i->uri_encoding);
342 i->uri_encoding = charset ? xstrdup (charset) : NULL;
345 /* Set content_encoding of struct iri i. */
347 set_content_encoding (struct iri *i, char *charset)
349 DEBUGP (("URI content encoding = %s\n", charset ? quote (charset) : "None"));
350 if (opt.encoding_remote)
352 if (i->content_encoding)
354 if (charset && !strcasecmp (i->content_encoding, charset))
356 xfree (i->content_encoding);
359 i->content_encoding = charset ? xstrdup (charset) : NULL;