1 /* IRI related functions.
2 Copyright (C) 2008, 2009 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. */
36 #include <stringprep.h>
42 /* RFC3987 section 3.1 mandates STD3 ASCII RULES */
43 #define IDNA_FLAGS IDNA_USE_STD3_ASCII_RULES
45 /* Note: locale encoding is kept in options struct (opt.locale) */
47 static bool do_conversion (iconv_t cd, char *in, size_t inlen, char **out);
50 /* Given a string containing "charset=XXX", return the encoding if found,
53 parse_charset (char *str)
60 str = strcasestr (str, "charset=");
67 /* sXXXav: which chars should be banned ??? */
68 while (*charset && !c_isspace (*charset))
71 /* sXXXav: could strdupdelim return NULL ? */
72 charset = strdupdelim (str, charset);
74 /* Do a minimum check on the charset value */
75 if (!check_encoding_name (charset))
81 /*logprintf (LOG_VERBOSE, "parse_charset: %s\n", quote (charset));*/
86 /* Find the locale used, or fall back on a default value */
90 return (char *) stringprep_locale_charset ();
93 /* Basic check of an encoding name. */
95 check_encoding_name (char *encoding)
101 if (!c_isascii (*s) || c_isspace (*s))
103 logprintf (LOG_VERBOSE, _("Encoding %s isn't valid\n"), quote (encoding));
113 /* Try opening an iconv_t descriptor for conversion from locale to UTF-8 */
115 open_locale_to_utf8 (void)
120 /* Try converting string str from locale to UTF-8. Return a new string
121 on success, or str on error or if conversion isn't needed. */
123 locale_to_utf8 (const char *str)
128 /* That shouldn't happen, just in case */
131 logprintf (LOG_VERBOSE, _("locale_to_utf8: locale is unset\n"));
132 opt.locale = find_locale ();
135 if (!opt.locale || !strcasecmp (opt.locale, "utf-8"))
138 l2u = iconv_open ("UTF-8", opt.locale);
139 if (l2u != (iconv_t)(-1))
141 logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"),
142 quote (opt.locale), quote ("UTF-8"));
146 if (do_conversion (l2u, (char *) str, strlen ((char *) str), &new))
147 return (const char *) new;
152 /* Do the conversion according to the passed conversion descriptor cd. *out
153 will contain the transcoded string on success. *out content is
154 unspecified otherwise. */
156 do_conversion (iconv_t cd, char *in, size_t inlen, char **out)
158 /* sXXXav : hummm hard to guess... */
159 size_t len, done, outlen = inlen * 2;
160 int invalid = 0, tooshort = 0;
163 s = xmalloc (outlen + 1);
170 if (iconv (cd, &in, &inlen, out, &outlen) != (size_t)(-1))
173 *(s + len - outlen - done) = '\0';
177 /* Incomplete or invalid multibyte sequence */
178 if (errno == EINVAL || errno == EILSEQ)
181 logprintf (LOG_VERBOSE,
182 _("Incomplete or invalid multibyte sequence encountered\n"));
191 else if (errno == E2BIG) /* Output buffer full */
197 outlen = done + inlen * 2;
198 new = xmalloc (outlen + 1);
199 memcpy (new, s, done);
205 else /* Weird, we got an unspecified error */
207 logprintf (LOG_VERBOSE, _("Unhandled errno %d\n"), errno);
215 /* Try to "ASCII encode" UTF-8 host. Return the new domain on success or NULL
218 idn_encode (struct iri *i, char *host)
223 /* Encode to UTF-8 if not done */
226 if (!remote_to_utf8 (i, (const char *) host, (const char **) &new))
227 return NULL; /* Nothing to encode or an error occured */
231 /* toASCII UTF-8 NULL terminated string */
232 ret = idna_to_ascii_8z (host, &new, IDNA_FLAGS);
233 if (ret != IDNA_SUCCESS)
235 /* sXXXav : free new when needed ! */
236 logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), ret,
237 quote (idna_strerror (ret)));
244 /* Try to decode an "ASCII encoded" host. Return the new domain in the locale
245 on success or NULL on error. */
247 idn_decode (char *host)
252 ret = idna_to_unicode_8zlz (host, &new, IDNA_FLAGS);
253 if (ret != IDNA_SUCCESS)
255 logprintf (LOG_VERBOSE, _("idn_decode failed (%d): %s\n"), ret,
256 quote (idna_strerror (ret)));
263 /* Try to transcode string str from remote encoding to UTF-8. On success, *new
264 contains the transcoded string. *new content is unspecified otherwise. */
266 remote_to_utf8 (struct iri *i, const char *str, const char **new)
271 if (!i->uri_encoding)
274 cd = iconv_open ("UTF-8", i->uri_encoding);
275 if (cd == (iconv_t)(-1))
278 if (do_conversion (cd, (char *) str, strlen ((char *) str), (char **) new))
283 /* Test if something was converted */
284 if (!strcmp (str, *new))
286 xfree ((char *) *new);
293 /* Allocate a new iri structure and return a pointer to it. */
297 struct iri *i = xmalloc (sizeof *i);
298 i->uri_encoding = opt.encoding_remote ? xstrdup (opt.encoding_remote) : NULL;
299 i->content_encoding = NULL;
301 i->utf8_encode = opt.enable_iri;
305 struct iri *iri_dup (const struct iri *src)
307 struct iri *i = xmalloc (sizeof *i);
308 i->uri_encoding = src->uri_encoding ? xstrdup (src->uri_encoding) : NULL;
309 i->content_encoding = (src->content_encoding ?
310 xstrdup (src->content_encoding) : NULL);
311 i->orig_url = src->orig_url ? xstrdup (src->orig_url) : NULL;
312 i->utf8_encode = src->utf8_encode;
316 /* Completely free an iri structure. */
318 iri_free (struct iri *i)
320 xfree_null (i->uri_encoding);
321 xfree_null (i->content_encoding);
322 xfree_null (i->orig_url);
326 /* Set uri_encoding of struct iri i. If a remote encoding was specified, use
327 it unless force is true. */
329 set_uri_encoding (struct iri *i, char *charset, bool force)
331 DEBUGP (("URI encoding = %s\n", charset ? quote (charset) : "None"));
332 if (!force && opt.encoding_remote)
336 if (charset && !strcasecmp (i->uri_encoding, charset))
338 xfree (i->uri_encoding);
341 i->uri_encoding = charset ? xstrdup (charset) : NULL;
344 /* Set content_encoding of struct iri i. */
346 set_content_encoding (struct iri *i, char *charset)
348 DEBUGP (("URI content encoding = %s\n", charset ? quote (charset) : "None"));
349 if (opt.encoding_remote)
351 if (i->content_encoding)
353 if (charset && !strcasecmp (i->content_encoding, charset))
355 xfree (i->content_encoding);
358 i->content_encoding = charset ? xstrdup (charset) : NULL;