X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Firi.c;h=08cfde40fb04d0d66a460c69ebb030d0d6d2c347;hp=44a262b8e25ba872153cc3724cb4aa34aa610940;hb=2f6aa1d7417df1dfc58597777686fbd77179b9fd;hpb=3ae04f5fe4ae2025c177168be4a2c396627c2ffb diff --git a/src/iri.c b/src/iri.c index 44a262b8..08cfde40 100644 --- a/src/iri.c +++ b/src/iri.c @@ -1,5 +1,5 @@ /* IRI related functions. - Copyright (C) 2008 Free Software Foundation, Inc. + Copyright (C) 2008, 2009, 2010, 2011 Free Software Foundation, Inc. This file is part of GNU Wget. @@ -31,7 +31,6 @@ as that of the covered work. */ #include #include -#include #include #include #include @@ -39,16 +38,12 @@ as that of the covered work. */ #include #include "utils.h" -#include "iri.h" /* RFC3987 section 3.1 mandates STD3 ASCII RULES */ #define IDNA_FLAGS IDNA_USE_STD3_ASCII_RULES /* Note: locale encoding is kept in options struct (opt.locale) */ -static iconv_t locale2utf8; - -static bool open_locale_to_utf8 (void); static bool do_conversion (iconv_t cd, char *in, size_t inlen, char **out); @@ -105,7 +100,7 @@ check_encoding_name (char *encoding) { if (!c_isascii (*s) || c_isspace (*s)) { - logprintf (LOG_VERBOSE, "Encoding %s isn't valid\n", quote (encoding)); + logprintf (LOG_VERBOSE, _("Encoding %s isn't valid\n"), quote (encoding)); return false; } @@ -115,54 +110,40 @@ check_encoding_name (char *encoding) return true; } -/* Try opening an iconv_t descriptor for conversion from locale to UTF-8 */ -static bool -open_locale_to_utf8 (void) -{ - if (locale2utf8) - return true; - - /* sXXXav : That shouldn't happen, just in case */ - if (!opt.locale) - { - logprintf (LOG_VERBOSE, "open_locale_to_utf8: locale is unset\n"); - opt.locale = find_locale (); - } - - if (!opt.locale) - return false; - - locale2utf8 = iconv_open ("UTF-8", opt.locale); - if (locale2utf8 != (iconv_t)(-1)) - return true; - - logprintf (LOG_VERBOSE, "Conversion from %s to %s isn't supported\n", - quote (opt.locale), quote ("UTF-8")); - locale2utf8 = NULL; - return false; -} - /* Try converting string str from locale to UTF-8. Return a new string on success, or str on error or if conversion isn't needed. */ const char * locale_to_utf8 (const char *str) { + iconv_t l2u; char *new; - if (!strcasecmp (opt.locale, "utf-8")) - return str; + /* That shouldn't happen, just in case */ + if (!opt.locale) + { + logprintf (LOG_VERBOSE, _("locale_to_utf8: locale is unset\n")); + opt.locale = find_locale (); + } - if (!open_locale_to_utf8 ()) + if (!opt.locale || !strcasecmp (opt.locale, "utf-8")) return str; - if (do_conversion (locale2utf8, (char *) str, strlen ((char *) str), &new)) + l2u = iconv_open ("UTF-8", opt.locale); + if (l2u != (iconv_t)(-1)) + { + logprintf (LOG_VERBOSE, _("Conversion from %s to %s isn't supported\n"), + quote (opt.locale), quote ("UTF-8")); + return str; + } + + if (do_conversion (l2u, (char *) str, strlen ((char *) str), &new)) return (const char *) new; return str; } /* Do the conversion according to the passed conversion descriptor cd. *out - will containes the transcoded string on success. *out content is + will contain the transcoded string on success. *out content is unspecified otherwise. */ static bool do_conversion (iconv_t cd, char *in, size_t inlen, char **out) @@ -191,7 +172,7 @@ do_conversion (iconv_t cd, char *in, size_t inlen, char **out) { if (!invalid) logprintf (LOG_VERBOSE, - "Incomplete or invalide multibyte sequence encountered\n"); + _("Incomplete or invalid multibyte sequence encountered\n")); invalid++; **out = *in; @@ -216,7 +197,7 @@ do_conversion (iconv_t cd, char *in, size_t inlen, char **out) } else /* Weird, we got an unspecified error */ { - logprintf (LOG_VERBOSE, "Unhandled errno %d\n", errno); + logprintf (LOG_VERBOSE, _("Unhandled errno %d\n"), errno); break; } } @@ -236,11 +217,7 @@ idn_encode (struct iri *i, char *host) if (!i->utf8_encode) { if (!remote_to_utf8 (i, (const char *) host, (const char **) &new)) - { - /* Nothing to encode or an error occured */ - return NULL; - } - + return NULL; /* Nothing to encode or an error occured */ host = new; } @@ -249,7 +226,7 @@ idn_encode (struct iri *i, char *host) if (ret != IDNA_SUCCESS) { /* sXXXav : free new when needed ! */ - logprintf (LOG_VERBOSE, "idn_encode failed (%d): %s\n", ret, + logprintf (LOG_VERBOSE, _("idn_encode failed (%d): %s\n"), ret, quote (idna_strerror (ret))); return NULL; } @@ -268,7 +245,7 @@ idn_decode (char *host) ret = idna_to_unicode_8zlz (host, &new, IDNA_FLAGS); if (ret != IDNA_SUCCESS) { - logprintf (LOG_VERBOSE, "idn_decode failed (%d): %s\n", ret, + logprintf (LOG_VERBOSE, _("idn_decode failed (%d): %s\n"), ret, quote (idna_strerror (ret))); return NULL; } @@ -281,18 +258,13 @@ idn_decode (char *host) bool remote_to_utf8 (struct iri *i, const char *str, const char **new) { - char *r; iconv_t cd; bool ret = false; - if (opt.encoding_remote) - r = opt.encoding_remote; - else if (i->uri_encoding) - r = i->uri_encoding; - else + if (!i->uri_encoding) return false; - cd = iconv_open ("UTF-8", r); + cd = iconv_open ("UTF-8", i->uri_encoding); if (cd == (iconv_t)(-1)) return false; @@ -311,32 +283,50 @@ remote_to_utf8 (struct iri *i, const char *str, const char **new) return ret; } +/* Allocate a new iri structure and return a pointer to it. */ struct iri * iri_new (void) { - struct iri *i = xmalloc (sizeof (struct iri)); + struct iri *i = xmalloc (sizeof *i); i->uri_encoding = opt.encoding_remote ? xstrdup (opt.encoding_remote) : NULL; i->content_encoding = NULL; + i->orig_url = NULL; i->utf8_encode = opt.enable_iri; + return i; } +struct iri *iri_dup (const struct iri *src) +{ + struct iri *i = xmalloc (sizeof *i); + i->uri_encoding = src->uri_encoding ? xstrdup (src->uri_encoding) : NULL; + i->content_encoding = (src->content_encoding ? + xstrdup (src->content_encoding) : NULL); + i->orig_url = src->orig_url ? xstrdup (src->orig_url) : NULL; + i->utf8_encode = src->utf8_encode; + return i; +} + +/* Completely free an iri structure. */ void iri_free (struct iri *i) { xfree_null (i->uri_encoding); xfree_null (i->content_encoding); + xfree_null (i->orig_url); xfree (i); } +/* Set uri_encoding of struct iri i. If a remote encoding was specified, use + it unless force is true. */ void -set_uri_encoding (struct iri *i, char *charset) +set_uri_encoding (struct iri *i, char *charset, bool force) { - DEBUGP (("[IRI uri = `%s'\n", quote (charset))); - if (opt.encoding_remote) + DEBUGP (("URI encoding = %s\n", charset ? quote (charset) : "None")); + if (!force && opt.encoding_remote) return; if (i->uri_encoding) { - if (!strcasecmp (i->uri_encoding, charset)) + if (charset && !strcasecmp (i->uri_encoding, charset)) return; xfree (i->uri_encoding); } @@ -344,15 +334,16 @@ set_uri_encoding (struct iri *i, char *charset) i->uri_encoding = charset ? xstrdup (charset) : NULL; } +/* Set content_encoding of struct iri i. */ void set_content_encoding (struct iri *i, char *charset) { - DEBUGP (("[IRI content = %s\n", quote (charset))); + DEBUGP (("URI content encoding = %s\n", charset ? quote (charset) : "None")); if (opt.encoding_remote) return; if (i->content_encoding) { - if (!strcasecmp (i->content_encoding, charset)) + if (charset && !strcasecmp (i->content_encoding, charset)) return; xfree (i->content_encoding); }