X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Furl.c;h=2593d09ed82e877ce4f8d0a3f934280c418d19ce;hp=c937d05695e03ede8d38dc79dd2bcb01632427d9;hb=2f6aa1d7417df1dfc58597777686fbd77179b9fd;hpb=cbd54b549a49465d4545c136d8061f6ef3889a30 diff --git a/src/url.c b/src/url.c index c937d056..2593d09e 100644 --- a/src/url.c +++ b/src/url.c @@ -1,6 +1,7 @@ /* URL handling. - Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, - 2004, 2005, 2006, 2007, 2008 Free Software Foundation, Inc. + Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004, + 2005, 2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation, + Inc. This file is part of GNU Wget. @@ -33,9 +34,7 @@ as that of the covered work. */ #include #include #include -#ifdef HAVE_UNISTD_H -# include -#endif +#include #include #include @@ -43,6 +42,10 @@ as that of the covered work. */ #include "url.h" #include "host.h" /* for is_valid_ipv6_address */ +#ifdef __VMS +#include "vms.h" +#endif /* def __VMS */ + #ifdef TESTING #include "test.h" #endif @@ -252,6 +255,15 @@ url_escape (const char *s) return url_escape_1 (s, urlchr_unsafe, false); } +/* URL-escape the unsafe and reserved characters (see urlchr_table) in + a given string, returning a freshly allocated string. */ + +char * +url_escape_unsafe_and_reserved (const char *s) +{ + return url_escape_1 (s, urlchr_unsafe|urlchr_reserved, false); +} + /* URL-escape the unsafe characters (see urlchr_table) in a given string. If no characters are unsafe, S is returned. */ @@ -450,6 +462,13 @@ url_has_scheme (const char *url) return *p == ':'; } +bool +url_valid_scheme (const char *url) +{ + enum url_scheme scheme = url_scheme (url); + return scheme != SCHEME_INVALID; +} + int scheme_default_port (enum url_scheme scheme) { @@ -611,7 +630,7 @@ init_seps (enum url_scheme scheme) *p++ = '?'; if (flags & scm_has_fragment) *p++ = '#'; - *p++ = '\0'; + *p = '\0'; return seps; } @@ -619,18 +638,20 @@ static const char *parse_errors[] = { #define PE_NO_ERROR 0 N_("No error"), #define PE_UNSUPPORTED_SCHEME 1 - N_("Unsupported scheme %s"), -#define PE_INVALID_HOST_NAME 2 + N_("Unsupported scheme %s"), /* support for format token only here */ +#define PE_MISSING_SCHEME 2 + N_("Scheme missing"), +#define PE_INVALID_HOST_NAME 3 N_("Invalid host name"), -#define PE_BAD_PORT_NUMBER 3 +#define PE_BAD_PORT_NUMBER 4 N_("Bad port number"), -#define PE_INVALID_USER_NAME 4 +#define PE_INVALID_USER_NAME 5 N_("Invalid user name"), -#define PE_UNTERMINATED_IPV6_ADDRESS 5 +#define PE_UNTERMINATED_IPV6_ADDRESS 6 N_("Unterminated IPv6 numeric address"), -#define PE_IPV6_NOT_SUPPORTED 6 +#define PE_IPV6_NOT_SUPPORTED 7 N_("IPv6 addresses not supported"), -#define PE_INVALID_IPV6_ADDRESS 7 +#define PE_INVALID_IPV6_ADDRESS 8 N_("Invalid IPv6 numeric address") }; @@ -640,7 +661,7 @@ static const char *parse_errors[] = { error, and if ERROR is not NULL, also set *ERROR to the appropriate error code. */ struct url * -url_parse (const char *url, int *error, struct iri *iri) +url_parse (const char *url, int *error, struct iri *iri, bool percent_encode) { struct url *u; const char *p; @@ -659,26 +680,36 @@ url_parse (const char *url, int *error, struct iri *iri) int port; char *user = NULL, *passwd = NULL; - char *url_encoded = NULL, *new_url = NULL; + const char *url_encoded = NULL; + char *new_url = NULL; int error_code; scheme = url_scheme (url); if (scheme == SCHEME_INVALID) { - error_code = PE_UNSUPPORTED_SCHEME; + if (url_has_scheme (url)) + error_code = PE_UNSUPPORTED_SCHEME; + else + error_code = PE_MISSING_SCHEME; goto error; } if (iri && iri->utf8_encode) { - url_unescape ((char *) url); - iri->utf8_encode = remote_to_utf8 (iri, url, (const char **) &new_url); + iri->utf8_encode = remote_to_utf8 (iri, iri->orig_url ? iri->orig_url : url, (const char **) &new_url); if (!iri->utf8_encode) new_url = NULL; + else + iri->orig_url = xstrdup (url); } - url_encoded = reencode_escapes (new_url ? new_url : url); + /* XXX XXX Could that change introduce (security) bugs ??? XXX XXX*/ + if (percent_encode) + url_encoded = reencode_escapes (new_url ? new_url : url); + else + url_encoded = new_url ? new_url : url; + p = url_encoded; if (new_url && url_encoded != new_url) @@ -889,7 +920,7 @@ url_parse (const char *url, int *error, struct iri *iri) if (url_encoded == url) u->url = xstrdup (url); else - u->url = url_encoded; + u->url = (char *) url_encoded; } return u; @@ -897,7 +928,7 @@ url_parse (const char *url, int *error, struct iri *iri) error: /* Cleanup in case of error: */ if (url_encoded && url_encoded != url) - xfree (url_encoded); + xfree ((char *) url_encoded); /* Transmit the error code to the caller, if the caller wants to know. */ @@ -923,9 +954,9 @@ url_error (const char *url, int error_code) if ((p = strchr (scheme, ':'))) *p = '\0'; if (!strcasecmp (scheme, "https")) - asprintf (&error, _("HTTPS support not compiled in")); + error = aprintf (_("HTTPS support not compiled in")); else - asprintf (&error, _(parse_errors[error_code]), quote (scheme)); + error = aprintf (_(parse_errors[error_code]), quote (scheme)); xfree (scheme); return error; @@ -1266,7 +1297,9 @@ enum { filechr_control = 4 /* a control character, e.g. 0-31 */ }; -#define FILE_CHAR_TEST(c, mask) (filechr_table[(unsigned char)(c)] & (mask)) +#define FILE_CHAR_TEST(c, mask) \ + ((opt.restrict_files_nonascii && !c_isascii ((unsigned char)(c))) || \ + (filechr_table[(unsigned char)(c)] & (mask))) /* Shorthands for the table: */ #define U filechr_not_unix @@ -1405,7 +1438,7 @@ append_uri_pathel (const char *b, const char *e, bool escaped, } assert (q - TAIL (dest) == outlen); } - + /* Perform inline case transformation if required. */ if (opt.restrict_files_case == restrict_lowercase || opt.restrict_files_case == restrict_uppercase) @@ -1419,7 +1452,7 @@ append_uri_pathel (const char *b, const char *e, bool escaped, *q = c_toupper (*q); } } - + TAIL_INCR (dest, outlen); } @@ -1465,7 +1498,7 @@ append_dir_structure (const struct url *u, struct growable *dest) possible. Does not create directories on the file system. */ char * -url_file_name (const struct url *u) +url_file_name (const struct url *u, char *replaced_filename) { struct growable fnres; /* stands for "file name result" */ @@ -1480,7 +1513,7 @@ url_file_name (const struct url *u) /* If an alternative index file was defined, change index_filename */ if (opt.default_page) index_filename = opt.default_page; - + /* Start with the directory prefix, if specified. */ if (opt.dir_prefix) @@ -1520,18 +1553,29 @@ url_file_name (const struct url *u) append_dir_structure (u, &fnres); } - /* Add the file name. */ - if (fnres.tail) - append_char ('/', &fnres); - u_file = *u->file ? u->file : index_filename; - append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres); - - /* Append "?query" to the file name. */ - u_query = u->query && *u->query ? u->query : NULL; - if (u_query) + if (!replaced_filename) { - append_char (FN_QUERY_SEP, &fnres); - append_uri_pathel (u_query, u_query + strlen (u_query), true, &fnres); + /* Add the file name. */ + if (fnres.tail) + append_char ('/', &fnres); + u_file = *u->file ? u->file : index_filename; + append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres); + + /* Append "?query" to the file name. */ + u_query = u->query && *u->query ? u->query : NULL; + if (u_query) + { + append_char (FN_QUERY_SEP, &fnres); + append_uri_pathel (u_query, u_query + strlen (u_query), + true, &fnres); + } + } + else + { + if (fnres.tail) + append_char ('/', &fnres); + u_file = replaced_filename; + append_uri_pathel (u_file, u_file + strlen (u_file), false, &fnres); } /* Zero-terminate the file name. */ @@ -1550,11 +1594,30 @@ url_file_name (const struct url *u) if ((opt.noclobber || opt.always_rest || opt.timestamping || opt.dirstruct) && !(file_exists_p (fname) && !file_non_directory_p (fname))) - return fname; + { + unique = fname; + } + else + { + unique = unique_name (fname, true); + if (unique != fname) + xfree (fname); + } + +/* On VMS, alter the name as required. */ +#ifdef __VMS + { + char *unique2; + + unique2 = ods_conform( unique); + if (unique2 != unique) + { + xfree (unique); + unique = unique2; + } + } +#endif /* def __VMS */ - unique = unique_name (fname, true); - if (unique != fname) - xfree (fname); return unique; } @@ -1973,7 +2036,7 @@ url_string (const struct url *url, enum url_auth_mode auth_mode) } /* Return true if scheme a is similar to scheme b. - + Schemes are similar if they are equal. If SSL is supported, schemes are also similar if one is http (SCHEME_HTTP) and the other is https (SCHEME_HTTPS). */ @@ -1992,12 +2055,12 @@ schemes_are_similar_p (enum url_scheme a, enum url_scheme b) static int getchar_from_escaped_string (const char *str, char *c) -{ +{ const char *p = str; assert (str && *str); assert (c); - + if (p[0] == '%') { if (!c_isxdigit(p[1]) || !c_isxdigit(p[2])) @@ -2047,7 +2110,7 @@ are_urls_equal (const char *u1, const char *u2) p += pp; q += qq; } - + return (*p == 0 && *q == 0 ? true : false); } @@ -2156,19 +2219,19 @@ test_append_uri_pathel() } test_array[] = { { "http://www.yoyodyne.com/path/", "somepage.html", false, "http://www.yoyodyne.com/path/somepage.html" }, }; - - for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i) + + for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i) { struct growable dest; const char *p = test_array[i].input; - + memset (&dest, 0, sizeof (dest)); - + append_string (test_array[i].original_url, &dest); append_uri_pathel (p, p + strlen(p), test_array[i].escaped, &dest); append_char ('\0', &dest); - mu_assert ("test_append_uri_pathel: wrong result", + mu_assert ("test_append_uri_pathel: wrong result", strcmp (dest.base, test_array[i].expected_result) == 0); } @@ -2191,10 +2254,10 @@ test_are_urls_equal() { "http://www.adomain.com/longer-path/", "http://www.adomain.com/path/", false }, { "http://www.adomain.com/path%2f", "http://www.adomain.com/path/", false }, }; - - for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i) + + for (i = 0; i < sizeof(test_array)/sizeof(test_array[0]); ++i) { - mu_assert ("test_are_urls_equal: wrong result", + mu_assert ("test_are_urls_equal: wrong result", are_urls_equal (test_array[i].url1, test_array[i].url2) == test_array[i].expected_result); }