X-Git-Url: http://sjero.net/git/?p=wget;a=blobdiff_plain;f=src%2Fhttp.c;h=d24db5fc38f3393ef6937c32e1ba03e3e6eba24b;hp=50f0c6439c776e50a4a75c25f8beb47de4cfcfc5;hb=9dadbf6fe9577a6a6b7e7bab4e4b782fc1a6f86c;hpb=37b7e547c31a85a429ceadaeb69ae62ab66855c8 diff --git a/src/http.c b/src/http.c index 50f0c643..d24db5fc 100644 --- a/src/http.c +++ b/src/http.c @@ -66,6 +66,10 @@ as that of the covered work. */ #include "test.h" #endif +#ifdef __VMS +# include "vms.h" +#endif /* def __VMS */ + extern char *version_string; /* Forward decls. */ @@ -1341,13 +1345,27 @@ free_hstat (struct http_stat *hs) && (c_isspace (line[sizeof (string_constant) - 1]) \ || !line[sizeof (string_constant) - 1])) +#ifdef __VMS #define SET_USER_AGENT(req) do { \ if (!opt.useragent) \ request_set_header (req, "User-Agent", \ - aprintf ("Wget/%s", version_string), rel_value); \ + aprintf ("Wget/%s (VMS %s %s)", \ + version_string, vms_arch(), vms_vers()), \ + rel_value); \ else if (*opt.useragent) \ request_set_header (req, "User-Agent", opt.useragent, rel_none); \ } while (0) +#else /* def __VMS */ +#define SET_USER_AGENT(req) do { \ + if (!opt.useragent) \ + request_set_header (req, "User-Agent", \ + aprintf ("Wget/%s (%s)", \ + version_string, OS_TYPE), \ + rel_value); \ + else if (*opt.useragent) \ + request_set_header (req, "User-Agent", opt.useragent, rel_none); \ +} while (0) +#endif /* def __VMS [else] */ /* The flags that allow clobbering the file (opening with "wb"). Defined here to avoid repetition later. #### This will require @@ -1366,7 +1384,8 @@ free_hstat (struct http_stat *hs) If PROXY is non-NULL, the connection will be made to the proxy server, and u->url will be requested. */ static uerr_t -gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy) +gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy, + struct iri *iri) { struct request *req; @@ -1743,7 +1762,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy) if (conn->scheme == SCHEME_HTTPS) { - if (!ssl_connect (sock) || !ssl_check_certificate (sock, u->host)) + if (!ssl_connect_wget (sock) || !ssl_check_certificate (sock, u->host)) { fd_close (sock); return CONSSLERR; @@ -1925,7 +1944,7 @@ gethttp (struct url *u, struct http_stat *hs, int *dt, struct url *proxy) hs->local_file = url_file_name (u); } } - + /* TODO: perform this check only once. */ if (!hs->existence_checked && file_exists_p (hs->local_file)) { @@ -1963,7 +1982,7 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); if (opt.timestamping && !hs->timestamp_checked) { size_t filename_len = strlen (hs->local_file); - char *filename_plus_orig_suffix = alloca (filename_len + sizeof (".orig")); + char *filename_plus_orig_suffix = alloca (filename_len + sizeof (ORIG_SFX)); bool local_dot_orig_file_exists = false; char *local_filename = NULL; struct_stat st; @@ -1988,7 +2007,7 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); --hniksic */ memcpy (filename_plus_orig_suffix, hs->local_file, filename_len); memcpy (filename_plus_orig_suffix + filename_len, - ".orig", sizeof (".orig")); + ORIG_SFX, sizeof (ORIG_SFX)); /* Try to stat() the .orig file. */ if (stat (filename_plus_orig_suffix, &st) == 0) @@ -1996,7 +2015,7 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); local_dot_orig_file_exists = true; local_filename = filename_plus_orig_suffix; } - } + } if (!local_dot_orig_file_exists) /* Couldn't stat() .orig, so try to stat() . */ @@ -2061,9 +2080,20 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); char *tmp = strchr (type, ';'); if (tmp) { + /* sXXXav: only needed if IRI support is enabled */ + char *tmp2 = tmp + 1; + while (tmp > type && c_isspace (tmp[-1])) --tmp; *tmp = '\0'; + + /* Try to get remote encoding if needed */ + if (opt.enable_iri && !opt.encoding_remote) + { + tmp = parse_charset (tmp2); + if (tmp) + set_content_encoding (iri, tmp); + } } } hs->newloc = resp_header_strdup (resp, "Location"); @@ -2145,10 +2175,10 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); else *dt &= ~TEXTCSS; - if (opt.html_extension) + if (opt.adjust_extension) { if (*dt & TEXTHTML) - /* -E / --html-extension / html_extension = on was specified, + /* -E / --adjust-extension / adjust_extension = on was specified, and this is a text/html file. If some case-insensitive variation on ".htm[l]" isn't already the file's suffix, tack on ".html". */ @@ -2258,6 +2288,16 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); return RETRFINISHED; } +/* 2005-06-17 SMS. + For VMS, define common fopen() optional arguments. +*/ +#ifdef __VMS +# define FOPEN_OPT_ARGS "fop=sqo", "acc", acc_cb, &open_id +# define FOPEN_BIN_FLAG 3 +#else /* def __VMS */ +# define FOPEN_BIN_FLAG 1 +#endif /* def __VMS [else] */ + /* Open the local file. */ if (!output_stream) { @@ -2265,9 +2305,27 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); if (opt.backups) rotate_backups (hs->local_file); if (hs->restval) - fp = fopen (hs->local_file, "ab"); + { +#ifdef __VMS + int open_id; + + open_id = 21; + fp = fopen (hs->local_file, "ab", FOPEN_OPT_ARGS); +#else /* def __VMS */ + fp = fopen (hs->local_file, "ab"); +#endif /* def __VMS [else] */ + } else if (ALLOW_CLOBBER) - fp = fopen (hs->local_file, "wb"); + { +#ifdef __VMS + int open_id; + + open_id = 22; + fp = fopen (hs->local_file, "wb", FOPEN_OPT_ARGS); +#else /* def __VMS */ + fp = fopen (hs->local_file, "wb"); +#endif /* def __VMS [else] */ + } else { fp = fopen_excl (hs->local_file, true); @@ -2348,7 +2406,7 @@ File %s already there; not retrieving.\n\n"), quote (hs->local_file)); retried, and retried, and retried, and... */ uerr_t http_loop (struct url *u, char **newloc, char **local_file, const char *referer, - int *dt, struct url *proxy) + int *dt, struct url *proxy, struct iri *iri) { int count; bool got_head = false; /* used for time-stamping and filename detection */ @@ -2359,17 +2417,17 @@ http_loop (struct url *u, char **newloc, char **local_file, const char *referer, uerr_t err, ret = TRYLIMEXC; time_t tmr = -1; /* remote time-stamp */ struct http_stat hstat; /* HTTP status */ - struct_stat st; + struct_stat st; bool send_head_first = true; char *file_name; /* Assert that no value for *LOCAL_FILE was passed. */ assert (local_file == NULL || *local_file == NULL); - + /* Set LOCAL_FILE parameter. */ if (local_file && opt.output_document) *local_file = HYPHENP (opt.output_document) ? NULL : xstrdup (opt.output_document); - + /* Reset NEWLOC parameter. */ *newloc = NULL; @@ -2406,7 +2464,7 @@ http_loop (struct url *u, char **newloc, char **local_file, const char *referer, retrieve the file. But if the output_document was given, then this test was already done and the file didn't exist. Hence the !opt.output_document */ logprintf (LOG_VERBOSE, _("\ -File %s already there; not retrieving.\n\n"), +File %s already there; not retrieving.\n\n"), quote (hstat.local_file)); /* If the file is there, we suppose it's retrieved OK. */ *dt |= RETROKF; @@ -2422,10 +2480,10 @@ File %s already there; not retrieving.\n\n"), /* Reset the counter. */ count = 0; - + /* Reset the document type. */ *dt = 0; - + /* Skip preliminary HEAD request if we're not in spider mode AND * if -O was given or HTTP Content-Disposition support is disabled. */ if (!opt.spider @@ -2435,7 +2493,7 @@ File %s already there; not retrieving.\n\n"), /* Send preliminary HEAD request if -N is given and we have an existing * destination file. */ file_name = url_file_name (u); - if (opt.timestamping + if (opt.timestamping && !opt.content_disposition && file_exists_p (file_name)) send_head_first = true; @@ -2447,10 +2505,10 @@ File %s already there; not retrieving.\n\n"), /* Increment the pass counter. */ ++count; sleep_between_retrievals (count); - + /* Get the current time string. */ tms = datetime_str (time (NULL)); - + if (opt.spider && !got_head) logprintf (LOG_VERBOSE, _("\ Spider mode enabled. Check if remote file exists.\n")); @@ -2459,20 +2517,20 @@ Spider mode enabled. Check if remote file exists.\n")); if (opt.verbose) { char *hurl = url_string (u, URL_AUTH_HIDE_PASSWD); - - if (count > 1) + + if (count > 1) { char tmp[256]; sprintf (tmp, _("(try:%2d)"), count); logprintf (LOG_NOTQUIET, "--%s-- %s %s\n", tms, tmp, hurl); } - else + else { logprintf (LOG_NOTQUIET, "--%s-- %s\n", tms, hurl); } - + #ifdef WINDOWS ws_changetitle (hurl); #endif @@ -2482,7 +2540,7 @@ Spider mode enabled. Check if remote file exists.\n")); /* Default document type is empty. However, if spider mode is on or time-stamping is employed, HEAD_ONLY commands is encoded within *dt. */ - if (send_head_first && !got_head) + if (send_head_first && !got_head) *dt |= HEAD_ONLY; else *dt &= ~HEAD_ONLY; @@ -2515,11 +2573,11 @@ Spider mode enabled. Check if remote file exists.\n")); *dt &= ~SEND_NOCACHE; /* Try fetching the document, or at least its head. */ - err = gethttp (u, &hstat, dt, proxy); + err = gethttp (u, &hstat, dt, proxy, iri); /* Time? */ tms = datetime_str (time (NULL)); - + /* Get the new location (with or without the redirection). */ if (hstat.newloc) *newloc = xstrdup (hstat.newloc); @@ -2558,7 +2616,7 @@ Spider mode enabled. Check if remote file exists.\n")); hstat.statcode); ret = WRONGCODE; } - else + else { ret = NEWLOCATION; } @@ -2574,7 +2632,7 @@ Spider mode enabled. Check if remote file exists.\n")); /* All possibilities should have been exhausted. */ abort (); } - + if (!(*dt & RETROKF)) { char *hurl = NULL; @@ -2593,11 +2651,13 @@ Spider mode enabled. Check if remote file exists.\n")); continue; } /* Maybe we should always keep track of broken links, not just in - * spider mode. */ - else if (opt.spider) + * spider mode. + * Don't log error if it was UTF-8 encoded because we will try + * once unencoded. */ + else if (opt.spider && !iri->utf8_encode) { /* #### Again: ugly ugly ugly! */ - if (!hurl) + if (!hurl) hurl = url_string (u, URL_AUTH_HIDE_PASSWD); nonexisting_url (hurl); logprintf (LOG_NOTQUIET, _("\ @@ -2606,7 +2666,7 @@ Remote file does not exist -- broken link!!!\n")); else { logprintf (LOG_NOTQUIET, _("%s ERROR %d: %s.\n"), - tms, hstat.statcode, + tms, hstat.statcode, quotearg_style (escape_quoting_style, hstat.error)); } logputs (LOG_VERBOSE, "\n"); @@ -2722,7 +2782,7 @@ Remote file exists.\n\n")); if (finished) { logprintf (LOG_NONVERBOSE, - _("%s URL:%s %2d %s\n"), + _("%s URL: %s %2d %s\n"), tms, u->url, hstat.statcode, hstat.message ? quotearg_style (escape_quoting_style, hstat.message) : ""); goto exit; @@ -2750,7 +2810,7 @@ Remote file exists.\n\n")); && hstat.remote_time && hstat.remote_time[0]) { newtmr = http_atotm (hstat.remote_time); - if (newtmr != -1) + if (newtmr != (time_t)-1) tmr = newtmr; } touch (fl, tmr);