/* File retrieval.
- 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.
#include <stdio.h>
#include <stdlib.h>
-#ifdef HAVE_UNISTD_H
-# include <unistd.h>
-#endif /* HAVE_UNISTD_H */
+#include <unistd.h>
#include <errno.h>
#include <string.h>
#include <assert.h>
+#include "exits.h"
#include "utils.h"
#include "retr.h"
#include "progress.h"
static int
write_data (FILE *out, const char *buf, int bufsize, wgint *skip,
- wgint *written, int flags)
+ wgint *written)
{
- static int cr_pending = 0; /* Found CR in ASCII FTP data. */
-
if (!out)
return 1;
if (*skip > bufsize)
return 1;
}
-/* Note: This code assumes that "\n" is the universal line ending
- character, as on UNIX and VMS. If this is not true, then here's
- where to change it.
-*/
-
-#if 1
-# define EOL_STRING "\n"
-#else /* 1 */
-# define EOL_STRING "\r\n"
-#endif /* 1 [else] */
-#define EOL_STRING_LEN (sizeof( EOL_STRING)- 1)
-
- if (flags & rb_ftp_ascii)
- {
- const char *bufend;
-
- /* ASCII transfer. Put out lines delimited by CRLF. */
- bufend = buf+ bufsize;
- while (buf < bufend)
- {
- /* If CR, put out any pending CR, then set CR-pending flag. */
- if (*buf == '\r')
- {
- if (cr_pending)
- {
- fwrite ("\r", 1, 1, out);
- *written += 1;
- }
- cr_pending = 1;
- buf++;
- continue;
- }
-
- if (cr_pending)
- {
- if (*buf == '\n')
- {
- /* Found FTP EOL (CRLF). Put out local EOL. */
- fwrite (EOL_STRING, 1, EOL_STRING_LEN, out);
- *written += EOL_STRING_LEN;
- }
- else
- {
- /* Normal character. Put out pending CR and it. */
- fwrite ("\r", 1, 1, out);
- fwrite (buf, 1, 1, out);
- *written += 2;
- }
- buf++;
- cr_pending = 0;
- }
- else
- {
- /* Normal character. Put it out. */
- fwrite (buf, 1, 1, out);
- *written += 1;
- buf++;
- }
- }
- }
- else
- {
- /* Image transfer. Put out buffer. */
- fwrite (buf, 1, bufsize, out);
- *written += bufsize;
- }
+ fwrite (buf, 1, bufsize, out);
+ *written += bufsize;
/* Immediately flush the downloaded data. This should not hinder
performance: fast downloads will arrive in large 16K chunks
wgint *qtyread, wgint *qtywritten, double *elapsed, int flags)
{
int ret = 0;
-
- static char dlbuf[16384];
- int dlbufsize = sizeof (dlbuf);
+#undef max
+#define max(a,b) ((a) > (b) ? (a) : (b))
+ int dlbufsize = max (BUFSIZ, 8 * 1024);
+ char *dlbuf = xmalloc (dlbufsize);
struct ptimer *timer = NULL;
double last_successful_read_tm = 0;
bool progress_interactive = false;
bool exact = !!(flags & rb_read_exactly);
+
+ /* Used only by HTTP/HTTPS chunked transfer encoding. */
+ bool chunked = flags & rb_chunked_transfer_encoding;
wgint skip = 0;
/* How much data we've read/written. */
wgint sum_read = 0;
wgint sum_written = 0;
+ wgint remaining_chunk_size = 0;
if (flags & rb_skip_startpos)
skip = startpos;
should be read. */
while (!exact || (sum_read < toread))
{
- int rdsize = exact ? MIN (toread - sum_read, dlbufsize) : dlbufsize;
+ int rdsize;
double tmout = opt.read_timeout;
+
+ if (chunked)
+ {
+ if (remaining_chunk_size == 0)
+ {
+ char *line = fd_read_line (fd);
+ char *endl;
+ if (line == NULL)
+ {
+ ret = -1;
+ break;
+ }
+
+ remaining_chunk_size = strtol (line, &endl, 16);
+ if (remaining_chunk_size == 0)
+ {
+ ret = 0;
+ if (fd_read_line (fd) == NULL)
+ ret = -1;
+ break;
+ }
+ }
+
+ rdsize = MIN (remaining_chunk_size, dlbufsize);
+ }
+ else
+ rdsize = exact ? MIN (toread - sum_read, dlbufsize) : dlbufsize;
+
if (progress_interactive)
{
/* For interactive progress gauges, always specify a ~1s
else if (ret <= 0)
break; /* EOF or read error */
- if (progress || opt.limit_rate)
+ if (progress || opt.limit_rate || elapsed)
{
ptimer_measure (timer);
if (ret > 0)
if (ret > 0)
{
sum_read += ret;
- if (!write_data (out, dlbuf, ret, &skip, &sum_written, flags))
+ if (!write_data (out, dlbuf, ret, &skip, &sum_written))
{
ret = -2;
goto out;
}
+ if (chunked)
+ {
+ remaining_chunk_size -= ret;
+ if (remaining_chunk_size == 0)
+ if (fd_read_line (fd) == NULL)
+ {
+ ret = -1;
+ break;
+ }
+ }
}
if (opt.limit_rate)
if (qtywritten)
*qtywritten += sum_written;
+ free (dlbuf);
+
return ret;
}
\f
uerr_t
retrieve_url (struct url * orig_parsed, const char *origurl, char **file,
char **newloc, const char *refurl, int *dt, bool recursive,
- struct iri *iri)
+ struct iri *iri, bool register_status)
{
uerr_t result;
char *url;
xfree (url);
xfree (error);
RESTORE_POST_DATA;
- return PROXERR;
+ result = PROXERR;
+ goto bail;
}
if (proxy_url->scheme != SCHEME_HTTP && proxy_url->scheme != u->scheme)
{
url_free (proxy_url);
xfree (url);
RESTORE_POST_DATA;
- return PROXERR;
+ result = PROXERR;
+ goto bail;
}
}
#endif
|| (proxy_url && proxy_url->scheme == SCHEME_HTTP))
{
- result = http_loop (u, &mynewloc, &local_file, refurl, dt, proxy_url, iri);
+ result = http_loop (u, orig_parsed, &mynewloc, &local_file, refurl, dt,
+ proxy_url, iri);
}
else if (u->scheme == SCHEME_FTP)
{
if (redirection_count)
oldrec = glob = false;
- result = ftp_loop (u, dt, proxy_url, recursive, glob);
+ result = ftp_loop (u, &local_file, dt, proxy_url, recursive, glob);
recursive = oldrec;
/* There is a possibility of having HTTP being redirected to
proxy_url = NULL;
}
- location_changed = (result == NEWLOCATION);
+ location_changed = (result == NEWLOCATION || result == NEWLOCATION_KEEP_POST);
if (location_changed)
{
char *construced_newloc;
xfree (mynewloc);
xfree (error);
RESTORE_POST_DATA;
- return result;
+ goto bail;
}
/* Now mynewloc will become newloc_parsed->url, because if the
xfree (url);
xfree (mynewloc);
RESTORE_POST_DATA;
- return WRONGCODE;
+ result = WRONGCODE;
+ goto bail;
}
xfree (url);
}
u = newloc_parsed;
- /* If we're being redirected from POST, we don't want to POST
+ /* If we're being redirected from POST, and we received a
+ redirect code different than 307, we don't want to POST
again. Many requests answer POST with a redirection to an
index page; that redirection is clearly a GET. We "suspend"
POST data for the duration of the redirections, and restore
- it when we're done. */
- if (!post_data_suspended)
+ it when we're done.
+
+ RFC2616 HTTP/1.1 introduces code 307 Temporary Redirect
+ specifically to preserve the method of the request.
+ */
+ if (result != NEWLOCATION_KEEP_POST && !post_data_suspended)
SUSPEND_POST_DATA;
goto redirected;
DEBUGP (("[Couldn't fallback to non-utf8 for %s\n", quote (url)));
}
- if (local_file && *dt & RETROKF)
+ if (local_file && u && *dt & RETROKF)
{
register_download (u->url, local_file);
- if (redirection_count && 0 != strcmp (origurl, u->url))
+
+ if (!opt.spider && redirection_count && 0 != strcmp (origurl, u->url))
register_redirection (origurl, u->url);
+
if (*dt & TEXTHTML)
register_html (u->url, local_file);
- if (*dt & RETROKF)
- {
- register_download (u->url, local_file);
- if (redirection_count && 0 != strcmp (origurl, u->url))
- register_redirection (origurl, u->url);
- if (*dt & TEXTHTML)
- register_html (u->url, local_file);
- if (*dt & TEXTCSS)
- register_css (u->url, local_file);
- }
+
+ if (*dt & TEXTCSS)
+ register_css (u->url, local_file);
}
if (file)
RESTORE_POST_DATA;
+bail:
+ if (register_status)
+ inform_exit_status (result);
return result;
}
struct urlpos *url_list, *cur_url;
struct iri *iri = iri_new();
- char *input_file = NULL;
+ char *input_file, *url_file = NULL;
const char *url = file;
status = RETROK; /* Suppose everything is OK. */
set_uri_encoding (iri, opt.locale, true);
set_content_encoding (iri, opt.locale);
- if (url_has_scheme (url))
+ if (url_valid_scheme (url))
{
int dt,url_err;
uerr_t status;
- struct url * url_parsed = url_parse(url, &url_err, iri, true);
-
+ struct url *url_parsed = url_parse (url, &url_err, iri, true);
if (!url_parsed)
{
char *error = url_error (url, url_err);
if (!opt.base_href)
opt.base_href = xstrdup (url);
- status = retrieve_url (url_parsed, url, &input_file, NULL, NULL, &dt,
- false, iri);
- if (status != RETROK)
+ status = retrieve_url (url_parsed, url, &url_file, NULL, NULL, &dt,
+ false, iri, true);
+ url_free (url_parsed);
+
+ if (!url_file || (status != RETROK))
return status;
if (dt & TEXTHTML)
iri->utf8_encode = opt.enable_iri;
xfree_null (iri->orig_url);
iri->orig_url = NULL;
+
+ input_file = url_file;
}
else
input_file = (char *) file;
url_list = (html ? get_urls_html (input_file, NULL, NULL, iri)
: get_urls_file (input_file));
+ xfree_null (url_file);
+
for (cur_url = url_list; cur_url; cur_url = cur_url->next, ++*count)
{
char *filename = NULL, *new_file = NULL;
break;
}
- /* Need to reparse the url, since it didn't have iri information. */
- if (opt.enable_iri)
- parsed_url = url_parse (cur_url->url->url, NULL, tmpiri, true);
+ parsed_url = url_parse (cur_url->url->url, NULL, tmpiri, true);
if ((opt.recursive || opt.page_requisites)
&& (cur_url->url->scheme != SCHEME_FTP || getproxy (cur_url->url)))
else
status = retrieve_url (parsed_url ? parsed_url : cur_url->url,
cur_url->url->url, &filename,
- &new_file, NULL, &dt, opt.recursive, tmpiri);
+ &new_file, NULL, &dt, opt.recursive, tmpiri,
+ true);
if (parsed_url)
url_free (parsed_url);
else
*file = default_file;
}
+
+/* Return true for an input file's own URL, false otherwise. */
+bool
+input_file_url (const char *input_file)
+{
+ static bool first = true;
+
+ if (input_file
+ && url_has_scheme (input_file)
+ && first)
+ {
+ first = false;
+ return true;
+ }
+ else
+ return false;
+}
projects / wget / blobdiff