/* File retrieval.
Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
- 2005, 2006, 2007, 2008, 2009 Free Software Foundation, Inc.
+ 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>
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
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
#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)
{
proxy_url = NULL;
}
- location_changed = (result == NEWLOCATION);
+ location_changed = (result == NEWLOCATION || result == NEWLOCATION_KEEP_POST);
if (location_changed)
{
char *construced_newloc;
}
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)
{
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);
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)))
projects / wget / blobdiff