/* 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>
/* Write data in BUF to OUT. However, if *SKIP is non-zero, skip that
amount of data and decrease SKIP. Increment *TOTAL by the amount
- of data written. */
+ of data written. If OUT2 is not NULL, also write BUF to OUT2.
+ In case of error writing to OUT, -1 is returned. In case of error
+ writing to OUT2, -2 is returned. In case of any other error,
+ 1 is returned. */
static int
-write_data (FILE *out, const char *buf, int bufsize, wgint *skip,
- wgint *written)
+write_data (FILE *out, FILE *out2, const char *buf, int bufsize,
+ wgint *skip, wgint *written)
{
- if (!out)
+ if (out == NULL && out2 == NULL)
return 1;
if (*skip > bufsize)
{
return 1;
}
- fwrite (buf, 1, bufsize, out);
+ if (out != NULL)
+ fwrite (buf, 1, bufsize, out);
+ if (out2 != NULL)
+ fwrite (buf, 1, bufsize, out2);
*written += bufsize;
/* Immediately flush the downloaded data. This should not hinder
actual justification. (Also, why 16K? Anyone test other values?)
*/
#ifndef __VMS
- fflush (out);
+ if (out != NULL)
+ fflush (out);
+ if (out2 != NULL)
+ fflush (out2);
#endif /* ndef __VMS */
- return !ferror (out);
+ if (out != NULL && ferror (out))
+ return -1;
+ else if (out2 != NULL && ferror (out2))
+ return -2;
+ else
+ return 0;
}
/* Read the contents of file descriptor FD until it the connection
the amount of data written to disk. The time it took to download
the data is stored to ELAPSED.
+ If OUT2 is non-NULL, the contents is also written to OUT2.
+ OUT2 will get an exact copy of the response: if this is a chunked
+ response, everything -- including the chunk headers -- is written
+ to OUT2. (OUT will only get the unchunked response.)
+
The function exits and returns the amount of data read. In case of
error while reading data, -1 is returned. In case of error while
- writing data, -2 is returned. */
+ writing data to OUT, -2 is returned. In case of error while writing
+ data to OUT2, -3 is returned. */
int
fd_read_body (int fd, FILE *out, wgint toread, wgint startpos,
- wgint *qtyread, wgint *qtywritten, double *elapsed, int flags)
+ wgint *qtyread, wgint *qtywritten, double *elapsed, int flags,
+ FILE *out2)
{
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;
+ }
+ else if (out2 != NULL)
+ fwrite (line, 1, strlen (line), out2);
+
+ remaining_chunk_size = strtol (line, &endl, 16);
+ xfree (line);
+
+ if (remaining_chunk_size == 0)
+ {
+ ret = 0;
+ line = fd_read_line (fd);
+ if (line == NULL)
+ ret = -1;
+ else
+ {
+ if (out2 != NULL)
+ fwrite (line, 1, strlen (line), out2);
+ xfree (line);
+ }
+ 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
if (ret > 0)
{
sum_read += ret;
- if (!write_data (out, dlbuf, ret, &skip, &sum_written))
+ int write_res = write_data (out, out2, dlbuf, ret, &skip, &sum_written);
+ if (write_res != 0)
{
- ret = -2;
+ ret = (write_res == -3) ? -3 : -2;
goto out;
}
+ if (chunked)
+ {
+ remaining_chunk_size -= ret;
+ if (remaining_chunk_size == 0)
+ {
+ char *line = fd_read_line (fd);
+ if (line == NULL)
+ {
+ ret = -1;
+ break;
+ }
+ else
+ {
+ if (out2 != NULL)
+ fwrite (line, 1, strlen (line), out2);
+ xfree (line);
+ }
+ }
+ }
}
if (opt.limit_rate)
if (qtywritten)
*qtywritten += sum_written;
+ free (dlbuf);
+
return ret;
}
\f
{
static char res[20];
static const char *rate_names[] = {"B/s", "KB/s", "MB/s", "GB/s" };
+ static const char *rate_names_bits[] = {"b/s", "Kb/s", "Mb/s", "Gb/s" };
int units;
double dlrate = calc_rate (bytes, secs, &units);
e.g. "1022", "247", "12.5", "2.38". */
sprintf (res, "%.*f %s",
dlrate >= 99.95 ? 0 : dlrate >= 9.995 ? 1 : 2,
- dlrate, rate_names[units]);
+ dlrate, !opt.report_bps ? rate_names[units]: rate_names_bits[units]);
return res;
}
calc_rate (wgint bytes, double secs, int *units)
{
double dlrate;
+ double bibyte = 1000.0;
+
+ if (!opt.report_bps)
+ bibyte = 1024.0;
+
assert (secs >= 0);
assert (bytes >= 0);
0 and the timer's resolution, assume half the resolution. */
secs = ptimer_resolution () / 2.0;
- dlrate = bytes / secs;
- if (dlrate < 1024.0)
+ dlrate = convert_to_bits (bytes) / secs;
+ if (dlrate < bibyte)
*units = 0;
- else if (dlrate < 1024.0 * 1024.0)
- *units = 1, dlrate /= 1024.0;
- else if (dlrate < 1024.0 * 1024.0 * 1024.0)
- *units = 2, dlrate /= (1024.0 * 1024.0);
+ else if (dlrate < (bibyte * bibyte))
+ *units = 1, dlrate /= bibyte;
+ else if (dlrate < (bibyte * bibyte * bibyte))
+ *units = 2, dlrate /= (bibyte * bibyte);
+
else
/* Maybe someone will need this, one day. */
- *units = 3, dlrate /= (1024.0 * 1024.0 * 1024.0);
+ *units = 3, dlrate /= (bibyte * bibyte * bibyte);
return dlrate;
}
#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);
- }
+ register_html (local_file);
+
+ if (*dt & TEXTCSS)
+ register_css (local_file);
}
if (file)
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);
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
*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;
+}