#include <stdio.h>
#include <stdlib.h>
-#include <sys/types.h>
#ifdef HAVE_UNISTD_H
# include <unistd.h>
#endif /* HAVE_UNISTD_H */
#include <errno.h>
-#ifdef HAVE_STRING_H
-# include <string.h>
-#else
-# include <strings.h>
-#endif /* HAVE_STRING_H */
+#include <string.h>
#include <assert.h>
#include "wget.h"
#include "url.h"
#include "recur.h"
#include "ftp.h"
+#include "http.h"
#include "host.h"
#include "connect.h"
#include "hash.h"
#include "convert.h"
#include "ptimer.h"
-#ifndef errno
-extern int errno;
-#endif
-
/* Total size of downloaded files. Used to enforce quota. */
-LARGE_INT total_downloaded_bytes;
+SUM_SIZE_INT total_downloaded_bytes;
+
+/* Total download time in milliseconds. */
+double total_download_time;
/* If non-NULL, the stream to which output should be written. This
stream is initialized when `-O' is used. */
/* Whether output_document is a regular file we can manipulate,
i.e. not `-' or a device file. */
-int output_stream_regular;
+bool output_stream_regular;
\f
static struct {
wgint chunk_bytes;
{
limit_data.chunk_bytes = 0;
limit_data.chunk_start = 0;
+ limit_data.sleep_adjust = 0;
}
/* Limit the bandwidth by pausing the download for an amount of time.
desired and the actual sleep, and adjust the next sleep by
that amount. */
limit_data.sleep_adjust = slp - (t1 - t0);
+ /* If sleep_adjust is very large, it's likely due to suspension
+ and not clock inaccuracy. Don't enforce those. */
+ if (limit_data.sleep_adjust > 500)
+ limit_data.sleep_adjust = 500;
+ else if (limit_data.sleep_adjust < -500)
+ limit_data.sleep_adjust = -500;
}
limit_data.chunk_bytes = 0;
continually update the display. When true, smaller timeout
values are used so that the gauge can update the display when
data arrives slowly. */
- int progress_interactive = 0;
+ bool progress_interactive = false;
- int exact = flags & rb_read_exactly;
+ bool exact = !!(flags & rb_read_exactly);
wgint skip = 0;
/* How much data we've read/written. */
if (!write_data (out, dlbuf, ret, &skip, &sum_written))
{
ret = -2;
- goto out_;
+ goto out;
}
}
if (ret < -1)
ret = -1;
- out_:
+ out:
if (progress)
progress_finish (progress, ptimer_read (timer));
return ret;
}
\f
-/* Read a hunk of data from FD, up until a terminator. The terminator
- is whatever the TERMINATOR function determines it to be; for
- example, it can be a line of data, or the head of an HTTP response.
- The function returns the data read allocated with malloc.
-
- In case of error, NULL is returned. In case of EOF and no data
- read, NULL is returned and errno set to 0. In case of EOF with
- data having been read, the data is returned, but it will
- (obviously) not contain the terminator.
+/* Read a hunk of data from FD, up until a terminator. The hunk is
+ limited by whatever the TERMINATOR callback chooses as its
+ terminator. For example, if terminator stops at newline, the hunk
+ will consist of a line of data; if terminator stops at two
+ newlines, it can be used to read the head of an HTTP response.
+ Upon determining the boundary, the function returns the data (up to
+ the terminator) in malloc-allocated storage.
+
+ In case of read error, NULL is returned. In case of EOF and no
+ data read, NULL is returned and errno set to 0. In case of having
+ read some data, but encountering EOF before seeing the terminator,
+ the data that has been read is returned, but it will (obviously)
+ not contain the terminator.
+
+ The TERMINATOR function is called with three arguments: the
+ beginning of the data read so far, the beginning of the current
+ block of peeked-at data, and the length of the current block.
+ Depending on its needs, the function is free to choose whether to
+ analyze all data or just the newly arrived data. If TERMINATOR
+ returns NULL, it means that the terminator has not been seen.
+ Otherwise it should return a pointer to the charactre immediately
+ following the terminator.
The idea is to be able to read a line of input, or otherwise a hunk
of text, such as the head of an HTTP request, without crossing the
boundary, so that the next call to fd_read etc. reads the data
after the hunk. To achieve that, this function does the following:
- 1. Peek at available data.
+ 1. Peek at incoming data.
2. Determine whether the peeked data, along with the previously
read data, includes the terminator.
/* First, peek at the available data. */
- pklen = fd_peek (fd, hunk + tail, bufsize - 1 - tail, -1.0);
+ pklen = fd_peek (fd, hunk + tail, bufsize - 1 - tail, -1);
if (pklen < 0)
{
xfree (hunk);
return NULL;
}
- end = terminator (hunk, tail, pklen);
+ end = terminator (hunk, hunk + tail, pklen);
if (end)
{
/* The data contains the terminator: we'll drain the data up
to the end of the terminator. */
remain = end - (hunk + tail);
+ assert (remain >= 0);
if (remain == 0)
{
/* No more data needs to be read. */
how much data we'll get. (Some TCP stacks are notorious for
read returning less data than the previous MSG_PEEK.) */
- rdlen = fd_read (fd, hunk + tail, remain, 0.0);
+ rdlen = fd_read (fd, hunk + tail, remain, 0);
if (rdlen < 0)
{
xfree_null (hunk);
}
static const char *
-line_terminator (const char *hunk, int oldlen, int peeklen)
+line_terminator (const char *start, const char *peeked, int peeklen)
{
- const char *p = memchr (hunk + oldlen, '\n', peeklen);
+ const char *p = memchr (peeked, '\n', peeklen);
if (p)
- /* p+1 because we want the line to include '\n' */
+ /* p+1 because the line must include '\n' */
return p + 1;
return NULL;
}
return fd_read_hunk (fd, line_terminator, 128, FD_READ_LINE_MAX);
}
\f
-/* Return a printed representation of the download rate, as
- appropriate for the speed. If PAD is non-zero, strings will be
- padded to the width of 7 characters (xxxx.xx). */
-char *
-retr_rate (wgint bytes, double msecs, int pad)
+/* Return a printed representation of the download rate, along with
+ the units appropriate for the download speed. */
+
+const char *
+retr_rate (wgint bytes, double msecs)
{
static char res[20];
static const char *rate_names[] = {"B/s", "KB/s", "MB/s", "GB/s" };
- int units = 0;
+ int units;
double dlrate = calc_rate (bytes, msecs, &units);
- sprintf (res, pad ? "%7.2f %s" : "%.2f %s", dlrate, rate_names[units]);
+ /* Use more digits for smaller numbers (regardless of unit used),
+ 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]);
return res;
}
#define MAX_REDIRECTIONS 20
#define SUSPEND_POST_DATA do { \
- post_data_suspended = 1; \
+ post_data_suspended = true; \
saved_post_data = opt.post_data; \
saved_post_file_name = opt.post_file_name; \
opt.post_data = NULL; \
{ \
opt.post_data = saved_post_data; \
opt.post_file_name = saved_post_file_name; \
- post_data_suspended = 0; \
+ post_data_suspended = false; \
} \
} while (0)
-static char *getproxy PARAMS ((struct url *));
+static char *getproxy (struct url *);
/* Retrieve the given URL. Decides which loop to call -- HTTP, FTP,
FTP, proxy, etc. */
{
uerr_t result;
char *url;
- int location_changed, dummy;
+ bool location_changed;
+ int dummy;
char *mynewloc, *proxy;
struct url *u, *proxy_url;
int up_error_code; /* url parse error code */
char *local_file;
int redirection_count = 0;
- int post_data_suspended = 0;
+ bool post_data_suspended = false;
char *saved_post_data = NULL;
char *saved_post_file_name = NULL;
}
else if (u->scheme == SCHEME_FTP)
{
- /* If this is a redirection, we must not allow recursive FTP
- retrieval, so we save recursion to oldrec, and restore it
- later. */
- int oldrec = opt.recursive;
+ /* If this is a redirection, temporarily turn off opt.ftp_glob
+ and opt.recursive, both being undesirable when following
+ redirects. */
+ bool oldrec = opt.recursive, oldglob = opt.ftp_glob;
if (redirection_count)
- opt.recursive = 0;
+ opt.recursive = opt.ftp_glob = false;
+
result = ftp_loop (u, dt, proxy_url);
opt.recursive = oldrec;
+ opt.ftp_glob = oldglob;
/* There is a possibility of having HTTP being redirected to
FTP. In these cases we must decide whether the text is HTML
return result;
}
-/* Find the URLs in the file and call retrieve_url() for each of
- them. If HTML is non-zero, treat the file as HTML, and construct
- the URLs accordingly.
+/* Find the URLs in the file and call retrieve_url() for each of them.
+ If HTML is true, treat the file as HTML, and construct the URLs
+ accordingly.
If opt.recursive is set, call retrieve_tree() for each file. */
uerr_t
-retrieve_from_file (const char *file, int html, int *count)
+retrieve_from_file (const char *file, bool html, int *count)
{
uerr_t status;
struct urlpos *url_list, *cur_url;
void
sleep_between_retrievals (int count)
{
- static int first_retrieval = 1;
+ static bool first_retrieval = true;
if (first_retrieval)
{
/* Don't sleep before the very first retrieval. */
- first_retrieval = 0;
+ first_retrieval = false;
return;
}
/* If opt.waitretry is specified and this is a retry, wait for
COUNT-1 number of seconds, or for opt.waitretry seconds. */
if (count <= opt.waitretry)
- xsleep (count - 1.0);
+ xsleep (count - 1);
else
xsleep (opt.waitretry);
}
rename(fname, to);
}
-static int no_proxy_match PARAMS ((const char *, const char **));
+static bool no_proxy_match (const char *, const char **);
/* Return the URL of the proxy appropriate for url U. */
}
/* Should a host be accessed through proxy, concerning no_proxy? */
-static int
+static bool
no_proxy_match (const char *host, const char **no_proxy)
{
if (!no_proxy)
- return 1;
+ return true;
else
return !sufmatch (no_proxy, host);
}