/* 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 Free Software Foundation, Inc.
This file is part of GNU Wget.
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)
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;
if (!opt.base_href)
opt.base_href = xstrdup (url);
- status = retrieve_url (url_parsed, url, &input_file, NULL, NULL, &dt,
+ status = retrieve_url (url_parsed, url, &url_file, NULL, NULL, &dt,
false, iri, true);
url_free (url_parsed);
- if (!input_file || (status != RETROK))
+ 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;
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;
+}