/* Conversion of links to local files.
- Copyright (C) 2003-2006 Free Software Foundation, Inc.
+ Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011
+ Free Software Foundation, Inc.
This file is part of GNU Wget.
GNU Wget is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 2 of the License, or
+the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
GNU Wget is distributed in the hope that it will be useful,
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
-along with Wget; if not, write to the Free Software Foundation, Inc.,
-51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+along with Wget. If not, see <http://www.gnu.org/licenses/>.
-In addition, as a special exception, the Free Software Foundation
-gives permission to link the code of its release of Wget with the
-OpenSSL project's "OpenSSL" library (or with modified versions of it
-that use the same license as the "OpenSSL" library), and distribute
-the linked executables. You must obey the GNU General Public License
-in all respects for all of the code used other than "OpenSSL". If you
-modify this file, you may extend this exception to your version of the
-file, but you are not obligated to do so. If you do not wish to do
-so, delete this exception statement from your version. */
+Additional permission under GNU GPL version 3 section 7
-#include <config.h>
+If you modify this program, or any covered work, by linking or
+combining it with the OpenSSL project's OpenSSL library (or a
+modified version of that library), containing parts covered by the
+terms of the OpenSSL or SSLeay licenses, the Free Software Foundation
+grants you additional permission to convey the resulting work.
+Corresponding Source for a non-source form of such a combination
+shall include the source code for the parts of OpenSSL used as well
+as that of the covered work. */
+
+#include "wget.h"
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
-#ifdef HAVE_UNISTD_H
-# include <unistd.h>
-#endif /* HAVE_UNISTD_H */
+#include <unistd.h>
#include <errno.h>
#include <assert.h>
-
-#include "wget.h"
#include "convert.h"
#include "url.h"
#include "recur.h"
#include "res.h"
#include "html-url.h"
#include "css-url.h"
+#include "iri.h"
static struct hash_table *dl_file_url_map;
struct hash_table *dl_url_file_map;
static void convert_links (const char *, struct urlpos *);
-void
+static void
convert_links_in_hashtable (struct hash_table *downloaded_set,
int is_css,
int *file_count)
/* Parse the file... */
urls = is_css ? get_urls_css_file (file, url) :
- get_urls_html (file, url, NULL);
+ get_urls_html (file, url, NULL, NULL);
/* We don't respect meta_disallow_follow here because, even if
the file is not followed, we might still want to convert the
for (cur_url = urls; cur_url; cur_url = cur_url->next)
{
char *local_name;
- struct url *u = cur_url->url;
+ struct url *u;
+ struct iri *pi;
if (cur_url->link_base_p)
{
/* We decide the direction of conversion according to whether
a URL was downloaded. Downloaded URLs will be converted
ABS2REL, whereas non-downloaded will be converted REL2ABS. */
+
+ pi = iri_new ();
+ set_uri_encoding (pi, opt.locale, true);
+
+ u = url_parse (cur_url->url->url, NULL, pi, true);
+ if (!u)
+ continue;
+
local_name = hash_table_get (dl_url_file_map, u->url);
/* Decide on the conversion type. */
cur_url->local_name = NULL;
DEBUGP (("will convert url %s to complete\n", u->url));
}
+
+ url_free (u);
+ iri_free (pi);
}
/* Convert the links in the file. */
convert_links_in_hashtable (downloaded_css_set, 1, &file_count);
secs = ptimer_measure (timer);
- ptimer_destroy (timer);
logprintf (LOG_VERBOSE, _("Converted %d files in %s seconds.\n"),
file_count, print_decimal (secs));
+
+ ptimer_destroy (timer);
}
static void write_backup_file (const char *, downloaded_file_t);
static const char *replace_attr (const char *, int, FILE *, const char *);
static const char *replace_attr_refresh_hack (const char *, int, FILE *,
const char *, int);
-static char *local_quote_string (const char *);
+static char *local_quote_string (const char *, bool);
static char *construct_relative (const char *, const char *);
/* Change the links in one file. LINKS is a list of links in the
}
}
- fm = read_file (file);
+ fm = wget_read_file (file);
if (!fm)
{
logprintf (LOG_NOTQUIET, _("Cannot convert links in %s: %s\n"),
zeroes from the mmaped region. */
if (unlink (file) < 0 && errno != ENOENT)
{
- logprintf (LOG_NOTQUIET, _("Unable to delete `%s': %s\n"),
- file, strerror (errno));
- read_file_free (fm);
+ logprintf (LOG_NOTQUIET, _("Unable to delete %s: %s\n"),
+ quote (file), strerror (errno));
+ wget_read_file_free (fm);
return;
}
/* Now open the file for writing. */
{
logprintf (LOG_NOTQUIET, _("Cannot convert links in %s: %s\n"),
file, strerror (errno));
- read_file_free (fm);
+ wget_read_file_free (fm);
return;
}
/* Convert absolute URL to relative. */
{
char *newname = construct_relative (file, link->local_name);
- char *quoted_newname = local_quote_string (newname);
+ char *quoted_newname = local_quote_string (newname,
+ link->link_css_p);
if (link->link_css_p)
p = replace_plain (p, link->size, fp, quoted_newname);
char *quoted_newlink = html_quote_string (newlink);
if (link->link_css_p)
- p = replace_plain (p, link->size, fp, quoted_newlink);
+ p = replace_plain (p, link->size, fp, newlink);
else if (!link->link_refresh_p)
p = replace_attr (p, link->size, fp, quoted_newlink);
else
if (p - fm->content < fm->length)
fwrite (p, 1, fm->length - (p - fm->content), fp);
fclose (fp);
- read_file_free (fm);
+ wget_read_file_free (fm);
logprintf (LOG_VERBOSE, "%d-%d\n", to_file_count, to_url_count);
}
/* Rather than just writing over the original .html file with the
converted version, save the former to *.orig. Note we only do
this for files we've _successfully_ downloaded, so we don't
- clobber .orig files sitting around from previous invocations. */
+ clobber .orig files sitting around from previous invocations.
+ On VMS, use "_orig" instead of ".orig". See "wget.h". */
/* Construct the backup filename as the original name plus ".orig". */
size_t filename_len = strlen (file);
else /* downloaded_file_return == FILE_DOWNLOADED_NORMALLY */
{
/* Append ".orig" to the name. */
- filename_plus_orig_suffix = alloca (filename_len + sizeof (".orig"));
+ filename_plus_orig_suffix = alloca (filename_len + sizeof (ORIG_SFX));
strcpy (filename_plus_orig_suffix, file);
- strcpy (filename_plus_orig_suffix + filename_len, ".orig");
+ strcpy (filename_plus_orig_suffix + filename_len, ORIG_SFX);
}
if (!converted_files)
We quote ? as %3F to avoid passing part of the file name as the
parameter when browsing the converted file through HTTP. However,
- it is safe to do this only when `--html-extension' is turned on.
+ it is safe to do this only when `--adjust-extension' is turned on.
This is because converting "index.html?foo=bar" to
"index.html%3Ffoo=bar" would break local browsing, as the latter
isn't even recognized as an HTML file! However, converting
"index.html?foo=bar.html" to "index.html%3Ffoo=bar.html" should be
safe for both local and HTTP-served browsing.
- We always quote "#" as "%23" and "%" as "%25" because those
- characters have special meanings in URLs. */
+ We always quote "#" as "%23", "%" as "%25" and ";" as "%3B"
+ because those characters have special meanings in URLs. */
static char *
-local_quote_string (const char *file)
+local_quote_string (const char *file, bool no_html_quote)
{
const char *from;
char *newname, *to;
- char *any = strpbrk (file, "?#%");
+ char *any = strpbrk (file, "?#%;");
if (!any)
- return html_quote_string (file);
+ return no_html_quote ? strdup (file) : html_quote_string (file);
/* Allocate space assuming the worst-case scenario, each character
having to be quoted. */
*to++ = '2';
*to++ = '3';
break;
+ case ';':
+ *to++ = '%';
+ *to++ = '3';
+ *to++ = 'B';
+ break;
case '?':
- if (opt.html_extension)
+ if (opt.adjust_extension)
{
*to++ = '%';
*to++ = '3';
}
*to = '\0';
- return html_quote_string (newname);
+ return no_html_quote ? strdup (newname) : html_quote_string (newname);
}
\f
/* Book-keeping code for dl_file_url_map, dl_url_file_map,
/* Register that FILE is an HTML file that has been downloaded. */
void
-register_html (const char *url, const char *file)
+register_html (const char *file)
{
if (!downloaded_html_set)
downloaded_html_set = make_string_hash_table (0);
/* Register that FILE is a CSS file that has been downloaded. */
void
-register_css (const char *url, const char *file)
+register_css (const char *file)
{
if (!downloaded_css_set)
downloaded_css_set = make_string_hash_table (0);
However, our hash tables only accept pointers for keys and values.
So when we need a pointer, we use the address of a
downloaded_file_t variable of static storage. */
-
+
static downloaded_file_t *
downloaded_mode_to_ptr (downloaded_file_t mode)
{