Basic IDN/IRI support

[wget] / src / html-url.c

diff --git a/src/html-url.c b/src/html-url.c
index 3ab7f7fe02127410bf8f3781874cf74fc701e203..0d580f9aaf74b3df8032756fc0ac929b541ea540 100644 (file)
--- a/src/html-url.c
+++ b/src/html-url.c
@@ -1,6 +1,6 @@
 /* Collect URLs from HTML source.
    Copyright (C) 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006,
-   2007 Free Software Foundation, Inc.
+   2007, 2008 Free Software Foundation, Inc.
 
 This file is part of GNU Wget.
 
@@ -17,15 +17,16 @@ GNU General Public License for more details.
 You should have received a copy of the GNU General Public License
 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
+
+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"
 
@@ -41,6 +42,7 @@ so, delete this exception statement from your version.  */
 #include "hash.h"
 #include "convert.h"
 #include "recur.h"              /* declaration of get_urls_html */
+#include "iri.h"
 
 struct map_context;
 
@@ -184,7 +186,7 @@ init_interesting (void)
      matches the user's preferences as specified through --ignore-tags
      and --follow-tags.  */
 
-  int i;
+  size_t i;
   interesting_tags = make_nocase_string_hash_table (countof (known_tags));
 
   /* First, add all the tags we know hot to handle, mapped to their
@@ -272,6 +274,7 @@ append_url (const char *link_uri,
   struct urlpos *newel;
   const char *base = ctx->base ? ctx->base : ctx->parent_base;
   struct url *url;
+  bool utf8_encode = false;
 
   if (!base)
     {
@@ -290,7 +293,7 @@ append_url (const char *link_uri,
           return NULL;
         }
 
-      url = url_parse (link_uri, NULL);
+      url = url_parse (link_uri, NULL, &utf8_encode);
       if (!url)
         {
           DEBUGP (("%s: link \"%s\" doesn't parse.\n",
@@ -309,7 +312,7 @@ append_url (const char *link_uri,
       DEBUGP (("%s: merge(\"%s\", \"%s\") -> %s\n",
                ctx->document_file, base, link_uri, complete_uri));
 
-      url = url_parse (complete_uri, NULL);
+      url = url_parse (complete_uri, NULL, &utf8_encode);
       if (!url)
         {
           DEBUGP (("%s: merged link \"%s\" doesn't parse.\n",
@@ -354,7 +357,8 @@ append_url (const char *link_uri,
 static void
 tag_find_urls (int tagid, struct taginfo *tag, struct map_context *ctx)
 {
-  int i, attrind;
+  size_t i;
+  int attrind;
   int first = -1;
 
   for (i = 0; i < countof (tag_url_attributes); i++)
@@ -381,7 +385,7 @@ tag_find_urls (int tagid, struct taginfo *tag, struct map_context *ctx)
       /* Find whether TAG/ATTRIND is a combination that contains a
          URL. */
       char *link = tag->attrs[attrind].value;
-      const int size = countof (tag_url_attributes);
+      const size_t size = countof (tag_url_attributes);
 
       /* If you're cringing at the inefficiency of the nested loops,
          remember that they both iterate over a very small number of
@@ -532,6 +536,25 @@ tag_handle_meta (int tagid, struct taginfo *tag, struct map_context *ctx)
           entry->link_expect_html = 1;
         }
     }
+  else if (http_equiv && 0 == strcasecmp (http_equiv, "content-type"))
+    {
+      /* Handle stuff like:
+         <meta http-equiv="Content-Type" content="text/html; charset=CHARSET"> */
+
+      char *mcharset;
+      char *content = find_attr (tag, "content", NULL);
+      if (!content)
+        return;
+
+      mcharset = parse_charset (content);
+      if (!mcharset)
+        return;
+
+      /*logprintf (LOG_VERBOSE, "Meta tag charset : %s\n", quote (mcharset));*/
+
+      set_current_charset (mcharset);
+      xfree (mcharset);
+    }
   else if (name && 0 == strcasecmp (name, "robots"))
     {
       /* Handle stuff like:
@@ -638,6 +661,7 @@ get_urls_file (const char *file)
   struct file_memory *fm;
   struct urlpos *head, *tail;
   const char *text, *text_end;
+  bool utf8_encode = false;
 
   /* Load the file.  */
   fm = read_file (file);
@@ -689,7 +713,7 @@ get_urls_file (const char *file)
           url_text = merged;
         }
 
-      url = url_parse (url_text, &up_error_code);
+      url = url_parse (url_text, &up_error_code, &utf8_encode);
       if (!url)
         {
           logprintf (LOG_NOTQUIET, _("%s: Invalid URL %s: %s\n"),