--- modules\filter\filter.module.org	Sun Jul 01 20:41:14 2007
+++ modules\filter\filter.module	Mon Sep 03 20:19:40 2007
@@ -1083,24 +1083,80 @@ function _filter_url_settings($format) {
  * ftp links, etc.) into hyperlinks.
  */
 function _filter_url($text, $format) {
+  // List of tags - the content of which must be skipped
+  $ignoretags = 'a|script|style|code';
+  
   // Pass length to regexp callback
   _filter_url_trim(NULL, variable_get('filter_url_length_'. $format, 72));
-
-  $text   = ' '. $text .' ';
-
-  // Match absolute URLs.
-  $text = preg_replace_callback("`(<p>|<li>|<br\s*/?>|[ \n\r\t\(])((http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://)([a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-]))([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '_filter_url_parse_full_links', $text);
-
-  // Match e-mail addresses.
-  $text = preg_replace("`(<p>|<li>|<br\s*/?>|[ \n\r\t\(])([A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4})([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '\1<a href="mailto:\2">\2</a>\3', $text);
-
-  // Match www domains/addresses.
-  $text = preg_replace_callback("`(<p>|<li>|[ \n\r\t\(])(www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-])([.,?!]*?)(?=(</p>|</li>|<br\s*/?>|[ \n\r\t\)]))`i", '_filter_url_parse_partial_links', $text);
-  $text = substr($text, 1, -1);
-
+  
+  // Need to process each replacement separately (see switch in the middle of loops).
+  // The text must be joined and split again after each replacement, since they create 
+  // new html tags.
+  for ( $task = 1; $task <= 3; $task++ ) {
+    // Split at all tags.
+    // This ensures that nothing that is a tagname or attribute will be processed.
+    $chunks = preg_split('´(<.+?>)´i', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+    // Note: PHP ensures the array consists of alternating delimiters and literals
+    // and begins and ends with a literal (inserting NULL as required).
+
+    // If an ignoretag is found, it is stored here and removed when the 
+    // closing tag is found. Until then no replacements are made.
+    // Think of this as a stack that always has 0 or 1 items
+    $opentag = '';
+    for ( $i = 0; $i < count( $chunks ); $i++ ) {
+      // Even/odd = text/tag
+      if ( $i % 2 == 0 ) { // Text
+        if ( $opentag == '' ) { 
+        // Only do replacements when there are no unclosed ignoretags
+          switch ($task) {
+            case 1:
+              // Match absolute URLs. 
+              $protocols = 'http://|https://|ftp://|mailto:|smb://|afp://|file://|gopher://|news://|ssl://|sslv2://|sslv3://|tls://|tcp://|udp://';
+              $urlpattern = "(?:$protocols)(?:[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+*~#&=/;-])";
+              $re = "`($urlpattern)([\.\,\?\!]*?)`i";
+              $chunks[$i] = preg_replace_callback($re, '_filter_url_parse_full_links', $chunks[$i] );
+              break;
+            case 2:
+              // Match e-mail addresses.
+              $urlpattern = '[A-Za-z0-9._-]+@[A-Za-z0-9._+-]+\.[A-Za-z]{2,4}';
+              $re = "`($urlpattern)`i";
+              $chunks[$i] = preg_replace($re, '<a href="mailto:\1">\1</a>', $chunks[$i]);
+              break;
+            case 3:
+              // Match www domains/addresses.
+              $urlpattern = 'www\.[a-zA-Z0-9@:%_+*~#?&=.,/;-]*[a-zA-Z0-9@:%_+~#\&=/;-]';
+              $re = "`($urlpattern)([\.\,\?\!]*?)`i";
+              $chunks[$i] = preg_replace_callback($re, '_filter_url_parse_partial_links', $chunks[$i]);
+              break;
+          }
+        }
+      }
+      else { // Tag
+        if( $opentag == '' ) { 
+          // No open "ignoretag"
+          // Is it an ignoretag? (opening tag)
+          if( preg_match( "´<($ignoretags)(?:\s|>)´i", $chunks[$i], $matches ) ) {
+            // Store and catch the tag in question
+            $opentag = $matches[1];
+          }
+        }
+        else { 
+          // Ignoretag found
+          // Nobody gets to do anything until we find a matching closing tag
+          if( preg_match( "´<\/$opentag>´i", $chunks[$i], $matches ) ) {
+            $opentag = '';
+          }
+        } // if ( $opentag == '' )
+      } // if ( $i % 2 )
+    } // for chunks
+    
+  $text = implode( $chunks );
+  } // for tasks 1..3
+  
   return $text;
 }
 
+
 /**
  * Scan input and make sure that all HTML tags are properly closed and nested.
  */
@@ -1176,23 +1232,27 @@ function _filter_htmlcorrector($text) {
 }
 
 /**
- * Make links out of absolute URLs.
+ * Callback function. Make links out of absolute URLs.
  */
 function _filter_url_parse_full_links($match) {
-  $match[2] = decode_entities($match[2]);
-  $caption = check_plain(_filter_url_trim($match[2]));
-  $match[2] = check_url($match[2]);
-  return $match[1] . '<a href="'. $match[2] .'" title="'. $match[2] .'">'. $caption .'</a>'. $match[5];
+  // Which capturing parenthesis in the regexp contains the url?
+  $i = 1;
+  $match[$i] = decode_entities($match[$i]);
+  $caption = check_plain(_filter_url_trim($match[$i]));
+  $match[$i] = check_url($match[$i]);
+  return '<a href="'. $match[$i] .'" title="'. $match[$i] .'">'. $caption .'</a>'. $match[$i+1];
 }
 
 /**
- * Make links out of domain names starting with "www."
+ * Callback function. Make links out of domain names starting with "www."
  */
 function _filter_url_parse_partial_links($match) {
-  $match[2] = decode_entities($match[2]);
-  $caption = check_plain(_filter_url_trim($match[2]));
-  $match[2] = check_plain($match[2]);
-  return $match[1] . '<a href="http://'. $match[2] .'" title="'. $match[2] .'">'. $caption .'</a>'. $match[3];
+  // Which parenthesis in the regexp contains the url?
+  $i = 1;
+  $match[$i] = decode_entities($match[$i]);
+  $caption = check_plain(_filter_url_trim($match[$i]));
+  $match[$i] = check_plain($match[$i]);
+  return '<a href="http://'. $match[$i] .'" title="'. $match[$i] .'">'. $caption .'</a>'. $match[$i+1];
 }
 
 /**