Added slight changes to how links are validated to bring them in line with valid_url()

link.module

@@ -837,34 +837,35 @@ function link_validate_url($text) {
   )), ENT_QUOTES, 'UTF-8');
   $allowed_protocols = variable_get('filter_allowed_protocols', array('http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'mailto', 'irc', 'ssh', 'sftp', 'webcal'));
 
-  $protocol = '(('. implode("|", $allowed_protocols) .'):\/\/)';
-  $authentication = '(([a-z0-9%' . $LINK_ICHARS . ']+(:[a-z0-9%'. $LINK_ICHARS . '!]*)?)?@)';
-  $domain = '(([a-z0-9' . $LINK_ICHARS_DOMAIN . ']([a-z0-9'. $LINK_ICHARS_DOMAIN . '\-_\[\]])*)(\.(([a-z0-9' . $LINK_ICHARS_DOMAIN . '\-_\[\]])+\.)*('. LINK_DOMAINS .'|[a-z]{2}))?)';
-  $ipv4 = '([0-9]{1,3}(\.[0-9]{1,3}){3})';
-  $ipv6 = '([0-9a-fA-F]{1,4}(\:[0-9a-fA-F]{1,4}){7})';
-  $port = '(:([0-9]{1,5}))';
+  // Starting a parenthesis group with (?: means that it is grouped, but is not captured
+  $protocol = '((?:'. implode("|", $allowed_protocols) .'):\/\/)';
+  $authentication = "(?:(?:(?:[\w\.\-\+!$&'\(\)*\+,;=" . $LINK_ICHARS . "]|%[0-9a-f]{2})+(?::(?:[\w". $LINK_ICHARS ."\.\-\+%!$&'\(\)*\+,;=]|%[0-9a-f]{2})*)?)?@)";
+  $domain = '(?:(?:[a-z0-9' . $LINK_ICHARS_DOMAIN . ']([a-z0-9'. $LINK_ICHARS_DOMAIN . '\-_\[\]])*)(\.(([a-z0-9' . $LINK_ICHARS_DOMAIN . '\-_\[\]])+\.)*('. LINK_DOMAINS .'|[a-z]{2}))?)';
+  $ipv4 = '(?:[0-9]{1,3}(\.[0-9]{1,3}){3})';
+  $ipv6 = '(?:[0-9a-fA-F]{1,4}(\:[0-9a-fA-F]{1,4}){7})';
+  $port = '(?::([0-9]{1,5}))';
 
   // Pattern specific to external links.
   $external_pattern = '/^'. $protocol .'?'. $authentication .'?('. $domain .'|'. $ipv4 .'|'. $ipv6 .' |localhost)'. $port .'?';
 
   // Pattern specific to internal links.
-  $internal_pattern = "/^([a-z0-9". $LINK_ICHARS ."_\-+\[\]]+)";
-  $internal_pattern_file = "/^([a-z0-9". $LINK_ICHARS ."_\-+\[\]\.]+)$/i";
+  $internal_pattern = "/^(?:[a-z0-9". $LINK_ICHARS ."_\-+\[\]]+)";
+  $internal_pattern_file = "/^(?:[a-z0-9". $LINK_ICHARS ."_\-+\[\]\.]+)$/i";
 
-  $directories = "(\/[a-z0-9". $LINK_ICHARS ."_\-\.~+%=&,$'!():;*@\[\]]*)*";
+  $directories = "(?:\/[a-z0-9". $LINK_ICHARS ."_\-\.~+%=&,$'!():;*@\[\]]*)*";
   // Yes, four backslashes == a single backslash.
-  $query = "(\/?\?([?a-z0-9". $LINK_ICHARS ."+_|\-\.\/\\\\%=&,$'():;*@\[\]{} ]*))";
-  $anchor = "(#[a-z0-9". $LINK_ICHARS ."_\-\.~+%=&,$'():;*@\[\]\/\?]*)";
+  $query = "(?:\/?\?([?a-z0-9". $LINK_ICHARS ."+_|\-\.\/\\\\%=&,$'():;*@\[\]{} ]*))";
+  $anchor = "(?:#[a-z0-9". $LINK_ICHARS ."_\-\.~+%=&,$'():;*@\[\]\/\?]*)";
 
   // The rest of the path for a standard URL.
   $end = $directories .'?'. $query .'?'. $anchor .'?'.'$/i';
 
   $message_id = '[^@].*@'. $domain;
-  $newsgroup_name = '([0-9a-z+-]*\.)*[0-9a-z+-]*';
+  $newsgroup_name = '(?:[0-9a-z+-]*\.)*[0-9a-z+-]*';
   $news_pattern = '/^news:('. $newsgroup_name .'|'. $message_id .')$/i';
 
   $user = '[a-zA-Z0-9'. $LINK_ICHARS .'_\-\.\+\^!#\$%&*+\/\=\?\`\|\{\}~\'\[\]]+';
-  $email_pattern = '/^mailto:'. $user .'@'.'('. $domain .'|'. $ipv4 .'|'. $ipv6 .'|localhost)'. $query .'?$/';
+  $email_pattern = '/^mailto:'. $user .'@'.'(?:'. $domain .'|'. $ipv4 .'|'. $ipv6 .'|localhost)'. $query .'?$/';
 
   if (strpos($text, '<front>') === 0) {
     return LINK_FRONT;

tests/link.validate.test

@@ -480,6 +480,9 @@ class LinkValidateUrlLight extends DrupalWebTestCase {
     foreach ($links as $link) {
       $valid = link_validate_url($link);
       $this->assertEqual(LINK_EXTERNAL, $valid, 'Testing that '. $link .' is a valid external link.');
+      // The following two lines are commented out and only used for comparisons.
+      //$valid2 = valid_url($link, TRUE);
+      //$this->assertEqual(TRUE, $valid2, "Using valid_url() on $link.");
     }
   }