support request #323879 by jcfiala:Updated link 5.x validation to use same code as 6.x branch.

bug report #436020 by jcfiala:Updated link domain names to include asia

link.module

@@ -10,7 +10,23 @@ define('LINK_EXTERNAL', 'external');
 define('LINK_INTERNAL', 'internal');
 define('LINK_FRONT', 'front');
 define('LINK_EMAIL', 'email');
-define('LINK_DOMAINS', 'aero|arpa|biz|com|cat|coop|edu|gov|info|int|jobs|mil|museum|name|nato|net|org|pro|travel|mobi|local');
+define('LINK_DOMAINS', 'aero|arpa|asia|biz|com|cat|coop|edu|gov|info|int|jobs|mil|museum|name|nato|net|org|pro|travel|mobi|local');
+
+// There are many other characters which are legal other than simply a-z - this includes them.
+define('LINK_ICHARS', (string) html_entity_decode(implode("", array(
+    "æ", // æ
+    "Æ", // Æ
+    "ø", // ø
+    "Ø", // Ø
+    "å", // å
+    "Å", // Å
+    "ä", // ä
+    "Ä", // Ä
+    "ö", // ö
+    "Ö", // Ö
+    "ü", // ü
+    "Ü", // Ü
+  )), ENT_QUOTES, 'UTF-8'));
 
 /**
  * Implementation of hook_menu().
@@ -843,32 +859,35 @@ function link_cleanup_url($url, $protocol = "http") {
  * the following attributes: protocol, hostname, ip, and port.
  */
 function link_validate_url($text) {
-
   $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]+(:[a-z0-9]+)?@)';
-  $domain = '(([a-z0-9]([a-z0-9\-_\[\]])*)(\.(([a-z0-9\-_\[\]])+\.)*('. LINK_DOMAINS .'|[a-z]{2}))?)';
+  $protocol = '(('. implode("|", $allowed_protocols) .'):\/\/)';
+  $authentication = '(([a-z0-9%' . LINK_ICHARS . ']+(:[a-z0-9%'. LINK_ICHARS . '!]*)?)?@)';
+  $domain = '(([a-z0-9' . LINK_ICHARS . ']([a-z0-9'. LINK_ICHARS . '\-_\[\]])*)(\.(([a-z0-9' . LINK_ICHARS . '\-_\[\]])+\.)*('. 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 eternal links.
-  $external_pattern = '/^' . $protocol . '?' . $authentication . '?' . '(' . $domain . '|' . $ipv4 . '|' . $ipv6 . ' |localhost)' . $port . '?';
+  // Pattern specific to external links.
+  $external_pattern = '/^'. $protocol .'?'. $authentication .'?('. $domain .'|'. $ipv4 .'|'. $ipv6 .' |localhost)'. $port .'?';
 
   // Pattern specific to internal links.
-  $internal_pattern = "/^([a-z0-9_\-+\[\]]+)";
+  $internal_pattern = "/^([a-z0-9". LINK_ICHARS ."_\-+\[\]]+)";
 
-  $directories = "(\/[a-z0-9_\-\.~+%=&,$'():;*@\[\]]*)*";
-   // Yes, four backslashes == a single backslash.
-  $query = "(\/?\?([?a-z0-9+_|\-\.\/\\\\%=&,$'():;*@\[\]]*))";
-  $anchor = "(#[a-z0-9_\-\.~+%=&,$'():;*@\[\]]*)";
+  $directories = "(\/[a-z0-9". LINK_ICHARS ."_\-\.~+%=&,$'!():;*@\[\]]*)*";
+  // Yes, four backslashes == a single backslash.
+  $query = "(\/?\?([?a-z0-9". LINK_ICHARS ."+_|\-\.\/\\\\%=&,$'():;*@\[\]{} ]*))";
+  $anchor = "(#[a-z0-9". LINK_ICHARS ."_\-\.~+%=&,$'():;*@\[\]\/\?]*)";
 
   // The rest of the path for a standard URL.
-  $end = $directories . '?' . $query . '?' . $anchor . '?' . '$/i';
+  $end = $directories .'?'. $query .'?'. $anchor .'?'.'$/i';
+  
+  $message_id = '[^@].*@'. $domain;
+  $newsgroup_name = '([0-9a-z+-]*\.)*[0-9a-z+-]*';
+  $news_pattern = '/^news:('. $newsgroup_name .'|'. $message_id .')$/i';
 
-  $user = '[a-zA-Z0-9_\-\.\+\^!#\$%&*+\/\=\?\`\|\{\}~\'\[\]]+';
-  $email_pattern = '/^mailto:' . $user . '@' . '(' . $domain . '|' . $ipv4 .'|'. $ipv6 . '|localhost)' . $query . '?$/';
+  $user = '[a-zA-Z0-9'. LINK_ICHARS .'_\-\.\+\^!#\$%&*+\/\=\?\`\|\{\}~\'\[\]]+';
+  $email_pattern = '/^mailto:'. $user .'@'.'('. $domain .'|'. $ipv4 .'|'. $ipv6 .'|localhost)'. $query .'?$/';
 
   if (strpos($text, '<front>') === 0) {
     return LINK_FRONT;
@@ -876,6 +895,9 @@ function link_validate_url($text) {
   if (in_array('mailto', $allowed_protocols) && preg_match($email_pattern, $text)) {
     return LINK_EMAIL;
   }
+  if (in_array('news', $allowed_protocols) && preg_match($news_pattern, $text)) {
+    return LINK_NEWS;
+  }
   if (preg_match($internal_pattern . $end, $text)) {
     return LINK_INTERNAL;
   }