Improved the URL tests, and improve the matcher so more tests are passed. The remaining failing tests I believe are incorrect.

1 files changed, 14 insertions, 10 deletions

diff --git a/lib/util.php b/lib/util.php
index 2be4213e7..ee3fe5ddc 100644
--- a/lib/util.php
+++ b/lib/util.php
@@ -412,30 +412,34 @@ function common_render_text($text)
 function common_replace_urls_callback($text, $callback, $notice_id = null) {
     // Start off with a regex
     $regex = '#'.
-    '(?:^|[\s\(\)\[\]\{\}]+)'.
-        '('.
+    '(?:^|[\s\(\)\[\]\{\}\\\'\\\";]+)(?![\@\!\#])'.
+    '('.
         '(?:'.
             '(?:'. //Known protocols
                 '(?:'.
                     '(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
                     '|'.
                     '(?:mailto|aim|tel|xmpp):'.
-                ')[^\s\/]+'.
+                ')'.
+                '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+                '[\pN\pL\-\_\:\.]+(?<![\.\:])'. //dns
             ')'.
             '|(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)'. //IPv4
             '|(?:'. //IPv6
                 '(?:(?:(?:[0-9A-Fa-f]{1,4}:){7}(?:(?:[0-9A-Fa-f]{1,4})|:))|(?:(?:[0-9A-Fa-f]{1,4}:){6}(?::|(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})|(?::[0-9A-Fa-f]{1,4})))|(?:(?:[0-9A-Fa-f]{1,4}:){5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){4}(?::[0-9A-Fa-f]{1,4}){0,1}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){3}(?::[0-9A-Fa-f]{1,4}){0,2}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:){2}(?::[0-9A-Fa-f]{1,4}){0,3}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:[0-9A-Fa-f]{1,4}:)(?::[0-9A-Fa-f]{1,4}){0,4}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?::(?::[0-9A-Fa-f]{1,4}){0,5}(?:(?::(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})?)|(?:(?::[0-9A-Fa-f]{1,4}){1,2})))|(?:(?:(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})(?:\.(?:25[0-5]|2[0-4]\d|[01]?\d{1,2})){3})))'.
             ')|(?:'. //DNS
-                '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
-            ')'.
+                '(?:[\pN\pL\-\_\+]+(?:\:[\pN\pL\-\_\+]+)?\@)?'. //user:pass@
+                '[\pN\pL\-\_]+(?:\.[\pN\pL\-\_]+)*\.(?:museum|travel|onion|local|[a-z]{2,4})'.
+            ')(?![\pN\pL\-\_])'.
         ')'.
         '(?:'.
-            '$|(?:'.
-                '/[^\s\(\)\[\]\{\}]*'.
-            ')'.
-        ')'.
+            '(?:\:\d+)?'. //:port
+            '(?:/[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;]*)?'. // /path
+            '(?:\?[\pN\pL\$\!\(\)\.\-\_\+\/\=\&\;\/]*)?'. // ?query string
+            '(?:\#[\pN\pL$\!\(\)\.\-\_\+\/\=\&\;\/\?\#]*)?'. // #fragment
+        ')(?<![\?\.\,\#\)])'.
     ')'.
-    '#ix';
+    '#ixu';
     return preg_replace_callback($regex, curry(callback_helper,$callback,$notice_id) ,$text);
 }