Improve url finding more. Properly end urls when a space is caught.

diff --git a/lib/util.php b/lib/util.php
index 575e796f11dff1aa3b27098fa88001811de32b8c..091533afb19c9c6bd4e5c6228940156760962063 100644 (file)
--- a/lib/util.php
+++ b/lib/util.php
@@ -412,37 +412,44 @@ function common_render_text($text)
 function common_replace_urls_callback($text, $callback, $notice_id = null) {
     // Start off with a regex
     $regex = '#'.
-    '(?:^|[\s\(\)\[\]\{\}]+)('.
-        '(?:'. //Known protocols
-            '(?:'.
-                '(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
-                '|'.
-                '(?:mailto|aim|tel|xmpp):'.
-            ')[^\s\(\)\[\]\{\}]+'.
+    '(?:^|[\s\(\)\[\]\{\}]+)'.
+        '('.
+        '(?:'.
+            '(?:'. //Known protocols
+                '(?:'.
+                    '(?:https?|ftps?|mms|rtsp|gopher|news|nntp|telnet|wais|file|prospero|webcal|irc)://'.
+                    '|'.
+                    '(?:mailto|aim|tel|xmpp):'.
+                ')[^\s\/]+'.
+            ')'.
+            '|(?:(?: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-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,6}|'.
+                '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,5}|'.
+                '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,4}|'.
+                '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,3}|'.
+                '(?:[0-9a-f]{1,4}:){1,5}(?::[0-9a-f]{1,4}){1,2}|'.
+                '(?:[0-9a-f]{1,4}:){1,6}(?::[0-9a-f]{1,4}){1,1}|'.
+                '(?:(?:[0-9a-f]{1,4}:){1,7}|:):|'.
+                ':(?::[0-9a-f]{1,4}){1,7}|'.
+                '(?:(?:(?:[0-9a-f]{1,4}:){6})(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
+                '(?:(?:[0-9a-f]{1,4}:){5}[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
+                '(?:[0-9a-f]{1,4}:){5}:[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                '(?:[0-9a-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,3}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,2}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,1}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                '(?:(?:[0-9a-f]{1,4}:){1,5}|:):(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
+                ':(?::[0-9a-f]{1,4}){1,5}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}'.
+            ')|(?:'. //DNS
+                '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
+            ')'.
         ')'.
-        '|(?:(?: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-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,6}|'.
-            '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,5}|'.
-            '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,4}|'.
-            '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,3}|'.
-            '(?:[0-9a-f]{1,4}:){1,5}(?::[0-9a-f]{1,4}){1,2}|'.
-            '(?:[0-9a-f]{1,4}:){1,6}(?::[0-9a-f]{1,4}){1,1}|'.
-            '(?:(?:[0-9a-f]{1,4}:){1,7}|:):|'.
-            ':(?::[0-9a-f]{1,4}){1,7}|'.
-            '(?:(?:(?:[0-9a-f]{1,4}:){6})(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
-            '(?:(?:[0-9a-f]{1,4}:){5}[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3})|'.
-            '(?:[0-9a-f]{1,4}:){5}:[0-9a-f]{1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            '(?:[0-9a-f]{1,4}:){1,1}(?::[0-9a-f]{1,4}){1,4}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            '(?:[0-9a-f]{1,4}:){1,2}(?::[0-9a-f]{1,4}){1,3}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            '(?:[0-9a-f]{1,4}:){1,3}(?::[0-9a-f]{1,4}){1,2}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            '(?:[0-9a-f]{1,4}:){1,4}(?::[0-9a-f]{1,4}){1,1}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            '(?:(?:[0-9a-f]{1,4}:){1,5}|:):(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}|'.
-            ':(?::[0-9a-f]{1,4}){1,5}:(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)(?:\.(?:25[0-5]|2[0-4]\d|[0-1]?\d?\d)){3}'.
-        ')|(?:'. //DNS
-            '\S+\.(?:museum|travel|onion|local|[a-z]{2,4})'.
+        '(?:'.
+            '$|(?:'.
+                '/[^\s\(\)\[\]\{\}]*'.
+            ')'.
         ')'.
-        '([^\s\(\)\[\]\{\}]*)'.
     ')'.
     '#ix';
     return preg_replace_callback($regex, curry(callback_helper,$callback,$notice_id) ,$text);