Changeset 1632

Timestamp:

04/18/2010 11:55:39 AM (3 years ago)

Author:

BrianKoontz

Message:

Modified forced links ([[...]]) to correctly parse non-CC page names.
In order to do this, and to maintain backwards compatibility, the
following cases are now checked (in the order specified) that should
account for the vast majority of forced links. We should consider
deprecating the use of forced links that contain a url and text, but
no separator (currently whitespace; proposed is the pipe character
"|"):

Case 1: First part is a URL, followed by one or more whitespaces,
followed by link text (deprecated; backwards compatible)

Case 2: First part is a CC string, followed by one or more whitespaces,
followed by link text (deprecated; backwards compatible)

Case 3: Text (possibly containing embedded whitespaces) that matches
an existing internal wiki page (must not contain "|" symbol; backwards
compatible)

Case 4: First part is a URL, followed by a "|" symbol, followed by
link text (new)

Refs #191

Files:

• branches/1.3/formatters/wakka.php (modified) (2 diffs)

branches/1.3/formatters/wakka.php

@@ -766 +766 @@
                         return $output;
                 }
+
                 // forced links
                 // \S : any character that is not a whitespace character
                 // \s : any whitespace character
-                // @@@ regex accepts NO non-whitespace before whitespace, surely not correct? [[  something]]
-                else if (preg_match("/^\[\[(\S*)(\s+(.+))?\]\]$/s", $thing, $matches))          # recognize forced links across lines
-                {
-                        if (!isset($matches[1])) $matches[1] = ''; #38
-                        if (!isset($matches[3])) $matches[3] = ''; #38
-                        list (, $url, , $text) = $matches;
+                else if(preg_match("/^\[\[(.*?)\]\]$/s", $thing, $matches))
+                {
+                        $contents = $matches[1];
+                        if(empty($contents) || !isset($contents))
+                                return "";
+
+                        // Case 1: Deprecated...(first part is a URL followed by
+                        // one or more whitespaces)
+                        if (preg_match("/^((http|https|ftp|news|irc|gopher):\/\/([^\|\\s\"<>]+))\s+([^\|]+)$/s", $contents, $matches))          # recognize forced links across lines
+                        {
+                                if (!isset($matches[1])) $matches[1] = ''; #38
+                                if (!isset($matches[4])) $matches[4] = ''; #38
+                                $url = $matches[1];
+                                $text = $matches[4];
+                        }
+
+                        // Case 2: Deprecated...(first part is a CC string
+                        // followed by one or more whitespaces)
+                        else if(preg_match("/^(.*?)\s+([^|]+)$/s", $contents, $matches) && 
+                                preg_match(VALID_PAGENAME_PATTERN, $matches[1]))
+                        {
+                                $url = $matches[1]; 
+                                $text = $matches[2];
+                        }
+
+                        // Case 3: If no "|" exists in $contents, assume the match
+                        // refers to an internal page
+                        else if(preg_match("/^([^\|]+)$/s", $contents, $matches))
+                        {
+                                $url = $matches[1];
+                                $text = $matches[1];
+                        }
+
+                        // Case 4: If a "|" symbol exists, assume two parts, a URL and
+                        // text
+                        else if(preg_match("/^(.*?)\s*\|\s*(.*?)$/s", $contents, $matches))
+                        {
+                                if (!isset($matches[1])) $matches[1] = '';
+                                if (!isset($matches[2])) $matches[2] = '';
+                                $url = $matches[1];
+                                $text = $matches[2];
+                        }
+
                         if ($url)
                         {
@@ -787 +825 @@
                         }
                 }
+
                 // indented text
                 elseif (preg_match("/(^|\n)([\t~]+)(-|&|([0-9a-zA-Z]+)\))?(\n|$)/s", $thing, $matches))