Changeset 30449 for trunk/src/wp-includes/formatting.php

Timestamp:

11/20/2014 02:27:08 PM (12 years ago)

Author:

nacin

Message:

Anchor texturize to shortcodes to improve regex efficiency.

props miqrogroove.
see #29557 for segfault issues.

File:

• trunk/src/wp-includes/formatting.php (modified) (3 diffs)

trunk/src/wp-includes/formatting.php

@@ -29 +29 @@
  */
 function wptexturize($text, $reset = false) {
-        global $wp_cockneyreplace;
+        global $wp_cockneyreplace, $shortcode_tags;
         static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
                 $default_no_texturize_tags, $default_no_texturize_shortcodes, $run_texturize = true;
@@ -206 +206 @@
         // Look for shortcodes and HTML elements.
 
+        $tagnames = array_keys( $shortcode_tags );
+        $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
+        $tagregexp = "(?:$tagregexp)(?![\\w-])"; // Excerpt of get_shortcode_regex().
+
         $comment_regex =
                   '!'           // Start of comment, after the <.
@@ -215 +219 @@
 
         $shortcode_regex =
-                  '\['          // Find start of shortcode.
-                . '[\/\[]?'     // Shortcodes may begin with [/ or [[
-                . '[^\s\/\[\]]' // No whitespace before name.
-                . '[^\[\]]*+'   // Shortcodes do not contain other shortcodes. Possessive critical.
-                . '\]'          // Find end of shortcode.
-                . '\]?';        // Shortcodes may end with ]]
+                  '\['              // Find start of shortcode.
+                . '[\/\[]?'         // Shortcodes may begin with [/ or [[
+                . $tagregexp        // Only match registered shortcodes, because performance.
+                . '(?:'
+                .     '[^\[\]<>]+'  // Shortcodes do not contain other shortcodes. Quantifier critical.
+                . '|'
+                .     '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
+                . ')*+'             // Possessive critical.
+                . '\]'              // Find end of shortcode.
+                . '\]?';            // Shortcodes may end with ]]
 
         $regex =