Changeset 30450 for branches/4.0/src/wp-includes/formatting.php

Timestamp:

11/20/2014 02:29:03 PM (10 years ago)

Author:

nacin

Message:

Anchor texturize to shortcodes to improve regex efficiency.

For the 4.0 branch; see [30449] for trunk.

props miqrogroove.
see #29557 for segfault issues.

File:

• branches/4.0/src/wp-includes/formatting.php (modified) (4 diffs)

branches/4.0/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 <.
+        . '(?:'         // Unroll the loop: Consume everything until --> is found.
+        .     '-(?!->)' // Dash not followed by end of comment.
+        .     '[^\-]*+' // Consume non-dashes.
+        . ')*+'         // Loop possessively.
+        . '-->';        // End of comment.
+
     $regex =  '/('          // Capture the entire match.
         .   '<'     // Find start of element.
         .   '(?(?=!--)' // Is this a comment?
-        .       '.+?--\s*>' // Find end of comment
+        .       $comment_regex  // Find end of comment
         .   '|'
         .       '[^>]+>'    // Find end of element
@@ -215 +227 @@
         . '|'
         .   '\['        // Find start of shortcode.
-        .   '\[?'       // Shortcodes may begin with [[
+        .   '[\/\[]?'   // Shortcodes may begin with [/ or [[
+        .   $tagregexp  // Only match registered shortcodes, because performance.
         .   '(?:'
-        .       '[^\[\]<>]' // Shortcodes do not contain other shortcodes.
+        .       '[^\[\]<>]+'    // Shortcodes do not contain other shortcodes. Quantifier critical.
         .   '|'
-        .       '<[^>]+>'   // HTML elements permitted. Prevents matching ] before >.
-        .   ')++'
+        .       '<[^\[\]>]*>'   // HTML elements permitted. Prevents matching ] before >.
+        .   ')*+'       // Possessive critical.
         .   '\]'        // Find end of shortcode.
         .   '\]?'       // Shortcodes may end with ]]
@@ -242 +255 @@
             continue;
 
-        } elseif ( '[' === $first && 1 === preg_match( '/^\[(?:[^\[\]<>]|<[^>]+>)++\]$/', $curl ) ) {
+        } elseif ( '[' === $first && 1 === preg_match( '/^\[\/?' . $tagregexp . '(?:[^\[\]<>]+|<[^\[\]>]*>)*+\]$/', $curl ) ) {
             // This is a shortcode delimiter.
 
             _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
 
-        } elseif ( '[' === $first && 1 === preg_match( '/^\[\[?(?:[^\[\]<>]|<[^>]+>)++\]\]?$/', $curl ) ) {
+        } elseif ( '[' === $first && 1 === preg_match( '/^\[[\/\[]?' . $tagregexp . '(?:[^\[\]<>]+|<[^\[\]>]*>)*+\]\]?$/', $curl ) ) {
             // This is an escaped shortcode delimiter.