<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN"
"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
<html xmlns="http://www.w3.org/1999/xhtml">
<head><meta http-equiv="content-type" content="text/html; charset=utf-8" /><style type="text/css"><!--
#msg dl { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; }
#msg dl a { font-weight: bold}
#msg dl a:link { color:#fc3; }
#msg dl a:active { color:#ff0; }
#msg dl a:visited { color:#cc6; }
h3 { font-family: verdana,arial,helvetica,sans-serif; font-size: 10pt; font-weight: bold; }
#msg pre { overflow: auto; background: #ffc; border: 1px #fc0 solid; padding: 6px; }
#msg ul, pre { overflow: auto; }
#header, #footer { color: #fff; background: #636; border: 1px #300 solid; padding: 6px; }
#patch { width: 100%; }
#patch h4 {font-family: verdana,arial,helvetica,sans-serif;font-size:10pt;padding:8px;background:#369;color:#fff;margin:0;}
#patch .propset h4, #patch .binary h4 {margin:0;}
#patch pre {padding:0;line-height:1.2em;margin:0;}
#patch .diff {width:100%;background:#eee;padding: 0 0 10px 0;overflow:auto;}
#patch .propset .diff, #patch .binary .diff {padding:10px 0;}
#patch span {display:block;padding:0 10px;}
#patch .modfile, #patch .addfile, #patch .delfile, #patch .propset, #patch .binary, #patch .copfile {border:1px solid #ccc;margin:10px 0;}
#patch ins {background:#dfd;text-decoration:none;display:block;padding:0 10px;}
#patch del {background:#fdd;text-decoration:none;display:block;padding:0 10px;}
#patch .lines, .info {color:#888;background:#fff;}
--></style>
<title>[12084] trunk/wp-includes/formatting.php: Improve wptexturize performance.</title>
</head>
<body>
<div id="msg">
<dl>
<dt>Revision</dt> <dd><a href="http://trac.wordpress.org/changeset/12084">12084</a></dd>
<dt>Author</dt> <dd>westi</dd>
<dt>Date</dt> <dd>2009-10-21 21:57:27 +0000 (Wed, 21 Oct 2009)</dd>
</dl>
<h3>Log Message</h3>
<pre>Improve wptexturize performance. Fixes <a href="http://trac.wordpress.org/ticket/10987">#10987</a> props johanee.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunkwpincludesformattingphp">trunk/wp-includes/formatting.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkwpincludesformattingphp"></a>
<div class="modfile"><h4>Modified: trunk/wp-includes/formatting.php (12083 => 12084)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/wp-includes/formatting.php 2009-10-21 15:17:57 UTC (rev 12083)
+++ trunk/wp-includes/formatting.php 2009-10-21 21:57:27 UTC (rev 12084)
</span><span class="lines">@@ -28,48 +28,67 @@
</span><span class="cx"> */
</span><span class="cx"> function wptexturize($text) {
</span><span class="cx"> global $wp_cockneyreplace;
</span><ins>+ static $static_setup = false, $opening_quote, $closing_quote, $default_no_texturize_tags, $default_no_texturize_shortcodes, $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements;
</ins><span class="cx"> $output = '';
</span><span class="cx"> $curl = '';
</span><span class="cx"> $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
</span><span class="cx"> $stop = count($textarr);
</span><ins>+
+ // No need to setup these variables more than once
+ if (!$static_setup) {
+ /* translators: opening curly quote */
+ $opening_quote = _x('&#8220;', 'opening curly quote');
+ /* translators: closing curly quote */
+ $closing_quote = _x('&#8221;', 'closing curly quote');
</ins><span class="cx">
</span><del>- /* translators: opening curly quote */
- $opening_quote = _x('&#8220;', 'opening curly quote');
- /* translators: closing curly quote */
- $closing_quote = _x('&#8221;', 'closing curly quote');
</del><ins>+ $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
+ $default_no_texturize_shortcodes = array('code');
</ins><span class="cx">
</span><del>- $no_texturize_tags = apply_filters('no_texturize_tags', array('pre', 'code', 'kbd', 'style', 'script', 'tt'));
- $no_texturize_shortcodes = apply_filters('no_texturize_shortcodes', array('code'));
- $no_texturize_tags_stack = array();
- $no_texturize_shortcodes_stack = array();
</del><ins>+ // if a plugin has provided an autocorrect array, use it
+ if ( isset($wp_cockneyreplace) ) {
+ $cockney = array_keys($wp_cockneyreplace);
+ $cockneyreplace = array_values($wp_cockneyreplace);
+ } else {
+ $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
+ $cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round","&#8217;cause");
+ }
</ins><span class="cx">
</span><del>- // if a plugin has provided an autocorrect array, use it
- if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
- } else {
- $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
- $cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round","&#8217;cause");
</del><ins>+ $static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn&#8211;', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
+ $static_replacements = array_merge(array('&#8212;', ' &#8212; ', '&#8211;', ' &#8211; ', 'xn--', '&#8230;', $opening_quote, '&#8217;s', $closing_quote, ' &#8482;'), $cockneyreplace);
+
+ $dynamic_characters = array('/\'(\d\d(?:&#8217;|\')?s)/', '/(\s|\A|[([{<]|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A|[([{<])"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
+ $dynamic_replacements = array('&#8217;$1','$1&#8216;', '$1&#8243;', '$1&#8242;', '$1&#8217;$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '&#8217;$1', '$1&#215;$2');
+
+ $static_setup = true;
</ins><span class="cx"> }
</span><span class="cx">
</span><del>- $static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn&#8211;', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
- $static_replacements = array_merge(array('&#8212;', ' &#8212; ', '&#8211;', ' &#8211; ', 'xn--', '&#8230;', $opening_quote, '&#8217;s', $closing_quote, ' &#8482;'), $cockneyreplace);
</del><ins>+ // Transform into regexp sub-expression used in _wptexturize_pushpop_element
+ // Must do this everytime in case plugins use these filters in a context sensitive manner
+ $no_texturize_tags = '(' . implode('|', apply_filters('no_texturize_tags', $default_no_texturize_tags) ) . ')';
+ $no_texturize_shortcodes = '(' . implode('|', apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes) ) . ')';
</ins><span class="cx">
</span><del>- $dynamic_characters = array('/\'(\d\d(?:&#8217;|\')?s)/', '/(\s|\A|[([{<]|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A|[([{<])"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
- $dynamic_replacements = array('&#8217;$1','$1&#8216;', '$1&#8243;', '$1&#8242;', '$1&#8217;$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '&#8217;$1', '$1&#215;$2');
</del><ins>+ $no_texturize_tags_stack = array();
+ $no_texturize_shortcodes_stack = array();
</ins><span class="cx">
</span><span class="cx"> for ( $i = 0; $i < $stop; $i++ ) {
</span><span class="cx"> $curl = $textarr[$i];
</span><span class="cx">
</span><span class="cx"> if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0}
</span><del>- && empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) { // If it's not a tag
</del><ins>+ && empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) {
+ // This is not a tag, nor is the texturization disabled
</ins><span class="cx"> // static strings
</span><span class="cx"> $curl = str_replace($static_characters, $static_replacements, $curl);
</span><span class="cx"> // regular expressions
</span><span class="cx"> $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
</span><del>- } else {
- wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
- wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
</del><ins>+ } elseif (!empty($curl)) {
+ /*
+ * Only call _wptexturize_pushpop_element if first char is correct
+ * tag opening
+ */
+ if ('<' == $curl{0})
+ _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
+ elseif ('[' == $curl{0})
+ _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&#038;$1', $curl);
</span><span class="lines">@@ -79,17 +98,44 @@
</span><span class="cx"> return $output;
</span><span class="cx"> }
</span><span class="cx">
</span><del>-function wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
- $o = preg_quote($opening, '/');
- $c = preg_quote($closing, '/');
- foreach($disabled_elements as $element) {
- if (preg_match('/^'.$o.$element.'\b/', $text)) array_push($stack, $element);
- if (preg_match('/^'.$o.'\/'.$element.$c.'/', $text)) {
</del><ins>+/**
+ * Search for disabled element tags. Push element to stack on tag open and pop
+ * on tag close. Assumes first character of $text is tag opening.
+ *
+ * @access private
+ * @since 2.9.0
+ *
+ * @param string $text Text to check. First character is assumed to be $opening
+ * @param array $stack Array used as stack of opened tag elements
+ * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
+ * @param string $opening Tag opening character, assumed to be 1 character long
+ * @param string $opening Tag closing character
+ * @return object
+ */
+function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
+ // Check if it is a closing tag -- otherwise assume opening tag
+ if (strncmp($opening . '/', $text, 2)) {
+ // Opening? Check $text+1 against disabled elements
+ if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
+ /*
+ * This disables texturize until we find a closing tag of our type
+ * (e.g. <pre>) even if there was invalid nesting before that
+ *
+ * Example: in the case <pre>sadsadasd</code>"baba"</pre>
+ * "baba" won't be texturize
+ */
+
+ array_push($stack, $matches[1]);
+ }
+ } else {
+ // Closing? Check $text+2 against disabled elements
+ $c = preg_quote($closing, '/');
+ if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
</ins><span class="cx"> $last = array_pop($stack);
</span><del>- // disable texturize until we find a closing tag of our type (e.g. <pre>)
- // even if there was invalid nesting before that
- // Example: in the case <pre>sadsadasd</code>"baba"</pre> "baba" won't be texturized
- if ($last != $element) array_push($stack, $last);
</del><ins>+
+ // Make sure it matches the opening tag
+ if ($last != $matches[1])
+ array_push($stack, $last);
</ins><span class="cx"> }
</span><span class="cx"> }
</span><span class="cx"> }
</span></span></pre>
</div>
</div>
</body>
</html>