<!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" />
<title>[28986] trunk/src/wp-includes/formatting.php: Optimize regexp usage in `wptexturize()` for a "3x Performance Boost."</title>
</head>
<body>
<style type="text/css"><!--
#msg dl.meta { border: 1px #006 solid; background: #369; padding: 6px; color: #fff; }
#msg dl.meta dt { float: left; width: 6em; font-weight: bold; }
#msg dt:after { content:':';}
#msg dl, #msg dt, #msg ul, #msg li, #header, #footer, #logmsg { 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 #fa0 solid; padding: 6px; }
#logmsg { background: #ffc; border: 1px #fa0 solid; padding: 1em 1em 0 1em; }
#logmsg p, #logmsg pre, #logmsg blockquote { margin: 0 0 1em 0; }
#logmsg p, #logmsg li, #logmsg dt, #logmsg dd { line-height: 14pt; }
#logmsg h1, #logmsg h2, #logmsg h3, #logmsg h4, #logmsg h5, #logmsg h6 { margin: .5em 0; }
#logmsg h1:first-child, #logmsg h2:first-child, #logmsg h3:first-child, #logmsg h4:first-child, #logmsg h5:first-child, #logmsg h6:first-child { margin-top: 0; }
#logmsg ul, #logmsg ol { padding: 0; list-style-position: inside; margin: 0 0 0 1em; }
#logmsg ul { text-indent: -1em; padding-left: 1em; }#logmsg ol { text-indent: -1.5em; padding-left: 1.5em; }
#logmsg > ul, #logmsg > ol { margin: 0 0 1em 0; }
#logmsg pre { background: #eee; padding: 1em; }
#logmsg blockquote { border: 1px solid #fa0; border-left-width: 10px; padding: 1em 1em 0 1em; background: white;}
#logmsg dl { margin: 0; }
#logmsg dt { font-weight: bold; }
#logmsg dd { margin: 0; padding: 0 0 0.5em 0; }
#logmsg dd:before { content:'\00bb';}
#logmsg table { border-spacing: 0px; border-collapse: collapse; border-top: 4px solid #fa0; border-bottom: 1px solid #fa0; background: #fff; }
#logmsg table th { text-align: left; font-weight: normal; padding: 0.2em 0.5em; border-top: 1px dotted #fa0; }
#logmsg table td { text-align: right; border-top: 1px dotted #fa0; padding: 0.2em 0.5em; }
#logmsg table thead th { text-align: center; border-bottom: 1px solid #fa0; }
#logmsg table th.Corner { text-align: left; }
#logmsg hr { border: none 0; border-top: 2px dashed #fa0; height: 1px; }
#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>
<div id="msg">
<dl class="meta">
<dt>Revision</dt> <dd><a href="http://core.trac.wordpress.org/changeset/28986">28986</a></dd>
<dt>Author</dt> <dd>wonderboymusic</dd>
<dt>Date</dt> <dd>2014-07-04 01:14:08 +0000 (Fri, 04 Jul 2014)</dd>
</dl>
<h3>Log Message</h3>
<pre>Optimize regexp usage in `wptexturize()` for a "3x Performance Boost."
Props miqrogroove.
See <a href="http://core.trac.wordpress.org/ticket/28724">#28724</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcwpincludesformattingphp">trunk/src/wp-includes/formatting.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcwpincludesformattingphp"></a>
<div class="modfile"><h4>Modified: trunk/src/wp-includes/formatting.php (28985 => 28986)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/src/wp-includes/formatting.php 2014-07-04 01:09:25 UTC (rev 28985)
+++ trunk/src/wp-includes/formatting.php 2014-07-04 01:14:08 UTC (rev 28986)
</span><span class="lines">@@ -96,11 +96,13 @@
</span><span class="cx"> $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
</span><span class="cx"> $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
</span><span class="cx">
</span><del>- $spaces = wp_spaces_regexp();
</del><span class="cx">
</span><del>-
</del><span class="cx"> // Pattern-based replacements of characters.
</span><ins>+ // Sort the remaining patterns into several arrays for performance tuning.
+ $dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
+ $dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
</ins><span class="cx"> $dynamic = array();
</span><ins>+ $spaces = wp_spaces_regexp();
</ins><span class="cx">
</span><span class="cx"> // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
</span><span class="cx"> if ( "'" !== $apos || "'" !== $closing_single_quote ) {
</span><span class="lines">@@ -115,10 +117,7 @@
</span><span class="cx"> $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
</span><span class="cx"> }
</span><span class="cx">
</span><del>- // Quoted Numbers like "42" or '42.00'
- if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
- $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $opening_quote . '$1' . $closing_quote;
- }
</del><ins>+ // Quoted Numbers like '0.42'
</ins><span class="cx"> if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
</span><span class="cx"> $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $opening_single_quote . '$1' . $closing_single_quote;
</span><span class="cx"> }
</span><span class="lines">@@ -133,16 +132,30 @@
</span><span class="cx"> $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos;
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+ // 9' (prime)
+ if ( "'" !== $prime ) {
+ $dynamic[ '/(?<=\d)\'/' ] = $prime;
+ }
+
+ // Single quotes followed by spaces or ending punctuation.
+ if ( "'" !== $closing_single_quote ) {
+ $dynamic[ '/\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $closing_single_quote;
+ }
+
+ $dynamic_characters['apos'] = array_keys( $dynamic );
+ $dynamic_replacements['apos'] = array_values( $dynamic );
+ $dynamic = array();
+
+ // Quoted Numbers like "42"
+ if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $opening_quote . '$1' . $closing_quote;
+ }
+
</ins><span class="cx"> // 9" (double prime)
</span><span class="cx"> if ( '"' !== $double_prime ) {
</span><span class="cx"> $dynamic[ '/(?<=\d)"/' ] = $double_prime;
</span><span class="cx"> }
</span><span class="cx">
</span><del>- // 9' (prime)
- if ( "'" !== $prime ) {
- $dynamic[ '/(?<=\d)\'/' ] = $prime;
- }
-
</del><span class="cx"> // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
</span><span class="cx"> if ( '"' !== $opening_quote ) {
</span><span class="cx"> $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
</span><span class="lines">@@ -152,20 +165,19 @@
</span><span class="cx"> if ( '"' !== $closing_quote ) {
</span><span class="cx"> $dynamic[ '/"/' ] = $closing_quote;
</span><span class="cx"> }
</span><del>-
- // Single quotes followed by spaces or ending punctuation.
- if ( "'" !== $closing_single_quote ) {
- $dynamic[ '/\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $closing_single_quote;
- }
-
</del><ins>+
+ $dynamic_characters['quote'] = array_keys( $dynamic );
+ $dynamic_replacements['quote'] = array_values( $dynamic );
+ $dynamic = array();
+
</ins><span class="cx"> // Dashes and spaces
</span><span class="cx"> $dynamic[ '/---/' ] = $em_dash;
</span><span class="cx"> $dynamic[ '/(?<=' . $spaces . ')--(?=' . $spaces . ')/' ] = $em_dash;
</span><span class="cx"> $dynamic[ '/(?<!xn)--/' ] = $en_dash;
</span><span class="cx"> $dynamic[ '/(?<=' . $spaces . ')-(?=' . $spaces . ')/' ] = $en_dash;
</span><span class="cx">
</span><del>- $dynamic_characters = array_keys( $dynamic );
- $dynamic_replacements = array_values( $dynamic );
</del><ins>+ $dynamic_characters['dash'] = array_keys( $dynamic );
+ $dynamic_replacements['dash'] = array_values( $dynamic );
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> // Must do this every time in case plugins use these filters in a context sensitive manner
</span><span class="lines">@@ -237,8 +249,17 @@
</span><span class="cx"> // This is neither a delimeter, nor is this content inside of no_texturize pairs. Do texturize.
</span><span class="cx">
</span><span class="cx"> $curl = str_replace( $static_characters, $static_replacements, $curl );
</span><del>- $curl = preg_replace( $dynamic_characters, $dynamic_replacements, $curl );
</del><span class="cx">
</span><ins>+ if ( false !== strpos( $curl, "'" ) ) {
+ $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
+ }
+ if ( false !== strpos( $curl, '"' ) ) {
+ $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
+ }
+ if ( false !== strpos( $curl, '-' ) ) {
+ $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
+ }
+
</ins><span class="cx"> // 9x9 (times), but never 0x9999
</span><span class="cx"> if ( 1 === preg_match( '/(?<=\d)x-?\d/', $curl ) ) {
</span><span class="cx"> // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
</span></span></pre>
</div>
</div>
</body>
</html>