<!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>[4992] sites/trunk/wordpress.org/public_html/wp-content/plugins/plugin-directory/libs/site-search/jetpack-search.php: Plugin directory search: improve balancing of matches against translated vs English content as backup.</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" style="font-size: 105%">
<dt style="float: left; width: 6em; font-weight: bold">Revision</dt> <dd><a style="font-weight: bold" href="http://meta.trac.wordpress.org/changeset/4992">4992</a><script type="application/ld+json">{"@context":"http://schema.org","@type":"EmailMessage","description":"Review this Commit","action":{"@type":"ViewAction","url":"http://meta.trac.wordpress.org/changeset/4992","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>tellyworth</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2017-02-23 08:17:11 +0000 (Thu, 23 Feb 2017)</dd>
</dl>
<pre style='padding-left: 1em; margin: 2em 0; border-left: 2px solid #ccc; line-height: 1.25; font-size: 105%; font-family: sans-serif'>Plugin directory search: improve balancing of matches against translated vs English content as backup. Props @gibrown
Fixes <a href="http://meta.trac.wordpress.org/ticket/2425">#2425</a></pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#sitestrunkwordpressorgpublic_htmlwpcontentpluginsplugindirectorylibssitesearchjetpacksearchphp">sites/trunk/wordpress.org/public_html/wp-content/plugins/plugin-directory/libs/site-search/jetpack-search.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="sitestrunkwordpressorgpublic_htmlwpcontentpluginsplugindirectorylibssitesearchjetpacksearchphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: sites/trunk/wordpress.org/public_html/wp-content/plugins/plugin-directory/libs/site-search/jetpack-search.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- sites/trunk/wordpress.org/public_html/wp-content/plugins/plugin-directory/libs/site-search/jetpack-search.php 2017-02-23 05:53:57 UTC (rev 4991)
+++ sites/trunk/wordpress.org/public_html/wp-content/plugins/plugin-directory/libs/site-search/jetpack-search.php 2017-02-23 08:17:11 UTC (rev 4992)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -618,8 +618,67 @@
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> if ( $args['locale'] && $args['locale'] !== 'en' && $args['locale'] !== 'en_US' ) {
</span><span class="cx" style="display: block; padding: 0 10px"> $locale = $args['locale'];
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+
+ //Because most plugins don't have any translations we need to
+ // correct for the very low scores that locale-specific fields.
+ // end up getting. This is caused by the average field length being
+ // very close to zero and thus the BM25 alg discounts fields that are
+ // significantly longer.
+ //
+ // As of 2017-01-23 it looked like we were off by about 10,000x,
+ // so rather than 0.1 we use a much smaller multiplier of en content
+ $en_boost = 0.00001;
+ $matching_fields = array(
+ 'all_content_' . $locale,
+ 'all_content_en^' . $en_boost
+ );
+ $boost_phrase_fields = array(
+ 'title_' . $locale,
+ 'excerpt_' . $locale,
+ 'description_' . $locale,
+ 'title_en^' . $en_boost,
+ 'excerpt_en^' . $en_boost,
+ 'description_en^' . $en_boost,
+ 'taxonomy.plugin_tags.name',
+ );
+ $boost_ngram_fields = array(
+ 'title_' . $locale . '.ngram',
+ 'title_en.ngram^' . $en_boost
+ );
+ $boost_title_fields = array(
+ 'title_' . $locale,
+ 'title_en^' . $en_boost,
+ 'slug_text',
+ );
+ $boost_content_fields = array(
+ 'excerpt_' . $locale,
+ 'description_' . $locale,
+ 'excerpt_en^' . $en_boost,
+ 'description_en^' . $en_boost,
+ 'taxonomy.plugin_tags.name',
+ );
</ins><span class="cx" style="display: block; padding: 0 10px"> } else {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $locale = 'en';
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $matching_fields = array(
+ 'all_content_en'
+ );
+ $boost_phrase_fields = array(
+ 'title_en',
+ 'excerpt_en',
+ 'description_en',
+ 'taxonomy.plugin_tags.name',
+ );
+ $boost_ngram_fields = array(
+ 'title_en.ngram'
+ );
+ $boost_title_fields = array(
+ 'title_en',
+ 'slug_text',
+ );
+ $boost_content_fields = array(
+ 'excerpt_en',
+ 'description_en',
+ 'taxonomy.plugin_tags.name',
+ );
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> ///////////////////////////////////////////////////////////
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -634,7 +693,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> 'must' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'multi_match' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'query' => $args['query'],
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'fields' => 'all_content_' . $locale,
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 'fields' => $matching_fields,
</ins><span class="cx" style="display: block; padding: 0 10px"> 'boost' => 0.1,
</span><span class="cx" style="display: block; padding: 0 10px"> 'operator' => 'and',
</span><span class="cx" style="display: block; padding: 0 10px"> ),
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -643,12 +702,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'multi_match' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'query' => $args['query'],
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'fields' => array(
- 'title_' . $locale,
- 'excerpt_' . $locale,
- 'description_' . $locale,
- 'taxonomy.plugin_tags.name',
- ),
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 'fields' => $boost_phrase_fields,
</ins><span class="cx" style="display: block; padding: 0 10px"> 'type' => 'phrase',
</span><span class="cx" style="display: block; padding: 0 10px"> 'boost' => 2
</span><span class="cx" style="display: block; padding: 0 10px"> ),
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -656,9 +710,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'multi_match' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'query' => $args['query'],
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'fields' => array(
- 'title_' . $locale . '.ngram'
- ),
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 'fields' => $boost_ngram_fields,
</ins><span class="cx" style="display: block; padding: 0 10px"> 'type' => 'phrase',
</span><span class="cx" style="display: block; padding: 0 10px"> 'boost' => 0.2
</span><span class="cx" style="display: block; padding: 0 10px"> ),
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -666,10 +718,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'multi_match' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'query' => $args['query'],
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'fields' => array(
- 'title_' . $locale,
- 'slug_text',
- ),
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 'fields' => $boost_title_fields,
</ins><span class="cx" style="display: block; padding: 0 10px"> 'type' => 'best_fields',
</span><span class="cx" style="display: block; padding: 0 10px"> 'boost' => 2
</span><span class="cx" style="display: block; padding: 0 10px"> ),
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -677,11 +726,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'multi_match' => array(
</span><span class="cx" style="display: block; padding: 0 10px"> 'query' => $args['query'],
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- 'fields' => array(
- 'excerpt_' . $locale,
- 'description_' . $locale,
- 'taxonomy.plugin_tags.name',
- ),
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ 'fields' => $boost_content_fields,
</ins><span class="cx" style="display: block; padding: 0 10px"> 'type' => 'best_fields',
</span><span class="cx" style="display: block; padding: 0 10px"> 'boost' => 2
</span><span class="cx" style="display: block; padding: 0 10px"> ),
</span></span></pre>
</div>
</div>
</body>
</html>