<!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>[2176] 2013/frederickding/importer/trunk/class-wordpress-importer.php: Add URL backfill and featured images remapping; see #327.</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://gsoc.trac.wordpress.org/changeset/2176">2176</a></dd>
<dt>Author</dt> <dd>frederick.ding</dd>
<dt>Date</dt> <dd>2013-07-29 19:57:46 +0000 (Mon, 29 Jul 2013)</dd>
</dl>
<h3>Log Message</h3>
<pre>Add URL backfill and featured images remapping; see <a href="http://gsoc.trac.wordpress.org/ticket/327">#327</a>.
- URL backfill step will honour cron `$this->have_time()`; as of right now,
only `process_posts()` and `process_urls()` check for time left</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#2013frederickdingimportertrunkclasswordpressimporterphp">2013/frederickding/importer/trunk/class-wordpress-importer.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="2013frederickdingimportertrunkclasswordpressimporterphp"></a>
<div class="modfile"><h4>Modified: 2013/frederickding/importer/trunk/class-wordpress-importer.php (2175 => 2176)</h4>
<pre class="diff"><span>
<span class="info">--- 2013/frederickding/importer/trunk/class-wordpress-importer.php 2013-07-29 19:29:18 UTC (rev 2175)
+++ 2013/frederickding/importer/trunk/class-wordpress-importer.php 2013-07-29 19:57:46 UTC (rev 2176)
</span><span class="lines">@@ -299,6 +299,9 @@
</span><span class="cx"> case 'urls':
</span><span class="cx"> $this->process_urls();
</span><span class="cx"> break;
</span><ins>+ case 'featured_images':
+ $this->process_featured_images();
+ break;
</ins><span class="cx"> case 'finish':
</span><span class="cx"> default:
</span><span class="cx"> $done = true;
</span><span class="lines">@@ -361,6 +364,7 @@
</span><span class="cx"> 'posts',
</span><span class="cx"> 'parents',
</span><span class="cx"> 'urls',
</span><ins>+ 'featured_images',
</ins><span class="cx"> 'finish'
</span><span class="cx"> );
</span><span class="cx">
</span><span class="lines">@@ -1267,10 +1271,77 @@
</span><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> /**
</span><ins>+ * Remaps attachment URLs to the new location.
</ins><span class="cx"> *
</span><del>- * @todo
</del><ins>+ * @todo Use some form of WP_Relocate instead of directly querying SQL
+ * @global $wpdb
+ * @return boolean True if completed, false if the process must continue in
+ * the next cron run
</ins><span class="cx"> */
</span><span class="cx"> protected function process_urls() {
</span><ins>+ global $wpdb;
+
+ if ( $this->get_param( 'sorted_processed_url_remap', false ) === false ) {
+ // only sort once!
+ uksort( $this->processed_url_remap,
+ array(
+ get_class( $this ),
+ 'compare_strlen'
+ ) );
+ $this->set_param( 'sorted_processed_url_remap', true );
+ }
+
+ // use an iterator object with which we can track state
+ if ( ! ($iterator = $this->get_param( 'process_urls_iterator', null ) instanceof ArrayIterator) )
+ $iterator = new ArrayIterator( $this->processed_url_remap );
+
+ // make sure we do the longest urls first, in case one is a
+ // substring of another
+ foreach ( $iterator as $from_url => $to_url ) {
+ // remap urls in post_content
+ $wpdb->query(
+ $wpdb->prepare(
+ "UPDATE {$wpdb->posts} SET post_content = REPLACE(post_content, %s, %s)",
+ $from_url, $to_url ) );
+ // remap enclosure urls
+ $result = $wpdb->query(
+ $wpdb->prepare(
+ "UPDATE {$wpdb->postmeta} SET meta_value = REPLACE(meta_value, %s, %s) WHERE meta_key='enclosure'",
+ $from_url, $to_url ) );
+
+ // stop execution if we've reached the end of this cron run's
+ // limit
+ if ( ! $this->have_time() )
+ break;
+ }
+
+ // only unset after all posts have gone through the foreach
+ if ( ! $iterator->valid() ) {
+ // done
+ $this->unset_param( 'process_urls_iterator' );
+ $this->advance();
+ return true;
+ }
+
+ // save the state of our iterator
+ $this->set_param( 'process_urls_iterator', $iterator );
+ return false;
+ }
+
+ /**
+ * Updates _thumbnail_id meta to new, imported attachment IDs.
+ */
+ protected function process_featured_images() {
+ // cycle through posts that have a featured image
+ foreach ( $this->processed_featured_images as $post_id => $value ) {
+ if ( isset( $this->processed_posts[$value] ) ) {
+ $new_id = $this->processed_posts[$value];
+ // only update if there's a difference
+ if ( $new_id != $value )
+ update_post_meta( $post_id, '_thumbnail_id', $new_id );
+ }
+ }
+
</ins><span class="cx"> $this->advance();
</span><span class="cx"> return true;
</span><span class="cx"> }
</span><span class="lines">@@ -1525,4 +1596,15 @@
</span><span class="cx"> public function get_all_params () {
</span><span class="cx"> return $this->params;
</span><span class="cx"> }
</span><ins>+
+ /**
+ * Subtracts the lengths of two strings.
+ *
+ * @param string $a
+ * @param string $b
+ * @return int The difference in their lengths
+ */
+ static function compare_strlen( $a, $b ) {
+ return strlen( $b ) - strlen( $a );
+ }
</ins><span class="cx"> }
</span><span class="cx">\ No newline at end of file
</span></span></pre>
</div>
</div>
</body>
</html>