<!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>[2168] 2013/frederickding/importer/trunk/class-wordpress-importer.php: Add attachment processing (verbatim) and use a stateful iterator for posts.</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/2168">2168</a></dd>
<dt>Author</dt> <dd>frederick.ding</dd>
<dt>Date</dt> <dd>2013-07-29 05:23:58 +0000 (Mon, 29 Jul 2013)</dd>
</dl>
<h3>Log Message</h3>
<pre>Add attachment processing (verbatim) and use a stateful iterator for posts.
- Currently using ArrayIterator that is stored between cron runs
- At the end of each foreach iteration in process_posts(), break if we're out
of time; see <a href="http://gsoc.trac.wordpress.org/ticket/327">#327</a></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 (2167 => 2168)</h4>
<pre class="diff"><span>
<span class="info">--- 2013/frederickding/importer/trunk/class-wordpress-importer.php 2013-07-29 05:23:49 UTC (rev 2167)
+++ 2013/frederickding/importer/trunk/class-wordpress-importer.php 2013-07-29 05:23:58 UTC (rev 2168)
</span><span class="lines">@@ -10,6 +10,7 @@
</span><span class="cx"> * @package WordPress
</span><span class="cx"> * @subpackage Importer
</span><span class="cx"> */
</span><ins>+require_once 'class-wxr-parser.php';
</ins><span class="cx">
</span><span class="cx"> class WordPress_Importer extends WP_Importer_Cron {
</span><span class="cx">
</span><span class="lines">@@ -274,6 +275,10 @@
</span><span class="cx"> * Performs post-import cleanup of files and the cache
</span><span class="cx"> */
</span><span class="cx"> public function do_cleanup() {
</span><ins>+ /*
+ * @todo remove this, which has to do with attachments and UI rather
+ * than actual importer logic
+ */
</ins><span class="cx"> wp_import_cleanup( $this->id );
</span><span class="cx">
</span><span class="cx"> wp_cache_flush();
</span><span class="lines">@@ -312,7 +317,7 @@
</span><span class="cx"> 'backfill_urls',
</span><span class="cx"> 'finish'
</span><span class="cx"> );
</span><del>-
</del><ins>+
</ins><span class="cx"> // if no step provided, advance to the next step
</span><span class="cx"> if ( empty( $step ) && ! empty( $this->wxr_file ) ) {
</span><span class="cx"> if ( empty( $this->progress[$this->wxr_file] ) ) {
</span><span class="lines">@@ -320,7 +325,7 @@
</span><span class="cx"> $step = $steps[0];
</span><span class="cx"> } else {
</span><span class="cx"> $step_index = array_search( $this->progress[$this->wxr_file], $steps );
</span><del>-
</del><ins>+
</ins><span class="cx"> // if currently on start step, fast forward 2 steps in total
</span><span class="cx"> if ( $step_index === 0 ) {
</span><span class="cx"> $step_index ++;
</span><span class="lines">@@ -335,7 +340,7 @@
</span><span class="cx"> __( 'Invalid step', 'wordpress-importer' ) );
</span><span class="cx"> }
</span><span class="cx"> $this->progress[$this->wxr_file] = $step;
</span><del>-
</del><ins>+
</ins><span class="cx"> return $step;
</span><span class="cx"> }
</span><span class="cx">
</span><span class="lines">@@ -669,7 +674,7 @@
</span><span class="cx"> esc_html( $term['term_name'] ), $id );
</span><span class="cx"> continue;
</span><span class="cx"> }
</span><del>- }
</del><ins>+ } // foreach
</ins><span class="cx">
</span><span class="cx"> unset( $this->terms );
</span><span class="cx"> $this->advance();
</span><span class="lines">@@ -680,7 +685,43 @@
</span><span class="cx"> *
</span><span class="cx"> * @todo
</span><span class="cx"> */
</span><del>- protected function process_attachment() {}
</del><ins>+ protected function process_attachment( $post, $url ) {
+ if ( ! $this->fetch_attachments )
+ return new WP_Error( 'attachment_processing_error',
+ __( 'Fetching attachments is not enabled', 'wordpress-importer' ) );
+
+ // if the URL is absolute, but does not contain address, then upload it assuming base_site_url
+ if ( preg_match( '|^/[\w\W]+$|', $url ) )
+ $url = rtrim( $this->base_url, '/' ) . $url;
+
+ $upload = $this->fetch_remote_file( $url, $post );
+ if ( is_wp_error( $upload ) )
+ return $upload;
+
+ if ( $info = wp_check_filetype( $upload['file'] ) )
+ $post['post_mime_type'] = $info['type'];
+ else
+ return new WP_Error( 'attachment_processing_error', __('Invalid file type', 'wordpress-importer') );
+
+ $post['guid'] = $upload['url'];
+
+ // as per wp-admin/includes/upload.php
+ $post_id = wp_insert_attachment( $post, $upload['file'] );
+ wp_update_attachment_metadata( $post_id, wp_generate_attachment_metadata( $post_id, $upload['file'] ) );
+
+ // remap resized image URLs, works by stripping the extension and remapping the URL stub.
+ if ( preg_match( '!^image/!', $info['type'] ) ) {
+ $parts = pathinfo( $url );
+ $name = basename( $parts['basename'], ".{$parts['extension']}" ); // PATHINFO_FILENAME in PHP 5.2
+
+ $parts_new = pathinfo( $upload['url'] );
+ $name_new = basename( $parts_new['basename'], ".{$parts_new['extension']}" );
+
+ $this->url_remap[$parts['dirname'] . '/' . $name] = $parts_new['dirname'] . '/' . $name_new;
+ }
+
+ return $post_id;
+ }
</ins><span class="cx">
</span><span class="cx"> /**
</span><span class="cx"> *
</span><span class="lines">@@ -698,9 +739,18 @@
</span><span class="cx"> * are imported for the last of the above.
</span><span class="cx"> */
</span><span class="cx"> protected function process_posts() {
</span><del>- $this->posts = apply_filters( 'wp_import_posts', $this->posts );
</del><ins>+ if($this->get_param('filtered_wp_import_posts', false) === false) {
+ // only filter once!
+ $this->posts = apply_filters( 'wp_import_posts', $this->posts );
+ $this->set_param('filtered_wp_import_posts', true);
+ }
</ins><span class="cx">
</span><del>- foreach ( $this->posts as $post ) {
</del><ins>+ // use an iterator object with which we can track state
+ if ( ! ($iterator = $this->get_param( 'process_posts_iterator', null )
+ instanceof ArrayIterator) )
+ $iterator = new ArrayIterator( $this->posts );
+
+ foreach ( $iterator as $post ) {
</ins><span class="cx"> $post = apply_filters( 'wp_import_post_data_raw', $post );
</span><span class="cx"> if ( ! post_type_exists( $post['post_type'] ) ) {
</span><span class="cx"> $this->warnings[] = new WP_Error(
</span><span class="lines">@@ -984,9 +1034,25 @@
</span><span class="cx"> }
</span><span class="cx"> }
</span><span class="cx"> }
</span><ins>+
+ // stop execution if we've reached the end of this cron run's
+ // limit
+ if ( ! $this->have_time() )
+ break;
+ } // foreach
+
+ // only unset after all posts have gone through the foreach
+ if(! $iterator->valid()) {
+ // done
+ $this->unset_param('process_posts_iterator');
+ unset( $this->posts );
+ $this->advance();
+ return true;
</ins><span class="cx"> }
</span><del>-
- unset( $this->posts );
</del><ins>+
+ // save the state of our iterator
+ $this->set_param('process_posts_iterator', $iterator);
+ return false;
</ins><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> /**
</span><span class="lines">@@ -1080,10 +1146,10 @@
</span><span class="cx"> public function get_warnings() {
</span><span class="cx"> return $this->warnings;
</span><span class="cx"> }
</span><del>-
</del><ins>+
</ins><span class="cx"> /**
</span><span class="cx"> * Retrieves the current step.
</span><del>- *
</del><ins>+ *
</ins><span class="cx"> * @return string|WP_Error
</span><span class="cx"> */
</span><span class="cx"> public function get_step() {
</span><span class="lines">@@ -1119,10 +1185,10 @@
</span><span class="cx">
</span><span class="cx"> return true;
</span><span class="cx"> }
</span><del>-
</del><ins>+
</ins><span class="cx"> /**
</span><span class="cx"> * Unsets a parameter.
</span><del>- *
</del><ins>+ *
</ins><span class="cx"> * @param string $name
</span><span class="cx"> * @return boolean|WP_Error
</span><span class="cx"> */
</span><span class="lines">@@ -1137,7 +1203,7 @@
</span><span class="cx"> $this->params[$this->wxr_file] = array();
</span><span class="cx"> elseif(key_exists($name, $this->params[$this->wxr_file]))
</span><span class="cx"> unset($this->params[$this->wxr_file][$name]);
</span><del>-
</del><ins>+
</ins><span class="cx"> return true;
</span><span class="cx"> }
</span><span class="cx">
</span></span></pre>
</div>
</div>
</body>
</html>