<!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>[12483] sites/trunk/api.wordpress.org/public_html/dotorg/helpscout/common.php: HelpScout: When parsing bounce emails, check in the attachments (which is likely the original email) when no emails within the body content match a WordPress.org account.</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 { white-space: pre-line; 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/12483">12483</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/12483","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>dd32</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2023-03-20 01:17:16 +0000 (Mon, 20 Mar 2023)</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'>HelpScout: When parsing bounce emails, check in the attachments (which is likely the original email) when no emails within the body content match a WordPress.org account.</pre>

<h3>Modified Paths</h3>
<ul>
<li><a href="#sitestrunkapiwordpressorgpublic_htmldotorghelpscoutcommonphp">sites/trunk/api.wordpress.org/public_html/dotorg/helpscout/common.php</a></li>
</ul>

</div>
<div id="patch">
<h3>Diff</h3>
<a id="sitestrunkapiwordpressorgpublic_htmldotorghelpscoutcommonphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: sites/trunk/api.wordpress.org/public_html/dotorg/helpscout/common.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- sites/trunk/api.wordpress.org/public_html/dotorg/helpscout/common.php     2023-03-17 14:53:39 UTC (rev 12482)
+++ sites/trunk/api.wordpress.org/public_html/dotorg/helpscout/common.php       2023-03-20 01:17:16 UTC (rev 12483)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -42,26 +42,34 @@
</span><span class="cx" style="display: block; padding: 0 10px">  * Caching wrapper around the HelpScout conversation API.
</span><span class="cx" style="display: block; padding: 0 10px">  */
</span><span class="cx" style="display: block; padding: 0 10px"> function get_email_thread( $thread_id, $force = false ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        wp_cache_add_global_groups( 'helpscout-thread' );
-
</del><span class="cx" style="display: block; padding: 0 10px">         if ( ! $thread_id ) {
</span><span class="cx" style="display: block; padding: 0 10px">                return false;
</span><span class="cx" style="display: block; padding: 0 10px">        }
</span><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        $client    = get_client();
-       $cache_key = "{$client->name}:{$thread_id}";
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ return cached_helpscout_get( '/v2/conversations/' . $thread_id . '?embed=threads', $force );
+}
</ins><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        if ( $thread = wp_cache_get( $cache_key, 'helpscout-thread' ) ) {
-               if ( ! $force ) {
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+/**
+ * Caching wrapper around the HelpScout GET API.
+ *
+ * TODO: This should probably be moved to the MU plugin.
+ */
+function cached_helpscout_get( $url, $force = false, $instance = false ) {
+       wp_cache_add_global_groups( 'helpscout-cache' );
+       $client    = get_client( $instance );
+       $cache_key = "{$client->name}:" . sha1( $url );
+
+       if ( $data = wp_cache_get( $cache_key, 'helpscout-cache' ) ) {
+               if ( ! $data ) {
</ins><span class="cx" style="display: block; padding: 0 10px">                         return $thread;
</span><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><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        $email_obj = $client->get( '/v2/conversations/' . $thread_id . '?embed=threads' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ $data = $client->get( $url );
</ins><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        wp_cache_set( $cache_key, $email_obj, 'helpscout-thread', 6 * HOUR_IN_SECONDS );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ wp_cache_set( $cache_key, $data, 'helpscout-cache', 6 * HOUR_IN_SECONDS );
</ins><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-        return $email_obj;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ return $data;
</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">@@ -117,6 +125,8 @@
</span><span class="cx" style="display: block; padding: 0 10px">                        // Fetch the email.
</span><span class="cx" style="display: block; padding: 0 10px">                        $email_obj = get_email_thread( $request->ticket->id ?? 0 );
</span><span class="cx" style="display: block; padding: 0 10px">                        if ( ! empty( $email_obj->_embedded->threads ) ) {
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+                                $attachment_api_urls = [];
+
</ins><span class="cx" style="display: block; padding: 0 10px">                                 foreach ( $email_obj->_embedded->threads as $thread ) {
</span><span class="cx" style="display: block; padding: 0 10px">                                        if ( 'customer' !== $thread->type ) {
</span><span class="cx" style="display: block; padding: 0 10px">                                                continue;
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -124,25 +134,37 @@
</span><span class="cx" style="display: block; padding: 0 10px"> 
</span><span class="cx" style="display: block; padding: 0 10px">                                        // Extract emails from the mailer-daemon.
</span><span class="cx" style="display: block; padding: 0 10px">                                        $email_body = strip_tags( str_replace( '<br>', "\n", $thread->body ) );
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+                                        $user       = get_user_from_emails( extract_emails_from_text( $email_body ) );
+                                       if ( $user ) {
+                                               break;
+                                       }
</ins><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-                                        // Extract `To:`, `X-Orig-To:`, and fallback to all emails.
-                                       $emails = [];
-                                       if ( preg_match( '!^(x-orig-to:|to:|Final-Recipient:(\s*rfc\d+;)?)\s*(?P<email>.+@.+)$!im', $email_body, $m ) ) {
-                                               $m['email'] = str_replace( [ '&lt;', '&gt;' ], '', $m['email'] );
-                                               $m['email'] = trim( $m['email'], '<> ' );
-
-                                               $emails = [ $m['email'] ];
-                                       } else {
-                                               // Ugly regex for emails, but it's good for mailer-daemon emails.
-                                               if ( preg_match_all( '![^\s;"]+@[^\s;&"]+\.[^\s;&"]+[a-z]!', $email_body, $m ) ) {
-                                                       $emails = array_unique( array_diff( $m[0], [ $request->mailbox->email ] ) );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+                                 // Track the attachments too, sometimes the email included in the body of the email is a final forwarded destination, but the attachment contains the real email.
+                                       foreach ( $thread->_embedded->attachments ?? [] as $attachment ) {
+                                               if (
+                                                       ! $attachment->width && // Exclude imagey attachments.
+                                                       $attachment->size < 100 * KB_IN_BYTES &&
+                                                       (
+                                                               str_contains( $attachment->mimeType, 'message' ) ||
+                                                               str_contains( $attachment->mimeType, 'text' ) ||
+                                                               str_contains( $attachment->mimeType, 'rfc' )
+                                                       )
+                                               ) {
+                                                       $attachment_api_urls[] = $attachment->_links->data->href;
</ins><span class="cx" style="display: block; padding: 0 10px">                                                 }
</span><span class="cx" style="display: block; padding: 0 10px">                                        }
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+                                }
</ins><span class="cx" style="display: block; padding: 0 10px"> 
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">-                                        foreach ( $emails as $maybe_email ) {
-                                               $user = get_user_by( 'email', $maybe_email );
-                                               if ( $user ) {
-                                                       break;
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+                         // If we didn't find a user, try to extract the email from the attachments (Which is likely the original email)
+                               if ( ! $user && $attachment_api_urls ) {
+                                       foreach ( $attachment_api_urls as $attachment_api_url ) {
+                                               $data = cached_helpscout_get( $attachment_api_url )->data ?? '';
+                                               if ( $data ) {
+                                                       $data = base64_decode( $data ) ?: $data;
+                                                       $user = get_user_from_emails( extract_emails_from_text( $data ) );
+                                                       if ( $user ) {
+                                                               break;
+                                                       }
</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">@@ -153,6 +175,50 @@
</span><span class="cx" style="display: block; padding: 0 10px">        return $user->user_email ?? $email;
</span><span class="cx" style="display: block; padding: 0 10px"> }
</span><span class="cx" style="display: block; padding: 0 10px"> 
</span><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+/**
+ * Extract email-like strings from a string.
+ *
+ * @param string $text The text to look in.
+ * @return array
+ */
+function extract_emails_from_text( $text ) {
+       // Extract `To:`, `X-Orig-To:`, and fallback to all emails.
+       $emails = [];
+       if ( preg_match( '!^(x-orig-to:|to:|Final-Recipient:(\s*rfc\d+;)?)\s*(?P<email>.+@.+)$!im', $text, $m ) ) {
+               $m['email'] = str_replace( [ '&lt;', '&gt;' ], '', $m['email'] );
+               $m['email'] = trim( $m['email'], '<> ' );
+
+               $emails = [ $m['email'] ];
+       } else {
+               // Ugly regex for emails, but it's good for mailer-daemon emails.
+               if ( preg_match_all( '![^\s;"]+@[^\s;&"]+\.[^\s;&"]+[a-z]!', $text, $m ) ) {
+                       $emails = array_unique( array_diff( $m[0], [ $request->mailbox->email ] ) );
+               }
+       }
+
+       return $emails;
+}
+
+/**
+ * Given a list of emails, find the first user that matches.
+ *
+ * @param array $emails The list of emails to check.
+ * @return WP_User|false
+ */
+function get_user_from_emails( $emails ) {
+       foreach ( $emails as $maybe_email ) {
+               $user = get_user_by( 'email', $maybe_email );
+               if ( $user ) {
+                       return $user;
+               }
+       }
+
+       return false;
+}
+
+/**
+ * Get the possible plugins or themes from the email.
+ */
</ins><span class="cx" style="display: block; padding: 0 10px"> function get_plugin_or_theme_from_email( $request ) {
</span><span class="cx" style="display: block; padding: 0 10px">        $subject = $request->ticket->subject ?? '';
</span><span class="cx" style="display: block; padding: 0 10px"> 
</span></span></pre>
</div>
</div>

</body>
</html>