<!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>[23804] trunk/wp-includes: Extract chats as structured data.</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, #logmsg > ol { margin-left: 0; 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/23804">23804</a></dd>
<dt>Author</dt> <dd>markjaquith</dd>
<dt>Date</dt> <dd>2013-03-27 08:31:12 +0000 (Wed, 27 Mar 2013)</dd>
</dl>
<h3>Log Message</h3>
<pre>Extract chats as structured data.
* add_chat_detection_format() ?\226?\128?\148 to add a chat regex pattern
* get_content_chat() ?\226?\128?\148 to grab a chat from content
* get_the_chat() ?\226?\128?\148 grab the chat from the current (or passed) post
* the_chat() ?\226?\128?\148 output the chat in formatted HTML
* paginate_content() ?\226?\128?\148 puts the <!--nextpage--> splitting stuff into a function
* get_paged_content() ?\226?\128?\148 grabs a page of raw content, needed to paginate chats properly
see <a href="http://core.trac.wordpress.org/ticket/23625">#23625</a>. props wonderboymusic, lancewillett.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunkwpincludespostformatsphp">trunk/wp-includes/post-formats.php</a></li>
<li><a href="#trunkwpincludesqueryphp">trunk/wp-includes/query.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkwpincludespostformatsphp"></a>
<div class="modfile"><h4>Modified: trunk/wp-includes/post-formats.php (23803 => 23804)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/wp-includes/post-formats.php 2013-03-27 05:11:41 UTC (rev 23803)
+++ trunk/wp-includes/post-formats.php 2013-03-27 08:31:12 UTC (rev 23804)
</span><span class="lines">@@ -392,6 +392,219 @@
</span><span class="cx"> }
</span><span class="cx">
</span><span class="cx"> /**
</span><ins>+ * Add chat detection support to the `get_content_chat()` chat parser
+ *
+ * @since 3.6.0
+ *
+ * @global array $_wp_chat_parsers
+ * @param string $name Unique identifier for chat format. Example: IRC
+ * @param string $newline_regex RegEx to match the start of a new line, typically when a new "username:" appears
+ * The parser will handle up to 3 matched expressions
+ * $matches[0] = the string before the user's message starts
+ * $matches[1] = the time of the message, if present
+ * $matches[2] = the author/username
+ * OR
+ * $matches[0] = the string before the user's message starts
+ * $matches[1] = the author/username
+ * @param string $delimiter_regex RegEx to determine where to split the username syntax from the chat message
+ */
+function add_chat_detection_format( $name, $newline_regex, $delimiter_regex ) {
+ global $_wp_chat_parsers;
+
+ if ( empty( $_wp_chat_parsers ) )
+ $_wp_chat_parsers = array();
+
+ $_wp_chat_parsers = array( $name => array( $newline_regex, $delimiter_regex ) ) + $_wp_chat_parsers;
+}
+add_chat_detection_format( 'IM', '#^([^:]+):#', '#[:]#' );
+add_chat_detection_format( 'Skype', '#^(\[.+?\])\s([^:]+):#', '#[:]#' );
+
+/**
+ * Deliberately interpret passed content as a chat transcript that is optionally
+ * followed by commentary
+ *
+ * If the content does not contain username syntax, assume that it does not contain
+ * chat logs and return
+ *
+ * @since 3.6.0
+ *
+ * Example:
+ *
+ * One stanza of chat:
+ * Scott: Hey, let's chat!
+ * Helen: No.
+ *
+ * $stanzas = array(
+ * array(
+ * array(
+ * 'time' => '',
+ * 'author' => 'Scott',
+ * 'messsage' => "Hey, let's chat!"
+ * ),
+ * array(
+ * 'time' => '',
+ * 'author' => 'Helen',
+ * 'message' => 'No.'
+ * )
+ * )
+ * )
+ * @param string $content A string which might contain chat data.
+ * @param boolean $remove Whether to remove the found data from the passed content.
+ * @return array A chat log as structured data
+ */
+function get_content_chat( &$content, $remove = false ) {
+ global $_wp_chat_parsers;
+
+ $trimmed = trim( $content );
+ if ( empty( $trimmed ) )
+ return array();
+
+ $has_match = false;
+ $matched_parser = false;
+ foreach ( $_wp_chat_parsers as $parser ) {
+ @list( $newline_regex ) = $parser;
+ if ( preg_match( $newline_regex, $trimmed ) ) {
+ $has_match = true;
+ $matched_parser = $parser;
+ break;
+ }
+ }
+
+ if ( false === $matched_parser )
+ return array();
+
+ @list( $newline_regex, $delimiter_regex ) = $parser;
+
+ $last_index = 0;
+ $stanzas = array();
+ $lines = explode( "\n", make_clickable( $trimmed ) );
+
+ $author = $time = '';
+ $data = array();
+ $stanza = array();
+
+ foreach ( $lines as $index => $line ) {
+ $line = trim( $line );
+
+ if ( empty( $line ) ) {
+ if ( ! empty( $author ) ) {
+ $stanza[] = array(
+ 'time' => $time,
+ 'author' => $author,
+ 'message' => join( ' ', $data )
+ );
+ }
+
+ $stanzas[] = $stanza;
+ $last_index = $index;
+ $stanza = array();
+ $author = $time = '';
+ $data = array();
+ if ( ! empty( $lines[$index + 1] ) && ! preg_match( $delimiter_regex, $lines[$index + 1] ) )
+ break;
+ }
+
+ $matches = array();
+ $matched = preg_match( $newline_regex, $line, $matches );
+ $author_match = empty( $matches[2] ) ? $matches[1] : $matches[2];
+ // assume username syntax if no whitespace is present
+ $no_ws = $matched && ! preg_match( '#\s#', $author_match );
+ // allow script-like stanzas
+ $has_ws = $matched && preg_match( '#\s#', $author_match ) && empty( $lines[$index + 1] ) && empty( $lines[$index - 1] );
+ if ( $matched && ( ! empty( $matches[2] ) || ( $no_ws || $has_ws ) ) ) {
+ if ( ! empty( $author ) ) {
+ $stanza[] = array(
+ 'time' => $time,
+ 'author' => $author,
+ 'message' => join( ' ', $data )
+ );
+ $data = array();
+ }
+
+ $time = empty( $matches[2] ) ? '' : $matches[1];
+ $author = $author_match;
+ $data[] = trim( str_replace( $matches[0], '', $line ) );
+ } elseif ( preg_match( '#\S#', $line ) ) {
+ $data[] = $line;
+ }
+ }
+
+ if ( ! empty( $author ) ) {
+ $stanza[] = array(
+ 'time' => $time,
+ 'author' => $author,
+ 'message' => trim( join( ' ', $data ) )
+ );
+ }
+
+ if ( ! empty( $stanza ) )
+ $stanzas[] = $stanza;
+
+ if ( $remove )
+ $content = trim( join( "\n", array_slice( $lines, $last_index ) ) );
+
+ return $stanzas;
+}
+
+/**
+ * Retrieve structured chat data from the current or passed post
+ *
+ * @since 3.6.0
+ *
+ * @param int $id Optional. Post ID
+ * @return array
+ */
+function get_the_chat( $id = 0 ) {
+ $post = empty( $id ) ? clone get_post() : get_post( $id );
+ if ( empty( $post ) )
+ return array();
+
+ $data = get_content_chat( get_paged_content( $post->post_content ) );
+ if ( empty( $data ) )
+ return array();
+
+ return $data;
+}
+
+/**
+ * Output HTML for a given chat's structured data. Themes can use this as a
+ * template tag in place of the_content() for Chat post format templates.
+ *
+ * @since 3.6.0
+ *
+ * @uses get_the_chat()
+ *
+ * @print HTML
+ */
+function the_chat() {
+ $output = '<dl class="chat-transcript">';
+
+ $stanzas = get_the_chat();
+
+ foreach ( $stanzas as $stanza ) {
+ foreach ( $stanza as $row ) {
+ $time = '';
+ if ( ! empty( $row['time'] ) )
+ $time = sprintf( '<time>%s</time>', esc_html( $row['time'] ) );
+
+ $output .= sprintf(
+ '<dt class="chat-author chat-author-%1$s vcard">%2$s <cite class="fn">%3$s</cite>: </dt>
+ <dd class="chat-text">%4$s</dd>
+ ',
+ esc_attr( strtolower( $row['author'] ) ), // Slug.
+ $time,
+ esc_html( $row['author'] ),
+ esc_html( $row['message'] )
+ );
+ }
+ }
+
+ $output .= '</dl><!-- .chat-transcript -->';
+
+ echo $output;
+}
+
+/**
</ins><span class="cx"> * Extract a URL from passed content, if possible
</span><span class="cx"> * Checks for a URL on the first line of the content or the first encountered href attribute.
</span><span class="cx"> *
</span></span></pre></div>
<a id="trunkwpincludesqueryphp"></a>
<div class="modfile"><h4>Modified: trunk/wp-includes/query.php (23803 => 23804)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/wp-includes/query.php 2013-03-27 05:11:41 UTC (rev 23803)
+++ trunk/wp-includes/query.php 2013-03-27 08:31:12 UTC (rev 23804)
</span><span class="lines">@@ -3621,8 +3621,53 @@
</span><span class="cx"> exit;
</span><span class="cx"> endif;
</span><span class="cx"> }
</span><ins>+/**
+ * Split the passed content by <!--nextpage-->
+ *
+ * @since 3.6.0
+ *
+ * @param string $content Content to split
+ * @return array Paged content
+ */
+function paginate_content( $content ) {
+ $content = str_replace( "\n<!--nextpage-->\n", '<!--nextpage-->', $content );
+ $content = str_replace( "\n<!--nextpage-->", '<!--nextpage-->', $content );
+ $content = str_replace( "<!--nextpage-->\n", '<!--nextpage-->', $content );
+ return explode( '<!--nextpage-->', $content);
+}
</ins><span class="cx">
</span><span class="cx"> /**
</span><ins>+ * Return content offset by $page
+ *
+ * @since 3.6.0
+ *
+ * @param string $content
+ * @return string
+ */
+function get_paged_content( $content = null, $paged = null ) {
+ global $page;
+ if ( empty( $page ) )
+ $page = 1;
+
+ if ( empty( $paged ) )
+ $paged = $page;
+
+ if ( empty( $content ) ) {
+ $post = get_post();
+ if ( empty( $post ) )
+ return;
+
+ $content = $post->post_content;
+ }
+
+ $pages = paginate_content( $content );
+ if ( isset( $pages[$paged - 1] ) )
+ return $pages[$paged - 1];
+
+ return reset( $pages );
+}
+
+/**
</ins><span class="cx"> * Set up global post data.
</span><span class="cx"> *
</span><span class="cx"> * @since 1.5.0
</span></span></pre>
</div>
</div>
</body>
</html>