<!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>[BuddyPress][4989] trunk: Modifies bp_create_excerpt() to take account of HTML tag length when truncating long texts.</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://buddypress.trac.wordpress.org/changeset/4989">4989</a></dd>
<dt>Author</dt> <dd>boonebgorges</dd>
<dt>Date</dt> <dd>2011-08-16 11:33:09 +0000 (Tue, 16 Aug 2011)</dd>
</dl>
<h3>Log Message</h3>
<pre>Modifies bp_create_excerpt() to take account of HTML tag length when truncating long texts. Thanks to CakePHP for the function. Refactors BP use of bp_create_excerpt(), where necessary, to account for new function argument structure. Reworks bp_activity_truncate_entry() so that already-truncated activity items (like blog posts) do not get a Read More link when they contain HTML. Introduces fallback functions for some multibyte string functions, to make bp_create_excerpt() work properly. Thanks to MediaWiki for these fallbacks. Fixes <a href="http://buddypress.trac.wordpress.org/ticket/3452">#3452</a>. Props DJPaul for all the help with this patch.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunkbpactivitybpactivityfiltersphp">trunk/bp-activity/bp-activity-filters.php</a></li>
<li><a href="#trunkbpactivitybpactivitytemplatephp">trunk/bp-activity/bp-activity-template.php</a></li>
<li><a href="#trunkbpcorebpcoretemplatephp">trunk/bp-core/bp-core-template.php</a></li>
<li><a href="#trunkbpcorebpcorewpabstractionphp">trunk/bp-core/bp-core-wpabstraction.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunkbpactivitybpactivityfiltersphp"></a>
<div class="modfile"><h4>Modified: trunk/bp-activity/bp-activity-filters.php (4988 => 4989)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/bp-activity/bp-activity-filters.php 2011-08-15 20:02:37 UTC (rev 4988)
+++ trunk/bp-activity/bp-activity-filters.php 2011-08-16 11:33:09 UTC (rev 4989)
</span><span class="lines">@@ -188,13 +188,19 @@
</span><span class="cx">
</span><span class="cx"> $append_text = apply_filters( 'bp_activity_excerpt_append_text', __( '[Read more]', 'buddypress' ) );
</span><span class="cx"> $excerpt_length = apply_filters( 'bp_activity_excerpt_length', 358 );
</span><del>- $excerpt = $text;
</del><span class="cx">
</span><del>- $id = !empty( $activities_template->activity->current_comment->id ) ? 'acomment-read-more-' . $activities_template->activity->current_comment->id : 'activity-read-more-' . bp_get_activity_id();
</del><ins>+ // Run the text through the excerpt function. If it's too short, the original text will be
+ // returned.
+ $excerpt = bp_create_excerpt( $text, $excerpt_length, array( 'ending' => __( '&hellip;', 'buddypress' ) ) );
</ins><span class="cx">
</span><del>- if ( strlen( $excerpt ) > $excerpt_length )
- $excerpt = sprintf( '%1$s<span class="activity-read-more" id="%2$s"><a href="%3$s" rel="nofollow">%4$s</a></span>', bp_create_excerpt( $excerpt, $excerpt_length, true, '&hellip;' ), $id, bp_get_activity_thread_permalink(), $append_text );
</del><ins>+ // If the text returned by bp_create_excerpt() is different from the original text (ie it's
+ // been truncated), add the "Read More" link.
+ if ( $excerpt != $text ) {
+ $id = !empty( $activities_template->activity->current_comment->id ) ? 'acomment-read-more-' . $activities_template->activity->current_comment->id : 'activity-read-more-' . bp_get_activity_id();
</ins><span class="cx">
</span><ins>+ $excerpt = sprintf( '%1$s<span class="activity-read-more" id="%2$s"><a href="%3$s" rel="nofollow">%4$s</a></span>', $excerpt, $id, bp_get_activity_thread_permalink(), $append_text );
+ }
+
</ins><span class="cx"> return apply_filters( 'bp_activity_truncate_entry', $excerpt, $text, $append_text );
</span><span class="cx"> }
</span><span class="cx"> add_filter( 'bp_get_activity_content_body', 'bp_activity_truncate_entry', 5 );
</span></span></pre></div>
<a id="trunkbpactivitybpactivitytemplatephp"></a>
<div class="modfile"><h4>Modified: trunk/bp-activity/bp-activity-template.php (4988 => 4989)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/bp-activity/bp-activity-template.php 2011-08-15 20:02:37 UTC (rev 4988)
+++ trunk/bp-activity/bp-activity-template.php 2011-08-16 11:33:09 UTC (rev 4989)
</span><span class="lines">@@ -1536,7 +1536,7 @@
</span><span class="cx"> $title = substr( $title, 0, -1 );
</span><span class="cx">
</span><span class="cx"> if ( 'activity_update' == $activities_template->activity->type )
</span><del>- $title .= ': ' . strip_tags( ent2ncr( trim( convert_chars( bp_create_excerpt( $activities_template->activity->content, 70, true, " [&#133;]" ) ) ) ) );
</del><ins>+ $title .= ': ' . strip_tags( ent2ncr( trim( convert_chars( bp_create_excerpt( $activities_template->activity->content, 70, array( 'ending' => " [&#133;]" ) ) ) ) ) );
</ins><span class="cx">
</span><span class="cx"> return apply_filters( 'bp_get_activity_feed_item_title', $title );
</span><span class="cx"> }
</span></span></pre></div>
<a id="trunkbpcorebpcoretemplatephp"></a>
<div class="modfile"><h4>Modified: trunk/bp-core/bp-core-template.php (4988 => 4989)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/bp-core/bp-core-template.php 2011-08-15 20:02:37 UTC (rev 4988)
+++ trunk/bp-core/bp-core-template.php 2011-08-16 11:33:09 UTC (rev 4989)
</span><span class="lines">@@ -346,36 +346,142 @@
</span><span class="cx"> return apply_filters( 'bp_get_button', $button->contents, $args, $button );
</span><span class="cx"> }
</span><span class="cx">
</span><ins>+
</ins><span class="cx"> /**
</span><del>- * bp_create_excerpt()
</del><ins>+ * Truncates text.
</ins><span class="cx"> *
</span><del>- * Fakes an excerpt on any content. Will not truncate words.
</del><ins>+ * Cuts a string to the length of $length and replaces the last characters
+ * with the ending if the text is longer than length.
</ins><span class="cx"> *
</span><del>- * @package BuddyPress Core
- * @param $text str The text to create the excerpt from
- * @param $excerpt_length Minimum excerpt length, in characters
- * @param $filter_shortcodes When true, registered shortcodes (in square brackets) will be stripped
- * @param $append_text Be sure to include a leading space
- * @return str The excerpt text
</del><ins>+ * This function is borrowed from CakePHP v2.0, under the MIT license. See
+ * http://book.cakephp.org/view/1469/Text#truncate-1625
+ *
+ * ### Options:
+ *
+ * - `ending` Will be used as Ending and appended to the trimmed string
+ * - `exact` If false, $text will not be cut mid-word
+ * - `html` If true, HTML tags would be handled correctly
+ * - `filter_shortcodes` If true, shortcodes will be stripped before truncating
+ *
+ * @package BuddyPress
+ *
+ * @param string $text String to truncate.
+ * @param integer $length Length of returned string, including ellipsis.
+ * @param array $options An array of html attributes and options.
+ * @return string Trimmed string.
</ins><span class="cx"> */
</span><del>-function bp_create_excerpt( $text, $excerpt_length = 225, $filter_shortcodes = true, $append_text = ' [&hellip;]' ) { // Fakes an excerpt if needed
</del><ins>+function bp_create_excerpt( $text, $length = 225, $options = array() ) {
+ // Backward compatibility. The third argument used to be a boolean $filter_shortcodes
+ $filter_shortcodes_default = is_bool( $options ) ? $options : true;
+
+ $defaults = array(
+ 'ending' => __( ' [&hellip;]', 'buddypress' ),
+ 'exact' => false,
+ 'html' => true,
+ 'filter_shortcodes' => $filter_shortcodes_default
+ );
+ $r = wp_parse_args( $options, $defaults );
+ extract( $r );
+
+ // Save the original text, to be passed along to the filter
</ins><span class="cx"> $original_text = $text;
</span><del>- $text = str_replace( ']]>', ']]&gt;', $text );
</del><span class="cx">
</span><del>- $excerpt_length = apply_filters( 'bp_excerpt_length', $excerpt_length );
- $append_text = apply_filters( 'bp_excerpt_append_text', $append_text );
</del><ins>+ // Allow plugins to modify these values globally
+ $length = apply_filters( 'bp_excerpt_length', $length );
+ $ending = apply_filters( 'bp_excerpt_append_text', $ending );
</ins><span class="cx">
</span><ins>+ // Remove shortcodes if necessary
</ins><span class="cx"> if ( $filter_shortcodes )
</span><span class="cx"> $text = strip_shortcodes( $text );
</span><span class="cx">
</span><del>- preg_match( "%\s*((?:<[^>]+>)+\S*)\s*|\s+%s", $text, $matches, PREG_OFFSET_CAPTURE, $excerpt_length );
</del><ins>+ // When $html is true, the excerpt should be created without including HTML tags in the
+ // excerpt length
+ if ( $html ) {
+ // The text is short enough. No need to truncate
+ if ( mb_strlen( preg_replace( '/<.*?>/', '', $text ) ) <= $length ) {
+ return $text;
+ }
</ins><span class="cx">
</span><del>- if ( !empty( $matches ) ) {
- $pos = array_pop( array_pop( $matches ) );
- $text = substr( $text, 0, $pos ) . $append_text;
</del><ins>+ $totalLength = mb_strlen( strip_tags( $ending ) );
+ $openTags = array();
+ $truncate = '';
+
+ // Find all the tags and put them in a stack for later use
+ preg_match_all( '/(<\/?([\w+]+)[^>]*>)?([^<>]*)/', $text, $tags, PREG_SET_ORDER );
+ foreach ( $tags as $tag ) {
+ // Process tags that need to be closed
+ if ( !preg_match( '/img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param/s', $tag[2] ) ) {
+ if ( preg_match( '/<[\w]+[^>]*>/s', $tag[0] ) ) {
+ array_unshift( $openTags, $tag[2] );
+ } else if ( preg_match('/<\/([\w]+)[^>]*>/s', $tag[0], $closeTag ) ) {
+ $pos = array_search( $closeTag[1], $openTags );
+ if ( $pos !== false ) {
+ array_splice( $openTags, $pos, 1 );
+ }
+ }
+ }
+ $truncate .= $tag[1];
+
+ $contentLength = mb_strlen( preg_replace( '/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/i', ' ', $tag[3] ) );
+ if ( $contentLength + $totalLength > $length ) {
+ $left = $length - $totalLength;
+ $entitiesLength = 0;
+ if ( preg_match_all( '/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/i', $tag[3], $entities, PREG_OFFSET_CAPTURE ) ) {
+ foreach ( $entities[0] as $entity ) {
+ if ( $entity[1] + 1 - $entitiesLength <= $left ) {
+ $left--;
+ $entitiesLength += mb_strlen( $entity[0] );
+ } else {
+ break;
+ }
+ }
+ }
+
+ $truncate .= mb_substr( $tag[3], 0 , $left + $entitiesLength );
+ break;
+ } else {
+ $truncate .= $tag[3];
+ $totalLength += $contentLength;
+ }
+ if ( $totalLength >= $length ) {
+ break;
+ }
+ }
+ } else {
+ if ( mb_strlen( $text ) <= $length ) {
+ return $text;
+ } else {
+ $truncate = mb_substr( $text, 0, $length - mb_strlen( $ending ) );
+ }
</ins><span class="cx"> }
</span><span class="cx">
</span><del>- return apply_filters( 'bp_create_excerpt', $text, $original_text, $excerpt_length, $filter_shortcodes, $append_text );
</del><ins>+ // If $exact is false, we can't break on words
+ if ( !$exact ) {
+ $spacepos = mb_strrpos( $truncate, ' ' );
+ if ( isset( $spacepos ) ) {
+ if ( $html ) {
+ $bits = mb_substr( $truncate, $spacepos );
+ preg_match_all( '/<\/([a-z]+)>/', $bits, $droppedTags, PREG_SET_ORDER );
+ if ( !empty( $droppedTags ) ) {
+ foreach ( $droppedTags as $closingTag ) {
+ if ( !in_array( $closingTag[1], $openTags ) ) {
+ array_unshift( $openTags, $closingTag[1] );
+ }
+ }
+ }
+ }
+ $truncate = mb_substr( $truncate, 0, $spacepos );
+ }
+ }
+ $truncate .= $ending;
+
+ if ( $html ) {
+ foreach ( $openTags as $tag ) {
+ $truncate .= '</' . $tag . '>';
+ }
+ }
+
+ return apply_filters( 'bp_create_excerpt', $truncate, $original_text, $length, $options );
</ins><span class="cx"> }
</span><span class="cx"> add_filter( 'bp_create_excerpt', 'wp_trim_excerpt' );
</span><span class="cx"> add_filter( 'bp_create_excerpt', 'stripslashes_deep' );
</span></span></pre></div>
<a id="trunkbpcorebpcorewpabstractionphp"></a>
<div class="modfile"><h4>Modified: trunk/bp-core/bp-core-wpabstraction.php (4988 => 4989)</h4>
<pre class="diff"><span>
<span class="info">--- trunk/bp-core/bp-core-wpabstraction.php 2011-08-15 20:02:37 UTC (rev 4988)
+++ trunk/bp-core/bp-core-wpabstraction.php 2011-08-16 11:33:09 UTC (rev 4989)
</span><span class="lines">@@ -26,7 +26,7 @@
</span><span class="cx"> return get_option( $option_name, $default );
</span><span class="cx"> }
</span><span class="cx"> }
</span><del>-
</del><ins>+
</ins><span class="cx"> if ( !function_exists( 'update_blog_option' ) ) {
</span><span class="cx"> function update_blog_option( $blog_id, $option_name, $value ) {
</span><span class="cx"> return update_option( $option_name, $value );
</span><span class="lines">@@ -73,4 +73,84 @@
</span><span class="cx"> else
</span><span class="cx"> return "{$prefix}spam = 0 AND {$prefix}deleted = 0 AND {$prefix}user_status = 0";
</span><span class="cx"> }
</span><ins>+
+/**
+ * Multibyte encoding fallback functions
+ *
+ * The PHP multibyte encoding extension is not enabled by default. In cases where it is not enabled,
+ * these functions provide a fallback.
+ *
+ * Borrowed from MediaWiki, under the GPLv2. Thanks!
+ */
+if ( !function_exists( 'mb_strlen' ) ) {
+ /**
+ * Fallback implementation of mb_strlen, hardcoded to UTF-8.
+ * @param string $str
+ * @param string $enc optional encoding; ignored
+ * @return int
+ */
+ function mb_strlen( $str, $enc = '' ) {
+ $counts = count_chars( $str );
+ $total = 0;
+
+ // Count ASCII bytes
+ for( $i = 0; $i < 0x80; $i++ ) {
+ $total += $counts[$i];
+ }
+
+ // Count multibyte sequence heads
+ for( $i = 0xc0; $i < 0xff; $i++ ) {
+ $total += $counts[$i];
+ }
+ return $total;
+ }
+}
+
+if ( !function_exists( 'mb_strpos' ) ) {
+ /**
+ * Fallback implementation of mb_strpos, hardcoded to UTF-8.
+ * @param $haystack String
+ * @param $needle String
+ * @param $offset String: optional start position
+ * @param $encoding String: optional encoding; ignored
+ * @return int
+ */
+ function mb_strpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
+ $needle = preg_quote( $needle, '/' );
+
+ $ar = array();
+ preg_match( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
+
+ if( isset( $ar[0][1] ) ) {
+ return $ar[0][1];
+ } else {
+ return false;
+ }
+ }
+}
+
+if ( !function_exists( 'mb_strrpos' ) ) {
+ /**
+ * Fallback implementation of mb_strrpos, hardcoded to UTF-8.
+ * @param $haystack String
+ * @param $needle String
+ * @param $offset String: optional start position
+ * @param $encoding String: optional encoding; ignored
+ * @return int
+ */
+ function mb_strrpos( $haystack, $needle, $offset = 0, $encoding = '' ) {
+ $needle = preg_quote( $needle, '/' );
+
+ $ar = array();
+ preg_match_all( '/' . $needle . '/u', $haystack, $ar, PREG_OFFSET_CAPTURE, $offset );
+
+ if( isset( $ar[0] ) && count( $ar[0] ) > 0 &&
+ isset( $ar[0][count( $ar[0] ) - 1][1] ) ) {
+ return $ar[0][count( $ar[0] ) - 1][1];
+ } else {
+ return false;
+ }
+ }
+}
+
</ins><span class="cx"> ?>
</span><span class="cx">\ No newline at end of file
</span></span></pre>
</div>
</div>
</body>
</html>