<!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][9962] trunk: Improve the HTML-handling logic of `bp_create_excerpt()`.</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" style="font-size: 105%">
<dt style="float: left; width: 6em; font-weight: bold">Revision</dt> <dd><a style="font-weight: bold" href="http://buddypress.trac.wordpress.org/changeset/9962">9962</a><script type="application/ld+json">{"@context":"http://schema.org","@type":"EmailMessage","description":"Review this Commit","action":{"@type":"ViewAction","url":"http://buddypress.trac.wordpress.org/changeset/9962","name":"Review Commit"}}</script></dd>
<dt style="float: left; width: 6em; font-weight: bold">Author</dt> <dd>boonebgorges</dd>
<dt style="float: left; width: 6em; font-weight: bold">Date</dt> <dd>2015-06-23 13:42:40 +0000 (Tue, 23 Jun 2015)</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'>Improve the HTML-handling logic of `bp_create_excerpt()`.
* The regular expression that detects tags should be less generous, to avoid false matches.
* Word boundary detection, as used when `exact=false`, should never return a space character inside of an HTML tag (such as the space in `<a href="http://example.com">`).
These changes fix some tag-parsing issues introduced in <a href="http://buddypress.trac.wordpress.org/changeset/9523">[9523]</a>.
Fixes <a href="http://buddypress.trac.wordpress.org/ticket/6517">#6517</a>.</pre>
<h3>Modified Paths</h3>
<ul>
<li><a href="#trunksrcbpcorebpcoretemplatephp">trunk/src/bp-core/bp-core-template.php</a></li>
<li><a href="#trunktestsphpunittestcasescoretemplatebpCreateExcerptphp">trunk/tests/phpunit/testcases/core/template/bpCreateExcerpt.php</a></li>
</ul>
</div>
<div id="patch">
<h3>Diff</h3>
<a id="trunksrcbpcorebpcoretemplatephp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/src/bp-core/bp-core-template.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/src/bp-core/bp-core-template.php 2015-06-22 19:17:05 UTC (rev 9961)
+++ trunk/src/bp-core/bp-core-template.php 2015-06-23 13:42:40 UTC (rev 9962)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -813,7 +813,7 @@
</span><span class="cx" style="display: block; padding: 0 10px"> $truncate = '';
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> // Find all the tags and HTML comments and put them in a stack for later use
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- preg_match_all( '/(<\/?([\w!].+?)[^>]*>)?([^<>]*)/', $text, $tags, PREG_SET_ORDER );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ preg_match_all( '/(<\/?([\w+!]+)[^>]*>)?([^<>]*)/', $text, $tags, PREG_SET_ORDER );
</ins><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> foreach ( $tags as $tag ) {
</span><span class="cx" style="display: block; padding: 0 10px"> // Process tags that need to be closed
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -865,7 +865,35 @@
</span><span class="cx" style="display: block; padding: 0 10px">
</span><span class="cx" style="display: block; padding: 0 10px"> // If $exact is false, we can't break on words
</span><span class="cx" style="display: block; padding: 0 10px"> if ( empty( $r['exact'] ) ) {
</span><del style="background-color: #fdd; text-decoration:none; display:block; padding: 0 10px">- $spacepos = mb_strrpos( $truncate, ' ' );
</del><ins style="background-color: #dfd; text-decoration:none; display:block; padding: 0 10px">+ // Find the position of the last space character not part of a tag.
+ preg_match_all( '/<[a-z\!\/][^>]*>/', $truncate, $truncate_tags, PREG_OFFSET_CAPTURE );
+ $rtruncate = strrev( $truncate );
+ $spacepos = false;
+ for ( $i = strlen( $rtruncate ) - 1; $i >= 0; $i-- ) {
+ if ( ' ' !== $rtruncate[ $i ] ) {
+ continue;
+ }
+
+ // Convert rpos to negative offset on forward-facing string.
+ $pos = -1 - $i;
+
+ // If there are no tags in the string, the first space found is the right one.
+ if ( empty( $truncate_tags[0] ) ) {
+ $spacepos = $pos;
+ break;
+ }
+
+ // Look at each tag to see if the space is inside of it.
+ foreach ( $truncate_tags[0] as $truncate_tag ) {
+ $start = $truncate_tag[1];
+ $end = $start + strlen( $truncate_tag[0] );
+ if ( $pos > $start && $pos < $end ) {
+ $spacepos = $pos;
+ break 2;
+ }
+ }
+ }
+
</ins><span class="cx" style="display: block; padding: 0 10px"> if ( false !== $spacepos ) {
</span><span class="cx" style="display: block; padding: 0 10px"> if ( $r['html'] ) {
</span><span class="cx" style="display: block; padding: 0 10px"> $bits = mb_substr( $truncate, $spacepos );
</span></span></pre></div>
<a id="trunktestsphpunittestcasescoretemplatebpCreateExcerptphp"></a>
<div class="modfile"><h4 style="background-color: #eee; color: inherit; margin: 1em 0; padding: 1.3em; font-size: 115%">Modified: trunk/tests/phpunit/testcases/core/template/bpCreateExcerpt.php</h4>
<pre class="diff"><span>
<span class="info" style="display: block; padding: 0 10px; color: #888">--- trunk/tests/phpunit/testcases/core/template/bpCreateExcerpt.php 2015-06-22 19:17:05 UTC (rev 9961)
+++ trunk/tests/phpunit/testcases/core/template/bpCreateExcerpt.php 2015-06-23 13:42:40 UTC (rev 9962)
</span><span class="lines" style="display: block; padding: 0 10px; color: #888">@@ -61,4 +61,17 @@
</span><span class="cx" style="display: block; padding: 0 10px"> 'ending' => '',
</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">+
+ /**
+ * @ticket BP6517
+ */
+ public function test_string_should_not_be_cut_mid_tag_when_exact_is_false() {
+ $text = '<p><span>Foo</span> <a href="http://example.com">Bar</a> Baz.</p><p>Foo Bar Baz</p>';
+ $actual = bp_create_excerpt( $text, 7, array(
+ 'html' => true,
+ 'ending' => '',
+ 'exact' => false,
+ ) );
+ $this->assertSame( '<p><span>Foo</span> <a href="http://example.com">Bar</a></p>', $actual );
+ }
</ins><span class="cx" style="display: block; padding: 0 10px"> }
</span></span></pre>
</div>
</div>
</body>
</html>