Changeset 7140

Timestamp:

03/03/2008 09:05:23 PM (17 years ago)

Author:

ryan

Message:

Multi-byte character safe excerpting from nbachiyski. fixes #6077

Location:

trunk

Files:

• wp-admin/includes/dashboard.php (modified) (1 diff)
• wp-includes/comment.php (modified) (1 diff)
• wp-includes/compat.php (modified) (1 diff)
• wp-includes/formatting.php (modified) (1 diff)
• wp-settings.php (modified) (2 diffs)
• wp-trackback.php (modified) (1 diff)

trunk/wp-admin/includes/dashboard.php

@@ -336 +336 @@
             else
                 $content = __( 'something' );
-            $content = strip_tags( $content );
-            if ( 50 < strlen($content) )
-                $content = substr($content, 0, 50) . ' ...';
-            $content = wp_specialchars( $content );
+            $content = wp_html_excerpt($content, 50) . ' ...';
             if ( $link )
                 $text = _c( '%1$s linked here <a href="%2$s">saying</a>, "%3$s"|feed_display' );

trunk/wp-includes/comment.php

@@ -1047 +1047 @@
         $excerpt = apply_filters('the_excerpt', $post->post_excerpt);
     $excerpt = str_replace(']]>', ']]>', $excerpt);
-    $excerpt = strip_tags($excerpt);
-    if ( function_exists('mb_strcut') ) // For international trackbacks
-        $excerpt = mb_strcut($excerpt, 0, 252, get_option('blog_charset')) . '...';
-    else
-        $excerpt = substr($excerpt, 0, 252) . '...';
+    $excerpt = wp_html_excerpt($excerpt, 252) . '...';
 
     $post_title = apply_filters('the_title', $post->post_title);

trunk/wp-includes/compat.php

@@ -78 +78 @@
 endif;
 
+if ( ! function_exists('mb_strcut') ):
+    function mb_strcut( $str, $start, $length=null, $encoding=null ) {
+        return _mb_strcut($str, $start, $length, $encoding);
+    }
+endif;
+
+function _mb_strcut( $str, $start, $length=null, $encoding=null ) {
+    // the solution below, works only for utf-8, so in case of a different
+    // charset, just use built-in substr
+    $charset = get_option( 'blog_charset' );
+    if ( !in_array( $charset, array('utf8', 'utf-8', 'UTF8', 'UTF-8') ) ) {
+        return is_null( $length )? substr( $str, $start ) : substr( $str, $start, $length);
+    }
+    // use the regex unicode support to separate the UTF-8 characters into an array
+    preg_match_all( '/./us', $str, $match );
+    $chars = is_null( $length )? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );
+    return implode( '', $chars );
+}
+
 ?>

trunk/wp-includes/formatting.php

@@ -1371 +1371 @@
 }
 
+/**
+ * Safely extracts not more than the first $count characters from html string
+ *
+ * UTF-8, tags and entities safe prefix extraction. Entities inside will be
+ * counted as one character. As a side effect, all entities will be converted to
+ * their decimal form.
+ *
+ * @param integer $str String to get the excerpt from
+ * @param integer $count Maximum number of visible characters to take
+ * @eaturn string the excerpt
+ */
+function wp_html_excerpt( $str, $count ) {
+    $str = strip_tags( $str );
+    $str = html_entity_decode( $str, ENT_QUOTES);
+    $str = mb_strcut( $str, 0, $count );
+    // remove part of an entity at the end
+    $str = preg_replace( '/&[^;\s]{0,6}$/', '', $str );
+    // we decoded some entities we should put back
+    $str = wp_specialchars( $str );
+    return $str;
+}
+
 ?>

trunk/wp-settings.php

@@ -15 +15 @@
 if ( function_exists('memory_get_usage') && ( (int) @ini_get('memory_limit') < abs(intval(WP_MEMORY_LIMIT)) ) )
     @ini_set('memory_limit', WP_MEMORY_LIMIT);
+
 
 /**
@@ -351 +352 @@
 require (ABSPATH . WPINC . '/pluggable.php');
 
+/*
+ * In most cases the default internal encoding is latin1, which is of no use,
+ * since we want to use the mb_ functions for utf-8 strings
+ */
+if ( function_exists('mb_internal_encoding') )
+    mb_internal_encoding( get_option( 'blog_charset' ) );
+
+
+
 if ( defined('WP_CACHE') && function_exists('wp_cache_postload') )
     wp_cache_postload();

trunk/wp-trackback.php

@@ -73 +73 @@
         trackback_response(1, 'Sorry, trackbacks are closed for this item.');
 
-    $title =  wp_specialchars( strip_tags( $title ) );
-    $excerpt = strip_tags($excerpt);
-    if ( function_exists('mb_strcut') ) { // For international trackbacks
-        $excerpt = mb_strcut($excerpt, 0, 252, get_option('blog_charset')) . '...';
-        $title = mb_strcut($title, 0, 250, get_option('blog_charset')) . '...';
-    } else {
-        $excerpt = (strlen($excerpt) > 255) ? substr($excerpt, 0, 252) . '...' : $excerpt;
-        $title = (strlen($title) > 250) ? substr($title, 0, 250) . '...' : $title;
-    }
+    $title =  wp_html_excerpt( $title, 250 ).'...';
+    $excerpt = wp_html_excerpt( $excerpt, 252 ).'...';
 
     $comment_post_ID = (int) $tb_id;