Changeset 4989

Timestamp:

08/16/2011 11:33:09 AM (14 years ago)

Author:

boonebgorges

Message:

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 #3452. Props DJPaul for all the help with this patch.

Location:

trunk

Files:

• bp-activity/bp-activity-filters.php (modified) (1 diff)
• bp-activity/bp-activity-template.php (modified) (1 diff)
• bp-core/bp-core-template.php (modified) (1 diff)
• bp-core/bp-core-wpabstraction.php (modified) (2 diffs)

trunk/bp-activity/bp-activity-filters.php

@@ -189 +189 @@
     $append_text    = apply_filters( 'bp_activity_excerpt_append_text', __( '[Read more]', 'buddypress' ) );
     $excerpt_length = apply_filters( 'bp_activity_excerpt_length', 358 );
-    $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();
-
-    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 );
+
+    // 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' ) ) );
+
+    // 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();
+
+        $excerpt = sprintf( '%1$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 );
+    }
 
     return apply_filters( 'bp_activity_truncate_entry', $excerpt, $text, $append_text );

trunk/bp-activity/bp-activity-template.php

@@ -1537 +1537 @@
 
         if ( 'activity_update' == $activities_template->activity->type )
-            $title .= ': ' . strip_tags( ent2ncr( trim( convert_chars( bp_create_excerpt( $activities_template->activity->content, 70, true, " […]" ) ) ) ) );
+            $title .= ': ' . strip_tags( ent2ncr( trim( convert_chars( bp_create_excerpt( $activities_template->activity->content, 70, array( 'ending' => " […]" ) ) ) ) ) );
 
         return apply_filters( 'bp_get_activity_feed_item_title', $title );

trunk/bp-core/bp-core-template.php

@@ -347 +347 @@
     }
 
-/**
- * bp_create_excerpt()
- *
- * Fakes an excerpt on any content. Will not truncate words.
- *
- * @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
- */
-function bp_create_excerpt( $text, $excerpt_length = 225, $filter_shortcodes = true, $append_text = ' […]' ) { // Fakes an excerpt if needed
+
+/**
+ * Truncates text.
+ *
+ * Cuts a string to the length of $length and replaces the last characters
+ * with the ending if the text is longer than length.
+ *
+ * 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.
+ */
+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'            => __( ' […]', '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
     $original_text = $text;
-    $text = str_replace( ']]>', ']]>', $text );
-
-    $excerpt_length = apply_filters( 'bp_excerpt_length', $excerpt_length );
-    $append_text = apply_filters( 'bp_excerpt_append_text', $append_text );
-
+
+    // Allow plugins to modify these values globally
+    $length = apply_filters( 'bp_excerpt_length', $length );
+    $ending = apply_filters( 'bp_excerpt_append_text', $ending );
+
+    // Remove shortcodes if necessary
     if ( $filter_shortcodes )
         $text = strip_shortcodes( $text );
 
-    preg_match( "%\s*((?:<[^>]+>)+\S*)\s*|\s+%s", $text, $matches, PREG_OFFSET_CAPTURE, $excerpt_length );
-
-    if ( !empty( $matches ) ) {
-        $pos = array_pop( array_pop( $matches ) );
-        $text = substr( $text, 0, $pos ) . $append_text;
-    }
-
-    return apply_filters( 'bp_create_excerpt', $text, $original_text, $excerpt_length, $filter_shortcodes, $append_text );
+    // 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;
+        }
+
+        $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 ) );
+        }
+    }
+
+    // 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 );
 }
 add_filter( 'bp_create_excerpt', 'wp_trim_excerpt' );

trunk/bp-core/bp-core-wpabstraction.php

@@ -27 +27 @@
         }
     }
-    
+
     if ( !function_exists( 'update_blog_option' ) ) {
         function update_blog_option( $blog_id, $option_name, $value ) {
@@ -74 +74 @@
         return "{$prefix}spam = 0 AND {$prefix}deleted = 0 AND {$prefix}user_status = 0";
 }
+
+/**
+ * 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;
+        }
+    }
+}
+
 ?>