Changeset 20859

Timestamp:

05/23/2012 09:04:35 PM (13 years ago)

Author:

westi

Message:

i18n: Update the word splitting we use when trimming strings to build excerpts so that it has support for a character based mode for locales where character splitting is more approproate like Japan.

See #16079 props tenpura.

File:

• trunk/wp-includes/formatting.php (modified) (2 diffs)

trunk/wp-includes/formatting.php

@@ -2128 +2128 @@
  * Trims text to a certain number of words.
  *
+ * This function is localized. For languages that count 'words' by the individual
+ * character (such as East Asian languages), the $num_words argument will apply
+ * to the number of individual characters.
+ *
  * @since 3.3.0
  *
@@ -2140 +2144 @@
     $original_text = $text;
     $text = wp_strip_all_tags( $text );
-    $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
+    /* translators: If your word count is based on single characters (East Asian characters), 
+       enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */ 
+    if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
+        $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
+        preg_match_all( '/./u', $text, $words_array );
+        $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
+        $sep = '';
+    } else {
+        $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
+        $sep = ' ';
+    }
     if ( count( $words_array ) > $num_words ) {
         array_pop( $words_array );
-        $text = implode( ' ', $words_array );
+        $text = implode( $sep, $words_array );
         $text = $text . $more;
     } else {
-        $text = implode( ' ', $words_array );
+        $text = implode( $sep, $words_array );
     }
     return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );