Changeset 32896 for trunk/src/wp-includes/formatting.php

Timestamp:

06/21/2015 12:58:12 AM (9 years ago)

Author:

azaozz

Message:

Update convert_chars():

• Stop trying to remove <title> and <category> meta tags. They have not been used for many many years.
• Replacement of <br> with <br /> and <hr> with <hr /> is not needed for HTML 5.0. Also, these tags are formatted like that by the visual editor.
• Replace invalid HTML entities that might be pasted in the Text editor on save instead of on display.

Fixes #32335.

File:

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

trunk/src/wp-includes/formatting.php

@@ -1504 +1504 @@
 
 /**
- * Converts a number of characters from a string.
- *
- * Metadata tags `<title>` and `<category>` are removed, `<br>` and `<hr>` are
- * converted into correct XHTML and Unicode characters are converted to the
- * valid range.
+ * Converts lone & characters into `&#038;` (a.k.a. `&amp;`)
  *
  * @since 0.71
@@ -1517 +1513 @@
  */
 function convert_chars( $content, $deprecated = '' ) {
-    if ( !empty( $deprecated ) )
+    if ( ! empty( $deprecated ) ) {
         _deprecated_argument( __FUNCTION__, '0.71' );
-
-    // Translation of invalid Unicode references range to valid range
+    }
+
+    if ( strpos( $content, '&' ) !== false ) {
+        $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content );
+    }
+
+    return $content;
+}
+
+/**
+ * Converts invalid Unicode references range to valid range.
+ *
+ * @since 4.3
+ *
+ * @param string $content String with entities that need converting.
+ * @return string Converted string.
+ */
+function convert_invalid_entities( $content ) {
     $wp_htmltranswinuni = array(
-    '&#128;' => '&#8364;', // the Euro sign
-    '&#129;' => '',
-    '&#130;' => '&#8218;', // these are Windows CP1252 specific characters
-    '&#131;' => '&#402;',  // they would look weird on non-Windows browsers
-    '&#132;' => '&#8222;',
-    '&#133;' => '&#8230;',
-    '&#134;' => '&#8224;',
-    '&#135;' => '&#8225;',
-    '&#136;' => '&#710;',
-    '&#137;' => '&#8240;',
-    '&#138;' => '&#352;',
-    '&#139;' => '&#8249;',
-    '&#140;' => '&#338;',
-    '&#141;' => '',
-    '&#142;' => '&#381;',
-    '&#143;' => '',
-    '&#144;' => '',
-    '&#145;' => '&#8216;',
-    '&#146;' => '&#8217;',
-    '&#147;' => '&#8220;',
-    '&#148;' => '&#8221;',
-    '&#149;' => '&#8226;',
-    '&#150;' => '&#8211;',
-    '&#151;' => '&#8212;',
-    '&#152;' => '&#732;',
-    '&#153;' => '&#8482;',
-    '&#154;' => '&#353;',
-    '&#155;' => '&#8250;',
-    '&#156;' => '&#339;',
-    '&#157;' => '',
-    '&#158;' => '&#382;',
-    '&#159;' => '&#376;'
+        '&#128;' => '&#8364;', // the Euro sign
+        '&#129;' => '',
+        '&#130;' => '&#8218;', // these are Windows CP1252 specific characters
+        '&#131;' => '&#402;',  // they would look weird on non-Windows browsers
+        '&#132;' => '&#8222;',
+        '&#133;' => '&#8230;',
+        '&#134;' => '&#8224;',
+        '&#135;' => '&#8225;',
+        '&#136;' => '&#710;',
+        '&#137;' => '&#8240;',
+        '&#138;' => '&#352;',
+        '&#139;' => '&#8249;',
+        '&#140;' => '&#338;',
+        '&#141;' => '',
+        '&#142;' => '&#381;',
+        '&#143;' => '',
+        '&#144;' => '',
+        '&#145;' => '&#8216;',
+        '&#146;' => '&#8217;',
+        '&#147;' => '&#8220;',
+        '&#148;' => '&#8221;',
+        '&#149;' => '&#8226;',
+        '&#150;' => '&#8211;',
+        '&#151;' => '&#8212;',
+        '&#152;' => '&#732;',
+        '&#153;' => '&#8482;',
+        '&#154;' => '&#353;',
+        '&#155;' => '&#8250;',
+        '&#156;' => '&#339;',
+        '&#157;' => '',
+        '&#158;' => '&#382;',
+        '&#159;' => '&#376;'
     );
 
-    // Remove metadata tags
-    $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
-    $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
-
-    // Converts lone & characters into &#38; (a.k.a. &amp;)
-    $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content);
-
-    // Fix Word pasting
-    $content = strtr($content, $wp_htmltranswinuni);
-
-    // Just a little XHTML help
-    $content = str_replace('<br>', '<br />', $content);
-    $content = str_replace('<hr>', '<hr />', $content);
+    if ( strpos( $content, '&#1' ) !== false ) {
+        $content = strtr( $content, $wp_htmltranswinuni );
+    }
 
     return $content;