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.
Built from https://develop.svn.wordpress.org/trunk@32896


git-svn-id: http://core.svn.wordpress.org/trunk@32867 1a063a9b-81f0-0310-95a4-ce76da25c4cd

wp-includes/default-filters.php

@@ -87,6 +87,7 @@ add_filter( 'post_mime_type', 'sanitize_mime_type' );
 
 // Places to balance tags on input
 foreach ( array( 'content_save_pre', 'excerpt_save_pre', 'comment_save_pre', 'pre_comment_content' ) as $filter ) {
+	add_filter( $filter, 'convert_invalid_entities' );
 	add_filter( $filter, 'balanceTags', 50 );
 }
 

wp-includes/formatting.php

@@ -1503,11 +1503,7 @@ function sanitize_html_class( $class, $fallback = '' ) {
 }
 
 /**
- * Converts a number of characters from a string.
+ * Converts lone & characters into `&` (a.k.a. `&`)
- *
- * Metadata tags `<title>` and `<category>` are removed, `<br>` and `<hr>` are
- * converted into correct XHTML and Unicode characters are converted to the
- * valid range.
  *
  * @since 0.71
  *
@@ -1516,10 +1512,26 @@ function sanitize_html_class( $class, $fallback = '' ) {
  * @return string Converted string.
  */
 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;' => '',
@@ -1555,19 +1567,9 @@ function convert_chars( $content, $deprecated = '' ) {
 		'&#159;' => '&#376;'
 	);
 
-	// Remove metadata tags
+	if ( strpos( $content, '&#1' ) !== false ) {
-	$content = preg_replace('/<title>(.+?)<\/title>/','',$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);
 
 	return $content;
 }

wp-includes/version.php

@@ -4,7 +4,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '4.3-alpha-32895';
+$wp_version = '4.3-alpha-32896';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.