Changeset 33469 for trunk/src/wp-includes/formatting.php

Timestamp:

07/28/2015 11:02:04 PM (8 years ago)

Author:

wonderboymusic

Message:

Protect newlines inside of CDATA. This was breaking things, notably inline JS that used comments for HTML standards compat.

• Tokenize newlines in WP_Embed::autoembed() before running ->autoembed_callback()
• Tokenize newlines with placeholders in wpautop()
• Introduce wp_html_split() to DRY the RegEx from wp_replace_in_html_tags() and do_shortcodes_in_html_tags()

Adds unit tests.

Props miqrogroove, kitchin, azaozz.
Fixes #33106.

File:

• trunk/src/wp-includes/formatting.php (modified) (3 diffs)

trunk/src/wp-includes/formatting.php

@@ -505 +505 @@
     $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
 
-    // Strip newlines from all elements.
-    $pee = wp_replace_in_html_tags( $pee, array( "\n" => " " ) );
+    // Find newlines in all elements and add placeholders.
+    $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
 
     // Collapse line breaks before and after <option> elements so they don't get autop'd.
@@ -593 +593 @@
         $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
 
+    // Restore newlines in all elements.
+    $pee = str_replace( " <!-- wpnl --> ", "\n", $pee );
+
     return $pee;
+}
+
+/**
+ * Separate HTML elements and comments from the text.
+ *
+ * @since 4.2.4
+ *
+ * @param string $input The text which has to be formatted.
+ * @return array The formatted text.
+ */
+function wp_html_split( $input ) {
+    static $regex;
+
+    if ( ! isset( $regex ) ) {
+        $comments =
+              '!'           // Start of comment, after the <.
+            . '(?:'         // Unroll the loop: Consume everything until --> is found.
+            .     '-(?!->)' // Dash not followed by end of comment.
+            .     '[^\-]*+' // Consume non-dashes.
+            . ')*+'         // Loop possessively.
+            . '(?:-->)?';   // End of comment. If not found, match all input.
+
+        $cdata =
+              '!\[CDATA\['  // Start of comment, after the <.
+            . '[^\]]*+'     // Consume non-].
+            . '(?:'         // Unroll the loop: Consume everything until ]]> is found.
+            .     '](?!]>)' // One ] not followed by end of comment.
+            .     '[^\]]*+' // Consume non-].
+            . ')*+'         // Loop possessively.
+            . '(?:]]>)?';   // End of comment. If not found, match all input.
+
+        $regex =
+              '/('              // Capture the entire match.
+            .     '<'           // Find start of element.
+            .     '(?(?=!--)'   // Is this a comment?
+            .         $comments // Find end of comment.
+            .     '|'
+            .         '(?(?=!\[CDATA\[)' // Is this a comment?
+            .             $cdata // Find end of comment.
+            .         '|'
+            .             '[^>]*>?' // Find end of element. If not found, match all input.
+            .         ')'
+            .     ')'
+            . ')/s';
+    }
+
+    return preg_split( $regex, $input, -1, PREG_SPLIT_DELIM_CAPTURE );
 }
 
@@ -607 +657 @@
 function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
     // Find all elements.
-    $comments =
-          '!'           // Start of comment, after the <.
-        . '(?:'         // Unroll the loop: Consume everything until --> is found.
-        .     '-(?!->)' // Dash not followed by end of comment.
-        .     '[^\-]*+' // Consume non-dashes.
-        . ')*+'         // Loop possessively.
-        . '(?:-->)?';   // End of comment. If not found, match all input.
-
-    $regex =
-          '/('              // Capture the entire match.
-        .     '<'           // Find start of element.
-        .     '(?(?=!--)'   // Is this a comment?
-        .         $comments // Find end of comment.
-        .     '|'
-        .         '[^>]*>?' // Find end of element. If not found, match all input.
-        .     ')'
-        . ')/s';
-
-    $textarr = preg_split( $regex, $haystack, -1, PREG_SPLIT_DELIM_CAPTURE );
+    $textarr = wp_html_split( $haystack );
     $changed = false;