Changeset 52483 for branches/4.0/src/wp-includes/formatting.php

Timestamp:

01/06/2022 06:25:11 PM (3 years ago)

Author:

desrosj

Message:

Grouped backports to the 4.0 branch.

• Query: Improve sanitization within WP_Tax_Query.
• Upgrade/Install: Avoid using unserialize() unnecessarily.
• Formatting: Correctly encode ASCII characters in post slugs.

Merges [52454,52456-52457] to the 4.0 branch.
Props vortfu, dd32, ehtis, zieladam, whyisjake, xknown, peterwilsoncc, desrosj, iandunn.

Location:

branches/4.0

Files:

• . (modified) (1 prop)
• src/wp-includes/formatting.php (modified) (2 diffs)

branches/4.0/src/wp-includes/formatting.php

@@ -859 +859 @@
  *
  * @since 1.5.0
+ * @since 5.8.3 Added the `encode_ascii_characters` parameter.
  *
  * @param string $utf8_string
  * @param int $length Max length of the string
+ * @param bool   $encode_ascii_characters Whether to encode ascii characters such as < " '
  * @return string String with Unicode encoded for URI.
  */
-function utf8_uri_encode( $utf8_string, $length = 0 ) {
+function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters = false ) {
     $unicode = '';
     $values = array();
@@ -879 +881 @@
 
         if ( $value < 128 ) {
-            if ( $length && ( $unicode_length >= $length ) )
+            $char                = chr( $value );
+            $encoded_char        = $encode_ascii_characters ? rawurlencode( $char ) : $char;
+            $encoded_char_length = strlen( $encoded_char );
+            if ( $length && ( $unicode_length + $encoded_char_length ) > $length ) {
                 break;
-            $unicode .= chr($value);
-            $unicode_length++;
+            }
+            $unicode        .= $encoded_char;
+            $unicode_length += $encoded_char_length;
         } else {
             if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;