From 77a972838c495dca96164e9ebfa24780be439e4e Mon Sep 17 00:00:00 2001
From: desrosj <desrosj@git.wordpress.org>
Date: Thu, 6 Jan 2022 17:10:00 +0000
Subject: [PATCH] Formatting: Correctly encode ASCII characters in post slugs.

Props zieladam, whyisjake, xknown, peterwilsoncc, desrosj, iandunn.
Built from https://develop.svn.wordpress.org/trunk@52457


git-svn-id: http://core.svn.wordpress.org/trunk@52049 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-includes/formatting.php | 17 +++++++++++------
 wp-includes/post.php       |  2 +-
 wp-includes/version.php    |  2 +-
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index 905b07b598..dac06eb571 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -1138,12 +1138,14 @@ function wp_check_invalid_utf8( $string, $strip = false ) {
  * Encode the Unicode values to be used in the URI.
  *
  * @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 string $utf8_string             String to encode.
+ * @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();
 	$num_octets     = 1;
@@ -1158,11 +1160,14 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) {
 		$value = ord( $utf8_string[ $i ] );
 
 		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 ) {
 				if ( $value < 224 ) {
diff --git a/wp-includes/post.php b/wp-includes/post.php
index 5cc7f66244..582e17a863 100644
--- a/wp-includes/post.php
+++ b/wp-includes/post.php
@@ -5142,7 +5142,7 @@ function _truncate_post_slug( $slug, $length = 200 ) {
 		if ( $decoded_slug === $slug ) {
 			$slug = substr( $slug, 0, $length );
 		} else {
-			$slug = utf8_uri_encode( $decoded_slug, $length );
+			$slug = utf8_uri_encode( $decoded_slug, $length, true );
 		}
 	}
 
diff --git a/wp-includes/version.php b/wp-includes/version.php
index 8db4c50615..d0d01ad390 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.0-alpha-52456';
+$wp_version = '6.0-alpha-52457';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.