From f7921555ca891ba55146820e7554709f240a334c Mon Sep 17 00:00:00 2001
From: audrasjb <audrasjb@git.wordpress.org>
Date: Thu, 21 Jul 2022 21:11:12 +0000
Subject: [PATCH] Formatting: Normalize to Unicode NFC encoding before
 converting accent characters in `remove_accents()`.

This changeset adds Unicode sequence normalization from NFD to NFC, via the `normalizer_normalize()` PHP function which is available with the recommended `intl` PHP extension.

This fixes an issue where NFD characters were not properly sanitized. It also provides a unit test for NFD sequences (alternate Unicode representations of the same characters).

Props NumidWasNotAvailable, targz, nacin, nunomorgadinho, p_enrique, gitlost, SergeyBiryukov, markoheijnen, mikeschroder, ocean90, pento, helen, rodrigosevero, zodiac1978, ironprogrammer, audrasjb, azaozz, laboiteare, nuryko, virgar, dxd5001, onnimonni, johnbillion.
Fixes #24661, #47763, #35951.
See #30130, #52654.

Built from https://develop.svn.wordpress.org/trunk@53754


git-svn-id: http://core.svn.wordpress.org/trunk@53313 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-includes/formatting.php | 10 ++++++++++
 wp-includes/version.php    |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index 3b977f4f4e..46668daafe 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -1584,6 +1584,7 @@ function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters =
  * @since 4.8.0 Added locale support for `bs_BA`.
  * @since 5.7.0 Added locale support for `de_AT`.
  * @since 6.0.0 Added the `$locale` parameter.
+ * @since 6.1.0 Added Unicode NFC encoding normalization support.
  *
  * @param string $string Text that might have accent characters.
  * @param string $locale Optional. The locale to use for accent removal. Some character
@@ -1597,6 +1598,15 @@ function remove_accents( $string, $locale = '' ) {
 	}
 
 	if ( seems_utf8( $string ) ) {
+
+		// Unicode sequence normalization from NFD (Normalization Form Decomposed)
+		// to NFC (Normalization Form [Pre]Composed), the encoding used in this function.
+		if ( function_exists( 'normalizer_normalize' ) ) {
+			if ( ! normalizer_is_normalized( $string, Normalizer::FORM_C ) ) {
+				$string = normalizer_normalize( $string, Normalizer::FORM_C );
+			}
+		}
+
 		$chars = array(
 			// Decompositions for Latin-1 Supplement.
 			'ª' => 'a',
diff --git a/wp-includes/version.php b/wp-includes/version.php
index f2f32610df..aa8e485b85 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.1-alpha-53753';
+$wp_version = '6.1-alpha-53754';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.