Formatting: Transform “ẞ” for German locales in remove_accents().

The capital Eszett was standardized in German orthography in 2017, DIN 5008, but WordPress has only been transforming the lowercase version.

This patch adds the uppercase variant to the list and transforms it to “SS” for more-appriate slug and permalink generation.

Developed in: #11188
Discussed in: https://core.trac.wordpress.org/ticket/64821

Props apermo, dmsnell.
Fixes #64821.


git-svn-id: https://develop.svn.wordpress.org/trunk@61855 602fd350-edb4-49c9-b593-d223f7449a82

Author: dmsnell

src/wp-includes/formatting.php

@@ -1566,6 +1566,7 @@ function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters =
  * | U+00F6   | ö     | oe          | Latin small letter o with diaeresis     |
  * | U+00DC   | Ü     | Ue          | Latin capital letter U with diaeresis   |
  * | U+00FC   | ü     | ue          | Latin small letter u with diaeresis     |
+ * | U+1E9E   | ẞ     | SS          | Latin capital letter sharp s            |
  * | U+00DF   | ß     | ss          | Latin small letter sharp s              |
  *
  * Danish (`da_DK`) locale:
@@ -1599,6 +1600,7 @@ function utf8_uri_encode( $utf8_string, $length = 0, $encode_ascii_characters =
  * @since 5.7.0 Added locale support for `de_AT`.
  * @since 6.0.0 Added the `$locale` parameter.
  * @since 6.1.0 Added Unicode NFC encoding normalization support.
+ * @since 7.0.0 Added capital Eszett (U+1E9E) support for German locales.
  *
  * @param string $text   Text that might have accent characters.
  * @param string $locale Optional. The locale to use for accent removal. Some character
@@ -1972,6 +1974,7 @@ function remove_accents( $text, $locale = '' ) {
 			$chars['ö'] = 'oe';
 			$chars['Ü'] = 'Ue';
 			$chars['ü'] = 'ue';
+			$chars['ẞ'] = 'SS';
 			$chars['ß'] = 'ss';
 		} elseif ( 'da_DK' === $locale ) {
 			$chars['Æ'] = 'Ae';

tests/phpunit/tests/formatting/removeAccents.php

@@ -108,6 +108,16 @@ public function test_remove_accents_germanic_umlauts() {
 		$this->assertSame( 'AeOeUeaeoeuess', remove_accents( 'ÄÖÜäöüß', 'de_DE' ) );
 	}
 
+	/**
+	 * @ticket 64821
+	 */
+	public function test_remove_accents_germanic_capital_eszett() {
+		// U+1E9E LATIN CAPITAL LETTER SHARP S, standardized in German orthography in 2017 (DIN 5008).
+		$this->assertSame( 'SS', remove_accents( 'ẞ', 'de_DE' ) );
+		// Verify it works in context alongside the lowercase variant.
+		$this->assertSame( 'SSstrasse', remove_accents( 'ẞstraße', 'de_DE' ) );
+	}
+
 	/**
 	 * @ticket 23907
 	 */