From 69adf95498bab1e68de12a05da309b1cb4a447ea Mon Sep 17 00:00:00 2001
From: Marin Atanasov <8436925+tyxla@users.noreply.github.com>
Date: Tue, 23 Apr 2024 14:29:47 +0300
Subject: [PATCH] ComboboxControl: Simplify string normalization (#60893)

* ComboboxControl: Simplify string normalization

* CHANGELOG

* Update CHANGELOG

* Try literal notation

* Add inline comment to clarify regex

* Fix test comments

Co-authored-by: tyxla <tyxla@git.wordpress.org>
Co-authored-by: Mamaduka <mamaduka@git.wordpress.org>
---
 packages/components/CHANGELOG.md              |  4 ++
 packages/components/src/utils/strings.ts      | 70 +++----------------
 packages/components/src/utils/test/strings.js | 62 ++++++++++++++++
 3 files changed, 77 insertions(+), 59 deletions(-)

diff --git a/packages/components/CHANGELOG.md b/packages/components/CHANGELOG.md
index 0df9c6c9df842..fe370102abfff 100644
--- a/packages/components/CHANGELOG.md
+++ b/packages/components/CHANGELOG.md
@@ -10,6 +10,10 @@
 
 -   `SlotFill`: fixed missing `getServerSnapshot` parameter in slot map ([#60943](https://github.com/WordPress/gutenberg/pull/60943)).
 
+### Enhancements
+
+-   `ComboboxControl`: Simplify string normalization ([#60893](https://github.com/WordPress/gutenberg/pull/60893)).
+
 ## 27.4.0 (2024-04-19)
 
 ### Deprecation
diff --git a/packages/components/src/utils/strings.ts b/packages/components/src/utils/strings.ts
index bb43a5e53a405..e15886da61f5a 100644
--- a/packages/components/src/utils/strings.ts
+++ b/packages/components/src/utils/strings.ts
@@ -4,66 +4,18 @@
 import removeAccents from 'remove-accents';
 import { paramCase } from 'change-case';
 
+/**
+ * All unicode characters that we consider "dash-like":
+ * - `\u007e`: ~ (tilde)
+ * - `\u00ad`: ­ (soft hyphen)
+ * - `\u2053`: ⁓ (swung dash)
+ * - `\u207b`: ⁻ (superscript minus)
+ * - `\u208b`: ₋ (subscript minus)
+ * - `\u2212`: − (minus sign)
+ * - `\\p{Pd}`: any other Unicode dash character
+ */
 const ALL_UNICODE_DASH_CHARACTERS = new RegExp(
-	`[${ [
-		// - (hyphen-minus)
-		'\u002d',
-		// ~ (tilde)
-		'\u007e',
-		// ­ (soft hyphen)
-		'\u00ad',
-		// ֊ (armenian hyphen)
-		'\u058a',
-		// ־ (hebrew punctuation maqaf)
-		'\u05be',
-		// ᐀ (canadian syllabics hyphen)
-		'\u1400',
-		// ᠆ (mongolian todo soft hyphen)
-		'\u1806',
-		// ‐ (hyphen)
-		'\u2010',
-		// non-breaking hyphen)
-		'\u2011',
-		// ‒ (figure dash)
-		'\u2012',
-		// – (en dash)
-		'\u2013',
-		// — (em dash)
-		'\u2014',
-		// ― (horizontal bar)
-		'\u2015',
-		// ⁓ (swung dash)
-		'\u2053',
-		// superscript minus)
-		'\u207b',
-		// subscript minus)
-		'\u208b',
-		// − (minus sign)
-		'\u2212',
-		// ⸗ (double oblique hyphen)
-		'\u2e17',
-		// ⸺ (two-em dash)
-		'\u2e3a',
-		// ⸻ (three-em dash)
-		'\u2e3b',
-		// 〜 (wave dash)
-		'\u301c',
-		// 〰 (wavy dash)
-		'\u3030',
-		// ゠ (katakana-hiragana double hyphen)
-		'\u30a0',
-		// ︱ (presentation form for vertical em dash)
-		'\ufe31',
-		// ︲ (presentation form for vertical en dash)
-		'\ufe32',
-		// ﹘ (small em dash)
-		'\ufe58',
-		// ﹣ (small hyphen-minus)
-		'\ufe63',
-		// － (fullwidth hyphen-minus)
-		'\uff0d',
-	].join( '' ) }]`,
-	'g'
+	/[\u007e\u00ad\u2053\u207b\u208b\u2212\p{Pd}]/gu
 );
 
 export const normalizeTextString = ( value: string ): string => {
diff --git a/packages/components/src/utils/test/strings.js b/packages/components/src/utils/test/strings.js
index 2c7d9641260f5..7d03075897318 100644
--- a/packages/components/src/utils/test/strings.js
+++ b/packages/components/src/utils/test/strings.js
@@ -106,5 +106,67 @@ describe( 'normalizeTextString', () => {
 		expect( normalizeTextString( 'foo⸻bar' ) ).toBe( 'foo-bar' );
 		expect( normalizeTextString( 'foo゠bar' ) ).toBe( 'foo-bar' );
 		expect( normalizeTextString( 'foo－bar' ) ).toBe( 'foo-bar' );
+
+		const dashCharacters = [
+			// - (hyphen-minus)
+			'\u002d',
+			// ~ (tilde)
+			'\u007e',
+			// ­ (soft hyphen)
+			'\u00ad',
+			// ֊ (armenian hyphen)
+			'\u058a',
+			// ־ (hebrew punctuation maqaf)
+			'\u05be',
+			// ᐀ (canadian syllabics hyphen)
+			'\u1400',
+			// ᠆ (mongolian todo soft hyphen)
+			'\u1806',
+			// ‐ (hyphen)
+			'\u2010',
+			// non-breaking hyphen)
+			'\u2011',
+			// ‒ (figure dash)
+			'\u2012',
+			// – (en dash)
+			'\u2013',
+			// — (em dash)
+			'\u2014',
+			// ― (horizontal bar)
+			'\u2015',
+			// ⁓ (swung dash)
+			'\u2053',
+			// ⁻ (superscript minus)
+			'\u207b',
+			// ₋ (subscript minus)
+			'\u208b',
+			// − (minus sign)
+			'\u2212',
+			// ⸗ (double oblique hyphen)
+			'\u2e17',
+			// ⸺ (two-em dash)
+			'\u2e3a',
+			// ⸻ (three-em dash)
+			'\u2e3b',
+			// 〜 (wave dash)
+			'\u301c',
+			// 〰 (wavy dash)
+			'\u3030',
+			// ゠ (katakana-hiragana double hyphen)
+			'\u30a0',
+			// ︱ (presentation form for vertical em dash)
+			'\ufe31',
+			// ︲ (presentation form for vertical en dash)
+			'\ufe32',
+			// ﹘ (small em dash)
+			'\ufe58',
+			// ﹣ (small hyphen-minus)
+			'\ufe63',
+			// － (fullwidth hyphen-minus)
+			'\uff0d',
+		];
+		expect( normalizeTextString( dashCharacters.join( '' ) ) ).toBe(
+			'-'.repeat( dashCharacters.length )
+		);
 	} );
 } );