Merge pull request #287150 from lucas-gomes-santana/fix/snippet-unicode-support

Improve snippet case transforms suport for non-Latin scripts (fix: #286165)

src/vs/editor/contrib/snippet/browser/snippetParser.ts

@@ -400,13 +400,15 @@ export class FormatString extends Marker {
 		}
 	}
 
+	// Note: word-based case transforms rely on uppercase/lowercase distinctions.
+	// For scripts without case, transforms are effectively no-ops.
 	private _toKebabCase(value: string): string {
-		const match = value.match(/[a-z0-9]+/gi);
+		const match = value.match(/[\p{L}0-9]+/gu);
 		if (!match) {
 			return value;
 		}
 
-		if (!value.match(/[a-z0-9]/)) {
+		if (!value.match(/[\p{L}0-9]/u)) {
 			return value
 				.trim()
 				.toLowerCase()
@@ -414,12 +416,16 @@ export class FormatString extends Marker {
 				.replace(/[\s_]+/g, '-');
 		}
 
-		const match2 = value
-			.trim()
-			.match(/[A-Z]{2,}(?=[A-Z][a-z]+[0-9]*|\b)|[A-Z]?[a-z]+[0-9]*|[A-Z]|[0-9]+/g);
+		const cleaned = value.trim().replace(/^_+|_+$/g, '');
+
+		const match2 = cleaned.match(/\p{Lu}{2,}(?=\p{Lu}\p{Ll}+[0-9]*|[\s_-]|$)|\p{Lu}?\p{Ll}+[0-9]*|\p{Lu}(?=\p{Lu}\p{Ll})|\p{Lu}(?=[\s_-]|$)|[0-9]+/gu);
 
 		if (!match2) {
-			return value;
+			return cleaned
+				.split(/[\s_-]+/)
+				.filter(word => word.length > 0)
+				.map(word => word.toLowerCase())
+				.join('-');
 		}
 
 		return match2
@@ -428,7 +434,7 @@ export class FormatString extends Marker {
 	}
 
 	private _toPascalCase(value: string): string {
-		const match = value.match(/[a-z0-9]+/gi);
+		const match = value.match(/[\p{L}0-9]+/gu);
 		if (!match) {
 			return value;
 		}
@@ -439,7 +445,7 @@ export class FormatString extends Marker {
 	}
 
 	private _toCamelCase(value: string): string {
-		const match = value.match(/[a-z0-9]+/gi);
+		const match = value.match(/[\p{L}0-9]+/gu);
 		if (!match) {
 			return value;
 		}
@@ -453,7 +459,7 @@ export class FormatString extends Marker {
 	}
 
 	private _toSnakeCase(value: string): string {
-		return value.replace(/([a-z])([A-Z])/g, '$1_$2')
+		return value.replace(/(\p{Ll})(\p{Lu})/gu, '$1_$2')
 			.replace(/[\s\-]+/g, '_')
 			.toLowerCase();
 	}

src/vs/editor/contrib/snippet/test/browser/snippetParser.test.ts

@@ -4,7 +4,7 @@
  *--------------------------------------------------------------------------------------------*/
 import assert from 'assert';
 import { ensureNoDisposablesAreLeakedInTestSuite } from '../../../../../base/test/common/utils.js';
-import { Choice, FormatString, Marker, Placeholder, Scanner, SnippetParser, Text, TextmateSnippet, TokenType, Transform, Variable } from '../../browser/snippetParser.js';
+import { Choice, FormatString, Marker, Placeholder, Scanner, SnippetParser, Text, TextmateSnippet, TokenType, Transform, Variable, VariableResolver } from '../../browser/snippetParser.js';
 
 suite('SnippetParser', () => {
 
@@ -700,6 +700,44 @@ suite('SnippetParser', () => {
 		assert.strictEqual(new FormatString(1, undefined, 'bar', 'foo').resolve('baz'), 'bar');
 	});
 
+	test('Unicode Variable Transformations', () => {
+		const resolver = new class implements VariableResolver {
+			resolve(variable: Variable): string | undefined {
+				const values: { [key: string]: string } = {
+					'RUSSIAN': 'одинДва',
+					'GREEK': 'έναςΔύο',
+					'TURKISH': 'istanbulLı',
+					'JAPANESE': 'こんにちは'
+				};
+				return values[variable.name];
+			}
+		};
+
+		function assertTransform(transformName: string, varName: string, expected: string) {
+			const p = new SnippetParser();
+			const snippet = p.parse(`\${${varName}/(.*)/\${1:/${transformName}}/}`);
+			const variable = snippet.children[0] as Variable;
+			variable.resolve(resolver);
+			const resolved = variable.toString();
+			assert.strictEqual(resolved, expected, `${transformName} failed for ${varName}`);
+		}
+
+		assertTransform('kebabcase', 'RUSSIAN', 'один-два');
+		assertTransform('kebabcase', 'GREEK', 'ένας-δύο');
+		assertTransform('snakecase', 'RUSSIAN', 'один_два');
+		assertTransform('snakecase', 'GREEK', 'ένας_δύο');
+		assertTransform('camelcase', 'RUSSIAN', 'одинДва');
+		assertTransform('camelcase', 'GREEK', 'έναςΔύο');
+		assertTransform('pascalcase', 'RUSSIAN', 'ОдинДва');
+		assertTransform('pascalcase', 'GREEK', 'ΈναςΔύο');
+		assertTransform('upcase', 'RUSSIAN', 'ОДИНДВА');
+		assertTransform('downcase', 'RUSSIAN', 'одиндва');
+		assertTransform('kebabcase', 'TURKISH', 'istanbul-lı');
+		assertTransform('pascalcase', 'TURKISH', 'IstanbulLı');
+		assertTransform('upcase', 'JAPANESE', 'こんにちは');
+		assertTransform('kebabcase', 'JAPANESE', 'こんにちは');
+	});
+
 	test('Snippet variable transformation doesn\'t work if regex is complicated and snippet body contains \'$$\' #55627', function () {
 		const snippet = new SnippetParser().parse('const fileName = "${TM_FILENAME/(.*)\\..+$/$1/}"');
 		assert.strictEqual(snippet.toTextmateString(), 'const fileName = "${TM_FILENAME/(.*)\\..+$/${1}/}"');