regexpu-core - npm Package Compare versions

Comparing version 5.3.2 to 6.0.0

data/iu-mappings.js

@@ -20,2 +20,3 @@ module.exports = new Map([
 	[0x345, 0x1FBE],
+	[0x390, 0x1FD3],
 	[0x392, 0x3D0],
@@ -32,2 +33,3 @@ [0x395, 0x3F5],
 	[0x3A9, 0x2126],
+	[0x3B0, 0x1FE3],
 	[0x3B8, 0x3F4],
@@ -126,2 +128,4 @@ [0x3C2, 0x3A3],
 	[0x1FCC, 0x1FC3],
+	[0x1FD3, 0x390],
+	[0x1FE3, 0x3B0],
 	[0x1FF3, 0x1FFC],
@@ -139,2 +143,4 @@ [0x1FFC, 0x1FF3],
 	[0xA64A, 0x1C88],
+	[0xFB05, 0xFB06],
+	[0xFB06, 0xFB05],
 	[0x10400, 0x10428],
@@ -141,0 +147,0 @@ [0x10401, 0x10429],

package.json

 {
 	"name": "regexpu-core",
-	"version": "5.3.2",
+	"version": "6.0.0",
 	"description": "regexpu’s core functionality (i.e. `rewritePattern(pattern, flag)`), capable of translating ES6 Unicode regular expressions to ES5.",
@@ -47,10 +47,11 @@ "homepage": "https://mths.be/regexpu",
 		"build": "node scripts/iu-mappings.js && node scripts/character-class-escape-sets.js",
-		"test": "mocha tests",
-		"cover": "istanbul cover --report html node_modules/.bin/_mocha tests -- -u exports -R spec"
+		"test": "node --test tests/tests.js",
+		"test-node6": "mocha tests",
+		"cover": "NODE_V8_COVERAGE=coverage node --test  --experimental-test-coverage tests/tests.js"
 	},
 	"dependencies": {
 		"regenerate": "^1.4.2",
-		"regenerate-unicode-properties": "^10.1.0",
-		"@babel/regjsgen": "^0.8.0",
-		"regjsparser": "^0.9.1",
+		"regenerate-unicode-properties": "^10.1.1",
+		"regjsgen": "^0.8.0",
+		"regjsparser": "^0.10.0",
 		"unicode-match-property-ecmascript": "^2.0.0",
@@ -60,10 +61,5 @@ "unicode-match-property-value-ecmascript": "^2.1.0"
 	"devDependencies": {
-		"codecov": "^3.8.3",
-		"istanbul": "^0.4.5",
 		"jsesc": "^3.0.2",
-		"lodash": "^4.17.21",
-		"mocha": "^10.1.0",
-		"regexpu-fixtures": "^2.1.6",
-		"@unicode/unicode-15.0.0": "^1.3.1"
+		"@unicode/unicode-15.1.0": "^1.5.2"
 	}
 }

README.md

@@ -30,9 +30,9 @@ # regexpu-core [![Build status](https://github.com/mathiasbynens/regexpu-core/workflows/run-checks/badge.svg)](https://github.com/mathiasbynens/regexpu-core/actions?query=workflow%3Arun-checks) [![regexpu-core on npm](https://img.shields.io/npm/v/regexpu-core)](https://www.npmjs.com/package/regexpu-core)
 ```js
-rewritePattern('foo.bar', 'u');
+rewritePattern('foo.bar', 'u', { unicodeFlag: "transform" });
 // → 'foo(?:[\\0-\\t\\x0B\\f\\x0E-\\u2027\\u202A-\\uD7FF\\uDC00-\\uFFFF]|[\\uD800-\\uDBFF][\\uDC00-\\uDFFF]|[\\uD800-\\uDBFF])bar'
 
-rewritePattern('[\\u{1D306}-\\u{1D308}a-z]', 'u');
+rewritePattern('[\\u{1D306}-\\u{1D308}a-z]', 'u', { unicodeFlag: "transform" });
 // → '(?:[a-z]|\\uD834[\\uDF06-\\uDF08])'
 
-rewritePattern('[\\u{1D306}-\\u{1D308}a-z]', 'ui');
+rewritePattern('[\\u{1D306}-\\u{1D308}a-z]', 'ui', { unicodeFlag: "transform" });
 // → '(?:[a-z\\u017F\\u212A]|\\uD834[\\uDF06-\\uDF08])'
@@ -45,7 +45,7 @@ ```
 // In ES5, the dot operator only matches BMP symbols:
-rewritePattern('foo.bar');
+rewritePattern('foo.bar', '', { unicodeFlag: "transform" });
 // → 'foo(?:[\\0-\\t\\x0B\\f\\x0E-\\u2027\\u202A-\\uFFFF])bar'
 
 // But with the ES2015 `u` flag, it matches astral symbols too:
-rewritePattern('foo.bar', 'u');
+rewritePattern('foo.bar', 'u', { unicodeFlag: "transform" });
 // → 'foo(?:[\\0-\\t\\x0B\\f\\x0E-\\u2027\\u202A-\\uD7FF\\uDC00-\\uFFFF]|[\\uD800-\\uDBFF][\\uDC00-\\uDFFF]|[\\uD800-\\uDBFF])bar'
@@ -119,15 +119,9 @@ ```
 
-#### Experimental regular expression features
-
-These options can be set to `false`, `'parse'` and `'transform'`. When using `'transform'`, the corresponding features are compiled to older syntax that can run in older browsers. When using `'parse'`, they are parsed and left as-is in the output pattern. When using `false` (the default), they result in a syntax error if used.
-
-Once these features become stable (when the proposals are accepted as part of ECMAScript), they will be parsed by default and thus `'parse'` will behave like `false`.
-
 - `unicodeSetsFlag` - [The `v` (`unicodeSets`) flag](https://github.com/tc39/proposal-regexp-set-notation)
 
   ```js
-  rewritePattern('[\\p{Emoji}&&\\p{ASCII}]', 'u', {
+  rewritePattern('[\\p{Emoji}&&\\p{ASCII}]', 'v', {
     unicodeSetsFlag: 'transform'
   });
-  // → '[#\*0-9]'
+  // → '[#\\*0-9]'
   ```
@@ -152,2 +146,8 @@
 
+#### Experimental regular expression features
+
+These options can be set to `false`, `'parse'` and `'transform'`. When using `'transform'`, the corresponding features are compiled to older syntax that can run in older browsers. When using `'parse'`, they are parsed and left as-is in the output pattern. When using `false` (the default), they result in a syntax error if used.
+
+Once these features become stable (when the proposals are accepted as part of ECMAScript), they will be parsed by default and thus `'parse'` will behave like `false`.
+
 - `modifiers` - [Inline `m`/`s`/`i` modifiers](https://github.com/tc39/proposal-regexp-modifiers)
@@ -154,0 +154,0 @@

rewrite-pattern.js

 'use strict';
 
-const generate = require('@babel/regjsgen').generate;
+const generate = require('regjsgen').generate;
 const parse = require('regjsparser').parse;
@@ -24,2 +24,7 @@ const regenerate = require('regenerate');
 
+function regenerateContainsAstral(regenerateData) {
+	const data = regenerateData.data;
+	return data.length >= 1 && data[data.length - 1] >= 0x10000;
+}
+
 const SPECIAL_CHARS = /([\\^$.*+?()[\]{}|])/g;
@@ -334,3 +339,3 @@
 		// reached. Code coverage tools should ignore it.
-		/* istanbul ignore next */
+		/* node:coverage ignore next */
 		default:
@@ -419,3 +424,3 @@ throw new Error(`Unknown set action: ${ characterClassItem.kind }`);
 		// reached. Code coverage tools should ignore it.
-		/* istanbul ignore next */
+		/* node:coverage ignore next */
 		default:
@@ -447,3 +452,3 @@ throw new Error(`Unknown character class kind: ${ characterClassItem.kind }`);
 					item.value,
-					config.flags.unicode,
+					config.flags.unicode || config.flags.unicodeSets,
 					config.flags.ignoreCase
@@ -458,3 +463,3 @@ ));
 					config.transform.unicodePropertyEscapes ||
-					(config.transform.unicodeSetsFlag && nestedData.maybeIncludesStrings);
+					(config.transform.unicodeSetsFlag && (nestedData.maybeIncludesStrings || characterClassItem.kind !== "union"));
 				break;
@@ -473,3 +478,3 @@ case 'characterClass':
 			// reached. Code coverage tools should ignore it.
-			/* istanbul ignore next */
+			/* node:coverage ignore next */
 			default:
@@ -497,3 +502,5 @@ throw new Error(`Unknown term type: ${ item.type }`);
 	if (transformed) {
-		const setStr = singleChars.toString(regenerateOptions);
+		// If single chars already contains some astral character, regenerate (bmpOnly: true) will create valid regex strings
+		const bmpOnly = regenerateContainsAstral(singleChars);
+		const setStr = singleChars.toString(Object.assign({}, regenerateOptions, { bmpOnly: bmpOnly }));
 
@@ -504,3 +511,3 @@ if (negative) {
 			} else {
-				if (config.flags.unicode) {
+				if (config.flags.unicode || config.flags.unicodeSets) {
 					if (config.flags.ignoreCase) {
@@ -529,6 +536,5 @@ const astralCharsSet = singleChars.clone().intersection(ASTRAL_SET);
 						// Generate negative set directly when case folding is not involved.
-						update(
-							characterClassItem,
-							UNICODE_SET.clone().remove(singleChars).toString(regenerateOptions)
-						);
+						const negativeSet = UNICODE_SET.clone().remove(singleChars);
+						const bmpOnly = regenerateContainsAstral(negativeSet);
+						update(characterClassItem, negativeSet.toString({ bmpOnly: bmpOnly }));
 					}
@@ -743,3 +749,3 @@ } else {
 		// reached. Code coverage tools should ignore it.
-		/* istanbul ignore next */
+		/* node:coverage ignore next */
 		default:
@@ -786,2 +792,3 @@ throw new Error(`Unknown term type: ${ item.type }`);
 			case 'unicodePropertyEscapes':
+			case 'unicodeSetsFlag':
 			case 'namedGroups':
@@ -793,3 +800,2 @@ if (value != null && value !== false && value !== 'transform') {
 			case 'modifiers':
-			case 'unicodeSetsFlag':
 				if (value != null && value !== false && value !== 'parse' && value !== 'transform') {
@@ -828,3 +834,3 @@ throw new Error(`.${key} must be false (default), 'parse' or 'transform'.`);
 	// unicodeFlag: 'transform' implies unicodePropertyEscapes: 'transform'
-	config.transform.unicodePropertyEscapes = config.flags.unicode && (
+	config.transform.unicodePropertyEscapes = (config.flags.unicode || config.flags.unicodeSets) && (
 		transform(options, 'unicodeFlag') || transform(options, 'unicodePropertyEscapes')
@@ -840,3 +846,2 @@ );
 	const regjsparserFeatures = {
-		'unicodeSet': Boolean(options && options.unicodeSetsFlag),
 		'modifiers': Boolean(options && options.modifiers),
@@ -846,2 +851,3 @@
 		'unicodePropertyEscape': true,
+		'unicodeSet': true,
 		'namedGroups': true,
@@ -853,3 +859,3 @@ 'lookbehind': true,
 		'hasUnicodeFlag': config.useUnicodeFlag,
-		'bmpOnly': !config.flags.unicode
+		'bmpOnly': !config.flags.unicode && !config.flags.unicodeSets
 	};
@@ -856,0 +862,0 @@

No alert changes

Improved metrics

Total package byte prevSize

54548

increased by1.42%

Dev dependency count

2

decreased by-71.43%

Lines of code

1595

increased by0.69%

Dependency changes

• + Addedregjsgen@^0.8.0

• + Addedregjsgen@0.8.0(transitive)

• + Addedregjsparser@0.10.0(transitive)

• - Removed@babel/regjsgen@^0.8.0

• - Removed@babel/regjsgen@0.8.0(transitive)

• - Removedregjsparser@0.9.1(transitive)

• Updatedregenerate-unicode-properties@^10.1.1

• Updatedregjsparser@^0.10.0