regexpu-core - npm Package Compare versions

Comparing version 2.0.0 to 3.0.1

data/character-class-escape-sets.js

@@ -1,15 +0,17 @@
-// Generated by `/scripts/character-class-escape-sets.js`. Do not edit.
-var regenerate = require('regenerate');
+// Generated using `npm run build`. Do not edit.
+'use strict';
 
-exports.REGULAR = {
-	'd': regenerate()
-		.addRange(0x30, 0x39),
-	'D': regenerate()
+const regenerate = require('regenerate');
+
+exports.REGULAR = new Map([
+	['d', regenerate()
+		.addRange(0x30, 0x39)],
+	['D', regenerate()
 		.addRange(0x0, 0x2F)
-		.addRange(0x3A, 0xFFFF),
-	's': regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
+		.addRange(0x3A, 0xFFFF)],
+	['s', regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
 		.addRange(0x9, 0xD)
 		.addRange(0x2000, 0x200A)
-		.addRange(0x2028, 0x2029),
-	'S': regenerate()
+		.addRange(0x2028, 0x2029)],
+	['S', regenerate()
 		.addRange(0x0, 0x8)
@@ -25,25 +27,25 @@ .addRange(0xE, 0x1F)
 		.addRange(0x3001, 0xFEFE)
-		.addRange(0xFF00, 0xFFFF),
-	'w': regenerate(0x5F)
+		.addRange(0xFF00, 0xFFFF)],
+	['w', regenerate(0x5F)
 		.addRange(0x30, 0x39)
 		.addRange(0x41, 0x5A)
-		.addRange(0x61, 0x7A),
-	'W': regenerate(0x60)
+		.addRange(0x61, 0x7A)],
+	['W', regenerate(0x60)
 		.addRange(0x0, 0x2F)
 		.addRange(0x3A, 0x40)
 		.addRange(0x5B, 0x5E)
-		.addRange(0x7B, 0xFFFF)
-};
+		.addRange(0x7B, 0xFFFF)]
+]);
 
-exports.UNICODE = {
-	'd': regenerate()
-		.addRange(0x30, 0x39),
-	'D': regenerate()
+exports.UNICODE = new Map([
+	['d', regenerate()
+		.addRange(0x30, 0x39)],
+	['D', regenerate()
 		.addRange(0x0, 0x2F)
-		.addRange(0x3A, 0x10FFFF),
-	's': regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
+		.addRange(0x3A, 0x10FFFF)],
+	['s', regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
 		.addRange(0x9, 0xD)
 		.addRange(0x2000, 0x200A)
-		.addRange(0x2028, 0x2029),
-	'S': regenerate()
+		.addRange(0x2028, 0x2029)],
+	['S', regenerate()
 		.addRange(0x0, 0x8)
@@ -59,25 +61,25 @@ .addRange(0xE, 0x1F)
 		.addRange(0x3001, 0xFEFE)
-		.addRange(0xFF00, 0x10FFFF),
-	'w': regenerate(0x5F)
+		.addRange(0xFF00, 0x10FFFF)],
+	['w', regenerate(0x5F)
 		.addRange(0x30, 0x39)
 		.addRange(0x41, 0x5A)
-		.addRange(0x61, 0x7A),
-	'W': regenerate(0x60)
+		.addRange(0x61, 0x7A)],
+	['W', regenerate(0x60)
 		.addRange(0x0, 0x2F)
 		.addRange(0x3A, 0x40)
 		.addRange(0x5B, 0x5E)
-		.addRange(0x7B, 0x10FFFF)
-};
+		.addRange(0x7B, 0x10FFFF)]
+]);
 
-exports.UNICODE_IGNORE_CASE = {
-	'd': regenerate()
-		.addRange(0x30, 0x39),
-	'D': regenerate()
+exports.UNICODE_IGNORE_CASE = new Map([
+	['d', regenerate()
+		.addRange(0x30, 0x39)],
+	['D', regenerate()
 		.addRange(0x0, 0x2F)
-		.addRange(0x3A, 0x10FFFF),
-	's': regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
+		.addRange(0x3A, 0x10FFFF)],
+	['s', regenerate(0x20, 0xA0, 0x1680, 0x202F, 0x205F, 0x3000, 0xFEFF)
 		.addRange(0x9, 0xD)
 		.addRange(0x2000, 0x200A)
-		.addRange(0x2028, 0x2029),
-	'S': regenerate()
+		.addRange(0x2028, 0x2029)],
+	['S', regenerate()
 		.addRange(0x0, 0x8)
@@ -93,12 +95,12 @@ .addRange(0xE, 0x1F)
 		.addRange(0x3001, 0xFEFE)
-		.addRange(0xFF00, 0x10FFFF),
-	'w': regenerate(0x5F, 0x17F, 0x212A)
+		.addRange(0xFF00, 0x10FFFF)],
+	['w', regenerate(0x5F, 0x17F, 0x212A)
 		.addRange(0x30, 0x39)
 		.addRange(0x41, 0x5A)
-		.addRange(0x61, 0x7A),
-	'W': regenerate(0x4B, 0x53, 0x60)
+		.addRange(0x61, 0x7A)],
+	['W', regenerate(0x4B, 0x53, 0x60)
 		.addRange(0x0, 0x2F)
 		.addRange(0x3A, 0x40)
 		.addRange(0x5B, 0x5E)
-		.addRange(0x7B, 0x10FFFF)
-};
+		.addRange(0x7B, 0x10FFFF)]
+]);

package.json

 {
-	"name": "regexpu-core",
-	"version": "2.0.0",
-	"description": "regexpu’s core functionality (i.e. `rewritePattern(pattern, flag)`), capable of translating ES6 Unicode regular expressions to ES5.",
-	"homepage": "https://mths.be/regexpu",
-	"main": "rewrite-pattern.js",
-	"keywords": [
-		"codegen",
-		"desugaring",
-		"ecmascript",
-		"es5",
-		"es6",
-		"harmony",
-		"javascript",
-		"refactoring",
-		"regex",
-		"regexp",
-		"regular expressions",
-		"rewriting",
-		"syntax",
-		"transformation",
-		"transpile",
-		"transpiler",
-		"unicode"
-	],
-	"license": "MIT",
-	"author": {
-		"name": "Mathias Bynens",
-		"url": "https://mathiasbynens.be/"
-	},
-	"repository": {
-		"type": "git",
-		"url": "https://github.com/mathiasbynens/regexpu-core.git"
-	},
-	"bugs": "https://github.com/mathiasbynens/regexpu-core/issues",
-	"files": [
-		"LICENSE-MIT.txt",
-		"rewrite-pattern.js",
-		"data/character-class-escape-sets.js",
-		"data/iu-mappings.json"
-	],
-	"scripts": {
-		"build": "node scripts/iu-mappings.js && node scripts/character-class-escape-sets.js",
-		"test": "mocha tests",
-		"coverage": "istanbul cover --report html node_modules/.bin/_mocha tests/tests.js -- -u exports -R spec"
-	},
-	"dependencies": {
-		"regenerate": "^1.2.1",
-		"regjsgen": "^0.2.0",
-		"regjsparser": "^0.1.4"
-	},
-	"devDependencies": {
-		"coveralls": "^2.11.2",
-		"istanbul": "^0.4.0",
-		"jsesc": "^0.5.0",
-		"lodash": "^3.6.0",
-		"mocha": "^2.2.1",
-		"regexpu-fixtures": "^2.0.0",
-		"unicode-8.0.0": "^0.1.5"
-	}
+  "name": "regexpu-core",
+  "version": "3.0.1",
+  "description": "regexpu’s core functionality (i.e. `rewritePattern(pattern, flag)`), capable of translating ES6 Unicode regular expressions to ES5.",
+  "homepage": "https://mths.be/regexpu",
+  "main": "rewrite-pattern.js",
+  "engines": {
+    "node": ">=4"
+  },
+  "keywords": [
+    "codegen",
+    "desugaring",
+    "ecmascript",
+    "es5",
+    "es6",
+    "harmony",
+    "javascript",
+    "refactoring",
+    "regex",
+    "regexp",
+    "regular expressions",
+    "rewriting",
+    "syntax",
+    "transformation",
+    "transpile",
+    "transpiler",
+    "unicode"
+  ],
+  "license": "MIT",
+  "author": {
+    "name": "Mathias Bynens",
+    "url": "https://mathiasbynens.be/"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/mathiasbynens/regexpu-core.git"
+  },
+  "bugs": "https://github.com/mathiasbynens/regexpu-core/issues",
+  "files": [
+    "LICENSE-MIT.txt",
+    "rewrite-pattern.js",
+    "data/character-class-escape-sets.js",
+    "data/iu-mappings.js"
+  ],
+  "scripts": {
+    "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"
+  },
+  "dependencies": {
+    "regenerate": "^1.3.1",
+    "regenerate-unicode-properties": "^1.0.0",
+    "regjsgen": "^0.3.0",
+    "regjsparser": "^0.2.0",
+    "unicode-loose-match": "^2.0.7"
+  },
+  "devDependencies": {
+    "codecov": "^1.0.1",
+    "istanbul": "^0.4.0",
+    "jsesc": "^2.1.0",
+    "lodash": "^4.13.1",
+    "mocha": "^2.2.1",
+    "regexpu-fixtures": "^2.0.0",
+    "unicode-8.0.0": "^0.6.0"
+  }
 }

rewrite-pattern.js

@@ -1,33 +0,73 @@
-var generate = require('regjsgen').generate;
-var parse = require('regjsparser').parse;
-var regenerate = require('regenerate');
-var iuMappings = require('./data/iu-mappings.json');
-var ESCAPE_SETS = require('./data/character-class-escape-sets.js');
+'use strict';
 
-function getCharacterClassEscapeSet(character) {
-	if (unicode) {
-		if (ignoreCase) {
-			return ESCAPE_SETS.UNICODE_IGNORE_CASE[character];
+const generate = require('regjsgen').generate;
+const parse = require('regjsparser').parse;
+const regenerate = require('regenerate');
+const looseMatch = require('unicode-loose-match');
+const knownUnicodeProperties = new Set(
+	require('regenerate-unicode-properties')
+);
+const iuMappings = require('./data/iu-mappings.js');
+const ESCAPE_SETS = require('./data/character-class-escape-sets.js');
+
+const getCharacterClassEscapeSet = function(character) {
+	if (config.unicode) {
+		if (config.ignoreCase) {
+			return ESCAPE_SETS.UNICODE_IGNORE_CASE.get(character);
 		}
-		return ESCAPE_SETS.UNICODE[character];
+		return ESCAPE_SETS.UNICODE.get(character);
 	}
-	return ESCAPE_SETS.REGULAR[character];
-}
+	return ESCAPE_SETS.REGULAR.get(character);
+};
 
-var object = {};
-var hasOwnProperty = object.hasOwnProperty;
-function has(object, property) {
-	return hasOwnProperty.call(object, property);
-}
+const getUnicodePropertyValueSet = function(property, value) {
+	const path = knownUnicodeProperties.has(property) ?
+		`${ property }/${ value }` :
+		`Binary_Property/${ property }`;
+	try {
+		return require(`regenerate-unicode-properties/${ path }.js`);
+	} catch (exception) {
+		throw new Error(
+			`Failed to recognize value \`${ value }\` for property ` +
+			`\`${ property }\`.`
+		);
+	}
+};
 
+const getUnicodePropertyEscapeSet = function(value, isNegative) {
+	const parts = value.split('=');
+	let canonical;
+	if (parts.length == 1) {
+		const firstPart = parts[0];
+		// It could be a `General_Category` value or a binary property.
+		canonical = looseMatch('General_Category', firstPart);
+		if (!canonical.value) {
+			// It’s not a `General_Category` value, so check if it’s a binary
+			// property. Note: `looseMatch` throws on invalid properties.
+			canonical = looseMatch(firstPart);
+		}
+	} else {
+		// The pattern consists of two parts, i.e. `Property=Value`.
+		canonical = looseMatch(parts[0], parts[1]);
+	}
+	const set = getUnicodePropertyValueSet(
+		canonical.property,
+		canonical.value
+	).clone();
+	if (isNegative) {
+		return UNICODE_SET.clone().remove(set);
+	}
+	return set;
+};
+
 // Prepare a Regenerate set containing all code points, used for negative
 // character classes (if any).
-var UNICODE_SET = regenerate().addRange(0x0, 0x10FFFF);
+const UNICODE_SET = regenerate().addRange(0x0, 0x10FFFF);
 // Without the `u` flag, the range stops at 0xFFFF.
 // https://mths.be/es6#sec-pattern-semantics
-var BMP_SET = regenerate().addRange(0x0, 0xFFFF);
+const BMP_SET = regenerate().addRange(0x0, 0xFFFF);
 
 // Prepare a Regenerate set containing all code points that are supposed to be
 // matched by `/./u`. https://mths.be/es6#sec-atom
-var DOT_SET_UNICODE = UNICODE_SET.clone() // all Unicode code points
+const DOT_SET_UNICODE = UNICODE_SET.clone() // all Unicode code points
 	.remove(
@@ -42,3 +82,3 @@ // minus `LineTerminator`s (https://mths.be/es6#sec-line-terminators):
 // matched by `/./` (only BMP code points).
-var DOT_SET = DOT_SET_UNICODE.clone()
+const DOT_SET = DOT_SET_UNICODE.clone()
 	.intersection(BMP_SET);
@@ -49,5 +89,5 @@
 regenerate.prototype.iuAddRange = function(min, max) {
-	var $this = this;
+	const $this = this;
 	do {
-		var folded = caseFold(min);
+		const folded = caseFold(min);
 		if (folded) {
@@ -60,15 +100,4 @@ $this.add(folded);
 
-function assign(target, source) {
-	for (var key in source) {
-		// Note: `hasOwnProperty` is not needed here.
-		target[key] = source[key];
-	}
-}
-
-function update(item, pattern) {
-	// TODO: Test if memoizing `pattern` here is worth the effort.
-	if (!pattern) {
-		return;
-	}
-	var tree = parse(pattern, '');
+const update = function(item, pattern) {
+	let tree = parse(pattern, config.useUnicodeFlag ? 'u' : '');
 	switch (tree.type) {
@@ -84,6 +113,6 @@ case 'characterClass':
 	}
-	assign(item, tree);
-}
+	Object.assign(item, tree);
+};
 
-function wrap(tree, pattern) {
+const wrap = function(tree, pattern) {
 	// Wrap the pattern in a non-capturing group.
@@ -94,20 +123,18 @@ return {
 		'body': [tree],
-		'raw': '(?:' + pattern + ')'
+		'raw': `(?:${ pattern })`
 	};
-}
+};
 
-function caseFold(codePoint) {
-	return has(iuMappings, codePoint) ? iuMappings[codePoint] : false;
-}
+const caseFold = function(codePoint) {
+	return iuMappings.get(codePoint) || false;
+};
 
-var ignoreCase = false;
-var unicode = false;
-function processCharacterClass(characterClassItem) {
-	var set = regenerate();
-	var body = characterClassItem.body.forEach(function(item) {
+const processCharacterClass = function(characterClassItem, regenerateOptions) {
+	let set = regenerate();
+	const body = characterClassItem.body.forEach(function(item) {
 		switch (item.type) {
 			case 'value':
 				set.add(item.codePoint);
-				if (ignoreCase && unicode) {
-					var folded = caseFold(item.codePoint);
+				if (config.ignoreCase && config.unicode) {
+					const folded = caseFold(item.codePoint);
 					if (folded) {
@@ -119,6 +146,6 @@ set.add(folded);
 			case 'characterClassRange':
-				var min = item.min.codePoint;
-				var max = item.max.codePoint;
+				const min = item.min.codePoint;
+				const max = item.max.codePoint;
 				set.addRange(min, max);
-				if (ignoreCase && unicode) {
+				if (config.ignoreCase && config.unicode) {
 					set.iuAddRange(min, max);
@@ -130,2 +157,5 @@ }
 				break;
+			case 'unicodePropertyEscape':
+				set.add(getUnicodePropertyEscapeSet(item.value, item.negative));
+				break;
 			// The `default` clause is only here as a safeguard; it should never be
@@ -135,13 +165,13 @@ // reached. Code coverage tools should ignore it.
 			default:
-				throw Error('Unknown term type: ' + item.type);
+				throw new Error(`Unknown term type: ${ item.type }`);
 		}
 	});
 	if (characterClassItem.negative) {
-		set = (unicode ? UNICODE_SET : BMP_SET).clone().remove(set);
+		set = (config.unicode ? UNICODE_SET : BMP_SET).clone().remove(set);
 	}
-	update(characterClassItem, set.toString());
+	update(characterClassItem, set.toString(regenerateOptions));
 	return characterClassItem;
-}
+};
 
-function processTerm(item) {
+const processTerm = function(item, regenerateOptions) {
 	switch (item.type) {
@@ -151,12 +181,20 @@ case 'dot':
 				item,
-				(unicode ? DOT_SET_UNICODE : DOT_SET).toString()
+				(config.unicode ? DOT_SET_UNICODE : DOT_SET)
+					.toString(regenerateOptions)
 			);
 			break;
 		case 'characterClass':
-			item = processCharacterClass(item);
+			item = processCharacterClass(item, regenerateOptions);
 			break;
+		case 'unicodePropertyEscape':
+			update(
+				item,
+				getUnicodePropertyEscapeSet(item.value, item.negative)
+					.toString(regenerateOptions)
+			);
+			break;
 		case 'characterClassEscape':
 			update(
 				item,
-				getCharacterClassEscapeSet(item.value).toString()
+				getCharacterClassEscapeSet(item.value).toString(regenerateOptions)
 			);
@@ -171,6 +209,6 @@ break;
 		case 'value':
-			var codePoint = item.codePoint;
-			var set = regenerate(codePoint);
-			if (ignoreCase && unicode) {
-				var folded = caseFold(codePoint);
+			const codePoint = item.codePoint;
+			const set = regenerate(codePoint);
+			if (config.ignoreCase && config.unicode) {
+				const folded = caseFold(codePoint);
 				if (folded) {
@@ -180,3 +218,3 @@ set.add(folded);
 			}
-			update(item, set.toString());
+			update(item, set.toString(regenerateOptions));
 			break;
@@ -193,3 +231,3 @@ case 'anchor':
 		default:
-			throw Error('Unknown term type: ' + item.type);
+			throw new Error(`Unknown term type: ${ item.type }`);
 	}
@@ -199,8 +237,22 @@ return item;
 
-module.exports = function(pattern, flags) {
-	var tree = parse(pattern, flags);
-	ignoreCase = flags ? flags.indexOf('i') > -1 : false;
-	unicode = flags ? flags.indexOf('u') > -1 : false;
-	assign(tree, processTerm(tree));
+const config = {
+	'ignoreCase': false,
+	'unicode': false,
+	'useUnicodeFlag': false
+};
+const rewritePattern = function(pattern, flags, options) {
+	const regjsparserFeatures = {
+		'unicodePropertyEscape': options && options.unicodePropertyEscape
+	};
+	config.useUnicodeFlag = options && options.useUnicodeFlag;
+	const regenerateOptions = {
+		'hasUnicodeFlag': config.useUnicodeFlag
+	};
+	const tree = parse(pattern, flags, regjsparserFeatures);
+	config.ignoreCase = flags && flags.includes('i');
+	config.unicode = flags && flags.includes('u');
+	Object.assign(tree, processTerm(tree, regenerateOptions));
 	return generate(tree);
 };
+
+module.exports = rewritePattern;

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Major refactor

Supply chain risk

Package has recently undergone a major refactor. It may be unstable or indicate significant internal changes. Use caution when updating to versions that include significant changes.

Found 1 instance in 1 package

No README

Quality

Package does not have a README. This may indicate a failed publish or a low quality package.

Found 1 instance in 1 package

Dynamic require

Supply chain risk

Dynamic require can indicate the package is performing dangerous or unsafe dynamic code execution.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

18357

increased by3.05%

Lines of code

626

increased by8.87%

Worsened metrics

Dependency count

5

increased by66.67%

Number of package files

5

decreased by-16.67%

Number of medium quality alerts

1

increased byInfinity%

Number of lines in readme file

0

decreased by-100%

Number of low supply chain risk alerts

1

increased byInfinity%

Number of medium supply chain risk alerts

1

increased byInfinity%

Dependency changes

• + Addedregenerate-unicode-properties@^1.0.0

• + Addedunicode-loose-match@^2.0.7

• + Addedregenerate-unicode-properties@1.0.0(transitive)

• + Addedregjsgen@0.3.0(transitive)

• + Addedregjsparser@0.2.1(transitive)

• + Addedunicode-loose-match@2.7.0(transitive)

• - Removedregjsgen@0.2.0(transitive)

• - Removedregjsparser@0.1.5(transitive)

• Updatedregenerate@^1.3.1

• Updatedregjsgen@^0.3.0

• Updatedregjsparser@^0.2.0