regexpu-core - npm Package Compare versions

Comparing version 5.2.2 to 5.3.0

package.json

 {
 	"name": "regexpu-core",
-	"version": "5.2.2",
+	"version": "5.3.0",
 	"description": "regexpu’s core functionality (i.e. `rewritePattern(pattern, flag)`), capable of translating ES6 Unicode regular expressions to ES5.",
@@ -53,3 +53,3 @@ "homepage": "https://mths.be/regexpu",
 		"regenerate-unicode-properties": "^10.1.0",
-		"regjsgen": "^0.7.1",
+		"@babel/regjsgen": "^0.8.0",
 		"regjsparser": "^0.9.1",
@@ -65,5 +65,5 @@ "unicode-match-property-ecmascript": "^2.0.0",
 		"mocha": "^10.1.0",
-		"regexpu-fixtures": "2.1.4",
+		"regexpu-fixtures": "mathiasbynens/regexpu-fixtures",
 		"@unicode/unicode-15.0.0": "^1.3.1"
 	}
 }

README.md

@@ -149,3 +149,11 @@ # 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)
 
+- `modifiers` - [Inline `m`/`s`/`i` modifiers](https://github.com/tc39/proposal-regexp-modifiers)
 
+  ```js
+  rewritePattern('(?i:[a-z])[a-z]', '', {
+    modifiers: 'transform'
+  });
+  // → '(?:[a-zA-Z])([a-z])'
+  ```
+
 #### Miscellaneous options
@@ -167,2 +175,16 @@
 
+- `onNewFlags`
+
+  This option is a function that gets called to pass the flags that the resulting pattern must be interpreted with.
+
+  ```js
+  rewritePattern('abc', 'um', '', {
+    unicodeFlag: 'transform',
+    onNewFlags(flags) {
+      console.log(flags);
+      // → 'm'
+    }
+  })
+  ```
+
 ### Caveats
@@ -169,0 +191,0 @@

rewrite-pattern.js

 'use strict';
 
-const generate = require('regjsgen').generate;
+const generate = require('@babel/regjsgen').generate;
 const parse = require('regjsparser').parse;
@@ -30,12 +30,16 @@ const regenerate = require('regenerate');
 
+const ASTRAL_SET = regenerate().addRange(0x10000, 0x10FFFF);
+
+const NEWLINE_SET = regenerate().add(
+	// `LineTerminator`s (https://mths.be/es6#sec-line-terminators):
+	0x000A, // Line Feed <LF>
+	0x000D, // Carriage Return <CR>
+	0x2028, // Line Separator <LS>
+	0x2029  // Paragraph Separator <PS>
+);
+
 // Prepare a Regenerate set containing all code points that are supposed to be
 // matched by `/./u`. https://mths.be/es6#sec-atom
 const DOT_SET_UNICODE = UNICODE_SET.clone() // all Unicode code points
-	.remove(
-		// minus `LineTerminator`s (https://mths.be/es6#sec-line-terminators):
-		0x000A, // Line Feed <LF>
-		0x000D, // Carriage Return <CR>
-		0x2028, // Line Separator <LS>
-		0x2029  // Paragraph Separator <PS>
-	);
+	.remove(NEWLINE_SET);
 
@@ -130,2 +134,13 @@ const getCharacterClassEscapeSet = (character, unicode, ignoreCase) => {
 
+function configNeedCaseFoldAscii() {
+	return !!config.modifiersData.i;
+}
+
+function configNeedCaseFoldUnicode() {
+	// config.modifiersData.i : undefined | false
+	if (config.modifiersData.i === false) return false;
+	if (!config.transform.unicodeFlag) return false;
+	return Boolean(config.modifiersData.i || config.flags.ignoreCase);
+}
+
 // Given a range of code points, add any case-folded code points in that range
@@ -136,3 +151,3 @@ // to a set.
 	do {
-		const folded = caseFold(min);
+		const folded = caseFold(min, configNeedCaseFoldAscii(), configNeedCaseFoldUnicode());
 		if (folded) {
@@ -147,3 +162,3 @@ $this.add(folded);
 	do {
-		const folded = caseFold(min);
+		const folded = caseFold(min, configNeedCaseFoldAscii(), configNeedCaseFoldUnicode());
 		if (folded) {
@@ -157,3 +172,9 @@ $this.remove(folded);
 const update = (item, pattern) => {
-	let tree = parse(pattern, config.useUnicodeFlag ? 'u' : '');
+	let tree = parse(pattern, config.useUnicodeFlag ? 'u' : '', {
+		lookbehind: true,
+		namedGroups: true,
+		unicodePropertyEscape: true,
+		unicodeSet: true,
+		modifiers: true,
+	});
 	switch (tree.type) {
@@ -182,4 +203,13 @@ case 'characterClass':
 
-const caseFold = (codePoint) => {
-	return iuMappings.get(codePoint) || false;
+const caseFold = (codePoint, includeAscii, includeUnicode) => {
+	let folded = (includeUnicode ? iuMappings.get(codePoint) : undefined) || [];
+	if (typeof folded === 'number') folded = [folded];
+	if (includeAscii) {
+		if (codePoint >= 0x41 && codePoint <= 0x5A) {
+			folded.push(codePoint + 0x20);
+		} else if (codePoint >= 0x61 && codePoint <= 0x7A) {
+			folded.push(codePoint - 0x20);
+		}
+	}
+	return folded.length == 0 ? false : folded;
 };
@@ -325,4 +355,7 @@
 const maybeFold = (codePoint) => {
-	if (config.flags.ignoreCase && config.transform.unicodeFlag) {
-		const folded = caseFold(codePoint);
+	const caseFoldAscii = configNeedCaseFoldAscii();
+	const caseFoldUnicode = configNeedCaseFoldUnicode();
+
+	if (caseFoldAscii || caseFoldUnicode) {
+		const folded = caseFold(codePoint, caseFoldAscii, caseFoldUnicode);
 		if (folded) {
@@ -338,2 +371,5 @@ return [codePoint, folded];
 
+	const caseFoldAscii = configNeedCaseFoldAscii();
+	const caseFoldUnicode = configNeedCaseFoldUnicode();
+
 	for (const string of classStrings.strings) {
@@ -346,7 +382,7 @@ if (string.characters.length === 1) {
 			let stringifiedString;
-			if (config.flags.ignoreCase && config.transform.unicodeFlag) {
+			if (caseFoldUnicode || caseFoldAscii) {
 				stringifiedString = '';
 				for (const ch of string.characters) {
 					let set = regenerate(ch.codePoint);
-					const folded = caseFold(ch.codePoint);
+					const folded = maybeFold(ch.codePoint);
 					if (folded) set.add(folded);
@@ -393,2 +429,5 @@ stringifiedString += set.toString(regenerateOptions);
 
+	const caseFoldAscii = configNeedCaseFoldAscii();
+	const caseFoldUnicode = configNeedCaseFoldUnicode();
+
 	for (const item of characterClassItem.body) {
@@ -405,4 +444,5 @@ switch (item.type) {
 				handlePositive.range(data, min, max);
-				if (config.flags.ignoreCase && config.transform.unicodeFlag) {
+				if (caseFoldAscii || caseFoldUnicode) {
 					handlePositive.iuRange(data, min, max);
+					data.transformed = true;
 				}
@@ -466,3 +506,34 @@ break;
 			} else {
-				update(characterClassItem, `(?!${setStr})[\\s\\S]`)
+				if (config.flags.unicode) {
+					if (config.flags.ignoreCase) {
+						const astralCharsSet = singleChars.clone().intersection(ASTRAL_SET);
+						// Assumption: singleChars do not contain lone surrogates.
+						// Regex like /[^\ud800]/u is not supported
+						const surrogateOrBMPSetStr = singleChars
+							.clone()
+							.remove(astralCharsSet)
+							.addRange(0xd800, 0xdfff)
+							.toString({ bmpOnly: true });
+						// Don't generate negative lookahead for astral characters
+						// because the case folding is not working anyway as we break
+						// code points into surrogate pairs.
+						const astralNegativeSetStr = ASTRAL_SET
+							.clone()
+							.remove(astralCharsSet)
+							.toString(regenerateOptions);
+						// The transform here does not support lone surrogates.
+						update(
+							characterClassItem,
+							`(?!${surrogateOrBMPSetStr})[\\s\\S]|${astralNegativeSetStr}`
+						);
+					} else {
+						// Generate negative set directly when case folding is not involved.
+						update(
+							characterClassItem,
+							UNICODE_SET.clone().remove(singleChars).toString(regenerateOptions)
+						);
+					}
+				} else {
+					update(characterClassItem, `(?!${setStr})[\\s\\S]`);
+				}
 			}
@@ -490,2 +561,27 @@ } else {
 
+const processModifiers = (item, regenerateOptions, groups) => {
+	const enabling = item.modifierFlags.enabling;
+	const disabling = item.modifierFlags.disabling;
+
+	delete item.modifierFlags;
+	item.behavior = 'ignore';
+
+	const oldData = Object.assign({}, config.modifiersData);
+
+	enabling.split('').forEach(flag => {
+		config.modifiersData[flag] = true;
+	});
+	disabling.split('').forEach(flag => {
+		config.modifiersData[flag] = false;
+	});
+
+	item.body = item.body.map(term => {
+		return processTerm(term, regenerateOptions, groups);
+	});
+
+	config.modifiersData = oldData;
+
+	return item;
+}
+
 const processTerm = (item, regenerateOptions, groups) => {
@@ -497,5 +593,5 @@ switch (item.type) {
 					item,
-					getUnicodeDotSet(config.flags.dotAll).toString(regenerateOptions)
+					getUnicodeDotSet(config.flags.dotAll || config.modifiersData.s).toString(regenerateOptions)
 				);
-			} else if (config.transform.dotAllFlag) {
+			} else if (config.transform.dotAllFlag || config.modifiersData.s) {
 				// TODO: consider changing this at the regenerate level.
@@ -571,2 +667,5 @@ update(item, '[\\s\\S]');
 			}
+			if (item.modifierFlags && config.transform.modifiers) {
+				return processModifiers(item, regenerateOptions, groups);
+			}
 			/* falls through */
@@ -595,8 +694,4 @@ case 'quantifier':
 			const set = regenerate(codePoint);
-			if (config.flags.ignoreCase && config.transform.unicodeFlag) {
-				const folded = caseFold(codePoint);
-				if (folded) {
-					set.add(folded);
-				}
-			}
+			const folded = maybeFold(codePoint);
+			set.add(folded);
 			update(item, set.toString(regenerateOptions));
@@ -641,4 +736,10 @@ break;
 		case 'anchor':
+			if (config.modifiersData.m) {
+				if (item.kind == 'start') {
+					update(item, `(?:^|(?<=${NEWLINE_SET.toString()}))`);
+				} else if (item.kind == 'end') {
+					update(item, `(?:$|(?=${NEWLINE_SET.toString()}))`);
+				}
+			}
 		case 'empty':
-		case 'group':
 			// Nothing to do here.
@@ -661,2 +762,3 @@ break;
 		'dotAll': false,
+		'multiline': false,
 	},
@@ -669,3 +771,9 @@ 'transform': {
 		'namedGroups': false,
+		'modifiers': false,
 	},
+	'modifiersData': {
+		'i': undefined,
+		's': undefined,
+		'm': undefined,
+	},
 	get useUnicodeFlag() {
@@ -690,2 +798,3 @@ return (this.flags.unicode || this.flags.unicodeSets) && !this.transform.unicodeFlag;
 				break;
+			case 'modifiers':
 			case 'unicodeSetsFlag':
@@ -697,4 +806,5 @@ if (value != null && value !== false && value !== 'parse' && value !== 'transform') {
 			case 'onNamedGroup':
+			case 'onNewFlags':
 				if (value != null && typeof value !== 'function') {
-					throw new Error('.onNamedGroup must be a function.');
+					throw new Error(`.${key} must be a function.`);
 				}
@@ -718,2 +828,3 @@ break;
 	config.flags.dotAll = hasFlag(flags, 's');
+	config.flags.multiline = hasFlag(flags, 'm');
 
@@ -729,5 +840,11 @@ config.transform.dotAllFlag = config.flags.dotAll && transform(options, 'dotAllFlag');
 	config.transform.namedGroups = transform(options, 'namedGroups');
+	config.transform.modifiers = transform(options, 'modifiers');
 
+	config.modifiersData.i = undefined;
+	config.modifiersData.s = undefined;
+	config.modifiersData.m = undefined;
+
 	const regjsparserFeatures = {
 		'unicodeSet': Boolean(options && options.unicodeSetsFlag),
+		'modifiers': Boolean(options && options.modifiers),
 
@@ -754,5 +871,50 @@ // Enable every stable RegExp feature by default
 	const tree = parse(pattern, flags, regjsparserFeatures);
+
+	if (config.transform.modifiers) {
+		if (/\(\?[a-z]*-[a-z]+:/.test(pattern)) {
+			// the pattern _likely_ contain inline disabled modifiers
+			// we need to traverse to make sure that they are actually modifiers and to collect them
+			const allDisabledModifiers = Object.create(null)
+			const itemStack = [tree];
+			let node;
+			while (node = itemStack.pop(), node != undefined) {
+				if (Array.isArray(node)) {
+					Array.prototype.push.apply(itemStack, node);
+				} else if (typeof node == 'object' && node != null) {
+					for (const key of Object.keys(node)) {
+						const value = node[key];
+						if (key == 'modifierFlags') {
+							if (value.disabling.length > 0){
+								value.disabling.split("").forEach((flag)=>{
+									allDisabledModifiers[flag] = true
+								});
+							}
+						} else if (typeof value == 'object' && value != null) {
+							itemStack.push(value);
+						}
+					}
+				}
+			}
+			for (const flag of Object.keys(allDisabledModifiers)) {
+				config.modifiersData[flag] = true;
+			}
+		}
+	}
+
 	// Note: `processTerm` mutates `tree` and `groups`.
 	processTerm(tree, regenerateOptions, groups);
 	assertNoUnmatchedReferences(groups);
+
+	const onNewFlags = options && options.onNewFlags;
+	if (onNewFlags) onNewFlags(flags.split('').filter((flag) => {
+		switch (flag) {
+			case 'u':
+				return !config.transform.unicodeFlag;
+			case 'v':
+				return !config.transform.unicodeSetsFlag;
+			default:
+				return !config.modifiersData[flag];
+		}
+	}).join(''));
+
 	return generate(tree);
@@ -759,0 +921,0 @@ };

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

New author

Supply chain risk

A new npm collaborator published a version of the package for the first time. New collaborators are usually benign additions to a project, but do indicate a change to the security surface area of a package.

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

53540

increased by11.89%

Lines of code

1579

increased by9.96%

Number of lines in readme file

227

increased by10.73%

Worsened metrics

Number of medium supply chain risk alerts

1

increased byInfinity%

Dependency changes

• + Added@babel/regjsgen@^0.8.0

• + Added@babel/regjsgen@0.8.0(transitive)

• - Removedregjsgen@^0.7.1

• - Removedregjsgen@0.7.1(transitive)