@xmldom/xmldom 0.9.6 → 0.9.8

package/CHANGELOG.md

@@ -4,6 +4,50 @@ All notable changes to this project will be documented in this file.
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.9.8](https://github.com/xmldom/xmldom/compare/0.9.8...0.9.7)
+
+### Fixed
+
+- fix: replace \u2029 as part of normalizeLineEndings [`#839`](https://github.com/xmldom/xmldom/pull/839) / [`#838`](https://github.com/xmldom/xmldom/issues/838)
+- perf: speed up line detection [`#847`](https://github.com/xmldom/xmldom/pull/847) / [`#838`](https://github.com/xmldom/xmldom/issues/838)
+
+### Chore
+
+- updated dependencies
+- drop jazzer and rxjs devDependencies [`#845`](https://github.com/xmldom/xmldom/pull/845)
+
+Thank you,
+[@kboshold](https://github.com/kboshold),
+[@Ponynjaa](https://github.com/Ponynjaa),
+for your contributions.
+
+
+## [0.9.7](https://github.com/xmldom/xmldom/compare/0.9.6...0.9.7)
+
+### Added
+
+- Implementation of `hasAttributes` [`#804`](https://github.com/xmldom/xmldom/pull/804)
+
+### Fixed
+
+- locator is now true even when other options are being used for the DOMParser [`#802`](https://github.com/xmldom/xmldom/issues/802) / [`#803`](https://github.com/xmldom/xmldom/pull/803)
+- allow case-insensitive DOCTYPE in HTML [`#817`](https://github.com/xmldom/xmldom/issues/817) / [`#819`](https://github.com/xmldom/xmldom/pull/819)
+
+### Performance
+
+- simplify `DOM.compareDocumentPosition` [`#805`](https://github.com/xmldom/xmldom/pull/805)
+
+### Chore
+
+- updated devDependencies
+
+Thank you,
+[@zorkow](https://github.com/zorkow),
+[@Ponynjaa](https://github.com/Ponynjaa),
+[@WesselKroos](https://github.com/WesselKroos),
+for your contributions.
+
+
 ## [0.9.6](https://github.com/xmldom/xmldom/compare/0.9.5...0.9.6)
 
 ### Fixed

package/index.d.ts

@@ -1527,12 +1527,15 @@ declare module '@xmldom/xmldom' {
 		readonly locator?: boolean;
 
 		/**
-		 * used to replace line endings before parsing, defaults to `normalizeLineEndings`,
-		 * which normalizes line endings according to <https://www.w3.org/TR/xml11/#sec-line-ends>.
+		 * used to replace line endings before parsing, defaults to exported `normalizeLineEndings`,
+		 * which normalizes line endings according to <https://www.w3.org/TR/xml11/#sec-line-ends>,
+		 * including some Unicode "newline" characters.
+		 *
+		 * @see {@link normalizeLineEndings}
 		 */
 		readonly normalizeLineEndings?: (source: string) => string;
 		/**
-		 * A function that is invoked for every error that occurs during parsing.
+		 * A function invoked for every error that occurs during parsing.
 		 *
 		 * If it is not provided, all errors are reported to `console.error`
 		 * and only `fatalError`s are thrown as a `ParseError`,
@@ -1572,6 +1575,29 @@ declare module '@xmldom/xmldom' {
 		): void;
 	}
 
+	/**
+	 * Normalizes line ending according to <https://www.w3.org/TR/xml11/#sec-line-ends>,
+	 * including some Unicode "newline" characters:
+	 *
+	 * > XML parsed entities are often stored in computer files which,
+	 * > for editing convenience, are organized into lines.
+	 * > These lines are typically separated by some combination
+	 * > of the characters CARRIAGE RETURN (#xD) and LINE FEED (#xA).
+	 * >
+	 * > To simplify the tasks of applications, the XML processor must behave
+	 * > as if it normalized all line breaks in external parsed entities (including the document entity)
+	 * > on input, before parsing, by translating the following to a single #xA character:
+	 * >
+	 * > 1. the two-character sequence #xD #xA,
+	 * > 2. the two-character sequence #xD #x85,
+	 * > 3. the single character #x85,
+	 * > 4. the single character #x2028,
+	 * > 5. the single character #x2029,
+	 * > 6. any #xD character that is not immediately followed by #xA or #x85.
+	 *
+	 * @prettierignore
+	 */
+	function normalizeLineEndings(input: string): string;
 	/**
 	 * A method that prevents any further parsing when an `error`
 	 * with level `error` is reported during parsing.

package/lib/conventions.js

@@ -324,7 +324,7 @@ var MIME_TYPE = freeze({
 	XML_APPLICATION: 'application/xml',
 
 	/**
-	 * `text/html`, an alias for `application/xml`.
+	 * `text/xml`, an alias for `application/xml`.
 	 *
 	 * @see https://tools.ietf.org/html/rfc7303#section-9.2 RFC 7303
 	 * @see https://www.iana.org/assignments/media-types/text/xml IANA MimeType registration

package/lib/dom-parser.js

@@ -18,7 +18,8 @@ var ParseError = errors.ParseError;
 var XMLReader = sax.XMLReader;
 
 /**
- * Normalizes line ending according to <https://www.w3.org/TR/xml11/#sec-line-ends>:
+ * Normalizes line ending according to <https://www.w3.org/TR/xml11/#sec-line-ends>,
+ * including some Unicode "newline" characters:
  *
  * > XML parsed entities are often stored in computer files which,
  * > for editing convenience, are organized into lines.
@@ -27,20 +28,21 @@ var XMLReader = sax.XMLReader;
  * >
  * > To simplify the tasks of applications, the XML processor must behave
  * > as if it normalized all line breaks in external parsed entities (including the document entity)
- * > on input, before parsing, by translating all of the following to a single #xA character:
+ * > on input, before parsing, by translating the following to a single #xA character:
  * >
  * > 1. the two-character sequence #xD #xA,
  * > 2. the two-character sequence #xD #x85,
  * > 3. the single character #x85,
  * > 4. the single character #x2028,
- * > 5. any #xD character that is not immediately followed by #xA or #x85.
+ * > 5. the single character #x2029,
+ * > 6. any #xD character that is not immediately followed by #xA or #x85.
  *
  * @param {string} input
  * @returns {string}
  * @prettierignore
  */
 function normalizeLineEndings(input) {
-	return input.replace(/\r[\n\u0085]/g, '\n').replace(/[\r\u0085\u2028]/g, '\n');
+	return input.replace(/\r[\n\u0085]/g, '\n').replace(/[\r\u0085\u2028\u2029]/g, '\n');
 }
 
 /**
@@ -63,7 +65,7 @@ function normalizeLineEndings(input) {
  * DEPRECATED! use `onError` instead.
  * @property {function(level:ErrorLevel, message:string, context: DOMHandler):void}
  * [onError]
- * A function that is invoked for every error that occurs during parsing.
+ * A function invoked for every error that occurs during parsing.
  *
  * If it is not provided, all errors are reported to `console.error`
  * and only `fatalError`s are thrown as a `ParseError`,
@@ -78,7 +80,9 @@ function normalizeLineEndings(input) {
  * attribute describing their location in the XML string.
  * Default is true.
  * @property {(string) => string} [normalizeLineEndings]
- * used to replace line endings before parsing, defaults to `normalizeLineEndings`
+ * used to replace line endings before parsing, defaults to exported `normalizeLineEndings`,
+ * which normalizes line endings according to <https://www.w3.org/TR/xml11/#sec-line-ends>,
+ * including some Unicode "newline" characters.
  * @property {Object} [xmlns]
  * The XML namespaces that should be assumed when parsing.
  * The default namespace can be provided by the key that is the empty string.
@@ -101,7 +105,10 @@ function normalizeLineEndings(input) {
  * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-parsing-and-serialization
  */
 function DOMParser(options) {
-	options = options || { locator: true };
+	options = options || {};
+	if (options.locator === undefined) {
+		options.locator = true;
+	}
 
 	/**
 	 * The method to use instead of `conventions.assign`, which is used to copy values from

package/lib/dom.js

@@ -257,23 +257,6 @@ var DocumentPosition = conventions.freeze({
 });
 
 //helper functions for compareDocumentPosition
-/**
- * Constructs a parent chain for a node.
- *
- * @param {Node} node
- * The start node from which the parent chain will be constructed.
- * @returns {Node[]}
- * The array of nodes representing the parent chain from the root to the specified node.
- */
-function parentChain(node) {
-	var chain = [];
-	while (node.parentNode || node.ownerElement) {
-		node = node.parentNode || node.ownerElement;
-		chain.unshift(node);
-	}
-	return chain;
-}
-
 /**
  * Finds the common ancestor in two parent chains.
  *
@@ -1476,15 +1459,36 @@ Node.prototype = {
 					: DocumentPosition.DOCUMENT_POSITION_PRECEDING)
 			);
 		}
-		var chain1 = parentChain(node1);
-		var chain2 = parentChain(node2);
-		if ((!attr1 && chain2.indexOf(node1) >= 0) || (attr2 && node1 === node2)) {
+		if (attr2 && node1 === node2) {
 			return DocumentPosition.DOCUMENT_POSITION_CONTAINS + DocumentPosition.DOCUMENT_POSITION_PRECEDING;
 		}
-		if ((!attr2 && chain1.indexOf(node2) >= 0) || (attr1 && node1 === node2)) {
+		if (attr1 && node1 === node2) {
 			return DocumentPosition.DOCUMENT_POSITION_CONTAINED_BY + DocumentPosition.DOCUMENT_POSITION_FOLLOWING;
 		}
-		var ca = commonAncestor(chain2, chain1);
+
+		var chain1 = [];
+		var ancestor1 = node1.parentNode;
+		while (ancestor1) {
+			if (!attr2 && ancestor1 === node2) {
+				return DocumentPosition.DOCUMENT_POSITION_CONTAINED_BY + DocumentPosition.DOCUMENT_POSITION_FOLLOWING;
+			}
+			chain1.push(ancestor1);
+			ancestor1 = ancestor1.parentNode;
+		}
+		chain1.reverse();
+
+		var chain2 = [];
+		var ancestor2 = node2.parentNode;
+		while (ancestor2) {
+			if (!attr1 && ancestor2 === node1) {
+				return DocumentPosition.DOCUMENT_POSITION_CONTAINS + DocumentPosition.DOCUMENT_POSITION_PRECEDING;
+			}
+			chain2.push(ancestor2);
+			ancestor2 = ancestor2.parentNode;
+		}
+		chain2.reverse();
+
+		var ca = commonAncestor(chain1, chain2);
 		for (var n in ca.childNodes) {
 			var child = ca.childNodes[n];
 			if (child === node2) return DocumentPosition.DOCUMENT_POSITION_FOLLOWING;
@@ -2353,6 +2357,16 @@ Element.prototype = {
 	_isInHTMLDocumentAndNamespace: function () {
 		return this.ownerDocument.type === 'html' && this.namespaceURI === NAMESPACE.HTML;
 	},
+	/**
+	 * Implementaton of Level2 Core function hasAttributes.
+	 *
+	 * @returns {boolean}
+	 * True if attribute list is not empty.
+	 * @see https://www.w3.org/TR/DOM-Level-2-Core/#core-ID-NodeHasAttrs
+	 */
+	hasAttributes: function () {
+		return !!(this.attributes && this.attributes.length);
+	},
 	hasAttribute: function (name) {
 		return !!this.getAttributeNode(name);
 	},

package/lib/grammar.js

@@ -381,6 +381,9 @@ var ATTLIST_DECL_START = '<!ATTLIST';
 // to support XML without namespaces in DTD we can not restrict it to QName
 var AttlistDecl = reg(ATTLIST_DECL_START, S, Name, AttDef, '*', S_OPT, '>');
 
+// https://html.spec.whatwg.org/multipage/urls-and-fetching.html#about:legacy-compat
+var ABOUT_LEGACY_COMPAT = 'about:legacy-compat';
+var ABOUT_LEGACY_COMPAT_SystemLiteral = regg('"' + ABOUT_LEGACY_COMPAT + '"', '|', "'" + ABOUT_LEGACY_COMPAT + "'");
 var SYSTEM = 'SYSTEM';
 var PUBLIC = 'PUBLIC';
 // https://www.w3.org/TR/xml11/#NT-ExternalID
@@ -494,6 +497,8 @@ exports.chars_without = chars_without;
 exports.detectUnicodeSupport = detectUnicodeSupport;
 exports.reg = reg;
 exports.regg = regg;
+exports.ABOUT_LEGACY_COMPAT = ABOUT_LEGACY_COMPAT;
+exports.ABOUT_LEGACY_COMPAT_SystemLiteral = ABOUT_LEGACY_COMPAT_SystemLiteral;
 exports.AttlistDecl = AttlistDecl;
 exports.CDATA_START = CDATA_START;
 exports.CDATA_END = CDATA_END;

package/lib/index.js

@@ -36,5 +36,6 @@ exports.XMLSerializer = dom.XMLSerializer;
 
 var domParser = require('./dom-parser');
 exports.DOMParser = domParser.DOMParser;
+exports.normalizeLineEndings = domParser.normalizeLineEndings;
 exports.onErrorStopParsing = domParser.onErrorStopParsing;
 exports.onWarningStopParsing = domParser.onWarningStopParsing;

package/lib/sax.js

@@ -81,7 +81,7 @@ function parse(source, defaultNSMapCopy, entityMap, domBuilder, errorHandler) {
 		if (hasOwn(entityMap, k)) {
 			return entityMap[k];
 		} else if (k.charAt(0) === '#') {
-			return fixedFromCharCode(parseInt(k.substr(1).replace('x', '0x')));
+			return fixedFromCharCode(parseInt(k.substring(1).replace('x', '0x')));
 		} else {
 			errorHandler.error('entity not found:' + a);
 			return a;
@@ -98,20 +98,20 @@ function parse(source, defaultNSMapCopy, entityMap, domBuilder, errorHandler) {
 		}
 	}
 
+	var lineStart = 0;
+	var lineEnd = 0;
+	var linePattern = /\r\n?|\n|$/g;
+	var locator = domBuilder.locator;
+
 	function position(p, m) {
 		while (p >= lineEnd && (m = linePattern.exec(source))) {
-			lineStart = m.index;
-			lineEnd = lineStart + m[0].length;
+			lineStart = lineEnd;
+			lineEnd = m.index + m[0].length;
 			locator.lineNumber++;
 		}
 		locator.columnNumber = p - lineStart + 1;
 	}
 
-	var lineStart = 0;
-	var lineEnd = 0;
-	var linePattern = /.*(?:\r\n?|\n)|.*$/g;
-	var locator = domBuilder.locator;
-
 	var parseStack = [{ currentNSMap: defaultNSMapCopy }];
 	var unclosedTags = [];
 	var start = 0;
@@ -124,7 +124,7 @@ function parse(source, defaultNSMapCopy, entityMap, domBuilder, errorHandler) {
 				}
 				if (!source.substring(start).match(/^\s*$/)) {
 					var doc = domBuilder.doc;
-					var text = doc.createTextNode(source.substr(start));
+					var text = doc.createTextNode(source.substring(start));
 					if (doc.documentElement) {
 						return errorHandler.error('Extra content at the end of the document');
 					}
@@ -587,8 +587,10 @@ function _copy(source, target) {
  * @property {function(): string} substringFromIndex
  * creates a substring from the current index to the end of `source`
  * @property {function(compareWith: string): boolean} substringStartsWith
- * Checks if source contains `compareWith`,
- * starting from the current index.
+ * Checks if `source` contains `compareWith`, starting from the current index.
+ * @property {function(compareWith: string): boolean} substringStartsWithCaseInsensitive
+ * Checks if `source` contains `compareWith`, starting from the current index,
+ * comparing the upper case of both sides.
  * @see {@link parseUtils}
  */
 
@@ -634,6 +636,9 @@ function parseUtils(source, start) {
 	function substringStartsWith(text) {
 		return source.substring(index, index + text.length) === text;
 	}
+	function substringStartsWithCaseInsensitive(text) {
+		return source.substring(index, index + text.length).toUpperCase() === text.toUpperCase();
+	}
 
 	function getMatch(args) {
 		var expr = g.reg('^', args);
@@ -657,6 +662,7 @@ function parseUtils(source, start) {
 		skipBlanks: skipBlanks,
 		substringFromIndex: substringFromIndex,
 		substringStartsWith: substringStartsWith,
+		substringStartsWithCaseInsensitive: substringStartsWithCaseInsensitive,
 	};
 }
 
@@ -753,7 +759,7 @@ function parseDoctypeInternalSubset(p, errorHandler) {
 function parseDoctypeCommentOrCData(source, start, domBuilder, errorHandler, isHTML) {
 	var p = parseUtils(source, start);
 
-	switch (p.char(2)) {
+	switch (isHTML ? p.char(2).toUpperCase() : p.char(2)) {
 		case '-':
 			// should be a comment
 			var comment = p.getMatch(g.Comment);
@@ -782,7 +788,7 @@ function parseDoctypeCommentOrCData(source, start, domBuilder, errorHandler, isH
 			if (domBuilder.doc && domBuilder.doc.documentElement) {
 				return errorHandler.fatalError('Doctype not allowed inside or after documentElement at position ' + p.getIndex());
 			}
-			if (!p.substringStartsWith(g.DOCTYPE_DECL_START)) {
+			if (isHTML ? !p.substringStartsWithCaseInsensitive(g.DOCTYPE_DECL_START) : !p.substringStartsWith(g.DOCTYPE_DECL_START)) {
 				return errorHandler.fatalError('Expected ' + g.DOCTYPE_DECL_START + ' at position ' + p.getIndex());
 			}
 			p.skip(g.DOCTYPE_DECL_START.length);
@@ -800,6 +806,10 @@ function parseDoctypeCommentOrCData(source, start, domBuilder, errorHandler, isH
 			doctype.name = p.getMatch(g.Name);
 			if (!doctype.name)
 				return errorHandler.fatalError('doctype name missing or contains unexpected characters at position ' + p.getIndex());
+
+			if (isHTML && doctype.name.toLowerCase() !== 'html') {
+				errorHandler.warning('Unexpected DOCTYPE in HTML document at position ' + p.getIndex());
+			}
 			p.skipBlanks();
 
 			// Check for ExternalID
@@ -815,10 +825,26 @@ function parseDoctypeCommentOrCData(source, start, domBuilder, errorHandler, isH
 					doctype.publicId = match.groups.PubidLiteral;
 				}
 				p.skip(match[0].length);
+			} else if (isHTML && p.substringStartsWithCaseInsensitive(g.SYSTEM)) {
+				// https://html.spec.whatwg.org/multipage/syntax.html#doctype-legacy-string
+				p.skip(g.SYSTEM.length);
+				if (p.skipBlanks() < 1) {
+					return errorHandler.fatalError('Expected whitespace after ' + g.SYSTEM + ' at position ' + p.getIndex());
+				}
+				doctype.systemId = p.getMatch(g.ABOUT_LEGACY_COMPAT_SystemLiteral);
+				if (!doctype.systemId) {
+					return errorHandler.fatalError(
+						'Expected ' + g.ABOUT_LEGACY_COMPAT + ' in single or double quotes after ' + g.SYSTEM + ' at position ' + p.getIndex()
+					);
+				}
+			}
+			if (isHTML && doctype.systemId && !g.ABOUT_LEGACY_COMPAT_SystemLiteral.test(doctype.systemId)) {
+				errorHandler.warning('Unexpected doctype.systemId in HTML document at position ' + p.getIndex());
+			}
+			if (!isHTML) {
+				p.skipBlanks();
+				doctype.internalSubset = parseDoctypeInternalSubset(p, errorHandler);
 			}
-
-			p.skipBlanks();
-			doctype.internalSubset = parseDoctypeInternalSubset(p, errorHandler);
 			p.skipBlanks();
 			if (p.char() !== '>') {
 				return errorHandler.fatalError('doctype not terminated with > at position ' + p.getIndex());

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@xmldom/xmldom",
-	"version": "0.9.6",
+	"version": "0.9.8",
 	"description": "A pure JavaScript W3C standard-based (XML DOM Level 2 Core) DOMParser and XMLSerializer module.",
 	"keywords": [
 		"w3c",
@@ -44,21 +44,18 @@
 	},
 	"devDependencies": {
 		"@homer0/prettier-plugin-jsdoc": "9.1.0",
-		"@jazzer.js/core": "2.1.0",
-		"@jazzer.js/jest-runner": "2.1.0",
 		"auto-changelog": "2.5.0",
 		"eslint": "8.57.1",
-		"eslint-config-prettier": "9.1.0",
+		"eslint-config-prettier": "10.0.1",
 		"eslint-plugin-anti-trojan-source": "1.1.1",
 		"eslint-plugin-es5": "1.5.0",
-		"eslint-plugin-n": "17.14.0",
-		"eslint-plugin-prettier": "5.2.1",
+		"eslint-plugin-n": "17.15.1",
+		"eslint-plugin-prettier": "5.2.3",
 		"get-stream": "6.0.1",
 		"jest": "29.7.0",
-		"nodemon": "3.1.7",
+		"nodemon": "3.1.9",
 		"np": "8.0.4",
-		"prettier": "3.4.1",
-		"rxjs": "7.8.1",
+		"prettier": "3.5.2",
 		"xmltest": "2.0.3",
 		"yauzl": "3.2.0"
 	},
@@ -71,5 +68,6 @@
 		"remote": "origin",
 		"tagPrefix": "",
 		"template": "./auto-changelog.hbs"
-	}
+	},
+	"packageManager": "npm@11.1.0+sha512.acf301ad9b9ddba948fcb72341e2f0fcae477f56a95cc2a092934d133a7461062633cefbf93d5934a3dc0768674e2edee9f04dcfcc4bb4c327ff0e3a7d552a1b"
 }