From e70d6ad59b5476aaf3cbd96484d5f11e631be3e1 Mon Sep 17 00:00:00 2001 From: zorkow Date: Sun, 15 Feb 2026 18:26:57 +0100 Subject: [PATCH 1/2] adds a clear button --- lib/v4-lab.js | 9 +++++++-- v4-lab.html | 1 + 2 files changed, 8 insertions(+), 2 deletions(-) diff --git a/lib/v4-lab.js b/lib/v4-lab.js index 347ddd4..b9da477 100644 --- a/lib/v4-lab.js +++ b/lib/v4-lab.js @@ -387,6 +387,10 @@ const Lab = window.Lab = { /*************************************************************/ + Clear() { + this.input.value = ''; + }, + /** * Record the current state in the URL and reload the page */ @@ -538,7 +542,7 @@ const Lab = window.Lab = { label.appendChild(document.createTextNode(key)); checkbox.appendChild(label); let span = div.appendChild(document.createElement('span')); - span = span.appendChild(document.createElement('span')); + span = span.appendChild(document.createElement('span')); span.appendChild(checkbox); span.appendChild(label); this.packages[type][key] = checkbox; @@ -610,7 +614,7 @@ const Lab = window.Lab = { input.disabled = disabled; } }, - + /*************************************************************/ /** @@ -1191,6 +1195,7 @@ const Lab = window.Lab = { MathJax.startup.promiseResolve(); this.newPackages(); this.Typeset(); + document.getElementById('clear').disabled = false; document.getElementById('keep').disabled = false; document.getElementById('typeset').disabled = false; }, diff --git a/v4-lab.html b/v4-lab.html index 3a146e5..913870c 100644 --- a/v4-lab.html +++ b/v4-lab.html @@ -39,6 +39,7 @@

MathJax v4 Interactive Lab

+
From 3915a58394dfb322166be284adbe874d60018b9c Mon Sep 17 00:00:00 2001 From: zorkow Date: Sat, 11 Apr 2026 19:45:50 +0200 Subject: [PATCH 2/2] updates xmldom to es6 variant of version 0.9.9 --- lib/xmldom/conventions.js | 354 +++- lib/xmldom/dom-parser.js | 630 +++++-- lib/xmldom/dom.js | 3332 ++++++++++++++++++++++++++----------- lib/xmldom/entities.js | 26 +- lib/xmldom/errors.js | 206 +++ lib/xmldom/grammar.js | 537 ++++++ lib/xmldom/index.js | 53 +- lib/xmldom/sax.js | 1248 ++++++++------ 8 files changed, 4638 insertions(+), 1748 deletions(-) create mode 100644 lib/xmldom/errors.js create mode 100644 lib/xmldom/grammar.js diff --git a/lib/xmldom/conventions.js b/lib/xmldom/conventions.js index b8594b5..d412207 100644 --- a/lib/xmldom/conventions.js +++ b/lib/xmldom/conventions.js @@ -1,17 +1,17 @@ -'use strict' +'use strict'; /** * Ponyfill for `Array.prototype.find` which is only available in ES6 runtimes. * - * Works with anything that has a `length` property and index access properties, including NodeList. + * Works with anything that has a `length` property and index access properties, + * including NodeList. * - * @template {unknown} T - * @param {Array | ({length:number, [number]: T})} list - * @param {function (item: T, index: number, list:Array | ({length:number, [number]: T})):boolean} predicate - * @param {Partial>?} ac `Array.prototype` by default, - * allows injecting a custom implementation in tests + * @param {T[] | { length: number; [number]: T }} list + * @param {function (item: T, index: number, list:T[]):boolean} predicate + * @param {Partial>?} ac + * Allows injecting a custom implementation in tests (`Array.prototype` by default). * @returns {T | undefined} - * + * @template {unknown} T * @see https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/find * @see https://tc39.es/ecma262/multipage/indexed-collections.html#sec-array.prototype.find */ @@ -23,7 +23,7 @@ function find(list, predicate, ac) { return ac.find.call(list, predicate); } for (var i = 0; i < list.length; i++) { - if (Object.prototype.hasOwnProperty.call(list, i)) { + if (hasOwn(list, i)) { var item = list[i]; if (predicate.call(undefined, item, i, list)) { return item; @@ -39,90 +39,292 @@ function find(list, predicate, ac) { * * Is used to create "enum like" objects. * - * @template T - * @param {T} object the object to freeze - * @param {Pick = Object} oc `Object` by default, - * allows to inject custom object constructor for tests - * @returns {Readonly} + * If `Object.getOwnPropertyDescriptors` is available, + * a new object with all properties of object but without any prototype is created and returned + * after freezing it. * + * @param {T} object + * The object to freeze. + * @param {Pick} [oc=Object] + * `Object` by default, + * allows to inject custom object constructor for tests. + * @returns {Readonly} + * @template {Object} T * @see https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Object/freeze + * @prettierignore */ function freeze(object, oc) { if (oc === undefined) { - oc = Object + oc = Object; } - return oc && typeof oc.freeze === 'function' ? oc.freeze(object) : object + if (oc && typeof oc.getOwnPropertyDescriptors === 'function') { + object = oc.create(null, oc.getOwnPropertyDescriptors(object)); + } + return oc && typeof oc.freeze === 'function' ? oc.freeze(object) : object; } /** - * Since we can not rely on `Object.assign` we provide a simplified version - * that is sufficient for our needs. + * Implementation for `Object.hasOwn` but ES5 compatible. + * + * @param {any} object + * @param {string | number} key + * @returns {boolean} + */ +function hasOwn(object, key) { + return Object.prototype.hasOwnProperty.call(object, key); +} + +/** + * Since xmldom can not rely on `Object.assign`, + * it uses/provides a simplified version that is sufficient for its needs. * * @param {Object} target * @param {Object | null | undefined} source - * - * @returns {Object} target - * @throws TypeError if target is not an object - * + * @returns {Object} + * The target with the merged/overridden properties. + * @throws {TypeError} + * If target is not an object. * @see https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Object/assign * @see https://tc39.es/ecma262/multipage/fundamental-objects.html#sec-object.assign */ function assign(target, source) { if (target === null || typeof target !== 'object') { - throw new TypeError('target is not an object') + throw new TypeError('target is not an object'); } for (var key in source) { - if (Object.prototype.hasOwnProperty.call(source, key)) { - target[key] = source[key] + if (hasOwn(source, key)) { + target[key] = source[key]; } } - return target + return target; +} + +/** + * A number of attributes are boolean attributes. + * The presence of a boolean attribute on an element represents the `true` value, + * and the absence of the attribute represents the `false` value. + * + * If the attribute is present, its value must either be the empty string, or a value that is + * an ASCII case-insensitive match for the attribute's canonical name, + * with no leading or trailing whitespace. + * + * Note: The values `"true"` and `"false"` are not allowed on boolean attributes. + * To represent a `false` value, the attribute has to be omitted altogether. + * + * @see https://html.spec.whatwg.org/#boolean-attributes + * @see https://html.spec.whatwg.org/#attributes-3 + */ +var HTML_BOOLEAN_ATTRIBUTES = freeze({ + allowfullscreen: true, + async: true, + autofocus: true, + autoplay: true, + checked: true, + controls: true, + default: true, + defer: true, + disabled: true, + formnovalidate: true, + hidden: true, + ismap: true, + itemscope: true, + loop: true, + multiple: true, + muted: true, + nomodule: true, + novalidate: true, + open: true, + playsinline: true, + readonly: true, + required: true, + reversed: true, + selected: true, +}); + +/** + * Check if `name` is matching one of the HTML boolean attribute names. + * This method doesn't check if such attributes are allowed in the context of the current + * document/parsing. + * + * @param {string} name + * @returns {boolean} + * @see {@link HTML_BOOLEAN_ATTRIBUTES} + * @see https://html.spec.whatwg.org/#boolean-attributes + * @see https://html.spec.whatwg.org/#attributes-3 + */ +function isHTMLBooleanAttribute(name) { + return hasOwn(HTML_BOOLEAN_ATTRIBUTES, name.toLowerCase()); +} + +/** + * Void elements only have a start tag; end tags must not be specified for void elements. + * These elements should be written as self-closing like this: ``. + * This should not be confused with optional tags that HTML allows to omit the end tag for + * (like `li`, `tr` and others), which can have content after them, + * so they can not be written as self-closing. + * xmldom does not have any logic for optional end tags cases, + * and will report them as a warning. + * Content that would go into the unopened element, + * will instead be added as a sibling text node. + * + * @type {Readonly<{ + * area: boolean; + * col: boolean; + * img: boolean; + * wbr: boolean; + * link: boolean; + * hr: boolean; + * source: boolean; + * br: boolean; + * input: boolean; + * param: boolean; + * meta: boolean; + * embed: boolean; + * track: boolean; + * base: boolean; + * }>} + * @see https://html.spec.whatwg.org/#void-elements + * @see https://html.spec.whatwg.org/#optional-tags + */ +var HTML_VOID_ELEMENTS = freeze({ + area: true, + base: true, + br: true, + col: true, + embed: true, + hr: true, + img: true, + input: true, + link: true, + meta: true, + param: true, + source: true, + track: true, + wbr: true, +}); + +/** + * Check if `tagName` is matching one of the HTML void element names. + * This method doesn't check if such tags are allowed in the context of the current + * document/parsing. + * + * @param {string} tagName + * @returns {boolean} + * @see {@link HTML_VOID_ELEMENTS} + * @see https://html.spec.whatwg.org/#void-elements + */ +function isHTMLVoidElement(tagName) { + return hasOwn(HTML_VOID_ELEMENTS, tagName.toLowerCase()); +} + +/** + * Tag names that are raw text elements according to HTML spec. + * The value denotes whether they are escapable or not. + * + * @see {@link isHTMLEscapableRawTextElement} + * @see {@link isHTMLRawTextElement} + * @see https://html.spec.whatwg.org/#raw-text-elements + * @see https://html.spec.whatwg.org/#escapable-raw-text-elements + */ +var HTML_RAW_TEXT_ELEMENTS = freeze({ + script: false, + style: false, + textarea: true, + title: true, +}); + +/** + * Check if `tagName` is matching one of the HTML raw text element names. + * This method doesn't check if such tags are allowed in the context of the current + * document/parsing. + * + * @param {string} tagName + * @returns {boolean} + * @see {@link isHTMLEscapableRawTextElement} + * @see {@link HTML_RAW_TEXT_ELEMENTS} + * @see https://html.spec.whatwg.org/#raw-text-elements + * @see https://html.spec.whatwg.org/#escapable-raw-text-elements + */ +function isHTMLRawTextElement(tagName) { + var key = tagName.toLowerCase(); + return hasOwn(HTML_RAW_TEXT_ELEMENTS, key) && !HTML_RAW_TEXT_ELEMENTS[key]; +} +/** + * Check if `tagName` is matching one of the HTML escapable raw text element names. + * This method doesn't check if such tags are allowed in the context of the current + * document/parsing. + * + * @param {string} tagName + * @returns {boolean} + * @see {@link isHTMLRawTextElement} + * @see {@link HTML_RAW_TEXT_ELEMENTS} + * @see https://html.spec.whatwg.org/#raw-text-elements + * @see https://html.spec.whatwg.org/#escapable-raw-text-elements + */ +function isHTMLEscapableRawTextElement(tagName) { + var key = tagName.toLowerCase(); + return hasOwn(HTML_RAW_TEXT_ELEMENTS, key) && HTML_RAW_TEXT_ELEMENTS[key]; +} +/** + * Only returns true if `value` matches MIME_TYPE.HTML, which indicates an HTML document. + * + * @param {string} mimeType + * @returns {mimeType is 'text/html'} + * @see https://www.iana.org/assignments/media-types/text/html + * @see https://en.wikipedia.org/wiki/HTML + * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString + * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-domparser-parsefromstring + */ +function isHTMLMimeType(mimeType) { + return mimeType === MIME_TYPE.HTML; +} +/** + * For both the `text/html` and the `application/xhtml+xml` namespace the spec defines that the + * HTML namespace is provided as the default. + * + * @param {string} mimeType + * @returns {boolean} + * @see https://dom.spec.whatwg.org/#dom-document-createelement + * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocument + * @see https://dom.spec.whatwg.org/#dom-domimplementation-createhtmldocument + */ +function hasDefaultHTMLNamespace(mimeType) { + return isHTMLMimeType(mimeType) || mimeType === MIME_TYPE.XML_XHTML_APPLICATION; } /** * All mime types that are allowed as input to `DOMParser.parseFromString` * - * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString#Argument02 MDN - * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#domparsersupportedtype WHATWG HTML Spec - * @see DOMParser.prototype.parseFromString + * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString#Argument02 + * MDN + * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#domparsersupportedtype + * WHATWG HTML Spec + * @see {@link DOMParser.prototype.parseFromString} */ var MIME_TYPE = freeze({ /** * `text/html`, the only mime type that triggers treating an XML document as HTML. * - * @see DOMParser.SupportedType.isHTML * @see https://www.iana.org/assignments/media-types/text/html IANA MimeType registration * @see https://en.wikipedia.org/wiki/HTML Wikipedia * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString MDN - * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-domparser-parsefromstring WHATWG HTML Spec + * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-domparser-parsefromstring + * WHATWG HTML Spec */ HTML: 'text/html', - /** - * Helper method to check a mime type if it indicates an HTML document - * - * @param {string} [value] - * @returns {boolean} - * - * @see https://www.iana.org/assignments/media-types/text/html IANA MimeType registration - * @see https://en.wikipedia.org/wiki/HTML Wikipedia - * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString MDN - * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-domparser-parsefromstring */ - isHTML: function (value) { - return value === MIME_TYPE.HTML - }, - /** * `application/xml`, the standard mime type for XML documents. * - * @see https://www.iana.org/assignments/media-types/application/xml IANA MimeType registration + * @see https://www.iana.org/assignments/media-types/application/xml IANA MimeType + * registration * @see https://tools.ietf.org/html/rfc7303#section-9.1 RFC 7303 * @see https://en.wikipedia.org/wiki/XML_and_MIME Wikipedia */ 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 @@ -134,7 +336,8 @@ var MIME_TYPE = freeze({ * `application/xhtml+xml`, indicates an XML document that has the default HTML namespace, * but is parsed as an XML document. * - * @see https://www.iana.org/assignments/media-types/application/xhtml+xml IANA MimeType registration + * @see https://www.iana.org/assignments/media-types/application/xhtml+xml IANA MimeType + * registration * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocument WHATWG DOM Spec * @see https://en.wikipedia.org/wiki/XHTML Wikipedia */ @@ -148,8 +351,31 @@ var MIME_TYPE = freeze({ * @see https://en.wikipedia.org/wiki/Scalable_Vector_Graphics Wikipedia */ XML_SVG_IMAGE: 'image/svg+xml', -}) +}); +/** + * @typedef {'application/xhtml+xml' | 'application/xml' | 'image/svg+xml' | 'text/html' | 'text/xml'} + * MimeType + */ +/** + * @type {MimeType[]} + * @private + * Basically `Object.values`, which is not available in ES5. + */ +var _MIME_TYPES = Object.keys(MIME_TYPE).map(function (key) { + return MIME_TYPE[key]; +}); +/** + * Only returns true if `mimeType` is one of the allowed values for + * `DOMParser.parseFromString`. + * + * @param {string} mimeType + * @returns {mimeType is 'application/xhtml+xml' | 'application/xml' | 'image/svg+xml' | 'text/html' | 'text/xml'} + * + */ +function isValidMimeType(mimeType) { + return _MIME_TYPES.indexOf(mimeType) > -1; +} /** * Namespaces that are used in this code base. * @@ -163,17 +389,6 @@ var NAMESPACE = freeze({ */ HTML: 'http://www.w3.org/1999/xhtml', - /** - * Checks if `uri` equals `NAMESPACE.HTML`. - * - * @param {string} [uri] - * - * @see NAMESPACE.HTML - */ - isHTML: function (uri) { - return uri === NAMESPACE.HTML - }, - /** * The SVG namespace. * @@ -189,19 +404,30 @@ var NAMESPACE = freeze({ XML: 'http://www.w3.org/XML/1998/namespace', /** - * The `xmlns:` namespace + * The `xmlns:` namespace. * * @see https://www.w3.org/2000/xmlns/ */ XMLNS: 'http://www.w3.org/2000/xmlns/', -}) +}); -export {assign, find, freeze, MIME_TYPE, NAMESPACE}; +export { assign, find, freeze, HTML_BOOLEAN_ATTRIBUTES, HTML_RAW_TEXT_ELEMENTS, HTML_VOID_ELEMENTS, hasDefaultHTMLNamespace, hasOwn, isHTMLBooleanAttribute, isHTMLRawTextElement, isHTMLEscapableRawTextElement, isHTMLMimeType, isHTMLVoidElement, isValidMimeType, MIME_TYPE, NAMESPACE }; -/* +/** exports.assign = assign; exports.find = find; exports.freeze = freeze; +exports.HTML_BOOLEAN_ATTRIBUTES = HTML_BOOLEAN_ATTRIBUTES; +exports.HTML_RAW_TEXT_ELEMENTS = HTML_RAW_TEXT_ELEMENTS; +exports.HTML_VOID_ELEMENTS = HTML_VOID_ELEMENTS; +exports.hasDefaultHTMLNamespace = hasDefaultHTMLNamespace; +exports.hasOwn = hasOwn; +exports.isHTMLBooleanAttribute = isHTMLBooleanAttribute; +exports.isHTMLRawTextElement = isHTMLRawTextElement; +exports.isHTMLEscapableRawTextElement = isHTMLEscapableRawTextElement; +exports.isHTMLMimeType = isHTMLMimeType; +exports.isHTMLVoidElement = isHTMLVoidElement; +exports.isValidMimeType = isValidMimeType; exports.MIME_TYPE = MIME_TYPE; exports.NAMESPACE = NAMESPACE; */ diff --git a/lib/xmldom/dom-parser.js b/lib/xmldom/dom-parser.js index 44e531e..8a185cb 100644 --- a/lib/xmldom/dom-parser.js +++ b/lib/xmldom/dom-parser.js @@ -1,17 +1,23 @@ -import * as conventions from "./conventions.js"; +import * as conventions from './conventions.js'; import * as dom from './dom.js'; +import * as errors from './errors.js'; import * as entities from './entities.js'; import * as sax from './sax.js'; var DOMImplementation = dom.DOMImplementation; +var hasDefaultHTMLNamespace = conventions.hasDefaultHTMLNamespace; +var isHTMLMimeType = conventions.isHTMLMimeType; +var isValidMimeType = conventions.isValidMimeType; +var MIME_TYPE = conventions.MIME_TYPE; var NAMESPACE = conventions.NAMESPACE; +var ParseError = errors.ParseError; -var ParseError = sax.ParseError; var XMLReader = sax.XMLReader; /** - * Normalizes line ending according to https://www.w3.org/TR/xml11/#sec-line-ends: + * Normalizes line ending according to , + * including some Unicode "newline" characters: * * > XML parsed entities are often stored in computer files which, * > for editing convenience, are organized into lines. @@ -20,21 +26,21 @@ 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. + * > 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. * * @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'); } /** @@ -45,229 +51,457 @@ function normalizeLineEndings(input) { /** * @typedef DOMParserOptions - * @property {DOMHandler} [domBuilder] + * @property {typeof assign} [assign] + * The method to use instead of `conventions.assign`, which is used to copy values from + * `options` before they are used for parsing. + * @property {typeof DOMHandler} [domHandler] + * For internal testing: The class for creating an instance for handling events from the SAX + * parser. + * *****Warning: By configuring a faulty implementation, the specified behavior can completely + * be broken.*****. * @property {Function} [errorHandler] - * @property {(string) => string} [normalizeLineEndings] used to replace line endings before parsing - * defaults to `normalizeLineEndings` - * @property {Locator} [locator] - * @property {Record} [xmlns] + * DEPRECATED! use `onError` instead. + * @property {function(level:ErrorLevel, message:string, context: DOMHandler):void} + * [onError] + * A function invoked for every error that occurs during parsing. * - * @see normalizeLineEndings + * If it is not provided, all errors are reported to `console.error` + * and only `fatalError`s are thrown as a `ParseError`, + * which prevents any further processing. + * If the provided method throws, a `ParserError` is thrown, + * which prevents any further processing. + * + * Be aware that many `warning`s are considered an error that prevents further processing in + * most implementations. + * @property {boolean} [locator=true] + * Configures if the nodes created during parsing will have a `lineNumber` and a `columnNumber` + * attribute describing their location in the XML string. + * Default is true. + * @property {(string) => string} [normalizeLineEndings] + * used to replace line endings before parsing, defaults to exported `normalizeLineEndings`, + * which normalizes line endings according to , + * 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. + * When the `mimeType` for HTML, XHTML or SVG are passed to `parseFromString`, + * the default namespace that will be used, + * will be overridden according to the specification. + * @see {@link normalizeLineEndings} */ /** - * The DOMParser interface provides the ability to parse XML or HTML source code - * from a string into a DOM `Document`. + * The DOMParser interface provides the ability to parse XML or HTML source code from a string + * into a DOM `Document`. * - * _xmldom is different from the spec in that it allows an `options` parameter, - * to override the default behavior._ + * ***xmldom is different from the spec in that it allows an `options` parameter, + * to control the behavior***. * + * @class * @param {DOMParserOptions} [options] - * @constructor - * * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser * @see https://html.spec.whatwg.org/multipage/dynamic-markup-insertion.html#dom-parsing-and-serialization */ -function DOMParser(options){ - this.options = options ||{locator:{}}; -} +function DOMParser(options) { + options = options || {}; + if (options.locator === undefined) { + options.locator = true; + } + + /** + * The method to use instead of `conventions.assign`, which is used to copy values from + * `options` + * before they are used for parsing. + * + * @type {conventions.assign} + * @private + * @see {@link conventions.assign} + * @readonly + */ + this.assign = options.assign || conventions.assign; -DOMParser.prototype.parseFromString = function(source,mimeType){ - var options = this.options; - var sax = new XMLReader(); - var domBuilder = options.domBuilder || new DOMHandler();//contentHandler and LexicalHandler - var errorHandler = options.errorHandler; - var locator = options.locator; - var defaultNSMap = options.xmlns||{}; - var isHTML = /\/x?html?$/.test(mimeType);//mimeType.toLowerCase().indexOf('html') > -1; - var entityMap = isHTML ? entities.HTML_ENTITIES : entities.XML_ENTITIES; - if(locator){ - domBuilder.setDocumentLocator(locator) + /** + * For internal testing: The class for creating an instance for handling events from the SAX + * parser. + * *****Warning: By configuring a faulty implementation, the specified behavior can completely + * be broken*****. + * + * @type {typeof DOMHandler} + * @private + * @readonly + */ + this.domHandler = options.domHandler || DOMHandler; + + /** + * A function that is 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`, + * which prevents any further processing. + * If the provided method throws, a `ParserError` is thrown, + * which prevents any further processing. + * + * Be aware that many `warning`s are considered an error that prevents further processing in + * most implementations. + * + * @type {function(level:ErrorLevel, message:string, context: DOMHandler):void} + * @see {@link onErrorStopParsing} + * @see {@link onWarningStopParsing} + */ + this.onError = options.onError || options.errorHandler; + if (options.errorHandler && typeof options.errorHandler !== 'function') { + throw new TypeError('errorHandler object is no longer supported, switch to onError!'); + } else if (options.errorHandler) { + options.errorHandler('warning', 'The `errorHandler` option has been deprecated, use `onError` instead!', this); } - sax.errorHandler = buildErrorHandler(errorHandler,domBuilder,locator); - sax.domBuilder = options.domBuilder || domBuilder; - if(isHTML){ - defaultNSMap[''] = NAMESPACE.HTML; + /** + * used to replace line endings before parsing, defaults to `normalizeLineEndings` + * + * @type {(string) => string} + * @readonly + */ + this.normalizeLineEndings = options.normalizeLineEndings || normalizeLineEndings; + + /** + * Configures if the nodes created during parsing will have a `lineNumber` and a + * `columnNumber` + * attribute describing their location in the XML string. + * Default is true. + * + * @type {boolean} + * @readonly + */ + this.locator = !!options.locator; + + /** + * The default namespace can be provided by the key that is the empty string. + * When the `mimeType` for HTML, XHTML or SVG are passed to `parseFromString`, + * the default namespace that will be used, + * will be overridden according to the specification. + * + * @type {Readonly} + * @readonly + */ + this.xmlns = this.assign(Object.create(null), options.xmlns); +} + +/** + * Parses `source` using the options in the way configured by the `DOMParserOptions` of `this` + * `DOMParser`. If `mimeType` is `text/html` an HTML `Document` is created, + * otherwise an XML `Document` is created. + * + * __It behaves different from the description in the living standard__: + * - Uses the `options` passed to the `DOMParser` constructor to modify the behavior. + * - Any unexpected input is reported to `onError` with either a `warning`, + * `error` or `fatalError` level. + * - Any `fatalError` throws a `ParseError` which prevents further processing. + * - Any error thrown by `onError` is converted to a `ParseError` which prevents further + * processing - If no `Document` was created during parsing it is reported as a `fatalError`. + * *****Warning: By configuring a faulty DOMHandler implementation, + * the specified behavior can completely be broken*****. + * + * @param {string} source + * The XML mime type only allows string input! + * @param {string} [mimeType='application/xml'] + * the mimeType or contentType of the document to be created determines the `type` of document + * created (XML or HTML) + * @returns {Document} + * The `Document` node. + * @throws {ParseError} + * for any `fatalError` or anything that is thrown by `onError` + * @throws {TypeError} + * for any invalid `mimeType` + * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMParser/parseFromString + * @see https://html.spec.whatwg.org/#dom-domparser-parsefromstring-dev + */ +DOMParser.prototype.parseFromString = function (source, mimeType) { + if (!isValidMimeType(mimeType)) { + throw new TypeError('DOMParser.parseFromString: the provided mimeType "' + mimeType + '" is not valid.'); } + var defaultNSMap = this.assign(Object.create(null), this.xmlns); + var entityMap = entities.XML_ENTITIES; + var defaultNamespace = defaultNSMap[''] || null; + if (hasDefaultHTMLNamespace(mimeType)) { + entityMap = entities.HTML_ENTITIES; + defaultNamespace = NAMESPACE.HTML; + } else if (mimeType === MIME_TYPE.XML_SVG_IMAGE) { + defaultNamespace = NAMESPACE.SVG; + } + defaultNSMap[''] = defaultNamespace; defaultNSMap.xml = defaultNSMap.xml || NAMESPACE.XML; - var normalize = options.normalizeLineEndings || normalizeLineEndings; - if (source && typeof source === 'string') { - sax.parse( - normalize(source), - defaultNSMap, - entityMap - ) - } else { - sax.errorHandler.error('invalid doc source') + + var domBuilder = new this.domHandler({ + mimeType: mimeType, + defaultNamespace: defaultNamespace, + onError: this.onError, + }); + var locator = this.locator ? {} : undefined; + if (this.locator) { + domBuilder.setDocumentLocator(locator); } - return domBuilder.doc; -} -function buildErrorHandler(errorImpl,domBuilder,locator){ - if(!errorImpl){ - if(domBuilder instanceof DOMHandler){ - return domBuilder; - } - errorImpl = domBuilder ; + + var sax = new XMLReader(); + sax.errorHandler = domBuilder; + sax.domBuilder = domBuilder; + var isXml = !conventions.isHTMLMimeType(mimeType); + if (isXml && typeof source !== 'string') { + sax.errorHandler.fatalError('source is not a string'); } - var errorHandler = {} - var isCallback = errorImpl instanceof Function; - locator = locator||{} - function build(key){ - var fn = errorImpl[key]; - if(!fn && isCallback){ - fn = errorImpl.length == 2?function(msg){errorImpl(key,msg)}:errorImpl; - } - errorHandler[key] = fn && function(msg){ - fn('[xmldom '+key+']\t'+msg+_locator(locator)); - }||function(){}; + sax.parse(this.normalizeLineEndings(String(source)), defaultNSMap, entityMap); + if (!domBuilder.doc.documentElement) { + sax.errorHandler.fatalError('missing root element'); } - build('warning'); - build('error'); - build('fatalError'); - return errorHandler; -} + return domBuilder.doc; +}; -//console.log('#\n\n\n\n\n\n\n####') /** - * +ContentHandler+ErrorHandler - * +LexicalHandler+EntityResolver2 - * -DeclHandler-DTDHandler + * @typedef DOMHandlerOptions + * @property {string} [mimeType=MIME_TYPE.XML_APPLICATION] + * @property {string | null} [defaultNamespace=null] + */ +/** + * The class that is used to handle events from the SAX parser to create the related DOM + * elements. + * + * Some methods are only implemented as an empty function, + * since they are (at least currently) not relevant for xmldom. * - * DefaultHandler:EntityResolver, DTDHandler, ContentHandler, ErrorHandler - * DefaultHandler2:DefaultHandler,LexicalHandler, DeclHandler, EntityResolver2 - * @link http://www.saxproject.org/apidoc/org/xml/sax/helpers/DefaultHandler.html + * @class + * @param {DOMHandlerOptions} [options] + * @see http://www.saxproject.org/apidoc/org/xml/sax/ext/DefaultHandler2.html */ -function DOMHandler() { - this.cdata = false; +function DOMHandler(options) { + var opt = options || {}; + /** + * The mime type is used to determine if the DOM handler will create an XML or HTML document. + * Only if it is set to `text/html` it will create an HTML document. + * It defaults to MIME_TYPE.XML_APPLICATION. + * + * @type {string} + * @see {@link MIME_TYPE} + * @readonly + */ + this.mimeType = opt.mimeType || MIME_TYPE.XML_APPLICATION; + + /** + * The namespace to use to create an XML document. + * For the following reasons this is required: + * - The SAX API for `startDocument` doesn't offer any way to pass a namespace, + * since at that point there is no way for the parser to know what the default namespace from + * the document will be. + * - When creating using `DOMImplementation.createDocument` it is required to pass a + * namespace, + * to determine the correct `Document.contentType`, which should match `this.mimeType`. + * - When parsing an XML document with the `application/xhtml+xml` mimeType, + * the HTML namespace needs to be the default namespace. + * + * @type {string | null} + * @private + * @readonly + */ + this.defaultNamespace = opt.defaultNamespace || null; + + /** + * @type {boolean} + * @private + */ + this.cdata = false; + + /** + * The last `Element` that was created by `startElement`. + * `endElement` sets it to the `currentElement.parentNode`. + * + * Note: The sax parser currently sets it to white space text nodes between tags. + * + * @type {Element | Node | undefined} + * @private + */ + this.currentElement = undefined; + + /** + * The Document that is created as part of `startDocument`, + * and returned by `DOMParser.parseFromString`. + * + * @type {Document | undefined} + * @readonly + */ + this.doc = undefined; + + /** + * The locator is stored as part of setDocumentLocator. + * It is controlled and mutated by the SAX parser to store the current parsing position. + * It is used by DOMHandler to set `columnNumber` and `lineNumber` + * on the DOM nodes. + * + * @type {Readonly | undefined} + * @private + * @readonly (the + * sax parser currently sometimes set's it) + */ + this.locator = undefined; + /** + * @type {function (level:ErrorLevel ,message:string, context:DOMHandler):void} + * @readonly + */ + this.onError = opt.onError; } -function position(locator,node){ + +function position(locator, node) { node.lineNumber = locator.lineNumber; node.columnNumber = locator.columnNumber; } -/** - * @see org.xml.sax.ContentHandler#startDocument - * @link http://www.saxproject.org/apidoc/org/xml/sax/ContentHandler.html - */ + DOMHandler.prototype = { - startDocument : function() { - this.doc = new DOMImplementation().createDocument(null, null, null); - if (this.locator) { - this.doc.documentURI = this.locator.systemId; - } + /** + * Either creates an XML or an HTML document and stores it under `this.doc`. + * If it is an XML document, `this.defaultNamespace` is used to create it, + * and it will not contain any `childNodes`. + * If it is an HTML document, it will be created without any `childNodes`. + * + * @see http://www.saxproject.org/apidoc/org/xml/sax/ContentHandler.html + */ + startDocument: function () { + var impl = new DOMImplementation(); + this.doc = isHTMLMimeType(this.mimeType) ? impl.createHTMLDocument(false) : impl.createDocument(this.defaultNamespace, ''); }, - startElement:function(namespaceURI, localName, qName, attrs) { + startElement: function (namespaceURI, localName, qName, attrs) { var doc = this.doc; - var el = doc.createElementNS(namespaceURI, qName||localName); - var len = attrs.length; - appendElement(this, el); - this.currentElement = el; - - this.locator && position(this.locator,el) - for (var i = 0 ; i < len; i++) { - var namespaceURI = attrs.getURI(i); - var value = attrs.getValue(i); - var qName = attrs.getQName(i); + var el = doc.createElementNS(namespaceURI, qName || localName); + var len = attrs.length; + appendElement(this, el); + this.currentElement = el; + + this.locator && position(this.locator, el); + for (var i = 0; i < len; i++) { + var namespaceURI = attrs.getURI(i); + var value = attrs.getValue(i); + var qName = attrs.getQName(i); var attr = doc.createAttributeNS(namespaceURI, qName); - this.locator &&position(attrs.getLocator(i),attr); + this.locator && position(attrs.getLocator(i), attr); attr.value = attr.nodeValue = value; - el.setAttributeNode(attr) - } - }, - endElement:function(namespaceURI, localName, qName) { - var current = this.currentElement - var tagName = current.tagName; - this.currentElement = current.parentNode; - }, - startPrefixMapping:function(prefix, uri) { - }, - endPrefixMapping:function(prefix) { + el.setAttributeNode(attr); + } }, - processingInstruction:function(target, data) { - var ins = this.doc.createProcessingInstruction(target, data); - this.locator && position(this.locator,ins) - appendElement(this, ins); + endElement: function (namespaceURI, localName, qName) { + this.currentElement = this.currentElement.parentNode; }, - ignorableWhitespace:function(ch, start, length) { + startPrefixMapping: function (prefix, uri) {}, + endPrefixMapping: function (prefix) {}, + processingInstruction: function (target, data) { + var ins = this.doc.createProcessingInstruction(target, data); + this.locator && position(this.locator, ins); + appendElement(this, ins); }, - characters:function(chars, start, length) { - chars = _toString.apply(this,arguments) + ignorableWhitespace: function (ch, start, length) {}, + characters: function (chars, start, length) { + chars = _toString.apply(this, arguments); //console.log(chars) - if(chars){ + if (chars) { if (this.cdata) { var charNode = this.doc.createCDATASection(chars); } else { var charNode = this.doc.createTextNode(chars); } - if(this.currentElement){ + if (this.currentElement) { this.currentElement.appendChild(charNode); - }else if(/^\s*$/.test(chars)){ + } else if (/^\s*$/.test(chars)) { this.doc.appendChild(charNode); //process xml } - this.locator && position(this.locator,charNode) + this.locator && position(this.locator, charNode); } }, - skippedEntity:function(name) { - }, - endDocument:function() { + skippedEntity: function (name) {}, + endDocument: function () { this.doc.normalize(); }, - setDocumentLocator:function (locator) { - if(this.locator = locator){// && !('lineNumber' in locator)){ - locator.lineNumber = 0; - } + /** + * Stores the locator to be able to set the `columnNumber` and `lineNumber` + * on the created DOM nodes. + * + * @param {Locator} locator + */ + setDocumentLocator: function (locator) { + if (locator) { + locator.lineNumber = 0; + } + this.locator = locator; }, //LexicalHandler - comment:function(chars, start, length) { - chars = _toString.apply(this,arguments) - var comm = this.doc.createComment(chars); - this.locator && position(this.locator,comm) - appendElement(this, comm); + comment: function (chars, start, length) { + chars = _toString.apply(this, arguments); + var comm = this.doc.createComment(chars); + this.locator && position(this.locator, comm); + appendElement(this, comm); }, - startCDATA:function() { - //used in characters() methods - this.cdata = true; + startCDATA: function () { + //used in characters() methods + this.cdata = true; }, - endCDATA:function() { - this.cdata = false; + endCDATA: function () { + this.cdata = false; }, - startDTD:function(name, publicId, systemId) { + startDTD: function (name, publicId, systemId, internalSubset) { var impl = this.doc.implementation; - if (impl && impl.createDocumentType) { - var dt = impl.createDocumentType(name, publicId, systemId); - this.locator && position(this.locator,dt) - appendElement(this, dt); - this.doc.doctype = dt; - } + if (impl && impl.createDocumentType) { + var dt = impl.createDocumentType(name, publicId, systemId, internalSubset); + this.locator && position(this.locator, dt); + appendElement(this, dt); + this.doc.doctype = dt; + } + }, + reportError: function (level, message) { + if (typeof this.onError === 'function') { + try { + this.onError(level, message, this); + } catch (e) { + throw new ParseError('Reporting ' + level + ' "' + message + '" caused ' + e, this.locator); + } + } else { + console.error('[xmldom ' + level + ']\t' + message, _locator(this.locator)); + } }, /** - * @see org.xml.sax.ErrorHandler - * @link http://www.saxproject.org/apidoc/org/xml/sax/ErrorHandler.html + * @see http://www.saxproject.org/apidoc/org/xml/sax/ErrorHandler.html */ - warning:function(error) { - console.warn('[xmldom warning]\t'+error,_locator(this.locator)); + warning: function (message) { + this.reportError('warning', message); }, - error:function(error) { - console.error('[xmldom error]\t'+error,_locator(this.locator)); + error: function (message) { + this.reportError('error', message); }, - fatalError:function(error) { - throw new ParseError(error, this.locator); - } -} -function _locator(l){ - if(l){ - return '\n@'+(l.systemId ||'')+'#[line:'+l.lineNumber+',col:'+l.columnNumber+']' + /** + * This function reports a fatal error and throws a ParseError. + * + * @param {string} message + * - The message to be used for reporting and throwing the error. + * @returns {never} + * This function always throws an error and never returns a value. + * @throws {ParseError} + * Always throws a ParseError with the provided message. + */ + fatalError: function (message) { + this.reportError('fatalError', message); + throw new ParseError(message, this.locator); + }, +}; + +function _locator(l) { + if (l) { + return '\n@#[line:' + l.lineNumber + ',col:' + l.columnNumber + ']'; } } -function _toString(chars,start,length){ - if(typeof chars == 'string'){ - return chars.substr(start,length) - }else{//java sax connect width xmldom on rhino(what about: "? && !(chars instanceof String)") - if(chars.length >= start+length || start){ - return new java.lang.String(chars,start,length)+''; + +function _toString(chars, start, length) { + if (typeof chars == 'string') { + return chars.substr(start, length); + } else { + //java sax connect width xmldom on rhino(what about: "? && !(chars instanceof String)") + if (chars.length >= start + length || start) { + return new java.lang.String(chars, start, length) + ''; } return chars; } @@ -304,24 +538,52 @@ function _toString(chars,start,length){ * #notationDecl(name, publicId, systemId) {}; * #unparsedEntityDecl(name, publicId, systemId, notationName) {}; */ -"endDTD,startEntity,endEntity,attributeDecl,elementDecl,externalEntityDecl,internalEntityDecl,resolveEntity,getExternalSubset,notationDecl,unparsedEntityDecl".replace(/\w+/g,function(key){ - DOMHandler.prototype[key] = function(){return null} -}) +'endDTD,startEntity,endEntity,attributeDecl,elementDecl,externalEntityDecl,internalEntityDecl,resolveEntity,getExternalSubset,notationDecl,unparsedEntityDecl'.replace( + /\w+/g, + function (key) { + DOMHandler.prototype[key] = function () { + return null; + }; + } +); /* Private static helpers treated below as private instance methods, so don't need to add these to the public API; we might use a Relator to also get rid of non-standard public properties */ -function appendElement (hander,node) { - if (!hander.currentElement) { - hander.doc.appendChild(node); - } else { - hander.currentElement.appendChild(node); - } -}//appendChild and setAttributeNS are preformance key +function appendElement(handler, node) { + if (!handler.currentElement) { + handler.doc.appendChild(node); + } else { + handler.currentElement.appendChild(node); + } +} + +/** + * A method that prevents any further parsing when an `error` + * with level `error` is reported during parsing. + * + * @see {@link DOMParserOptions.onError} + * @see {@link onWarningStopParsing} + */ +function onErrorStopParsing(level) { + if (level === 'error') throw 'onErrorStopParsing'; +} + +/** + * A method that prevents any further parsing when any `error` is reported during parsing. + * + * @see {@link DOMParserOptions.onError} + * @see {@link onErrorStopParsing} + */ +function onWarningStopParsing() { + throw 'onWarningStopParsing'; +} -const __DOMHandler = DOMHandler; -export {__DOMHandler, normalizeLineEndings, DOMParser}; + +export {DOMHandler, DOMParser, normalizeLineEndings, onErrorStopParsing, onWarningStopParsing}; /* exports.__DOMHandler = DOMHandler; -exports.normalizeLineEndings = normalizeLineEndings; exports.DOMParser = DOMParser; +exports.normalizeLineEndings = normalizeLineEndings; +exports.onErrorStopParsing = onErrorStopParsing; +exports.onWarningStopParsing = onWarningStopParsing; */ diff --git a/lib/xmldom/dom.js b/lib/xmldom/dom.js index 507b838..17705b3 100644 --- a/lib/xmldom/dom.js +++ b/lib/xmldom/dom.js @@ -1,650 +1,1663 @@ -import * as conventions from "./conventions.js"; - +import * as conventions from './conventions.js'; var find = conventions.find; +var hasDefaultHTMLNamespace = conventions.hasDefaultHTMLNamespace; +var hasOwn = conventions.hasOwn; +var isHTMLMimeType = conventions.isHTMLMimeType; +var isHTMLRawTextElement = conventions.isHTMLRawTextElement; +var isHTMLVoidElement = conventions.isHTMLVoidElement; +var MIME_TYPE = conventions.MIME_TYPE; var NAMESPACE = conventions.NAMESPACE; /** - * A prerequisite for `[].filter`, to drop elements that are empty + * Private DOM Constructor symbol + * + * Internal symbol used for construction of all classes whose constructors should be private. + * Currently used for checks in `Node`, `Document`, `Element`, `Attr`, `CharacterData`, `Text`, `Comment`, + * `CDATASection`, `DocumentType`, `Notation`, `Entity`, `EntityReference`, `DocumentFragment`, `ProcessingInstruction` + * so the constructor can't be used from outside the module. + */ +var PDC = Symbol(); + +import * as errors from './errors.js'; +var DOMException = errors.DOMException; +var DOMExceptionName = errors.DOMExceptionName; + +import * as g from './grammar.js'; + +/** + * Checks if the given symbol equals the Private DOM Constructor symbol (PDC) + * and throws an Illegal constructor exception when the symbols don't match. + * This ensures that the constructor remains private and can't be used outside this module. + */ +function checkSymbol(symbol) { + if (symbol !== PDC) { + throw new TypeError('Illegal constructor'); + } +} + +/** + * A prerequisite for `[].filter`, to drop elements that are empty. + * * @param {string} input + * The string to be checked. * @returns {boolean} + * Returns `true` if the input string is not empty, `false` otherwise. */ -function notEmptyString (input) { - return input !== '' +function notEmptyString(input) { + return input !== ''; } /** - * @see https://infra.spec.whatwg.org/#split-on-ascii-whitespace - * @see https://infra.spec.whatwg.org/#ascii-whitespace + * Splits a string on ASCII whitespace characters (U+0009 TAB, U+000A LF, U+000C FF, U+000D CR, + * U+0020 SPACE). + * It follows the definition from the infra specification from WHATWG. * * @param {string} input - * @returns {string[]} (can be empty) + * The string to be split. + * @returns {string[]} + * An array of the split strings. The array can be empty if the input string is empty or only + * contains whitespace characters. + * @see {@link https://infra.spec.whatwg.org/#split-on-ascii-whitespace} + * @see {@link https://infra.spec.whatwg.org/#ascii-whitespace} */ function splitOnASCIIWhitespace(input) { // U+0009 TAB, U+000A LF, U+000C FF, U+000D CR, U+0020 SPACE - return input ? input.split(/[\t\n\f\r ]+/).filter(notEmptyString) : [] + return input ? input.split(/[\t\n\f\r ]+/).filter(notEmptyString) : []; } /** * Adds element as a key to current if it is not already present. * * @param {Record} current + * The current record object to which the element will be added as a key. + * The object's keys are string types and values are either boolean or undefined. * @param {string} element + * The string to be added as a key to the current record. * @returns {Record} + * The updated record object after the addition of the new element. */ -function orderedSetReducer (current, element) { - if (!current.hasOwnProperty(element)) { +function orderedSetReducer(current, element) { + if (!hasOwn(current, element)) { current[element] = true; } return current; } /** - * @see https://infra.spec.whatwg.org/#ordered-set + * Converts a string into an ordered set by splitting the input on ASCII whitespace and + * ensuring uniqueness of elements. + * This follows the definition of an ordered set from the infra specification by WHATWG. + * * @param {string} input + * The input string to be transformed into an ordered set. * @returns {string[]} + * An array of unique strings obtained from the input, preserving the original order. + * The array can be empty if the input string is empty or only contains whitespace characters. + * @see {@link https://infra.spec.whatwg.org/#ordered-set} */ function toOrderedSet(input) { if (!input) return []; var list = splitOnASCIIWhitespace(input); - return Object.keys(list.reduce(orderedSetReducer, {})) + return Object.keys(list.reduce(orderedSetReducer, {})); } /** - * Uses `list.indexOf` to implement something like `Array.prototype.includes`, - * which we can not rely on being available. + * Uses `list.indexOf` to implement a function that behaves like `Array.prototype.includes`. + * This function is used in environments where `Array.prototype.includes` may not be available. * * @param {any[]} list + * The array in which to search for the element. * @returns {function(any): boolean} + * A function that accepts an element and returns a boolean indicating whether the element is + * included in the provided list. */ -function arrayIncludes (list) { - return function(element) { +function arrayIncludes(list) { + return function (element) { return list && list.indexOf(element) !== -1; + }; +} + +/** + * Validates a qualified name based on the criteria provided in the DOM specification by + * WHATWG. + * + * @param {string} qualifiedName + * The qualified name to be validated. + * @throws {DOMException} + * With code {@link DOMException.INVALID_CHARACTER_ERR} if the qualified name contains an + * invalid character. + * @see {@link https://dom.spec.whatwg.org/#validate} + */ +function validateQualifiedName(qualifiedName) { + if (!g.QName_exact.test(qualifiedName)) { + throw new DOMException(DOMException.INVALID_CHARACTER_ERR, 'invalid character in qualified name "' + qualifiedName + '"'); + } +} + +/** + * Validates a qualified name and the namespace associated with it, + * based on the criteria provided in the DOM specification by WHATWG. + * + * @param {string | null} namespace + * The namespace to be validated. It can be a string or null. + * @param {string} qualifiedName + * The qualified name to be validated. + * @returns {[namespace: string | null, prefix: string | null, localName: string]} + * Returns a tuple with the namespace, + * prefix and local name of the qualified name. + * @throws {DOMException} + * Throws a DOMException if the qualified name or the namespace is not valid. + * @see {@link https://dom.spec.whatwg.org/#validate-and-extract} + */ +function validateAndExtract(namespace, qualifiedName) { + validateQualifiedName(qualifiedName); + namespace = namespace || null; + /** + * @type {string | null} + */ + var prefix = null; + var localName = qualifiedName; + if (qualifiedName.indexOf(':') >= 0) { + var splitResult = qualifiedName.split(':'); + prefix = splitResult[0]; + localName = splitResult[1]; + } + if (prefix !== null && namespace === null) { + throw new DOMException(DOMException.NAMESPACE_ERR, 'prefix is non-null and namespace is null'); } + if (prefix === 'xml' && namespace !== conventions.NAMESPACE.XML) { + throw new DOMException(DOMException.NAMESPACE_ERR, 'prefix is "xml" and namespace is not the XML namespace'); + } + if ((prefix === 'xmlns' || qualifiedName === 'xmlns') && namespace !== conventions.NAMESPACE.XMLNS) { + throw new DOMException( + DOMException.NAMESPACE_ERR, + 'either qualifiedName or prefix is "xmlns" and namespace is not the XMLNS namespace' + ); + } + if (namespace === conventions.NAMESPACE.XMLNS && prefix !== 'xmlns' && qualifiedName !== 'xmlns') { + throw new DOMException( + DOMException.NAMESPACE_ERR, + 'namespace is the XMLNS namespace and neither qualifiedName nor prefix is "xmlns"' + ); + } + return [namespace, prefix, localName]; } -function copy(src,dest){ - for(var p in src){ - if (Object.prototype.hasOwnProperty.call(src, p)) { +/** + * Copies properties from one object to another. + * It only copies the object's own (not inherited) properties. + * + * @param {Object} src + * The source object from which properties are copied. + * @param {Object} dest + * The destination object to which properties are copied. + */ +function copy(src, dest) { + for (var p in src) { + if (hasOwn(src, p)) { dest[p] = src[p]; } } } /** -^\w+\.prototype\.([_\w]+)\s*=\s*((?:.*\{\s*?[\r\n][\s\S]*?^})|\S.*?(?=[;\r\n]));? -^\w+\.prototype\.([_\w]+)\s*=\s*(\S.*?(?=[;\r\n]));? + * Extends a class with the properties and methods of a super class. + * It uses a form of prototypal inheritance, and establishes the `constructor` property + * correctly(?). + * + * It is not clear to the current maintainers if this implementation is making sense, + * since it creates an intermediate prototype function, + * which all properties of `Super` are copied onto using `_copy`. + * + * @param {Object} Class + * The class that is to be extended. + * @param {Object} Super + * The super class from which properties and methods are inherited. + * @private */ -function _extends(Class,Super){ +function _extends(Class, Super) { var pt = Class.prototype; - if(!(pt instanceof Super)){ - function t(){}; + if (!(pt instanceof Super)) { + function t() {} t.prototype = Super.prototype; t = new t(); - copy(pt,t); + copy(pt, t); Class.prototype = pt = t; } - if(pt.constructor != Class){ - if(typeof Class != 'function'){ - console.error("unknown Class:"+Class) + if (pt.constructor != Class) { + if (typeof Class != 'function') { + console.error('unknown Class:' + Class); } - pt.constructor = Class + pt.constructor = Class; } } -// Node Types -var NodeType = {} -var ELEMENT_NODE = NodeType.ELEMENT_NODE = 1; -var ATTRIBUTE_NODE = NodeType.ATTRIBUTE_NODE = 2; -var TEXT_NODE = NodeType.TEXT_NODE = 3; -var CDATA_SECTION_NODE = NodeType.CDATA_SECTION_NODE = 4; -var ENTITY_REFERENCE_NODE = NodeType.ENTITY_REFERENCE_NODE = 5; -var ENTITY_NODE = NodeType.ENTITY_NODE = 6; -var PROCESSING_INSTRUCTION_NODE = NodeType.PROCESSING_INSTRUCTION_NODE = 7; -var COMMENT_NODE = NodeType.COMMENT_NODE = 8; -var DOCUMENT_NODE = NodeType.DOCUMENT_NODE = 9; -var DOCUMENT_TYPE_NODE = NodeType.DOCUMENT_TYPE_NODE = 10; -var DOCUMENT_FRAGMENT_NODE = NodeType.DOCUMENT_FRAGMENT_NODE = 11; -var NOTATION_NODE = NodeType.NOTATION_NODE = 12; - -// ExceptionCode -var ExceptionCode = {} -var ExceptionMessage = {}; -var INDEX_SIZE_ERR = ExceptionCode.INDEX_SIZE_ERR = ((ExceptionMessage[1]="Index size error"),1); -var DOMSTRING_SIZE_ERR = ExceptionCode.DOMSTRING_SIZE_ERR = ((ExceptionMessage[2]="DOMString size error"),2); -var HIERARCHY_REQUEST_ERR = ExceptionCode.HIERARCHY_REQUEST_ERR = ((ExceptionMessage[3]="Hierarchy request error"),3); -var WRONG_DOCUMENT_ERR = ExceptionCode.WRONG_DOCUMENT_ERR = ((ExceptionMessage[4]="Wrong document"),4); -var INVALID_CHARACTER_ERR = ExceptionCode.INVALID_CHARACTER_ERR = ((ExceptionMessage[5]="Invalid character"),5); -var NO_DATA_ALLOWED_ERR = ExceptionCode.NO_DATA_ALLOWED_ERR = ((ExceptionMessage[6]="No data allowed"),6); -var NO_MODIFICATION_ALLOWED_ERR = ExceptionCode.NO_MODIFICATION_ALLOWED_ERR = ((ExceptionMessage[7]="No modification allowed"),7); -var NOT_FOUND_ERR = ExceptionCode.NOT_FOUND_ERR = ((ExceptionMessage[8]="Not found"),8); -var NOT_SUPPORTED_ERR = ExceptionCode.NOT_SUPPORTED_ERR = ((ExceptionMessage[9]="Not supported"),9); -var INUSE_ATTRIBUTE_ERR = ExceptionCode.INUSE_ATTRIBUTE_ERR = ((ExceptionMessage[10]="Attribute in use"),10); -//level2 -var INVALID_STATE_ERR = ExceptionCode.INVALID_STATE_ERR = ((ExceptionMessage[11]="Invalid state"),11); -var SYNTAX_ERR = ExceptionCode.SYNTAX_ERR = ((ExceptionMessage[12]="Syntax error"),12); -var INVALID_MODIFICATION_ERR = ExceptionCode.INVALID_MODIFICATION_ERR = ((ExceptionMessage[13]="Invalid modification"),13); -var NAMESPACE_ERR = ExceptionCode.NAMESPACE_ERR = ((ExceptionMessage[14]="Invalid namespace"),14); -var INVALID_ACCESS_ERR = ExceptionCode.INVALID_ACCESS_ERR = ((ExceptionMessage[15]="Invalid access"),15); - +var NodeType = {}; +var ELEMENT_NODE = (NodeType.ELEMENT_NODE = 1); +var ATTRIBUTE_NODE = (NodeType.ATTRIBUTE_NODE = 2); +var TEXT_NODE = (NodeType.TEXT_NODE = 3); +var CDATA_SECTION_NODE = (NodeType.CDATA_SECTION_NODE = 4); +var ENTITY_REFERENCE_NODE = (NodeType.ENTITY_REFERENCE_NODE = 5); +var ENTITY_NODE = (NodeType.ENTITY_NODE = 6); +var PROCESSING_INSTRUCTION_NODE = (NodeType.PROCESSING_INSTRUCTION_NODE = 7); +var COMMENT_NODE = (NodeType.COMMENT_NODE = 8); +var DOCUMENT_NODE = (NodeType.DOCUMENT_NODE = 9); +var DOCUMENT_TYPE_NODE = (NodeType.DOCUMENT_TYPE_NODE = 10); +var DOCUMENT_FRAGMENT_NODE = (NodeType.DOCUMENT_FRAGMENT_NODE = 11); +var NOTATION_NODE = (NodeType.NOTATION_NODE = 12); + +var DocumentPosition = conventions.freeze({ + DOCUMENT_POSITION_DISCONNECTED: 1, + DOCUMENT_POSITION_PRECEDING: 2, + DOCUMENT_POSITION_FOLLOWING: 4, + DOCUMENT_POSITION_CONTAINS: 8, + DOCUMENT_POSITION_CONTAINED_BY: 16, + DOCUMENT_POSITION_IMPLEMENTATION_SPECIFIC: 32, +}); + +//helper functions for compareDocumentPosition /** - * DOM Level 2 - * Object DOMException - * @see http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/ecma-script-binding.html - * @see http://www.w3.org/TR/REC-DOM-Level-1/ecma-script-language-binding.html + * Finds the common ancestor in two parent chains. + * + * @param {Node[]} a + * The first parent chain. + * @param {Node[]} b + * The second parent chain. + * @returns {Node} + * The common ancestor node if it exists. If there is no common ancestor, the function will + * return `null`. */ -function DOMException(code, message) { - if(message instanceof Error){ - var error = message; - }else{ - error = this; - Error.call(this, ExceptionMessage[code]); - this.message = ExceptionMessage[code]; - if(Error.captureStackTrace) Error.captureStackTrace(this, DOMException); +function commonAncestor(a, b) { + if (b.length < a.length) return commonAncestor(b, a); + var c = null; + for (var n in a) { + if (a[n] !== b[n]) return c; + c = a[n]; } - error.code = code; - if(message) this.message = this.message + ": " + message; - return error; -}; -DOMException.prototype = Error.prototype; -copy(ExceptionCode,DOMException) + return c; +} /** - * @see http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/core.html#ID-536297177 - * The NodeList interface provides the abstraction of an ordered collection of nodes, without defining or constraining how this collection is implemented. NodeList objects in the DOM are live. + * Assigns a unique identifier to a document to ensure consistency while comparing unrelated + * nodes. + * + * @param {Document} doc + * The document to which a unique identifier is to be assigned. + * @returns {string} + * The unique identifier of the document. If the document already had a unique identifier, the + * function will return the existing one. + */ +function docGUID(doc) { + if (!doc.guid) doc.guid = Math.random(); + return doc.guid; +} +//-- end of helper functions + +/** + * The NodeList interface provides the abstraction of an ordered collection of nodes, + * without defining or constraining how this collection is implemented. + * NodeList objects in the DOM are live. * The items in the NodeList are accessible via an integral index, starting from 0. + * You can also access the items of the NodeList with a `for...of` loop. + * + * @class NodeList + * @see http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/core.html#ID-536297177 + * @constructs NodeList */ -function NodeList() { -}; +function NodeList() {} NodeList.prototype = { /** - * The number of nodes in the list. The range of valid child node indices is 0 to length-1 inclusive. - * @standard level1 + * The number of nodes in the list. The range of valid child node indices is 0 to length-1 + * inclusive. + * + * @type {number} */ - length:0, + length: 0, /** - * Returns the indexth item in the collection. If index is greater than or equal to the number of nodes in the list, this returns null. - * @standard level1 - * @param index unsigned long - * Index into the collection. - * @return Node - * The node at the indexth position in the NodeList, or null if that is not a valid index. + * Returns the item at `index`. If index is greater than or equal to the number of nodes in + * the list, this returns null. + * + * @param index + * Unsigned long Index into the collection. + * @returns {Node | null} + * The node at position `index` in the NodeList, + * or null if that is not a valid index. */ - item: function(index) { + item: function (index) { return index >= 0 && index < this.length ? this[index] : null; }, - toString:function(isHTML,nodeFilter){ - for(var buf = [], i = 0;i=0){ - var lastIndex = list.length-1 - while(i= 0) { + var lastIndex = list.length - 1; + while (i <= lastIndex) { + list[i] = list[++i]; } list.length = lastIndex; - if(el){ + if (el) { var doc = el.ownerDocument; - if(doc){ - _onRemoveAttribute(doc,el,attr); - attr.ownerElement = null; + if (doc) { + _onRemoveAttribute(doc, el, attr); } + attr.ownerElement = null; } - }else{ - throw new DOMException(NOT_FOUND_ERR,new Error(el.tagName+'@'+attr)) } } NamedNodeMap.prototype = { - length:0, - item:NodeList.prototype.item, - getNamedItem: function(key) { -// if(key.indexOf(':')>0 || key == 'xmlns'){ -// return null; -// } - //console.log() - var i = this.length; - while(i--){ + length: 0, + item: NodeList.prototype.item, + + /** + * Get an attribute by name. Note: Name is in lower case in case of HTML namespace and + * document. + * + * @param {string} localName + * The local name of the attribute. + * @returns {Attr | null} + * The attribute with the given local name, or null if no such attribute exists. + * @see https://dom.spec.whatwg.org/#concept-element-attributes-get-by-name + */ + getNamedItem: function (localName) { + if (this._ownerElement && this._ownerElement._isInHTMLDocumentAndNamespace()) { + localName = localName.toLowerCase(); + } + var i = 0; + while (i < this.length) { var attr = this[i]; - //console.log(attr.nodeName,key) - if(attr.nodeName == key){ + if (attr.nodeName === localName) { return attr; } + i++; } + return null; }, - setNamedItem: function(attr) { + + /** + * Set an attribute. + * + * @param {Attr} attr + * The attribute to set. + * @returns {Attr | null} + * The old attribute with the same local name and namespace URI as the new one, or null if no + * such attribute exists. + * @throws {DOMException} + * With code: + * - {@link INUSE_ATTRIBUTE_ERR} - If the attribute is already an attribute of another + * element. + * @see https://dom.spec.whatwg.org/#concept-element-attributes-set + */ + setNamedItem: function (attr) { var el = attr.ownerElement; - if(el && el!=this._ownerElement){ - throw new DOMException(INUSE_ATTRIBUTE_ERR); + if (el && el !== this._ownerElement) { + throw new DOMException(DOMException.INUSE_ATTRIBUTE_ERR); } - var oldAttr = this.getNamedItem(attr.nodeName); - _addNamedNode(this._ownerElement,this,attr,oldAttr); - return oldAttr; - }, - /* returns Node */ - setNamedItemNS: function(attr) {// raises: WRONG_DOCUMENT_ERR,NO_MODIFICATION_ALLOWED_ERR,INUSE_ATTRIBUTE_ERR - var el = attr.ownerElement, oldAttr; - if(el && el!=this._ownerElement){ - throw new DOMException(INUSE_ATTRIBUTE_ERR); + var oldAttr = this.getNamedItemNS(attr.namespaceURI, attr.localName); + if (oldAttr === attr) { + return attr; } - oldAttr = this.getNamedItemNS(attr.namespaceURI,attr.localName); - _addNamedNode(this._ownerElement,this,attr,oldAttr); + _addNamedNode(this._ownerElement, this, attr, oldAttr); return oldAttr; }, - /* returns Node */ - removeNamedItem: function(key) { - var attr = this.getNamedItem(key); - _removeNamedNode(this._ownerElement,this,attr); - return attr; - + /** + * Set an attribute, replacing an existing attribute with the same local name and namespace + * URI if one exists. + * + * @param {Attr} attr + * The attribute to set. + * @returns {Attr | null} + * The old attribute with the same local name and namespace URI as the new one, or null if no + * such attribute exists. + * @throws {DOMException} + * Throws a DOMException with the name "InUseAttributeError" if the attribute is already an + * attribute of another element. + * @see https://dom.spec.whatwg.org/#concept-element-attributes-set + */ + setNamedItemNS: function (attr) { + return this.setNamedItem(attr); + }, - },// raises: NOT_FOUND_ERR,NO_MODIFICATION_ALLOWED_ERR + /** + * Removes an attribute specified by the local name. + * + * @param {string} localName + * The local name of the attribute to be removed. + * @returns {Attr} + * The attribute node that was removed. + * @throws {DOMException} + * With code: + * - {@link DOMException.NOT_FOUND_ERR} if no attribute with the given name is found. + * @see https://dom.spec.whatwg.org/#dom-namednodemap-removenameditem + * @see https://dom.spec.whatwg.org/#concept-element-attributes-remove-by-name + */ + removeNamedItem: function (localName) { + var attr = this.getNamedItem(localName); + if (!attr) { + throw new DOMException(DOMException.NOT_FOUND_ERR, localName); + } + _removeNamedNode(this._ownerElement, this, attr); + return attr; + }, - //for level2 - removeNamedItemNS:function(namespaceURI,localName){ - var attr = this.getNamedItemNS(namespaceURI,localName); - _removeNamedNode(this._ownerElement,this,attr); + /** + * Removes an attribute specified by the namespace and local name. + * + * @param {string | null} namespaceURI + * The namespace URI of the attribute to be removed. + * @param {string} localName + * The local name of the attribute to be removed. + * @returns {Attr} + * The attribute node that was removed. + * @throws {DOMException} + * With code: + * - {@link DOMException.NOT_FOUND_ERR} if no attribute with the given namespace URI and local + * name is found. + * @see https://dom.spec.whatwg.org/#dom-namednodemap-removenameditemns + * @see https://dom.spec.whatwg.org/#concept-element-attributes-remove-by-namespace + */ + removeNamedItemNS: function (namespaceURI, localName) { + var attr = this.getNamedItemNS(namespaceURI, localName); + if (!attr) { + throw new DOMException(DOMException.NOT_FOUND_ERR, namespaceURI ? namespaceURI + ' : ' + localName : localName); + } + _removeNamedNode(this._ownerElement, this, attr); return attr; }, - getNamedItemNS: function(namespaceURI, localName) { - var i = this.length; - while(i--){ + + /** + * Get an attribute by namespace and local name. + * + * @param {string | null} namespaceURI + * The namespace URI of the attribute. + * @param {string} localName + * The local name of the attribute. + * @returns {Attr | null} + * The attribute with the given namespace URI and local name, or null if no such attribute + * exists. + * @see https://dom.spec.whatwg.org/#concept-element-attributes-get-by-namespace + */ + getNamedItemNS: function (namespaceURI, localName) { + if (!namespaceURI) { + namespaceURI = null; + } + var i = 0; + while (i < this.length) { var node = this[i]; - if(node.localName == localName && node.namespaceURI == namespaceURI){ + if (node.localName === localName && node.namespaceURI === namespaceURI) { return node; } + i++; } return null; - } + }, +}; +NamedNodeMap.prototype[Symbol.iterator] = function () { + var me = this; + var index = 0; + + return { + next: function () { + if (index < me.length) { + return { + value: me[index++], + done: false, + }; + } else { + return { + done: true, + }; + } + }, + return: function () { + return { + done: true, + }; + }, + }; }; /** - * The DOMImplementation interface represents an object providing methods - * which are not dependent on any particular document. - * Such an object is returned by the `Document.implementation` property. + * The DOMImplementation interface provides a number of methods for performing operations that + * are independent of any particular instance of the document object model. * - * __The individual methods describe the differences compared to the specs.__ + * The DOMImplementation interface represents an object providing methods which are not + * dependent on any particular document. + * Such an object is returned by the `Document.implementation` property. * - * @constructor + * **The individual methods describe the differences compared to the specs**. * + * @class DOMImplementation * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMImplementation MDN - * @see https://www.w3.org/TR/REC-DOM-Level-1/level-one-core.html#ID-102161490 DOM Level 1 Core (Initial) + * @see https://www.w3.org/TR/REC-DOM-Level-1/level-one-core.html#ID-102161490 DOM Level 1 Core + * (Initial) * @see https://www.w3.org/TR/DOM-Level-2-Core/core.html#ID-102161490 DOM Level 2 Core * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#ID-102161490 DOM Level 3 Core * @see https://dom.spec.whatwg.org/#domimplementation DOM Living Standard + * @constructs DOMImplementation */ -function DOMImplementation() { -} +function DOMImplementation() {} DOMImplementation.prototype = { /** - * The DOMImplementation.hasFeature() method returns a Boolean flag indicating if a given feature is supported. - * The different implementations fairly diverged in what kind of features were reported. - * The latest version of the spec settled to force this method to always return true, where the functionality was accurate and in use. + * Test if the DOM implementation implements a specific feature and version, as specified in + * {@link https://www.w3.org/TR/DOM-Level-3-Core/core.html#DOMFeatures DOM Features}. * - * @deprecated It is deprecated and modern browsers return true in all cases. + * The DOMImplementation.hasFeature() method returns a Boolean flag indicating if a given + * feature is supported. The different implementations fairly diverged in what kind of + * features were reported. The latest version of the spec settled to force this method to + * always return true, where the functionality was accurate and in use. * + * @deprecated + * It is deprecated and modern browsers return true in all cases. + * @function DOMImplementation#hasFeature * @param {string} feature + * The name of the feature to test. * @param {string} [version] - * @returns {boolean} always true - * + * This is the version number of the feature to test. + * @returns {boolean} + * Always returns true. * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMImplementation/hasFeature MDN * @see https://www.w3.org/TR/REC-DOM-Level-1/level-one-core.html#ID-5CED94D7 DOM Level 1 Core * @see https://dom.spec.whatwg.org/#dom-domimplementation-hasfeature DOM Living Standard + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#ID-5CED94D7 DOM Level 3 Core */ - hasFeature: function(feature, version) { - return true; + hasFeature: function (feature, version) { + return true; }, /** - * Creates an XML Document object of the specified type with its document element. + * Creates a DOM Document object of the specified type with its document element. Note that + * based on the {@link DocumentType} + * given to create the document, the implementation may instantiate specialized + * {@link Document} objects that support additional features than the "Core", such as "HTML" + * {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#DOM2HTML DOM Level 2 HTML}. + * On the other hand, setting the {@link DocumentType} after the document was created makes + * this very unlikely to happen. Alternatively, specialized {@link Document} creation methods, + * such as createHTMLDocument + * {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#DOM2HTML DOM Level 2 HTML}, + * can be used to obtain specific types of {@link Document} objects. * * __It behaves slightly different from the description in the living standard__: - * - There is no interface/class `XMLDocument`, it returns a `Document` instance. - * - `contentType`, `encoding`, `mode`, `origin`, `url` fields are currently not declared. - * - this implementation is not validating names or qualified names - * (when parsing XML strings, the SAX parser takes care of that) + * - There is no interface/class `XMLDocument`, it returns a `Document` + * instance (with it's `type` set to `'xml'`). + * - `encoding`, `mode`, `origin`, `url` fields are currently not declared. * - * @param {string|null} namespaceURI - * @param {string} qualifiedName - * @param {DocumentType=null} doctype + * @function DOMImplementation.createDocument + * @param {string | null} namespaceURI + * The + * {@link https://www.w3.org/TR/DOM-Level-3-Core/glossary.html#dt-namespaceURI namespace URI} + * of the document element to create or null. + * @param {string | null} qualifiedName + * The + * {@link https://www.w3.org/TR/DOM-Level-3-Core/glossary.html#dt-qualifiedname qualified name} + * of the document element to be created or null. + * @param {DocumentType | null} [doctype=null] + * The type of document to be created or null. When doctype is not null, its + * {@link Node#ownerDocument} attribute is set to the document being created. Default is + * `null` * @returns {Document} + * A new {@link Document} object with its document element. If the NamespaceURI, + * qualifiedName, and doctype are null, the returned {@link Document} is empty with no + * document element. + * @throws {DOMException} + * With code: * + * - `INVALID_CHARACTER_ERR`: Raised if the specified qualified name is not an XML name + * according to {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#XML XML 1.0}. + * - `NAMESPACE_ERR`: Raised if the qualifiedName is malformed, if the qualifiedName has a + * prefix and the namespaceURI is null, or if the qualifiedName is null and the namespaceURI + * is different from null, or if the qualifiedName has a prefix that is "xml" and the + * namespaceURI is different from "{@link http://www.w3.org/XML/1998/namespace}" + * {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#Namespaces XML Namespaces}, + * or if the DOM implementation does not support the "XML" feature but a non-null namespace + * URI was provided, since namespaces were defined by XML. + * - `WRONG_DOCUMENT_ERR`: Raised if doctype has already been used with a different document + * or was created from a different implementation. + * - `NOT_SUPPORTED_ERR`: May be raised if the implementation does not support the feature + * "XML" and the language exposed through the Document does not support XML Namespaces (such + * as {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#HTML40 HTML 4.01}). + * @since DOM Level 2. + * @see {@link #createHTMLDocument} * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMImplementation/createDocument MDN - * @see https://www.w3.org/TR/DOM-Level-2-Core/core.html#Level-2-Core-DOM-createDocument DOM Level 2 Core (initial) - * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocument DOM Level 2 Core - * - * @see https://dom.spec.whatwg.org/#validate-and-extract DOM: Validate and extract - * @see https://www.w3.org/TR/xml/#NT-NameStartChar XML Spec: Names - * @see https://www.w3.org/TR/xml-names/#ns-qualnames XML Namespaces: Qualified names + * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocument DOM Living Standard + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#Level-2-Core-DOM-createDocument DOM + * Level 3 Core + * @see https://www.w3.org/TR/DOM-Level-2-Core/core.html#Level-2-Core-DOM-createDocument DOM + * Level 2 Core (initial) */ - createDocument: function(namespaceURI, qualifiedName, doctype){ - var doc = new Document(); + createDocument: function (namespaceURI, qualifiedName, doctype) { + var contentType = MIME_TYPE.XML_APPLICATION; + if (namespaceURI === NAMESPACE.HTML) { + contentType = MIME_TYPE.XML_XHTML_APPLICATION; + } else if (namespaceURI === NAMESPACE.SVG) { + contentType = MIME_TYPE.XML_SVG_IMAGE; + } + var doc = new Document(PDC, { contentType: contentType }); doc.implementation = this; doc.childNodes = new NodeList(); doc.doctype = doctype || null; - if (doctype){ + if (doctype) { doc.appendChild(doctype); } - if (qualifiedName){ + if (qualifiedName) { var root = doc.createElementNS(namespaceURI, qualifiedName); doc.appendChild(root); } return doc; }, /** - * Returns a doctype, with the given `qualifiedName`, `publicId`, and `systemId`. + * Creates an empty DocumentType node. Entity declarations and notations are not made + * available. Entity reference expansions and default attribute additions do not occur. * - * __This behavior is slightly different from the in the specs__: - * - this implementation is not validating names or qualified names - * (when parsing XML strings, the SAX parser takes care of that) + * **This behavior is slightly different from the one in the specs**: + * - `encoding`, `mode`, `origin`, `url` fields are currently not declared. + * - `publicId` and `systemId` contain the raw data including any possible quotes, + * so they can always be serialized back to the original value + * - `internalSubset` contains the raw string between `[` and `]` if present, + * but is not parsed or validated in any form. * + * @function DOMImplementation#createDocumentType * @param {string} qualifiedName + * The {@link https://www.w3.org/TR/DOM-Level-3-Core/glossary.html#dt-qualifiedname qualified + * name} of the document type to be created. * @param {string} [publicId] + * The external subset public identifier. * @param {string} [systemId] - * @returns {DocumentType} which can either be used with `DOMImplementation.createDocument` upon document creation - * or can be put into the document via methods like `Node.insertBefore()` or `Node.replaceChild()` + * The external subset system identifier. + * @param {string} [internalSubset] + * the internal subset or an empty string if it is not present + * @returns {DocumentType} + * A new {@link DocumentType} node with {@link Node#ownerDocument} set to null. + * @throws {DOMException} + * With code: * - * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMImplementation/createDocumentType MDN - * @see https://www.w3.org/TR/DOM-Level-2-Core/core.html#Level-2-Core-DOM-createDocType DOM Level 2 Core - * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocumenttype DOM Living Standard - * - * @see https://dom.spec.whatwg.org/#validate-and-extract DOM: Validate and extract - * @see https://www.w3.org/TR/xml/#NT-NameStartChar XML Spec: Names - * @see https://www.w3.org/TR/xml-names/#ns-qualnames XML Namespaces: Qualified names + * - `INVALID_CHARACTER_ERR`: Raised if the specified qualified name is not an XML name + * according to {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#XML XML 1.0}. + * - `NAMESPACE_ERR`: Raised if the qualifiedName is malformed. + * - `NOT_SUPPORTED_ERR`: May be raised if the implementation does not support the feature + * "XML" and the language exposed through the Document does not support XML Namespaces (such + * as {@link https://www.w3.org/TR/DOM-Level-3-Core/references.html#HTML40 HTML 4.01}). + * @since DOM Level 2. + * @see https://developer.mozilla.org/en-US/docs/Web/API/DOMImplementation/createDocumentType + * MDN + * @see https://dom.spec.whatwg.org/#dom-domimplementation-createdocumenttype DOM Living + * Standard + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#Level-3-Core-DOM-createDocType DOM + * Level 3 Core + * @see https://www.w3.org/TR/DOM-Level-2-Core/core.html#Level-2-Core-DOM-createDocType DOM + * Level 2 Core + * @see https://github.com/xmldom/xmldom/blob/master/CHANGELOG.md#050 + * @see https://www.w3.org/TR/DOM-Level-2-Core/#core-ID-Core-DocType-internalSubset + * @prettierignore */ - createDocumentType: function(qualifiedName, publicId, systemId){ - var node = new DocumentType(); + createDocumentType: function (qualifiedName, publicId, systemId, internalSubset) { + validateQualifiedName(qualifiedName); + var node = new DocumentType(PDC); node.name = qualifiedName; node.nodeName = qualifiedName; node.publicId = publicId || ''; node.systemId = systemId || ''; + node.internalSubset = internalSubset || ''; + node.childNodes = new NodeList(); return node; - } + }, + /** + * Returns an HTML document, that might already have a basic DOM structure. + * + * __It behaves slightly different from the description in the living standard__: + * - If the first argument is `false` no initial nodes are added (steps 3-7 in the specs are + * omitted) + * - `encoding`, `mode`, `origin`, `url` fields are currently not declared. + * + * @param {string | false} [title] + * A string containing the title to give the new HTML document. + * @returns {Document} + * The HTML document. + * @since WHATWG Living Standard. + * @see {@link #createDocument} + * @see https://dom.spec.whatwg.org/#dom-domimplementation-createhtmldocument + * @see https://dom.spec.whatwg.org/#html-document + */ + createHTMLDocument: function (title) { + var doc = new Document(PDC, { contentType: MIME_TYPE.HTML }); + doc.implementation = this; + doc.childNodes = new NodeList(); + if (title !== false) { + doc.doctype = this.createDocumentType('html'); + doc.doctype.ownerDocument = doc; + doc.appendChild(doc.doctype); + var htmlNode = doc.createElement('html'); + doc.appendChild(htmlNode); + var headNode = doc.createElement('head'); + htmlNode.appendChild(headNode); + if (typeof title === 'string') { + var titleNode = doc.createElement('title'); + titleNode.appendChild(doc.createTextNode(title)); + headNode.appendChild(titleNode); + } + htmlNode.appendChild(doc.createElement('body')); + } + return doc; + }, }; - /** + * The DOM Node interface is an abstract base class upon which many other DOM API objects are + * based, thus letting those object types to be used similarly and often interchangeably. As an + * abstract class, there is no such thing as a plain Node object. All objects that implement + * Node functionality are based on one of its subclasses. Most notable are Document, Element, + * and DocumentFragment. + * + * In addition, every kind of DOM node is represented by an interface based on Node. These + * include Attr, CharacterData (which Text, Comment, CDATASection and ProcessingInstruction are + * all based on), and DocumentType. + * + * In some cases, a particular feature of the base Node interface may not apply to one of its + * child interfaces; in that case, the inheriting node may return null or throw an exception, + * depending on circumstances. For example, attempting to add children to a node type that + * cannot have children will throw an exception. + * + * **This behavior is slightly different from the in the specs**: + * - unimplemented interfaces: `EventTarget` + * + * @class + * @abstract + * @param {Symbol} symbol * @see http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/core.html#ID-1950641247 + * @see https://dom.spec.whatwg.org/#node + * @prettierignore */ - -function Node() { -}; +function Node(symbol) { + checkSymbol(symbol); +} Node.prototype = { - firstChild : null, - lastChild : null, - previousSibling : null, - nextSibling : null, - attributes : null, - parentNode : null, - childNodes : null, - ownerDocument : null, - nodeValue : null, - namespaceURI : null, - prefix : null, - localName : null, - // Modified in DOM Level 2: - insertBefore:function(newChild, refChild){//raises - return _insertBefore(this,newChild,refChild); - }, - replaceChild:function(newChild, oldChild){//raises - _insertBefore(this, newChild,oldChild, assertPreReplacementValidityInDocument); - if(oldChild){ + /** + * The first child of this node. + * + * @type {Node | null} + */ + firstChild: null, + /** + * The last child of this node. + * + * @type {Node | null} + */ + lastChild: null, + /** + * The previous sibling of this node. + * + * @type {Node | null} + */ + previousSibling: null, + /** + * The next sibling of this node. + * + * @type {Node | null} + */ + nextSibling: null, + /** + * The parent node of this node. + * + * @type {Node | null} + */ + parentNode: null, + /** + * The parent element of this node. + * + * @type {Element | null} + */ + get parentElement() { + return this.parentNode && this.parentNode.nodeType === this.ELEMENT_NODE ? this.parentNode : null; + }, + /** + * The child nodes of this node. + * + * @type {NodeList} + */ + childNodes: null, + /** + * The document object associated with this node. + * + * @type {Document | null} + */ + ownerDocument: null, + /** + * The value of this node. + * + * @type {string | null} + */ + nodeValue: null, + /** + * The namespace URI of this node. + * + * @type {string | null} + */ + namespaceURI: null, + /** + * The prefix of the namespace for this node. + * + * @type {string | null} + */ + prefix: null, + /** + * The local part of the qualified name of this node. + * + * @type {string | null} + */ + localName: null, + /** + * The baseURI is currently always `about:blank`, + * since that's what happens when you create a document from scratch. + * + * @type {'about:blank'} + */ + baseURI: 'about:blank', + /** + * Is true if this node is part of a document. + * + * @type {boolean} + */ + get isConnected() { + var rootNode = this.getRootNode(); + return rootNode && rootNode.nodeType === rootNode.DOCUMENT_NODE; + }, + /** + * Checks whether `other` is an inclusive descendant of this node. + * + * @param {Node | null | undefined} other + * The node to check. + * @returns {boolean} + * True if `other` is an inclusive descendant of this node; false otherwise. + * @see https://dom.spec.whatwg.org/#dom-node-contains + */ + contains: function (other) { + if (!other) return false; + var parent = other; + do { + if (this === parent) return true; + parent = parent.parentNode; + } while (parent); + return false; + }, + /** + * @typedef GetRootNodeOptions + * @property {boolean} [composed=false] + */ + /** + * Searches for the root node of this node. + * + * **This behavior is slightly different from the in the specs**: + * - ignores `options.composed`, since `ShadowRoot`s are unsupported, always returns root. + * + * @param {GetRootNodeOptions} [options] + * @returns {Node} + * Root node. + * @see https://dom.spec.whatwg.org/#dom-node-getrootnode + * @see https://dom.spec.whatwg.org/#concept-shadow-including-root + */ + getRootNode: function (options) { + var parent = this; + do { + if (!parent.parentNode) { + return parent; + } + parent = parent.parentNode; + } while (parent); + }, + /** + * Checks whether the given node is equal to this node. + * + * @param {Node} [otherNode] + * @see https://dom.spec.whatwg.org/#concept-node-equals + */ + isEqualNode: function (otherNode) { + if (!otherNode) return false; + + if (this.nodeType !== otherNode.nodeType) return false; + + switch (this.nodeType) { + case this.DOCUMENT_TYPE_NODE: + if (this.name !== otherNode.name) return false; + if (this.publicId !== otherNode.publicId) return false; + if (this.systemId !== otherNode.systemId) return false; + break; + case this.ELEMENT_NODE: + if (this.namespaceURI !== otherNode.namespaceURI) return false; + if (this.prefix !== otherNode.prefix) return false; + if (this.localName !== otherNode.localName) return false; + if (this.attributes.length !== otherNode.attributes.length) return false; + for (var i = 0; i < this.attributes.length; i++) { + var attr = this.attributes.item(i); + if (!attr.isEqualNode(otherNode.getAttributeNodeNS(attr.namespaceURI, attr.localName))) { + return false; + } + } + break; + case this.ATTRIBUTE_NODE: + if (this.namespaceURI !== otherNode.namespaceURI) return false; + if (this.localName !== otherNode.localName) return false; + if (this.value !== otherNode.value) return false; + + break; + case this.PROCESSING_INSTRUCTION_NODE: + if (this.target !== otherNode.target || this.data !== otherNode.data) { + return false; + } + break; + case this.TEXT_NODE: + case this.COMMENT_NODE: + if (this.data !== otherNode.data) return false; + break; + } + + if (this.childNodes.length !== otherNode.childNodes.length) { + return false; + } + + for (var i = 0; i < this.childNodes.length; i++) { + if (!this.childNodes[i].isEqualNode(otherNode.childNodes[i])) { + return false; + } + } + + return true; + }, + /** + * Checks whether or not the given node is this node. + * + * @param {Node} [otherNode] + */ + isSameNode: function (otherNode) { + return this === otherNode; + }, + /** + * Inserts a node before a reference node as a child of this node. + * + * @param {Node} newChild + * The new child node to be inserted. + * @param {Node | null} refChild + * The reference node before which newChild will be inserted. + * @returns {Node} + * The new child node successfully inserted. + * @throws {DOMException} + * Throws a DOMException if inserting the node would result in a DOM tree that is not + * well-formed, or if `child` is provided but is not a child of `parent`. + * See {@link _insertBefore} for more details. + * @since Modified in DOM L2 + */ + insertBefore: function (newChild, refChild) { + return _insertBefore(this, newChild, refChild); + }, + /** + * Replaces an old child node with a new child node within this node. + * + * @param {Node} newChild + * The new node that is to replace the old node. + * If it already exists in the DOM, it is removed from its original position. + * @param {Node} oldChild + * The existing child node to be replaced. + * @returns {Node} + * Returns the replaced child node. + * @throws {DOMException} + * Throws a DOMException if replacing the node would result in a DOM tree that is not + * well-formed, or if `oldChild` is not a child of `this`. + * This can also occur if the pre-replacement validity assertion fails. + * See {@link _insertBefore}, {@link Node.removeChild}, and + * {@link assertPreReplacementValidityInDocument} for more details. + * @see https://dom.spec.whatwg.org/#concept-node-replace + */ + replaceChild: function (newChild, oldChild) { + _insertBefore(this, newChild, oldChild, assertPreReplacementValidityInDocument); + if (oldChild) { this.removeChild(oldChild); } }, - removeChild:function(oldChild){ - return _removeChild(this,oldChild); + /** + * Removes an existing child node from this node. + * + * @param {Node} oldChild + * The child node to be removed. + * @returns {Node} + * Returns the removed child node. + * @throws {DOMException} + * Throws a DOMException if `oldChild` is not a child of `this`. + * See {@link _removeChild} for more details. + */ + removeChild: function (oldChild) { + return _removeChild(this, oldChild); }, - appendChild:function(newChild){ - return this.insertBefore(newChild,null); + /** + * Appends a child node to this node. + * + * @param {Node} newChild + * The child node to be appended to this node. + * If it already exists in the DOM, it is removed from its original position. + * @returns {Node} + * Returns the appended child node. + * @throws {DOMException} + * Throws a DOMException if appending the node would result in a DOM tree that is not + * well-formed, or if `newChild` is not a valid Node. + * See {@link insertBefore} for more details. + */ + appendChild: function (newChild) { + return this.insertBefore(newChild, null); }, - hasChildNodes:function(){ + /** + * Determines whether this node has any child nodes. + * + * @returns {boolean} + * Returns true if this node has any child nodes, and false otherwise. + */ + hasChildNodes: function () { return this.firstChild != null; }, - cloneNode:function(deep){ - return cloneNode(this.ownerDocument||this,this,deep); + /** + * Creates a copy of the calling node. + * + * @param {boolean} deep + * If true, the contents of the node are recursively copied. + * If false, only the node itself (and its attributes, if it is an element) are copied. + * @returns {Node} + * Returns the newly created copy of the node. + * @throws {DOMException} + * May throw a DOMException if operations within {@link Element#setAttributeNode} or + * {@link Node#appendChild} (which are potentially invoked in this method) do not meet their + * specific constraints. + * @see {@link cloneNode} + */ + cloneNode: function (deep) { + return cloneNode(this.ownerDocument || this, this, deep); }, - // Modified in DOM Level 2: - normalize:function(){ + /** + * Puts the specified node and all of its subtree into a "normalized" form. In a normalized + * subtree, no text nodes in the subtree are empty and there are no adjacent text nodes. + * + * Specifically, this method merges any adjacent text nodes (i.e., nodes for which `nodeType` + * is `TEXT_NODE`) into a single node with the combined data. It also removes any empty text + * nodes. + * + * This method operates recursively, so it also normalizes any and all descendent nodes within + * the subtree. + * + * @throws {DOMException} + * May throw a DOMException if operations within removeChild or appendData (which are + * potentially invoked in this method) do not meet their specific constraints. + * @since Modified in DOM Level 2 + * @see {@link Node.removeChild} + * @see {@link CharacterData.appendData} + */ + normalize: function () { var child = this.firstChild; - while(child){ + while (child) { var next = child.nextSibling; - if(next && next.nodeType == TEXT_NODE && child.nodeType == TEXT_NODE){ + if (next && next.nodeType == TEXT_NODE && child.nodeType == TEXT_NODE) { this.removeChild(next); child.appendData(next.data); - }else{ + } else { child.normalize(); child = next; } } }, - // Introduced in DOM Level 2: - isSupported:function(feature, version){ - return this.ownerDocument.implementation.hasFeature(feature,version); + /** + * Checks whether the DOM implementation implements a specific feature and its version. + * + * @deprecated + * Since `DOMImplementation.hasFeature` is deprecated and always returns true. + * @param {string} feature + * The package name of the feature to test. This is the same name that can be passed to the + * method `hasFeature` on `DOMImplementation`. + * @param {string} version + * This is the version number of the package name to test. + * @returns {boolean} + * Returns true in all cases in the current implementation. + * @since Introduced in DOM Level 2 + * @see {@link DOMImplementation.hasFeature} + */ + isSupported: function (feature, version) { + return this.ownerDocument.implementation.hasFeature(feature, version); }, - // Introduced in DOM Level 2: - hasAttributes:function(){ - return this.attributes.length>0; - }, /** * Look up the prefix associated to the given namespace URI, starting from this node. * **The default namespace declarations are ignored by this method.** * See Namespace Prefix Lookup for details on the algorithm used by this method. * - * _Note: The implementation seems to be incomplete when compared to the algorithm described in the specs._ + * **This behavior is different from the in the specs**: + * - no node type specific handling + * - uses the internal attribute _nsMap for resolving namespaces that is updated when changing attributes * * @param {string | null} namespaceURI + * The namespace URI for which to find the associated prefix. * @returns {string | null} + * The associated prefix, if found; otherwise, null. * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#Node3-lookupNamespacePrefix * @see https://www.w3.org/TR/DOM-Level-3-Core/namespaces-algorithms.html#lookupNamespacePrefixAlgo * @see https://dom.spec.whatwg.org/#dom-node-lookupprefix * @see https://github.com/xmldom/xmldom/issues/322 + * @prettierignore */ - lookupPrefix:function(namespaceURI){ - var el = this; - while(el){ - var map = el._nsMap; - //console.dir(map) - if(map){ - for(var n in map){ - if (Object.prototype.hasOwnProperty.call(map, n) && map[n] === namespaceURI) { - return n; - } - } - } - el = el.nodeType == ATTRIBUTE_NODE?el.ownerDocument : el.parentNode; - } - return null; - }, - // Introduced in DOM Level 3: - lookupNamespaceURI:function(prefix){ - var el = this; - while(el){ - var map = el._nsMap; - //console.dir(map) - if(map){ - if(Object.prototype.hasOwnProperty.call(map, prefix)){ - return map[prefix] ; - } - } - el = el.nodeType == ATTRIBUTE_NODE?el.ownerDocument : el.parentNode; - } - return null; - }, - // Introduced in DOM Level 3: - isDefaultNamespace:function(namespaceURI){ - var prefix = this.lookupPrefix(namespaceURI); - return prefix == null; - } -}; + lookupPrefix: function (namespaceURI) { + var el = this; + while (el) { + var map = el._nsMap; + //console.dir(map) + if (map) { + for (var n in map) { + if (hasOwn(map, n) && map[n] === namespaceURI) { + return n; + } + } + } + el = el.nodeType == ATTRIBUTE_NODE ? el.ownerDocument : el.parentNode; + } + return null; + }, + /** + * This function is used to look up the namespace URI associated with the given prefix, + * starting from this node. + * + * **This behavior is different from the in the specs**: + * - no node type specific handling + * - uses the internal attribute _nsMap for resolving namespaces that is updated when changing attributes + * + * @param {string | null} prefix + * The prefix for which to find the associated namespace URI. + * @returns {string | null} + * The associated namespace URI, if found; otherwise, null. + * @since DOM Level 3 + * @see https://dom.spec.whatwg.org/#dom-node-lookupnamespaceuri + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#Node3-lookupNamespaceURI + * @prettierignore + */ + lookupNamespaceURI: function (prefix) { + var el = this; + while (el) { + var map = el._nsMap; + //console.dir(map) + if (map) { + if (hasOwn(map, prefix)) { + return map[prefix]; + } + } + el = el.nodeType == ATTRIBUTE_NODE ? el.ownerDocument : el.parentNode; + } + return null; + }, + /** + * Determines whether the given namespace URI is the default namespace. + * + * The function works by looking up the prefix associated with the given namespace URI. If no + * prefix is found (i.e., the namespace URI is not registered in the namespace map of this + * node or any of its ancestors), it returns `true`, implying the namespace URI is considered + * the default. + * + * **This behavior is different from the in the specs**: + * - no node type specific handling + * - uses the internal attribute _nsMap for resolving namespaces that is updated when changing attributes + * + * @param {string | null} namespaceURI + * The namespace URI to be checked. + * @returns {boolean} + * Returns true if the given namespace URI is the default namespace, false otherwise. + * @since DOM Level 3 + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#Node3-isDefaultNamespace + * @see https://dom.spec.whatwg.org/#dom-node-isdefaultnamespace + * @prettierignore + */ + isDefaultNamespace: function (namespaceURI) { + var prefix = this.lookupPrefix(namespaceURI); + return prefix == null; + }, + /** + * Compares the reference node with a node with regard to their position in the document and + * according to the document order. + * + * @param {Node} other + * The node to compare the reference node to. + * @returns {number} + * Returns how the node is positioned relatively to the reference node according to the + * bitmask. 0 if reference node and given node are the same. + * @since DOM Level 3 + * @see https://www.w3.org/TR/2004/REC-DOM-Level-3-Core-20040407/core.html#Node3-compare + * @see https://dom.spec.whatwg.org/#dom-node-comparedocumentposition + */ + compareDocumentPosition: function (other) { + if (this === other) return 0; + var node1 = other; + var node2 = this; + var attr1 = null; + var attr2 = null; + if (node1 instanceof Attr) { + attr1 = node1; + node1 = attr1.ownerElement; + } + if (node2 instanceof Attr) { + attr2 = node2; + node2 = attr2.ownerElement; + if (attr1 && node1 && node2 === node1) { + for (var i = 0, attr; (attr = node2.attributes[i]); i++) { + if (attr === attr1) + return DocumentPosition.DOCUMENT_POSITION_IMPLEMENTATION_SPECIFIC + DocumentPosition.DOCUMENT_POSITION_PRECEDING; + if (attr === attr2) + return DocumentPosition.DOCUMENT_POSITION_IMPLEMENTATION_SPECIFIC + DocumentPosition.DOCUMENT_POSITION_FOLLOWING; + } + } + } + if (!node1 || !node2 || node2.ownerDocument !== node1.ownerDocument) { + return ( + DocumentPosition.DOCUMENT_POSITION_DISCONNECTED + + DocumentPosition.DOCUMENT_POSITION_IMPLEMENTATION_SPECIFIC + + (docGUID(node2.ownerDocument) > docGUID(node1.ownerDocument) + ? DocumentPosition.DOCUMENT_POSITION_FOLLOWING + : DocumentPosition.DOCUMENT_POSITION_PRECEDING) + ); + } + if (attr2 && node1 === node2) { + return DocumentPosition.DOCUMENT_POSITION_CONTAINS + DocumentPosition.DOCUMENT_POSITION_PRECEDING; + } + if (attr1 && node1 === node2) { + return DocumentPosition.DOCUMENT_POSITION_CONTAINED_BY + DocumentPosition.DOCUMENT_POSITION_FOLLOWING; + } + + 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; + if (child === node1) return DocumentPosition.DOCUMENT_POSITION_PRECEDING; + if (chain2.indexOf(child) >= 0) return DocumentPosition.DOCUMENT_POSITION_FOLLOWING; + if (chain1.indexOf(child) >= 0) return DocumentPosition.DOCUMENT_POSITION_PRECEDING; + } + return 0; + }, +}; -function _xmlEncoder(c){ - return c == '<' && '<' || - c == '>' && '>' || - c == '&' && '&' || - c == '"' && '"' || - '&#'+c.charCodeAt()+';' +/** + * Encodes special XML characters to their corresponding entities. + * + * @param {string} c + * The character to be encoded. + * @returns {string} + * The encoded character. + * @private + */ +function _xmlEncoder(c) { + return ( + (c == '<' && '<') || (c == '>' && '>') || (c == '&' && '&') || (c == '"' && '"') || '&#' + c.charCodeAt() + ';' + ); } - -copy(NodeType,Node); -copy(NodeType,Node.prototype); +copy(NodeType, Node); +copy(NodeType, Node.prototype); +copy(DocumentPosition, Node); +copy(DocumentPosition, Node.prototype); /** - * @param callback return true for continue,false for break - * @return boolean true: break visit; + * @param callback + * Return true for continue,false for break. + * @returns + * boolean true: break visit; */ -function _visitNode(node,callback){ - if(callback(node)){ +function _visitNode(node, callback) { + if (callback(node)) { return true; } - if(node = node.firstChild){ - do{ - if(_visitNode(node,callback)){return true} - }while(node=node.nextSibling) - } + if ((node = node.firstChild)) { + do { + if (_visitNode(node, callback)) { + return true; + } + } while ((node = node.nextSibling)); + } } +/** + * @typedef DocumentOptions + * @property {string} [contentType=MIME_TYPE.XML_APPLICATION] + */ +/** + * The Document interface describes the common properties and methods for any kind of document. + * + * It should usually be created using `new DOMImplementation().createDocument(...)` + * or `new DOMImplementation().createHTMLDocument(...)`. + * + * The constructor is considered a private API and offers to initially set the `contentType` + * property via it's options parameter. + * + * @class + * @param {Symbol} symbol + * @param {DocumentOptions} [options] + * @augments Node + * @private + * @see https://developer.mozilla.org/en-US/docs/Web/API/Document + * @see https://dom.spec.whatwg.org/#interface-document + */ +function Document(symbol, options) { + checkSymbol(symbol); - -function Document(){ + var opt = options || {}; this.ownerDocument = this; + /** + * The mime type of the document is determined at creation time and can not be modified. + * + * @type {string} + * @see https://dom.spec.whatwg.org/#concept-document-content-type + * @see {@link DOMImplementation} + * @see {@link MIME_TYPE} + * @readonly + */ + this.contentType = opt.contentType || MIME_TYPE.XML_APPLICATION; + /** + * @type {'html' | 'xml'} + * @see https://dom.spec.whatwg.org/#concept-document-type + * @see {@link DOMImplementation} + * @readonly + */ + this.type = isHTMLMimeType(this.contentType) ? 'html' : 'xml'; } -function _onAddAttribute(doc,el,newAttr){ +/** + * Updates the namespace mapping of an element when a new attribute is added. + * + * @param {Document} doc + * The document that the element belongs to. + * @param {Element} el + * The element to which the attribute is being added. + * @param {Attr} newAttr + * The new attribute being added. + * @private + */ +function _onAddAttribute(doc, el, newAttr) { doc && doc._inc++; - var ns = newAttr.namespaceURI ; - if(ns === NAMESPACE.XMLNS){ + var ns = newAttr.namespaceURI; + if (ns === NAMESPACE.XMLNS) { //update namespace - el._nsMap[newAttr.prefix?newAttr.localName:''] = newAttr.value + el._nsMap[newAttr.prefix ? newAttr.localName : ''] = newAttr.value; } } -function _onRemoveAttribute(doc,el,newAttr,remove){ +/** + * Updates the namespace mapping of an element when an attribute is removed. + * + * @param {Document} doc + * The document that the element belongs to. + * @param {Element} el + * The element from which the attribute is being removed. + * @param {Attr} newAttr + * The attribute being removed. + * @param {boolean} remove + * Indicates whether the attribute is to be removed. + * @private + */ +function _onRemoveAttribute(doc, el, newAttr, remove) { doc && doc._inc++; - var ns = newAttr.namespaceURI ; - if(ns === NAMESPACE.XMLNS){ + var ns = newAttr.namespaceURI; + if (ns === NAMESPACE.XMLNS) { //update namespace - delete el._nsMap[newAttr.prefix?newAttr.localName:''] + delete el._nsMap[newAttr.prefix ? newAttr.localName : '']; } } /** - * Updates `el.childNodes`, updating the indexed items and it's `length`. - * Passing `newChild` means it will be appended. - * Otherwise it's assumed that an item has been removed, - * and `el.firstNode` and it's `.nextSibling` are used - * to walk the current list of child nodes. + * Updates `parent.childNodes`, adjusting the indexed items and its `length`. + * If `newChild` is provided and has no nextSibling, it will be appended. + * Otherwise, it's assumed that an item has been removed or inserted, + * and `parent.firstNode` and its `.nextSibling` to re-indexing all child nodes of `parent`. * * @param {Document} doc - * @param {Node} el + * The parent document of `el`. + * @param {Node} parent + * The parent node whose childNodes list needs to be updated. * @param {Node} [newChild] + * The new child node to be appended. If not provided, the function assumes a node has been + * removed. * @private */ -function _onUpdateChild (doc, el, newChild) { - if(doc && doc._inc){ +function _onUpdateChild(doc, parent, newChild) { + if (doc && doc._inc) { doc._inc++; - //update childNodes - var cs = el.childNodes; - if (newChild) { - cs[cs.length++] = newChild; + var childNodes = parent.childNodes; + // assumes nextSibling and previousSibling were already configured upfront + if (newChild && !newChild.nextSibling) { + // if an item has been appended, we only need to update the last index and the length + childNodes[childNodes.length++] = newChild; } else { - var child = el.firstChild; + // otherwise we need to reindex all items, + // which can take a while when processing nodes with a lot of children + var child = parent.firstChild; var i = 0; while (child) { - cs[i++] = child; + childNodes[i++] = child; child = child.nextSibling; } - cs.length = i; - delete cs[cs.length]; + childNodes.length = i; + delete childNodes[childNodes.length]; } } } @@ -653,36 +1666,45 @@ function _onUpdateChild (doc, el, newChild) { * Removes the connections between `parentNode` and `child` * and any existing `child.previousSibling` or `child.nextSibling`. * - * @see https://github.com/xmldom/xmldom/issues/135 - * @see https://github.com/xmldom/xmldom/issues/145 - * * @param {Node} parentNode + * The parent node from which the child node is to be removed. * @param {Node} child - * @returns {Node} the child that was removed. + * The child node to be removed from the parentNode. + * @returns {Node} + * Returns the child node that was removed. + * @throws {DOMException} + * With code: + * - {@link DOMException.NOT_FOUND_ERR} If the parentNode is not the parent of the child node. * @private + * @see https://github.com/xmldom/xmldom/issues/135 + * @see https://github.com/xmldom/xmldom/issues/145 */ -function _removeChild (parentNode, child) { - var previous = child.previousSibling; - var next = child.nextSibling; - if (previous) { - previous.nextSibling = next; +function _removeChild(parentNode, child) { + if (parentNode !== child.parentNode) { + throw new DOMException(DOMException.NOT_FOUND_ERR, "child's parent is not parent"); + } + var oldPreviousSibling = child.previousSibling; + var oldNextSibling = child.nextSibling; + if (oldPreviousSibling) { + oldPreviousSibling.nextSibling = oldNextSibling; } else { - parentNode.firstChild = next; + parentNode.firstChild = oldNextSibling; } - if (next) { - next.previousSibling = previous; + if (oldNextSibling) { + oldNextSibling.previousSibling = oldPreviousSibling; } else { - parentNode.lastChild = previous; + parentNode.lastChild = oldPreviousSibling; } + _onUpdateChild(parentNode.ownerDocument, parentNode); child.parentNode = null; child.previousSibling = null; child.nextSibling = null; - _onUpdateChild(parentNode.ownerDocument, parentNode); return child; } /** * Returns `true` if `node` can be a parent for insertion. + * * @param {Node} node * @returns {boolean} */ @@ -695,23 +1717,26 @@ function hasValidParentNodeType(node) { /** * Returns `true` if `node` can be inserted according to it's `nodeType`. + * * @param {Node} node * @returns {boolean} */ function hasInsertableNodeType(node) { return ( node && - (isElementNode(node) || - isTextNode(node) || - isDocTypeNode(node) || - node.nodeType === Node.DOCUMENT_FRAGMENT_NODE || + (node.nodeType === Node.CDATA_SECTION_NODE || node.nodeType === Node.COMMENT_NODE || - node.nodeType === Node.PROCESSING_INSTRUCTION_NODE) + node.nodeType === Node.DOCUMENT_FRAGMENT_NODE || + node.nodeType === Node.DOCUMENT_TYPE_NODE || + node.nodeType === Node.ELEMENT_NODE || + node.nodeType === Node.PROCESSING_INSTRUCTION_NODE || + node.nodeType === Node.TEXT_NODE) ); } /** - * Returns true if `node` is a DOCTYPE node + * Returns true if `node` is a DOCTYPE node. + * * @param {Node} node * @returns {boolean} */ @@ -720,7 +1745,8 @@ function isDocTypeNode(node) { } /** - * Returns true if the node is an element + * Returns true if the node is an element. + * * @param {Node} node * @returns {boolean} */ @@ -728,7 +1754,8 @@ function isElementNode(node) { return node && node.nodeType === Node.ELEMENT_NODE; } /** - * Returns true if `node` is a text node + * Returns true if `node` is a text node. + * * @param {Node} node * @returns {boolean} */ @@ -740,11 +1767,13 @@ function isTextNode(node) { * Check if en element node can be inserted before `child`, or at the end if child is falsy, * according to the presence and position of a doctype node on the same level. * - * @param {Document} doc The document node - * @param {Node} child the node that would become the nextSibling if the element would be inserted - * @returns {boolean} `true` if an element can be inserted before child + * @param {Document} doc + * The document node. + * @param {Node} child + * The node that would become the nextSibling if the element would be inserted. + * @returns {boolean} + * `true` if an element can be inserted before child. * @private - * https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity */ function isElementInsertionPossible(doc, child) { var parentChildNodes = doc.childNodes || []; @@ -759,11 +1788,13 @@ function isElementInsertionPossible(doc, child) { * Check if en element node can be inserted before `child`, or at the end if child is falsy, * according to the presence and position of a doctype node on the same level. * - * @param {Node} doc The document node - * @param {Node} child the node that would become the nextSibling if the element would be inserted - * @returns {boolean} `true` if an element can be inserted before child + * @param {Node} doc + * The document node. + * @param {Node} child + * The node that would become the nextSibling if the element would be inserted. + * @returns {boolean} + * `true` if an element can be inserted before child. * @private - * https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity */ function isElementReplacementPossible(doc, child) { var parentChildNodes = doc.childNodes || []; @@ -780,28 +1811,41 @@ function isElementReplacementPossible(doc, child) { } /** - * @private - * Steps 1-5 of the checks before inserting and before replacing a child are the same. + * Asserts pre-insertion validity of a node into a parent before a child. + * Throws errors for invalid node combinations that would result in an ill-formed DOM. * - * @param {Node} parent the parent node to insert `node` into - * @param {Node} node the node to insert - * @param {Node=} child the node that should become the `nextSibling` of `node` - * @returns {Node} - * @throws DOMException for several node combinations that would create a DOM that is not well-formed. - * @throws DOMException if `child` is provided but is not a child of `parent`. + * @param {Node} parent + * The parent node to insert `node` into. + * @param {Node} node + * The node to insert. + * @param {Node | null} child + * The node that should become the `nextSibling` of `node`. If null, no sibling is considered. + * @throws {DOMException} + * With code: + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `parent` is not a Document, + * DocumentFragment, or Element node. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is a host-including inclusive + * ancestor of `parent`. (Currently not implemented) + * - {@link DOMException.NOT_FOUND_ERR} If `child` is non-null and its `parent` is not + * `parent`. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is not a DocumentFragment, + * DocumentType, Element, or CharacterData node. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If either `node` is a Text node and `parent` is + * a document, or if `node` is a doctype and `parent` is not a document. + * @private * @see https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity * @see https://dom.spec.whatwg.org/#concept-node-replace */ function assertPreInsertionValidity1to5(parent, node, child) { // 1. If `parent` is not a Document, DocumentFragment, or Element node, then throw a "HierarchyRequestError" DOMException. if (!hasValidParentNodeType(parent)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Unexpected parent node type ' + parent.nodeType); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Unexpected parent node type ' + parent.nodeType); } // 2. If `node` is a host-including inclusive ancestor of `parent`, then throw a "HierarchyRequestError" DOMException. // not implemented! // 3. If `child` is non-null and its parent is not `parent`, then throw a "NotFoundError" DOMException. if (child && child.parentNode !== parent) { - throw new DOMException(NOT_FOUND_ERR, 'child not in parent'); + throw new DOMException(DOMException.NOT_FOUND_ERR, 'child not in parent'); } if ( // 4. If `node` is not a DocumentFragment, DocumentType, Element, or CharacterData node, then throw a "HierarchyRequestError" DOMException. @@ -813,22 +1857,38 @@ function assertPreInsertionValidity1to5(parent, node, child) { (isDocTypeNode(node) && parent.nodeType !== Node.DOCUMENT_NODE) ) { throw new DOMException( - HIERARCHY_REQUEST_ERR, + DOMException.HIERARCHY_REQUEST_ERR, 'Unexpected node type ' + node.nodeType + ' for parent node type ' + parent.nodeType ); } } /** - * @private - * Step 6 of the checks before inserting and before replacing a child are different. + * Asserts pre-insertion validity of a node into a document before a child. + * Throws errors for invalid node combinations that would result in an ill-formed DOM. * - * @param {Document} parent the parent node to insert `node` into - * @param {Node} node the node to insert - * @param {Node | undefined} child the node that should become the `nextSibling` of `node` + * @param {Document} parent + * The parent node to insert `node` into. + * @param {Node} node + * The node to insert. + * @param {Node | undefined} child + * The node that should become the `nextSibling` of `node`. If undefined, no sibling is + * considered. * @returns {Node} - * @throws DOMException for several node combinations that would create a DOM that is not well-formed. - * @throws DOMException if `child` is provided but is not a child of `parent`. + * @throws {DOMException} + * With code: + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is a DocumentFragment with more than + * one element child or has a Text node child. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is a DocumentFragment with one + * element child and either `parent` has an element child, `child` is a doctype, or `child` is + * non-null and a doctype is following `child`. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is an Element and `parent` has an + * element child, `child` is a doctype, or `child` is non-null and a doctype is following + * `child`. + * - {@link DOMException.HIERARCHY_REQUEST_ERR} If `node` is a DocumentType and `parent` has a + * doctype child, `child` is non-null and an element is preceding `child`, or `child` is null + * and `parent` has an element child. + * @private * @see https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity * @see https://dom.spec.whatwg.org/#concept-node-replace */ @@ -841,12 +1901,12 @@ function assertPreInsertionValidityInDocument(parent, node, child) { var nodeChildElements = nodeChildNodes.filter(isElementNode); // If node has more than one element child or has a Text node child. if (nodeChildElements.length > 1 || find(nodeChildNodes, isTextNode)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'More than one element or text in fragment'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'More than one element or text in fragment'); } // Otherwise, if `node` has one element child and either `parent` has an element child, // `child` is a doctype, or `child` is non-null and a doctype is following `child`. if (nodeChildElements.length === 1 && !isElementInsertionPossible(parent, child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Element in fragment can not be inserted before doctype'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Element in fragment can not be inserted before doctype'); } } // Element @@ -854,37 +1914,40 @@ function assertPreInsertionValidityInDocument(parent, node, child) { // `parent` has an element child, `child` is a doctype, // or `child` is non-null and a doctype is following `child`. if (!isElementInsertionPossible(parent, child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one element can be added and only after doctype'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Only one element can be added and only after doctype'); } } // DocumentType if (isDocTypeNode(node)) { // `parent` has a doctype child, if (find(parentChildNodes, isDocTypeNode)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one doctype is allowed'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Only one doctype is allowed'); } var parentElementChild = find(parentChildNodes, isElementNode); // `child` is non-null and an element is preceding `child`, if (child && parentChildNodes.indexOf(parentElementChild) < parentChildNodes.indexOf(child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Doctype can only be inserted before an element'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Doctype can only be inserted before an element'); } // or `child` is null and `parent` has an element child. if (!child && parentElementChild) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Doctype can not be appended since element is present'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Doctype can not be appended since element is present'); } } } /** - * @private - * Step 6 of the checks before inserting and before replacing a child are different. - * - * @param {Document} parent the parent node to insert `node` into - * @param {Node} node the node to insert - * @param {Node | undefined} child the node that should become the `nextSibling` of `node` + * @param {Document} parent + * The parent node to insert `node` into. + * @param {Node} node + * The node to insert. + * @param {Node | undefined} child + * the node that should become the `nextSibling` of `node` * @returns {Node} - * @throws DOMException for several node combinations that would create a DOM that is not well-formed. - * @throws DOMException if `child` is provided but is not a child of `parent`. + * @throws {DOMException} + * For several node combinations that would create a DOM that is not well-formed. + * @throws {DOMException} + * If `child` is provided but is not a child of `parent`. + * @private * @see https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity * @see https://dom.spec.whatwg.org/#concept-node-replace */ @@ -897,18 +1960,18 @@ function assertPreReplacementValidityInDocument(parent, node, child) { var nodeChildElements = nodeChildNodes.filter(isElementNode); // If `node` has more than one element child or has a Text node child. if (nodeChildElements.length > 1 || find(nodeChildNodes, isTextNode)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'More than one element or text in fragment'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'More than one element or text in fragment'); } // Otherwise, if `node` has one element child and either `parent` has an element child that is not `child` or a doctype is following `child`. if (nodeChildElements.length === 1 && !isElementReplacementPossible(parent, child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Element in fragment can not be inserted before doctype'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Element in fragment can not be inserted before doctype'); } } // Element if (isElementNode(node)) { // `parent` has an element child that is not `child` or a doctype is following `child`. if (!isElementReplacementPossible(parent, child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one element can be added and only after doctype'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Only one element can be added and only after doctype'); } } // DocumentType @@ -919,24 +1982,39 @@ function assertPreReplacementValidityInDocument(parent, node, child) { // `parent` has a doctype child that is not `child`, if (find(parentChildNodes, hasDoctypeChildThatIsNotChild)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one doctype is allowed'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Only one doctype is allowed'); } var parentElementChild = find(parentChildNodes, isElementNode); // or an element is preceding `child`. if (child && parentChildNodes.indexOf(parentElementChild) < parentChildNodes.indexOf(child)) { - throw new DOMException(HIERARCHY_REQUEST_ERR, 'Doctype can only be inserted before an element'); + throw new DOMException(DOMException.HIERARCHY_REQUEST_ERR, 'Doctype can only be inserted before an element'); } } } /** - * @private - * @param {Node} parent the parent node to insert `node` into - * @param {Node} node the node to insert - * @param {Node=} child the node that should become the `nextSibling` of `node` + * Inserts a node into a parent node before a child node. + * + * @param {Node} parent + * The parent node to insert the node into. + * @param {Node} node + * The node to insert into the parent. + * @param {Node | null} child + * The node that should become the next sibling of the node. + * If null, the function inserts the node at the end of the children of the parent node. + * @param {Function} [_inDocumentAssertion] + * An optional function to check pre-insertion validity if parent is a document node. + * Defaults to {@link assertPreInsertionValidityInDocument} * @returns {Node} - * @throws DOMException for several node combinations that would create a DOM that is not well-formed. - * @throws DOMException if `child` is provided but is not a child of `parent`. + * Returns the inserted node. + * @throws {DOMException} + * Throws a DOMException if inserting the node would result in a DOM tree that is not + * well-formed. See {@link assertPreInsertionValidity1to5}, + * {@link assertPreInsertionValidityInDocument}. + * @throws {DOMException} + * Throws a DOMException if child is provided but is not a child of the parent. See + * {@link Node.removeChild} + * @private * @see https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity */ function _insertBefore(parent, node, child, _inDocumentAssertion) { @@ -950,16 +2028,16 @@ function _insertBefore(parent, node, child, _inDocumentAssertion) { } var cp = node.parentNode; - if(cp){ - cp.removeChild(node);//remove and update + if (cp) { + cp.removeChild(node); //remove and update } - if(node.nodeType === DOCUMENT_FRAGMENT_NODE){ + if (node.nodeType === DOCUMENT_FRAGMENT_NODE) { var newFirst = node.firstChild; if (newFirst == null) { return node; } var newLast = node.lastChild; - }else{ + } else { newFirst = newLast = node; } var pre = child ? child.previousSibling : parent.lastChild; @@ -967,76 +2045,54 @@ function _insertBefore(parent, node, child, _inDocumentAssertion) { newFirst.previousSibling = pre; newLast.nextSibling = child; - - if(pre){ + if (pre) { pre.nextSibling = newFirst; - }else{ + } else { parent.firstChild = newFirst; } - if(child == null){ + if (child == null) { parent.lastChild = newLast; - }else{ + } else { child.previousSibling = newLast; } - do{ + do { newFirst.parentNode = parent; - }while(newFirst !== newLast && (newFirst= newFirst.nextSibling)) - _onUpdateChild(parent.ownerDocument||parent, parent); - //console.log(parent.lastChild.nextSibling == null) + } while (newFirst !== newLast && (newFirst = newFirst.nextSibling)); + _onUpdateChild(parent.ownerDocument || parent, parent, node); if (node.nodeType == DOCUMENT_FRAGMENT_NODE) { node.firstChild = node.lastChild = null; } - return node; -} -/** - * Appends `newChild` to `parentNode`. - * If `newChild` is already connected to a `parentNode` it is first removed from it. - * - * @see https://github.com/xmldom/xmldom/issues/135 - * @see https://github.com/xmldom/xmldom/issues/145 - * @param {Node} parentNode - * @param {Node} newChild - * @returns {Node} - * @private - */ -function _appendSingleChild (parentNode, newChild) { - if (newChild.parentNode) { - newChild.parentNode.removeChild(newChild); - } - newChild.parentNode = parentNode; - newChild.previousSibling = parentNode.lastChild; - newChild.nextSibling = null; - if (newChild.previousSibling) { - newChild.previousSibling.nextSibling = newChild; - } else { - parentNode.firstChild = newChild; - } - parentNode.lastChild = newChild; - _onUpdateChild(parentNode.ownerDocument, parentNode, newChild); - return newChild; + return node; } Document.prototype = { - //implementation : null, - nodeName : '#document', - nodeType : DOCUMENT_NODE, /** - * The DocumentType node of the document. + * The implementation that created this document. * + * @type DOMImplementation * @readonly + */ + implementation: null, + nodeName: '#document', + nodeType: DOCUMENT_NODE, + /** + * The DocumentType node of the document. + * * @type DocumentType + * @readonly */ - doctype : null, - documentElement : null, - _inc : 1, + doctype: null, + documentElement: null, + _inc: 1, - insertBefore : function(newChild, refChild){//raises - if(newChild.nodeType == DOCUMENT_FRAGMENT_NODE){ + insertBefore: function (newChild, refChild) { + //raises + if (newChild.nodeType === DOCUMENT_FRAGMENT_NODE) { var child = newChild.firstChild; - while(child){ + while (child) { var next = child.nextSibling; - this.insertBefore(child,refChild); + this.insertBefore(child, refChild); child = next; } return newChild; @@ -1049,11 +2105,12 @@ Document.prototype = { return newChild; }, - removeChild : function(oldChild){ - if(this.documentElement == oldChild){ + removeChild: function (oldChild) { + var removed = _removeChild(this, oldChild); + if (removed === this.documentElement) { this.documentElement = null; } - return _removeChild(this,oldChild); + return removed; }, replaceChild: function (newChild, oldChild) { //raises @@ -1062,394 +2119,623 @@ Document.prototype = { if (oldChild) { this.removeChild(oldChild); } - if (isElementNode(newChild)) { - this.documentElement = newChild; - } - }, - // Introduced in DOM Level 2: - importNode : function(importedNode,deep){ - return importNode(this,importedNode,deep); - }, - // Introduced in DOM Level 2: - getElementById : function(id){ - var rtv = null; - _visitNode(this.documentElement,function(node){ - if(node.nodeType == ELEMENT_NODE){ - if(node.getAttribute('id') == id){ - rtv = node; - return true; - } - } - }) - return rtv; - }, - - /** - * The `getElementsByClassName` method of `Document` interface returns an array-like object - * of all child elements which have **all** of the given class name(s). - * - * Returns an empty list if `classeNames` is an empty string or only contains HTML white space characters. - * - * - * Warning: This is a live LiveNodeList. - * Changes in the DOM will reflect in the array as the changes occur. - * If an element selected by this array no longer qualifies for the selector, - * it will automatically be removed. Be aware of this for iteration purposes. - * - * @param {string} classNames is a string representing the class name(s) to match; multiple class names are separated by (ASCII-)whitespace - * - * @see https://developer.mozilla.org/en-US/docs/Web/API/Document/getElementsByClassName - * @see https://dom.spec.whatwg.org/#concept-getelementsbyclassname - */ - getElementsByClassName: function(classNames) { - var classNamesSet = toOrderedSet(classNames) - return new LiveNodeList(this, function(base) { - var ls = []; - if (classNamesSet.length > 0) { - _visitNode(base.documentElement, function(node) { - if(node !== base && node.nodeType === ELEMENT_NODE) { - var nodeClassNames = node.getAttribute('class') - // can be null if the attribute does not exist - if (nodeClassNames) { - // before splitting and iterating just compare them for the most common case - var matches = classNames === nodeClassNames; - if (!matches) { - var nodeClassNamesSet = toOrderedSet(nodeClassNames) - matches = classNamesSet.every(arrayIncludes(nodeClassNamesSet)) - } - if(matches) { - ls.push(node); - } - } - } - }); + if (isElementNode(newChild)) { + this.documentElement = newChild; + } + }, + // Introduced in DOM Level 2: + importNode: function (importedNode, deep) { + return importNode(this, importedNode, deep); + }, + // Introduced in DOM Level 2: + getElementById: function (id) { + var rtv = null; + _visitNode(this.documentElement, function (node) { + if (node.nodeType == ELEMENT_NODE) { + if (node.getAttribute('id') == id) { + rtv = node; + return true; + } } - return ls; }); + return rtv; }, - //document factory method: - createElement : function(tagName){ - var node = new Element(); + /** + * Creates a new `Element` that is owned by this `Document`. + * In HTML Documents `localName` is the lower cased `tagName`, + * otherwise no transformation is being applied. + * When `contentType` implies the HTML namespace, it will be set as `namespaceURI`. + * + * __This implementation differs from the specification:__ - The provided name is not checked + * against the `Name` production, + * so no related error will be thrown. + * - There is no interface `HTMLElement`, it is always an `Element`. + * - There is no support for a second argument to indicate using custom elements. + * + * @param {string} tagName + * @returns {Element} + * @see https://developer.mozilla.org/en-US/docs/Web/API/Document/createElement + * @see https://dom.spec.whatwg.org/#dom-document-createelement + * @see https://dom.spec.whatwg.org/#concept-create-element + */ + createElement: function (tagName) { + var node = new Element(PDC); node.ownerDocument = this; + if (this.type === 'html') { + tagName = tagName.toLowerCase(); + } + if (hasDefaultHTMLNamespace(this.contentType)) { + node.namespaceURI = NAMESPACE.HTML; + } node.nodeName = tagName; node.tagName = tagName; node.localName = tagName; node.childNodes = new NodeList(); - var attrs = node.attributes = new NamedNodeMap(); + var attrs = (node.attributes = new NamedNodeMap()); attrs._ownerElement = node; return node; }, - createDocumentFragment : function(){ - var node = new DocumentFragment(); + /** + * @returns {DocumentFragment} + */ + createDocumentFragment: function () { + var node = new DocumentFragment(PDC); node.ownerDocument = this; node.childNodes = new NodeList(); return node; }, - createTextNode : function(data){ - var node = new Text(); + /** + * @param {string} data + * @returns {Text} + */ + createTextNode: function (data) { + var node = new Text(PDC); node.ownerDocument = this; - node.appendData(data) + node.childNodes = new NodeList(); + node.appendData(data); return node; }, - createComment : function(data){ - var node = new Comment(); + /** + * @param {string} data + * @returns {Comment} + */ + createComment: function (data) { + var node = new Comment(PDC); node.ownerDocument = this; - node.appendData(data) + node.childNodes = new NodeList(); + node.appendData(data); return node; }, - createCDATASection : function(data){ - var node = new CDATASection(); + /** + * Returns a new CDATASection node whose data is `data`. + * + * __This implementation differs from the specification:__ - calling this method on an HTML + * document does not throw `NotSupportedError`. + * + * @param {string} data + * @returns {CDATASection} + * @throws {DOMException} + * With code `INVALID_CHARACTER_ERR` if `data` contains `"]]>"`. + * @see https://developer.mozilla.org/en-US/docs/Web/API/Document/createCDATASection + * @see https://dom.spec.whatwg.org/#dom-document-createcdatasection + */ + createCDATASection: function (data) { + if (data.indexOf(']]>') !== -1) { + throw new DOMException(DOMException.INVALID_CHARACTER_ERR, 'data contains "]]>"'); + } + var node = new CDATASection(PDC); node.ownerDocument = this; - node.appendData(data) + node.childNodes = new NodeList(); + node.appendData(data); return node; }, - createProcessingInstruction : function(target,data){ - var node = new ProcessingInstruction(); + /** + * @param {string} target + * @param {string} data + * @returns {ProcessingInstruction} + */ + createProcessingInstruction: function (target, data) { + var node = new ProcessingInstruction(PDC); node.ownerDocument = this; - node.tagName = node.nodeName = node.target = target; + node.childNodes = new NodeList(); + node.nodeName = node.target = target; node.nodeValue = node.data = data; return node; }, - createAttribute : function(name){ - var node = new Attr(); - node.ownerDocument = this; + /** + * Creates an `Attr` node that is owned by this document. + * In HTML Documents `localName` is the lower cased `name`, + * otherwise no transformation is being applied. + * + * __This implementation differs from the specification:__ - The provided name is not checked + * against the `Name` production, + * so no related error will be thrown. + * + * @param {string} name + * @returns {Attr} + * @see https://developer.mozilla.org/en-US/docs/Web/API/Document/createAttribute + * @see https://dom.spec.whatwg.org/#dom-document-createattribute + */ + createAttribute: function (name) { + if (!g.QName_exact.test(name)) { + throw new DOMException(DOMException.INVALID_CHARACTER_ERR, 'invalid character in name "' + name + '"'); + } + if (this.type === 'html') { + name = name.toLowerCase(); + } + return this._createAttribute(name); + }, + _createAttribute: function (name) { + var node = new Attr(PDC); + node.ownerDocument = this; + node.childNodes = new NodeList(); node.name = name; - node.nodeName = name; + node.nodeName = name; node.localName = name; node.specified = true; return node; }, - createEntityReference : function(name){ - var node = new EntityReference(); - node.ownerDocument = this; - node.nodeName = name; + /** + * Creates an EntityReference object. + * The current implementation does not fill the `childNodes` with those of the corresponding + * `Entity` + * + * @deprecated + * In DOM Level 4. + * @param {string} name + * The name of the entity to reference. No namespace well-formedness checks are performed. + * @returns {EntityReference} + * @throws {DOMException} + * With code `INVALID_CHARACTER_ERR` when `name` is not valid. + * @throws {DOMException} + * with code `NOT_SUPPORTED_ERR` when the document is of type `html` + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#ID-392B75AE + */ + createEntityReference: function (name) { + if (!g.Name.test(name)) { + throw new DOMException(DOMException.INVALID_CHARACTER_ERR, 'not a valid xml name "' + name + '"'); + } + if (this.type === 'html') { + throw new DOMException('document is an html document', DOMExceptionName.NotSupportedError); + } + + var node = new EntityReference(PDC); + node.ownerDocument = this; + node.childNodes = new NodeList(); + node.nodeName = name; return node; }, // Introduced in DOM Level 2: - createElementNS : function(namespaceURI,qualifiedName){ - var node = new Element(); - var pl = qualifiedName.split(':'); - var attrs = node.attributes = new NamedNodeMap(); + /** + * @param {string} namespaceURI + * @param {string} qualifiedName + * @returns {Element} + */ + createElementNS: function (namespaceURI, qualifiedName) { + var validated = validateAndExtract(namespaceURI, qualifiedName); + var node = new Element(PDC); + var attrs = (node.attributes = new NamedNodeMap()); node.childNodes = new NodeList(); node.ownerDocument = this; node.nodeName = qualifiedName; node.tagName = qualifiedName; - node.namespaceURI = namespaceURI; - if(pl.length == 2){ - node.prefix = pl[0]; - node.localName = pl[1]; - }else{ - //el.prefix = null; - node.localName = qualifiedName; - } + node.namespaceURI = validated[0]; + node.prefix = validated[1]; + node.localName = validated[2]; attrs._ownerElement = node; return node; }, // Introduced in DOM Level 2: - createAttributeNS : function(namespaceURI,qualifiedName){ - var node = new Attr(); - var pl = qualifiedName.split(':'); + /** + * @param {string} namespaceURI + * @param {string} qualifiedName + * @returns {Attr} + */ + createAttributeNS: function (namespaceURI, qualifiedName) { + var validated = validateAndExtract(namespaceURI, qualifiedName); + var node = new Attr(PDC); node.ownerDocument = this; + node.childNodes = new NodeList(); node.nodeName = qualifiedName; node.name = qualifiedName; - node.namespaceURI = namespaceURI; node.specified = true; - if(pl.length == 2){ - node.prefix = pl[0]; - node.localName = pl[1]; - }else{ - //el.prefix = null; - node.localName = qualifiedName; - } + node.namespaceURI = validated[0]; + node.prefix = validated[1]; + node.localName = validated[2]; return node; - } + }, }; -_extends(Document,Node); +_extends(Document, Node); +function Element(symbol) { + checkSymbol(symbol); -function Element() { - this._nsMap = {}; -}; + this._nsMap = Object.create(null); +} Element.prototype = { - nodeType : ELEMENT_NODE, - hasAttribute : function(name){ - return this.getAttributeNode(name)!=null; + nodeType: ELEMENT_NODE, + /** + * The attributes of this element. + * + * @type {NamedNodeMap | null} + */ + attributes: null, + getQualifiedName: function () { + return this.prefix ? this.prefix + ':' + this.localName : this.localName; + }, + _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); }, - getAttribute : function(name){ + hasAttribute: function (name) { + return !!this.getAttributeNode(name); + }, + /** + * Returns element’s first attribute whose qualified name is `name`, and `null` + * if there is no such attribute. + * + * @param {string} name + * @returns {string | null} + */ + getAttribute: function (name) { var attr = this.getAttributeNode(name); - return attr && attr.value || ''; + return attr ? attr.value : null; }, - getAttributeNode : function(name){ + getAttributeNode: function (name) { + if (this._isInHTMLDocumentAndNamespace()) { + name = name.toLowerCase(); + } return this.attributes.getNamedItem(name); }, - setAttribute : function(name, value){ - var attr = this.ownerDocument.createAttribute(name); - attr.value = attr.nodeValue = "" + value; - this.setAttributeNode(attr) + /** + * Sets the value of element’s first attribute whose qualified name is qualifiedName to value. + * + * @param {string} name + * @param {string} value + */ + setAttribute: function (name, value) { + if (this._isInHTMLDocumentAndNamespace()) { + name = name.toLowerCase(); + } + var attr = this.getAttributeNode(name); + if (attr) { + attr.value = attr.nodeValue = '' + value; + } else { + attr = this.ownerDocument._createAttribute(name); + attr.value = attr.nodeValue = '' + value; + this.setAttributeNode(attr); + } }, - removeAttribute : function(name){ - var attr = this.getAttributeNode(name) + removeAttribute: function (name) { + var attr = this.getAttributeNode(name); attr && this.removeAttributeNode(attr); }, - - //four real opeartion method - appendChild:function(newChild){ - if(newChild.nodeType === DOCUMENT_FRAGMENT_NODE){ - return this.insertBefore(newChild,null); - }else{ - return _appendSingleChild(this,newChild); - } - }, - setAttributeNode : function(newAttr){ + setAttributeNode: function (newAttr) { return this.attributes.setNamedItem(newAttr); }, - setAttributeNodeNS : function(newAttr){ + setAttributeNodeNS: function (newAttr) { return this.attributes.setNamedItemNS(newAttr); }, - removeAttributeNode : function(oldAttr){ + removeAttributeNode: function (oldAttr) { //console.log(this == oldAttr.ownerElement) return this.attributes.removeNamedItem(oldAttr.nodeName); }, //get real attribute name,and remove it by removeAttributeNode - removeAttributeNS : function(namespaceURI, localName){ + removeAttributeNS: function (namespaceURI, localName) { var old = this.getAttributeNodeNS(namespaceURI, localName); old && this.removeAttributeNode(old); }, - hasAttributeNS : function(namespaceURI, localName){ - return this.getAttributeNodeNS(namespaceURI, localName)!=null; + hasAttributeNS: function (namespaceURI, localName) { + return this.getAttributeNodeNS(namespaceURI, localName) != null; }, - getAttributeNS : function(namespaceURI, localName){ + /** + * Returns element’s attribute whose namespace is `namespaceURI` and local name is + * `localName`, + * or `null` if there is no such attribute. + * + * @param {string} namespaceURI + * @param {string} localName + * @returns {string | null} + */ + getAttributeNS: function (namespaceURI, localName) { var attr = this.getAttributeNodeNS(namespaceURI, localName); - return attr && attr.value || ''; + return attr ? attr.value : null; }, - setAttributeNS : function(namespaceURI, qualifiedName, value){ - var attr = this.ownerDocument.createAttributeNS(namespaceURI, qualifiedName); - attr.value = attr.nodeValue = "" + value; - this.setAttributeNode(attr) + /** + * Sets the value of element’s attribute whose namespace is `namespaceURI` and local name is + * `localName` to value. + * + * @param {string} namespaceURI + * @param {string} qualifiedName + * @param {string} value + * @see https://dom.spec.whatwg.org/#dom-element-setattributens + */ + setAttributeNS: function (namespaceURI, qualifiedName, value) { + var validated = validateAndExtract(namespaceURI, qualifiedName); + var localName = validated[2]; + var attr = this.getAttributeNodeNS(namespaceURI, localName); + if (attr) { + attr.value = attr.nodeValue = '' + value; + } else { + attr = this.ownerDocument.createAttributeNS(namespaceURI, qualifiedName); + attr.value = attr.nodeValue = '' + value; + this.setAttributeNode(attr); + } }, - getAttributeNodeNS : function(namespaceURI, localName){ + getAttributeNodeNS: function (namespaceURI, localName) { return this.attributes.getNamedItemNS(namespaceURI, localName); }, - getElementsByTagName : function(tagName){ - return new LiveNodeList(this,function(base){ + /** + * Returns a LiveNodeList of all child elements which have **all** of the given class name(s). + * + * Returns an empty list if `classNames` is an empty string or only contains HTML white space + * characters. + * + * Warning: This returns a live LiveNodeList. + * Changes in the DOM will reflect in the array as the changes occur. + * If an element selected by this array no longer qualifies for the selector, + * it will automatically be removed. Be aware of this for iteration purposes. + * + * @param {string} classNames + * Is a string representing the class name(s) to match; multiple class names are separated by + * (ASCII-)whitespace. + * @see https://developer.mozilla.org/en-US/docs/Web/API/Element/getElementsByClassName + * @see https://developer.mozilla.org/en-US/docs/Web/API/Document/getElementsByClassName + * @see https://dom.spec.whatwg.org/#concept-getelementsbyclassname + */ + getElementsByClassName: function (classNames) { + var classNamesSet = toOrderedSet(classNames); + return new LiveNodeList(this, function (base) { + var ls = []; + if (classNamesSet.length > 0) { + _visitNode(base, function (node) { + if (node !== base && node.nodeType === ELEMENT_NODE) { + var nodeClassNames = node.getAttribute('class'); + // can be null if the attribute does not exist + if (nodeClassNames) { + // before splitting and iterating just compare them for the most common case + var matches = classNames === nodeClassNames; + if (!matches) { + var nodeClassNamesSet = toOrderedSet(nodeClassNames); + matches = classNamesSet.every(arrayIncludes(nodeClassNamesSet)); + } + if (matches) { + ls.push(node); + } + } + } + }); + } + return ls; + }); + }, + + /** + * Returns a LiveNodeList of elements with the given qualifiedName. + * Searching for all descendants can be done by passing `*` as `qualifiedName`. + * + * All descendants of the specified element are searched, but not the element itself. + * The returned list is live, which means it updates itself with the DOM tree automatically. + * Therefore, there is no need to call `Element.getElementsByTagName()` + * with the same element and arguments repeatedly if the DOM changes in between calls. + * + * When called on an HTML element in an HTML document, + * `getElementsByTagName` lower-cases the argument before searching for it. + * This is undesirable when trying to match camel-cased SVG elements (such as + * ``) in an HTML document. + * Instead, use `Element.getElementsByTagNameNS()`, + * which preserves the capitalization of the tag name. + * + * `Element.getElementsByTagName` is similar to `Document.getElementsByTagName()`, + * except that it only searches for elements that are descendants of the specified element. + * + * @param {string} qualifiedName + * @returns {LiveNodeList} + * @see https://developer.mozilla.org/en-US/docs/Web/API/Element/getElementsByTagName + * @see https://dom.spec.whatwg.org/#concept-getelementsbytagname + */ + getElementsByTagName: function (qualifiedName) { + var isHTMLDocument = (this.nodeType === DOCUMENT_NODE ? this : this.ownerDocument).type === 'html'; + var lowerQualifiedName = qualifiedName.toLowerCase(); + return new LiveNodeList(this, function (base) { var ls = []; - _visitNode(base,function(node){ - if(node !== base && node.nodeType == ELEMENT_NODE && (tagName === '*' || node.tagName == tagName)){ + _visitNode(base, function (node) { + if (node === base || node.nodeType !== ELEMENT_NODE) { + return; + } + if (qualifiedName === '*') { ls.push(node); + } else { + var nodeQualifiedName = node.getQualifiedName(); + var matchingQName = isHTMLDocument && node.namespaceURI === NAMESPACE.HTML ? lowerQualifiedName : qualifiedName; + if (nodeQualifiedName === matchingQName) { + ls.push(node); + } } }); return ls; }); }, - getElementsByTagNameNS : function(namespaceURI, localName){ - return new LiveNodeList(this,function(base){ + getElementsByTagNameNS: function (namespaceURI, localName) { + return new LiveNodeList(this, function (base) { var ls = []; - _visitNode(base,function(node){ - if(node !== base && node.nodeType === ELEMENT_NODE && (namespaceURI === '*' || node.namespaceURI === namespaceURI) && (localName === '*' || node.localName == localName)){ + _visitNode(base, function (node) { + if ( + node !== base && + node.nodeType === ELEMENT_NODE && + (namespaceURI === '*' || node.namespaceURI === namespaceURI) && + (localName === '*' || node.localName == localName) + ) { ls.push(node); } }); return ls; - }); - } + }, }; +Document.prototype.getElementsByClassName = Element.prototype.getElementsByClassName; Document.prototype.getElementsByTagName = Element.prototype.getElementsByTagName; Document.prototype.getElementsByTagNameNS = Element.prototype.getElementsByTagNameNS; +_extends(Element, Node); +function Attr(symbol) { + checkSymbol(symbol); -_extends(Element,Node); -function Attr() { -}; + this.namespaceURI = null; + this.prefix = null; + this.ownerElement = null; +} Attr.prototype.nodeType = ATTRIBUTE_NODE; -_extends(Attr,Node); +_extends(Attr, Node); - -function CharacterData() { -}; +function CharacterData(symbol) { + checkSymbol(symbol); +} CharacterData.prototype = { - data : '', - substringData : function(offset, count) { - return this.data.substring(offset, offset+count); + data: '', + substringData: function (offset, count) { + return this.data.substring(offset, offset + count); }, - appendData: function(text) { - text = this.data+text; + appendData: function (text) { + text = this.data + text; this.nodeValue = this.data = text; this.length = text.length; }, - insertData: function(offset,text) { - this.replaceData(offset,0,text); - - }, - appendChild:function(newChild){ - throw new Error(ExceptionMessage[HIERARCHY_REQUEST_ERR]) + insertData: function (offset, text) { + this.replaceData(offset, 0, text); }, - deleteData: function(offset, count) { - this.replaceData(offset,count,""); + deleteData: function (offset, count) { + this.replaceData(offset, count, ''); }, - replaceData: function(offset, count, text) { - var start = this.data.substring(0,offset); - var end = this.data.substring(offset+count); + replaceData: function (offset, count, text) { + var start = this.data.substring(0, offset); + var end = this.data.substring(offset + count); text = start + text + end; this.nodeValue = this.data = text; this.length = text.length; - } -} -_extends(CharacterData,Node); -function Text() { + }, }; +_extends(CharacterData, Node); +function Text(symbol) { + checkSymbol(symbol); +} Text.prototype = { - nodeName : "#text", - nodeType : TEXT_NODE, - splitText : function(offset) { + nodeName: '#text', + nodeType: TEXT_NODE, + splitText: function (offset) { var text = this.data; var newText = text.substring(offset); text = text.substring(0, offset); this.data = this.nodeValue = text; this.length = text.length; var newNode = this.ownerDocument.createTextNode(newText); - if(this.parentNode){ + if (this.parentNode) { this.parentNode.insertBefore(newNode, this.nextSibling); } return newNode; - } -} -_extends(Text,CharacterData); -function Comment() { + }, }; -Comment.prototype = { - nodeName : "#comment", - nodeType : COMMENT_NODE +_extends(Text, CharacterData); +function Comment(symbol) { + checkSymbol(symbol); } -_extends(Comment,CharacterData); - -function CDATASection() { +Comment.prototype = { + nodeName: '#comment', + nodeType: COMMENT_NODE, }; -CDATASection.prototype = { - nodeName : "#cdata-section", - nodeType : CDATA_SECTION_NODE -} -_extends(CDATASection,CharacterData); - +_extends(Comment, CharacterData); -function DocumentType() { +function CDATASection(symbol) { + checkSymbol(symbol); +} +CDATASection.prototype = { + nodeName: '#cdata-section', + nodeType: CDATA_SECTION_NODE, }; +_extends(CDATASection, Text); + +function DocumentType(symbol) { + checkSymbol(symbol); +} DocumentType.prototype.nodeType = DOCUMENT_TYPE_NODE; -_extends(DocumentType,Node); +_extends(DocumentType, Node); -function Notation() { -}; +function Notation(symbol) { + checkSymbol(symbol); +} Notation.prototype.nodeType = NOTATION_NODE; -_extends(Notation,Node); +_extends(Notation, Node); -function Entity() { -}; +function Entity(symbol) { + checkSymbol(symbol); +} Entity.prototype.nodeType = ENTITY_NODE; -_extends(Entity,Node); +_extends(Entity, Node); -function EntityReference() { -}; +function EntityReference(symbol) { + checkSymbol(symbol); +} EntityReference.prototype.nodeType = ENTITY_REFERENCE_NODE; -_extends(EntityReference,Node); - -function DocumentFragment() { -}; -DocumentFragment.prototype.nodeName = "#document-fragment"; -DocumentFragment.prototype.nodeType = DOCUMENT_FRAGMENT_NODE; -_extends(DocumentFragment,Node); +_extends(EntityReference, Node); +function DocumentFragment(symbol) { + checkSymbol(symbol); +} +DocumentFragment.prototype.nodeName = '#document-fragment'; +DocumentFragment.prototype.nodeType = DOCUMENT_FRAGMENT_NODE; +_extends(DocumentFragment, Node); -function ProcessingInstruction() { +function ProcessingInstruction(symbol) { + checkSymbol(symbol); } ProcessingInstruction.prototype.nodeType = PROCESSING_INSTRUCTION_NODE; -_extends(ProcessingInstruction,Node); -function XMLSerializer(){} -XMLSerializer.prototype.serializeToString = function(node,isHtml,nodeFilter){ - return nodeSerializeToString.call(node,isHtml,nodeFilter); -} +_extends(ProcessingInstruction, CharacterData); +function XMLSerializer() {} +/** + * Returns the result of serializing `node` to XML. + * + * __This implementation differs from the specification:__ - CDATASection nodes whose data + * contains `]]>` are serialized by splitting the section at each `]]>` occurrence (following + * W3C DOM Level 3 Core `split-cdata-sections` + * default behaviour). A configurable option is not yet implemented. + * + * @param {Node} node + * @param {function} [nodeFilter] + * @returns {string} + * @see https://html.spec.whatwg.org/#dom-xmlserializer-serializetostring + */ +XMLSerializer.prototype.serializeToString = function (node, nodeFilter) { + return nodeSerializeToString.call(node, nodeFilter); +}; Node.prototype.toString = nodeSerializeToString; -function nodeSerializeToString(isHtml,nodeFilter){ +function nodeSerializeToString(nodeFilter) { var buf = []; - var refNode = this.nodeType == 9 && this.documentElement || this; + var refNode = (this.nodeType === DOCUMENT_NODE && this.documentElement) || this; var prefix = refNode.prefix; var uri = refNode.namespaceURI; - if(uri && prefix == null){ - //console.log(prefix) + if (uri && prefix == null) { var prefix = refNode.lookupPrefix(uri); - if(prefix == null){ - //isHTML = true; - var visibleNamespaces=[ - {namespace:uri,prefix:null} - //{namespace:uri,prefix:''} - ] + if (prefix == null) { + var visibleNamespaces = [ + { namespace: uri, prefix: null }, + //{namespace:uri,prefix:''} + ]; } } - serializeToString(this,buf,isHtml,nodeFilter,visibleNamespaces); - //console.log('###',this.nodeType,uri,prefix,buf.join('')) + serializeToString(this, buf, nodeFilter, visibleNamespaces); return buf.join(''); } @@ -1466,11 +2752,11 @@ function needNamespaceDefine(node, isHTML, visibleNamespaces) { if (!uri) { return false; } - if (prefix === "xml" && uri === NAMESPACE.XML || uri === NAMESPACE.XMLNS) { + if ((prefix === 'xml' && uri === NAMESPACE.XML) || uri === NAMESPACE.XMLNS) { return false; } - var i = visibleNamespaces.length + var i = visibleNamespaces.length; while (i--) { var ns = visibleNamespaces[i]; // get namespace prefix @@ -1481,366 +2767,428 @@ function needNamespaceDefine(node, isHTML, visibleNamespaces) { return true; } /** - * Well-formed constraint: No < in Attribute Values + * Literal whitespace other than space that appear in attribute values are serialized as + * their entity references, so they will be preserved. + * (In contrast to whitespace literals in the input which are normalized to spaces). + * + * Well-formed constraint: No < in Attribute Values: * > The replacement text of any entity referred to directly or indirectly * > in an attribute value must not contain a <. + * * @see https://www.w3.org/TR/xml11/#CleanAttrVals * @see https://www.w3.org/TR/xml11/#NT-AttValue - * - * Literal whitespace other than space that appear in attribute values - * are serialized as their entity references, so they will be preserved. - * (In contrast to whitespace literals in the input which are normalized to spaces) * @see https://www.w3.org/TR/xml11/#AVNormalize * @see https://w3c.github.io/DOM-Parsing/#serializing-an-element-s-attributes + * @prettierignore */ function addSerializedAttribute(buf, qualifiedName, value) { - buf.push(' ', qualifiedName, '="', value.replace(/[<>&"\t\n\r]/g, _xmlEncoder), '"') + buf.push(' ', qualifiedName, '="', value.replace(/[<>&"\t\n\r]/g, _xmlEncoder), '"'); } -function serializeToString(node,buf,isHTML,nodeFilter,visibleNamespaces){ +function serializeToString(node, buf, nodeFilter, visibleNamespaces) { if (!visibleNamespaces) { visibleNamespaces = []; } + var doc = node.nodeType === DOCUMENT_NODE ? node : node.ownerDocument; + var isHTML = doc.type === 'html'; - if(nodeFilter){ + if (nodeFilter) { node = nodeFilter(node); - if(node){ - if(typeof node == 'string'){ + if (node) { + if (typeof node == 'string') { buf.push(node); return; } - }else{ + } else { return; } //buf.sort.apply(attrs, attributeSorter); } - switch(node.nodeType){ - case ELEMENT_NODE: - var attrs = node.attributes; - var len = attrs.length; - var child = node.firstChild; - var nodeName = node.tagName; - - isHTML = NAMESPACE.isHTML(node.namespaceURI) || isHTML - - var prefixedNodeName = nodeName - if (!isHTML && !node.prefix && node.namespaceURI) { - var defaultNS - // lookup current default ns from `xmlns` attribute - for (var ai = 0; ai < attrs.length; ai++) { - if (attrs.item(ai).name === 'xmlns') { - defaultNS = attrs.item(ai).value - break + switch (node.nodeType) { + case ELEMENT_NODE: + var attrs = node.attributes; + var len = attrs.length; + var child = node.firstChild; + var nodeName = node.tagName; + + var prefixedNodeName = nodeName; + if (!isHTML && !node.prefix && node.namespaceURI) { + var defaultNS; + // lookup current default ns from `xmlns` attribute + for (var ai = 0; ai < attrs.length; ai++) { + if (attrs.item(ai).name === 'xmlns') { + defaultNS = attrs.item(ai).value; + break; + } } - } - if (!defaultNS) { - // lookup current default ns in visibleNamespaces - for (var nsi = visibleNamespaces.length - 1; nsi >= 0; nsi--) { - var namespace = visibleNamespaces[nsi] - if (namespace.prefix === '' && namespace.namespace === node.namespaceURI) { - defaultNS = namespace.namespace - break + if (!defaultNS) { + // lookup current default ns in visibleNamespaces + for (var nsi = visibleNamespaces.length - 1; nsi >= 0; nsi--) { + var namespace = visibleNamespaces[nsi]; + if (namespace.prefix === '' && namespace.namespace === node.namespaceURI) { + defaultNS = namespace.namespace; + break; + } } } - } - if (defaultNS !== node.namespaceURI) { - for (var nsi = visibleNamespaces.length - 1; nsi >= 0; nsi--) { - var namespace = visibleNamespaces[nsi] - if (namespace.namespace === node.namespaceURI) { - if (namespace.prefix) { - prefixedNodeName = namespace.prefix + ':' + nodeName + if (defaultNS !== node.namespaceURI) { + for (var nsi = visibleNamespaces.length - 1; nsi >= 0; nsi--) { + var namespace = visibleNamespaces[nsi]; + if (namespace.namespace === node.namespaceURI) { + if (namespace.prefix) { + prefixedNodeName = namespace.prefix + ':' + nodeName; + } + break; } - break } } } - } - buf.push('<', prefixedNodeName); - - for(var i=0;i'); - //if is cdata child node - if(isHTML && /^script$/i.test(nodeName)){ - while(child){ - if(child.data){ - buf.push(child.data); - }else{ - serializeToString(child, buf, isHTML, nodeFilter, visibleNamespaces.slice()); + // add namespace for current node + if (nodeName === prefixedNodeName && needNamespaceDefine(node, isHTML, visibleNamespaces)) { + var prefix = node.prefix || ''; + var uri = node.namespaceURI; + addSerializedAttribute(buf, prefix ? 'xmlns:' + prefix : 'xmlns', uri); + visibleNamespaces.push({ prefix: prefix, namespace: uri }); + } + // in XML elements can be closed when they have no children + var canCloseTag = !child; + if (canCloseTag && (isHTML || node.namespaceURI === NAMESPACE.HTML)) { + // in HTML (doc or ns) only void elements can be closed right away + canCloseTag = isHTMLVoidElement(nodeName); + } + if (canCloseTag) { + buf.push('/>'); + } else { + buf.push('>'); + //if is cdata child node + if (isHTML && isHTMLRawTextElement(nodeName)) { + while (child) { + if (child.data) { + buf.push(child.data); + } else { + serializeToString(child, buf, nodeFilter, visibleNamespaces.slice()); + } + child = child.nextSibling; + } + } else { + while (child) { + serializeToString(child, buf, nodeFilter, visibleNamespaces.slice()); + child = child.nextSibling; } - child = child.nextSibling; } - }else - { - while(child){ - serializeToString(child, buf, isHTML, nodeFilter, visibleNamespaces.slice()); - child = child.nextSibling; + buf.push(''); + } + // remove added visible namespaces + //visibleNamespaces.length = startVisibleNamespaces; + return; + case DOCUMENT_NODE: + case DOCUMENT_FRAGMENT_NODE: + var child = node.firstChild; + while (child) { + serializeToString(child, buf, nodeFilter, visibleNamespaces.slice()); + child = child.nextSibling; + } + return; + case ATTRIBUTE_NODE: + return addSerializedAttribute(buf, node.name, node.value); + case TEXT_NODE: + /* + * The ampersand character (&) and the left angle bracket (<) must not appear in their literal form, + * except when used as markup delimiters, or within a comment, a processing instruction, + * or a CDATA section. + * If they are needed elsewhere, they must be escaped using either numeric character + * references or the strings `&` and `<` respectively. + * The right angle bracket (>) may be represented using the string " > ", + * and must, for compatibility, be escaped using either `>`, + * or a character reference when it appears in the string `]]>` in content, + * when that string is not marking the end of a CDATA section. + * + * In the content of elements, character data is any string of characters which does not + * contain the start-delimiter of any markup and does not include the CDATA-section-close + * delimiter, `]]>`. + * + * @see https://www.w3.org/TR/xml/#NT-CharData + * @see https://w3c.github.io/DOM-Parsing/#xml-serializing-a-text-node + */ + return buf.push(node.data.replace(/[<&>]/g, _xmlEncoder)); + case CDATA_SECTION_NODE: + return buf.push(g.CDATA_START, node.data.replace(/]]>/g, ']]]]>'), g.CDATA_END); + case COMMENT_NODE: + return buf.push(g.COMMENT_START, node.data, g.COMMENT_END); + case DOCUMENT_TYPE_NODE: + var pubid = node.publicId; + var sysid = node.systemId; + buf.push(g.DOCTYPE_DECL_START, ' ', node.name); + if (pubid) { + buf.push(' ', g.PUBLIC, ' ', pubid); + if (sysid && sysid !== '.') { + buf.push(' ', sysid); } + } else if (sysid && sysid !== '.') { + buf.push(' ', g.SYSTEM, ' ', sysid); } - buf.push(''); - }else{ - buf.push('/>'); - } - // remove added visible namespaces - //visibleNamespaces.length = startVisibleNamespaces; - return; - case DOCUMENT_NODE: - case DOCUMENT_FRAGMENT_NODE: - var child = node.firstChild; - while(child){ - serializeToString(child, buf, isHTML, nodeFilter, visibleNamespaces.slice()); - child = child.nextSibling; - } - return; - case ATTRIBUTE_NODE: - return addSerializedAttribute(buf, node.name, node.value); - case TEXT_NODE: - /** - * The ampersand character (&) and the left angle bracket (<) must not appear in their literal form, - * except when used as markup delimiters, or within a comment, a processing instruction, or a CDATA section. - * If they are needed elsewhere, they must be escaped using either numeric character references or the strings - * `&` and `<` respectively. - * The right angle bracket (>) may be represented using the string " > ", and must, for compatibility, - * be escaped using either `>` or a character reference when it appears in the string `]]>` in content, - * when that string is not marking the end of a CDATA section. - * - * In the content of elements, character data is any string of characters - * which does not contain the start-delimiter of any markup - * and does not include the CDATA-section-close delimiter, `]]>`. - * - * @see https://www.w3.org/TR/xml/#NT-CharData - * @see https://w3c.github.io/DOM-Parsing/#xml-serializing-a-text-node - */ - return buf.push(node.data - .replace(/[<&>]/g,_xmlEncoder) - ); - case CDATA_SECTION_NODE: - return buf.push( ''); - case COMMENT_NODE: - return buf.push( ""); - case DOCUMENT_TYPE_NODE: - var pubid = node.publicId; - var sysid = node.systemId; - buf.push(''); - }else if(sysid && sysid!='.'){ - buf.push(' SYSTEM ', sysid, '>'); - }else{ - var sub = node.internalSubset; - if(sub){ - buf.push(" [",sub,"]"); - } - buf.push(">"); - } - return; - case PROCESSING_INSTRUCTION_NODE: - return buf.push( ""); - case ENTITY_REFERENCE_NODE: - return buf.push( '&',node.nodeName,';'); - //case ENTITY_NODE: - //case NOTATION_NODE: - default: - buf.push('??',node.nodeName); + return; + case PROCESSING_INSTRUCTION_NODE: + return buf.push(''); + case ENTITY_REFERENCE_NODE: + return buf.push('&', node.nodeName, ';'); + //case ENTITY_NODE: + //case NOTATION_NODE: + default: + buf.push('??', node.nodeName); } } -function importNode(doc,node,deep){ +function importNode(doc, node, deep) { var node2; switch (node.nodeType) { - case ELEMENT_NODE: - node2 = node.cloneNode(false); - node2.ownerDocument = doc; + case ELEMENT_NODE: + node2 = node.cloneNode(false); + node2.ownerDocument = doc; //var attrs = node2.attributes; //var len = attrs.length; //for(var i=0;i= 1 && value <= 25; +} +function endsWithError(value) { + return typeof value === 'string' && value.substring(value.length - DOMExceptionName.Error.length) === DOMExceptionName.Error; +} +/** + * DOM operations only raise exceptions in "exceptional" circumstances, i.e., when an operation + * is impossible to perform (either for logical reasons, because data is lost, or because the + * implementation has become unstable). In general, DOM methods return specific error values in + * ordinary processing situations, such as out-of-bound errors when using NodeList. + * + * Implementations should raise other exceptions under other circumstances. For example, + * implementations should raise an implementation-dependent exception if a null argument is + * passed when null was not expected. + * + * This implementation supports the following usages: + * 1. according to the living standard (both arguments are optional): + * ``` + * new DOMException("message (can be empty)", DOMExceptionNames.HierarchyRequestError) + * ``` + * 2. according to previous xmldom implementation (only the first argument is required): + * ``` + * new DOMException(DOMException.HIERARCHY_REQUEST_ERR, "optional message") + * ``` + * both result in the proper name being set. + * + * @class DOMException + * @param {number | string} messageOrCode + * The reason why an operation is not acceptable. + * If it is a number, it is used to determine the `name`, see + * {@link https://www.w3.org/TR/DOM-Level-3-Core/core.html#ID-258A00AF ExceptionCode} + * @param {string | keyof typeof DOMExceptionName | Error} [nameOrMessage] + * The `name` to use for the error. + * If `messageOrCode` is a number, this arguments is used as the `message` instead. + * @augments Error + * @see https://webidl.spec.whatwg.org/#idl-DOMException + * @see https://webidl.spec.whatwg.org/#dfn-error-names-table + * @see https://www.w3.org/TR/DOM-Level-3-Core/core.html#ID-17189187 + * @see http://www.w3.org/TR/2000/REC-DOM-Level-2-Core-20001113/ecma-script-binding.html + * @see http://www.w3.org/TR/REC-DOM-Level-1/ecma-script-language-binding.html + */ +function DOMException(messageOrCode, nameOrMessage) { + // support old way of passing arguments: first argument is a valid number + if (isValidDomExceptionCode(messageOrCode)) { + this.name = DOMExceptionNames[messageOrCode]; + this.message = nameOrMessage || ''; + } else { + this.message = messageOrCode; + this.name = endsWithError(nameOrMessage) ? nameOrMessage : DOMExceptionName.Error; + } + if (Error.captureStackTrace) Error.captureStackTrace(this, DOMException); +} +extendError(DOMException, true); +Object.defineProperties(DOMException.prototype, { + code: { + enumerable: true, + get: function () { + var code = DOMExceptionNames.indexOf(this.name); + if (isValidDomExceptionCode(code)) return code; + return 0; + }, + }, +}); + +var ExceptionCode = { + INDEX_SIZE_ERR: 1, + DOMSTRING_SIZE_ERR: 2, + HIERARCHY_REQUEST_ERR: 3, + WRONG_DOCUMENT_ERR: 4, + INVALID_CHARACTER_ERR: 5, + NO_DATA_ALLOWED_ERR: 6, + NO_MODIFICATION_ALLOWED_ERR: 7, + NOT_FOUND_ERR: 8, + NOT_SUPPORTED_ERR: 9, + INUSE_ATTRIBUTE_ERR: 10, + INVALID_STATE_ERR: 11, + SYNTAX_ERR: 12, + INVALID_MODIFICATION_ERR: 13, + NAMESPACE_ERR: 14, + INVALID_ACCESS_ERR: 15, + VALIDATION_ERR: 16, + TYPE_MISMATCH_ERR: 17, + SECURITY_ERR: 18, + NETWORK_ERR: 19, + ABORT_ERR: 20, + URL_MISMATCH_ERR: 21, + QUOTA_EXCEEDED_ERR: 22, + TIMEOUT_ERR: 23, + INVALID_NODE_TYPE_ERR: 24, + DATA_CLONE_ERR: 25, +}; + +var entries = Object.entries(ExceptionCode); +for (var i = 0; i < entries.length; i++) { + var key = entries[i][0]; + DOMException[key] = entries[i][1]; +} + +/** + * Creates an error that will not be caught by XMLReader aka the SAX parser. + * + * @class + * @param {string} message + * @param {any} [locator] + */ +function ParseError(message, locator) { + this.message = message; + this.locator = locator; + if (Error.captureStackTrace) Error.captureStackTrace(this, ParseError); +} +extendError(ParseError); + +export {DOMException, DOMExceptionName, ExceptionCode, ParseError }; + +/* +exports.DOMException = DOMException; +exports.DOMExceptionName = DOMExceptionName; +exports.ExceptionCode = ExceptionCode; +exports.ParseError = ParseError; +*/ diff --git a/lib/xmldom/grammar.js b/lib/xmldom/grammar.js new file mode 100644 index 0000000..f09e00c --- /dev/null +++ b/lib/xmldom/grammar.js @@ -0,0 +1,537 @@ +'use strict'; + +/** + * Detects relevant unicode support for regular expressions in the runtime. + * Should the runtime not accepts the flag `u` or unicode ranges, + * character classes without unicode handling will be used. + * + * @param {typeof RegExp} [RegExpImpl=RegExp] + * For testing: the RegExp class. + * @returns {boolean} + * @see https://node.green/#ES2015-syntax-RegExp--y--and--u--flags + */ +function detectUnicodeSupport(RegExpImpl) { + try { + if (typeof RegExpImpl !== 'function') { + RegExpImpl = RegExp; + } + // eslint-disable-next-line es5/no-unicode-regex,es5/no-unicode-code-point-escape + var match = new RegExpImpl('\u{1d306}', 'u').exec('𝌆'); + return !!match && match[0].length === 2; + } catch (error) {} + return false; +} +var UNICODE_SUPPORT = detectUnicodeSupport(); + +/** + * Removes `[`, `]` and any trailing quantifiers from the source of a RegExp. + * + * @param {RegExp} regexp + */ +function chars(regexp) { + if (regexp.source[0] !== '[') { + throw new Error(regexp + ' can not be used with chars'); + } + return regexp.source.slice(1, regexp.source.lastIndexOf(']')); +} + +/** + * Creates a new character list regular expression, + * by removing `search` from the source of `regexp`. + * + * @param {RegExp} regexp + * @param {string} search + * The character(s) to remove. + * @returns {RegExp} + */ +function chars_without(regexp, search) { + if (regexp.source[0] !== '[') { + throw new Error('/' + regexp.source + '/ can not be used with chars_without'); + } + if (!search || typeof search !== 'string') { + throw new Error(JSON.stringify(search) + ' is not a valid search'); + } + if (regexp.source.indexOf(search) === -1) { + throw new Error('"' + search + '" is not is /' + regexp.source + '/'); + } + if (search === '-' && regexp.source.indexOf(search) !== 1) { + throw new Error('"' + search + '" is not at the first postion of /' + regexp.source + '/'); + } + return new RegExp(regexp.source.replace(search, ''), UNICODE_SUPPORT ? 'u' : ''); +} + +/** + * Combines and Regular expressions correctly by using `RegExp.source`. + * + * @param {...(RegExp | string)[]} args + * @returns {RegExp} + */ +function reg(args) { + var self = this; + return new RegExp( + Array.prototype.slice + .call(arguments) + .map(function (part) { + var isStr = typeof part === 'string'; + if (isStr && self === undefined && part === '|') { + throw new Error('use regg instead of reg to wrap expressions with `|`!'); + } + return isStr ? part : part.source; + }) + .join(''), + UNICODE_SUPPORT ? 'mu' : 'm' + ); +} + +/** + * Like `reg` but wraps the expression in `(?:`,`)` to create a non tracking group. + * + * @param {...(RegExp | string)[]} args + * @returns {RegExp} + */ +function regg(args) { + if (arguments.length === 0) { + throw new Error('no parameters provided'); + } + return reg.apply(regg, ['(?:'].concat(Array.prototype.slice.call(arguments), [')'])); +} + +// /** +// * Append ^ to the beginning of the expression. +// * @param {...(RegExp | string)[]} args +// * @returns {RegExp} +// */ +// function reg_start(args) { +// if (arguments.length === 0) { +// throw new Error('no parameters provided'); +// } +// return reg.apply(reg_start, ['^'].concat(Array.prototype.slice.call(arguments))); +// } + +// https://www.w3.org/TR/xml/#document +// `[1] document ::= prolog element Misc*` +// https://www.w3.org/TR/xml11/#NT-document +// `[1] document ::= ( prolog element Misc* ) - ( Char* RestrictedChar Char* )` + +/** + * A character usually appearing in wrongly converted strings. + * + * @type {string} + * @see https://en.wikipedia.org/wiki/Specials_(Unicode_block)#Replacement_character + * @see https://nodejs.dev/en/api/v18/buffer/#buffers-and-character-encodings + * @see https://www.unicode.org/faq/utf_bom.html#BOM + * @readonly + */ +var UNICODE_REPLACEMENT_CHARACTER = '\uFFFD'; +// https://www.w3.org/TR/xml/#NT-Char +// any Unicode character, excluding the surrogate blocks, FFFE, and FFFF. +// `[2] Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]` +// https://www.w3.org/TR/xml11/#NT-Char +// `[2] Char ::= [#x1-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]` +// https://www.w3.org/TR/xml11/#NT-RestrictedChar +// `[2a] RestrictedChar ::= [#x1-#x8] | [#xB-#xC] | [#xE-#x1F] | [#x7F-#x84] | [#x86-#x9F]` +// https://www.w3.org/TR/xml11/#charsets +var Char = /[-\x09\x0A\x0D\x20-\x2C\x2E-\uD7FF\uE000-\uFFFD]/; // without \u10000-\uEFFFF +if (UNICODE_SUPPORT) { + // eslint-disable-next-line es5/no-unicode-code-point-escape + Char = reg('[', chars(Char), '\\u{10000}-\\u{10FFFF}', ']'); +} + +var _SChar = /[\x20\x09\x0D\x0A]/; +var SChar_s = chars(_SChar); +// https://www.w3.org/TR/xml11/#NT-S +// `[3] S ::= (#x20 | #x9 | #xD | #xA)+` +var S = reg(_SChar, '+'); +// optional whitespace described as `S?` in the grammar, +// simplified to 0-n occurrences of the character class +// instead of 0-1 occurrences of a non-capturing group around S +var S_OPT = reg(_SChar, '*'); + +// https://www.w3.org/TR/xml11/#NT-NameStartChar +// `[4] NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] | [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF]` +var NameStartChar = + /[:_a-zA-Z\xC0-\xD6\xD8-\xF6\xF8-\u02FF\u0370-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]/; // without \u10000-\uEFFFF +if (UNICODE_SUPPORT) { + // eslint-disable-next-line es5/no-unicode-code-point-escape + NameStartChar = reg('[', chars(NameStartChar), '\\u{10000}-\\u{10FFFF}', ']'); +} +var NameStartChar_s = chars(NameStartChar); + +// https://www.w3.org/TR/xml11/#NT-NameChar +// `[4a] NameChar ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040]` +var NameChar = reg('[', NameStartChar_s, chars(/[-.0-9\xB7]/), chars(/[\u0300-\u036F\u203F-\u2040]/), ']'); +// https://www.w3.org/TR/xml11/#NT-Name +// `[5] Name ::= NameStartChar (NameChar)*` +var Name = reg(NameStartChar, NameChar, '*'); +/* +https://www.w3.org/TR/xml11/#NT-Names +`[6] Names ::= Name (#x20 Name)*` +*/ + +// https://www.w3.org/TR/xml11/#NT-Nmtoken +// `[7] Nmtoken ::= (NameChar)+` +var Nmtoken = reg(NameChar, '+'); +/* +https://www.w3.org/TR/xml11/#NT-Nmtokens +`[8] Nmtokens ::= Nmtoken (#x20 Nmtoken)*` +var Nmtokens = reg(Nmtoken, regg(/\x20/, Nmtoken), '*'); +*/ + +// https://www.w3.org/TR/xml11/#NT-EntityRef +// `[68] EntityRef ::= '&' Name ';'` [WFC: Entity Declared] [VC: Entity Declared] [WFC: Parsed Entity] [WFC: No Recursion] +var EntityRef = reg('&', Name, ';'); +// https://www.w3.org/TR/xml11/#NT-CharRef +// `[66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'` [WFC: Legal Character] +var CharRef = regg(/&#[0-9]+;|&#x[0-9a-fA-F]+;/); + +/* +https://www.w3.org/TR/xml11/#NT-Reference +- `[67] Reference ::= EntityRef | CharRef` +- `[66] CharRef ::= '&#' [0-9]+ ';' | '&#x' [0-9a-fA-F]+ ';'` [WFC: Legal Character] +- `[68] EntityRef ::= '&' Name ';'` [WFC: Entity Declared] [VC: Entity Declared] [WFC: Parsed Entity] [WFC: No Recursion] +*/ +var Reference = regg(EntityRef, '|', CharRef); + +// https://www.w3.org/TR/xml11/#NT-PEReference +// `[69] PEReference ::= '%' Name ';'` +// [VC: Entity Declared] [WFC: No Recursion] [WFC: In DTD] +var PEReference = reg('%', Name, ';'); + +// https://www.w3.org/TR/xml11/#NT-EntityValue +// `[9] EntityValue ::= '"' ([^%&"] | PEReference | Reference)* '"' | "'" ([^%&'] | PEReference | Reference)* "'"` +var EntityValue = regg( + reg('"', regg(/[^%&"]/, '|', PEReference, '|', Reference), '*', '"'), + '|', + reg("'", regg(/[^%&']/, '|', PEReference, '|', Reference), '*', "'") +); + +// https://www.w3.org/TR/xml11/#NT-AttValue +// `[10] AttValue ::= '"' ([^<&"] | Reference)* '"' | "'" ([^<&'] | Reference)* "'"` +var AttValue = regg('"', regg(/[^<&"]/, '|', Reference), '*', '"', '|', "'", regg(/[^<&']/, '|', Reference), '*', "'"); + +// https://www.w3.org/TR/xml-names/#ns-decl +// https://www.w3.org/TR/xml-names/#ns-qualnames +// NameStartChar without ":" +var NCNameStartChar = chars_without(NameStartChar, ':'); +// https://www.w3.org/TR/xml-names/#orphans +// `[5] NCNameChar ::= NameChar - ':'` +// An XML NameChar, minus the ":" +var NCNameChar = chars_without(NameChar, ':'); +// https://www.w3.org/TR/xml-names/#NT-NCName +// `[4] NCName ::= Name - (Char* ':' Char*)` +// An XML Name, minus the ":" +var NCName = reg(NCNameStartChar, NCNameChar, '*'); + +/** +https://www.w3.org/TR/xml-names/#ns-qualnames + +``` +[7] QName ::= PrefixedName | UnprefixedName + === (NCName ':' NCName) | NCName + === NCName (':' NCName)? +[8] PrefixedName ::= Prefix ':' LocalPart + === NCName ':' NCName +[9] UnprefixedName ::= LocalPart + === NCName +[10] Prefix ::= NCName +[11] LocalPart ::= NCName +``` +*/ +var QName = reg(NCName, regg(':', NCName), '?'); +var QName_exact = reg('^', QName, '$'); +var QName_group = reg('(', QName, ')'); + +// https://www.w3.org/TR/xml11/#NT-SystemLiteral +// `[11] SystemLiteral ::= ('"' [^"]* '"') | ("'" [^']* "'")` +var SystemLiteral = regg(/"[^"]*"|'[^']*'/); + +/* + https://www.w3.org/TR/xml11/#NT-PI + ``` + [17] PITarget ::= Name - (('X' | 'x') ('M' | 'm') ('L' | 'l')) + [16] PI ::= '' Char*)))? '?>' + ``` + target /xml/i is not excluded! +*/ +var PI = reg(/^<\?/, '(', Name, ')', regg(S, '(', Char, '*?)'), '?', /\?>/); + +// https://www.w3.org/TR/xml11/#NT-PubidChar +// `[13] PubidChar ::= #x20 | #xD | #xA | [a-zA-Z0-9] | [-'()+,./:=?;!*#@$_%]` +var PubidChar = /[\x20\x0D\x0Aa-zA-Z0-9-'()+,./:=?;!*#@$_%]/; + +// https://www.w3.org/TR/xml11/#NT-PubidLiteral +// `[12] PubidLiteral ::= '"' PubidChar* '"' | "'" (PubidChar - "'")* "'"` +var PubidLiteral = regg('"', PubidChar, '*"', '|', "'", chars_without(PubidChar, "'"), "*'"); + +// https://www.w3.org/TR/xml11/#NT-CharData +// `[14] CharData ::= [^<&]* - ([^<&]* ']]>' [^<&]*)` + +var COMMENT_START = ''; +// https://www.w3.org/TR/xml11/#NT-Comment +// `[15] Comment ::= ''` +var Comment = reg(COMMENT_START, regg(chars_without(Char, '-'), '|', reg('-', chars_without(Char, '-'))), '*', COMMENT_END); + +var PCDATA = '#PCDATA'; +// https://www.w3.org/TR/xml11/#NT-Mixed +// `[51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? Name)* S? ')*' | '(' S? '#PCDATA' S? ')'` +// https://www.w3.org/TR/xml-names/#NT-Mixed +// `[51] Mixed ::= '(' S? '#PCDATA' (S? '|' S? QName)* S? ')*' | '(' S? '#PCDATA' S? ')'` +// [VC: Proper Group/PE Nesting] [VC: No Duplicate Types] +var Mixed = regg( + reg(/\(/, S_OPT, PCDATA, regg(S_OPT, /\|/, S_OPT, QName), '*', S_OPT, /\)\*/), + '|', + reg(/\(/, S_OPT, PCDATA, S_OPT, /\)/) +); + +var _children_quantity = /[?*+]?/; +/* + `[49] choice ::= '(' S? cp ( S? '|' S? cp )+ S? ')'` [VC: Proper Group/PE Nesting] + `[50] seq ::= '(' S? cp ( S? ',' S? cp )* S? ')'` [VC: Proper Group/PE Nesting] + simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting" + var _choice_or_seq = reg('[', NameChar_s, SChar_s, chars(_children_quantity), '()|,]*'); + ``` + [48] cp ::= (Name | choice | seq) ('?' | '*' | '+')? + === (Name | '(' S? cp ( S? '|' S? cp )+ S? ')' | '(' S? cp ( S? ',' S? cp )* S? ')') ('?' | '*' | '+')? + !== (Name | [_choice_or_seq]*) ('?' | '*' | '+')? + ``` + simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting" + var cp = reg(regg(Name, '|', _choice_or_seq), _children_quantity); +*/ +/* +Inefficient regular expression (High) +This part of the regular expression may cause exponential backtracking on strings starting with '(|' and containing many repetitions of '|'. +https://github.com/xmldom/xmldom/security/code-scanning/91 +var choice = regg(/\(/, S_OPT, cp, regg(S_OPT, /\|/, S_OPT, cp), '+', S_OPT, /\)/); +*/ +/* +Inefficient regular expression (High) +This part of the regular expression may cause exponential backtracking on strings starting with '(,' and containing many repetitions of ','. +https://github.com/xmldom/xmldom/security/code-scanning/92 +var seq = regg(/\(/, S_OPT, cp, regg(S_OPT, /,/, S_OPT, cp), '*', S_OPT, /\)/); +*/ + +// `[47] children ::= (choice | seq) ('?' | '*' | '+')?` +// simplification to solve circular referencing, but doesn't check validity constraint "Proper Group/PE Nesting" +var children = reg(/\([^>]+\)/, _children_quantity /*regg(choice, '|', seq), _children_quantity*/); + +// https://www.w3.org/TR/xml11/#NT-contentspec +// `[46] contentspec ::= 'EMPTY' | 'ANY' | Mixed | children` +var contentspec = regg('EMPTY', '|', 'ANY', '|', Mixed, '|', children); + +var ELEMENTDECL_START = ''` +// https://www.w3.org/TR/xml-names/#NT-elementdecl +// `[17] elementdecl ::= ''` +// because of https://www.w3.org/TR/xml11/#NT-PEReference +// since xmldom is not supporting replacements of PEReferences in the DTD +// this also supports PEReference in the possible places +var elementdecl = reg(ELEMENTDECL_START, S, regg(QName, '|', PEReference), S, regg(contentspec, '|', PEReference), S_OPT, '>'); + +// https://www.w3.org/TR/xml11/#NT-NotationType +// `[58] NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')'` +// [VC: Notation Attributes] [VC: One Notation Per Element Type] [VC: No Notation on Empty Element] [VC: No Duplicate Tokens] +var NotationType = reg('NOTATION', S, /\(/, S_OPT, Name, regg(S_OPT, /\|/, S_OPT, Name), '*', S_OPT, /\)/); +// https://www.w3.org/TR/xml11/#NT-Enumeration +// `[59] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')'` +// [VC: Enumeration] [VC: No Duplicate Tokens] +var Enumeration = reg(/\(/, S_OPT, Nmtoken, regg(S_OPT, /\|/, S_OPT, Nmtoken), '*', S_OPT, /\)/); + +// https://www.w3.org/TR/xml11/#NT-EnumeratedType +// `[57] EnumeratedType ::= NotationType | Enumeration` +var EnumeratedType = regg(NotationType, '|', Enumeration); + +/* +``` +[55] StringType ::= 'CDATA' +[56] TokenizedType ::= 'ID' [VC: ID] [VC: One ID per Element Type] [VC: ID Attribute Default] + | 'IDREF' [VC: IDREF] + | 'IDREFS' [VC: IDREF] + | 'ENTITY' [VC: Entity Name] + | 'ENTITIES' [VC: Entity Name] + | 'NMTOKEN' [VC: Name Token] + | 'NMTOKENS' [VC: Name Token] + [54] AttType ::= StringType | TokenizedType | EnumeratedType +```*/ +var AttType = regg(/CDATA|ID|IDREF|IDREFS|ENTITY|ENTITIES|NMTOKEN|NMTOKENS/, '|', EnumeratedType); + +// `[60] DefaultDecl ::= '#REQUIRED' | '#IMPLIED' | (('#FIXED' S)? AttValue)` +// [WFC: No < in Attribute Values] [WFC: No External Entity References] +// [VC: Fixed Attribute Default] [VC: Required Attribute] [VC: Attribute Default Value Syntactically Correct] +var DefaultDecl = regg(/#REQUIRED|#IMPLIED/, '|', regg(regg('#FIXED', S), '?', AttValue)); + +// https://www.w3.org/TR/xml11/#NT-AttDef +// [53] AttDef ::= S Name S AttType S DefaultDecl +// https://www.w3.org/TR/xml-names/#NT-AttDef +// [1] NSAttName ::= PrefixedAttName | DefaultAttName +// [2] PrefixedAttName ::= 'xmlns:' NCName [NSC: Reserved Prefixes and Namespace Names] +// [3] DefaultAttName ::= 'xmlns' +// [21] AttDef ::= S (QName | NSAttName) S AttType S DefaultDecl +// === S Name S AttType S DefaultDecl +// xmldom is not distinguishing between QName and NSAttName on this level +// to support XML without namespaces in DTD we can not restrict it to QName +var AttDef = regg(S, Name, S, AttType, S, DefaultDecl); + +var ATTLIST_DECL_START = ''` +// https://www.w3.org/TR/xml-names/#NT-AttlistDecl +// `[20] AttlistDecl ::= ''` +// 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 +// `[75] ExternalID ::= 'SYSTEM' S SystemLiteral | 'PUBLIC' S PubidLiteral S SystemLiteral` +var ExternalID = regg(regg(SYSTEM, S, SystemLiteral), '|', regg(PUBLIC, S, PubidLiteral, S, SystemLiteral)); +var ExternalID_match = reg( + '^', + regg( + regg(SYSTEM, S, '(?', SystemLiteral, ')'), + '|', + regg(PUBLIC, S, '(?', PubidLiteral, ')', S, '(?', SystemLiteral, ')') + ) +); + +// https://www.w3.org/TR/xml11/#NT-NDataDecl +// `[76] NDataDecl ::= S 'NDATA' S Name` [VC: Notation Declared] +var NDataDecl = regg(S, 'NDATA', S, Name); + +// https://www.w3.org/TR/xml11/#NT-EntityDef +// `[73] EntityDef ::= EntityValue | (ExternalID NDataDecl?)` +var EntityDef = regg(EntityValue, '|', regg(ExternalID, NDataDecl, '?')); + +var ENTITY_DECL_START = ''` +var GEDecl = reg(ENTITY_DECL_START, S, Name, S, EntityDef, S_OPT, '>'); +// https://www.w3.org/TR/xml11/#NT-PEDef +// `[74] PEDef ::= EntityValue | ExternalID` +var PEDef = regg(EntityValue, '|', ExternalID); +// https://www.w3.org/TR/xml11/#NT-PEDecl +// `[72] PEDecl ::= ''` +var PEDecl = reg(ENTITY_DECL_START, S, '%', S, Name, S, PEDef, S_OPT, '>'); +// https://www.w3.org/TR/xml11/#NT-EntityDecl +// `[70] EntityDecl ::= GEDecl | PEDecl` +var EntityDecl = regg(GEDecl, '|', PEDecl); + +// https://www.w3.org/TR/xml11/#NT-PublicID +// `[83] PublicID ::= 'PUBLIC' S PubidLiteral` +var PublicID = reg(PUBLIC, S, PubidLiteral); +// https://www.w3.org/TR/xml11/#NT-NotationDecl +// `[82] NotationDecl ::= ''` [VC: Unique Notation Name] +var NotationDecl = reg(''); + +// https://www.w3.org/TR/xml11/#NT-Eq +// `[25] Eq ::= S? '=' S?` +var Eq = reg(S_OPT, '=', S_OPT); +// https://www.w3.org/TR/xml/#NT-VersionNum +// `[26] VersionNum ::= '1.' [0-9]+` +// https://www.w3.org/TR/xml11/#NT-VersionNum +// `[26] VersionNum ::= '1.1'` +var VersionNum = /1[.]\d+/; +// https://www.w3.org/TR/xml11/#NT-VersionInfo +// `[24] VersionInfo ::= S 'version' Eq ("'" VersionNum "'" | '"' VersionNum '"')` +var VersionInfo = reg(S, 'version', Eq, regg("'", VersionNum, "'", '|', '"', VersionNum, '"')); +// https://www.w3.org/TR/xml11/#NT-EncName +// `[81] EncName ::= [A-Za-z] ([A-Za-z0-9._] | '-')*` +var EncName = /[A-Za-z][-A-Za-z0-9._]*/; +// https://www.w3.org/TR/xml11/#NT-EncDecl +// `[80] EncodingDecl ::= S 'encoding' Eq ('"' EncName '"' | "'" EncName "'" )` +var EncodingDecl = regg(S, 'encoding', Eq, regg('"', EncName, '"', '|', "'", EncName, "'")); +// https://www.w3.org/TR/xml11/#NT-SDDecl +// `[32] SDDecl ::= S 'standalone' Eq (("'" ('yes' | 'no') "'") | ('"' ('yes' | 'no') '"'))` +var SDDecl = regg(S, 'standalone', Eq, regg("'", regg('yes', '|', 'no'), "'", '|', '"', regg('yes', '|', 'no'), '"')); +// https://www.w3.org/TR/xml11/#NT-XMLDecl +// [23] XMLDecl ::= '' +var XMLDecl = reg(/^<\?xml/, VersionInfo, EncodingDecl, '?', SDDecl, '?', S_OPT, /\?>/); + +/* + https://www.w3.org/TR/xml/#NT-markupdecl + https://www.w3.org/TR/xml11/#NT-markupdecl + `[29] markupdecl ::= elementdecl | AttlistDecl | EntityDecl | NotationDecl | PI | Comment` + var markupdecl = regg(elementdecl, '|', AttlistDecl, '|', EntityDecl, '|', NotationDecl, '|', PI_unsafe, '|', Comment); +*/ +/* + https://www.w3.org/TR/xml-names/#NT-doctypedecl +`[28a] DeclSep ::= PEReference | S` + https://www.w3.org/TR/xml11/#NT-intSubset +``` + [28b] intSubset ::= (markupdecl | DeclSep)* + === (markupdecl | PEReference | S)* +``` + [WFC: PE Between Declarations] + var intSubset = reg(regg(markupdecl, '|', PEReference, '|', S), '*'); +*/ +var DOCTYPE_DECL_START = ''` + https://www.afterwardsw3.org/TR/xml-names/#NT-doctypedecl + `[16] doctypedecl ::= ''` + var doctypedecl = reg(''); +*/ + +var CDATA_START = ''; +var CDStart = //; +var CData = reg(Char, '*?', CDEnd); +/* + https://www.w3.org/TR/xml/#dt-cdsection + `[18] CDSect ::= CDStart CData CDEnd` + `[19] CDStart ::= '' Char*))` + `[21] CDEnd ::= ']]>'` +*/ +var CDSect = reg(CDStart, CData); + +export { chars, chars_without, detectUnicodeSupport, reg, regg, ABOUT_LEGACY_COMPAT, ABOUT_LEGACY_COMPAT_SystemLiteral, AttlistDecl, CDATA_START, CDATA_END, CDSect, Char, Comment, COMMENT_START, COMMENT_END, DOCTYPE_DECL_START, elementdecl, EntityDecl, EntityValue, ExternalID, ExternalID_match, Name, NotationDecl, Reference, PEReference, PI, PUBLIC, PubidLiteral, QName, QName_exact, QName_group, S, SChar_s, S_OPT, SYSTEM, SystemLiteral, UNICODE_REPLACEMENT_CHARACTER, UNICODE_SUPPORT, XMLDecl } + +/* +// unit tested +exports.chars = chars; +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; +exports.CDSect = CDSect; +exports.Char = Char; +exports.Comment = Comment; +exports.COMMENT_START = COMMENT_START; +exports.COMMENT_END = COMMENT_END; +exports.DOCTYPE_DECL_START = DOCTYPE_DECL_START; +exports.elementdecl = elementdecl; +exports.EntityDecl = EntityDecl; +exports.EntityValue = EntityValue; +exports.ExternalID = ExternalID; +exports.ExternalID_match = ExternalID_match; +exports.Name = Name; +exports.NotationDecl = NotationDecl; +exports.Reference = Reference; +exports.PEReference = PEReference; +exports.PI = PI; +exports.PUBLIC = PUBLIC; +exports.PubidLiteral = PubidLiteral; +exports.QName = QName; +exports.QName_exact = QName_exact; +exports.QName_group = QName_group; +exports.S = S; +exports.SChar_s = SChar_s; +exports.S_OPT = S_OPT; +exports.SYSTEM = SYSTEM; +exports.SystemLiteral = SystemLiteral; +exports.UNICODE_REPLACEMENT_CHARACTER = UNICODE_REPLACEMENT_CHARACTER; +exports.UNICODE_SUPPORT = UNICODE_SUPPORT; +exports.XMLDecl = XMLDecl; +*/ diff --git a/lib/xmldom/index.js b/lib/xmldom/index.js index bc8f6dd..7129bb6 100644 --- a/lib/xmldom/index.js +++ b/lib/xmldom/index.js @@ -1,5 +1,48 @@ -import * as dom from './dom.js'; -import * as parser from './dom-parser.js'; -export const DOMImplementation = dom.DOMImplementation; -export const XMLSerializer = dom.XMLSerializer; -export const DOMParser = parser.DOMParser; +export * from './conventions.js'; +/* +exports.assign = conventions.assign; +exports.hasDefaultHTMLNamespace = conventions.hasDefaultHTMLNamespace; +exports.isHTMLMimeType = conventions.isHTMLMimeType; +exports.isValidMimeType = conventions.isValidMimeType; +exports.MIME_TYPE = conventions.MIME_TYPE; +exports.NAMESPACE = conventions.NAMESPACE; +*/ + +export * from './errors.js'; +/* +exports.DOMException = errors.DOMException; +exports.DOMExceptionName = errors.DOMExceptionName; +exports.ExceptionCode = errors.ExceptionCode; +exports.ParseError = errors.ParseError; +*/ + +export * from './dom.js'; +/* +exports.Attr = dom.Attr; +exports.CDATASection = dom.CDATASection; +exports.CharacterData = dom.CharacterData; +exports.Comment = dom.Comment; +exports.Document = dom.Document; +exports.DocumentFragment = dom.DocumentFragment; +exports.DocumentType = dom.DocumentType; +exports.DOMImplementation = dom.DOMImplementation; +exports.Element = dom.Element; +exports.Entity = dom.Entity; +exports.EntityReference = dom.EntityReference; +exports.LiveNodeList = dom.LiveNodeList; +exports.NamedNodeMap = dom.NamedNodeMap; +exports.Node = dom.Node; +exports.NodeList = dom.NodeList; +exports.Notation = dom.Notation; +exports.ProcessingInstruction = dom.ProcessingInstruction; +exports.Text = dom.Text; +exports.XMLSerializer = dom.XMLSerializer; +*/ + +export * from './dom-parser.js'; +/* +exports.DOMParser = domParser.DOMParser; +exports.normalizeLineEndings = domParser.normalizeLineEndings; +exports.onErrorStopParsing = domParser.onErrorStopParsing; +exports.onWarningStopParsing = domParser.onWarningStopParsing; +*/ diff --git a/lib/xmldom/sax.js b/lib/xmldom/sax.js index 0699e17..9137ec5 100644 --- a/lib/xmldom/sax.js +++ b/lib/xmldom/sax.js @@ -1,239 +1,275 @@ -import {NAMESPACE} from "./conventions.js"; - -//[4] NameStartChar ::= ":" | [A-Z] | "_" | [a-z] | [#xC0-#xD6] | [#xD8-#xF6] | [#xF8-#x2FF] | [#x370-#x37D] | [#x37F-#x1FFF] | [#x200C-#x200D] | [#x2070-#x218F] | [#x2C00-#x2FEF] | [#x3001-#xD7FF] | [#xF900-#xFDCF] | [#xFDF0-#xFFFD] | [#x10000-#xEFFFF] -//[4a] NameChar ::= NameStartChar | "-" | "." | [0-9] | #xB7 | [#x0300-#x036F] | [#x203F-#x2040] -//[5] Name ::= NameStartChar (NameChar)* -var nameStartChar = /[A-Z_a-z\xC0-\xD6\xD8-\xF6\u00F8-\u02FF\u0370-\u037D\u037F-\u1FFF\u200C-\u200D\u2070-\u218F\u2C00-\u2FEF\u3001-\uD7FF\uF900-\uFDCF\uFDF0-\uFFFD]///\u10000-\uEFFFF -var nameChar = new RegExp("[\\-\\.0-9"+nameStartChar.source.slice(1,-1)+"\\u00B7\\u0300-\\u036F\\u203F-\\u2040]"); -var tagNamePattern = new RegExp('^'+nameStartChar.source+nameChar.source+'*(?:\:'+nameStartChar.source+nameChar.source+'*)?$'); -//var tagNamePattern = /^[a-zA-Z_][\w\-\.]*(?:\:[a-zA-Z_][\w\-\.]*)?$/ +import * as conventions from './conventions.js'; +import * as g from './grammar.js'; +import * as errors from './errors.js'; + +var isHTMLEscapableRawTextElement = conventions.isHTMLEscapableRawTextElement; +var isHTMLMimeType = conventions.isHTMLMimeType; +var isHTMLRawTextElement = conventions.isHTMLRawTextElement; +var hasOwn = conventions.hasOwn; +var NAMESPACE = conventions.NAMESPACE; +var ParseError = errors.ParseError; +var DOMException = errors.DOMException; + //var handlers = 'resolveEntity,getExternalSubset,characters,endDocument,endElement,endPrefixMapping,ignorableWhitespace,processingInstruction,setDocumentLocator,skippedEntity,startDocument,startElement,startPrefixMapping,notationDecl,unparsedEntityDecl,error,fatalError,warning,attributeDecl,elementDecl,externalEntityDecl,internalEntityDecl,comment,endCDATA,endDTD,endEntity,startCDATA,startDTD,startEntity'.split(',') //S_TAG, S_ATTR, S_EQ, S_ATTR_NOQUOT_VALUE //S_ATTR_SPACE, S_ATTR_END, S_TAG_SPACE, S_TAG_CLOSE -var S_TAG = 0;//tag name offerring -var S_ATTR = 1;//attr name offerring -var S_ATTR_SPACE=2;//attr name end and space offer -var S_EQ = 3;//=space? -var S_ATTR_NOQUOT_VALUE = 4;//attr value(no quot value only) -var S_ATTR_END = 5;//attr value end and no space(quot end) -var S_TAG_SPACE = 6;//(attr value end || tag end ) && (space offer) -var S_TAG_CLOSE = 7;//closed el - -/** - * Creates an error that will not be caught by XMLReader aka the SAX parser. - * - * @param {string} message - * @param {any?} locator Optional, can provide details about the location in the source - * @constructor - */ -function ParseError(message, locator) { - this.message = message - this.locator = locator - if(Error.captureStackTrace) Error.captureStackTrace(this, ParseError); -} -ParseError.prototype = new Error(); -ParseError.prototype.name = ParseError.name - -function XMLReader(){ +var S_TAG = 0; //tag name offerring +var S_ATTR = 1; //attr name offerring +var S_ATTR_SPACE = 2; //attr name end and space offer +var S_EQ = 3; //=space? +var S_ATTR_NOQUOT_VALUE = 4; //attr value(no quot value only) +var S_ATTR_END = 5; //attr value end and no space(quot end) +var S_TAG_SPACE = 6; //(attr value end || tag end ) && (space offer) +var S_TAG_CLOSE = 7; //closed el -} +function XMLReader() {} XMLReader.prototype = { - parse:function(source,defaultNSMap,entityMap){ + parse: function (source, defaultNSMap, entityMap) { var domBuilder = this.domBuilder; domBuilder.startDocument(); - _copy(defaultNSMap ,defaultNSMap = {}) - parse(source,defaultNSMap,entityMap, - domBuilder,this.errorHandler); + _copy(defaultNSMap, (defaultNSMap = Object.create(null))); + parse(source, defaultNSMap, entityMap, domBuilder, this.errorHandler); domBuilder.endDocument(); + }, +}; + +/** + * Detecting everything that might be a reference, + * including those without ending `;`, since those are allowed in HTML. + * The entityReplacer takes care of verifying and transforming each occurrence, + * and reports to the errorHandler on those that are not OK, + * depending on the context. + */ +var ENTITY_REG = /&#?\w+;?/g; + +function parse(source, defaultNSMapCopy, entityMap, domBuilder, errorHandler) { + var isHTML = isHTMLMimeType(domBuilder.mimeType); + if (source.indexOf(g.UNICODE_REPLACEMENT_CHARACTER) >= 0) { + errorHandler.warning('Unicode replacement character detected, source encoding issues?'); } -} -function parse(source,defaultNSMapCopy,entityMap,domBuilder,errorHandler){ + function fixedFromCharCode(code) { // String.prototype.fromCharCode does not supports // > 2 bytes unicode chars directly if (code > 0xffff) { code -= 0x10000; - var surrogate1 = 0xd800 + (code >> 10) - , surrogate2 = 0xdc00 + (code & 0x3ff); + var surrogate1 = 0xd800 + (code >> 10), + surrogate2 = 0xdc00 + (code & 0x3ff); return String.fromCharCode(surrogate1, surrogate2); } else { return String.fromCharCode(code); } } - function entityReplacer(a){ - var k = a.slice(1,-1); - if (Object.hasOwnProperty.call(entityMap, k)) { - return entityMap[k]; - }else if(k.charAt(0) === '#'){ - return fixedFromCharCode(parseInt(k.substr(1).replace('x','0x'))) - }else{ - errorHandler.error('entity not found:'+a); + + function entityReplacer(a) { + var complete = a[a.length - 1] === ';' ? a : a + ';'; + if (!isHTML && complete !== a) { + errorHandler.error('EntityRef: expecting ;'); return a; } - } - function appendText(end){//has some bugs - if(end>start){ - var xt = source.substring(start,end).replace(/&#?\w+;/g,entityReplacer); - locator&&position(start); - domBuilder.characters(xt,0,end-start); - start = end + var match = g.Reference.exec(complete); + if (!match || match[0].length !== complete.length) { + errorHandler.error('entity not matching Reference production: ' + a); + return a; + } + var k = complete.slice(1, -1); + if (hasOwn(entityMap, k)) { + return entityMap[k]; + } else if (k.charAt(0) === '#') { + return fixedFromCharCode(parseInt(k.substring(1).replace('x', '0x'))); + } else { + errorHandler.error('entity not found:' + a); + return a; } } - function position(p,m){ - while(p>=lineEnd && (m = linePattern.exec(source))){ - lineStart = m.index; - lineEnd = lineStart + m[0].length; - locator.lineNumber++; - //console.log('line++:',locator,startPos,endPos) + + function appendText(end) { + //has some bugs + if (end > start) { + var xt = source.substring(start, end).replace(ENTITY_REG, entityReplacer); + locator && position(start); + domBuilder.characters(xt, 0, end - start); + start = end; } - locator.columnNumber = p-lineStart+1; } + var lineStart = 0; var lineEnd = 0; - var linePattern = /.*(?:\r\n?|\n)|.*$/g + var linePattern = /\r\n?|\n|$/g; var locator = domBuilder.locator; - var parseStack = [{currentNSMap:defaultNSMapCopy}] - var closeMap = {}; + function position(p, m) { + while (p >= lineEnd && (m = linePattern.exec(source))) { + lineStart = lineEnd; + lineEnd = m.index + m[0].length; + locator.lineNumber++; + } + locator.columnNumber = p - lineStart + 1; + } + + var parseStack = [{ currentNSMap: defaultNSMapCopy }]; + var unclosedTags = []; var start = 0; - while(true){ - try{ - var tagStart = source.indexOf('<',start); - if(tagStart<0){ - if(!source.substr(start).match(/^\s*$/)){ + while (true) { + try { + var tagStart = source.indexOf('<', start); + if (tagStart < 0) { + if (!isHTML && unclosedTags.length > 0) { + return errorHandler.fatalError('unclosed xml tag(s): ' + unclosedTags.join(', ')); + } + if (!source.substring(start).match(/^\s*$/)) { var doc = domBuilder.doc; - var text = doc.createTextNode(source.substr(start)); - doc.appendChild(text); - domBuilder.currentElement = text; + var text = doc.createTextNode(source.substring(start)); + if (doc.documentElement) { + return errorHandler.error('Extra content at the end of the document'); + } + doc.appendChild(text); + domBuilder.currentElement = text; } return; } - if(tagStart>start){ + if (tagStart > start) { + var fromSource = source.substring(start, tagStart); + if (!isHTML && unclosedTags.length === 0) { + fromSource = fromSource.replace(new RegExp(g.S_OPT.source, 'g'), ''); + fromSource && errorHandler.error("Unexpected content outside root element: '" + fromSource + "'"); + } appendText(tagStart); } - switch(source.charAt(tagStart+1)){ - case '/': - var end = source.indexOf('>',tagStart+3); - var tagName = source.substring(tagStart + 2, end).replace(/[ \t\n\r]+$/g, ''); - var config = parseStack.pop(); - if(end<0){ - - tagName = source.substring(tagStart+2).replace(/[\s<].*/,''); - errorHandler.error("end tag name: "+tagName+' is not complete:'+config.tagName); - end = tagStart+1+tagName.length; - }else if(tagName.match(/\s', tagStart + 2); + var tagNameRaw = source.substring(tagStart + 2, end > 0 ? end : undefined); + if (!tagNameRaw) { + return errorHandler.fatalError('end tag name missing'); + } + var tagNameMatch = end > 0 && g.reg('^', g.QName_group, g.S_OPT, '$').exec(tagNameRaw); + if (!tagNameMatch) { + return errorHandler.fatalError('end tag name contains invalid characters: "' + tagNameRaw + '"'); + } + if (!domBuilder.currentElement && !domBuilder.doc.documentElement) { + // not enough information to provide a helpful error message, + // but parsing will throw since there is no root element + return; + } + var currentTagName = + unclosedTags[unclosedTags.length - 1] || + domBuilder.currentElement.tagName || + domBuilder.doc.documentElement.tagName || + ''; + if (currentTagName !== tagNameMatch[1]) { + var tagNameLower = tagNameMatch[1].toLowerCase(); + if (!isHTML || currentTagName.toLowerCase() !== tagNameLower) { + return errorHandler.fatalError('Opening and ending tag mismatch: "' + currentTagName + '" != "' + tagNameRaw + '"'); + } + } + var config = parseStack.pop(); + unclosedTags.pop(); + var localNSMap = config.localNSMap; + domBuilder.endElement(config.uri, config.localName, currentTagName); + if (localNSMap) { for (var prefix in localNSMap) { - if (Object.prototype.hasOwnProperty.call(localNSMap, prefix)) { + if (hasOwn(localNSMap, prefix)) { domBuilder.endPrefixMapping(prefix); } } } - if(!endMatch){ - errorHandler.fatalError("end tag name: "+tagName+' is not match the current start tagName:'+config.tagName ); // No known test case - } - }else{ - parseStack.push(config) - } - end++; - break; - // end elment - case '?':// - locator&&position(tagStart); - end = parseInstruction(source,tagStart,domBuilder); - break; - case '!':// + locator && position(tagStart); + end = parseProcessingInstruction(source, tagStart, domBuilder, errorHandler); + break; + case '!': // start){ + if (end > start) { start = end; - }else{ - //TODO: 这里有可能sax回退，有位置错误风险 - appendText(Math.max(tagStart,start)+1); + } else { + //Possible sax fallback here, risk of positional error + appendText(Math.max(tagStart, start) + 1); } } } -function copyLocator(f,t){ + +function copyLocator(f, t) { t.lineNumber = f.lineNumber; t.columnNumber = f.columnNumber; return t; } /** - * @see #appendElement(source,elStartEnd,el,selfClosed,entityReplacer,domBuilder,parseStack); - * @return end of the elementStartPart(end of elementEndPart for selfClosed el) + * @returns + * end of the elementStartPart(end of elementEndPart for selfClosed el) + * @see {@link #appendElement} */ -function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,errorHandler){ - +function parseElementStartPart(source, start, el, currentNSMap, entityReplacer, errorHandler, isHTML) { /** * @param {string} qname * @param {string} value * @param {number} startIndex */ function addAttribute(qname, value, startIndex) { - if (el.attributeNames.hasOwnProperty(qname)) { - errorHandler.fatalError('Attribute ' + qname + ' redefined') + if (hasOwn(el.attributeNames, qname)) { + return errorHandler.fatalError('Attribute ' + qname + ' redefined'); + } + if (!isHTML && value.indexOf('<') >= 0) { + return errorHandler.fatalError("Unescaped '<' not allowed in attributes values"); } el.addValue( qname, @@ -241,429 +277,655 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error // since the xmldom sax parser does not "interpret" DTD the following is not implemented: // - recursive replacement of (DTD) entity references // - trimming and collapsing multiple spaces into a single one for attributes that are not of type CDATA - value.replace(/[\t\n\r]/g, ' ').replace(/&#?\w+;/g, entityReplacer), + value.replace(/[\t\n\r]/g, ' ').replace(ENTITY_REG, entityReplacer), startIndex - ) + ); } + var attrName; var value; var p = ++start; - var s = S_TAG;//status - while(true){ + var s = S_TAG; //status + while (true) { var c = source.charAt(p); - switch(c){ - case '=': - if(s === S_ATTR){//attrName - attrName = source.slice(start,p); - s = S_EQ; - }else if(s === S_ATTR_SPACE){ - s = S_EQ; - }else{ - //fatalError: equal must after attrName or space after attrName - throw new Error('attribute equal must after attrName'); // No known test case - } - break; - case '\'': - case '"': - if(s === S_EQ || s === S_ATTR //|| s == S_ATTR_SPACE - ){//equal - if(s === S_ATTR){ - errorHandler.warning('attribute value must after "="') - attrName = source.slice(start,p) + switch (c) { + case '=': + if (s === S_ATTR) { + //attrName + attrName = source.slice(start, p); + s = S_EQ; + } else if (s === S_ATTR_SPACE) { + s = S_EQ; + } else { + //fatalError: equal must after attrName or space after attrName + throw new Error('attribute equal must after attrName'); // No known test case } - start = p+1; - p = source.indexOf(c,start) - if(p>0){ + break; + case "'": + case '"': + if ( + s === S_EQ || + s === S_ATTR //|| s == S_ATTR_SPACE + ) { + //equal + if (s === S_ATTR) { + errorHandler.warning('attribute value must after "="'); + attrName = source.slice(start, p); + } + start = p + 1; + p = source.indexOf(c, start); + if (p > 0) { + value = source.slice(start, p); + addAttribute(attrName, value, start - 1); + s = S_ATTR_END; + } else { + //fatalError: no end quot match + throw new Error("attribute value no end '" + c + "' match"); + } + } else if (s == S_ATTR_NOQUOT_VALUE) { value = source.slice(start, p); - addAttribute(attrName, value, start-1); + addAttribute(attrName, value, start); + errorHandler.warning('attribute "' + attrName + '" missed start quot(' + c + ')!!'); + start = p + 1; s = S_ATTR_END; - }else{ - //fatalError: no end quot match - throw new Error('attribute value no end \''+c+'\' match'); + } else { + //fatalError: no equal before + throw new Error('attribute value must after "="'); // No known test case } - }else if(s == S_ATTR_NOQUOT_VALUE){ - value = source.slice(start, p); - addAttribute(attrName, value, start); - errorHandler.warning('attribute "'+attrName+'" missed start quot('+c+')!!'); - start = p+1; - s = S_ATTR_END - }else{ - //fatalError: no equal before - throw new Error('attribute value must after "="'); // No known test case - } - break; - case '/': - switch(s){ - case S_TAG: - el.setTagName(source.slice(start,p)); - case S_ATTR_END: - case S_TAG_SPACE: - case S_TAG_CLOSE: - s =S_TAG_CLOSE; - el.closed = true; - case S_ATTR_NOQUOT_VALUE: - case S_ATTR: break; - case S_ATTR_SPACE: - el.closed = true; + case '/': + switch (s) { + case S_TAG: + el.setTagName(source.slice(start, p)); + case S_ATTR_END: + case S_TAG_SPACE: + case S_TAG_CLOSE: + s = S_TAG_CLOSE; + el.closed = true; + case S_ATTR_NOQUOT_VALUE: + case S_ATTR: + break; + case S_ATTR_SPACE: + el.closed = true; + break; + //case S_EQ: + default: + throw new Error("attribute invalid close char('/')"); // No known test case + } break; - //case S_EQ: - default: - throw new Error("attribute invalid close char('/')") // No known test case - } - break; - case ''://end document - errorHandler.error('unexpected end of input'); - if(s == S_TAG){ - el.setTagName(source.slice(start,p)); - } - return p; - case '>': - switch(s){ - case S_TAG: - el.setTagName(source.slice(start,p)); - case S_ATTR_END: - case S_TAG_SPACE: - case S_TAG_CLOSE: - break;//normal - case S_ATTR_NOQUOT_VALUE://Compatible state - case S_ATTR: - value = source.slice(start,p); - if(value.slice(-1) === '/'){ - el.closed = true; - value = value.slice(0,-1) + case '': //end document + errorHandler.error('unexpected end of input'); + if (s == S_TAG) { + el.setTagName(source.slice(start, p)); } - case S_ATTR_SPACE: - if(s === S_ATTR_SPACE){ - value = attrName; + return p; + case '>': + switch (s) { + case S_TAG: + el.setTagName(source.slice(start, p)); + case S_ATTR_END: + case S_TAG_SPACE: + case S_TAG_CLOSE: + break; //normal + case S_ATTR_NOQUOT_VALUE: //Compatible state + case S_ATTR: + value = source.slice(start, p); + if (value.slice(-1) === '/') { + el.closed = true; + value = value.slice(0, -1); + } + case S_ATTR_SPACE: + if (s === S_ATTR_SPACE) { + value = attrName; + } + if (s == S_ATTR_NOQUOT_VALUE) { + errorHandler.warning('attribute "' + value + '" missed quot(")!'); + addAttribute(attrName, value, start); + } else { + if (!isHTML) { + errorHandler.warning('attribute "' + value + '" missed value!! "' + value + '" instead!!'); + } + addAttribute(value, value, start); + } + break; + case S_EQ: + if (!isHTML) { + return errorHandler.fatalError('AttValue: \' or " expected'); + } } - if(s == S_ATTR_NOQUOT_VALUE){ - errorHandler.warning('attribute "'+value+'" missed quot(")!'); - addAttribute(attrName, value, start) - }else{ - if(!NAMESPACE.isHTML(currentNSMap['']) || !value.match(/^(?:disabled|checked|selected)$/i)){ - errorHandler.warning('attribute "'+value+'" missed value!! "'+value+'" instead!!') + return p; + /*xml space '\x20' | #x9 | #xD | #xA; */ + case '\u0080': + c = ' '; + default: + if (c <= ' ') { + //space + switch (s) { + case S_TAG: + el.setTagName(source.slice(start, p)); //tagName + s = S_TAG_SPACE; + break; + case S_ATTR: + attrName = source.slice(start, p); + s = S_ATTR_SPACE; + break; + case S_ATTR_NOQUOT_VALUE: + var value = source.slice(start, p); + errorHandler.warning('attribute "' + value + '" missed quot(")!!'); + addAttribute(attrName, value, start); + case S_ATTR_END: + s = S_TAG_SPACE; + break; + //case S_TAG_SPACE: + //case S_EQ: + //case S_ATTR_SPACE: + // void();break; + //case S_TAG_CLOSE: + //ignore warning } - addAttribute(value, value, start) - } - break; - case S_EQ: - throw new Error('attribute value missed!!'); - } -// console.log(tagName,tagNamePattern,tagNamePattern.test(tagName)) - return p; - /*xml space '\x20' | #x9 | #xD | #xA; */ - case '\u0080': - c = ' '; - default: - if(c<= ' '){//space - switch(s){ - case S_TAG: - el.setTagName(source.slice(start,p));//tagName - s = S_TAG_SPACE; - break; - case S_ATTR: - attrName = source.slice(start,p) - s = S_ATTR_SPACE; - break; - case S_ATTR_NOQUOT_VALUE: - var value = source.slice(start, p); - errorHandler.warning('attribute "'+value+'" missed quot(")!!'); - addAttribute(attrName, value, start) - case S_ATTR_END: - s = S_TAG_SPACE; - break; - //case S_TAG_SPACE: - //case S_EQ: - //case S_ATTR_SPACE: - // void();break; - //case S_TAG_CLOSE: - //ignore warning - } - }else{//not space -//S_TAG, S_ATTR, S_EQ, S_ATTR_NOQUOT_VALUE -//S_ATTR_SPACE, S_ATTR_END, S_TAG_SPACE, S_TAG_CLOSE - switch(s){ - //case S_TAG:void();break; - //case S_ATTR:void();break; - //case S_ATTR_NOQUOT_VALUE:void();break; - case S_ATTR_SPACE: - var tagName = el.tagName; - if (!NAMESPACE.isHTML(currentNSMap['']) || !attrName.match(/^(?:disabled|checked|selected)$/i)) { - errorHandler.warning('attribute "'+attrName+'" missed value!! "'+attrName+'" instead2!!') + } else { + //not space + //S_TAG, S_ATTR, S_EQ, S_ATTR_NOQUOT_VALUE + //S_ATTR_SPACE, S_ATTR_END, S_TAG_SPACE, S_TAG_CLOSE + switch (s) { + //case S_TAG:void();break; + //case S_ATTR:void();break; + //case S_ATTR_NOQUOT_VALUE:void();break; + case S_ATTR_SPACE: + if (!isHTML) { + errorHandler.warning('attribute "' + attrName + '" missed value!! "' + attrName + '" instead2!!'); + } + addAttribute(attrName, attrName, start); + start = p; + s = S_ATTR; + break; + case S_ATTR_END: + errorHandler.warning('attribute space is required"' + attrName + '"!!'); + case S_TAG_SPACE: + s = S_ATTR; + start = p; + break; + case S_EQ: + s = S_ATTR_NOQUOT_VALUE; + start = p; + break; + case S_TAG_CLOSE: + throw new Error("elements closed character '/' and '>' must be connected to"); } - addAttribute(attrName, attrName, start); - start = p; - s = S_ATTR; - break; - case S_ATTR_END: - errorHandler.warning('attribute space is required"'+attrName+'"!!') - case S_TAG_SPACE: - s = S_ATTR; - start = p; - break; - case S_EQ: - s = S_ATTR_NOQUOT_VALUE; - start = p; - break; - case S_TAG_CLOSE: - throw new Error("elements closed character '/' and '>' must be connected to"); } - } - }//end outer switch - //console.log('p++',p) + } //end outer switch p++; } } + /** - * @return true if has new namespace define + * @returns + * `true` if a new namespace has been defined. */ -function appendElement(el,domBuilder,currentNSMap){ +function appendElement(el, domBuilder, currentNSMap) { var tagName = el.tagName; var localNSMap = null; - //var currentNSMap = parseStack[parseStack.length-1].currentNSMap; var i = el.length; - while(i--){ + while (i--) { var a = el[i]; var qName = a.qName; var value = a.value; var nsp = qName.indexOf(':'); - if(nsp>0){ - var prefix = a.prefix = qName.slice(0,nsp); - var localName = qName.slice(nsp+1); - var nsPrefix = prefix === 'xmlns' && localName - }else{ + if (nsp > 0) { + var prefix = (a.prefix = qName.slice(0, nsp)); + var localName = qName.slice(nsp + 1); + var nsPrefix = prefix === 'xmlns' && localName; + } else { localName = qName; - prefix = null - nsPrefix = qName === 'xmlns' && '' + prefix = null; + nsPrefix = qName === 'xmlns' && ''; } //can not set prefix,because prefix !== '' - a.localName = localName ; + a.localName = localName; //prefix == null for no ns prefix attribute - if(nsPrefix !== false){//hack!! - if(localNSMap == null){ - localNSMap = {} - //console.log(currentNSMap,0) - _copy(currentNSMap,currentNSMap={}) - //console.log(currentNSMap,1) + if (nsPrefix !== false) { + //hack!! + if (localNSMap == null) { + localNSMap = Object.create(null); + _copy(currentNSMap, (currentNSMap = Object.create(null))); } currentNSMap[nsPrefix] = localNSMap[nsPrefix] = value; - a.uri = NAMESPACE.XMLNS - domBuilder.startPrefixMapping(nsPrefix, value) + a.uri = NAMESPACE.XMLNS; + domBuilder.startPrefixMapping(nsPrefix, value); } } var i = el.length; - while(i--){ + while (i--) { a = el[i]; - var prefix = a.prefix; - if(prefix){//no prefix attribute has no namespace - if(prefix === 'xml'){ + if (a.prefix) { + //no prefix attribute has no namespace + if (a.prefix === 'xml') { a.uri = NAMESPACE.XML; - }if(prefix !== 'xmlns'){ - a.uri = currentNSMap[prefix || ''] - - //{console.log('###'+a.qName,domBuilder.locator.systemId+'',currentNSMap,a.uri)} + } + if (a.prefix !== 'xmlns') { + a.uri = currentNSMap[a.prefix]; } } } var nsp = tagName.indexOf(':'); - if(nsp>0){ - prefix = el.prefix = tagName.slice(0,nsp); - localName = el.localName = tagName.slice(nsp+1); - }else{ - prefix = null;//important!! + if (nsp > 0) { + prefix = el.prefix = tagName.slice(0, nsp); + localName = el.localName = tagName.slice(nsp + 1); + } else { + prefix = null; //important!! localName = el.localName = tagName; } //no prefix element has default namespace - var ns = el.uri = currentNSMap[prefix || '']; - domBuilder.startElement(ns,localName,tagName,el); + var ns = (el.uri = currentNSMap[prefix || '']); + domBuilder.startElement(ns, localName, tagName, el); //endPrefixMapping and startPrefixMapping have not any help for dom builder //localNSMap = null - if(el.closed){ - domBuilder.endElement(ns,localName,tagName); - if(localNSMap){ + if (el.closed) { + domBuilder.endElement(ns, localName, tagName); + if (localNSMap) { for (prefix in localNSMap) { - if (Object.prototype.hasOwnProperty.call(localNSMap, prefix)) { + if (hasOwn(localNSMap, prefix)) { domBuilder.endPrefixMapping(prefix); } } } - }else{ + } else { el.currentNSMap = currentNSMap; el.localNSMap = localNSMap; //parseStack.push(el); return true; } } -function parseHtmlSpecialContent(source,elStartEnd,tagName,entityReplacer,domBuilder){ - if(/^(?:script|textarea)$/i.test(tagName)){ - var elEndStart = source.indexOf('',elStartEnd); - var text = source.substring(elStartEnd+1,elEndStart); - if(/[&<]/.test(text)){ - if(/^script$/i.test(tagName)){ - //if(!/\]\]>/.test(text)){ - //lexHandler.startCDATA(); - domBuilder.characters(text,0,text.length); - //lexHandler.endCDATA(); - return elEndStart; - //} - }//}else{//text area - text = text.replace(/&#?\w+;/g,entityReplacer); - domBuilder.characters(text,0,text.length); - return elEndStart; - //} +function parseHtmlSpecialContent(source, elStartEnd, tagName, entityReplacer, domBuilder) { + // https://html.spec.whatwg.org/#raw-text-elements + // https://html.spec.whatwg.org/#escapable-raw-text-elements + // https://html.spec.whatwg.org/#cdata-rcdata-restrictions:raw-text-elements + // TODO: https://html.spec.whatwg.org/#cdata-rcdata-restrictions + var isEscapableRaw = isHTMLEscapableRawTextElement(tagName); + if (isEscapableRaw || isHTMLRawTextElement(tagName)) { + var elEndStart = source.indexOf('', elStartEnd); + var text = source.substring(elStartEnd + 1, elEndStart); + + if (isEscapableRaw) { + text = text.replace(ENTITY_REG, entityReplacer); } + domBuilder.characters(text, 0, text.length); + return elEndStart; } - return elStartEnd+1; -} -function fixSelfClosed(source,elStartEnd,tagName,closeMap){ - //if(tagName in closeMap){ - var pos = closeMap[tagName]; - if(pos == null){ - //console.log(tagName) - pos = source.lastIndexOf('') - if(pos',start+4); - //append comment source.substring(4,end)//