@xmldom/xmldom 0.8.3 → 0.8.5

package/CHANGELOG.md

@@ -4,6 +4,28 @@ All notable changes to this project will be documented in this file.
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.8.5](https://github.com/xmldom/xmldom/compare/0.8.4...0.8.5)
+
+### Fixed
+
+- fix: Restore ES5 compatibility [`#452`](https://github.com/xmldom/xmldom/pull/452) / [`#453`](https://github.com/xmldom/xmldom/issues/453)
+
+Thank you, [@fengxinming](https://github.com/fengxinming), for your contributions
+
+
+## [0.8.4](https://github.com/xmldom/xmldom/compare/0.8.3...0.8.4)
+
+### Fixed
+
+- Security: Prevent inserting DOM nodes when they are not well-formed [`CVE-2022-39353`](https://github.com/xmldom/xmldom/security/advisories/GHSA-crh6-fp67-6883)
+  In case such a DOM would be created, the part that is not well-formed will be transformed into text nodes, in which xml specific characters like `<` and `>` are encoded accordingly.
+  In the upcoming version 0.9.0 those text nodes will no longer be added and an error will be thrown instead.
+  This change can break your code, if you relied on this behavior, e.g. multiple root elements in the past. We consider it more important to align with the specs that we want to be aligned with, considering the potential security issues that might derive from people not being aware of the difference in behavior.
+  Related Spec: <https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity>
+
+Thank you, [@frumioj](https://github.com/frumioj), [@cjbarth](https://github.com/cjbarth), [@markgollnick](https://github.com/markgollnick) for your contributions
+
+
 ## [0.8.3](https://github.com/xmldom/xmldom/compare/0.8.3...0.8.2)
 
 ### Fixed

package/lib/conventions.js

@@ -1,5 +1,37 @@
 '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.
+ *
+ * @template {unknown} T
+ * @param {Array<T> | ({length:number, [number]: T})} list
+ * @param {function (item: T, index: number, list:Array<T> | ({length:number, [number]: T})):boolean} predicate
+ * @param {Partial<Pick<ArrayConstructor['prototype'], 'find'>>?} ac `Array.prototype` by default,
+ * 				allows injecting a custom implementation in tests
+ * @returns {T | undefined}
+ *
+ * @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
+ */
+function find(list, predicate, ac) {
+	if (ac === undefined) {
+		ac = Array.prototype;
+	}
+	if (list && typeof ac.find === 'function') {
+		return ac.find.call(list, predicate);
+	}
+	for (var i = 0; i < list.length; i++) {
+		if (Object.prototype.hasOwnProperty.call(list, i)) {
+			var item = list[i];
+			if (predicate.call(undefined, item, i, list)) {
+				return item;
+			}
+		}
+	}
+}
+
 /**
  * "Shallow freezes" an object to render it immutable.
  * Uses `Object.freeze` if available,
@@ -165,6 +197,7 @@ var NAMESPACE = freeze({
 })
 
 exports.assign = assign;
+exports.find = find;
 exports.freeze = freeze;
 exports.MIME_TYPE = MIME_TYPE;
 exports.NAMESPACE = NAMESPACE;

package/lib/dom.js

@@ -1,5 +1,6 @@
 var conventions = require("./conventions");
 
+var find = conventions.find;
 var NAMESPACE = conventions.NAMESPACE;
 
 /**
@@ -158,14 +159,14 @@ NodeList.prototype = {
 	 * The number of nodes in the list. The range of valid child node indices is 0 to length-1 inclusive.
 	 * @standard level1
 	 */
-	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 
+	 * @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. 
+	 * 	The node at the indexth position in the NodeList, or null if that is not a valid index.
 	 */
 	item: function(index) {
 		return this[index] || null;
@@ -175,7 +176,23 @@ NodeList.prototype = {
 			serializeToString(this[i],buf,isHTML,nodeFilter);
 		}
 		return buf.join('');
-	}
+	},
+	/**
+	 * @private
+	 * @param {function (Node):boolean} predicate
+	 * @returns {Node[]}
+	 */
+	filter: function (predicate) {
+		return Array.prototype.filter.call(this, predicate);
+	},
+	/**
+	 * @private
+	 * @param {Node} item
+	 * @returns {number}
+	 */
+	indexOf: function (item) {
+		return Array.prototype.indexOf.call(this, item);
+	},
 };
 
 function LiveNodeList(node,refresh){
@@ -209,7 +226,7 @@ _extends(LiveNodeList,NodeList);
  * but this is simply to allow convenient enumeration of the contents of a NamedNodeMap,
  * and does not imply that the DOM specifies an order to these Nodes.
  * NamedNodeMap objects in the DOM are live.
- * used for attributes or DocumentType entities 
+ * used for attributes or DocumentType entities
  */
 function NamedNodeMap() {
 };
@@ -253,7 +270,7 @@ function _removeNamedNode(el,list,attr){
 			}
 		}
 	}else{
-		throw DOMException(NOT_FOUND_ERR,new Error(el.tagName+'@'+attr))
+		throw new DOMException(NOT_FOUND_ERR,new Error(el.tagName+'@'+attr))
 	}
 }
 NamedNodeMap.prototype = {
@@ -298,10 +315,10 @@ NamedNodeMap.prototype = {
 		var attr = this.getNamedItem(key);
 		_removeNamedNode(this._ownerElement,this,attr);
 		return attr;
-		
-		
+
+
 	},// raises: NOT_FOUND_ERR,NO_MODIFICATION_ALLOWED_ERR
-	
+
 	//for level2
 	removeNamedItemNS:function(namespaceURI,localName){
 		var attr = this.getNamedItemNS(namespaceURI,localName);
@@ -447,10 +464,10 @@ Node.prototype = {
 	prefix : null,
 	localName : null,
 	// Modified in DOM Level 2:
-	insertBefore:function(newChild, refChild){//raises 
+	insertBefore:function(newChild, refChild){//raises
 		return _insertBefore(this,newChild,refChild);
 	},
-	replaceChild:function(newChild, oldChild){//raises 
+	replaceChild:function(newChild, oldChild){//raises
 		this.insertBefore(newChild,oldChild);
 		if(oldChild){
 			this.removeChild(oldChild);
@@ -656,48 +673,177 @@ function _removeChild (parentNode, child) {
 	_onUpdateChild(parentNode.ownerDocument, parentNode);
 	return child;
 }
+
+/**
+ * Returns `true` if `node` can be a parent for insertion.
+ * @param {Node} node
+ * @returns {boolean}
+ */
+function hasValidParentNodeType(node) {
+	return (
+		node &&
+		(node.nodeType === Node.DOCUMENT_NODE || node.nodeType === Node.DOCUMENT_FRAGMENT_NODE || node.nodeType === Node.ELEMENT_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.COMMENT_NODE ||
+			node.nodeType === Node.PROCESSING_INSTRUCTION_NODE)
+	);
+}
+
+/**
+ * Returns true if `node` is a DOCTYPE node
+ * @param {Node} node
+ * @returns {boolean}
+ */
+function isDocTypeNode(node) {
+	return node && node.nodeType === Node.DOCUMENT_TYPE_NODE;
+}
+
 /**
- * preformance key(refChild == null)
+ * Returns true if the node is an element
+ * @param {Node} node
+ * @returns {boolean}
  */
-function _insertBefore(parentNode,newChild,nextChild){
-	var cp = newChild.parentNode;
+function isElementNode(node) {
+	return node && node.nodeType === Node.ELEMENT_NODE;
+}
+/**
+ * Returns true if `node` is a text node
+ * @param {Node} node
+ * @returns {boolean}
+ */
+function isTextNode(node) {
+	return node && node.nodeType === Node.TEXT_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
+ * @private
+ * https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity
+ */
+function isElementInsertionPossible(doc, child) {
+	var parentChildNodes = doc.childNodes || [];
+	if (find(parentChildNodes, isElementNode) || isDocTypeNode(child)) {
+		return false;
+	}
+	var docTypeNode = find(parentChildNodes, isDocTypeNode);
+	return !(child && docTypeNode && parentChildNodes.indexOf(docTypeNode) > parentChildNodes.indexOf(child));
+}
+/**
+ * @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`
+ * @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`.
+ * @see https://dom.spec.whatwg.org/#concept-node-ensure-pre-insertion-validity
+ */
+function _insertBefore(parent, node, child) {
+	if (!hasValidParentNodeType(parent)) {
+		throw new DOMException(HIERARCHY_REQUEST_ERR, 'Unexpected parent node type ' + parent.nodeType);
+	}
+	if (child && child.parentNode !== parent) {
+		throw new DOMException(NOT_FOUND_ERR, 'child not in parent');
+	}
+	if (
+		!hasInsertableNodeType(node) ||
+		// the sax parser currently adds top level text nodes, this will be fixed in 0.9.0
+		// || (node.nodeType === Node.TEXT_NODE && parent.nodeType === Node.DOCUMENT_NODE)
+		(isDocTypeNode(node) && parent.nodeType !== Node.DOCUMENT_NODE)
+	) {
+		throw new DOMException(
+			HIERARCHY_REQUEST_ERR,
+			'Unexpected node type ' + node.nodeType + ' for parent node type ' + parent.nodeType
+		);
+	}
+	var parentChildNodes = parent.childNodes || [];
+	var nodeChildNodes = node.childNodes || [];
+	if (parent.nodeType === Node.DOCUMENT_NODE) {
+		if (node.nodeType === Node.DOCUMENT_FRAGMENT_NODE) {
+			var nodeChildElements = nodeChildNodes.filter(isElementNode);
+			if (nodeChildElements.length > 1 || find(nodeChildNodes, isTextNode)) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'More than one element or text in fragment');
+			}
+			if (nodeChildElements.length === 1 && !isElementInsertionPossible(parent, child)) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'Element in fragment can not be inserted before doctype');
+			}
+		}
+		if (isElementNode(node)) {
+			if (find(parentChildNodes, isElementNode) || !isElementInsertionPossible(parent, child)) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one element can be added and only after doctype');
+			}
+		}
+		if (isDocTypeNode(node)) {
+			if (find(parentChildNodes, isDocTypeNode)) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'Only one doctype is allowed');
+			}
+			var parentElementChild = find(parentChildNodes, isElementNode);
+			if (child && parentChildNodes.indexOf(parentElementChild) < parentChildNodes.indexOf(child)) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'Doctype can only be inserted before an element');
+			}
+			if (!child && parentElementChild) {
+				throw new DOMException(HIERARCHY_REQUEST_ERR, 'Doctype can not be appended since element is present');
+			}
+		}
+	}
+
+	var cp = node.parentNode;
 	if(cp){
-		cp.removeChild(newChild);//remove and update
+		cp.removeChild(node);//remove and update
 	}
-	if(newChild.nodeType === DOCUMENT_FRAGMENT_NODE){
-		var newFirst = newChild.firstChild;
+	if(node.nodeType === DOCUMENT_FRAGMENT_NODE){
+		var newFirst = node.firstChild;
 		if (newFirst == null) {
-			return newChild;
+			return node;
 		}
-		var newLast = newChild.lastChild;
+		var newLast = node.lastChild;
 	}else{
-		newFirst = newLast = newChild;
+		newFirst = newLast = node;
 	}
-	var pre = nextChild ? nextChild.previousSibling : parentNode.lastChild;
+	var pre = child ? child.previousSibling : parent.lastChild;
 
 	newFirst.previousSibling = pre;
-	newLast.nextSibling = nextChild;
-	
-	
+	newLast.nextSibling = child;
+
+
 	if(pre){
 		pre.nextSibling = newFirst;
 	}else{
-		parentNode.firstChild = newFirst;
+		parent.firstChild = newFirst;
 	}
-	if(nextChild == null){
-		parentNode.lastChild = newLast;
+	if(child == null){
+		parent.lastChild = newLast;
 	}else{
-		nextChild.previousSibling = newLast;
+		child.previousSibling = newLast;
 	}
 	do{
-		newFirst.parentNode = parentNode;
+		newFirst.parentNode = parent;
 	}while(newFirst !== newLast && (newFirst= newFirst.nextSibling))
-	_onUpdateChild(parentNode.ownerDocument||parentNode,parentNode);
-	//console.log(parentNode.lastChild.nextSibling == null)
-	if (newChild.nodeType == DOCUMENT_FRAGMENT_NODE) {
-		newChild.firstChild = newChild.lastChild = null;
+	_onUpdateChild(parent.ownerDocument||parent, parent);
+	//console.log(parent.lastChild.nextSibling == null)
+	if (node.nodeType == DOCUMENT_FRAGMENT_NODE) {
+		node.firstChild = node.lastChild = null;
 	}
-	return newChild;
+	return node;
 }
 
 /**
@@ -752,11 +898,13 @@ Document.prototype = {
 			}
 			return newChild;
 		}
-		if(this.documentElement == null && newChild.nodeType == ELEMENT_NODE){
+		_insertBefore(this, newChild, refChild);
+		newChild.ownerDocument = this;
+		if (this.documentElement === null && newChild.nodeType === ELEMENT_NODE) {
 			this.documentElement = newChild;
 		}
 
-		return _insertBefore(this,newChild,refChild),(newChild.ownerDocument = this),newChild;
+		return newChild;
 	},
 	removeChild :  function(oldChild){
 		if(this.documentElement == oldChild){
@@ -950,7 +1098,7 @@ Element.prototype = {
 		var attr = this.getAttributeNode(name)
 		attr && this.removeAttributeNode(attr);
 	},
-	
+
 	//four real opeartion method
 	appendChild:function(newChild){
 		if(newChild.nodeType === DOCUMENT_FRAGMENT_NODE){
@@ -974,7 +1122,7 @@ Element.prototype = {
 		var old = this.getAttributeNodeNS(namespaceURI, localName);
 		old && this.removeAttributeNode(old);
 	},
-	
+
 	hasAttributeNS : function(namespaceURI, localName){
 		return this.getAttributeNodeNS(namespaceURI, localName)!=null;
 	},
@@ -990,7 +1138,7 @@ Element.prototype = {
 	getAttributeNodeNS : function(namespaceURI, localName){
 		return this.attributes.getNamedItemNS(namespaceURI, localName);
 	},
-	
+
 	getElementsByTagName : function(tagName){
 		return new LiveNodeList(this,function(base){
 			var ls = [];
@@ -1011,7 +1159,7 @@ Element.prototype = {
 				}
 			});
 			return ls;
-			
+
 		});
 	}
 };
@@ -1040,7 +1188,7 @@ CharacterData.prototype = {
 	},
 	insertData: function(offset,text) {
 		this.replaceData(offset,0,text);
-	
+
 	},
 	appendChild:function(newChild){
 		throw new Error(ExceptionMessage[HIERARCHY_REQUEST_ERR])
@@ -1134,7 +1282,7 @@ function nodeSerializeToString(isHtml,nodeFilter){
 	var refNode = this.nodeType == 9 && this.documentElement || this;
 	var prefix = refNode.prefix;
 	var uri = refNode.namespaceURI;
-	
+
 	if(uri && prefix == null){
 		//console.log(prefix)
 		var prefix = refNode.lookupPrefix(uri);
@@ -1167,8 +1315,8 @@ function needNamespaceDefine(node, isHTML, visibleNamespaces) {
 	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
@@ -1219,7 +1367,7 @@ function serializeToString(node,buf,isHTML,nodeFilter,visibleNamespaces){
 		var len = attrs.length;
 		var child = node.firstChild;
 		var nodeName = node.tagName;
-		
+
 		isHTML = NAMESPACE.isHTML(node.namespaceURI) || isHTML
 
 		var prefixedNodeName = nodeName
@@ -1278,14 +1426,14 @@ function serializeToString(node,buf,isHTML,nodeFilter,visibleNamespaces){
 			serializeToString(attr,buf,isHTML,nodeFilter,visibleNamespaces);
 		}
 
-		// add namespace for current node		
+		// 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 });
 		}
-		
+
 		if(child || isHTML && !/^(?:meta|link|img|br|hr|input)$/i.test(nodeName)){
 			buf.push('>');
 			//if is cdata child node
@@ -1500,7 +1648,7 @@ try{
 				}
 			}
 		})
-		
+
 		function getTextContent(node){
 			switch(node.nodeType){
 			case ELEMENT_NODE:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xmldom/xmldom",
-  "version": "0.8.3",
+  "version": "0.8.5",
   "description": "A pure JavaScript W3C standard-based (XML DOM Level 2 Core) DOMParser and XMLSerializer module.",
   "keywords": [
     "w3c",
@@ -29,13 +29,15 @@
   ],
   "scripts": {
     "lint": "eslint lib test",
+    "format": "prettier --write test",
     "changelog": "auto-changelog --unreleased-only",
     "start": "nodemon --watch package.json --watch lib --watch test --exec 'npm --silent run test && npm --silent run lint'",
     "stryker": "stryker run",
     "stryker:dry-run": "stryker run -m '' --reporters progress",
     "test": "jest",
+    "testrelease": "npm test && npm run lint",
     "version": "./changelog-has-version.sh",
-    "release": "np --no-yarn"
+    "release": "np --no-yarn --test-script testrelease"
   },
   "engines": {
     "node": ">=10.0.0"