@xmldom/xmldom 0.7.5 → 0.8.0

package/CHANGELOG.md

@@ -4,6 +4,27 @@ 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).
 
+## [0.8.0](https://github.com/xmldom/xmldom/compare/0.7.5...0.8.0)
+
+### Fixed
+- Normalize all line endings according to XML specs [1.0](https://w3.org/TR/xml/#sec-line-ends) and [1.1](https://www.w3.org/TR/xml11/#sec-line-ends) \
+  BREAKING CHANGE: Certain combination of line break characters are normalized to a single `\n` before parsing takes place and will no longer be preserved.
+  - [`#303`](https://github.com/xmldom/xmldom/issues/303) / [`#307`](https://github.com/xmldom/xmldom/pull/307)
+  - [`#49`](https://github.com/xmldom/xmldom/issues/49), [`#97`](https://github.com/xmldom/xmldom/issues/97), [`#324`](https://github.com/xmldom/xmldom/issues/324) / [`#314`](https://github.com/xmldom/xmldom/pull/314)
+- XMLSerializer: Preserve whitespace character references [`#284`](https://github.com/xmldom/xmldom/issues/284) / [`#310`](https://github.com/xmldom/xmldom/pull/310) \
+  BREAKING CHANGE: If you relied on the not spec compliant preservation of literal `\t`, `\n` or `\r` in **attribute values**.
+  To preserve those you will have to create XML that instead contains the correct numerical (or hexadecimal) equivalent (e.g. `	`, `
`, `
`).
+- Drop deprecated exports `DOMImplementation` and `XMLSerializer` from `lib/dom-parser.js` [#53](https://github.com/xmldom/xmldom/issues/53) / [`#309`](https://github.com/xmldom/xmldom/pull/309)
+  BREAKING CHANGE: Use the one provided by the main package export.
+- dom: Remove all links as part of `removeChild` [`#343`](https://github.com/xmldom/xmldom/issues/343) / [`#355`](https://github.com/xmldom/xmldom/pull/355)
+
+### Chore
+- ci: Restore latest tested node version to 16.x [`#325`](https://github.com/xmldom/xmldom/pull/325)
+- ci: Split test and lint steps into jobs [`#111`](https://github.com/xmldom/xmldom/issues/111) / [`#304`](https://github.com/xmldom/xmldom/pull/304)
+- Pinned and updated devDependencies
+
+Thank you [@marrus-sh](https://github.com/marrus-sh), [@victorandree](https://github.com/victorandree), [@mdierolf](https://github.com/mdierolf), [@tsabbay](https://github.com/tsabbay), [@fatihpense](https://github.com/fatihpense) for your contributions
+
 ## 0.7.5
 
 [Commits](https://github.com/xmldom/xmldom/compare/0.7.4...0.7.5)

package/lib/dom-parser.js

@@ -10,6 +10,64 @@ var NAMESPACE = conventions.NAMESPACE;
 var ParseError = sax.ParseError;
 var XMLReader = sax.XMLReader;
 
+/**
+ * Normalizes line ending according to https://www.w3.org/TR/xml11/#sec-line-ends:
+ *
+ * > XML parsed entities are often stored in computer files which,
+ * > for editing convenience, are organized into lines.
+ * > These lines are typically separated by some combination
+ * > of the characters CARRIAGE RETURN (#xD) and LINE FEED (#xA).
+ * >
+ * > To simplify the tasks of applications, the XML processor must behave
+ * > as if it normalized all line breaks in external parsed entities (including the document entity)
+ * > on input, before parsing, by translating all of 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.
+ *
+ * @param {string} input
+ * @returns {string}
+ */
+function normalizeLineEndings(input) {
+	return input
+		.replace(/\r[\n\u0085]/g, '\n')
+		.replace(/[\r\u0085\u2028]/g, '\n')
+}
+
+/**
+ * @typedef Locator
+ * @property {number} [columnNumber]
+ * @property {number} [lineNumber]
+ */
+
+/**
+ * @typedef DOMParserOptions
+ * @property {DOMHandler} [domBuilder]
+ * @property {Function} [errorHandler]
+ * @property {(string) => string} [normalizeLineEndings] used to replace line endings before parsing
+ * 						defaults to `normalizeLineEndings`
+ * @property {Locator} [locator]
+ * @property {Record<string, string>} [xmlns]
+ *
+ * @see normalizeLineEndings
+ */
+
+/**
+ * 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._
+ *
+ * @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:{}};
 }
@@ -33,10 +91,15 @@ DOMParser.prototype.parseFromString = function(source,mimeType){
 		defaultNSMap[''] = NAMESPACE.HTML;
 	}
 	defaultNSMap.xml = defaultNSMap.xml || NAMESPACE.XML;
-	if(source && typeof source === 'string'){
-		sax.parse(source,defaultNSMap,entityMap);
-	}else{
-		sax.errorHandler.error("invalid doc source");
+	var normalize = options.normalizeLineEndings || normalizeLineEndings;
+	if (source && typeof source === 'string') {
+		sax.parse(
+			normalize(source),
+			defaultNSMap,
+			entityMap
+		)
+	} else {
+		sax.errorHandler.error('invalid doc source')
 	}
 	return domBuilder.doc;
 }
@@ -255,14 +318,5 @@ function appendElement (hander,node) {
 }//appendChild and setAttributeNS are preformance key
 
 exports.__DOMHandler = DOMHandler;
+exports.normalizeLineEndings = normalizeLineEndings;
 exports.DOMParser = DOMParser;
-
-/**
- * @deprecated Import/require from main entry point instead
- */
-exports.DOMImplementation = dom.DOMImplementation;
-
-/**
- * @deprecated Import/require from main entry point instead
- */
-exports.XMLSerializer = dom.XMLSerializer;

package/lib/dom.js

@@ -591,48 +591,67 @@ function _onRemoveAttribute(doc,el,newAttr,remove){
 	}
 }
 
-function _onUpdateChild(doc,el,newChild){
+/**
+ * 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.
+ *
+ * @param {Document} doc
+ * @param {Node} el
+ * @param {Node} [newChild]
+ * @private
+ */
+function _onUpdateChild (doc, el, newChild) {
 	if(doc && doc._inc){
 		doc._inc++;
 		//update childNodes
 		var cs = el.childNodes;
-		if(newChild){
+		if (newChild) {
 			cs[cs.length++] = newChild;
-		}else{
-			//console.log(1)
+		} else {
 			var child = el.firstChild;
 			var i = 0;
-			while(child){
+			while (child) {
 				cs[i++] = child;
-				child =child.nextSibling;
+				child = child.nextSibling;
 			}
 			cs.length = i;
+			delete cs[cs.length];
 		}
 	}
 }
 
 /**
- * attributes;
- * children;
- * 
- * writeable properties:
- * nodeValue,Attr:value,CharacterData:data
- * prefix
+ * 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
+ * @param {Node} child
+ * @returns {Node} the child that was removed.
+ * @private
  */
-function _removeChild(parentNode,child){
+function _removeChild (parentNode, child) {
 	var previous = child.previousSibling;
 	var next = child.nextSibling;
-	if(previous){
+	if (previous) {
 		previous.nextSibling = next;
-	}else{
-		parentNode.firstChild = next
+	} else {
+		parentNode.firstChild = next;
 	}
-	if(next){
+	if (next) {
 		next.previousSibling = previous;
-	}else{
+	} else {
 		parentNode.lastChild = previous;
 	}
-	_onUpdateChild(parentNode.ownerDocument,parentNode);
+	child.parentNode = null;
+	child.previousSibling = null;
+	child.nextSibling = null;
+	_onUpdateChild(parentNode.ownerDocument, parentNode);
 	return child;
 }
 /**
@@ -678,27 +697,35 @@ function _insertBefore(parentNode,newChild,nextChild){
 	}
 	return newChild;
 }
-function _appendSingleChild(parentNode,newChild){
-	var cp = newChild.parentNode;
-	if(cp){
-		var pre = parentNode.lastChild;
-		cp.removeChild(newChild);//remove and update
-		var pre = parentNode.lastChild;
+
+/**
+ * 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);
 	}
-	var pre = parentNode.lastChild;
 	newChild.parentNode = parentNode;
-	newChild.previousSibling = pre;
+	newChild.previousSibling = parentNode.lastChild;
 	newChild.nextSibling = null;
-	if(pre){
-		pre.nextSibling = newChild;
-	}else{
+	if (newChild.previousSibling) {
+		newChild.previousSibling.nextSibling = newChild;
+	} else {
 		parentNode.firstChild = newChild;
 	}
 	parentNode.lastChild = newChild;
-	_onUpdateChild(parentNode.ownerDocument,parentNode,newChild);
+	_onUpdateChild(parentNode.ownerDocument, parentNode, newChild);
 	return newChild;
-	//console.log("__aa",parentNode.lastChild.nextSibling == null)
 }
+
 Document.prototype = {
 	//implementation : null,
 	nodeName :  '#document',
@@ -1151,12 +1178,18 @@ function needNamespaceDefine(node, isHTML, visibleNamespaces) {
 }
 /**
  * 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/xml/#CleanAttrVals
- * @see https://www.w3.org/TR/xml/#NT-AttValue
+ * > 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
  */
 function addSerializedAttribute(buf, qualifiedName, value) {
-	buf.push(' ', qualifiedName, '="', value.replace(/[<&"]/g,_xmlEncoder), '"')
+	buf.push(' ', qualifiedName, '="', value.replace(/[<&"\t\n\r]/g, _xmlEncoder), '"')
 }
 
 function serializeToString(node,buf,isHTML,nodeFilter,visibleNamespaces){

package/lib/sax.js

@@ -233,7 +233,15 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error
 		if (el.attributeNames.hasOwnProperty(qname)) {
 			errorHandler.fatalError('Attribute ' + qname + ' redefined')
 		}
-		el.addValue(qname, value, startIndex)
+		el.addValue(
+			qname,
+			// @see https://www.w3.org/TR/xml/#AVNormalize
+			// 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),
+			startIndex
+		)
 	}
 	var attrName;
 	var value;
@@ -264,7 +272,7 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error
 				start = p+1;
 				p = source.indexOf(c,start)
 				if(p>0){
-					value = source.slice(start,p).replace(/&#?\w+;/g,entityReplacer);
+					value = source.slice(start, p);
 					addAttribute(attrName, value, start-1);
 					s = S_ATTR_END;
 				}else{
@@ -272,10 +280,8 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error
 					throw new Error('attribute value no end \''+c+'\' match');
 				}
 			}else if(s == S_ATTR_NOQUOT_VALUE){
-				value = source.slice(start,p).replace(/&#?\w+;/g,entityReplacer);
-				//console.log(attrName,value,start,p)
+				value = source.slice(start, p);
 				addAttribute(attrName, value, start);
-				//console.dir(el)
 				errorHandler.warning('attribute "'+attrName+'" missed start quot('+c+')!!');
 				start = p+1;
 				s = S_ATTR_END
@@ -329,7 +335,7 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error
 				}
 				if(s == S_ATTR_NOQUOT_VALUE){
 					errorHandler.warning('attribute "'+value+'" missed quot(")!');
-					addAttribute(attrName, value.replace(/&#?\w+;/g,entityReplacer), start)
+					addAttribute(attrName, value, start)
 				}else{
 					if(!NAMESPACE.isHTML(currentNSMap['']) || !value.match(/^(?:disabled|checked|selected)$/i)){
 						errorHandler.warning('attribute "'+value+'" missed value!! "'+value+'" instead!!')
@@ -357,7 +363,7 @@ function parseElementStartPart(source,start,el,currentNSMap,entityReplacer,error
 					s = S_ATTR_SPACE;
 					break;
 				case S_ATTR_NOQUOT_VALUE:
-					var value = source.slice(start,p).replace(/&#?\w+;/g,entityReplacer);
+					var value = source.slice(start, p);
 					errorHandler.warning('attribute "'+value+'" missed quot(")!!');
 					addAttribute(attrName, value, start)
 				case S_ATTR_END:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xmldom/xmldom",
-  "version": "0.7.5",
+  "version": "0.8.0",
   "description": "A pure JavaScript W3C standard-based (XML DOM Level 2 Core) DOMParser and XMLSerializer module.",
   "keywords": [
     "w3c",
@@ -38,17 +38,17 @@
   },
   "dependencies": {},
   "devDependencies": {
-    "@stryker-mutator/core": "^5.2.2",
-    "eslint": "^7.32.0",
-    "eslint-config-prettier": "^8.3.0",
-    "eslint-plugin-es5": "^1.5.0",
-    "eslint-plugin-prettier": "^3.4.1",
-    "get-stream": "^6.0.1",
-    "jest": "^27.0.6",
-    "nodemon": "^2.0.12",
-    "prettier": "^2.3.2",
-    "xmltest": "^1.5.0",
-    "yauzl": "^2.10.0"
+    "@stryker-mutator/core": "5.5.1",
+    "eslint": "8.5.0",
+    "eslint-config-prettier": "8.3.0",
+    "eslint-plugin-es5": "1.5.0",
+    "eslint-plugin-prettier": "4.0.0",
+    "get-stream": "6.0.1",
+    "jest": "27.4.5",
+    "nodemon": "2.0.15",
+    "prettier": "2.5.1",
+    "xmltest": "1.5.0",
+    "yauzl": "2.10.0"
   },
   "bugs": {
     "url": "https://github.com/xmldom/xmldom/issues"