Upgrade parse5 to v3.0.2

Fixes #1778. This changes the public API in that the nodeLocation() functions now return differently-structured objects. parse5 has also removed support for serialization of obsolete doctypes. #1316 is a more ambitious attempt to use parse5's new streaming interface to get correct script execution semantics, but is still not ready; this is just a minimal upgrade to the latest parse5 version.
jsdom · May 14, 2017 · 29c4a7b · 29c4a7b
1 parent e1dba03
commit 29c4a7b
Show file tree

Hide file tree

Showing 8 changed files with 57 additions and 71 deletions.
diff --git a/README.md b/README.md
@@ -223,9 +223,9 @@ const textNode = pEl.firstChild;
 const imgEl = document.querySelector("img");
 
 console.log(dom.nodeLocation(bodyEl));   // null; it's not in the source
-console.log(dom.nodeLocation(pEl));      // { start: 0, end: 39, startTag: ..., endTag: ... }
-console.log(dom.nodeLocation(textNode)); // { start: 3, end: 13 }
-console.log(dom.nodeLocation(imgEl));    // { start: 13, end: 32 }
+console.log(dom.nodeLocation(pEl));      // { startOffset: 0, endOffset: 39, startTag: ..., endTag: ... }
+console.log(dom.nodeLocation(textNode)); // { startOffset: 3, endOffset: 13 }
+console.log(dom.nodeLocation(imgEl));    // { startOffset: 13, endOffset: 32 }
 ```
 
 Note that this feature only works if you have set the `includeNodeLocations` option; node locations are off by default for performance reasons.

diff --git a/lib/jsdom/browser/documentAdapter.js b/lib/jsdom/browser/documentAdapter.js
@@ -1,21 +1,12 @@
 "use strict";
 
-const idlUtils = require("../living/generated/utils");
-
 // Tree traversing
 exports.getFirstChild = function (node) {
   return node.childNodes[0];
 };
 
 exports.getChildNodes = function (node) {
-  // parse5 treats template elements specially, assuming you return an array whose single item is the document fragment
-  const children = node._templateContents ? [node._templateContents] : [];
-  if (children.length === 0) {
-    for (let i = 0; i < node.childNodes.length; ++i) {
-      children.push(idlUtils.implForWrapper(node.childNodes[i]));
-    }
-  }
-  return children;
+  return node.childNodes;
 };
 
 exports.getParentNode = function (node) {
@@ -35,6 +26,10 @@ exports.getNamespaceURI = function (element) {
   return element.namespaceURI || "http://www.w3.org/1999/xhtml";
 };
 
+exports.getTemplateContent = function (node) {
+  return node.content;
+};
+
 exports.getTextNodeContent = function (textNode) {
   return textNode.nodeValue;
 };

diff --git a/lib/jsdom/browser/domtohtml.js b/lib/jsdom/browser/domtohtml.js
@@ -4,15 +4,17 @@ const documentAdapter = require("./documentAdapter");
 const NODE_TYPE = require("../living/node-type");
 const idlUtils = require("../living/generated/utils");
 
-const serializer = new parse5.TreeSerializer(documentAdapter);
-
 exports.domToHtml = function (iterable) {
   let ret = "";
   for (const node of iterable) {
     if (node.nodeType === NODE_TYPE.DOCUMENT_NODE) {
-      ret += serializer.serialize(node);
+      ret += parse5.serialize(node, {
+        treeAdapter: documentAdapter
+      });
     } else {
-      ret += serializer.serialize({ childNodes: [idlUtils.wrapperForImpl(node)] });
+      ret += parse5.serialize({ childNodes: [idlUtils.wrapperForImpl(node)] }, {
+        treeAdapter: documentAdapter
+      });
     }
   }
   return ret;

diff --git a/lib/jsdom/browser/htmltodom.js b/lib/jsdom/browser/htmltodom.js
@@ -22,8 +22,8 @@ class HtmlToDom {
 
     if (parser.DefaultHandler) {
       this.parserType = "htmlparser2";
-    } else if (parser.Parser && parser.TreeAdapters) {
-      this.parserType = "parse5v1";
+    } else if (parser.parse && parser.treeAdapters) {
+      this.parserType = "parse5";
     } else if (parser.moduleName === "HTML5") {
       this.parserType = "html5";
     } else if (parser.parser) {
@@ -70,20 +70,24 @@ class HtmlToDom {
     return element;
   }
 
-  _parseWithparse5v1(html, fragment, element, options) {
+  _parseWithparse5(html, fragment, element, options = {}) {
     if (this.parsingMode === "xml") {
       throw new Error("Can't parse XML with parse5, please use htmlparser2 instead.");
     }
 
-    const htmlparser2Adapter = this.parser.TreeAdapters.htmlparser2;
+    const htmlparser2Adapter = parse5.treeAdapters.htmlparser2;
+
     let dom;
     if (fragment) {
-      const instance = new this.parser.Parser(htmlparser2Adapter);
-      const parentElement = htmlparser2Adapter.createElement(element.tagName.toLowerCase(), element.namespaceURI, []);
-      dom = instance.parseFragment(html, parentElement);
+      const parentElement = htmlparser2Adapter.createElement(
+        element.tagName.toLowerCase(), element.namespaceURI, []
+      );
+
+      options.treeAdapter = htmlparser2Adapter;
+      dom = this.parser.parseFragment(parentElement, html, options);
     } else {
-      const instance = new this.parser.Parser(htmlparser2Adapter, options);
-      dom = instance.parse(html);
+      options.treeAdapter = htmlparser2Adapter;
+      dom = this.parser.parse(html, options);
     }
 
     const parsed = dom.children;

diff --git a/lib/old-api.md b/lib/old-api.md
@@ -533,9 +533,9 @@ var textNode = pEl.firstChild;
 var imgEl = document.querySelector("img");
 
 console.log(jsdom.nodeLocation(bodyEl));   // null; it's not in the source
-console.log(jsdom.nodeLocation(pEl));      // { start: 0, end: 39, startTag: ..., endTag: ... }
-console.log(jsdom.nodeLocation(textNode)); // { start: 3, end: 13 }
-console.log(jsdom.nodeLocation(imgEl));    // { start: 13, end: 32 }
+console.log(jsdom.nodeLocation(pEl));      // { startOffset: 0, endOffset: 39, startTag: ..., endTag: ... }
+console.log(jsdom.nodeLocation(textNode)); // { startOffset: 3, endOffset: 13 }
+console.log(jsdom.nodeLocation(imgEl));    // { startOffset: 13, endOffset: 32 }
 ```
 
 This returns the [parse5 location info](https://www.npmjs.com/package/parse5#options-locationinfo) for the node.

diff --git a/package.json b/package.json
@@ -27,7 +27,7 @@
     "escodegen": "^1.6.1",
     "html-encoding-sniffer": "^1.0.1",
     "nwmatcher": ">= 1.3.9 < 2.0.0",
-    "parse5": "^1.5.1",
+    "parse5": "^3.0.2",
     "pn": "^1.0.0",
     "request": "^2.79.0",
     "request-promise-native": "^1.0.3",

diff --git a/test/api/methods.js b/test/api/methods.js
@@ -63,18 +63,25 @@ describe("API: JSDOM class's methods", () => {
       const node = dom.window.document.querySelector("p");
 
       assert.deepEqual(dom.nodeLocation(node), {
-        start: 0,
-        end: 12,
-        startTag: { start: 0, end: 3 },
-        endTag: { start: 8, end: 12 }
+        line: 1,
+        col: 1,
+        startOffset: 0,
+        endOffset: 12,
+        startTag: { line: 1, col: 1, startOffset: 0, endOffset: 3 },
+        endTag: { line: 1, col: 9, startOffset: 8, endOffset: 12 }
       });
     });
 
     it("should give the correct location for a text node", () => {
       const dom = new JSDOM(`<p>Hello</p>`, { includeNodeLocations: true });
       const node = dom.window.document.querySelector("p").firstChild;
 
-      assert.deepEqual(dom.nodeLocation(node), { start: 3, end: 8 });
+      assert.deepEqual(dom.nodeLocation(node), {
+        line: 1,
+        col: 4,
+        startOffset: 3,
+        endOffset: 8
+      });
     });
 
     it("should give the correct location for a void element", () => {
@@ -83,7 +90,20 @@ describe("API: JSDOM class's methods", () => {
       </p>`, { includeNodeLocations: true });
       const node = dom.window.document.querySelector("img");
 
-      assert.deepEqual(dom.nodeLocation(node), { start: 17, end: 36 });
+      assert.deepEqual(dom.nodeLocation(node), {
+        attrs: {
+          src: {
+            line: 2,
+            col: 14,
+            startOffset: 22,
+            endOffset: 35
+          }
+        },
+        line: 2,
+        col: 9,
+        startOffset: 17,
+        endOffset: 36
+      });
     });
   });
 

diff --git a/test/to-port-to-wpts/misc.js b/test/to-port-to-wpts/misc.js
@@ -165,41 +165,6 @@ describe("browser/index", () => {
     assert.ok(regexp.test(serializeDocument(document)), "HTML 5 doctype did not serialize correctly");
   });
 
-  specify("serialize_html4_strict_doctype", () => {
-    const doc = jsdom.jsdom();
-    const dom = doc.implementation;
-
-    const doctype = dom.createDocumentType(
-      "html",
-      "-//W3C//DTD HTML 4.01//EN",
-      "http://www.w3.org/TR/html4/strict.dtd"
-    );
-    const document = dom.createDocument(null, null, doctype);
-    const regexp =
-      /^\s*<!DOCTYPE html PUBLIC "-\/\/W3C\/\/DTD HTML 4.01\/\/EN" "http:\/\/www.w3.org\/TR\/html4\/strict.dtd">/;
-    assert.ok(regexp.test(serializeDocument(document)), "HTML 4 strict doctype did not serialize correctly");
-  });
-
-  specify("serialize_system_doctype", () => {
-    const doc = jsdom.jsdom();
-    const dom = doc.implementation;
-
-    const doctype = dom.createDocumentType("foo", "", "foo.dtd");
-    const document = dom.createDocument(null, null, doctype);
-    const regexp = /^\s*<!DOCTYPE foo SYSTEM "foo.dtd">/;
-    assert.ok(regexp.test(serializeDocument(document)), "Doctype did not serialize correctly");
-  });
-
-  specify("serialize_doctype_containing_quotes", () => {
-    const doc = jsdom.jsdom();
-    const dom = doc.implementation;
-
-    const doctype = dom.createDocumentType("foo", "", "foo \"bar\".dtd");
-    const document = dom.createDocument(null, null, doctype);
-    const regexp = /^\s*<!DOCTYPE foo SYSTEM 'foo "bar"\.dtd'>/;
-    assert.ok(regexp.test(serializeDocument(document)), "Doctype did not serialize correctly");
-  });
-
   specify("parse_doctype_containing_newline", () => {
     const html = `<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN"\n
              "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">\n<html></html>`;