node-html-parser 5.1.0 → 5.2.0

package/CHANGELOG.md

@@ -4,23 +4,9 @@ All notable changes to this project will be documented in this file. See [standa
 
 ## [5.1.0](https://github.com/taoqf/node-fast-html-parser/compare/v4.1.5...v5.1.0) (2021-10-28)
 
-
-### ⚠ BREAKING CHANGES
-
-* Add esm named export support (closes #160 closes #139)
-
 ### Features
 
-* Add esm named export support (closes [#160](https://github.com/taoqf/node-fast-html-parser/issues/160) closes [#139](https://github.com/taoqf/node-fast-html-parser/issues/139)) ([0d4b922](https://github.com/taoqf/node-fast-html-parser/commit/0d4b922eefd6210fe802991e464b21b0c69d5f63))
-* Added HTMLElement#getElementsByTagName ([d462e44](https://github.com/taoqf/node-fast-html-parser/commit/d462e449e7ebb00a5a43fb574133681ad5a62475))
-* Expose `HTMLElement#rawAttrs` (make public) ([34f1595](https://github.com/taoqf/node-fast-html-parser/commit/34f1595756c0974b6ae7ef5755a615f09e421f32))
-* Improved parsing performance + matching (closes [#164](https://github.com/taoqf/node-fast-html-parser/issues/164)) ([3c5b8e2](https://github.com/taoqf/node-fast-html-parser/commit/3c5b8e2a9104b01a8ca899a7970507463e42adaf))
-
-
-### Bug Fixes
-
-* Add null to return type for HTMLElement#querySelector (closes [#157](https://github.com/taoqf/node-fast-html-parser/issues/157)) ([2b65583](https://github.com/taoqf/node-fast-html-parser/commit/2b655839bd3868c41fb19cae5786ca097565bc7f))
-* blockTextElements incorrectly matching partial tag (detail) (fixes [#156](https://github.com/taoqf/node-fast-html-parser/issues/156) fixes [#124](https://github.com/taoqf/node-fast-html-parser/issues/124)) ([6823349](https://github.com/taoqf/node-fast-html-parser/commit/6823349fdf1809c7484c70d948aa24930ef4983f))
+* Exposed `HTMLElement#rawAttrs` (made public) ([34f1595](https://github.com/taoqf/node-fast-html-parser/commit/34f1595756c0974b6ae7ef5755a615f09e421f32))
 
 ## [5.0.0](https://github.com/taoqf/node-fast-html-parser/compare/v4.1.5...v5.0.0) (2021-10-10)
 

package/README.md

@@ -19,15 +19,18 @@ npm install --save node-html-parser
 
 ## Performance
 
-Faster than htmlparser2!
-
 ```shell
-htmlparser      :26.7111 ms/file ± 170.066
-cheerio         :24.2480 ms/file ± 17.1711
-parse5          :13.7239 ms/file ± 8.68561
-high5           :7.75466 ms/file ± 5.33549
-htmlparser2     :5.27376 ms/file ± 8.68456
-node-html-parser:2.85768 ms/file ± 2.87784
+cheerio         :12.0726 ms/file ± 7.31605
+parse5          :8.18615 ms/file ± 6.15337
+node-html-parser (last release):2.16533 ms/file ± 1.56924
+htmlparser      :17.0658 ms/file ± 120.901
+htmlparser2     :2.62695 ms/file ± 4.17579
+node-html-parser:2.14907 ms/file ± 1.66632
+html-parser     :24.6505 ms/file ± 18.9996
+htmljs-parser   :5.81797 ms/file ± 6.55537
+html-dom-parser :2.52265 ms/file ± 3.54858
+html5parser     :2.01144 ms/file ± 2.53570
+high5           :3.91342 ms/file ± 2.65563
 ```
 
 Tested with [htmlparser-benchmark](https://github.com/AndreasMadsen/htmlparser-benchmark).
@@ -70,15 +73,15 @@ var root = HTMLParser.parse('<ul id="list"><li>Hello World</li></ul>');
 
 ### parse(data[, options])
 
-Parse given data, and return root of the generated DOM.
+Parse the data provided, and return the root of the generated DOM.
 
 - **data**, data to parse
 - **options**, parse options
 
   ```js
   {
-    lowerCaseTagName: false,  // convert tag name to lower case (hurt performance heavily)
-    comment: false,            // retrieve comments (hurt performance slightly)
+    lowerCaseTagName: false,  // convert tag name to lower case (hurts performance heavily)
+    comment: false,            // retrieve comments (hurts performance slightly)
     blockTextElements: {
       script: true,	// keep text content when parsing
       noscript: true,	// keep text content when parsing
@@ -90,7 +93,7 @@ Parse given data, and return root of the generated DOM.
 
 ### valid(data[, options])
 
-Parse given data, return true if the givent data is valid, and return false if not.
+Parse the data provided, return true if the given data is valid, and return false if not.
 
 ## HTMLElement Methods
 
@@ -106,7 +109,7 @@ Remove whitespaces in this sub tree.
 
 Query CSS selector to find matching nodes.
 
-Note: Full css3 selector supported since v3.0.0.
+Note: Full range of CSS3 selectors supported since v3.0.0.
 
 ### HTMLElement#querySelector(selector)
 
@@ -116,7 +119,7 @@ Query CSS Selector to find matching node.
 
 Get all elements with the specified tagName.
 
-Note: * for all elements.
+Note: Use * for all elements.
 
 ### HTMLElement#closest(selector)
 
@@ -128,7 +131,7 @@ Append a child node to childNodes
 
 ### HTMLElement#insertAdjacentHTML(where, html)
 
-parses the specified text as HTML and inserts the resulting nodes into the DOM tree at a specified position.
+Parses the specified text as HTML and inserts the resulting nodes into the DOM tree at a specified position.
 
 ### HTMLElement#setAttribute(key: string, value: string)
 
@@ -186,15 +189,15 @@ Remove class name.
 
 #### HTMLElement#classList.toggle(className: string):void
 
-Toggle class.
+Toggle class. Remove it if it is already included, otherwise add.
 
 #### HTMLElement#classList.contains(className: string): boolean
 
-Get if contains
+Returns true if the classname is already in the classList.
 
 #### HTMLElement#classList.values()
 
-get class names
+Get class names.
 
 ## HTMLElement Properties
 
@@ -205,28 +208,28 @@ Get unescaped text value of current node and its children. Like `innerText`.
 
 ### HTMLElement#rawText
 
-Get escaped (as-it) text value of current node and its children. May have
+Get escaped (as-is) text value of current node and its children. May have
 `&amp;` in it. (fast)
 
 ### HTMLElement#tagName
 
-Get tag name of HTMLElement. Notice: the returned value would be an uppercase string.
+Get or Set tag name of HTMLElement. Notice: the returned value would be an uppercase string.
 
 ### HTMLElement#structuredText
 
-Get structured Text
+Get structured Text.
 
 ### HTMLElement#structure
 
-Get DOM structure
+Get DOM structure.
 
 ### HTMLElement#firstChild
 
-Get first child node
+Get first child node.
 
 ### HTMLElement#lastChild
 
-Get last child node
+Get last child node.
 
 ### HTMLElement#innerHTML
 

package/dist/main.js

@@ -482,6 +482,9 @@ define("nodes/html", ["require", "exports", "he", "css-select", "nodes/node", "n
             get: function () {
                 return this.rawTagName ? this.rawTagName.toUpperCase() : this.rawTagName;
             },
+            set: function (newname) {
+                this.rawTagName = newname.toLowerCase();
+            },
             enumerable: false,
             configurable: true
         });

package/dist/nodes/html.d.ts

@@ -76,6 +76,7 @@ export default class HTMLElement extends Node {
      */
     exchangeChild(oldNode: Node, newNode: Node): void;
     get tagName(): string;
+    set tagName(newname: string);
     get localName(): string;
     get isVoidElement(): boolean;
     /**

package/dist/nodes/html.js

@@ -236,6 +236,9 @@ var HTMLElement = /** @class */ (function (_super) {
         get: function () {
             return this.rawTagName ? this.rawTagName.toUpperCase() : this.rawTagName;
         },
+        set: function (newname) {
+            this.rawTagName = newname.toLowerCase();
+        },
         enumerable: false,
         configurable: true
     });

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "node-html-parser",
-	"version": "5.1.0",
+	"version": "5.2.0",
 	"description": "A very fast HTML parser, generating a simplified DOM, with basic element query support.",
 	"main": "dist/index.js",
 	"types": "dist/index.d.ts",
@@ -60,25 +60,32 @@
 		"@typescript-eslint/parser": "latest",
 		"blanket": "latest",
 		"cheerio": "^1.0.0-rc.5",
-		"rimraf": "^3.0.2",
+		"cross-env": "^7.0.3",
 		"eslint": "^7.32.0",
 		"eslint-config-prettier": "latest",
 		"eslint-plugin-import": "latest",
 		"high5": "^1.0.0",
+		"html-dom-parser": "^1.0.4",
+		"html-parser": "^0.11.0",
+		"html5": "^1.0.5",
+		"html5parser": "^2.0.2",
+		"htmljs-parser": "^2.11.1",
 		"htmlparser": "^1.7.7",
 		"htmlparser-benchmark": "^1.1.3",
 		"htmlparser2": "^6.0.0",
 		"mocha": "latest",
 		"mocha-each": "^2.0.1",
+		"neutron-html5parser": "^0.2.0",
 		"np": "latest",
 		"parse5": "^6.0.1",
+		"rimraf": "^3.0.2",
+		"saxes": "^6.0.0",
 		"should": "latest",
 		"spec": "latest",
 		"standard-version": "^9.3.1",
 		"travis-cov": "latest",
 		"ts-node": "^10.2.1",
-		"typescript": "latest",
-		"cross-env": "^7.0.3"
+		"typescript": "latest"
 	},
 	"config": {
 		"blanket": {