@tkeron/html-parser 0.1.7 → 1.1.0

package/README.md

@@ -1,7 +1,5 @@
 # HTML Parser - Powered by Bun Native Tokenizer
 
-> ⚠️ **Work in Progress** - This package is currently under active development.
-
 A fast and lightweight HTML parser for Bun that converts HTML strings into DOM Document objects. **Now powered by a native Bun tokenizer** for optimal performance.
 
 ## Features
@@ -11,15 +9,11 @@ A fast and lightweight HTML parser for Bun that converts HTML strings into DOM D
 - 🪶 **Lightweight**: Minimal dependencies, native implementation
 - 🌐 **Standards Compliant**: Returns standard DOM Document objects
 - 🔧 **TypeScript Support**: Full TypeScript definitions included
-- ✅ **Well Tested**: Comprehensive unit test suite (569 tests passing)
+- ✅ **Well Tested**: Comprehensive test suite (5200+ tests passing)
 - 🔄 **100% Compatible**: Drop-in replacement, same API
 
 ## Installation
 
-> **Note**: This package is not yet published to npm. For now, you can clone and build locally.
-
-Once published, it will be available as:
-
 ```bash
 npm install @tkeron/html-parser
 ```

package/bun.lock

@@ -4,6 +4,9 @@
   "workspaces": {
     "": {
       "name": "@tkeron/html-parser",
+      "dependencies": {
+        "all-named-html-entities": "^3.1.3",
+      },
       "devDependencies": {
         "@types/bun": "^1.3.6",
       },
@@ -17,6 +20,8 @@
 
     "@types/node": ["@types/node@25.0.3", "", { "dependencies": { "undici-types": "~7.16.0" } }, "sha512-W609buLVRVmeW693xKfzHeIV6nJGGz98uCPfeXI1ELMLXVeKYZ9m15fAMSaUPBHYLGFsVRcMmSCksQOrZV9BYA=="],
 
+    "all-named-html-entities": ["all-named-html-entities@3.1.3", "", {}, "sha512-eG7/XkhxyIUWApWvhVPcusxZ3PTebJo1AvkFkQj7MDSkBYmzXZsNadKZWuo1UxEX6QrE7y7JQx7G3Fx0YjVtnA=="],
+
     "bun-types": ["bun-types@1.3.6", "", { "dependencies": { "@types/node": "*" } }, "sha512-OlFwHcnNV99r//9v5IIOgQ9Uk37gZqrNMCcqEaExdkVq3Avwqok1bJFmvGMCkCE0FqzdY8VMOZpfpR3lwI+CsQ=="],
 
     "typescript": ["typescript@5.9.3", "", { "bin": { "tsc": "bin/tsc", "tsserver": "bin/tsserver" } }, "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw=="],

package/index.ts

@@ -7,6 +7,10 @@ import {
 export function parseHTML(html: string = ""): Document {
   const tokens = tokenize(html);
   const ast = parse(tokens);
+  // If parse already returns a DOM document, return it directly
+  if (ast && typeof ast.nodeType === 'number' && ast.nodeType === 9) {
+    return ast;
+  }
   return astToDOM(ast);
 }
 

package/package.json

@@ -1,12 +1,15 @@
 {
   "name": "@tkeron/html-parser",
-  "version": "0.1.7",
+  "version": "1.1.0",
   "description": "A fast and lightweight HTML parser for Bun",
   "main": "index.js",
   "module": "index.ts",
   "type": "module",
   "author": "tkeron",
   "license": "MIT",
+  "scripts": {
+    "test": "bun test --concurrent"
+  },
   "devDependencies": {
     "@types/bun": "^1.3.6"
   },
@@ -22,5 +25,8 @@
   ],
   "repository": {
     "url": "git@github.com:tkeron/html-parser.git"
+  },
+  "dependencies": {
+    "all-named-html-entities": "^3.1.3"
   }
 }

package/src/css-selector.ts

@@ -26,7 +26,7 @@ function parseSelector(selector: string): SelectorGroup[] {
     let remaining = trimmed;
     
     // Extract tag name first if present
-    const tagMatch = remaining.match(/^([a-zA-Z][a-zA-Z0-9]*)/);
+    const tagMatch = remaining.match(/^([a-zA-Z][a-zA-Z0-9-]*)/);
     if (tagMatch) {
       tokens.push({ type: "tag", value: tagMatch[1].toLowerCase() });
       remaining = remaining.slice(tagMatch[1].length);

package/src/dom-simulator.ts

@@ -6,6 +6,11 @@ import {
   querySelectorAll as querySelectorAllFunction,
 } from "./css-selector.js";
 
+// Escape special HTML characters in text content
+function escapeTextContent(text: string): string {
+  return text.replace(/&/g, '&amp;').replace(/</g, '&lt;').replace(/>/g, '&gt;');
+}
+
 const VOID_ELEMENTS = new Set([
   'area', 'base', 'br', 'col', 'embed', 'hr', 'img', 'input',
   'link', 'meta', 'param', 'source', 'track', 'wbr'
@@ -23,7 +28,8 @@ export const enum NodeType {
 
 export function createElement(
   tagName: string,
-  attributes: Record<string, string> = {}
+  attributes: Record<string, string> = {},
+  namespaceURI?: string
 ): any {
   const innerHTML = "";
   const tagNameLower = tagName.toLowerCase();
@@ -41,6 +47,7 @@ export function createElement(
     nodeName: tagName.toUpperCase(),
     nodeValue: null,
     tagName: tagName.toUpperCase(),
+    namespaceURI: namespaceURI || null,
     attributes: { ...attributes },
     childNodes: [],
     children: [],
@@ -226,6 +233,25 @@ export function createComment(content: string): any {
   return commentNode;
 }
 
+export function createDoctype(name: string = 'html'): any {
+  const doctypeNode: any = {
+    nodeType: NodeType.DOCUMENT_TYPE_NODE,
+    nodeName: name.toUpperCase(),
+    name: name.toLowerCase(),
+    nodeValue: null,
+    textContent: "",
+    publicId: null,
+    systemId: null,
+    childNodes: [],
+    parentNode: null,
+    firstChild: null,
+    lastChild: null,
+    nextSibling: null,
+    previousSibling: null,
+  };
+  return doctypeNode;
+}
+
 export function createDocument(): any {
   const document: any = {
     nodeType: NodeType.DOCUMENT_NODE,
@@ -375,7 +401,7 @@ function convertASTNodeToDOM(astNode: ASTNode): any {
   }
 }
 
-function appendChild(parent: any, child: any): void {
+export function appendChild(parent: any, child: any): void {
   if (child.nodeType === NodeType.ELEMENT_NODE || child.nodeType === NodeType.DOCUMENT_NODE) {
     let ancestor = parent;
     while (ancestor) {
@@ -918,13 +944,13 @@ export function setInnerHTML(element: any, html: string): void {
 
   if (html.trim()) {
     const tokens = tokenize(html);
-    const ast = parse(tokens);
-    if (ast.children) {
-      for (const child of ast.children) {
-        const domChild = convertASTNodeToDOM(child);
-        if (domChild) {
-          appendChild(element, domChild);
-        }
+    const doc = parse(tokens);
+    const body = doc.body;
+    if (body && body.childNodes) {
+      const nodesToMove = [...body.childNodes];
+      for (const child of nodesToMove) {
+        child.parentNode = null;
+        appendChild(element, child);
       }
     }
   }
@@ -975,14 +1001,12 @@ export function setOuterHTML(element: any, html: string): void {
   
   if (html.trim()) {
     const tokens = tokenize(html);
-    const ast = parse(tokens);
-    
-    if (ast.children) {
-      for (const child of ast.children) {
-        const domChild = convertASTNodeToDOM(child);
-        if (domChild) {
-          newNodes.push(domChild);
-        }
+    const doc = parse(tokens);
+    const body = doc.body;
+    if (body && body.childNodes) {
+      for (const child of body.childNodes) {
+        child.parentNode = null;
+        newNodes.push(child);
       }
     }
   }

package/src/encoding.ts

@@ -0,0 +1,39 @@
+/**
+ * Detects the character encoding of an HTML document.
+ * Based on HTML5 specification for encoding detection.
+ */
+
+const encodingAliases: Record<string, string> = {
+  'iso-8859-1': 'windows-1252',
+  'iso8859-1': 'windows-1252',
+  'iso-8859-2': 'iso-8859-2',
+  'iso8859-2': 'iso-8859-2',
+  'utf-8': 'utf-8',
+  'utf8': 'utf-8',
+  // Add more as needed
+};
+
+function normalizeEncoding(name: string): string | null {
+  const lower = name.toLowerCase().replace(/[^a-z0-9-]/g, '');
+  return encodingAliases[lower] || lower;
+}
+
+export function detectEncoding(html: string): string | null {
+  // Limit to first 1024 characters for performance
+  const prefix = html.substring(0, 1024);
+
+  // Look for <meta charset="...">
+  const charsetMatch = prefix.match(/<meta[^>]*charset\s*=\s*["']?([^"'\s>]+)["']?/i);
+  if (charsetMatch) {
+    return normalizeEncoding(charsetMatch[1]);
+  }
+
+  // Look for <meta http-equiv="Content-Type" content="text/html; charset=...">
+  const contentTypeMatch = prefix.match(/<meta[^>]*http-equiv\s*=\s*["']?\s*content-type\s*["']?[^>]*content\s*=\s*["']?\s*text\/html;\s*charset\s*=\s*([^"'\s>]+)["']?/i);
+  if (contentTypeMatch) {
+    return normalizeEncoding(contentTypeMatch[1]);
+  }
+
+  // Default to Windows-1252 if no encoding found (as per HTML5 spec)
+  return 'windows-1252';
+}

package/src/index.ts

@@ -0,0 +1,9 @@
+import { tokenize } from './tokenizer.js';
+import { parse } from './parser.js';
+
+export function parseHTML(html: string): any {
+  const tokens = tokenize(html);
+  return parse(tokens);
+}
+
+export { parse } from './parser';