@tkeron/html-parser 0.1.4 → 0.1.7

package/tests/official/final-output/final-output.test.ts

@@ -1,7 +1,7 @@
 import { describe, it, expect } from 'bun:test';
 import { parseHTML } from '../../../index';
 
-// Helper function to normalize text for comparison
+
 function normalizeText(text: string): string {
   return text
     .replace(/\s+/g, ' ')
@@ -16,7 +16,7 @@ describe('Final HTML Output Validation', () => {
       const document = parseHTML(html);
       
       expect(document).toBeDefined();
-      expect(document.nodeType).toBe(9); // DOCUMENT_NODE
+      expect(document.nodeType).toBe(9); 
       
       const div = document.querySelector('div');
       expect(div).toBeDefined();
@@ -101,9 +101,9 @@ describe('Final HTML Output Validation', () => {
       expect(p).toBeDefined();
       expect(p?.textContent).toBe('Content');
       
-      // Check for comment node
+      
       const commentNode = div?.childNodes[0];
-      expect(commentNode?.nodeType).toBe(8); // COMMENT_NODE
+      expect(commentNode?.nodeType).toBe(8); 
     });
   });
 
@@ -135,16 +135,16 @@ describe('Final HTML Output Validation', () => {
       expect(div).toBeDefined();
       expect(div?.childNodes.length).toBe(3);
       
-      // First text node
-      expect(div?.childNodes[0]?.nodeType).toBe(3); // TEXT_NODE
+      
+      expect(div?.childNodes[0]?.nodeType).toBe(3); 
       expect(div?.childNodes[0]?.textContent).toBe('Text before ');
       
-      // Span element
-      expect(div?.childNodes[1]?.nodeType).toBe(1); // ELEMENT_NODE
+      
+      expect(div?.childNodes[1]?.nodeType).toBe(1); 
       expect((div?.childNodes[1] as Element)?.tagName).toBe('SPAN');
       
-      // Last text node
-      expect(div?.childNodes[2]?.nodeType).toBe(3); // TEXT_NODE
+      
+      expect(div?.childNodes[2]?.nodeType).toBe(3); 
       expect(div?.childNodes[2]?.textContent).toBe(' text after');
     });
 
@@ -264,7 +264,7 @@ describe('Final HTML Output Validation', () => {
       const document = parseHTML(malformedHTML);
       
       expect(document).toBeDefined();
-      expect(document.nodeType).toBe(9); // DOCUMENT_NODE
+      expect(document.nodeType).toBe(9); 
       
       const divs = document.querySelectorAll('div');
       expect(divs.length).toBeGreaterThan(0);
@@ -296,7 +296,7 @@ describe('Final HTML Output Validation', () => {
       const p = document.querySelector('p');
       expect(p).toBeDefined();
       expect(p?.textContent).toContain('Special chars:');
-      // The exact entity handling depends on your implementation
+      
     });
 
     it('should handle multiple top-level elements', () => {
@@ -321,17 +321,17 @@ describe('Final HTML Output Validation', () => {
       
       const document = parseHTML(html);
       
-      // Test getElementById
+      
       const byId = document.getElementById('test');
       expect(byId).toBeDefined();
       expect(byId?.tagName).toBe('DIV');
       
-      // Test querySelector
+      
       const bySelector = document.querySelector('.container');
       expect(bySelector).toBeDefined();
       expect(bySelector?.id).toBe('test');
       
-      // Test querySelectorAll
+      
       const byClass = document.querySelectorAll('.text');
       expect(byClass.length).toBe(1);
       expect(byClass[0]?.textContent).toBe('Hello');

package/tests/official/html5lib/tokenizer-utils.ts

@@ -2,7 +2,7 @@ import { expect, describe, it } from 'bun:test';
 import { tokenize, TokenType } from '../../../src/tokenizer';
 import type { Token } from '../../../src/tokenizer';
 
-// HTML5lib tokenizer test format
+
 export interface HTML5libTokenizerTest {
   description: string;
   input: string;
@@ -18,12 +18,12 @@ export interface HTML5libTokenizerTestSuite {
 }
 
 export type HTML5libTokenOutput = 
-  | ['StartTag', string, Record<string, string>] // StartTag without self-closing
-  | ['StartTag', string, Record<string, string>, boolean] // StartTag with self-closing
-  | ['EndTag', string] // EndTag
-  | ['Comment', string] // Comment
-  | ['Character', string] // Character
-  | ['DOCTYPE', string, string | null, string | null, boolean]; // DOCTYPE
+  | ['StartTag', string, Record<string, string>] 
+  | ['StartTag', string, Record<string, string>, boolean] 
+  | ['EndTag', string] 
+  | ['Comment', string] 
+  | ['Character', string] 
+  | ['DOCTYPE', string, string | null, string | null, boolean]; 
 
 export interface HTML5libError {
   code: string;
@@ -31,9 +31,7 @@ export interface HTML5libError {
   col: number;
 }
 
-/**
- * Converts HTML5lib token format to our internal token format
- */
+
 export function convertHTML5libToken(html5libToken: HTML5libTokenOutput): Partial<Token> {
   const type = html5libToken[0];
   const nameOrData = html5libToken[1];
@@ -78,9 +76,7 @@ export function convertHTML5libToken(html5libToken: HTML5libTokenOutput): Partia
   }
 }
 
-/**
- * Converts our internal token format to HTML5lib format for comparison
- */
+
 export function convertToHTML5libToken(token: Token): HTML5libTokenOutput {
   switch (token.type) {
     case TokenType.DOCTYPE:
@@ -102,9 +98,7 @@ export function convertToHTML5libToken(token: Token): HTML5libTokenOutput {
   }
 }
 
-/**
- * Normalizes adjacent character tokens as per HTML5lib spec
- */
+
 export function normalizeCharacterTokens(tokens: Token[]): Token[] {
   const normalized: Token[] = [];
   let currentText = '';
@@ -140,13 +134,11 @@ export function normalizeCharacterTokens(tokens: Token[]): Token[] {
   return normalized;
 }
 
-/**
- * Runs a single HTML5lib tokenizer test
- */
+
 export function runHTML5libTokenizerTest(test: HTML5libTokenizerTest): void {
   const { description, input, output: expectedOutput, initialStates = ['Data state'] } = test;
   
-  // Process double-escaped input if needed
+  
   let processedInput = input;
   if (test.doubleEscaped) {
     processedInput = processedInput.replace(/\\u([0-9a-fA-F]{4})/g, (match, hex) => {
@@ -156,16 +148,16 @@ export function runHTML5libTokenizerTest(test: HTML5libTokenizerTest): void {
   
   for (const initialState of initialStates) {
     it(`${description} (${initialState})`, () => {
-      // Tokenize the input
+      
       const tokens = tokenize(processedInput);
       
-      // Normalize character tokens
+      
       const normalizedTokens = normalizeCharacterTokens(tokens);
       
-      // Convert to HTML5lib format for comparison
+      
       const actualOutput = normalizedTokens.map(convertToHTML5libToken);
       
-      // Process expected output if double-escaped
+      
       let processedExpectedOutput = expectedOutput;
       if (test.doubleEscaped) {
         processedExpectedOutput = expectedOutput.map(token => {
@@ -178,15 +170,13 @@ export function runHTML5libTokenizerTest(test: HTML5libTokenizerTest): void {
         });
       }
       
-      // Compare outputs
+      
       expect(actualOutput).toEqual(processedExpectedOutput);
     });
   }
 }
 
-/**
- * Runs all tests from an HTML5lib tokenizer test suite
- */
+
 export function runHTML5libTokenizerTestSuite(testSuite: HTML5libTokenizerTestSuite, suiteName: string): void {
   describe(`HTML5lib Tokenizer Tests: ${suiteName}`, () => {
     testSuite.tests.forEach(test => {
@@ -195,9 +185,7 @@ export function runHTML5libTokenizerTestSuite(testSuite: HTML5libTokenizerTestSu
   });
 }
 
-/**
- * Loads and runs HTML5lib tokenizer tests from JSON
- */
+
 export async function loadHTML5libTokenizerTests(testData: string, suiteName: string): Promise<void> {
   const testSuite: HTML5libTokenizerTestSuite = JSON.parse(testData);
   runHTML5libTokenizerTestSuite(testSuite, suiteName);

package/tests/official/html5lib/tokenizer.test.ts

@@ -5,7 +5,7 @@ import {
   type HTML5libTokenizerTestSuite
 } from './tokenizer-utils';
 
-// Sample HTML5lib tokenizer tests embedded directly
+
 const basicTokenizerTests: HTML5libTokenizerTestSuite = {
   "tests": [
     {
@@ -86,7 +86,7 @@ const basicTokenizerTests: HTML5libTokenizerTestSuite = {
   ]
 };
 
-// Entity tests
+
 const entityTests: HTML5libTokenizerTestSuite = {
   "tests": [
     {
@@ -123,7 +123,7 @@ const entityTests: HTML5libTokenizerTestSuite = {
   ]
 };
 
-// Comment tests
+
 const commentTests: HTML5libTokenizerTestSuite = {
   "tests": [
     {
@@ -163,7 +163,7 @@ const commentTests: HTML5libTokenizerTestSuite = {
   ]
 };
 
-// Run the embedded tests
+
 describe('HTML5lib Tokenizer Tests', () => {
   runHTML5libTokenizerTestSuite(basicTokenizerTests, 'Basic Tokenizer');
   runHTML5libTokenizerTestSuite(entityTests, 'Entity Handling');

package/tests/official/html5lib/tree-construction-utils.ts

@@ -3,7 +3,7 @@ import { parse } from '../../../src/parser';
 import { tokenize } from '../../../src/tokenizer';
 import type { ASTNode } from '../../../src/parser';
 
-// HTML5lib tree construction test format
+
 export interface HTML5libTreeTest {
   data: string;
   errors: string[];
@@ -14,9 +14,7 @@ export interface HTML5libTreeTest {
   document: string;
 }
 
-/**
- * Parses HTML5lib DAT format test files
- */
+
 export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
   const tests: HTML5libTreeTest[] = [];
   const sections = content.split('\n\n').filter(section => section.trim());
@@ -24,7 +22,7 @@ export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
   for (const section of sections) {
     const lines = section.split('\n');
     const test: Partial<HTML5libTreeTest> = {
-      errors: [] // Initialize errors as empty array
+      errors: [] 
     };
     
     let currentSection = '';
@@ -32,7 +30,7 @@ export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
     
     for (const line of lines) {
       if (line.startsWith('#')) {
-        // Save previous section
+        
         if (currentSection) {
           switch (currentSection) {
             case 'data':
@@ -53,11 +51,11 @@ export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
           }
         }
         
-        // Start new section
+        
         currentSection = line.substring(1);
         currentContent = [];
         
-        // Handle script flags
+        
         if (currentSection === 'script-off') {
           test.scriptOff = true;
         } else if (currentSection === 'script-on') {
@@ -68,7 +66,7 @@ export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
       }
     }
     
-    // Save last section
+    
     if (currentSection) {
       switch (currentSection) {
         case 'data':
@@ -97,16 +95,14 @@ export function parseHTML5libDATFile(content: string): HTML5libTreeTest[] {
   return tests;
 }
 
-/**
- * Converts AST to HTML5lib tree format
- */
+
 export function convertASTToHTML5libTree(node: ASTNode, depth: number = 0): string[] {
   const lines: string[] = [];
   const indent = '| ' + '  '.repeat(depth);
   
   switch (node.type) {
     case 'DOCUMENT':
-      // Document node doesn't have a line representation
+      
       break;
     case 'DOCTYPE':
       lines.push(`${indent}<!DOCTYPE ${node.tagName || 'html'}>`);
@@ -115,7 +111,7 @@ export function convertASTToHTML5libTree(node: ASTNode, depth: number = 0): stri
       const tagName = node.tagName || 'unknown';
       lines.push(`${indent}<${tagName}>`);
       
-      // Add attributes
+      
       if (node.attributes) {
         for (const [name, value] of Object.entries(node.attributes).sort()) {
           lines.push(`${indent}  ${name}="${value}"`);
@@ -135,7 +131,7 @@ export function convertASTToHTML5libTree(node: ASTNode, depth: number = 0): stri
       break;
   }
   
-  // Add children
+  
   if (node.children) {
     for (const child of node.children) {
       lines.push(...convertASTToHTML5libTree(child, depth + 1));
@@ -145,9 +141,7 @@ export function convertASTToHTML5libTree(node: ASTNode, depth: number = 0): stri
   return lines;
 }
 
-/**
- * Normalizes HTML5lib tree format for comparison
- */
+
 export function normalizeHTML5libTree(tree: string): string {
   return tree
     .split('\n')
@@ -156,33 +150,29 @@ export function normalizeHTML5libTree(tree: string): string {
     .join('\n');
 }
 
-/**
- * Runs a single HTML5lib tree construction test
- */
+
 export function runHTML5libTreeTest(test: HTML5libTreeTest, testName: string): void {
   it(testName, () => {
     const { data, document: expectedTree, documentFragment, scriptOff, scriptOn } = test;
     
-    // Parse the HTML
+    
     const tokens = tokenize(data);
     const ast = parse(tokens);
     
-    // Convert to HTML5lib tree format
+    
     const actualTreeLines = convertASTToHTML5libTree(ast);
     const actualTree = actualTreeLines.join('\n');
     
-    // Normalize both trees for comparison
+    
     const normalizedActual = normalizeHTML5libTree(actualTree);
     const normalizedExpected = normalizeHTML5libTree(expectedTree);
     
-    // Compare trees
+    
     expect(normalizedActual).toBe(normalizedExpected);
   });
 }
 
-/**
- * Runs all tests from an HTML5lib tree construction test suite
- */
+
 export function runHTML5libTreeTestSuite(tests: HTML5libTreeTest[], suiteName: string): void {
   describe(`HTML5lib Tree Construction Tests: ${suiteName}`, () => {
     tests.forEach((test, index) => {
@@ -192,17 +182,13 @@ export function runHTML5libTreeTestSuite(tests: HTML5libTreeTest[], suiteName: s
   });
 }
 
-/**
- * Loads and runs HTML5lib tree construction tests from DAT format
- */
+
 export async function loadHTML5libTreeTests(testData: string, suiteName: string): Promise<void> {
   const tests = parseHTML5libDATFile(testData);
   runHTML5libTreeTestSuite(tests, suiteName);
 }
 
-/**
- * Validates HTML5lib tree construction test format
- */
+
 export function validateHTML5libTreeTest(test: HTML5libTreeTest): boolean {
   return !!(test.data && test.document && test.errors !== undefined);
 }

package/tests/official/html5lib/tree-construction.test.ts

@@ -6,7 +6,7 @@ import {
   type HTML5libTreeTest,
 } from "./tree-construction-utils";
 
-// Sample HTML5lib tree construction tests in DAT format
+
 const basicTreeTestData = `#data
 Test
 #errors
@@ -206,13 +206,13 @@ const errorHandlingTestData = `#data
 |       <a>
 |     <a>`;
 
-// Run the embedded tests
+
 describe("HTML5lib Tree Construction Tests", () => {
   it("should parse DAT format correctly", () => {
     const tests = parseHTML5libDATFile(basicTreeTestData);
     expect(tests.length).toBeGreaterThan(0);
 
-    // Check first test
+    
     const firstTest = tests[0];
     if (firstTest) {
       expect(firstTest.data).toBe("Test");
@@ -225,7 +225,7 @@ describe("HTML5lib Tree Construction Tests", () => {
     const tests = parseHTML5libDATFile(doctypeTestData);
     expect(tests.length).toBeGreaterThan(0);
 
-    // Check first doctype test
+    
     const firstTest = tests[0];
     if (firstTest) {
       expect(firstTest.data).toBe("<!DOCTYPE html>");
@@ -238,7 +238,7 @@ describe("HTML5lib Tree Construction Tests", () => {
     const tests = parseHTML5libDATFile(errorHandlingTestData);
     expect(tests.length).toBeGreaterThan(0);
 
-    // Check error handling
+    
     const firstTest = tests[0];
     if (firstTest) {
       expect(firstTest.errors.length).toBeGreaterThan(0);

package/tests/official/validator/validator-tests.test.ts

@@ -42,7 +42,7 @@ describe('Validator.nu Tests', () => {
     });
 
     it('should handle content model violations', () => {
-      // These should parse but may generate warnings in a full validator
+      
       const contentModelHTML = `
         <p>
           <div>Block inside paragraph</div>
@@ -53,7 +53,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(contentModelHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -67,7 +67,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(obsoleteHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -85,7 +85,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(deprecatedHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -114,7 +114,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(formHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -136,7 +136,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(mediaHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -162,7 +162,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(semanticHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -184,7 +184,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(interactiveHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -200,7 +200,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(unclosedHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -215,7 +215,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(mismatchedHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });
@@ -229,7 +229,7 @@ describe('Validator.nu Tests', () => {
       `;
       
       const document = parseHTML(invalidNestingHTML);
-      // const ast = parse(tokens);
+      
       
       expect(document).toBeDefined();
     });

package/tests/official/wpt/wpt-tests.test.ts

@@ -135,10 +135,10 @@ describe('Web Platform Tests (WPT) Compliance', () => {
     
     it('should handle numeric character references', () => {
       const numericRefs = [
-        'A',   // A
-        'A',  // A (hex)
-        '€', // Euro symbol
-        '€' // Euro symbol (hex)
+        'A',   
+        'A',  
+        '€', 
+        '€' 
       ];
       
       numericRefs.forEach(ref => {
@@ -404,6 +404,6 @@ describe('WPT Integration Tests', () => {
     
     expect(ast).toBeDefined();
     expect((ast as any).children?.length).toBeGreaterThan(0);
-    expect(end - start).toBeLessThan(1000); // Should parse within 1 second
+    expect(end - start).toBeLessThan(1000); 
   });
 });