Move fork back into main project (inikulin#362)

- Ported to TypeScript
- Switched to npm workspaces, in favour of `lerna`
- Switched to Jest as the test runner
- Switched to the `entities` module for decoding entities
  - A version of parse5's decoding logic was adapted for `entities`. Adopting this dependency allows us to share the maintenance with the `entities` & `htmlparser2` modules.
- Moved the docs back to TSDoc comments
- Switched to the state machine pattern of `htmlparser2` for tokenizer
- No more mixins: Merged location & error mixins into the main classes
- Introduced tag IDs, to avoid branching over large numbers of strings.
- Introduced Maps and Sets where appropriate
- Switched the order of the formatted elements list
- Introduced array helpers in a lot of places
- Updated tests to no longer build objects of tests (used `describe`/`it` constructs instead)

Co-authored-by: Titus <tituswormer@gmail.com>
Co-authored-by: 43081j <43081j@users.noreply.github.com>

.eslintignore

@@ -1,4 +1,4 @@
-packages/parse5/lib/tokenizer/named-entity-data.js
-test/benchmark/node_modules/**/*.js
-test/memory_benchmark/node_modules/**/*.js
+test/data/html5lib-tests
+packages/*/dist/
+test/dist/
 node_modules

.eslintrc.json

@@ -2,7 +2,7 @@
     "env": {
         "es2020": true,
         "node": true,
-        "mocha": true
+        "jest": true
     },
     "extends": ["eslint:recommended", "prettier", "plugin:unicorn/recommended"],
     "rules": {
@@ -21,6 +21,7 @@
             }
         ],
         "prefer-template": "error",
+        "arrow-body-style": ["error", "as-needed"],
 
         "unicorn/no-null": "off",
         "unicorn/prevent-abbreviations": "off",
@@ -30,10 +31,26 @@
         "unicorn/no-array-reduce": "off",
         "unicorn/no-for-loop": "off",
         "unicorn/consistent-destructuring": "off",
-        "unicorn/prefer-switch": ["error", { "emptyDefaultCase": "do-nothing-comment" }],
-        "unicorn/number-literal-case": "off"
+        "unicorn/prefer-switch": ["error", { "emptyDefaultCase": "do-nothing-comment" }]
     },
     "parserOptions": {
         "sourceType": "module"
-    }
+    },
+    "overrides": [
+        {
+            "files": "*.ts",
+            "extends": [
+                "plugin:@typescript-eslint/eslint-recommended",
+                "plugin:@typescript-eslint/recommended",
+                "prettier"
+            ],
+            "rules": {
+                "@typescript-eslint/no-non-null-assertion": "warn",
+                "@typescript-eslint/no-explicit-any": "warn",
+                "@typescript-eslint/explicit-function-return-type": "error",
+
+                "@typescript-eslint/no-unused-vars": ["error", { "argsIgnorePattern": "^_" }]
+            }
+        }
+    ]
 }

.gitattributes

@@ -1,3 +1,3 @@
 # Exclude the HTML files from GitHub's language statistics
 # https://github.com/github/linguist#using-gitattributes
-test/data/* linguist-vendored
+packages/test-utils/data/* linguist-vendored

.gitignore

@@ -4,6 +4,7 @@
 node_modules
 docs/build
 docs/05_api_reference.md
-package-lock.json
-bench/package-lock.json
+packages/*/dist/
+test/dist/
 .DS_Store
+tsconfig.tsbuildinfo

.gitmodules

@@ -1,3 +1,3 @@
-[submodule "test/data/html5lib-tests"]
+[submodule "html5lib-tests"]
 	path = test/data/html5lib-tests
 	url = https://github.com/HTMLParseErrorWG/html5lib-tests

.husky/pre-commit

@@ -0,0 +1,4 @@
+#!/bin/sh
+. "$(dirname "$0")/_/husky.sh"
+
+npm run pre-commit

.prettierignore

@@ -1,2 +1,4 @@
-packages/parse5/lib/tokenizer/named-entity-data.js
+packages/*/dist/
+test/dist/
 docs
+test/data/html5lib-tests

README.md

@@ -9,7 +9,7 @@
 </p>
 
 <p align="center">
-  <a href="https://travis-ci.org/inikulin/parse5"><img alt="Build Status" src="https://api.travis-ci.org/inikulin/parse5.svg"></a>
+  <a href="https://github.com/inikulin/parse5/actions/workflows/nodejs-test.yml"><img alt="Build Status" src="https://img.shields.io/github/workflow/status/inikulin/parse5/Node.js%20CI?label=tests&style=flat"></a>
   <a href="https://www.npmjs.com/package/parse5"><img alt="NPM Version" src="https://img.shields.io/npm/v/parse5.svg"></a>
   <a href="https://npmjs.org/package/parse5"><img alt="Downloads" src="http://img.shields.io/npm/dm/parse5.svg"></a>
   <a href="https://npmjs.org/package/parse5"><img alt="Downloads total" src="http://img.shields.io/npm/dt/parse5.svg"></a>

bench/memory/sax-parser.js

@@ -1,8 +1,8 @@
-import * as fs from 'node:fs';
+import { readFile } from 'node:fs/promises';
 import format from 'human-format';
 import promisifyEvent from 'promisify-event';
 import memwatch from '@airbnb/node-memwatch';
-import SAXParser from '../../packages/parse5-sax-parser/lib/index.js';
+import { SAXParser } from '../../packages/parse5-sax-parser/dist/index.js';
 
 main();
 
@@ -15,7 +15,7 @@ async function main() {
     let heapDiff = null;
 
     memwatch.on('stats', (stats) => {
-        maxMemUsage = Math.max(maxMemUsage, stats['current_base']);
+        maxMemUsage = Math.max(maxMemUsage, stats.used_heap_size);
     });
 
     startDate = new Date();
@@ -35,7 +35,7 @@ async function main() {
 }
 
 async function parse() {
-    const data = fs.readFileSync('../test/data/huge-page/huge-page.html', 'utf8');
+    const data = await readFile(new URL('../../test/data/huge-page/huge-page.html', import.meta.url), 'utf8');
     let parsedDataSize = 0;
     const stream = new SAXParser();
 

bench/package.json

@@ -1,15 +1,16 @@
 {
     "name": "parse5-benchmarks",
+    "private": "true",
     "type": "module",
     "version": "1.0.0",
     "description": "parse5 regression benchmarks",
     "author": "Ivan Nikulin <ifaaan@gmail.com>",
     "license": "MIT",
     "dependencies": {
         "benchmark": "^2.1.4",
-        "human-format": "^0.7.0",
+        "human-format": "^0.11.0",
         "@airbnb/node-memwatch": "^2.0.0",
-        "parse5": "*",
+        "parse5": "npm:parse5",
         "promisify-event": "^1.0.0"
     }
 }

bench/perf/index.js

@@ -1,10 +1,10 @@
 import { readFileSync, createReadStream, readdirSync } from 'node:fs';
 import Benchmark from 'benchmark';
-import { loadTreeConstructionTestData } from '../../test/utils/generate-parsing-tests.js';
-import { loadSAXParserTestData } from '../../test/utils/load-sax-parser-test-data.js';
-import { treeAdapters, WritableStreamStub } from '../../test/utils/common.js';
-import * as parse5 from '../../packages/parse5/lib/index.js';
-import { ParserStream as parse5Stream } from '../../packages/parse5-parser-stream/lib/index.js';
+import { loadTreeConstructionTestData } from 'parse5-test-utils/dist/generate-parsing-tests.js';
+import { loadSAXParserTestData } from 'parse5-test-utils/dist/load-sax-parser-test-data.js';
+import { treeAdapters, WritableStreamStub } from 'parse5-test-utils/dist/common.js';
+import * as parse5 from '../../packages/parse5/dist/index.js';
+import { ParserStream as parse5Stream } from '../../packages/parse5-parser-stream/dist/index.js';
 import * as parse5Upstream from 'parse5';
 
 const hugePagePath = new URL('../../test/data/huge-page/huge-page.html', import.meta.url);
@@ -46,19 +46,21 @@ global.runMicro = function (parser) {
 const pages = loadSAXParserTestData().map((test) => test.src);
 
 global.runPages = function (parser) {
-    for (let j = 0; j < pages.length; j++) {
-        parser.parse(pages[j]);
+    for (const page of pages) {
+        parser.parse(page);
     }
 };
 
 // Stream data
-global.files = readdirSync(saxPath).map((dirName) => {
-    return new URL(`${dirName}/src.html`, saxPath).pathname;
-});
+global.files = readdirSync(saxPath).map((dirName) => new URL(`${dirName}/src.html`, saxPath).pathname);
 
 // Utils
 function getHz(suite, testName) {
-    return suite.find((t) => t.name === testName).hz;
+    for (let i = 0; i < suite.length; i++) {
+        if (suite[i].name === testName) {
+            return suite[i].hz;
+        }
+    }
 }
 
 function runBench({ name, workingCopyFn, upstreamFn, defer = false }) {