Add task for retrieving the list of known elements

RoboFile.php

@@ -1,6 +1,7 @@
 <?php
 
 use Robo\Result;
+use MensBeam\HTML\DOMParser;
 
 const BASE = __DIR__.\DIRECTORY_SEPARATOR;
 const BASE_TEST = BASE."tests".\DIRECTORY_SEPARATOR;
@@ -9,6 +10,8 @@ define("IS_MAC", php_uname("s") === "Darwin");
 define("IS_LINUX", !IS_WIN && !IS_MAC);
 error_reporting(0);
 
+require_once BASE."vendor".DIRECTORY_SEPARATOR."autoload.php";
+
 function norm(string $path): string {
     $out = realpath($path);
     if (!$out) {
@@ -153,4 +156,33 @@ class RoboFile extends \Robo\Tasks {
         $c->addTask($this->taskExec(BASE_TEST."parsetests")->arg(BASE_TEST."platform-tests")->rawArg(">")->arg(BASE_TEST."cases".DIRECTORY_SEPARATOR."std-sanitize.json"));
         return $c->run();
     }
+
+    public function constants(): Result {
+        $c = $this->collectionBuilder()->addCode(function() {
+            $elems = [];
+            // retrieve the single-page HTML specification (this is around 15MB in size)
+            $spec = file_get_contents("https://html.spec.whatwg.org/");
+            // parse it (this may take several seconds
+            if ($spec) {
+                $p = new DOMParser;
+                $document = $p->parseFromString($spec, "text/html;charset=utf-8");
+                // pick out element definitions from the specification
+                foreach ($document->getElementsByTagName("dfn") as $el) {
+                    if ($el->getAttribute("data-dfn-type") === "element") {
+                        $elems[] = trim($el->textContent);
+                    }
+                }
+            }
+            // sort and filter the results for unqiueness
+            sort($elems);
+            $elems = array_unique($elems);
+            // output the list of elements as a PHP array
+            $elems = array_map(function($e) {
+                return "'$e' => true";
+            }, $elems);
+            $elems = implode(", ", $elems);
+            echo "protected const KNOWN_ELEMENTS_HTML = [".$elems."];\n";
+        });
+        return $c->run();
+    }
 }

composer.json

@@ -31,7 +31,8 @@
         }
     },
     "require-dev": {
-        "bamarni/composer-bin-plugin": "^1.3"
+        "bamarni/composer-bin-plugin": "^1.3",
+        "mensbeam/html-parser": "^1.3"
     },
     "config": {
         "allow-plugins": {

composer.lock

@@ -4,7 +4,7 @@
         "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#installing-dependencies",
         "This file is @generated automatically"
     ],
-    "content-hash": "ca1817f63eaf25e350da3b69bae122a0",
+    "content-hash": "2a1fcce4abef9d281df651d5260de85d",
     "packages": [],
     "packages-dev": [
         {
@@ -63,6 +63,235 @@
                 "source": "https://github.com/bamarni/composer-bin-plugin/tree/1.8.2"
             },
             "time": "2022-10-31T08:38:03+00:00"
+        },
+        {
+            "name": "mensbeam/html-parser",
+            "version": "1.3.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/mensbeam/HTML-Parser.git",
+                "reference": "d499fac607ae06311df54887ba45c120797c76ed"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/mensbeam/HTML-Parser/zipball/d499fac607ae06311df54887ba45c120797c76ed",
+                "reference": "d499fac607ae06311df54887ba45c120797c76ed",
+                "shasum": ""
+            },
+            "require": {
+                "ext-dom": "*",
+                "mensbeam/intl": ">=0.9.1",
+                "mensbeam/mimesniff": ">=0.2.0",
+                "php": ">=7.1"
+            },
+            "require-dev": {
+                "bamarni/composer-bin-plugin": "^1.3"
+            },
+            "suggest": {
+                "ext-ctype": "Improved performance"
+            },
+            "type": "library",
+            "autoload": {
+                "files": [
+                    "lib/Parser/ctype.php"
+                ],
+                "psr-4": {
+                    "MensBeam\\HTML\\": [
+                        "lib/"
+                    ]
+                },
+                "classmap": [
+                    "lib/Parser/Token.php"
+                ]
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "Dustin Wilson",
+                    "email": "dustin@dustinwilson.com",
+                    "homepage": "https://dustinwilson.com/"
+                },
+                {
+                    "name": "J. King",
+                    "email": "jking@jkingweb.ca",
+                    "homepage": "https://jkingweb.ca/"
+                }
+            ],
+            "description": "Parser and serializer for modern HTML documents",
+            "keywords": [
+                "HTML5",
+                "WHATWG",
+                "dom",
+                "html",
+                "parser",
+                "parsing"
+            ],
+            "support": {
+                "source": "https://github.com/mensbeam/HTML-Parser/tree/1.3.0"
+            },
+            "time": "2023-04-02T01:38:10+00:00"
+        },
+        {
+            "name": "mensbeam/intl",
+            "version": "0.9.2",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/mensbeam/intl.git",
+                "reference": "88dbf8398ab69e71164ac073f9ec011be2baa4ae"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/mensbeam/intl/zipball/88dbf8398ab69e71164ac073f9ec011be2baa4ae",
+                "reference": "88dbf8398ab69e71164ac073f9ec011be2baa4ae",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=7.1"
+            },
+            "require-dev": {
+                "bamarni/composer-bin-plugin": "*",
+                "ext-intl": "*"
+            },
+            "type": "library",
+            "autoload": {
+                "psr-4": {
+                    "MensBeam\\Intl\\": "lib/"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "J. King",
+                    "email": "jking@jkingweb.ca",
+                    "homepage": "https://jkingweb.ca/"
+                }
+            ],
+            "description": "A set of dependency-free basic internationalization tools",
+            "keywords": [
+                "WHATWG",
+                "charset",
+                "encoding",
+                "internationalization",
+                "intl",
+                "unicode",
+                "utf-8",
+                "utf8"
+            ],
+            "support": {
+                "issues": "https://github.com/mensbeam/intl/issues",
+                "source": "https://github.com/mensbeam/intl/tree/0.9.2"
+            },
+            "time": "2023-01-25T22:12:58+00:00"
+        },
+        {
+            "name": "mensbeam/mimesniff",
+            "version": "0.2.1",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/mensbeam/mime.git",
+                "reference": "c19be2496ab1e27fbf9c3483c2a9faa2781796cd"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/mensbeam/mime/zipball/c19be2496ab1e27fbf9c3483c2a9faa2781796cd",
+                "reference": "c19be2496ab1e27fbf9c3483c2a9faa2781796cd",
+                "shasum": ""
+            },
+            "require": {
+                "php": ">=7.1",
+                "psr/http-message": "^1.0"
+            },
+            "require-dev": {
+                "bamarni/composer-bin-plugin": "^1.3",
+                "ext-intl": "*"
+            },
+            "type": "library",
+            "autoload": {
+                "psr-4": {
+                    "MensBeam\\Mime\\": "lib/"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "J. King",
+                    "email": "jking@jkingweb.ca",
+                    "homepage": "https://jkingweb.ca/"
+                }
+            ],
+            "description": "An implementation of the WHATWG MIME Sniffing specification",
+            "keywords": [
+                "WHATWG",
+                "mime",
+                "mimesniff"
+            ],
+            "support": {
+                "issues": "https://github.com/mensbeam/mime/issues",
+                "source": "https://github.com/mensbeam/mime/tree/0.2.1"
+            },
+            "time": "2021-03-07T03:58:00+00:00"
+        },
+        {
+            "name": "psr/http-message",
+            "version": "1.1",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/php-fig/http-message.git",
+                "reference": "cb6ce4845ce34a8ad9e68117c10ee90a29919eba"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/php-fig/http-message/zipball/cb6ce4845ce34a8ad9e68117c10ee90a29919eba",
+                "reference": "cb6ce4845ce34a8ad9e68117c10ee90a29919eba",
+                "shasum": ""
+            },
+            "require": {
+                "php": "^7.2 || ^8.0"
+            },
+            "type": "library",
+            "extra": {
+                "branch-alias": {
+                    "dev-master": "1.1.x-dev"
+                }
+            },
+            "autoload": {
+                "psr-4": {
+                    "Psr\\Http\\Message\\": "src/"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "PHP-FIG",
+                    "homepage": "http://www.php-fig.org/"
+                }
+            ],
+            "description": "Common interface for HTTP messages",
+            "homepage": "https://github.com/php-fig/http-message",
+            "keywords": [
+                "http",
+                "http-message",
+                "psr",
+                "psr-7",
+                "request",
+                "response"
+            ],
+            "support": {
+                "source": "https://github.com/php-fig/http-message/tree/1.1"
+            },
+            "time": "2023-04-04T09:50:52+00:00"
         }
     ],
     "aliases": [],

vendor-bin/phpunit/composer.lock

@@ -622,16 +622,16 @@
         },
         {
             "name": "phpunit/phpunit",
-            "version": "9.6.6",
+            "version": "9.6.7",
             "source": {
                 "type": "git",
                 "url": "https://github.com/sebastianbergmann/phpunit.git",
-                "reference": "b65d59a059d3004a040c16a82e07bbdf6cfdd115"
+                "reference": "c993f0d3b0489ffc42ee2fe0bd645af1538a63b2"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/b65d59a059d3004a040c16a82e07bbdf6cfdd115",
-                "reference": "b65d59a059d3004a040c16a82e07bbdf6cfdd115",
+                "url": "https://api.github.com/repos/sebastianbergmann/phpunit/zipball/c993f0d3b0489ffc42ee2fe0bd645af1538a63b2",
+                "reference": "c993f0d3b0489ffc42ee2fe0bd645af1538a63b2",
                 "shasum": ""
             },
             "require": {
@@ -705,7 +705,7 @@
             "support": {
                 "issues": "https://github.com/sebastianbergmann/phpunit/issues",
                 "security": "https://github.com/sebastianbergmann/phpunit/security/policy",
-                "source": "https://github.com/sebastianbergmann/phpunit/tree/9.6.6"
+                "source": "https://github.com/sebastianbergmann/phpunit/tree/9.6.7"
             },
             "funding": [
                 {
@@ -721,7 +721,7 @@
                     "type": "tidelift"
                 }
             ],
-            "time": "2023-03-27T11:43:46+00:00"
+            "time": "2023-04-14T08:58:40+00:00"
         },
         {
             "name": "sebastian/cli-parser",

vendor-bin/robo/composer.lock

@@ -957,16 +957,16 @@
         },
         {
             "name": "symfony/console",
-            "version": "v6.2.7",
+            "version": "v6.2.8",
             "source": {
                 "type": "git",
                 "url": "https://github.com/symfony/console.git",
-                "reference": "cbad09eb8925b6ad4fb721c7a179344dc4a19d45"
+                "reference": "3582d68a64a86ec25240aaa521ec8bc2342b369b"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/symfony/console/zipball/cbad09eb8925b6ad4fb721c7a179344dc4a19d45",
-                "reference": "cbad09eb8925b6ad4fb721c7a179344dc4a19d45",
+                "url": "https://api.github.com/repos/symfony/console/zipball/3582d68a64a86ec25240aaa521ec8bc2342b369b",
+                "reference": "3582d68a64a86ec25240aaa521ec8bc2342b369b",
                 "shasum": ""
             },
             "require": {
@@ -1028,12 +1028,12 @@
             "homepage": "https://symfony.com",
             "keywords": [
                 "cli",
-                "command line",
+                "command-line",
                 "console",
                 "terminal"
             ],
             "support": {
-                "source": "https://github.com/symfony/console/tree/v6.2.7"
+                "source": "https://github.com/symfony/console/tree/v6.2.8"
             },
             "funding": [
                 {
@@ -1049,7 +1049,7 @@
                     "type": "tidelift"
                 }
             ],
-            "time": "2023-02-25T17:00:03+00:00"
+            "time": "2023-03-29T21:42:15+00:00"
         },
         {
             "name": "symfony/deprecation-contracts",
@@ -1120,16 +1120,16 @@
         },
         {
             "name": "symfony/event-dispatcher",
-            "version": "v6.2.7",
+            "version": "v6.2.8",
             "source": {
                 "type": "git",
                 "url": "https://github.com/symfony/event-dispatcher.git",
-                "reference": "404b307de426c1c488e5afad64403e5f145e82a5"
+                "reference": "04046f35fd7d72f9646e721fc2ecb8f9c67d3339"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/symfony/event-dispatcher/zipball/404b307de426c1c488e5afad64403e5f145e82a5",
-                "reference": "404b307de426c1c488e5afad64403e5f145e82a5",
+                "url": "https://api.github.com/repos/symfony/event-dispatcher/zipball/04046f35fd7d72f9646e721fc2ecb8f9c67d3339",
+                "reference": "04046f35fd7d72f9646e721fc2ecb8f9c67d3339",
                 "shasum": ""
             },
             "require": {
@@ -1183,7 +1183,7 @@
             "description": "Provides tools that allow your application components to communicate with each other by dispatching events and listening to them",
             "homepage": "https://symfony.com",
             "support": {
-                "source": "https://github.com/symfony/event-dispatcher/tree/v6.2.7"
+                "source": "https://github.com/symfony/event-dispatcher/tree/v6.2.8"
             },
             "funding": [
                 {
@@ -1199,7 +1199,7 @@
                     "type": "tidelift"
                 }
             ],
-            "time": "2023-02-14T08:44:56+00:00"
+            "time": "2023-03-20T16:06:02+00:00"
         },
         {
             "name": "symfony/event-dispatcher-contracts",
@@ -1818,16 +1818,16 @@
         },
         {
             "name": "symfony/process",
-            "version": "v6.2.7",
+            "version": "v6.2.8",
             "source": {
                 "type": "git",
                 "url": "https://github.com/symfony/process.git",
-                "reference": "680e8a2ea6b3f87aecc07a6a65a203ae573d1902"
+                "reference": "75ed64103df4f6615e15a7fe38b8111099f47416"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/symfony/process/zipball/680e8a2ea6b3f87aecc07a6a65a203ae573d1902",
-                "reference": "680e8a2ea6b3f87aecc07a6a65a203ae573d1902",
+                "url": "https://api.github.com/repos/symfony/process/zipball/75ed64103df4f6615e15a7fe38b8111099f47416",
+                "reference": "75ed64103df4f6615e15a7fe38b8111099f47416",
                 "shasum": ""
             },
             "require": {
@@ -1859,7 +1859,7 @@
             "description": "Executes commands in sub-processes",
             "homepage": "https://symfony.com",
             "support": {
-                "source": "https://github.com/symfony/process/tree/v6.2.7"
+                "source": "https://github.com/symfony/process/tree/v6.2.8"
             },
             "funding": [
                 {
@@ -1875,7 +1875,7 @@
                     "type": "tidelift"
                 }
             ],
-            "time": "2023-02-24T10:42:00+00:00"
+            "time": "2023-03-09T16:20:02+00:00"
         },
         {
             "name": "symfony/service-contracts",
@@ -1964,16 +1964,16 @@
         },
         {
             "name": "symfony/string",
-            "version": "v6.2.7",
+            "version": "v6.2.8",
             "source": {
                 "type": "git",
                 "url": "https://github.com/symfony/string.git",
-                "reference": "67b8c1eec78296b85dc1c7d9743830160218993d"
+                "reference": "193e83bbd6617d6b2151c37fff10fa7168ebddef"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/symfony/string/zipball/67b8c1eec78296b85dc1c7d9743830160218993d",
-                "reference": "67b8c1eec78296b85dc1c7d9743830160218993d",
+                "url": "https://api.github.com/repos/symfony/string/zipball/193e83bbd6617d6b2151c37fff10fa7168ebddef",
+                "reference": "193e83bbd6617d6b2151c37fff10fa7168ebddef",
                 "shasum": ""
             },
             "require": {
@@ -2030,7 +2030,7 @@
                 "utf8"
             ],
             "support": {
-                "source": "https://github.com/symfony/string/tree/v6.2.7"
+                "source": "https://github.com/symfony/string/tree/v6.2.8"
             },
             "funding": [
                 {
@@ -2046,7 +2046,7 @@
                     "type": "tidelift"
                 }
             ],
-            "time": "2023-02-24T10:42:00+00:00"
+            "time": "2023-03-20T16:06:02+00:00"
         },
         {
             "name": "symfony/yaml",