use html5 parser and update php-mf2

composer.json

@@ -5,7 +5,7 @@
   "homepage": "https://github.com/aaronpk/XRay",
   "description": "X-Ray returns structured data from any URL",
   "require": {
-    "mf2/mf2": ">=0.4.0",
+    "mf2/mf2": "0.4.4-alpha",
     "ezyang/htmlpurifier": "4.10.*",
     "indieweb/link-rel-parser": "0.1.*",
     "dg/twitter-php": "3.6.*",
@@ -13,7 +13,8 @@
     "p3k/http": ">=0.1.7",
     "cebe/markdown": "1.1.*",
     "p3k/picofeed": ">=0.1.38",
-    "facebook/graph-sdk": "^5.5"
+    "facebook/graph-sdk": "^5.5",
+    "masterminds/html5": "^2.3"
   },
   "autoload": {
     "psr-4": {

composer.lock

@@ -4,7 +4,7 @@
         "Read more about it at https://getcomposer.org/doc/01-basic-usage.md#composer-lock-the-lock-file",
         "This file is @generated automatically"
     ],
-    "content-hash": "60f545028d44eb8e15c499fbe7ecf4d0",
+    "content-hash": "2c97abbbb6d2a94d0b72828c1edc41a3",
     "packages": [
         {
             "name": "cebe/markdown",
@@ -259,18 +259,83 @@
             ],
             "time": "2017-01-11T17:14:49+00:00"
         },
+        {
+            "name": "masterminds/html5",
+            "version": "2.3.0",
+            "source": {
+                "type": "git",
+                "url": "https://github.com/Masterminds/html5-php.git",
+                "reference": "2c37c6c520b995b761674de3be8455a381679067"
+            },
+            "dist": {
+                "type": "zip",
+                "url": "https://api.github.com/repos/Masterminds/html5-php/zipball/2c37c6c520b995b761674de3be8455a381679067",
+                "reference": "2c37c6c520b995b761674de3be8455a381679067",
+                "shasum": ""
+            },
+            "require": {
+                "ext-libxml": "*",
+                "php": ">=5.3.0"
+            },
+            "require-dev": {
+                "phpunit/phpunit": "4.*",
+                "sami/sami": "~2.0",
+                "satooshi/php-coveralls": "1.0.*"
+            },
+            "type": "library",
+            "extra": {
+                "branch-alias": {
+                    "dev-master": "2.2-dev"
+                }
+            },
+            "autoload": {
+                "psr-4": {
+                    "Masterminds\\": "src"
+                }
+            },
+            "notification-url": "https://packagist.org/downloads/",
+            "license": [
+                "MIT"
+            ],
+            "authors": [
+                {
+                    "name": "Matt Butcher",
+                    "email": "technosophos@gmail.com"
+                },
+                {
+                    "name": "Asmir Mustafic",
+                    "email": "goetas@gmail.com"
+                },
+                {
+                    "name": "Matt Farina",
+                    "email": "matt@mattfarina.com"
+                }
+            ],
+            "description": "An HTML5 parser and serializer.",
+            "homepage": "http://masterminds.github.io/html5-php",
+            "keywords": [
+                "HTML5",
+                "dom",
+                "html",
+                "parser",
+                "querypath",
+                "serializer",
+                "xml"
+            ],
+            "time": "2017-09-04T12:26:28+00:00"
+        },
         {
             "name": "mf2/mf2",
-            "version": "v0.4.1",
+            "version": "v0.4.4-alpha",
             "source": {
                 "type": "git",
                 "url": "https://github.com/indieweb/php-mf2.git",
-                "reference": "e044330550a16d1a512248a5b9f663736538da44"
+                "reference": "e8da04f93d548d26287a8980eca4216639cbc61d"
             },
             "dist": {
                 "type": "zip",
-                "url": "https://api.github.com/repos/indieweb/php-mf2/zipball/e044330550a16d1a512248a5b9f663736538da44",
-                "reference": "e044330550a16d1a512248a5b9f663736538da44",
+                "url": "https://api.github.com/repos/indieweb/php-mf2/zipball/e8da04f93d548d26287a8980eca4216639cbc61d",
+                "reference": "e8da04f93d548d26287a8980eca4216639cbc61d",
                 "shasum": ""
             },
             "require": {
@@ -282,7 +347,8 @@
                 "phpunit/phpunit": "4.8.*"
             },
             "suggest": {
-                "barnabywalters/mf-cleaner": "To more easily handle the canonical data php-mf2 gives you"
+                "barnabywalters/mf-cleaner": "To more easily handle the canonical data php-mf2 gives you",
+                "masterminds/html5": "Alternative HTML parser for PHP, for better HTML5 support."
             },
             "bin": [
                 "bin/fetch-mf2",
@@ -312,7 +378,7 @@
                 "parser",
                 "semantic"
             ],
-            "time": "2018-03-15T16:51:15+00:00"
+            "time": "2018-03-29T20:48:28+00:00"
         },
         {
             "name": "p3k/http",
@@ -2089,7 +2155,9 @@
     ],
     "aliases": [],
     "minimum-stability": "stable",
-    "stability-flags": [],
+    "stability-flags": {
+        "mf2/mf2": 15
+    },
     "prefer-stable": false,
     "prefer-lowest": false,
     "platform": [],

controllers/Parse.php

@@ -10,7 +10,7 @@ class Parse {
   public $mc;
   private $_cacheTime = 120;
   private $_pretty = false;
-  private static $_version = '1.4.21';
+  private static $_version = '1.4.24';
 
   public static function useragent() {
     return 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.133 Safari/537.36 XRay/'.self::$_version.' ('.\Config::$base.')';

tests/ParseTest.php

@@ -684,4 +684,16 @@ class ParseTest extends PHPUnit_Framework_TestCase {
     $this->assertEquals(1, count($data['data']['like-of']));
   }
 
+  public function testHTML5Markup() {
+    $url = 'http://source.example.com/html5-tags';
+    $response = $this->parse(['url' => $url]);
+
+    $body = $response->getContent();
+    $this->assertEquals(200, $response->getStatusCode());
+    $data = json_decode($body, true);
+
+    $this->assertEquals('Hello World', $data['data']['name']);
+    $this->assertEquals('The content of the blog post', $data['data']['content']['text']);
+  }
+
 }

tests/data/source.example.com/html5-tags

@@ -0,0 +1,17 @@
+HTTP/1.1 200 OK
+Server: Apache
+Date: Wed, 09 Dec 2015 03:29:14 GMT
+Content-Type: text/html; charset=utf-8
+Connection: keep-alive
+
+<html>
+  <head>
+    <title>Test</title>
+  </head>
+  <body>
+    <div class="h-entry">
+      <p class="p-name">Hello World
+      <article class="e-content">The content of the blog post</article>
+    </div>
+  </body>
+</html>