update readme

we already say "warning" in bold and upper case — the warning emoji feels unnecessary

.gitattributes

@@ -0,0 +1,6 @@
+# Ignore all tests for archive
+/test               export-ignore
+/.gitattributes     export-ignore
+/.gitignore         export-ignore
+/.travis.yml        export-ignore
+/phpunit.xml.dist   export-ignore

.gitignore

@@ -0,0 +1,2 @@
+composer.lock
+vendor/

.travis.yml

@@ -1,9 +1,30 @@
 language: php
 
-php:
-  - 5.6
-  - 5.5
-  - 5.4
-  - 5.3
-  - 5.2
-  - hhvm
+matrix:
+  include:
+    - php: 5.3
+      dist: precise
+    - php: 5.4
+      dist: trusty
+    - php: 5.5
+      dist: trusty
+    - php: 5.6
+      dist: xenial
+    - php: 7.0
+      dist: xenial
+    - php: 7.1
+      dist: bionic
+    - php: 7.2
+      dist: bionic
+    - php: 7.3
+      dist: bionic
+    - php: 7.4
+      dist: bionic
+
+install:
+  - composer install --prefer-dist --no-interaction --no-progress
+
+script:
+  - vendor/bin/phpunit
+  - vendor/bin/phpunit test/CommonMarkTestWeak.php || true
+  - '[ -z "$TRAVIS_TAG" ] || [ "$TRAVIS_TAG" == "$(php -r "require(\"Parsedown.php\"); echo Parsedown::version;")" ]'

LICENSE.txt

@@ -1,6 +1,6 @@
 The MIT License (MIT)
 
-Copyright (c) 2013 Emanuil Rusev, erusev.com
+Copyright (c) 2013-2018 Emanuil Rusev, erusev.com
 
 Permission is hereby granted, free of charge, to any person obtaining a copy of
 this software and associated documentation files (the "Software"), to deal in
@@ -17,4 +17,4 @@ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
 FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
 COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
 IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

README.md

@@ -1,26 +1,103 @@
-## Parsedown
+<!-- ![Parsedown](https://i.imgur.com/yE8afYV.png) -->
 
-Better [Markdown](http://en.wikipedia.org/wiki/Markdown) parser for PHP.
+<p align="center"><img alt="Parsedown" src="https://i.imgur.com/fKVY6Kz.png" width="240" /></p>
 
-- [Demo](http://parsedown.org/demo)
-- [Tests](http://parsedown.org/tests/)
+<h1>Parsedown</h1>
 
-### Features
+[![Build Status](https://travis-ci.org/erusev/parsedown.svg)](https://travis-ci.org/erusev/parsedown)
+[![Total Downloads](https://poser.pugx.org/erusev/parsedown/d/total.svg)](https://packagist.org/packages/erusev/parsedown)
+[![Version](https://poser.pugx.org/erusev/parsedown/v/stable.svg)](https://packagist.org/packages/erusev/parsedown)
+[![License](https://poser.pugx.org/erusev/parsedown/license.svg)](https://packagist.org/packages/erusev/parsedown)
 
-* [Fast](http://parsedown.org/speed)
-* [Consistent](http://parsedown.org/consistency)
-* [GitHub Flavored](https://help.github.com/articles/github-flavored-markdown)
-* [Tested](https://travis-ci.org/erusev/parsedown) in PHP 5.2, 5.3, 5.4, 5.5, 5.6 and [hhvm](http://www.hhvm.com/)
+Better Markdown Parser in PHP - <a href="http://parsedown.org/demo">Demo</a>.
+
+## Features
+
+* One File
+* No Dependencies
+* [Super Fast](http://parsedown.org/speed)
 * Extensible
+* [GitHub flavored](https://github.github.com/gfm)
+* [Tested](http://parsedown.org/tests/) in 5.3 to 7.3
+* [Markdown Extra extension](https://github.com/erusev/parsedown-extra)
 
-### Installation
+## Installation
 
-Include `Parsedown.php` or install [the composer package](https://packagist.org/packages/erusev/parsedown).
+Install the [composer package]:
 
-### Example
+    composer require erusev/parsedown
 
-``` php
+Or download the [latest release] and include `Parsedown.php`
+
+[composer package]: https://packagist.org/packages/erusev/parsedown "The Parsedown package on packagist.org"
+[latest release]: https://github.com/erusev/parsedown/releases/latest "The latest release of Parsedown"
+
+## Example
+
+```php
 $Parsedown = new Parsedown();
 
 echo $Parsedown->text('Hello _Parsedown_!'); # prints: <p>Hello <em>Parsedown</em>!</p>
 ```
+
+You can also parse inline markdown only:
+
+```php
+echo $Parsedown->line('Hello _Parsedown_!'); # prints: Hello <em>Parsedown</em>!
+```
+
+More examples in [the wiki](https://github.com/erusev/parsedown/wiki/) and in [this video tutorial](http://youtu.be/wYZBY8DEikI).
+
+## Security
+
+Parsedown is capable of escaping user-input within the HTML that it generates. Additionally Parsedown will apply sanitisation to additional scripting vectors (such as scripting link destinations) that are introduced by the markdown syntax itself.
+
+To tell Parsedown that it is processing untrusted user-input, use the following:
+
+```php
+$Parsedown->setSafeMode(true);
+```
+
+If instead, you wish to allow HTML within untrusted user-input, but still want output to be free from XSS it is recommended that you make use of a HTML sanitiser that allows HTML tags to be whitelisted, like [HTML Purifier](http://htmlpurifier.org/).
+
+In both cases you should strongly consider employing defence-in-depth measures, like [deploying a Content-Security-Policy](https://scotthelme.co.uk/content-security-policy-an-introduction/) (a browser security feature) so that your page is likely to be safe even if an attacker finds a vulnerability in one of the first lines of defence above.
+
+#### Security of Parsedown Extensions
+
+Safe mode does not necessarily yield safe results when using extensions to Parsedown. Extensions should be evaluated on their own to determine their specific safety against XSS.
+
+## Escaping HTML
+
+> **WARNING:** This method isn't safe from XSS!
+
+If you wish to escape HTML **in trusted input**, you can use the following:
+
+```php
+$Parsedown->setMarkupEscaped(true);
+```
+
+Beware that this still allows users to insert unsafe scripting vectors, such as links like `[xss](javascript:alert%281%29)`.
+
+## Questions
+
+**How does Parsedown work?**
+
+It tries to read Markdown like a human. First, it looks at the lines. It’s interested in how the lines start. This helps it recognise blocks. It knows, for example, that if a line starts with a `-` then perhaps it belongs to a list. Once it recognises the blocks, it continues to the content. As it reads, it watches out for special characters. This helps it recognise inline elements (or inlines).
+
+We call this approach "line based". We believe that Parsedown is the first Markdown parser to use it. Since the release of Parsedown, other developers have used the same approach to develop other Markdown parsers in PHP and in other languages.
+
+**Is it compliant with CommonMark?**
+
+It passes most of the CommonMark tests. Most of the tests that don't pass deal with cases that are quite uncommon. Still, as CommonMark matures, compliance should improve.
+
+**Who uses it?**
+
+[Laravel Framework](https://laravel.com/), [Bolt CMS](http://bolt.cm/), [Grav CMS](http://getgrav.org/), [Herbie CMS](http://www.getherbie.org/), [Kirby CMS](http://getkirby.com/), [October CMS](http://octobercms.com/), [Pico CMS](http://picocms.org), [Statamic CMS](http://www.statamic.com/), [phpDocumentor](http://www.phpdoc.org/), [RaspberryPi.org](http://www.raspberrypi.org/), [Symfony Demo](https://github.com/symfony/demo) and [more](https://packagist.org/packages/erusev/parsedown/dependents).
+
+**How can I help?**
+
+Use it, star it, share it and if you feel generous, [donate](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=528P3NZQMP8N2).
+
+**What else should I know?**
+
+I also make [Nota](https://nota.md/) — a writing app designed for Markdown files :)

composer.json

@@ -12,7 +12,22 @@
             "homepage": "http://erusev.com"
         }
     ],
+    "require": {
+        "php": ">=5.3.0",
+        "ext-mbstring": "*"
+    },
+    "require-dev": {
+        "phpunit/phpunit": "^4.8.35"
+    },
     "autoload": {
         "psr-0": {"Parsedown": ""}
+    },
+    "autoload-dev": {
+        "psr-0": {
+            "TestParsedown": "test/",
+            "ParsedownTest": "test/",
+            "CommonMarkTest": "test/",
+            "CommonMarkTestWeak": "test/"
+        }
     }
-}
+}

phpunit.xml.dist

@@ -1,8 +1,8 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<phpunit colors="true">
+<phpunit bootstrap="vendor/autoload.php" colors="true">
 	<testsuites>
 		<testsuite>
-			<file>tests/Test.php</file>
+			<file>test/ParsedownTest.php</file>
 		</testsuite>
 	</testsuites>
-</phpunit>
+</phpunit>

test/CommonMarkTestStrict.php

@@ -0,0 +1,71 @@
+<?php
+
+/**
+ * Test Parsedown against the CommonMark spec
+ *
+ * @link http://commonmark.org/ CommonMark
+ */
+class CommonMarkTestStrict extends PHPUnit_Framework_TestCase
+{
+    const SPEC_URL = 'https://raw.githubusercontent.com/jgm/CommonMark/master/spec.txt';
+
+    protected $parsedown;
+
+    protected function setUp()
+    {
+        $this->parsedown = new TestParsedown();
+        $this->parsedown->setUrlsLinked(false);
+    }
+
+    /**
+     * @dataProvider data
+     * @param $id
+     * @param $section
+     * @param $markdown
+     * @param $expectedHtml
+     */
+    public function testExample($id, $section, $markdown, $expectedHtml)
+    {
+        $actualHtml = $this->parsedown->text($markdown);
+        $this->assertEquals($expectedHtml, $actualHtml);
+    }
+
+    /**
+     * @return array
+     */
+    public function data()
+    {
+        $spec = file_get_contents(self::SPEC_URL);
+        if ($spec === false) {
+            $this->fail('Unable to load CommonMark spec from ' . self::SPEC_URL);
+        }
+
+        $spec = str_replace("\r\n", "\n", $spec);
+        $spec = strstr($spec, '<!-- END TESTS -->', true);
+
+        $matches = array();
+        preg_match_all('/^`{32} example\n((?s).*?)\n\.\n(?:|((?s).*?)\n)`{32}$|^#{1,6} *(.*?)$/m', $spec, $matches, PREG_SET_ORDER);
+
+        $data = array();
+        $currentId = 0;
+        $currentSection = '';
+        foreach ($matches as $match) {
+            if (isset($match[3])) {
+                $currentSection = $match[3];
+            } else {
+                $currentId++;
+                $markdown = str_replace('→', "\t", $match[1]);
+                $expectedHtml = isset($match[2]) ? str_replace('→', "\t", $match[2]) : '';
+
+                $data[$currentId] = array(
+                    'id' => $currentId,
+                    'section' => $currentSection,
+                    'markdown' => $markdown,
+                    'expectedHtml' => $expectedHtml
+                );
+            }
+        }
+
+        return $data;
+    }
+}

test/CommonMarkTestWeak.php

@@ -0,0 +1,63 @@
+<?php
+require_once(__DIR__ . '/CommonMarkTestStrict.php');
+
+/**
+ * Test Parsedown against the CommonMark spec, but less aggressive
+ *
+ * The resulting HTML markup is cleaned up before comparison, so examples
+ * which would normally fail due to actually invisible differences (e.g.
+ * superfluous whitespaces), don't fail. However, cleanup relies on block
+ * element detection. The detection doesn't work correctly when a element's
+ * `display` CSS property is manipulated. According to that this test is only
+ * a interim solution on Parsedown's way to full CommonMark compatibility.
+ *
+ * @link http://commonmark.org/ CommonMark
+ */
+class CommonMarkTestWeak extends CommonMarkTestStrict
+{
+    protected $textLevelElementRegex;
+
+    protected function setUp()
+    {
+        parent::setUp();
+
+        $textLevelElements = $this->parsedown->getTextLevelElements();
+        array_walk($textLevelElements, function (&$element) {
+            $element = preg_quote($element, '/');
+        });
+        $this->textLevelElementRegex = '\b(?:' . implode('|', $textLevelElements) . ')\b';
+    }
+
+    /**
+     * @dataProvider data
+     * @param $id
+     * @param $section
+     * @param $markdown
+     * @param $expectedHtml
+     */
+    public function testExample($id, $section, $markdown, $expectedHtml)
+    {
+        $expectedHtml = $this->cleanupHtml($expectedHtml);
+
+        $actualHtml = $this->parsedown->text($markdown);
+        $actualHtml = $this->cleanupHtml($actualHtml);
+
+        $this->assertEquals($expectedHtml, $actualHtml);
+    }
+
+    protected function cleanupHtml($markup)
+    {
+        // invisible whitespaces at the beginning and end of block elements
+        // however, whitespaces at the beginning of <pre> elements do matter
+        $markup = preg_replace(
+            array(
+                '/(<(?!(?:' . $this->textLevelElementRegex . '|\bpre\b))\w+\b[^>]*>(?:<' . $this->textLevelElementRegex . '[^>]*>)*)\s+/s',
+                '/\s+((?:<\/' . $this->textLevelElementRegex . '>)*<\/(?!' . $this->textLevelElementRegex . ')\w+\b>)/s'
+            ),
+            '$1',
+            $markup
+        );
+
+        return $markup;
+    }
+}

test/ParsedownTest.php

@@ -0,0 +1,199 @@
+<?php
+require 'SampleExtensions.php';
+
+use PHPUnit\Framework\TestCase;
+
+class ParsedownTest extends TestCase
+{
+    final function __construct($name = null, array $data = array(), $dataName = '')
+    {
+        $this->dirs = $this->initDirs();
+        $this->Parsedown = $this->initParsedown();
+
+        parent::__construct($name, $data, $dataName);
+    }
+
+    private $dirs;
+    protected $Parsedown;
+
+    /**
+     * @return array
+     */
+    protected function initDirs()
+    {
+        $dirs []= dirname(__FILE__).'/data/';
+
+        return $dirs;
+    }
+
+    /**
+     * @return Parsedown
+     */
+    protected function initParsedown()
+    {
+        $Parsedown = new TestParsedown();
+
+        return $Parsedown;
+    }
+
+    /**
+     * @dataProvider data
+     * @param $test
+     * @param $dir
+     */
+    function test_($test, $dir)
+    {
+        $markdown = file_get_contents($dir . $test . '.md');
+
+        $expectedMarkup = file_get_contents($dir . $test . '.html');
+
+        $expectedMarkup = str_replace("\r\n", "\n", $expectedMarkup);
+        $expectedMarkup = str_replace("\r", "\n", $expectedMarkup);
+
+        $this->Parsedown->setSafeMode(substr($test, 0, 3) === 'xss');
+        $this->Parsedown->setStrictMode(substr($test, 0, 6) === 'strict');
+
+        $actualMarkup = $this->Parsedown->text($markdown);
+
+        $this->assertEquals($expectedMarkup, $actualMarkup);
+    }
+
+    function testRawHtml()
+    {
+        $markdown = "```php\nfoobar\n```";
+        $expectedMarkup = '<pre><code class="language-php"><p>foobar</p></code></pre>';
+        $expectedSafeMarkup = '<pre><code class="language-php">&lt;p&gt;foobar&lt;/p&gt;</code></pre>';
+
+        $unsafeExtension = new UnsafeExtension;
+        $actualMarkup = $unsafeExtension->text($markdown);
+
+        $this->assertEquals($expectedMarkup, $actualMarkup);
+
+        $unsafeExtension->setSafeMode(true);
+        $actualSafeMarkup = $unsafeExtension->text($markdown);
+
+        $this->assertEquals($expectedSafeMarkup, $actualSafeMarkup);
+    }
+
+    function testTrustDelegatedRawHtml()
+    {
+        $markdown = "```php\nfoobar\n```";
+        $expectedMarkup = '<pre><code class="language-php"><p>foobar</p></code></pre>';
+        $expectedSafeMarkup = $expectedMarkup;
+
+        $unsafeExtension = new TrustDelegatedExtension;
+        $actualMarkup = $unsafeExtension->text($markdown);
+
+        $this->assertEquals($expectedMarkup, $actualMarkup);
+
+        $unsafeExtension->setSafeMode(true);
+        $actualSafeMarkup = $unsafeExtension->text($markdown);
+
+        $this->assertEquals($expectedSafeMarkup, $actualSafeMarkup);
+    }
+
+    function data()
+    {
+        $data = array();
+
+        foreach ($this->dirs as $dir)
+        {
+            $Folder = new DirectoryIterator($dir);
+
+            foreach ($Folder as $File)
+            {
+                /** @var $File DirectoryIterator */
+
+                if ( ! $File->isFile())
+                {
+                    continue;
+                }
+
+                $filename = $File->getFilename();
+
+                $extension = pathinfo($filename, PATHINFO_EXTENSION);
+
+                if ($extension !== 'md')
+                {
+                    continue;
+                }
+
+                $basename = $File->getBasename('.md');
+
+                if (file_exists($dir . $basename . '.html'))
+                {
+                    $data []= array($basename, $dir);
+                }
+            }
+        }
+
+        return $data;
+    }
+
+    public function test_no_markup()
+    {
+        $markdownWithHtml = <<<MARKDOWN_WITH_MARKUP
+<div>_content_</div>
+
+sparse:
+
+<div>
+<div class="inner">
+_content_
+</div>
+</div>
+
+paragraph
+
+<style type="text/css">
+    p {
+        color: red;
+    }
+</style>
+
+comment
+
+<!-- html comment -->
+MARKDOWN_WITH_MARKUP;
+
+        $expectedHtml = <<<EXPECTED_HTML
+<p>&lt;div&gt;<em>content</em>&lt;/div&gt;</p>
+<p>sparse:</p>
+<p>&lt;div&gt;
+&lt;div class="inner"&gt;
+<em>content</em>
+&lt;/div&gt;
+&lt;/div&gt;</p>
+<p>paragraph</p>
+<p>&lt;style type="text/css"&gt;
+p {
+color: red;
+}
+&lt;/style&gt;</p>
+<p>comment</p>
+<p>&lt;!-- html comment --&gt;</p>
+EXPECTED_HTML;
+
+        $parsedownWithNoMarkup = new TestParsedown();
+        $parsedownWithNoMarkup->setMarkupEscaped(true);
+        $this->assertEquals($expectedHtml, $parsedownWithNoMarkup->text($markdownWithHtml));
+    }
+
+    public function testLateStaticBinding()
+    {
+        $parsedown = Parsedown::instance();
+        $this->assertInstanceOf('Parsedown', $parsedown);
+
+        // After instance is already called on Parsedown
+        // subsequent calls with the same arguments return the same instance
+        $sameParsedown = TestParsedown::instance();
+        $this->assertInstanceOf('Parsedown', $sameParsedown);
+        $this->assertSame($parsedown, $sameParsedown);
+
+        $testParsedown = TestParsedown::instance('test late static binding');
+        $this->assertInstanceOf('TestParsedown', $testParsedown);
+
+        $sameInstanceAgain = TestParsedown::instance('test late static binding');
+        $this->assertSame($testParsedown, $sameInstanceAgain);
+    }
+}

test/SampleExtensions.php

@@ -0,0 +1,40 @@
+<?php
+
+class UnsafeExtension extends Parsedown
+{
+    protected function blockFencedCodeComplete($Block)
+    {
+        $text = $Block['element']['element']['text'];
+        unset($Block['element']['element']['text']);
+
+        // WARNING: There is almost always a better way of doing things!
+        //
+        // This example is one of them, unsafe behaviour is NOT needed here.
+        // Only use this if you trust the input and have no idea what
+        // the output HTML will look like (e.g. using an external parser).
+        $Block['element']['element']['rawHtml'] = "<p>$text</p>";
+
+        return $Block;
+    }
+}
+
+
+class TrustDelegatedExtension extends Parsedown
+{
+    protected function blockFencedCodeComplete($Block)
+    {
+        $text = $Block['element']['element']['text'];
+        unset($Block['element']['element']['text']);
+
+        // WARNING: There is almost always a better way of doing things!
+        //
+        // This behaviour is NOT needed in the demonstrated case.
+        // Only use this if you are sure that the result being added into
+        // rawHtml is safe.
+        // (e.g. using an external parser with escaping capabilities).
+        $Block['element']['element']['rawHtml'] = "<p>$text</p>";
+        $Block['element']['element']['allowRawHtmlInSafeMode'] = true;
+
+        return $Block;
+    }
+}

test/TestParsedown.php

@@ -0,0 +1,9 @@
+<?php
+
+class TestParsedown extends Parsedown
+{
+    public function getTextLevelElements()
+    {
+        return $this->textLevelElements;
+    }
+}

test/data/aligned_table.html

@@ -0,0 +1,21 @@
+<table>
+<thead>
+<tr>
+<th style="text-align: left;">header 1</th>
+<th style="text-align: center;">header 2</th>
+<th style="text-align: right;">header 2</th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td style="text-align: left;">cell 1.1</td>
+<td style="text-align: center;">cell 1.2</td>
+<td style="text-align: right;">cell 1.3</td>
+</tr>
+<tr>
+<td style="text-align: left;">cell 2.1</td>
+<td style="text-align: center;">cell 2.2</td>
+<td style="text-align: right;">cell 2.3</td>
+</tr>
+</tbody>
+</table>

test/data/atx_heading.html

@@ -0,0 +1,13 @@
+<h1>h1</h1>
+<h2>h2</h2>
+<h3>h3</h3>
+<h4>h4</h4>
+<h5>h5</h5>
+<h6>h6</h6>
+<p>####### not a heading</p>
+<h1>closed h1</h1>
+<h1></h1>
+<h2></h2>
+<h1># of levels</h1>
+<h1># of levels #</h1>
+<h1>heading</h1>

test/data/atx_heading.md

@@ -0,0 +1,25 @@
+# h1
+
+## h2
+
+### h3
+
+#### h4
+
+##### h5
+
+###### h6
+
+####### not a heading
+
+# closed h1 #
+
+#
+
+##
+
+# # of levels
+
+# # of levels # #
+
+#heading

test/data/block-level_html.html

@@ -0,0 +1,12 @@
+<div>_content_</div>
+<p>paragraph</p>
+<div>
+  <div class="inner">
+    _content_
+  </div>
+</div>
+<style type="text/css">
+  p {color: #789;}
+</style>
+<div>
+  <a href="/">home</a></div>

test/data/block-level_html.md

@@ -0,0 +1,16 @@
+<div>_content_</div>
+
+paragraph
+
+<div>
+  <div class="inner">
+    _content_
+  </div>
+</div>
+
+<style type="text/css">
+  p {color: #789;}
+</style>
+
+<div>
+  <a href="/">home</a></div>

test/data/code_block.html

@@ -1,8 +1,13 @@
-<pre><code>&lt;?php
-
-$message = 'Hello World!';
-echo $message;</code></pre>
-<hr />
-<pre><code>&gt; not a quote
-- not a list item
-[not a reference]: http://foo.com</code></pre>
+<pre><code>&lt;?php
+
+$message = 'Hello World!';
+echo $message;</code></pre>
+<hr />
+<pre><code>&gt; not a quote
+- not a list item
+[not a reference]: http://foo.com</code></pre>
+<hr />
+<pre><code>foo
+
+
+bar</code></pre>

test/data/code_block.md

@@ -1,10 +1,17 @@
-    <?php
-
-    $message = 'Hello World!';
-    echo $message;
-
----
-
-    > not a quote
-    - not a list item
-    [not a reference]: http://foo.com
+    <?php
+
+    $message = 'Hello World!';
+    echo $message;
+
+---
+
+    > not a quote
+    - not a list item
+    [not a reference]: http://foo.com
+
+---
+
+    foo
+
+
+    bar

test/data/deeply_nested_list.html

@@ -0,0 +1,40 @@
+<ul>
+<li>li<ul>
+<li>li<ul>
+<li>li</li>
+<li>li</li>
+</ul>
+</li>
+<li>li</li>
+</ul>
+</li>
+<li>li</li>
+</ul>
+<hr />
+<ul>
+<li>level 1<ul>
+<li>level 2<ul>
+<li>level 3<ul>
+<li>level 4<ul>
+<li>level 5</li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+</li>
+</ul>
+<hr />
+<ul>
+<li>a</li>
+<li>b</li>
+<li>c</li>
+<li>d</li>
+<li>e</li>
+<li>f</li>
+<li>g</li>
+<li>h</li>
+<li>i</li>
+</ul>

test/data/deeply_nested_list.md

@@ -0,0 +1,26 @@
+- li
+    - li
+        - li
+        - li
+    - li
+- li
+
+---
+
+- level 1
+  - level 2
+    - level 3
+      - level 4
+        - level 5
+
+---
+
+- a
+ - b
+  - c
+   - d
+    - e
+   - f
+  - g
+ - h
+- i

test/data/email.html

@@ -0,0 +1,2 @@
+<p>my email is <a href="mailto:me@example.com">me@example.com</a></p>
+<p>html tags shouldn't start an email autolink <strong>first.last@example.com</strong></p>

test/data/email.md

@@ -0,0 +1,3 @@
+my email is <me@example.com>
+
+html tags shouldn't start an email autolink <strong>first.last@example.com</strong>

test/data/emphasis.html

@@ -1,8 +1,8 @@
-<p><em>underscore</em>, <em>asterisk</em>, <em>one two</em>, <em>three four</em>, <em>a</em>, <em>b</em></p>
-<p><strong>strong</strong> and <em>em</em> and <strong>strong</strong> and <em>em</em></p>
-<p><em>line
-line
-line</em></p>
-<p>this_is_not_an_emphasis</p>
-<p>an empty emphasis __ ** is not an emphasis</p>
+<p><em>underscore</em>, <em>asterisk</em>, <em>one two</em>, <em>three four</em>, <em>a</em>, <em>b</em></p>
+<p><strong>strong</strong> and <em>em</em> and <strong>strong</strong> and <em>em</em></p>
+<p><em>line
+line
+line</em></p>
+<p>this_is_not_an_emphasis</p>
+<p>an empty emphasis __ ** is not an emphasis</p>
 <p>*mixed *<em>double and</em> single asterisk** spans</p>

test/data/emphasis.md

@@ -1,13 +1,13 @@
-_underscore_, *asterisk*, _one two_, *three four*, _a_, *b*
-
-**strong** and *em* and **strong** and *em*
-
-_line
-line
-line_
-
-this_is_not_an_emphasis
-
-an empty emphasis __ ** is not an emphasis
-
+_underscore_, *asterisk*, _one two_, *three four*, _a_, *b*
+
+**strong** and *em* and **strong** and *em*
+
+_line
+line
+line_
+
+this_is_not_an_emphasis
+
+an empty emphasis __ ** is not an emphasis
+
 *mixed **double and* single asterisk** spans

test/data/escaping.html

@@ -1,4 +1,6 @@
 <p>escaped *emphasis*.</p>
 <p><code>escaped \*emphasis\* in a code span</code></p>
 <pre><code>escaped \*emphasis\* in a code block</code></pre>
-<p>\ ` * _ { } [ ] ( ) > # + - . !</p>
+<p>\ ` * _ { } [ ] ( ) > # + - . !</p>
+<p><em>one_two</em> <strong>one_two</strong></p>
+<p><em>one*two</em> <strong>one*two</strong></p>

test/data/escaping.md

@@ -4,4 +4,8 @@ escaped \*emphasis\*.
 
     escaped \*emphasis\* in a code block
 
-\\ \` \* \_ \{ \} \[ \] \( \) \> \# \+ \- \. \!
+\\ \` \* \_ \{ \} \[ \] \( \) \> \# \+ \- \. \!
+
+_one\_two_ __one\_two__
+
+*one\*two* **one\*two**

test/data/fenced_code_block.html

@@ -0,0 +1,18 @@
+<pre><code>&lt;?php
+
+$message = 'fenced code block';
+echo $message;</code></pre>
+<pre><code>tilde</code></pre>
+<pre><code class="language-php">echo 'language identifier';</code></pre>
+<pre><code class="language-c#">echo 'language identifier with non words';</code></pre>
+<pre><code class="language-html+php">&lt;?php
+echo "Hello World";
+?&gt;
+&lt;a href="http://auraphp.com" &gt;Aura Project&lt;/a&gt;</code></pre>
+<pre><code>the following isn't quite enough to close
+```
+still a fenced code block</code></pre>
+<pre><code>foo
+
+
+bar</code></pre>

test/data/fenced_code_block.md

@@ -0,0 +1,38 @@
+```
+<?php
+
+$message = 'fenced code block';
+echo $message;
+```
+
+~~~
+tilde
+~~~
+
+```php
+echo 'language identifier';
+```
+
+```c#
+echo 'language identifier with non words';
+```
+
+```html+php
+<?php
+echo "Hello World";
+?>
+<a href="http://auraphp.com" >Aura Project</a>
+```
+
+````
+the following isn't quite enough to close
+```
+still a fenced code block
+````
+
+```
+foo
+
+
+bar
+```

test/data/horizontal_rule.html

@@ -1,5 +1,5 @@
-<hr />
-<hr />
-<hr />
-<hr />
+<hr />
+<hr />
+<hr />
+<hr />
 <hr />

test/data/horizontal_rule.md

@@ -1,9 +1,9 @@
----
-
-- - -
-
-   - - -
-
-***
-
+---
+
+- - -
+
+   - - -
+
+***
+
 ___

test/data/html_comment.html

@@ -0,0 +1,11 @@
+<!-- single line -->
+<p>paragraph</p>
+<!-- 
+  multiline -->
+<p>paragraph</p>
+<!-- sss -->abc
+<ul>
+<li>abcd</li>
+<li>bbbb</li>
+<li>cccc</li>
+</ul>

test/data/html_comment.md

@@ -0,0 +1,14 @@
+<!-- single line -->
+
+paragraph
+
+<!-- 
+  multiline -->
+
+paragraph
+
+<!-- sss -->abc
+
+* abcd
+* bbbb
+* cccc

test/data/image_reference.html

@@ -0,0 +1,2 @@
+<p><img src="/md.png" alt="Markdown Logo" /></p>
+<p>![missing reference]</p>

test/data/image_reference.md

@@ -1,3 +1,5 @@
 ![Markdown Logo][image]
 
 [image]: /md.png
+
+![missing reference]

test/data/image_title.html

@@ -0,0 +1,2 @@
+<p><img src="/md.png" alt="alt" title="title" /></p>
+<p><img src="/md.png" alt="blank title" title="" /></p>

test/data/image_title.md

@@ -0,0 +1,3 @@
+![alt](/md.png "title")
+
+![blank title](/md.png "")

test/data/implicit_reference.html

@@ -1,3 +1,4 @@
 <p>an <a href="http://example.com">implicit</a> reference link</p>
 <p>an <a href="http://example.com">implicit</a> reference link with an empty link definition</p>
+<p>an <a href="http://example.com">implicit</a> reference link followed by <a href="http://cnn.com">another</a></p>
 <p>an <a href="http://example.com" title="Example">explicit</a> reference link with a title</p>

test/data/implicit_reference.md

@@ -4,6 +4,10 @@ an [implicit] reference link
 
 an [implicit][] reference link with an empty link definition
 
+an [implicit][] reference link followed by [another][]
+
+[another]: http://cnn.com
+
 an [explicit][example] reference link with a title
 
 [example]: http://example.com "Example"

test/data/inline_link_title.html

@@ -0,0 +1,6 @@
+<p><a href="http://example.com" title="Title">single quotes</a></p>
+<p><a href="http://example.com" title="Title">double quotes</a></p>
+<p><a href="http://example.com" title="">single quotes blank</a></p>
+<p><a href="http://example.com" title="">double quotes blank</a></p>
+<p><a href="http://example.com" title="2 Words">space</a></p>
+<p><a href="http://example.com/url-(parentheses)" title="Title">parentheses</a></p>

test/data/inline_link_title.md

@@ -0,0 +1,11 @@
+[single quotes](http://example.com 'Title')
+
+[double quotes](http://example.com "Title")
+
+[single quotes blank](http://example.com '')
+
+[double quotes blank](http://example.com "")
+
+[space](http://example.com "2 Words")
+
+[parentheses](http://example.com/url-(parentheses) "Title")

test/data/lazy_blockquote.html

@@ -0,0 +1,8 @@
+<blockquote>
+<p>quote
+the rest of it</p>
+</blockquote>
+<blockquote>
+<p>another paragraph
+the rest of it</p>
+</blockquote>

test/data/lazy_blockquote.md

@@ -0,0 +1,5 @@
+> quote
+the rest of it
+
+> another paragraph
+the rest of it

test/data/line_break.html

@@ -1,2 +1,2 @@
-<p>line<br />
+<p>line<br />
 line</p>

test/data/line_break.md

@@ -1,2 +1,2 @@
-line  
+line  
 line

test/data/markup_consecutive_one.html

@@ -0,0 +1,3 @@
+<div>Markup</div>
+_No markdown_ without blank line for **strict** compliance with CommonMark.
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_one.md

@@ -0,0 +1,4 @@
+<div>Markup</div>
+_No markdown_ without blank line for **strict** compliance with CommonMark.
+
+**Markdown**

test/data/markup_consecutive_one_line.html

@@ -0,0 +1,4 @@
+<div>One markup on
+two lines</div>
+_No markdown_
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_one_line.md

@@ -0,0 +1,5 @@
+<div>One markup on
+two lines</div>
+_No markdown_
+
+**Markdown**

test/data/markup_consecutive_one_stripped.html

@@ -0,0 +1,3 @@
+<div><p>Stripped markup</p></div>
+_No markdown_
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_one_stripped.md

@@ -0,0 +1,4 @@
+<div><p>Stripped markup</p></div>
+_No markdown_
+
+**Markdown**

test/data/markup_consecutive_two.html

@@ -0,0 +1,3 @@
+<div>First markup</div><p>and second markup on the same line.</p>
+_No markdown_
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_two.md

@@ -0,0 +1,4 @@
+<div>First markup</div><p>and second markup on the same line.</p>
+_No markdown_
+
+**Markdown**

test/data/markup_consecutive_two_lines.html

@@ -0,0 +1,4 @@
+<div>First markup</div><p>and partial markup
+on two lines.</p>
+_No markdown_
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_two_lines.md

@@ -0,0 +1,5 @@
+<div>First markup</div><p>and partial markup
+on two lines.</p>
+_No markdown_
+
+**Markdown**

test/data/markup_consecutive_two_stripped.html

@@ -0,0 +1,4 @@
+<div><p>Stripped markup
+on two lines</p></div>
+_No markdown_
+<p><strong>Markdown</strong></p>

test/data/markup_consecutive_two_stripped.md

@@ -0,0 +1,5 @@
+<div><p>Stripped markup
+on two lines</p></div>
+_No markdown_
+
+**Markdown**

test/data/multiline_lists.html

@@ -0,0 +1,10 @@
+<ol>
+<li>
+<p>One
+First body copy</p>
+</li>
+<li>
+<p>Two
+Last body copy</p>
+</li>
+</ol>

test/data/multiline_lists.md

@@ -0,0 +1,5 @@
+1. One
+   First body copy
+
+2. Two
+   Last body copy

test/data/ordered_list.html

@@ -8,6 +8,9 @@
 <li>two</li>
 </ol>
 <p>large numbers:</p>
-<ol>
+<ol start="123">
 <li>one</li>
-</ol>
+</ol>
+<p>foo 1. the following should not start a list
+100.<br />
+200. </p>

test/data/ordered_list.md

@@ -0,0 +1,15 @@
+1. one
+2. two
+
+repeating numbers:
+
+1. one
+1. two
+
+large numbers:
+
+123. one
+
+foo 1. the following should not start a list
+100.  
+200. 

test/data/paragraph_list.html

@@ -8,5 +8,7 @@
 <li>
 <p>li</p>
 </li>
-<li>li</li>
+<li>
+<p>li</p>
+</li>
 </ul>

test/data/self-closing_html.html

@@ -0,0 +1,12 @@
+<hr>
+<p>paragraph</p>
+<hr/>
+<p>paragraph</p>
+<hr />
+<p>paragraph</p>
+<hr class="foo" id="bar" />
+<p>paragraph</p>
+<hr class="foo" id="bar"/>
+<p>paragraph</p>
+<hr class="foo" id="bar" >
+<p>paragraph</p>

test/data/self-closing_html.md

@@ -0,0 +1,18 @@
+<hr>
+
+paragraph
+<hr/>
+
+paragraph
+<hr />
+
+paragraph
+<hr class="foo" id="bar" />
+
+paragraph
+<hr class="foo" id="bar"/>
+
+paragraph
+<hr class="foo" id="bar" >
+
+paragraph

test/data/separated_nested_list.html

@@ -1,7 +1,9 @@
 <ul>
 <li>
 <p>li</p>
+<ul>
+<li>li</li>
+<li>li</li>
+</ul>
 </li>
-<li>li</li>
-<li>li</li>
 </ul>

test/data/separated_nested_list.md

@@ -0,0 +1,4 @@
+- li
+
+    - li
+    - li

test/data/setext_header.html

@@ -1,5 +1,5 @@
-<h1>h1</h1>
-<h2>h2</h2>
-<h2>single character</h2>
-<p>not a header</p>
+<h1>h1</h1>
+<h2>h2</h2>
+<h2>single character</h2>
+<p>not a header</p>
 <hr />

test/data/setext_header.md

@@ -1,12 +1,12 @@
-h1
-==
-
-h2
---
-
-single character
--
-
-not a header
-
+h1
+==
+
+h2
+--
+
+single character
+-
+
+not a header
+
 ------------

test/data/setext_header_spaces.html

@@ -0,0 +1,12 @@
+<h1>trailing space</h1>
+<h2>trailing space</h2>
+<h1>leading and trailing space</h1>
+<h2>leading and trailing space</h2>
+<h1>1 leading space</h1>
+<h2>1 leading space</h2>
+<h1>3 leading spaces</h1>
+<h2>3 leading spaces</h2>
+<p>too many leading spaces
+==</p>
+<p>too many leading spaces
+--</p>