markup should preserve empty lines

Ignore html comments as well with markupEscape option.

Parsedown.php

@@ -18,11 +18,10 @@ class Parsedown
     #
     # Philosophy
 
-    # Markdown is intended to be easy-to-read by humans - those of us who read
-    # line by line, left to right, top to bottom. In order to take advantage of
-    # this, Parsedown tries to read in a similar way. It breaks texts into
-    # lines, it iterates through them and it looks at how they start and relate
-    # to each other.
+    # Parsedown recognises that the Markdown syntax is optimised for humans so
+    # it tries to read like one. It goes through text line by line. It looks at
+    # how lines start to identify blocks. It looks for special characters to
+    # identify inline elements.
 
     #
     # ~
@@ -67,6 +66,15 @@ class Parsedown
         return $this;
     }
 
+    private $markupEscaped;
+
+    function setMarkupEscaped($markupEscaped)
+    {
+        $this->markupEscaped = $markupEscaped;
+
+        return $this;
+    }
+
     #
     # Lines
     #
@@ -87,7 +95,7 @@ class Parsedown
         '8' => array('List'),
         '9' => array('List'),
         ':' => array('Table'),
-        '<' => array('Markup'),
+        '<' => array('Comment', 'Markup'),
         '=' => array('Setext'),
         '>' => array('Quote'),
         '_' => array('Rule'),
@@ -280,7 +288,7 @@ class Parsedown
 
             $Block = array(
                 'element' => array(
-                    'name' => 'h'.$level,
+                    'name' => 'h' . min(6, $level),
                     'text' => $text,
                     'handler' => 'line',
                 ),
@@ -346,6 +354,48 @@ class Parsedown
         return $Block;
     }
 
+    #
+    # Comment
+
+    protected function identifyComment($Line)
+    {
+        if ($this->markupEscaped)
+        {
+            return;
+        }
+
+        if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!')
+        {
+            $Block = array(
+                'element' => $Line['body'],
+            );
+
+            if (preg_match('/-->$/', $Line['text']))
+            {
+                $Block['closed'] = true;
+            }
+
+            return $Block;
+        }
+    }
+
+    protected function addToComment($Line, array $Block)
+    {
+        if (isset($Block['closed']))
+        {
+            return;
+        }
+
+        $Block['element'] .= "\n" . $Line['body'];
+
+        if (preg_match('/-->$/', $Line['text']))
+        {
+            $Block['closed'] = true;
+        }
+
+        return $Block;
+    }
+
     #
     # Fenced Code
 
@@ -583,7 +633,12 @@ class Parsedown
 
     protected function identifyMarkup($Line)
     {
-        if (preg_match('/^<(\w[\w\d]*)(?:[ ][^>\/]*)?(\/?)[ ]*>/', $Line['text'], $matches))
+        if ($this->markupEscaped)
+        {
+            return;
+        }
+
+        if (preg_match('/^<(\w[\w\d]*)(?:[ ][^>]*)?(\/?)[ ]*>/', $Line['text'], $matches))
         {
             if (in_array($matches[1], $this->textLevelElements))
             {
@@ -594,15 +649,14 @@ class Parsedown
                 'element' => $Line['body'],
             );
 
-            if ($matches[2] or $matches[1] === 'hr' or preg_match('/<\/'.$matches[1].'>[ ]*$/', $Line['text']))
+            if ($matches[2] or in_array($matches[1], $this->voidElements) or preg_match('/<\/'.$matches[1].'>[ ]*$/', $Line['text']))
             {
                 $Block['closed'] = true;
             }
             else
             {
                 $Block['depth'] = 0;
-                $Block['start'] = '<'.$matches[1].'>';
-                $Block['end'] = '</'.$matches[1].'>';
+                $Block['name'] = $matches[1];
             }
 
             return $Block;
@@ -616,12 +670,12 @@ class Parsedown
             return;
         }
 
-        if (stripos($Line['text'], $Block['start']) !== false) # opening tag
+        if (preg_match('/<'.$Block['name'].'([ ][^\/]+)?>/', $Line['text'])) # opening tag
         {
             $Block['depth'] ++;
         }
 
-        if (stripos($Line['text'], $Block['end']) !== false) # closing tag
+        if (stripos($Line['text'], '</'.$Block['name'].'>') !== false) # closing tag
         {
             if ($Block['depth'] > 0)
             {
@@ -633,6 +687,13 @@ class Parsedown
             }
         }
 
+        if (isset($Block['interrupted']))
+        {
+            $Block['element'] .= "\n";
+
+            unset($Block['interrupted']);
+        }
+
         $Block['element'] .= "\n".$Line['body'];
 
         return $Block;
@@ -1109,6 +1170,11 @@ class Parsedown
 
     protected function identifyTag($Excerpt)
     {
+        if ($this->markupEscaped)
+        {
+            return;
+        }
+
         if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<\/?\w.*?>/', $Excerpt['text'], $matches))
         {
             return array(
@@ -1353,6 +1419,10 @@ class Parsedown
         '_' => '/^_((?:[^_]|__[^_]*__)+?)_(?!_)\b/us',
     );
 
+    protected $voidElements = array(
+        'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source',
+    );
+
     protected $textLevelElements = array(
         'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont',
         'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing',

README.md

@@ -1,17 +1,18 @@
 ## Parsedown
 
-Better [Markdown](http://en.wikipedia.org/wiki/Markdown) parser for PHP.
+Better Markdown Parser in PHP
 
-- [Demo](http://parsedown.org/demo)
-- [Tests](http://parsedown.org/tests/)
+[[ demo ]](http://parsedown.org/demo)
 
 ### Features
 
 * [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/)
+* [GitHub flavored](https://help.github.com/articles/github-flavored-markdown)
+* [Tested](http://parsedown.org/tests/) in PHP 5.2, 5.3, 5.4, 5.5, 5.6 and [hhvm](http://www.hhvm.com/)
 * Extensible
+* [Markdown Extra extension](https://github.com/erusev/parsedown-extra) <sup>new</sup>
+* [JavaScript port](https://github.com/hkdobrev/parsedown.js) under development <sup>new</sup>
 
 ### Installation
 
@@ -24,3 +25,19 @@ $Parsedown = new Parsedown();
 
 echo $Parsedown->text('Hello _Parsedown_!'); # prints: <p>Hello <em>Parsedown</em>!</p>
 ```
+
+More examples in [the wiki](https://github.com/erusev/parsedown/wiki/Usage) and in [this video tutorial](http://youtu.be/wYZBY8DEikI).
+
+### Questions
+
+**How does Parsedown work?**<br/>
+Parsedown recognises that the Markdown syntax is optimised for humans so it tries to read like one. It goes through text line by line. It looks at how lines start to identify blocks. It looks for special characters to identify inline elements.
+
+**Why doesn’t Parsedown use namespaces?**<br/>
+Using namespaces would mean dropping support for PHP 5.2. We believe that since Parsedown is a single class with an uncommon name, making this trade wouldn't be worth it.
+
+**Is Parsedown compliant with CommonMark?**<br/>
+We are [working on it](https://github.com/erusev/parsedown/tree/commonmark).
+
+**Who uses Parsedown?**<br/>
+[phpDocumentor](http://www.phpdoc.org/), [October CMS](http://octobercms.com/), [Bolt CMS](http://bolt.cm/), [RaspberryPi.org](http://www.raspberrypi.org/) and [more](https://www.versioneye.com/php/erusev:parsedown/references).

phpunit.xml.dist

@@ -2,7 +2,7 @@
 <phpunit bootstrap="test/bootstrap.php" colors="true">
 	<testsuites>
 		<testsuite>
-			<file>test/Test.php</file>
+			<file>test/ParsedownTest.php</file>
 		</testsuite>
 	</testsuites>
 </phpunit>

test/ParsedownTest.php

@@ -0,0 +1,139 @@
+<?php
+
+class ParsedownTest extends PHPUnit_Framework_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, $Parsedown;
+
+    /**
+     * @return array
+     */
+    protected function initDirs()
+    {
+        $dirs []= dirname(__FILE__).'/data/';
+
+        return $dirs;
+    }
+
+    /**
+     * @return Parsedown
+     */
+    protected function initParsedown()
+    {
+        $Parsedown = new Parsedown();
+
+        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);
+
+        $actualMarkup = $this->Parsedown->text($markdown);
+
+        $this->assertEquals($expectedMarkup, $actualMarkup);
+    }
+
+    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><em>content</em>&lt;/div></p>
+<p>sparse:</p>
+<p>&lt;div>
+&lt;div class="inner">
+<em>content</em>
+&lt;/div>
+&lt;/div></p>
+<p>paragraph</p>
+<p>&lt;style type="text/css"></p>
+<pre><code>p {
+    color: red;
+}</code></pre>
+<p>&lt;/style></p>
+<p>comment</p>
+<p>&lt;!-- html comment --></p>
+EXPECTED_HTML;
+        $parsedownWithNoMarkup = new Parsedown();
+        $parsedownWithNoMarkup->setMarkupEscaped(true);
+        $this->assertEquals($expectedHtml, $parsedownWithNoMarkup->text($markdownWithHtml));
+    }
+}

test/Test.php

@@ -1,65 +0,0 @@
-<?php
-
-class Test extends PHPUnit_Framework_TestCase
-{
-    public function __construct($name = null, array $data = array(), $dataName = '')
-    {
-        $this->dataDir = dirname(__FILE__).'/data/';
-
-        parent::__construct($name, $data, $dataName);
-    }
-
-    private $dataDir;
-
-    /**
-     * @dataProvider data
-     */
-    function test_($filename)
-    {
-        $markdown = file_get_contents($this->dataDir . $filename . '.md');
-
-        $expectedMarkup = file_get_contents($this->dataDir . $filename . '.html');
-
-        $expectedMarkup = str_replace("\r\n", "\n", $expectedMarkup);
-        $expectedMarkup = str_replace("\r", "\n", $expectedMarkup);
-
-        $actualMarkup = Parsedown::instance()->text($markdown);
-
-        $this->assertEquals($expectedMarkup, $actualMarkup);
-    }
-
-    function data()
-    {
-        $data = array();
-
-        $Folder = new DirectoryIterator($this->dataDir);
-
-        foreach ($Folder as $File)
-        {
-            /** @var $File DirectoryIterator */
-
-            if ( ! $File->isFile())
-            {
-                continue;
-            }
-
-            $filename = $File->getFilename();
-
-            $extension = pathinfo($filename, PATHINFO_EXTENSION);
-
-            if ($extension !== 'md')
-            {
-                continue;
-            }
-
-            $basename = $File->getBasename('.md');
-
-            if (file_exists($this->dataDir . $basename . '.html'))
-            {
-                $data []= array($basename);
-            }
-        }
-
-        return $data;
-    }
-}

test/data/atx_heading.html

@@ -4,5 +4,6 @@
 <h4>h4</h4>
 <h5>h5</h5>
 <h6>h6</h6>
+<h6>h6</h6>
 <h1>closed h1</h1>
 <p>#</p>

test/data/atx_heading.md

@@ -10,6 +10,8 @@
 
 ###### h6
 
+####### h6
+
 # closed h1 #
 
 #

test/data/block-level_html.html

@@ -1,5 +1,13 @@
 <div>_content_</div>
 <p>sparse:</p>
 <div>
+<div class="inner">
 _content_
 </div>
+</div>
+<p>paragraph</p>
+<style type="text/css">
+    p {
+        color: red;
+    }
+</style>

test/data/block-level_html.md

@@ -3,5 +3,15 @@
 sparse:
 
 <div>
+<div class="inner">
 _content_
 </div>
+</div>
+
+paragraph
+
+<style type="text/css">
+    p {
+        color: red;
+    }
+</style>

test/data/html_comment.html

@@ -0,0 +1,5 @@
+<!-- single line -->
+<p>paragraph</p>
+<!-- 
+  multiline -->
+<p>paragraph</p>

test/data/html_comment.md

@@ -0,0 +1,8 @@
+<!-- single line -->
+
+paragraph
+
+<!-- 
+  multiline -->
+
+paragraph

test/data/html_simple.html

@@ -1,28 +0,0 @@
-<p>Headings:</p>
-<h2 id="overview">Overview</h2>
-<p>blah</p>
-<H2 id="block">Block Elements</H2>
-<p>blah</p>
-<h3 id="span">
-      Span Elements
-</h3>
-<p>blah</p>
-<p>Hr's:</p>
-<hr>
-<p>blah</p>
-<hr/>
-<p>blah</p>
-<hr />
-<p>blah</p>
-<hr>   
-<p>blah</p>
-<hr/>  
-<p>blah</p>
-<hr /> 
-<p>blah</p>
-<hr class="foo" id="bar" />
-<p>blah</p>
-<hr class="foo" id="bar"/>
-<p>blah</p>
-<hr class="foo" id="bar" >
-<p>blah</p>

test/data/html_simple.md

@@ -1,39 +0,0 @@
-Headings:
-
-<h2 id="overview">Overview</h2>
-blah
-<H2 id="block">Block Elements</H2>
-blah
-<h3 id="span">
-      Span Elements
-</h3>
-blah
-
-Hr's:
-
-<hr>
-blah
-
-<hr/>
-blah
-
-<hr />
-blah
-
-<hr>   
-blah
-
-<hr/>  
-blah
-
-<hr /> 
-blah
-
-<hr class="foo" id="bar" />
-blah
-
-<hr class="foo" id="bar"/>
-blah
-
-<hr class="foo" id="bar" >
-blah

test/data/self-closing_block-level_html.html

@@ -1,4 +0,0 @@
-<hr />
-<p>attributes:</p>
-<hr style="background: #9bd;" />
-<p>...</p>

test/data/self-closing_block-level_html.md

@@ -1,7 +0,0 @@
-<hr />
-
-attributes:
-
-<hr style="background: #9bd;" />
-
-...

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 +1,12 @@
+<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/sparse_html.html

@@ -0,0 +1,8 @@
+<div>
+line 1
+
+line 2
+line 3
+
+line 4
+</div>

test/data/sparse_html.md

@@ -0,0 +1,8 @@
+<div>
+line 1
+
+line 2
+line 3
+
+line 4
+</div>