From 7ab3c60a77646aa20c5356907ecb0b37cceeb59d Mon Sep 17 00:00:00 2001
From: Emanuil Rusev <hello@erusev.com>
Date: Tue, 2 Dec 2014 22:23:43 +0200
Subject: [PATCH] improve CommonMark compliance

---
 Parsedown.php                     | 21 ++++++++++++++++-----
 test/data/image_reference.html    |  2 +-
 test/data/image_title.html        |  2 +-
 test/data/inline_link.html        |  4 ++--
 test/data/special_characters.html |  2 +-
 5 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/Parsedown.php b/Parsedown.php
index 0258075..b622d15 100755
--- a/Parsedown.php
+++ b/Parsedown.php
@@ -972,6 +972,7 @@ class Parsedown
         '*' => array('Emphasis'),
         '/' => array('Url'),
         '<' => array('UrlTag', 'EmailTag', 'Tag', 'LessThan'),
+        '>' => array('GreaterThan'),
         '[' => array('Link'),
         '_' => array('Emphasis'),
         '`' => array('InlineCode'),
@@ -981,7 +982,7 @@ class Parsedown
 
     # ~
 
-    protected $spanMarkerList = '*_!&[</`~\\';
+    protected $spanMarkerList = '*_!&[<>/`~\\';
 
     #
     # ~
@@ -1132,6 +1133,14 @@ class Parsedown
         );
     }
 
+    protected function identifyGreaterThan()
+    {
+        return array(
+            'markup' => '&gt;',
+            'extent' => 1,
+        );
+    }
+
     protected function identifyUrlTag($Excerpt)
     {
         if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(https?:[\/]{2}[^\s]+?)>/i', $Excerpt['text'], $matches))
@@ -1175,7 +1184,7 @@ class Parsedown
             return;
         }
 
-        if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<\/?\w.*?>/', $Excerpt['text'], $matches))
+        if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<\/?\w.*?>/s', $Excerpt['text'], $matches))
         {
             return array(
                 'markup' => $matches[0],
@@ -1188,10 +1197,11 @@ class Parsedown
     {
         $marker = $Excerpt['text'][0];
 
-        if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(?<!'.$marker.')\1(?!'.$marker.')/', $Excerpt['text'], $matches))
+        if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(?<!'.$marker.')\1(?!'.$marker.')/s', $Excerpt['text'], $matches))
         {
             $text = $matches[2];
             $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8');
+            $text = preg_replace("/[ ]*\n/", ' ', $text);
 
             return array(
                 'extent' => strlen($matches[0]),
@@ -1267,8 +1277,8 @@ class Parsedown
             $Element = array(
                 'name' => 'img',
                 'attributes' => array(
-                    'alt' => $Link['text'],
                     'src' => $url,
+                    'alt' => $Link['text'],
                 ),
             );
         }
@@ -1332,9 +1342,10 @@ class Parsedown
 
     protected function readPlainText($text)
     {
-        $breakMarker = $this->breaksEnabled ? "\n" : "  \n";
+        $breakMarker = $this->breaksEnabled ? "\n" : array("  \n", "\\\n");
 
         $text = str_replace($breakMarker, "<br />\n", $text);
+        $text = str_replace(" \n", "\n", $text);
 
         return $text;
     }
diff --git a/test/data/image_reference.html b/test/data/image_reference.html
index b3249cb..6e45cba 100644
--- a/test/data/image_reference.html
+++ b/test/data/image_reference.html
@@ -1 +1 @@
-<p><img alt="Markdown Logo" src="/md.png" /></p>
\ No newline at end of file
+<p><img src="/md.png" alt="Markdown Logo" /></p>
\ No newline at end of file
diff --git a/test/data/image_title.html b/test/data/image_title.html
index 82c155f..4fc59f6 100644
--- a/test/data/image_title.html
+++ b/test/data/image_title.html
@@ -1 +1 @@
-<p><img alt="alt" src="/md.png" title="title" /></p>
\ No newline at end of file
+<p><img src="/md.png" alt="alt" title="title" /></p>
\ No newline at end of file
diff --git a/test/data/inline_link.html b/test/data/inline_link.html
index 2b9e649..226fa53 100644
--- a/test/data/inline_link.html
+++ b/test/data/inline_link.html
@@ -1,4 +1,4 @@
 <p><a href="http://example.com">link</a> and <a href="/tests/">another link</a></p>
 <p><a href="http://example.com"><code>link</code></a></p>
-<p><a href="http://example.com"><img alt="MD Logo" src="http://parsedown.org/md.png" /></a></p>
-<p><a href="http://example.com"><img alt="MD Logo" src="http://parsedown.org/md.png" /> and text</a></p>
\ No newline at end of file
+<p><a href="http://example.com"><img src="http://parsedown.org/md.png" alt="MD Logo" /></a></p>
+<p><a href="http://example.com"><img src="http://parsedown.org/md.png" alt="MD Logo" /> and text</a></p>
\ No newline at end of file
diff --git a/test/data/special_characters.html b/test/data/special_characters.html
index 8199abc..3b652c3 100644
--- a/test/data/special_characters.html
+++ b/test/data/special_characters.html
@@ -1,6 +1,6 @@
 <p>AT&amp;T has an ampersand in their name</p>
 <p>this &amp; that</p>
-<p>4 &lt; 5 and 6 > 5</p>
+<p>4 &lt; 5 and 6 &gt; 5</p>
 <p><a href="http://example.com/autolink?a=1&amp;b=2">http://example.com/autolink?a=1&amp;b=2</a></p>
 <p><a href="/script?a=1&amp;b=2">inline link</a></p>
 <p><a href="http://example.com/?a=1&amp;b=2">reference link</a></p>
\ No newline at end of file