CS

https://github.com/wallabag/php-readability/commit/e9e4ff87f8fc56d406ccdd5a9a7f1d3d6af07e79

.gitignore

@@ -1 +1,3 @@
 vendor/
+coverage/
+composer.lock

.scrutinizer.yml

@@ -0,0 +1,3 @@
+tools:
+    external_code_coverage:
+        timeout: 600

.travis.yml

@@ -1,13 +1,34 @@
 language: php
 
 php:
+    - 5.3.3
+    - 5.3
     - 5.4
     - 5.5
     - 5.6
+    - nightly
+    - hhvm
+
+# run build against nightly but allow them to fail
+matrix:
+    fast_finish: true
+    allow_failures:
+        - php: nightly
+        - php: hhvm
+
+# faster builds on new travis setup not using sudo
+sudo: false
+
+install:
+    - composer self-update
 
 before_script:
-    - composer self-update
     - composer install --prefer-dist --no-interaction
 
 script:
-    - phpunit --coverage-text
+    - phpunit --coverage-clover=coverage.clover
+
+after_script:
+    - |
+        wget https://scrutinizer-ci.com/ocular.phar
+        php ocular.phar code-coverage:upload --format=php-clover coverage.clover

README.md

@@ -1,6 +1,7 @@
 # Readability
 
 [![Build Status](https://travis-ci.org/j0k3r/php-readability.svg?branch=master)](https://travis-ci.org/j0k3r/php-readability)
+[![Code Coverage](https://scrutinizer-ci.com/g/j0k3r/php-readability/badges/coverage.png?b=master)](https://scrutinizer-ci.com/g/j0k3r/php-readability/?branch=master)
 
 This is an extract of the Readability class from the [full-text-rss](https://github.com/Dither/full-text-rss) fork. It kind be defined as a better version of the original [php-readability](http://code.fivefilters.org/php-readability).
 

composer.json

@@ -24,7 +24,7 @@
         "role": "Developer (original JS version)"
     }],
     "require": {
-        "php": ">=5.4",
+        "php": ">=5.3.3",
         "ext-tidy": ">=1.2"
     },
     "autoload": {

phpunit.xml.dist

@@ -19,11 +19,14 @@
 
     <filter>
         <whitelist>
-            <directory>./src/TubeLink/</directory>
+            <directory>./src/</directory>
             <exclude>
                 <directory>./tests</directory>
             </exclude>
         </whitelist>
     </filter>
 
+    <logging>
+        <log type="coverage-html" target="coverage" title="Readability" charset="UTF-8" yui="true" highlight="true" lowUpperBound="35" highLowerBound="70"/>
+    </logging>
 </phpunit>

src/JSLikeHTMLElement.php

@@ -3,7 +3,7 @@
 namespace Readability;
 
 /**
- * JavaScript-like HTML DOM Element
+ * JavaScript-like HTML DOM Element.
  *
  * This class extends PHP's DOMElement to allow
  * users to get and set the innerHTML property of
@@ -31,12 +31,14 @@ namespace Readability;
  *     echo $doc->saveXML();
  *
  * @author Keyvan Minoukadeh - http://www.keyvan.net - keyvan@keyvan.net
+ *
  * @see http://fivefilters.org (the project this was written for)
  */
 class JSLikeHTMLElement extends \DOMElement
 {
     /**
-     * Used for setting innerHTML like it's done in JavaScript:
+     * Used for setting innerHTML like it's done in JavaScript:.
+     *
      * @code
      * $div->innerHTML = '<h2>Chapter 2</h2><p>The story begins...</p>';
      * @endcode
@@ -45,7 +47,7 @@ class JSLikeHTMLElement extends \DOMElement
     {
         if ($name == 'innerHTML') {
             // first, empty the element
-            for ($x=$this->childNodes->length-1; $x>=0; $x--) {
+            for ($x = $this->childNodes->length - 1; $x >= 0; --$x) {
                 $this->removeChild($this->childNodes->item($x));
             }
             // $value holds our new inner HTML
@@ -86,7 +88,8 @@ class JSLikeHTMLElement extends \DOMElement
     }
 
     /**
-     * Used for getting innerHTML like it's done in JavaScript:
+     * Used for getting innerHTML like it's done in JavaScript:.
+     *
      * @code
      * $string = $div->innerHTML;
      * @endcode
@@ -105,7 +108,7 @@ class JSLikeHTMLElement extends \DOMElement
         $trace = debug_backtrace();
         trigger_error('Undefined property via __get(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE);
 
-        return null;
+        return;
     }
 
     public function __toString()

tests/ReadabilityTest.php

@@ -3,7 +3,6 @@
 namespace Tests\Readability;
 
 use Readability\Readability;
-use Readability\JSLikeHTMLElement;
 
 class ReadabilityTested extends Readability
 {
@@ -49,6 +48,8 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertFalse($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('Sorry, Readability was unable to parse this page for content.', $readability->getContent()->innerHTML);
     }
 
@@ -59,7 +60,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is the awesome content :)', $readability->getContent()->innerHTML);
     }
 
@@ -70,7 +73,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is the awesome content :)', $readability->getContent()->innerHTML);
     }
 
@@ -82,7 +87,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is the awesome content :)', $readability->getContent()->innerHTML);
     }
 
@@ -95,7 +102,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertContains('readabilityFootnoteLink', $readability->getContent()->innerHTML);
         $this->assertContains('readabilityLink-3', $readability->getContent()->innerHTML);
@@ -110,7 +119,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('will be removed', $readability->getContent()->innerHTML);
         $this->assertNotContains('<h2>', $readability->getContent()->innerHTML);
@@ -124,7 +135,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('<div readability=', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertContains('nofollow', $readability->getContent()->innerHTML);
     }
@@ -137,7 +150,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertContains('nofollow', $readability->getContent()->innerHTML);
     }
@@ -150,7 +165,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('<aside>', $readability->getContent()->innerHTML);
         $this->assertContains('<footer/>', $readability->getContent()->innerHTML);
@@ -164,7 +181,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text should be removed', $readability->getContent()->innerHTML);
     }
@@ -177,7 +196,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="tr"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
     }
 
@@ -189,7 +210,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
     }
@@ -202,7 +225,69 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEmpty($readability->getTitle()->innerHTML);
+        $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
+        $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
+    }
+
+    public function testTitle()
+    {
+        $readability = new ReadabilityTested('<title>this is my title</title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability->debug = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEquals('this is my title', $readability->getTitle()->innerHTML);
+        $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
+        $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
+    }
+
+    public function testTitleWithDash()
+    {
+        $readability = new ReadabilityTested('<title> title2 - title3 </title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability->debug = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEquals('title2 - title3', $readability->getTitle()->innerHTML);
+        $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
+        $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
+    }
+
+    public function testTitleWithDoubleDot()
+    {
+        $readability = new ReadabilityTested('<title> title2 : title3 </title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability->debug = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEquals('title2 : title3', $readability->getTitle()->innerHTML);
+        $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
+        $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
+    }
+
+    public function testTitleTooShortUseH1()
+    {
+        $readability = new ReadabilityTested('<title>too short</title><h1>this is my h1 title !</h1><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability->debug = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
+        $this->assertEquals('this is my h1 title !', $readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
     }