infong
/
php-readability
mirror of https://github.com/j0k3r/php-readability
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Improve Travis & add Scrutinizer

Browse Source 
+ CS
+ Update README
pull/3/head
Jeremy Benoist 11 years ago
parent f5d473780d
commit 1963319a55
6 changed files with 152 additions and 126 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 3
      .scrutinizer.yml
  2. 23
      .travis.yml
  3. 1
      README.md
  4. 11
      src/JSLikeHTMLElement.php
  5. 113
      src/Readability.php
  6. 1
      tests/ReadabilityTest.php

3
.scrutinizer.yml
Unescape View File

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

23
.travis.yml
Unescape View File

@ -4,10 +4,29 @@ php:
- 5.4 - 5.4
- 5.5 - 5.5
- 5.6 - 5.6
- nightly
- hhvm-nightly
before_script: # run build against nightly but allow them to fail
matrix:
fast_finish: true
allow_failures:
- php: nightly
- php: hhvm-nightly
# faster builds on new travis setup not using sudo
sudo: false
install:
- composer self-update - composer self-update
before_script:
- composer install --prefer-dist --no-interaction - composer install --prefer-dist --no-interaction
script: 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

1
README.md
Unescape View File

@ -1,6 +1,7 @@
# Readability # Readability
[![Build Status](https://travis-ci.org/j0k3r/php-readability.svg?branch=master)](https://travis-ci.org/j0k3r/php-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). 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).

11
src/JSLikeHTMLElement.php
Unescape View File

@ -3,7 +3,7 @@
namespace Readability; namespace Readability;
/** /**
* JavaScript-like HTML DOM Element * JavaScript-like HTML DOM Element.
* *
* This class extends PHP's DOMElement to allow * This class extends PHP's DOMElement to allow
* users to get and set the innerHTML property of * users to get and set the innerHTML property of
@ -31,12 +31,14 @@ namespace Readability;
* echo $doc->saveXML(); * echo $doc->saveXML();
* *
* @author Keyvan Minoukadeh - http://www.keyvan.net - keyvan@keyvan.net * @author Keyvan Minoukadeh - http://www.keyvan.net - keyvan@keyvan.net
*
* @see http://fivefilters.org (the project this was written for) * @see http://fivefilters.org (the project this was written for)
*/ */
class JSLikeHTMLElement extends \DOMElement 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 * @code
* $div->innerHTML = '<h2>Chapter 2</h2><p>The story begins...</p>'; * $div->innerHTML = '<h2>Chapter 2</h2><p>The story begins...</p>';
* @endcode * @endcode
@ -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 * @code
* $string = $div->innerHTML; * $string = $div->innerHTML;
* @endcode * @endcode
@ -105,7 +108,7 @@ class JSLikeHTMLElement extends \DOMElement
$trace = debug_backtrace(); $trace = debug_backtrace();
trigger_error('Undefined property via __get(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE); 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() public function __toString()

113
src/Readability.php
Unescape View File

@ -14,7 +14,7 @@ namespace Readability;
* More information: http://fivefilters.org/content-only/ * More information: http://fivefilters.org/content-only/
* License: Apache License, Version 2.0 * License: Apache License, Version 2.0
* Requires: PHP version 5.2.0+ * Requires: PHP version 5.2.0+
* Date: 2013-08-02 * Date: 2013-08-02.
* *
* Differences between the PHP port and the original * Differences between the PHP port and the original
* ------------------------------------------------------ * ------------------------------------------------------
@ -76,7 +76,7 @@ class Readability
'divToPElements' => '/<(?:blockquote|code|div|article|footer|aside|img|p|pre|dl|ol|ul)/mi', 'divToPElements' => '/<(?:blockquote|code|div|article|footer|aside|img|p|pre|dl|ol|ul)/mi',
'killBreaks' => '/(<br\s*\/?>([ \r\n\s]|&nbsp;?)*)+/', 'killBreaks' => '/(<br\s*\/?>([ \r\n\s]|&nbsp;?)*)+/',
'media' => '!//(?:[^\.\?/]+\.)?(?:youtu(?:be)?|soundcloud|dailymotion|vimeo|pornhub|xvideos|twitvid|rutube|viddler)\.(?:com|be|org|net)/!i', 'media' => '!//(?:[^\.\?/]+\.)?(?:youtu(?:be)?|soundcloud|dailymotion|vimeo|pornhub|xvideos|twitvid|rutube|viddler)\.(?:com|be|org|net)/!i',
'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i' 'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i',
); );
public $tidy_config = array( public $tidy_config = array(
'tidy-mark' => false, 'tidy-mark' => false,
@ -101,7 +101,7 @@ class Readability
// 'merge-spans' => true, // 'merge-spans' => true,
'input-encoding' => '????', 'input-encoding' => '????',
'output-encoding' => 'utf8', 'output-encoding' => 'utf8',
'hide-comments' => true 'hide-comments' => true,
); );
// raw HTML filters // raw HTML filters
protected $pre_filters = array( protected $pre_filters = array(
@ -111,7 +111,7 @@ class Readability
'!<font[^>]*>\s*\[AD\]\s*</font>!is' => '', // HACK: firewall-filtered content '!<font[^>]*>\s*\[AD\]\s*</font>!is' => '', // HACK: firewall-filtered content
'!(<br[^>]*>[ \r\n\s]*){2,}!i' => '</p><p>', // HACK: replace linebreaks plus br's with p's '!(<br[^>]*>[ \r\n\s]*){2,}!i' => '</p><p>', // HACK: replace linebreaks plus br's with p's
//'!</?noscript>!is' => '', // replace noscripts //'!</?noscript>!is' => '', // replace noscripts
'!<(/?)font[^>]*>!is' => '<\\1span>' // replace fonts to spans '!<(/?)font[^>]*>!is' => '<\\1span>', // replace fonts to spans
); );
// output HTML filters // output HTML filters
protected $post_filters = array( protected $post_filters = array(
@ -121,7 +121,7 @@ class Readability
"/\n+/" => "\n", //single newlines cleanup "/\n+/" => "\n", //single newlines cleanup
'!<pre[^>]*>\s*<code!is' => '<pre', // modern web... '!<pre[^>]*>\s*<code!is' => '<pre', // modern web...
'!</code>\s*</pre>!is' => '</pre>', '!</code>\s*</pre>!is' => '</pre>',
'!<[hb]r>!is' => '<\\1 />' '!<[hb]r>!is' => '<\\1 />',
); );
// flags // flags
const FLAG_STRIP_UNLIKELYS = 1; const FLAG_STRIP_UNLIKELYS = 1;
@ -139,11 +139,12 @@ class Readability
const MIN_NODE_LENGTH = 80; const MIN_NODE_LENGTH = 80;
const MAX_LINK_DENSITY = 0.25; const MAX_LINK_DENSITY = 0.25;
/** /**
* Create instance of Readability * Create instance of Readability.
*
* @param string UTF-8 encoded string * @param string UTF-8 encoded string
* @param string (optional) URL associated with HTML (for footnotes) * @param string (optional) URL associated with HTML (for footnotes)
* @param string (optional) Which parser to use for turning raw HTML into a DOMDocument * @param string (optional) Which parser to use for turning raw HTML into a DOMDocument
* @param boolean (optional) Use tidy * @param bool (optional) Use tidy
*/ */
public function __construct($html, $url = null, $parser = 'libxml', $use_tidy = true) public function __construct($html, $url = null, $parser = 'libxml', $use_tidy = true)
{ {
@ -154,9 +155,9 @@ class Readability
$this->domainRegExp = '/'.strtr(preg_replace('/www\d*\./', '', parse_url($url, PHP_URL_HOST)), array('.' => '\.')).'/'; $this->domainRegExp = '/'.strtr(preg_replace('/www\d*\./', '', parse_url($url, PHP_URL_HOST)), array('.' => '\.')).'/';
} }
mb_internal_encoding("UTF-8"); mb_internal_encoding('UTF-8');
mb_http_output("UTF-8"); mb_http_output('UTF-8');
mb_regex_encoding("UTF-8"); mb_regex_encoding('UTF-8');
// HACK: dirty cleanup to replace some stuff; shouldn't use regexps with HTML but well... // HACK: dirty cleanup to replace some stuff; shouldn't use regexps with HTML but well...
if (!$this->flagIsActive(self::FLAG_DISABLE_PREFILTER)) { if (!$this->flagIsActive(self::FLAG_DISABLE_PREFILTER)) {
@ -170,7 +171,7 @@ class Readability
$html = '<html></html>'; $html = '<html></html>';
} }
/** /*
* Use tidy (if it exists). * Use tidy (if it exists).
* This fixes problems with some sites which would otherwise trouble DOMDocument's HTML parsing. * This fixes problems with some sites which would otherwise trouble DOMDocument's HTML parsing.
* Although sometimes it makes matters worse, which is why there is an option to disable it. * Although sometimes it makes matters worse, which is why there is an option to disable it.
@ -188,7 +189,7 @@ class Readability
} }
unset($tidy); unset($tidy);
} }
$html = mb_convert_encoding($html, 'HTML-ENTITIES', "UTF-8"); $html = mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8');
if (!($parser == 'html5lib' && ($this->dom = \HTML5_Parser::parse($html)))) { if (!($parser == 'html5lib' && ($this->dom = \HTML5_Parser::parse($html)))) {
libxml_use_internal_errors(true); libxml_use_internal_errors(true);
@ -201,7 +202,8 @@ class Readability
$this->dom->registerNodeClass('DOMElement', 'Readability\JSLikeHTMLElement'); $this->dom->registerNodeClass('DOMElement', 'Readability\JSLikeHTMLElement');
} }
/** /**
* Get article title element * Get article title element.
*
* @return DOMElement * @return DOMElement
*/ */
public function getTitle() public function getTitle()
@ -209,7 +211,8 @@ class Readability
return $this->articleTitle; return $this->articleTitle;
} }
/** /**
* Get article content element * Get article content element.
*
* @return DOMElement * @return DOMElement
*/ */
public function getContent() public function getContent()
@ -217,7 +220,8 @@ class Readability
return $this->articleContent; return $this->articleContent;
} }
/** /**
* Add pre filter for raw input HTML processing * Add pre filter for raw input HTML processing.
*
* @param string RegExp for replace * @param string RegExp for replace
* @param string (optional) Replacer * @param string (optional) Replacer
*/ */
@ -226,7 +230,8 @@ class Readability
$this->pre_filters[$filter] = $replacer; $this->pre_filters[$filter] = $replacer;
} }
/** /**
* Add post filter for raw output HTML processing * Add post filter for raw output HTML processing.
*
* @param string RegExp for replace * @param string RegExp for replace
* @param string (optional) Replacer * @param string (optional) Replacer
*/ */
@ -244,7 +249,7 @@ class Readability
* 4. Replace the current DOM tree with the new one. * 4. Replace the current DOM tree with the new one.
* 5. Read peacefully. * 5. Read peacefully.
* *
* @return boolean true if we found content, false otherwise * @return bool true if we found content, false otherwise
*/ */
public function init() public function init()
{ {
@ -296,7 +301,7 @@ class Readability
return $this->success; return $this->success;
} }
/** /**
* Debug * Debug.
*/ */
protected function dbg($msg) //, $error=false) protected function dbg($msg) //, $error=false)
{ {
@ -306,12 +311,12 @@ class Readability
} }
/** /**
* Dump debug info * Dump debug info.
*/ */
protected function dump_dbg() protected function dump_dbg()
{ {
if ($this->debug) { if ($this->debug) {
openlog("Readability PHP ", LOG_PID | LOG_PERROR, 0); openlog('Readability PHP ', LOG_PID | LOG_PERROR, 0);
syslog(6, $this->debugText); // 1 - error 6 - info syslog(6, $this->debugText); // 1 - error 6 - info
} }
} }
@ -319,7 +324,6 @@ class Readability
* Run any post-process modifications to article content as necessary. * Run any post-process modifications to article content as necessary.
* *
* @param DOMElement * @param DOMElement
* @return void
*/ */
public function postProcessContent($articleContent) public function postProcessContent($articleContent)
{ {
@ -338,7 +342,8 @@ class Readability
$origTitle = ''; $origTitle = '';
try { try {
$curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0)); $curTitle = $origTitle = $this->getInnerText($this->dom->getElementsByTagName('title')->item(0));
} catch (Exception $e) {} } catch (Exception $e) {
}
if (preg_match('/ [\|\-] /', $curTitle)) { if (preg_match('/ [\|\-] /', $curTitle)) {
$curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle); $curTitle = preg_replace('/(.*)[\|\-] .*/i', '$1', $origTitle);
if (count(explode(' ', $curTitle)) < 3) { if (count(explode(' ', $curTitle)) < 3) {
@ -367,12 +372,10 @@ class Readability
/** /**
* Prepare the HTML document for readability to scrape it. * Prepare the HTML document for readability to scrape it.
* This includes things like stripping javascript, CSS, and handling terrible markup. * This includes things like stripping javascript, CSS, and handling terrible markup.
*
* @return void
*/ */
protected function prepDocument() protected function prepDocument()
{ {
/** /*
* In some cases a body element can't be found (if the HTML is totally hosed for example) * In some cases a body element can't be found (if the HTML is totally hosed for example)
* so we create a new body node and append it to the document. * so we create a new body node and append it to the document.
*/ */
@ -393,9 +396,8 @@ class Readability
} }
/** /**
* For easier reading, convert this document to have footnotes at the bottom rather than inline links. * For easier reading, convert this document to have footnotes at the bottom rather than inline links.
* @see http://www.roughtype.com/archives/2010/05/experiments_in.php
* *
* @return void * @see http://www.roughtype.com/archives/2010/05/experiments_in.php
*/ */
public function addFootnotes($articleContent) public function addFootnotes($articleContent)
{ {
@ -451,7 +453,6 @@ class Readability
* iframes, forms, strip extraneous <p> tags, etc. * iframes, forms, strip extraneous <p> tags, etc.
* *
* @param DOMElement * @param DOMElement
* @return void
*/ */
public function prepArticle($articleContent) public function prepArticle($articleContent)
{ {
@ -464,7 +465,7 @@ class Readability
$this->killBreaks($articleContent); $this->killBreaks($articleContent);
$xpath = new \DOMXPath($articleContent->ownerDocument); $xpath = new \DOMXPath($articleContent->ownerDocument);
if ($this->revertForcedParagraphElements) { if ($this->revertForcedParagraphElements) {
/** /*
* Reverts P elements with class 'readability-styled' to text nodes: * Reverts P elements with class 'readability-styled' to text nodes:
* which is what they were before. * which is what they were before.
*/ */
@ -494,7 +495,7 @@ class Readability
$this->clean($articleContent, 'canvas'); $this->clean($articleContent, 'canvas');
$this->clean($articleContent, 'h1'); $this->clean($articleContent, 'h1');
/** /*
* If there is only one h2, they are probably using it as a main header, so remove it since we * If there is only one h2, they are probably using it as a main header, so remove it since we
* already have a header. * already have a header.
*/ */
@ -537,7 +538,7 @@ class Readability
} }
unset($search, $replace); unset($search, $replace);
} catch (Exception $e) { } catch (Exception $e) {
$this->dbg("Cleaning output HTML failed. Ignoring: " . $e->getMessage()); $this->dbg('Cleaning output HTML failed. Ignoring: '.$e->getMessage());
} }
} }
} }
@ -546,7 +547,6 @@ class Readability
* className/id for special names to add to its score. * className/id for special names to add to its score.
* *
* @param Element * @param Element
* @return void
*/ */
protected function initializeNode($node) protected function initializeNode($node)
{ {
@ -668,7 +668,7 @@ class Readability
} }
} }
} }
/** /*
* Loop through all paragraphs, and assign a score to them based on how content-y they look. * Loop through all paragraphs, and assign a score to them based on how content-y they look.
* Then add their score to their parent node. * Then add their score to their parent node.
* *
@ -724,7 +724,7 @@ class Readability
$grandParentNode->getAttributeNode('readability')->value += $contentScore / self::GRANDPARENT_SCORE_DIVISOR; $grandParentNode->getAttributeNode('readability')->value += $contentScore / self::GRANDPARENT_SCORE_DIVISOR;
} }
} }
/** /*
* Node prepping: trash nodes that look cruddy (like ones with the class name "comment", etc). * Node prepping: trash nodes that look cruddy (like ones with the class name "comment", etc).
* This is faster to do before scoring but safer after. * This is faster to do before scoring but safer after.
*/ */
@ -743,7 +743,7 @@ class Readability
$node = $candidates->item($c); $node = $candidates->item($c);
$tagName = $node->tagName; $tagName = $node->tagName;
/* Remove unlikely candidates */ /* Remove unlikely candidates */
$unlikelyMatchString = $node->getAttribute('class')." ".$node->getAttribute('id')." ".$node->getAttribute('style'); $unlikelyMatchString = $node->getAttribute('class').' '.$node->getAttribute('id').' '.$node->getAttribute('style');
//$this->dbg('Processing '.$node->getNodePath().' by "'. $unlikelyMatchString.'" with readability '.($node->hasAttribute('readability') ? (int)$node->getAttributeNode('readability')->value : 0)); //$this->dbg('Processing '.$node->getNodePath().' by "'. $unlikelyMatchString.'" with readability '.($node->hasAttribute('readability') ? (int)$node->getAttributeNode('readability')->value : 0));
if (mb_strlen($unlikelyMatchString) > 3 && // don't process "empty" strings if (mb_strlen($unlikelyMatchString) > 3 && // don't process "empty" strings
preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) && preg_match($this->regexps['unlikelyCandidates'], $unlikelyMatchString) &&
@ -756,7 +756,7 @@ class Readability
} }
unset($candidates); unset($candidates);
} }
/** /*
* After we've calculated scores, loop through all of the possible candidate nodes we found * After we've calculated scores, loop through all of the possible candidate nodes we found
* and find the one with the highest score. * and find the one with the highest score.
*/ */
@ -777,7 +777,7 @@ class Readability
} }
unset($candidates); unset($candidates);
} }
/** /*
* If we still have no top candidate, just use the body as a last resort. * If we still have no top candidate, just use the body as a last resort.
* We also have to copy the body node so it is something we can modify. * We also have to copy the body node so it is something we can modify.
*/ */
@ -812,7 +812,7 @@ class Readability
} }
} }
$this->dbg('Top candidate: '.$topCandidate->getNodePath()); $this->dbg('Top candidate: '.$topCandidate->getNodePath());
/** /*
* Now that we have the top candidate, look through its siblings for content that might also be related. * Now that we have the top candidate, look through its siblings for content that might also be related.
* Things like preambles, content split by ads that we removed, etc. * Things like preambles, content split by ads that we removed, etc.
*/ */
@ -884,7 +884,7 @@ class Readability
unset($xpath); unset($xpath);
// So we have all of the content that we need. Now we clean it up for presentation. // So we have all of the content that we need. Now we clean it up for presentation.
$this->prepArticle($articleContent); $this->prepArticle($articleContent);
/** /*
* Now that we've gone through the full algorithm, check to see if we got any meaningful content. * Now that we've gone through the full algorithm, check to see if we got any meaningful content.
* If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher * If we didn't, we may need to re-run grabArticle with different flags set. This gives us a higher
* likelihood of finding the content, and the sieve approach gives us a higher likelihood of * likelihood of finding the content, and the sieve approach gives us a higher likelihood of
@ -897,17 +897,17 @@ class Readability
$this->body->innerHTML = $this->bodyCache; $this->body->innerHTML = $this->bodyCache;
if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) { if ($this->flagIsActive(self::FLAG_STRIP_UNLIKELYS)) {
$this->removeFlag(self::FLAG_STRIP_UNLIKELYS); $this->removeFlag(self::FLAG_STRIP_UNLIKELYS);
$this->dbg("...content is shorter than ".self::MIN_ARTICLE_LENGTH." letters, trying not to strip unlikely content.\n"); $this->dbg('...content is shorter than '.self::MIN_ARTICLE_LENGTH." letters, trying not to strip unlikely content.\n");
return $this->grabArticle($this->body); return $this->grabArticle($this->body);
} elseif ($this->flagIsActive(self::FLAG_WEIGHT_ATTRIBUTES)) { } elseif ($this->flagIsActive(self::FLAG_WEIGHT_ATTRIBUTES)) {
$this->removeFlag(self::FLAG_WEIGHT_ATTRIBUTES); $this->removeFlag(self::FLAG_WEIGHT_ATTRIBUTES);
$this->dbg("...content is shorter than ".self::MIN_ARTICLE_LENGTH." letters, trying not to weight attributes.\n"); $this->dbg('...content is shorter than '.self::MIN_ARTICLE_LENGTH." letters, trying not to weight attributes.\n");
return $this->grabArticle($this->body); return $this->grabArticle($this->body);
} elseif ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) { } elseif ($this->flagIsActive(self::FLAG_CLEAN_CONDITIONALLY)) {
$this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY); $this->removeFlag(self::FLAG_CLEAN_CONDITIONALLY);
$this->dbg("...content is shorter than ".self::MIN_ARTICLE_LENGTH." letters, trying not to clean at all.\n"); $this->dbg('...content is shorter than '.self::MIN_ARTICLE_LENGTH." letters, trying not to clean at all.\n");
return $this->grabArticle($this->body); return $this->grabArticle($this->body);
} else { } else {
@ -922,8 +922,9 @@ class Readability
* This also strips out any excess whitespace to be found. * This also strips out any excess whitespace to be found.
* *
* @param DOMElement $e * @param DOMElement $e
* @param boolean $normalizeSpaces (default: true) * @param bool $normalizeSpaces (default: true)
* @param boolean $flattenLines (default: false) * @param bool $flattenLines (default: false)
*
* @return string * @return string
*/ */
public function getInnerText($e, $normalizeSpaces = true, $flattenLines = false) public function getInnerText($e, $normalizeSpaces = true, $flattenLines = false)
@ -944,7 +945,6 @@ class Readability
* Remove the style attribute on every $e and under. * Remove the style attribute on every $e and under.
* *
* @param DOMElement $e * @param DOMElement $e
* @return void
*/ */
public function cleanStyles($e) public function cleanStyles($e)
{ {
@ -960,6 +960,7 @@ class Readability
* Get comma number for a given text. * Get comma number for a given text.
* *
* @param string $text * @param string $text
*
* @return number (integer) * @return number (integer)
*/ */
public function getCommaCount($text) public function getCommaCount($text)
@ -971,6 +972,7 @@ class Readability
* Input string should be normalized. * Input string should be normalized.
* *
* @param string $text * @param string $text
*
* @return number (integer) * @return number (integer)
*/ */
public function getWordCount($text) public function getWordCount($text)
@ -984,6 +986,7 @@ class Readability
* *
* @param DOMElement $e * @param DOMElement $e
* @param string $excludeExternal * @param string $excludeExternal
*
* @return number (float) * @return number (float)
*/ */
public function getLinkDensity($e, $excludeExternal = false) public function getLinkDensity($e, $excludeExternal = false)
@ -1009,6 +1012,7 @@ class Readability
* *
* @param DOMElement $element * @param DOMElement $element
* @param string $attribute * @param string $attribute
*
* @return number (Integer) * @return number (Integer)
*/ */
protected function weightAttribute($element, $attribute) protected function weightAttribute($element, $attribute)
@ -1040,6 +1044,7 @@ class Readability
* Get an element relative weight. * Get an element relative weight.
* *
* @param DOMElement $e * @param DOMElement $e
*
* @return number (Integer) * @return number (Integer)
*/ */
public function getWeight($e) public function getWeight($e)
@ -1059,7 +1064,6 @@ class Readability
* Remove extraneous break tags from a node. * Remove extraneous break tags from a node.
* *
* @param DOMElement $node * @param DOMElement $node
* @return void
*/ */
public function killBreaks($node) public function killBreaks($node)
{ {
@ -1069,13 +1073,12 @@ class Readability
} }
/** /**
* Clean a node of all elements of type "tag". * Clean a node of all elements of type "tag".
* (Unless it's a youtube/vimeo video. People love movies.) * (Unless it's a youtube/vimeo video. People love movies.).
* *
* Updated 2012-09-18 to preserve youtube/vimeo iframes * Updated 2012-09-18 to preserve youtube/vimeo iframes
* *
* @param DOMElement $e * @param DOMElement $e
* @param string $tag * @param string $tag
* @return void
*/ */
public function clean($e, $tag) public function clean($e, $tag)
{ {
@ -1105,7 +1108,6 @@ class Readability
* *
* @param DOMElement $e * @param DOMElement $e
* @param string $tag * @param string $tag
* @return void
*/ */
public function cleanConditionally($e, $tag) public function cleanConditionally($e, $tag)
{ {
@ -1114,7 +1116,7 @@ class Readability
} }
$tagsList = $e->getElementsByTagName($tag); $tagsList = $e->getElementsByTagName($tag);
$curTagsLength = $tagsList->length; $curTagsLength = $tagsList->length;
/** /*
* Gather counts for other typical elements embedded within. * Gather counts for other typical elements embedded within.
* Traverse backwards so we can remove nodes at the same time without effecting the traversal. * Traverse backwards so we can remove nodes at the same time without effecting the traversal.
* *
@ -1130,7 +1132,7 @@ class Readability
$this->dbg('Removing...'); $this->dbg('Removing...');
$node->parentNode->removeChild($node); $node->parentNode->removeChild($node);
} elseif ($this->getCommaCount($this->getInnerText($node)) < self::MIN_COMMAS_IN_PARAGRAPH) { } elseif ($this->getCommaCount($this->getInnerText($node)) < self::MIN_COMMAS_IN_PARAGRAPH) {
/** /*
* If there are not very many commas, and the number of * If there are not very many commas, and the number of
* non-paragraph elements is more than paragraphs or other ominous signs, remove the element. * non-paragraph elements is more than paragraphs or other ominous signs, remove the element.
*/ */
@ -1166,10 +1168,10 @@ class Readability
$this->dbg(' content length less than 6 chars, 0 embeds and either 0 images or more than 2 images'); $this->dbg(' content length less than 6 chars, 0 embeds and either 0 images or more than 2 images');
$toRemove = true; $toRemove = true;
} elseif ($weight < 25 && $linkDensity > 0.25) { } elseif ($weight < 25 && $linkDensity > 0.25) {
$this->dbg(' weight is '.$weight.' < 25 and link density is '.sprintf("%.2f", $linkDensity).' > 0.25'); $this->dbg(' weight is '.$weight.' < 25 and link density is '.sprintf('%.2f', $linkDensity).' > 0.25');
$toRemove = true; $toRemove = true;
} elseif ($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) { } elseif ($a > 2 && ($weight >= 25 && $linkDensity > 0.5)) {
$this->dbg(' more than 2 links and weight is '.$weight.' > 25 but link density is '.sprintf("%.2f", $linkDensity).' > 0.5'); $this->dbg(' more than 2 links and weight is '.$weight.' > 25 but link density is '.sprintf('%.2f', $linkDensity).' > 0.5');
$toRemove = true; $toRemove = true;
} elseif ($embedCount > 3) { } elseif ($embedCount > 3) {
$this->dbg(' more than 3 embeds'); $this->dbg(' more than 3 embeds');
@ -1189,10 +1191,10 @@ class Readability
$this->dbg(' content length less than 25 chars and 0 images, or more than 2 images'); $this->dbg(' content length less than 25 chars and 0 images, or more than 2 images');
$toRemove = true; $toRemove = true;
} elseif ($weight < 25 && $linkDensity > 0.2) { } elseif ($weight < 25 && $linkDensity > 0.2) {
$this->dbg(' weight is '.$weight.' lower than 0 and link density is '.sprintf("%.2f", $linkDensity).' > 0.2'); $this->dbg(' weight is '.$weight.' lower than 0 and link density is '.sprintf('%.2f', $linkDensity).' > 0.2');
$toRemove = true; $toRemove = true;
} elseif ($weight >= 25 && $linkDensity > 0.5) { } elseif ($weight >= 25 && $linkDensity > 0.5) {
$this->dbg(' weight above 25 but link density is '.sprintf("%.2f", $linkDensity).' > 0.5'); $this->dbg(' weight above 25 but link density is '.sprintf('%.2f', $linkDensity).' > 0.5');
$toRemove = true; $toRemove = true;
} elseif (($embedCount == 1 && $contentLength < 75) || $embedCount > 1) { } elseif (($embedCount == 1 && $contentLength < 75) || $embedCount > 1) {
$this->dbg(' 1 embed and content length smaller than 75 chars, or more than one embed'); $this->dbg(' 1 embed and content length smaller than 75 chars, or more than one embed');
@ -1211,7 +1213,6 @@ class Readability
* Clean out spurious headers from an Element. Checks things like classnames and link density. * Clean out spurious headers from an Element. Checks things like classnames and link density.
* *
* @param DOMElement $e * @param DOMElement $e
* @return void
*/ */
public function cleanHeaders($e) public function cleanHeaders($e)
{ {

1
tests/ReadabilityTest.php
Unescape View File

@ -3,7 +3,6 @@
namespace Tests\Readability; namespace Tests\Readability;
use Readability\Readability; use Readability\Readability;
use Readability\JSLikeHTMLElement;
class ReadabilityTested extends Readability class ReadabilityTested extends Readability
{ {

Write Preview
Loading…
Cancel
Save