JayBizzle / Crawler-Detect

src/CrawlerDetect.php

Spacing +2 added lines, -2 removed lines

@@ -461,7 +461,7 @@ 
     public function setHttpHeaders($httpHeaders = null)
     {
         // use global _SERVER if $httpHeaders aren't defined
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
+        if ( ! is_array($httpHeaders) || ! count($httpHeaders)) {
             $httpHeaders = $_SERVER;
         }
         // clear existing headers
@@ -492,7 +492,7 @@ 
                 }
             }
 
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
+            return $this->userAgent = ( ! empty($this->userAgent) ? trim($this->userAgent) : null);
         }
     }
 

Indentation +174 added lines, -174 removed lines

@@ -16,178 +16,178 @@
 
 class CrawlerDetect
 {
-    /**
-     * The user agent.
-     *
-     * @var null
-     */
-    protected $userAgent = null;
-
-    /**
-     * Headers that contain a user agent.
-     *
-     * @var array
-     */
-    protected $httpHeaders = array();
-
-    /**
-     * Store regex matches.
-     *
-     * @var array
-     */
-    protected $matches = array();
-
-    /**
-     * Crawlers object.
-     *
-     * @var \Jaybizzle\CrawlerDetect\Fixtures\Crawlers
-     */
-    protected $crawlers;
-
-    /**
-     * Exclusions object.
-     *
-     * @var \Jaybizzle\CrawlerDetect\Fixtures\Exclusions
-     */
-    protected $exclusions;
-
-    /**
-     * All possible HTTP headers that represent the
-     * User-Agent string.
-     *
-     * @var array
-     */
-    protected static $uaHttpHeaders = array(
-        // The default User-Agent string.
-        'HTTP_USER_AGENT',
-        // Header can occur on devices using Opera Mini.
-        'HTTP_X_OPERAMINI_PHONE_UA',
-        // Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
-        'HTTP_X_DEVICE_USER_AGENT',
-        'HTTP_X_ORIGINAL_USER_AGENT',
-        'HTTP_X_SKYFIRE_PHONE',
-        'HTTP_X_BOLT_PHONE_UA',
-        'HTTP_DEVICE_STOCK_UA',
-        'HTTP_X_UCBROWSER_DEVICE_UA',
-    );
-
-    /**
-     * Class constructor.
-     */
-    public function __construct(array $headers = null, $userAgent = null)
-    {
-        $this->setHttpHeaders($headers);
-        $this->setUserAgent($userAgent);
-        $this->crawlers = new Crawlers();
-        $this->exclusions = new Exclusions();
-    }
-
-    /**
-     * Set HTTP headers.
-     *
-     * @param array $httpHeaders
-     */
-    public function setHttpHeaders($httpHeaders = null)
-    {
-        // use global _SERVER if $httpHeaders aren't defined
-        if (!is_array($httpHeaders) || !count($httpHeaders)) {
-            $httpHeaders = $_SERVER;
-        }
-        // clear existing headers
-        $this->httpHeaders = array();
-        // Only save HTTP headers. In PHP land, that means only _SERVER vars that
-        // start with HTTP_.
-        foreach ($httpHeaders as $key => $value) {
-            if (substr($key, 0, 5) === 'HTTP_') {
-                $this->httpHeaders[$key] = $value;
-            }
-        }
-    }
-
-    /**
-     * Return user agent headers.
-     *
-     * @return array
-     */
-    public function getUaHttpHeaders()
-    {
-        return self::$uaHttpHeaders;
-    }
-
-    /**
-     * Set the user agent.
-     *
-     * @param string $userAgent
-     */
-    public function setUserAgent($userAgent = null)
-    {
-        if (false === empty($userAgent)) {
-            return $this->userAgent = $userAgent;
-        } else {
-            $this->userAgent = null;
-            foreach ($this->getUaHttpHeaders() as $altHeader) {
-                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
-                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
-                }
-            }
-
-            return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
-        }
-    }
-
-    /**
-     * Build the user agent regex.
-     *
-     * @return string
-     */
-    public function getRegex()
-    {
-        return '('.implode('|', $this->crawlers->getAll()).')';
-    }
-
-    /**
-     * Build the replacement regex.
-     *
-     * @return string
-     */
-    public function getExclusions()
-    {
-        return '('.implode('|', $this->exclusions->getAll()).')';
-    }
-
-    /**
-     * Check user agent string against the regex.
-     *
-     * @param string $userAgent
-     *
-     * @return bool
-     */
-    public function isCrawler($userAgent = null)
-    {
-        $agent = is_null($userAgent) ? $this->userAgent : $userAgent;
-
-        $agent = preg_replace('/'.$this->getExclusions().'/i', '', $agent);
-
-        if (trim($agent) === false) {
-            return false;
-        } else {
-            $result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
-        }
-
-        if ($matches) {
-            $this->matches = $matches;
-        }
-
-        return (bool) $result;
-    }
-
-    /**
-     * Return the matches.
-     *
-     * @return string
-     */
-    public function getMatches()
-    {
-        return $this->matches[0];
-    }
+	/**
+	 * The user agent.
+	 *
+	 * @var null
+	 */
+	protected $userAgent = null;
+
+	/**
+	 * Headers that contain a user agent.
+	 *
+	 * @var array
+	 */
+	protected $httpHeaders = array();
+
+	/**
+	 * Store regex matches.
+	 *
+	 * @var array
+	 */
+	protected $matches = array();
+
+	/**
+	 * Crawlers object.
+	 *
+	 * @var \Jaybizzle\CrawlerDetect\Fixtures\Crawlers
+	 */
+	protected $crawlers;
+
+	/**
+	 * Exclusions object.
+	 *
+	 * @var \Jaybizzle\CrawlerDetect\Fixtures\Exclusions
+	 */
+	protected $exclusions;
+
+	/**
+	 * All possible HTTP headers that represent the
+	 * User-Agent string.
+	 *
+	 * @var array
+	 */
+	protected static $uaHttpHeaders = array(
+		// The default User-Agent string.
+		'HTTP_USER_AGENT',
+		// Header can occur on devices using Opera Mini.
+		'HTTP_X_OPERAMINI_PHONE_UA',
+		// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
+		'HTTP_X_DEVICE_USER_AGENT',
+		'HTTP_X_ORIGINAL_USER_AGENT',
+		'HTTP_X_SKYFIRE_PHONE',
+		'HTTP_X_BOLT_PHONE_UA',
+		'HTTP_DEVICE_STOCK_UA',
+		'HTTP_X_UCBROWSER_DEVICE_UA',
+	);
+
+	/**
+	 * Class constructor.
+	 */
+	public function __construct(array $headers = null, $userAgent = null)
+	{
+		$this->setHttpHeaders($headers);
+		$this->setUserAgent($userAgent);
+		$this->crawlers = new Crawlers();
+		$this->exclusions = new Exclusions();
+	}
+
+	/**
+	 * Set HTTP headers.
+	 *
+	 * @param array $httpHeaders
+	 */
+	public function setHttpHeaders($httpHeaders = null)
+	{
+		// use global _SERVER if $httpHeaders aren't defined
+		if (!is_array($httpHeaders) || !count($httpHeaders)) {
+			$httpHeaders = $_SERVER;
+		}
+		// clear existing headers
+		$this->httpHeaders = array();
+		// Only save HTTP headers. In PHP land, that means only _SERVER vars that
+		// start with HTTP_.
+		foreach ($httpHeaders as $key => $value) {
+			if (substr($key, 0, 5) === 'HTTP_') {
+				$this->httpHeaders[$key] = $value;
+			}
+		}
+	}
+
+	/**
+	 * Return user agent headers.
+	 *
+	 * @return array
+	 */
+	public function getUaHttpHeaders()
+	{
+		return self::$uaHttpHeaders;
+	}
+
+	/**
+	 * Set the user agent.
+	 *
+	 * @param string $userAgent
+	 */
+	public function setUserAgent($userAgent = null)
+	{
+		if (false === empty($userAgent)) {
+			return $this->userAgent = $userAgent;
+		} else {
+			$this->userAgent = null;
+			foreach ($this->getUaHttpHeaders() as $altHeader) {
+				if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
+					$this->userAgent .= $this->httpHeaders[$altHeader].' ';
+				}
+			}
+
+			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
+		}
+	}
+
+	/**
+	 * Build the user agent regex.
+	 *
+	 * @return string
+	 */
+	public function getRegex()
+	{
+		return '('.implode('|', $this->crawlers->getAll()).')';
+	}
+
+	/**
+	 * Build the replacement regex.
+	 *
+	 * @return string
+	 */
+	public function getExclusions()
+	{
+		return '('.implode('|', $this->exclusions->getAll()).')';
+	}
+
+	/**
+	 * Check user agent string against the regex.
+	 *
+	 * @param string $userAgent
+	 *
+	 * @return bool
+	 */
+	public function isCrawler($userAgent = null)
+	{
+		$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
+
+		$agent = preg_replace('/'.$this->getExclusions().'/i', '', $agent);
+
+		if (trim($agent) === false) {
+			return false;
+		} else {
+			$result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
+		}
+
+		if ($matches) {
+			$this->matches = $matches;
+		}
+
+		return (bool) $result;
+	}
+
+	/**
+	 * Return the matches.
+	 *
+	 * @return string
+	 */
+	public function getMatches()
+	{
+		return $this->matches[0];
+	}
 }

tests/bootstrap.php

Indentation +1 added lines, -1 removed lines

@@ -11,7 +11,7 @@
 $dot = dirname(__FILE__);
 
 if (!file_exists($composer = dirname($dot).'/vendor/autoload.php')) {
-    throw new RuntimeException("Please run 'composer install' first to set up autoloading. $composer");
+	throw new RuntimeException("Please run 'composer install' first to set up autoloading. $composer");
 }
 /** @var \Composer\Autoload\ClassLoader $autoloader */
 $autoloader = include $composer;

Spacing +1 added lines, -1 removed lines

@@ -10,7 +10,7 @@
  */
 $dot = dirname(__FILE__);
 
-if (!file_exists($composer = dirname($dot).'/vendor/autoload.php')) {
+if ( ! file_exists($composer = dirname($dot).'/vendor/autoload.php')) {
     throw new RuntimeException("Please run 'composer install' first to set up autoloading. $composer");
 }
 /** @var \Composer\Autoload\ClassLoader $autoloader */

src/Fixtures/Exclusions.php

Indentation +49 added lines, -49 removed lines

@@ -13,53 +13,53 @@
 
 class Exclusions extends AbstractProvider
 {
-    /**
-     * List of strings to remove from the user agent before running the crawler regex
-     * Over a large list of user agents, this gives us about a 55% speed increase!
-     *
-     * @var array
-     */
-    protected $data = array(
-        'Safari.[\d\.]*',
-        'Firefox.[\d\.]*',
-        'Chrome.[\d\.]*',
-        'Chromium.[\d\.]*',
-        'MSIE.[\d\.]',
-        'Opera\/[\d\.]*',
-        'Mozilla.[\d\.]*',
-        'AppleWebKit.[\d\.]*',
-        'Trident.[\d\.]*',
-        'Windows NT.[\d\.]*',
-        'Android.[\d\.]*',
-        'Macintosh.',
-        'Ubuntu',
-        'Linux',
-        '[ ]Intel',
-        'Mac OS X [\d_]*',
-        '(like )?Gecko(.[\d\.]*)?',
-        'KHTML',
-        'CriOS.[\d\.]*',
-        'CPU iPhone OS ([0-9_])* like Mac OS X',
-        'CPU OS ([0-9_])* like Mac OS X',
-        'iPod',
-        'compatible',
-        'x86_..',
-        'i686',
-        'x64',
-        'X11',
-        'rv:[\d\.]*',
-        'Version.[\d\.]*',
-        'WOW64',
-        'Win64',
-        'Dalvik.[\d\.]*',
-        ' \.NET CLR [\d\.]*',
-        'Presto.[\d\.]*',
-        'Media Center PC',
-        'BlackBerry',
-        'Build',
-        'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.',
-        'Opera',
-        ' \.NET[\d\.]*',
-        '\(|\)|;|,', // Remove the following characters ( ) : ,
-    );
+	/**
+	 * List of strings to remove from the user agent before running the crawler regex
+	 * Over a large list of user agents, this gives us about a 55% speed increase!
+	 *
+	 * @var array
+	 */
+	protected $data = array(
+		'Safari.[\d\.]*',
+		'Firefox.[\d\.]*',
+		'Chrome.[\d\.]*',
+		'Chromium.[\d\.]*',
+		'MSIE.[\d\.]',
+		'Opera\/[\d\.]*',
+		'Mozilla.[\d\.]*',
+		'AppleWebKit.[\d\.]*',
+		'Trident.[\d\.]*',
+		'Windows NT.[\d\.]*',
+		'Android.[\d\.]*',
+		'Macintosh.',
+		'Ubuntu',
+		'Linux',
+		'[ ]Intel',
+		'Mac OS X [\d_]*',
+		'(like )?Gecko(.[\d\.]*)?',
+		'KHTML',
+		'CriOS.[\d\.]*',
+		'CPU iPhone OS ([0-9_])* like Mac OS X',
+		'CPU OS ([0-9_])* like Mac OS X',
+		'iPod',
+		'compatible',
+		'x86_..',
+		'i686',
+		'x64',
+		'X11',
+		'rv:[\d\.]*',
+		'Version.[\d\.]*',
+		'WOW64',
+		'Win64',
+		'Dalvik.[\d\.]*',
+		' \.NET CLR [\d\.]*',
+		'Presto.[\d\.]*',
+		'Media Center PC',
+		'BlackBerry',
+		'Build',
+		'Opera Mini\/\d{1,2}\.\d{1,2}\.[\d\.]*\/\d{1,2}\.',
+		'Opera',
+		' \.NET[\d\.]*',
+		'\(|\)|;|,', // Remove the following characters ( ) : ,
+	);
 }

src/Fixtures/Crawlers.php

Indentation +320 added lines, -320 removed lines

@@ -13,324 +13,324 @@
 
 class Crawlers extends AbstractProvider
 {
-    /**
-     * Array of regular expressions to match against the user agent.
-     *
-     * @var array
-     */
-    protected $data = array(
-        '.*Java.*outbrain',
-        '008\/',
-        '^NING\/',
-        'A6-Indexer',
-        'Aboundex',
-        'Accoona-AI-Agent',
-        'acoon',
-        'AddThis',
-        'ADmantX',
-        'AHC',
-        'Airmail',
-        'alexa site audit',
-        'Anemone',
-        'Apache-HttpClient\/',
-        'Arachmo',
-        'archive-com',
-        'B-l-i-t-z-B-O-T',
-        'Backlink-Ceck\.de',
-        'baidu\.com',
-        'BazQux',
-        'bibnum\.bnf',
-        'biglotron',
-        'BingLocalSearch',
-        'BingPreview',
-        'binlar',
-        'Bloglovin',
-        'Blogtrottr',
-        'boitho\.com-dc',
-        'Browsershots',
-        'BUbiNG',
-        'Butterfly\/',
-        'BuzzSumo',
-        'CapsuleChecker',
-        'CC Metadata Scaper',
-        'Cerberian Drtrs',
-        'changedetection',
-        'Charlotte',
-        'clips\.ua\.ac\.be',
-        'CloudFlare-AlwaysOnline',
-        'coccoc',
-        'CommaFeed',
-        'Commons-HttpClient',
-        'convera',
-        'cosmos',
-        'corporatetwitnews',
-        'Covario-IDS',
-        'cron-job\.org',
-        'Curious George',
-        'curl',
-        'CyberPatrol',
-        'DataparkSearch',
-        'dataprovider',
-        'Daum(oa)?[ \/][0-9]',
-        'developers\.google\.com\/\+\/web\/snippet\/',
-        'Digg',
-        'DomainAppender',
-        'Dragonfly File Reader',
-        'drupact',
-        'EARTHCOM',
-        'ec2linkfinder',
-        'ECCP',
-        'ElectricMonk',
-        'EMail Exractor',
-        'EmailWolf',
-        'Embed PHP Library',
-        'Embedly',
-        'europarchive\.org',
-        'EventMachine HttpClient',
-        'ExactSearch',
-        'ExaleadCloudview',
-        'ezooms',
-        'facebookexternalhit',
-        'facebookplatform',
-        'Feed Wrangler',
-        'Feedbin',
-        'FeedBurner',
-        'Feedfetcher-Google',
-        'Feedly',
-        'Feedspot',
-        'FeedValidator',
-        'Fever',
-        'findlink',
-        'findthatfile',
-        'Flamingo_SearchEngine',
-        'FlipboardProxy',
-        'fluffy',
-        'Funnelback',
-        'g00g1e\.net',
-        'Genieo',
-        'getprismatic\.com',
-        'GigablastOpenSource',
-        'Go-http-client',
-        'Google favicon',
-        'Google Keyword Suggestion',
-        'Google Page Speed Insights',
-        'Google Web Preview',
-        'Google-HTTP-Java-Client',
-        'Google-Site-Verification',
-        'google_partner_monitoring',
-        'GoogleProducer',
-        'Grammarly',
-        'grub-client',
-        'heritrix',
-        'Holmes',
-        'htdig',
-        'HTTPMon',
-        'http-kit',
-        'http_requester',
-        'httpunit',
-        'http_request2',
-        'httrack',
-        'HubPages.*crawlingpolicy',
-        'HubSpot Marketing Grader',
-        'ichiro',
-        'IDG Twitter Links Resolver',
-        'igdeSpyder',
-        'InAGist',
-        'infegy',
-        'InfoWizards Reciprocal Link System PRO',
-        'inpwrd\.com',
-        'integromedb',
-        'IODC',
-        'IOI',
-        'ips-agent',
-        'iZSearch',
-        '^Java\/',
-        'Jigsaw',
-        'Jobrapido',
-        'kouio',
-        'L\.webis',
-        'Larbin',
-        'libwww',
-        'Link Valet',
-        'linkCheck',
-        'linkdex',
-        'LinkExaminer',
-        'LinkWalker',
-        'Lipperhey',
-        'link checker',
-        'link validator',
-        'LongURL API',
-        'ltx71',
-        'lwp-trivial',
-        'lycos',
-        'mabontland',
-        'MagpieRSS',
-        'Mediapartners-Google',
-        'MegaIndex\.ru',
-        'MetaURI',
-        'MergeFlow-PageReader',
-        'Mnogosearch',
-        'mogimogi',
-        'Mojolicious (Perl)',
-        'Morning Paper',
-        'Mrcgiguy',
-        'MVAClient',
-        'Netcraft Web Server Survey',
-        'NetcraftSurveyAgent',
-        'NetLyzer FastProbe',
-        'netresearch',
-        'Netvibes',
-        'NewsBlur .*(Fetcher|Finder)',
-        'NewsGator',
-        'newsme',
-        'newspaper\/',
-        'NG-Search',
-        'nineconnections\.com',
-        'nominet\.org\.uk',
-        'Notifixious',
-        'nuhk',
-        'nutch',
-        'Nuzzel',
-        'Nymesis',
-        'oegp',
-        'Omea Reader',
-        'omgili',
-        'Orbiter',
-        'ow\.ly',
-        'Go [\d\.]* package http',
-        'page2rss',
-        'PagePeeker',
-        'panscient',
-        'Peew',
-        'PhantomJS\/',
-        'phpcrawl',
-        'phpservermon',
-        'Pingdom\.com',
-        'Pinterest',
-        'Pizilla',
-        'Ploetz \+ Zeller',
-        'Plukkie',
-        'PocketParser',
-        'Pompos',
-        'postano',
-        'PostPost',
-        'postrank',
-        'proximic',
-        'Pulsepoint XT3 web scraper',
-        'Python-httplib2',
-        'python-requests',
-        'Python-urllib',
-        'Qseero',
-        'Qwantify',
-        'Radian6',
-        'Readability',
-        'RebelMouse',
-        'RetrevoPageAnalyzer',
-        'Riddler',
-        'Robosourcer',
-        'ROI Hunter',
-        'Ruby',
-        'SalesIntelligent',
-        'SBIder',
-        'scooter',
-        'ScoutJet',
-        'ScoutURLMonitor',
-        'Scrapy',
-        'Scrubby',
-        'SearchSight',
-        'semanticdiscovery',
-        'SEOstats',
-        'Server Density Service Monitoring',
-        'servernfo\.com',
-        'Seznam screenshot-generator',
-        'ShopWiki',
-        'SilverReader',
-        'SimplePie',
-        'Site24x7',
-        'SiteBar',
-        'siteexplorer\.info',
-        'Siteimprove\.com',
-        'SkypeUriPreview',
-        'slider\.com',
-        'slurp',
-        'SMRF URL Expander',
-        'snapchat-proxy',
-        'Snappy',
-        'SNK Siteshooter B0t',
-        'sogou',
-        'SortSite',
-        'speedy',
-        'Spinn3r',
-        'Sqworm',
-        'StackRambler',
-        'Stratagems Kumo',
-        'summify',
-        'teoma',
-        'theoldreader\.com',
-        'TinEye',
-        'Tiny Tiny RSS',
-        'Traackr.com',
-        'truwoGPS',
-        'tweetedtimes\.com',
-        'Twikle',
-        'Typhoeus',
-        'ubermetrics-technologies',
-        'UdmSearch',
-        'UnwindFetchor',
-        'updated',
-        'URLChecker',
-        'urlresolver',
-        'Vagabondo',
-        'Validator\.nu\/LV',
-        'via ggpht\.com GoogleImageProxy',
-        'vkShare',
-        'Vortex',
-        'voyager\/',
-        'VYU2',
-        'W3C-checklink',
-        'W3C-mobileOK',
-        'W3C_CSS_Validator_JFouffa',
-        'W3C_I18n-Checker',
-        'W3C_Unicorn',
-        'W3C_Validator',
-        'Wappalyzer',
-        'WinHttpRequest',
-        'web-capture\.net',
-        'WebCapture',
-        'WebCorp',
-        'webcollage',
-        'WebIndex',
-        'WebFetch',
-        'webmon ',
-        'websitepulse[+ ]checker',
-        'Websquash\.com',
-        'WebThumbnail',
-        'WeSEE:Search',
-        'wf84',
-        'wget',
-        'WhatsApp',
-        'WomlpeFactory',
-        'WordPress\/',
-        'wotbox',
-        'wscheck',
-        'WWW-Mechanize',
-        'www\.monitor\.us',
-        'XaxisSemanticsClassifier',
-        'Xenu Link Sleuth',
-        'XML Sitemaps Generator',
-        'Y!J-ASR',
-        'yacy',
-        'Yahoo Ad monitoring',
-        'Yahoo Link Preview',
-        'YahooSeeker',
-        'yandex',
-        'yanga',
-        'yeti',
-        'yoogliFetchAgent',
-        'YottaaMonitor',
-        'Zao',
-        'zgrab',
-        'ZyBorg',
-        '[a-z0-9\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
-    );
+	/**
+	 * Array of regular expressions to match against the user agent.
+	 *
+	 * @var array
+	 */
+	protected $data = array(
+		'.*Java.*outbrain',
+		'008\/',
+		'^NING\/',
+		'A6-Indexer',
+		'Aboundex',
+		'Accoona-AI-Agent',
+		'acoon',
+		'AddThis',
+		'ADmantX',
+		'AHC',
+		'Airmail',
+		'alexa site audit',
+		'Anemone',
+		'Apache-HttpClient\/',
+		'Arachmo',
+		'archive-com',
+		'B-l-i-t-z-B-O-T',
+		'Backlink-Ceck\.de',
+		'baidu\.com',
+		'BazQux',
+		'bibnum\.bnf',
+		'biglotron',
+		'BingLocalSearch',
+		'BingPreview',
+		'binlar',
+		'Bloglovin',
+		'Blogtrottr',
+		'boitho\.com-dc',
+		'Browsershots',
+		'BUbiNG',
+		'Butterfly\/',
+		'BuzzSumo',
+		'CapsuleChecker',
+		'CC Metadata Scaper',
+		'Cerberian Drtrs',
+		'changedetection',
+		'Charlotte',
+		'clips\.ua\.ac\.be',
+		'CloudFlare-AlwaysOnline',
+		'coccoc',
+		'CommaFeed',
+		'Commons-HttpClient',
+		'convera',
+		'cosmos',
+		'corporatetwitnews',
+		'Covario-IDS',
+		'cron-job\.org',
+		'Curious George',
+		'curl',
+		'CyberPatrol',
+		'DataparkSearch',
+		'dataprovider',
+		'Daum(oa)?[ \/][0-9]',
+		'developers\.google\.com\/\+\/web\/snippet\/',
+		'Digg',
+		'DomainAppender',
+		'Dragonfly File Reader',
+		'drupact',
+		'EARTHCOM',
+		'ec2linkfinder',
+		'ECCP',
+		'ElectricMonk',
+		'EMail Exractor',
+		'EmailWolf',
+		'Embed PHP Library',
+		'Embedly',
+		'europarchive\.org',
+		'EventMachine HttpClient',
+		'ExactSearch',
+		'ExaleadCloudview',
+		'ezooms',
+		'facebookexternalhit',
+		'facebookplatform',
+		'Feed Wrangler',
+		'Feedbin',
+		'FeedBurner',
+		'Feedfetcher-Google',
+		'Feedly',
+		'Feedspot',
+		'FeedValidator',
+		'Fever',
+		'findlink',
+		'findthatfile',
+		'Flamingo_SearchEngine',
+		'FlipboardProxy',
+		'fluffy',
+		'Funnelback',
+		'g00g1e\.net',
+		'Genieo',
+		'getprismatic\.com',
+		'GigablastOpenSource',
+		'Go-http-client',
+		'Google favicon',
+		'Google Keyword Suggestion',
+		'Google Page Speed Insights',
+		'Google Web Preview',
+		'Google-HTTP-Java-Client',
+		'Google-Site-Verification',
+		'google_partner_monitoring',
+		'GoogleProducer',
+		'Grammarly',
+		'grub-client',
+		'heritrix',
+		'Holmes',
+		'htdig',
+		'HTTPMon',
+		'http-kit',
+		'http_requester',
+		'httpunit',
+		'http_request2',
+		'httrack',
+		'HubPages.*crawlingpolicy',
+		'HubSpot Marketing Grader',
+		'ichiro',
+		'IDG Twitter Links Resolver',
+		'igdeSpyder',
+		'InAGist',
+		'infegy',
+		'InfoWizards Reciprocal Link System PRO',
+		'inpwrd\.com',
+		'integromedb',
+		'IODC',
+		'IOI',
+		'ips-agent',
+		'iZSearch',
+		'^Java\/',
+		'Jigsaw',
+		'Jobrapido',
+		'kouio',
+		'L\.webis',
+		'Larbin',
+		'libwww',
+		'Link Valet',
+		'linkCheck',
+		'linkdex',
+		'LinkExaminer',
+		'LinkWalker',
+		'Lipperhey',
+		'link checker',
+		'link validator',
+		'LongURL API',
+		'ltx71',
+		'lwp-trivial',
+		'lycos',
+		'mabontland',
+		'MagpieRSS',
+		'Mediapartners-Google',
+		'MegaIndex\.ru',
+		'MetaURI',
+		'MergeFlow-PageReader',
+		'Mnogosearch',
+		'mogimogi',
+		'Mojolicious (Perl)',
+		'Morning Paper',
+		'Mrcgiguy',
+		'MVAClient',
+		'Netcraft Web Server Survey',
+		'NetcraftSurveyAgent',
+		'NetLyzer FastProbe',
+		'netresearch',
+		'Netvibes',
+		'NewsBlur .*(Fetcher|Finder)',
+		'NewsGator',
+		'newsme',
+		'newspaper\/',
+		'NG-Search',
+		'nineconnections\.com',
+		'nominet\.org\.uk',
+		'Notifixious',
+		'nuhk',
+		'nutch',
+		'Nuzzel',
+		'Nymesis',
+		'oegp',
+		'Omea Reader',
+		'omgili',
+		'Orbiter',
+		'ow\.ly',
+		'Go [\d\.]* package http',
+		'page2rss',
+		'PagePeeker',
+		'panscient',
+		'Peew',
+		'PhantomJS\/',
+		'phpcrawl',
+		'phpservermon',
+		'Pingdom\.com',
+		'Pinterest',
+		'Pizilla',
+		'Ploetz \+ Zeller',
+		'Plukkie',
+		'PocketParser',
+		'Pompos',
+		'postano',
+		'PostPost',
+		'postrank',
+		'proximic',
+		'Pulsepoint XT3 web scraper',
+		'Python-httplib2',
+		'python-requests',
+		'Python-urllib',
+		'Qseero',
+		'Qwantify',
+		'Radian6',
+		'Readability',
+		'RebelMouse',
+		'RetrevoPageAnalyzer',
+		'Riddler',
+		'Robosourcer',
+		'ROI Hunter',
+		'Ruby',
+		'SalesIntelligent',
+		'SBIder',
+		'scooter',
+		'ScoutJet',
+		'ScoutURLMonitor',
+		'Scrapy',
+		'Scrubby',
+		'SearchSight',
+		'semanticdiscovery',
+		'SEOstats',
+		'Server Density Service Monitoring',
+		'servernfo\.com',
+		'Seznam screenshot-generator',
+		'ShopWiki',
+		'SilverReader',
+		'SimplePie',
+		'Site24x7',
+		'SiteBar',
+		'siteexplorer\.info',
+		'Siteimprove\.com',
+		'SkypeUriPreview',
+		'slider\.com',
+		'slurp',
+		'SMRF URL Expander',
+		'snapchat-proxy',
+		'Snappy',
+		'SNK Siteshooter B0t',
+		'sogou',
+		'SortSite',
+		'speedy',
+		'Spinn3r',
+		'Sqworm',
+		'StackRambler',
+		'Stratagems Kumo',
+		'summify',
+		'teoma',
+		'theoldreader\.com',
+		'TinEye',
+		'Tiny Tiny RSS',
+		'Traackr.com',
+		'truwoGPS',
+		'tweetedtimes\.com',
+		'Twikle',
+		'Typhoeus',
+		'ubermetrics-technologies',
+		'UdmSearch',
+		'UnwindFetchor',
+		'updated',
+		'URLChecker',
+		'urlresolver',
+		'Vagabondo',
+		'Validator\.nu\/LV',
+		'via ggpht\.com GoogleImageProxy',
+		'vkShare',
+		'Vortex',
+		'voyager\/',
+		'VYU2',
+		'W3C-checklink',
+		'W3C-mobileOK',
+		'W3C_CSS_Validator_JFouffa',
+		'W3C_I18n-Checker',
+		'W3C_Unicorn',
+		'W3C_Validator',
+		'Wappalyzer',
+		'WinHttpRequest',
+		'web-capture\.net',
+		'WebCapture',
+		'WebCorp',
+		'webcollage',
+		'WebIndex',
+		'WebFetch',
+		'webmon ',
+		'websitepulse[+ ]checker',
+		'Websquash\.com',
+		'WebThumbnail',
+		'WeSEE:Search',
+		'wf84',
+		'wget',
+		'WhatsApp',
+		'WomlpeFactory',
+		'WordPress\/',
+		'wotbox',
+		'wscheck',
+		'WWW-Mechanize',
+		'www\.monitor\.us',
+		'XaxisSemanticsClassifier',
+		'Xenu Link Sleuth',
+		'XML Sitemaps Generator',
+		'Y!J-ASR',
+		'yacy',
+		'Yahoo Ad monitoring',
+		'Yahoo Link Preview',
+		'YahooSeeker',
+		'yandex',
+		'yanga',
+		'yeti',
+		'yoogliFetchAgent',
+		'YottaaMonitor',
+		'Zao',
+		'zgrab',
+		'ZyBorg',
+		'[a-z0-9\-_]*((?<!cu)bot|crawler|archiver|transcoder|spider)',
+	);
 }

tests/UATests.php

Indentation +40 added lines, -40 removed lines

@@ -14,55 +14,55 @@
 
 class UserAgentTest extends PHPUnit_Framework_TestCase
 {
-    protected $CrawlerDetect;
+	protected $CrawlerDetect;
 
-    public function setUp()
-    {
-        $this->CrawlerDetect = new CrawlerDetect();
-    }
+	public function setUp()
+	{
+		$this->CrawlerDetect = new CrawlerDetect();
+	}
 
-    public function testBots()
-    {
-        $lines = file(__DIR__.'/crawlers.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
+	public function testBots()
+	{
+		$lines = file(__DIR__.'/crawlers.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
 
-        foreach ($lines as $line) {
-            $test = $this->CrawlerDetect->isCrawler($line);
-            $this->assertEquals($test, true, $line);
-        }
-    }
+		foreach ($lines as $line) {
+			$test = $this->CrawlerDetect->isCrawler($line);
+			$this->assertEquals($test, true, $line);
+		}
+	}
 
-    public function testDevices()
-    {
-        $lines = file(__DIR__.'/devices.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
+	public function testDevices()
+	{
+		$lines = file(__DIR__.'/devices.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
 
-        foreach ($lines as $line) {
-            $test = $this->CrawlerDetect->isCrawler($line);
-            $this->assertEquals($test, false, $line);
-        }
-    }
+		foreach ($lines as $line) {
+			$test = $this->CrawlerDetect->isCrawler($line);
+			$this->assertEquals($test, false, $line);
+		}
+	}
 
-    public function testReturnsCorrectMatchedBotName()
-    {
-        $test = $this->CrawlerDetect->isCrawler('Mozilla/5.0 (iPhone; CPU iPhone OS 7_1 like Mac OS X) AppleWebKit (KHTML, like Gecko) Mobile (compatible; Yahoo Ad monitoring; https://help.yahoo.com/kb/yahoo-ad-monitoring-SLN24857.html)');
+	public function testReturnsCorrectMatchedBotName()
+	{
+		$test = $this->CrawlerDetect->isCrawler('Mozilla/5.0 (iPhone; CPU iPhone OS 7_1 like Mac OS X) AppleWebKit (KHTML, like Gecko) Mobile (compatible; Yahoo Ad monitoring; https://help.yahoo.com/kb/yahoo-ad-monitoring-SLN24857.html)');
 
-        $matches = $this->CrawlerDetect->getMatches();
+		$matches = $this->CrawlerDetect->getMatches();
 
-        $this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
-    }
+		$this->assertEquals($this->CrawlerDetect->getMatches(), 'Yahoo Ad monitoring', $matches);
+	}
 
-    public function testForRegexCollision()
-    {
-        $crawlers = new Crawlers();
+	public function testForRegexCollision()
+	{
+		$crawlers = new Crawlers();
 
-        foreach ($crawlers->getAll() as $key1 => $regex) {
-            foreach ($crawlers->getAll() as $key2 => $compare) {
-                // Dont check this regex against itself
-                if ($key1 != $key2) {
-                    preg_match('/'.$regex.'/i', stripslashes($compare), $matches);
+		foreach ($crawlers->getAll() as $key1 => $regex) {
+			foreach ($crawlers->getAll() as $key2 => $compare) {
+				// Dont check this regex against itself
+				if ($key1 != $key2) {
+					preg_match('/'.$regex.'/i', stripslashes($compare), $matches);
 
-                    $this->assertEmpty($matches, $regex.' collided with '.$compare);
-                }
-            }
-        }
-    }
+					$this->assertEmpty($matches, $regex.' collided with '.$compare);
+				}
+			}
+		}
+	}
 }

src/Fixtures/AbstractProvider.php

Indentation +5 added lines, -5 removed lines

@@ -13,10 +13,10 @@
 
 abstract class AbstractProvider
 {
-    protected $data;
+	protected $data;
 
-    public function getAll()
-    {
-        return $this->data;
-    }
+	public function getAll()
+	{
+		return $this->data;
+	}
 }