CrawlerDetect::getExclusions() - Code Metrics - Inspection of "Separate fixtures into their own classes (#89)" - JayBizzle/Crawler-Detect - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 85d367...f929c4 )

by Mark

created 2016-04-24 21:17 UTC

CrawlerDetect::getExclusions() A

↳ Parent: CrawlerDetect

Complexity

Conditions	1
Paths	1

Size

Total Lines	4
Code Lines	2

Duplication

Lines	0
Ratio	0 %

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
c	1
b	0
f	0
dl	0
loc	4
rs	10
cc	1
eloc	2
nc	1
nop	0

<?php

/*
 * This file is part of Crawler Detect - the web crawler detection library.
 *
 * (c) Mark Beech <[email protected]>
 *
 * This source file is subject to the MIT license that is bundled
 * with this source code in the file LICENSE.
 */

namespace Jaybizzle\CrawlerDetect;

use Jaybizzle\CrawlerDetect\Fixtures\Crawlers;
use Jaybizzle\CrawlerDetect\Fixtures\Exclusions;

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)
// Bad
class Router
{
    public function generate($path)
    {
        return $_SERVER['HOST'].$path;
    }
}

// Better
class Router
{
    private $host;

    public function __construct($host)
    {
        $this->host = $host;
    }

    public function generate($path)
    {
        return $this->host.$path;
    }
}

class Controller
{
    public function myAction(Request $request)
    {
        // Instead of
        $page = isset($_GET['page']) ? intval($_GET['page']) : 1;

        // Better (assuming you use the Symfony2 request)
        $page = $request->query->get('page', 1);
    }
}
    {
        // 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);
class Id
{
    public $id;

    public function __construct($id)
    {
        $this->id = $id;
    }

}

class Account
{
    /** @var  Id $id */
    public $id;
}

$account_id = false;

if (starsAreRight()) {
    $account_id = new Id(42);
}

$account = new Account();
if ($account instanceof Id)
{
    $account->id = $account_id;
}
        }
    }

    /**
     * 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];
    }
}


1			<?php
2
3			/*
4			* This file is part of Crawler Detect - the web crawler detection library.
5			*
6			* (c) Mark Beech <[email protected]>
7			*
8			* This source file is subject to the MIT license that is bundled
9			* with this source code in the file LICENSE.
10			*/
11
12			namespace Jaybizzle\CrawlerDetect;
13
14			use Jaybizzle\CrawlerDetect\Fixtures\Crawlers;
15			use Jaybizzle\CrawlerDetect\Fixtures\Exclusions;
16
17			class CrawlerDetect
18			{
19			/**
20			* The user agent.
21			*
22			* @var null
23			*/
24			protected $userAgent = null;
25
26			/**
27			* Headers that contain a user agent.
28			*
29			* @var array
30			*/
31			protected $httpHeaders = array();
32
33			/**
34			* Store regex matches.
35			*
36			* @var array
37			*/
38			protected $matches = array();
39
40			/**
41			* Crawlers object.
42			*
43			* @var \Jaybizzle\CrawlerDetect\Fixtures\Crawlers
44			*/
45			protected $crawlers;
46
47			/**
48			* Exclusions object.
49			*
50			* @var \Jaybizzle\CrawlerDetect\Fixtures\Exclusions
51			*/
52			protected $exclusions;
53
54			/**
55			* All possible HTTP headers that represent the
56			* User-Agent string.
57			*
58			* @var array
59			*/
60			protected static $uaHttpHeaders = array(
61			// The default User-Agent string.
62			'HTTP_USER_AGENT',
63			// Header can occur on devices using Opera Mini.
64			'HTTP_X_OPERAMINI_PHONE_UA',
65			// Vodafone specific header: http://www.seoprinciple.com/mobile-web-community-still-angry-at-vodafone/24/
66			'HTTP_X_DEVICE_USER_AGENT',
67			'HTTP_X_ORIGINAL_USER_AGENT',
68			'HTTP_X_SKYFIRE_PHONE',
69			'HTTP_X_BOLT_PHONE_UA',
70			'HTTP_DEVICE_STOCK_UA',
71			'HTTP_X_UCBROWSER_DEVICE_UA',
72			);
73
74			/**
75			* Class constructor.
76			*/
77			public function __construct(array $headers = null, $userAgent = null)
78			{
79			$this->setHttpHeaders($headers);
80			$this->setUserAgent($userAgent);
81			$this->crawlers = new Crawlers();
82			$this->exclusions = new Exclusions();
83			}
84
85			/**
86			* Set HTTP headers.
87			*
88			* @param array $httpHeaders
89			*/
90			public function setHttpHeaders($httpHeaders = null)
			0 ignored issues – show Coding Style introduced 2015-11-25 13:32 UTC by Report Bug Copy Issue Report `setHttpHeaders` uses the super-global variable `$_SERVER` which is generally not recommended. Instead of super-globals, we recommend to explicitly inject the dependencies of your class. This makes your code less dependent on global state and it becomes generally more testable: // Bad class Router { public function generate($path) { return $_SERVER['HOST'].$path; } } // Better class Router { private $host; public function __construct($host) { $this->host = $host; } public function generate($path) { return $this->host.$path; } } class Controller { public function myAction(Request $request) { // Instead of $page = isset($_GET['page']) ? intval($_GET['page']) : 1; // Better (assuming you use the Symfony2 request) $page = $request->query->get('page', 1); } } Loading history...
91			{
92			// use global _SERVER if $httpHeaders aren't defined
93			if (!is_array($httpHeaders) \|\| !count($httpHeaders)) {
94			$httpHeaders = $_SERVER;
95			}
96			// clear existing headers
97			$this->httpHeaders = array();
98			// Only save HTTP headers. In PHP land, that means only _SERVER vars that
99			// start with HTTP_.
100			foreach ($httpHeaders as $key => $value) {
101			if (substr($key, 0, 5) === 'HTTP_') {
102			$this->httpHeaders[$key] = $value;
103			}
104			}
105			}
106
107			/**
108			* Return user agent headers.
109			*
110			* @return array
111			*/
112			public function getUaHttpHeaders()
113			{
114			return self::$uaHttpHeaders;
115			}
116
117			/**
118			* Set the user agent.
119			*
120			* @param string $userAgent
121			*/
122			public function setUserAgent($userAgent = null)
123			{
124			if (false === empty($userAgent)) {
125			return $this->userAgent = $userAgent;
			0 ignored issues – show Documentation Bug introduced 2015-12-10 20:57 UTC by Report Bug Copy Issue Report It seems like `$userAgent` of type `string` is incompatible with the declared type `null` of property `$userAgent`. Our type inference engine has found an assignment to a property that is incompatible with the declared type of that property. Either this assignment is in error or the assigned type should be added to the documentation/type hint for that property.. Loading history...
126			} else {
127			$this->userAgent = null;
128			foreach ($this->getUaHttpHeaders() as $altHeader) {
129			if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
130			$this->userAgent .= $this->httpHeaders[$altHeader].' ';
131			}
132			}
133
134			return $this->userAgent = (!empty($this->userAgent) ? trim($this->userAgent) : null);
			0 ignored issues – show Documentation Bug introduced 2015-12-10 20:57 UTC by Report Bug Copy Issue Report It seems like `!empty($this->userAgent)...this->userAgent) : null` can also be of type `string`. However, the property `$userAgent` is declared as type `null`. Maybe add an additional type check? Our type inference engine has found a suspicous assignment of a value to a property. This check raises an issue when a value that can be of a mixed type is assigned to a property that is type hinted more strictly. For example, imagine you have a variable `$accountId` that can either hold an Id object or false (if there is no account id yet). Your code now assigns that value to the `id` property of an instance of the `Account` class. This class holds a proper account, so the id value must no longer be false. Either this assignment is in error or a type check should be added for that assignment. class Id { public $id; public function __construct($id) { $this->id = $id; } } class Account { /** @var Id $id */ public $id; } $account_id = false; if (starsAreRight()) { $account_id = new Id(42); } $account = new Account(); if ($account instanceof Id) { $account->id = $account_id; } Loading history...
135			}
136			}
137
138			/**
139			* Build the user agent regex.
140			*
141			* @return string
142			*/
143			public function getRegex()
144			{
145			return '('.implode('\|', $this->crawlers->getAll()).')';
146			}
147
148			/**
149			* Build the replacement regex.
150			*
151			* @return string
152			*/
153			public function getExclusions()
154			{
155			return '('.implode('\|', $this->exclusions->getAll()).')';
156			}
157
158			/**
159			* Check user agent string against the regex.
160			*
161			* @param string $userAgent
162			*
163			* @return bool
164			*/
165			public function isCrawler($userAgent = null)
166			{
167			$agent = is_null($userAgent) ? $this->userAgent : $userAgent;
168
169			$agent = preg_replace('/'.$this->getExclusions().'/i', '', $agent);
170
171			if (trim($agent) === false) {
172			return false;
173			} else {
174			$result = preg_match('/'.$this->getRegex().'/i', trim($agent), $matches);
175			}
176
177			if ($matches) {
			0 ignored issues – show Bug Best Practice introduced 2015-11-25 13:32 UTC by Report Bug Copy Issue Report The expression `$matches` of type `string[]` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
178			$this->matches = $matches;
179			}
180
181			return (bool) $result;
182			}
183
184			/**
185			* Return the matches.
186			*
187			* @return string
188			*/
189			public function getMatches()
190			{
191			return $this->matches[0];
192			}
193			}
194

JayBizzle / Crawler-Detect

Push — master ( 85d367...f929c4 )

CrawlerDetect::getExclusions() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like