CrawlerDetect::setUserAgent() - Code Metrics - Inspection of "Performance improvements" - JayBizzle/Crawler-Detect - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#171)

by Mark

created 2017-02-02 20:54 UTC

CrawlerDetect::setUserAgent() B

↳ Parent: CrawlerDetect

Complexity

Conditions	5
Paths	7

Size

Total Lines	15
Code Lines	9

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	15
rs	8.8571
c	0
b	0
f	0
cc	5
eloc	9
nc	7
nop	1

<?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;
use Jaybizzle\CrawlerDetect\Fixtures\Headers;

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;

    /**
     * Headers object.
     *
     * @var \Jaybizzle\CrawlerDetect\Fixtures\Headers
     */
    protected $uaHttpHeaders;

    /**
     * The compiled regex string.
     *
     * @var string
     */
    protected $compiledRegex;

    /**
     * The compiled exclusions regex string.
     *
     * @var string
     */
    protected $compiledExclusions;

    /**
     * Class constructor.
     */
    public function __construct(array $headers = null, $userAgent = null)
    {
        $this->crawlers = new Crawlers();
        $this->exclusions = new Exclusions();
        $this->uaHttpHeaders = new Headers();

        $this->compiledRegex = $this->compileRegex($this->crawlers->getAll());
        $this->compiledExclusions = $this->compileRegex($this->exclusions->getAll());

        $this->setHttpHeaders($headers);
        $this->setUserAgent($userAgent);
    }

    /**
     * Compile the regex patterns into one regex string.
     *
     * @param array
     * @return string
     */
    public function compileRegex($patterns)
    {
        return '('.implode('|', $patterns).')';
    }

    /**
     * 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 => $value) {
            if (strpos($key, 'HTTP_') === 0) {
                $this->httpHeaders[$key] = $value;
            }
        }
    }

    /**
     * Return user agent headers.
     *
     * @return array
     */
    public function getUaHttpHeaders()
    {
        return $this->uaHttpHeaders->getAll();
    }

    /**
     * Set the user agent.
     *
     * @param string $userAgent
     */
    public function setUserAgent($userAgent = null)
    {
        if (false === empty($userAgent)) {
            $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].' ';
                }
            }

            $this->userAgent = (! empty($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;
}
        }
    }

    /**
     * Check user agent string against the regex.
     *
     * @param string $userAgent
     *
     * @return bool
     */
    public function isCrawler($userAgent = null)
    {
        $agent = $userAgent ?: $this->userAgent;

        $agent = preg_replace('/'.$this->compiledExclusions.'/i', '', $agent);

        if (strlen(trim($agent)) == 0) {
            return false;
        }

        $result = preg_match('/'.$this->compiledRegex.'/i', trim($agent), $matches);

        if ($matches) {

            $this->matches = $matches;
        }

        return (bool) $result;
    }

    /**
     * Return the matches.
     *
     * @return string|null
     */
    public function getMatches()
    {
        return isset($this->matches[0]) ? $this->matches[0] : null;
    }
}


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			use Jaybizzle\CrawlerDetect\Fixtures\Headers;
17
18			class CrawlerDetect
19			{
20			/**
21			* The user agent.
22			*
23			* @var null
24			*/
25			protected $userAgent = null;
26
27			/**
28			* Headers that contain a user agent.
29			*
30			* @var array
31			*/
32			protected $httpHeaders = array();
33
34			/**
35			* Store regex matches.
36			*
37			* @var array
38			*/
39			protected $matches = array();
40
41			/**
42			* Crawlers object.
43			*
44			* @var \Jaybizzle\CrawlerDetect\Fixtures\Crawlers
45			*/
46			protected $crawlers;
47
48			/**
49			* Exclusions object.
50			*
51			* @var \Jaybizzle\CrawlerDetect\Fixtures\Exclusions
52			*/
53			protected $exclusions;
54
55			/**
56			* Headers object.
57			*
58			* @var \Jaybizzle\CrawlerDetect\Fixtures\Headers
59			*/
60			protected $uaHttpHeaders;
61
62			/**
63			* The compiled regex string.
64			*
65			* @var string
66			*/
67			protected $compiledRegex;
68
69			/**
70			* The compiled exclusions regex string.
71			*
72			* @var string
73			*/
74			protected $compiledExclusions;
75
76			/**
77			* Class constructor.
78			*/
79			public function __construct(array $headers = null, $userAgent = null)
80			{
81			$this->crawlers = new Crawlers();
82			$this->exclusions = new Exclusions();
83			$this->uaHttpHeaders = new Headers();
84
85			$this->compiledRegex = $this->compileRegex($this->crawlers->getAll());
86			$this->compiledExclusions = $this->compileRegex($this->exclusions->getAll());
87
88			$this->setHttpHeaders($headers);
89			$this->setUserAgent($userAgent);
90			}
91
92			/**
93			* Compile the regex patterns into one regex string.
94			*
95			* @param array
96			* @return string
97			*/
98			public function compileRegex($patterns)
99			{
100			return '('.implode('\|', $patterns).')';
101			}
102
103			/**
104			* Set HTTP headers.
105			*
106			* @param array $httpHeaders
107			*/
108			public function setHttpHeaders($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...
109			{
110			// Use global _SERVER if $httpHeaders aren't defined.
111			if (! is_array($httpHeaders) \|\| ! count($httpHeaders)) {
112			$httpHeaders = $_SERVER;
113			}
114
115			// Clear existing headers.
116			$this->httpHeaders = array();
117
118			// Only save HTTP headers. In PHP land, that means
119			// only _SERVER vars that start with HTTP_.
120			foreach ($httpHeaders as $key => $value) {
121			if (strpos($key, 'HTTP_') === 0) {
122			$this->httpHeaders[$key] = $value;
123			}
124			}
125			}
126
127			/**
128			* Return user agent headers.
129			*
130			* @return array
131			*/
132			public function getUaHttpHeaders()
133			{
134			return $this->uaHttpHeaders->getAll();
135			}
136
137			/**
138			* Set the user agent.
139			*
140			* @param string $userAgent
141			*/
142			public function setUserAgent($userAgent = null)
143			{
144			if (false === empty($userAgent)) {
145			$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...
146			} else {
147			$this->userAgent = null;
148			foreach ($this->getUaHttpHeaders() as $altHeader) {
149			if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
150			$this->userAgent .= $this->httpHeaders[$altHeader].' ';
151			}
152			}
153
154			$this->userAgent = (! empty($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...
155			}
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 = $userAgent ?: $this->userAgent;
168
169			$agent = preg_replace('/'.$this->compiledExclusions.'/i', '', $agent);
170
171			if (strlen(trim($agent)) == 0) {
172			return false;
173			}
174
175			$result = preg_match('/'.$this->compiledRegex.'/i', trim($agent), $matches);
176
177			if ($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) $result;
182			}
183
184			/**
185			* Return the matches.
186			*
187			* @return string\|null
188			*/
189			public function getMatches()
190			{
191			return isset($this->matches[0]) ? $this->matches[0] : null;
192			}
193			}
194

JayBizzle / Crawler-Detect

Pull Request — master (#171)

CrawlerDetect::setUserAgent() B

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like