Completed
Push — master ( 55090d...5ff059 )
by Mark
02:02
created

CrawlerDetect::compileRegex()   A

Complexity

Conditions 1
Paths 1

Size

Total Lines 4
Code Lines 2

Duplication

Lines 0
Ratio 0 %

Importance

Changes 0
Metric Value
dl 0
loc 4
rs 10
c 0
b 0
f 0
cc 1
eloc 2
nc 1
nop 1
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
     * 
97
     * @return string
98
     */
99
    public function compileRegex($patterns)
100
    {
101
        return '('.implode('|', $patterns).')';
102
    }
103
104
    /**
105
     * Set HTTP headers.
106
     *
107
     * @param array $httpHeaders
108
     */
109
    public function setHttpHeaders($httpHeaders = null)
0 ignored issues
show
Coding Style introduced by Mark Beech
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...
110
    {
111
        // Use global _SERVER if $httpHeaders aren't defined.
112
        if (! is_array($httpHeaders) || ! count($httpHeaders)) {
113
            $httpHeaders = $_SERVER;
114
        }
115
116
        // Clear existing headers.
117
        $this->httpHeaders = array();
118
119
        // Only save HTTP headers. In PHP land, that means
120
        // only _SERVER vars that start with HTTP_.
121
        foreach ($httpHeaders as $key => $value) {
122
            if (strpos($key, 'HTTP_') === 0) {
123
                $this->httpHeaders[$key] = $value;
124
            }
125
        }
126
    }
127
128
    /**
129
     * Return user agent headers.
130
     *
131
     * @return array
132
     */
133
    public function getUaHttpHeaders()
134
    {
135
        return $this->uaHttpHeaders->getAll();
136
    }
137
138
    /**
139
     * Set the user agent.
140
     *
141
     * @param string $userAgent
142
     */
143
    public function setUserAgent($userAgent = null)
144
    {
145
        if (false === empty($userAgent)) {
146
            $this->userAgent = $userAgent;
0 ignored issues
show
Documentation Bug introduced by Mark Beech
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...
147
        } else {
148
            $this->userAgent = null;
149
            foreach ($this->getUaHttpHeaders() as $altHeader) {
150
                if (false === empty($this->httpHeaders[$altHeader])) { // @todo: should use getHttpHeader(), but it would be slow.
151
                    $this->userAgent .= $this->httpHeaders[$altHeader].' ';
152
                }
153
            }
154
155
            $this->userAgent = (! empty($this->userAgent) ? trim($this->userAgent) : null);
0 ignored issues
show
Documentation Bug introduced by Mark Beech
It seems like !empty($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...
156
        }
157
    }
158
159
    /**
160
     * Check user agent string against the regex.
161
     *
162
     * @param string $userAgent
163
     *
164
     * @return bool
165
     */
166
    public function isCrawler($userAgent = null)
167
    {
168
        $agent = $userAgent ?: $this->userAgent;
169
170
        $agent = preg_replace('/'.$this->compiledExclusions.'/i', '', $agent);
171
172
        if (strlen(trim($agent)) == 0) {
173
            return false;
174
        }
175
176
        $result = preg_match('/'.$this->compiledRegex.'/i', trim($agent), $matches);
177
178
        if ($matches) {
0 ignored issues
show
Bug Best Practice introduced by Mark Beech
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...
179
            $this->matches = $matches;
180
        }
181
182
        return (bool) $result;
183
    }
184
185
    /**
186
     * Return the matches.
187
     *
188
     * @return string|null
189
     */
190
    public function getMatches()
191
    {
192
        return isset($this->matches[0]) ? $this->matches[0] : null;
193
    }
194
}
195