UriParser::extractUriParts() - Code Metrics - Inspection of "Improve URI services" - thephpleague/uri - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Pull Request — master (#30)

by ignace nyamagana

created 2016-01-18 08:45 UTC

UriParser::extractUriParts() A

↳ Parent: UriParser

Complexity

Conditions	2
Paths	2

Size

Total Lines	15
Code Lines	9

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	3
CRAP Score	2

Importance

Changes	1
Bugs	0	Features	0

Metric	Value
c	1
b	0
f	0
dl	0
loc	15
ccs	3
cts	3
cp	1
rs	9.4285
cc	2
eloc	9
nc	2
nop	1
crap	2

<?php
/**
 * League.Url (http://url.thephpleague.com)
 *
 * @package   League.url
 * @author    Ignace Nyamagana Butera <[email protected]>
 * @copyright 2013-2015 Ignace Nyamagana Butera
 * @license   https://github.com/thephpleague/uri/blob/master/LICENSE (MIT License)
 * @version   4.0.0
 * @link      https://github.com/thephpleague/uri/
 */
namespace League\Uri;

use InvalidArgumentException;
use League\Uri\Components\HostIpTrait;
use League\Uri\Components\HostnameTrait;
use League\Uri\Schemes\Generic\PathFormatterTrait;
use League\Uri\Types\ValidatorTrait;

/**
 * a class to parse a URI string according to RFC3986
 *
 * @package League.uri
 * @author  Ignace Nyamagana Butera <[email protected]>
 * @since   4.0.0
 */
class UriParser
{
    use HostIpTrait;

    use HostnameTrait;

    use PathFormatterTrait;

    use ValidatorTrait;

    const REGEXP_URI = ',^((?<scheme>[^:/?\#]+):)?
        (?<authority>//([^/?\#]*))?
        (?<path>[^?\#]*)
        (?<query>\?([^\#]*))?
        (?<fragment>\#(.*))?,x';

    const REGEXP_AUTHORITY = ',^(?<userinfo>(?<ucontent>.*?)@)?(?<hostname>.*?)?$,';

    const REGEXP_REVERSE_HOSTNAME = ',^((?<port>[^(\[\])]*):)?(?<host>.*)?$,';

    const REGEXP_SCHEME = ',^([a-z]([-a-z0-9+.]+)?)?$,i';

    const REGEXP_INVALID_USER = ',[/?#@:],';

    const REGEXP_INVALID_PASS = ',[/?#@],';

    /**
     * default components hash table
     *
     * @var array
     */
    protected $components = [
        'scheme' => null, 'user' => null, 'pass' => null, 'host' => null,
        'port' => null, 'path' => null, 'query' => null, 'fragment' => null,
    ];

    /**
     * Parse a string as an URI according to the regexp form rfc3986
     *
     * @param string $uri The URI to parse
     *
     * @return array the array is similar to PHP's parse_url hash response
     */
    public function parse($uri)
    {
        $parts = $this->extractUriParts($uri);

        return $this->normalizeUriHash(array_merge(
            $this->parseAuthority($parts['authority']),
            [
                'scheme' => empty($parts['scheme']) ? null : $parts['scheme'],
                'path' => $parts['path'],
                'query' => empty($parts['query']) ? null : mb_substr($parts['query'], 1, null, 'UTF-8'),
                'fragment' => empty($parts['fragment']) ? null : mb_substr($parts['fragment'], 1, null, 'UTF-8'),
            ]
        ));
    }

    /**
     * Parse a string as an URI according to the regexp form rfc3986
     *
     * @param string $uri The URI to parse
     *
     * @return array the array is similar to PHP's parse_url hash response
     */
    public function __invoke($uri)
    {
        return $this->parse($uri);
    }

    /**
     * Extract URI parts
     *
     * @see http://tools.ietf.org/html/rfc3986#appendix-B
     *
     * @param string $uri The URI to split
     *
     * @return string[]
     */
    protected function extractUriParts($uri)
    {
        preg_match(self::REGEXP_URI, $uri, $parts);
        $parts += ['query' => '', 'fragment' => ''];

        if (preg_match(self::REGEXP_SCHEME, $parts['scheme'])) {
            return $parts;
        }

        $parts['path'] = $parts['scheme'].':'.$parts['authority'].$parts['path'];
        $parts['scheme'] = '';
        $parts['authority'] = '';

        return $parts;
    }

    /**
     * Normalize URI components hash
     *
     * @param array $components a hash representation of the URI components
     *                          similar to PHP parse_url function result
     *
     * @return array
     */
    public function normalizeUriHash(array $components)
    {
        return array_replace($this->components, $components);
    }

    /**
     * Parse a URI authority part into its components
     *
     * @param string $authority
     *
     * @return array
     */
    protected function parseAuthority($authority)
    {
        $res = ['user' => null, 'pass' => null, 'host' => null, 'port' => null];
        if (empty($authority)) {
            return $res;
        }

        $content = mb_substr($authority, 2, null, 'UTF-8');
        if (empty($content)) {
            return ['host' => ''] + $res;
        }

        preg_match(self::REGEXP_AUTHORITY, $content, $auth);
        if (!empty($auth['userinfo'])) {
            $userinfo = explode(':', $auth['ucontent'], 2);
            $res = ['user' => array_shift($userinfo), 'pass' => array_shift($userinfo)] + $res;
        }

        return $this->parseHostname($auth['hostname']) + $res;
    }

    /**
     * Parse the hostname into its components Host and Port
     *
     * No validation is done on the port or host component found
     *
     * @param string $hostname
     *
     * @return array
     */
    protected function parseHostname($hostname)
    {
        $components = ['host' => null, 'port' => null];
        $hostname = strrev($hostname);
        if (preg_match(self::REGEXP_REVERSE_HOSTNAME, $hostname, $res)) {
            $components['host'] = strrev($res['host']);
            $components['port'] = strrev($res['port']);
        }
        $components['host'] = $this->filterHost($components['host']);
        $components['port'] = $this->validatePort($components['port']);

        return $components;
    }

    /**
     * validate the host component
     *
     * @param string $host
     *
     * @return int|null
     */
    protected function filterHost($host)
    {
        if (empty($this->validateIpHost($host))) {
            $this->validateStringHost($host);
        }

        return $host;
    }

    /**
     * @inheritdoc
     */
    protected function setIsAbsolute($host)
    {
        return ('.' == mb_substr($host, -1, 1, 'UTF-8')) ? mb_substr($host, 0, -1, 'UTF-8') : $host;
    }

    /**
     * @inheritdoc
     */
    protected function assertLabelsCount(array $labels)
    {
        if (127 <= count($labels)) {
            throw new InvalidArgumentException('Invalid Host, verify labels count');
        }
    }

    /**
     * Format the user info
     *
     * @param string $user
     * @param string $pass
     *
     * @return string
     */
    public function buildUserInfo($user, $pass)
    {
        $userinfo = $this->filterUser($user);
        if (null === $userinfo) {
            return '';
        }
        $pass = $this->filterPass($pass);
        if (null !== $pass) {
            $userinfo .= ':'.$pass;
        }
        return $userinfo.'@';
    }

    /**
     * Filter and format the user for URI string representation
     *
     * @param null|string $user
     *
     * @throws InvalidArgumentException If the user is invalid
     *
     * @return null|string
     */
    protected function filterUser($user)
    {
        if (!preg_match(self::REGEXP_INVALID_USER, $user)) {
            return $user;
        }

        throw new InvalidArgumentException('The user component contains invalid characters');
    }

    /**
     * Filter and format the pass for URI string representation
     *
     * @param null|string $pass
     *
     * @throws InvalidArgumentException If the pass is invalid
     *
     * @return null|string
     */
    protected function filterPass($pass)
    {
        if (!preg_match(self::REGEXP_INVALID_PASS, $pass)) {
            return $pass;
        }

        throw new InvalidArgumentException('The user component contains invalid characters');
    }
}


1		<?php
2		/**
3		* League.Url (http://url.thephpleague.com)
4		*
5		* @package League.url
6		* @author Ignace Nyamagana Butera <[email protected]>
7		* @copyright 2013-2015 Ignace Nyamagana Butera
8		* @license https://github.com/thephpleague/uri/blob/master/LICENSE (MIT License)
9		* @version 4.0.0
10		* @link https://github.com/thephpleague/uri/
11		*/
12		namespace League\Uri;
13
14		use InvalidArgumentException;
15		use League\Uri\Components\HostIpTrait;
16		use League\Uri\Components\HostnameTrait;
17		use League\Uri\Schemes\Generic\PathFormatterTrait;
18		use League\Uri\Types\ValidatorTrait;
19
20		/**
21		* a class to parse a URI string according to RFC3986
22		*
23		* @package League.uri
24		* @author Ignace Nyamagana Butera <[email protected]>
25		* @since 4.0.0
26		*/
27		class UriParser
28		{
29		use HostIpTrait;
30
31		use HostnameTrait;
32
33		use PathFormatterTrait;
34
35		use ValidatorTrait;
36
37		const REGEXP_URI = ',^((?<scheme>[^:/?\#]+):)?
38		(?<authority>//([^/?\#]*))?
39		(?<path>[^?\#]*)
40		(?<query>\?([^\#]*))?
41		(?<fragment>\#(.*))?,x';
42
43		const REGEXP_AUTHORITY = ',^(?<userinfo>(?<ucontent>.?)@)?(?<hostname>.?)?$,';
44
45		const REGEXP_REVERSE_HOSTNAME = ',^((?<port>[^(\[\])]):)?(?<host>.)?$,';
46
47		const REGEXP_SCHEME = ',^([a-z]([-a-z0-9+.]+)?)?$,i';
48
49		const REGEXP_INVALID_USER = ',[/?#@:],';
50
51		const REGEXP_INVALID_PASS = ',[/?#@],';
52
53		/**
54		* default components hash table
55		*
56		* @var array
57		*/
58		protected $components = [
59		'scheme' => null, 'user' => null, 'pass' => null, 'host' => null,
60		'port' => null, 'path' => null, 'query' => null, 'fragment' => null,
61		];
62
63		/**
64		* Parse a string as an URI according to the regexp form rfc3986
65		*
66		* @param string $uri The URI to parse
67		*
68		* @return array the array is similar to PHP's parse_url hash response
69		*/
70	440	public function parse($uri)
71		{
72	440	$parts = $this->extractUriParts($uri);
73
74	440	return $this->normalizeUriHash(array_merge(
75	440	$this->parseAuthority($parts['authority']),
76		[
77	432	'scheme' => empty($parts['scheme']) ? null : $parts['scheme'],
78	432	'path' => $parts['path'],
79	432	'query' => empty($parts['query']) ? null : mb_substr($parts['query'], 1, null, 'UTF-8'),
80	432	'fragment' => empty($parts['fragment']) ? null : mb_substr($parts['fragment'], 1, null, 'UTF-8'),
81		]
82	432	));
83		}
84
85		/**
86		* Parse a string as an URI according to the regexp form rfc3986
87		*
88		* @param string $uri The URI to parse
89		*
90		* @return array the array is similar to PHP's parse_url hash response
91		*/
92		public function __invoke($uri)
93		{
94	440	return $this->parse($uri);
95		}
96	440
97	440	/**
98		* Extract URI parts
99	440	*
100	436	* @see http://tools.ietf.org/html/rfc3986#appendix-B
101		*
102		* @param string $uri The URI to split
103	4	*
104	4	* @return string[]
105	4	*/
106		protected function extractUriParts($uri)
107	4	{
108		preg_match(self::REGEXP_URI, $uri, $parts);
109		$parts += ['query' => '', 'fragment' => ''];
110
111		if (preg_match(self::REGEXP_SCHEME, $parts['scheme'])) {
112		return $parts;
113		}
114
115		$parts['path'] = $parts['scheme'].':'.$parts['authority'].$parts['path'];
116		$parts['scheme'] = '';
117		$parts['authority'] = '';
118	434
119		return $parts;
120	434	}
121
122		/**
123		* Normalize URI components hash
124		*
125		* @param array $components a hash representation of the URI components
126		* similar to PHP parse_url function result
127		*
128		* @return array
129		*/
130	440	public function normalizeUriHash(array $components)
131		{
132	440	return array_replace($this->components, $components);
133	440	}
134	154
135		/**
136		* Parse a URI authority part into its components
137	352	*
138	352	* @param string $authority
139	2	*
140		* @return array
141		*/
142	350	protected function parseAuthority($authority)
143	350	{
144	108	$res = ['user' => null, 'pass' => null, 'host' => null, 'port' => null];
145	108	if (empty($authority)) {
146	108	return $res;
147		}
148	350
149		$content = mb_substr($authority, 2, null, 'UTF-8');
150		if (empty($content)) {
151		return ['host' => ''] + $res;
152		}
153
154		preg_match(self::REGEXP_AUTHORITY, $content, $auth);
155		if (!empty($auth['userinfo'])) {
156		$userinfo = explode(':', $auth['ucontent'], 2);
157		$res = ['user' => array_shift($userinfo), 'pass' => array_shift($userinfo)] + $res;
158		}
159
160	350	return $this->parseHostname($auth['hostname']) + $res;
161		}
162	350
163	350	/**
164	350	* Parse the hostname into its components Host and Port
165	350	*
166	350	* No validation is done on the port or host component found
167	350	*
168	350	* @param string $hostname
169	344	*
170		* @return array
171	342	*/
172		protected function parseHostname($hostname)
173		{
174		$components = ['host' => null, 'port' => null];
175		$hostname = strrev($hostname);
176		if (preg_match(self::REGEXP_REVERSE_HOSTNAME, $hostname, $res)) {
177		$components['host'] = strrev($res['host']);
178		$components['port'] = strrev($res['port']);
179		}
180		$components['host'] = $this->filterHost($components['host']);
181	350	$components['port'] = $this->validatePort($components['port']);
182
183	350	return $components;
184	340	}
185	334
186		/**
187	344	* validate the host component
188		*
189		* @param string $host
190		*
191		* @return int\|null
192		*/
193	340	protected function filterHost($host)
194		{
195	340	if (empty($this->validateIpHost($host))) {
196		$this->validateStringHost($host);
197		}
198
199		return $host;
200		}
201	340
202		/**
203	340	* @inheritdoc
204	2	*/
205		protected function setIsAbsolute($host)
206	338	{
207		return ('.' == mb_substr($host, -1, 1, 'UTF-8')) ? mb_substr($host, 0, -1, 'UTF-8') : $host;
208		}
209
210		/**
211		* @inheritdoc
212		*/
213		protected function assertLabelsCount(array $labels)
214		{
215		if (127 <= count($labels)) {
216	46	throw new InvalidArgumentException('Invalid Host, verify labels count');
217		}
218	46	}
219	44
220	4	/**
221		* Format the user info
222	40	*
223	38	* @param string $user
224	36	* @param string $pass
225	36	*
226	38	* @return string
227		*/
228		public function buildUserInfo($user, $pass)
229		{
230		$userinfo = $this->filterUser($user);
231		if (null === $userinfo) {
232		return '';
233		}
234		$pass = $this->filterPass($pass);
235		if (null !== $pass) {
236		$userinfo .= ':'.$pass;
237		}
238	46	return $userinfo.'@';
239		}
240	46
241	44	/**
242		* Filter and format the user for URI string representation
243		*
244	2	* @param null\|string $user
245		*
246		* @throws InvalidArgumentException If the user is invalid
247		*
248		* @return null\|string
249		*/
250		protected function filterUser($user)
251		{
252		if (!preg_match(self::REGEXP_INVALID_USER, $user)) {
253		return $user;
254		}
255
256	40	throw new InvalidArgumentException('The user component contains invalid characters');
257		}
258	40
259	38	/**
260		* Filter and format the pass for URI string representation
261		*
262	2	* @param null\|string $pass
263		*
264		* @throws InvalidArgumentException If the pass is invalid
265		*
266		* @return null\|string
267		*/
268		protected function filterPass($pass)
269		{
270		if (!preg_match(self::REGEXP_INVALID_PASS, $pass)) {
271		return $pass;
272		}
273
274		throw new InvalidArgumentException('The user component contains invalid characters');
275		}
276		}
277

thephpleague / uri

Pull Request — master (#30)

UriParser::extractUriParts() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like