wordpress-seo / vendor_prefixed / guzzlehttp / psr7 / src / UriNormalizer.php

UriNormalizer.php in Yoast SEO – Advanced SEO with real-time guidance and built-in AI 18.2, at vendor_prefixed/guzzlehttp/psr7/src/UriNormalizer.php

182 lines 8.3 KB

Raw Download Zip

1	<?php
2
3	namespace YoastSEO_Vendor\GuzzleHttp\Psr7;
4
5	use YoastSEO_Vendor\Psr\Http\Message\UriInterface;
6	/**
7	* Provides methods to normalize and compare URIs.
8	*
9	* @author Tobias Schultze
10	*
11	* @link https://tools.ietf.org/html/rfc3986#section-6
12	*/
13	final class UriNormalizer
14	{
15	/**
16	* Default normalizations which only include the ones that preserve semantics.
17	*
18	* self::CAPITALIZE_PERCENT_ENCODING \| self::DECODE_UNRESERVED_CHARACTERS \| self::CONVERT_EMPTY_PATH \|
19	* self::REMOVE_DEFAULT_HOST \| self::REMOVE_DEFAULT_PORT \| self::REMOVE_DOT_SEGMENTS
20	*/
21	const PRESERVING_NORMALIZATIONS = 63;
22	/**
23	* All letters within a percent-encoding triplet (e.g., "%3A") are case-insensitive, and should be capitalized.
24	*
25	* Example: http://example.org/a%c2%b1b → http://example.org/a%C2%B1b
26	*/
27	const CAPITALIZE_PERCENT_ENCODING = 1;
28	/**
29	* Decodes percent-encoded octets of unreserved characters.
30	*
31	* For consistency, percent-encoded octets in the ranges of ALPHA (%41–%5A and %61–%7A), DIGIT (%30–%39),
32	* hyphen (%2D), period (%2E), underscore (%5F), or tilde (%7E) should not be created by URI producers and,
33	* when found in a URI, should be decoded to their corresponding unreserved characters by URI normalizers.
34	*
35	* Example: http://example.org/%7Eusern%61me/ → http://example.org/~username/
36	*/
37	const DECODE_UNRESERVED_CHARACTERS = 2;
38	/**
39	* Converts the empty path to "/" for http and https URIs.
40	*
41	* Example: http://example.org → http://example.org/
42	*/
43	const CONVERT_EMPTY_PATH = 4;
44	/**
45	* Removes the default host of the given URI scheme from the URI.
46	*
47	* Only the "file" scheme defines the default host "localhost".
48	* All of `file:/myfile`, `file:///myfile`, and `file://localhost/myfile`
49	* are equivalent according to RFC 3986. The first format is not accepted
50	* by PHPs stream functions and thus already normalized implicitly to the
51	* second format in the Uri class. See `GuzzleHttp\Psr7\Uri::composeComponents`.
52	*
53	* Example: file://localhost/myfile → file:///myfile
54	*/
55	const REMOVE_DEFAULT_HOST = 8;
56	/**
57	* Removes the default port of the given URI scheme from the URI.
58	*
59	* Example: http://example.org:80/ → http://example.org/
60	*/
61	const REMOVE_DEFAULT_PORT = 16;
62	/**
63	* Removes unnecessary dot-segments.
64	*
65	* Dot-segments in relative-path references are not removed as it would
66	* change the semantics of the URI reference.
67	*
68	* Example: http://example.org/../a/b/../c/./d.html → http://example.org/a/c/d.html
69	*/
70	const REMOVE_DOT_SEGMENTS = 32;
71	/**
72	* Paths which include two or more adjacent slashes are converted to one.
73	*
74	* Webservers usually ignore duplicate slashes and treat those URIs equivalent.
75	* But in theory those URIs do not need to be equivalent. So this normalization
76	* may change the semantics. Encoded slashes (%2F) are not removed.
77	*
78	* Example: http://example.org//foo///bar.html → http://example.org/foo/bar.html
79	*/
80	const REMOVE_DUPLICATE_SLASHES = 64;
81	/**
82	* Sort query parameters with their values in alphabetical order.
83	*
84	* However, the order of parameters in a URI may be significant (this is not defined by the standard).
85	* So this normalization is not safe and may change the semantics of the URI.
86	*
87	* Example: ?lang=en&article=fred → ?article=fred&lang=en
88	*
89	* Note: The sorting is neither locale nor Unicode aware (the URI query does not get decoded at all) as the
90	* purpose is to be able to compare URIs in a reproducible way, not to have the params sorted perfectly.
91	*/
92	const SORT_QUERY_PARAMETERS = 128;
93	/**
94	* Returns a normalized URI.
95	*
96	* The scheme and host component are already normalized to lowercase per PSR-7 UriInterface.
97	* This methods adds additional normalizations that can be configured with the $flags parameter.
98	*
99	* PSR-7 UriInterface cannot distinguish between an empty component and a missing component as
100	* getQuery(), getFragment() etc. always return a string. This means the URIs "/?#" and "/" are
101	* treated equivalent which is not necessarily true according to RFC 3986. But that difference
102	* is highly uncommon in reality. So this potential normalization is implied in PSR-7 as well.
103	*
104	* @param UriInterface $uri The URI to normalize
105	* @param int $flags A bitmask of normalizations to apply, see constants
106	*
107	* @return UriInterface The normalized URI
108	*
109	* @link https://tools.ietf.org/html/rfc3986#section-6.2
110	*/
111	public static function normalize(\YoastSEO_Vendor\Psr\Http\Message\UriInterface $uri, $flags = self::PRESERVING_NORMALIZATIONS)
112	{
113	if ($flags & self::CAPITALIZE_PERCENT_ENCODING) {
114	$uri = self::capitalizePercentEncoding($uri);
115	}
116	if ($flags & self::DECODE_UNRESERVED_CHARACTERS) {
117	$uri = self::decodeUnreservedCharacters($uri);
118	}
119	if ($flags & self::CONVERT_EMPTY_PATH && $uri->getPath() === '' && ($uri->getScheme() === 'http' \|\| $uri->getScheme() === 'https')) {
120	$uri = $uri->withPath('/');
121	}
122	if ($flags & self::REMOVE_DEFAULT_HOST && $uri->getScheme() === 'file' && $uri->getHost() === 'localhost') {
123	$uri = $uri->withHost('');
124	}
125	if ($flags & self::REMOVE_DEFAULT_PORT && $uri->getPort() !== null && \YoastSEO_Vendor\GuzzleHttp\Psr7\Uri::isDefaultPort($uri)) {
126	$uri = $uri->withPort(null);
127	}
128	if ($flags & self::REMOVE_DOT_SEGMENTS && !\YoastSEO_Vendor\GuzzleHttp\Psr7\Uri::isRelativePathReference($uri)) {
129	$uri = $uri->withPath(\YoastSEO_Vendor\GuzzleHttp\Psr7\UriResolver::removeDotSegments($uri->getPath()));
130	}
131	if ($flags & self::REMOVE_DUPLICATE_SLASHES) {
132	$uri = $uri->withPath(\preg_replace('#//++#', '/', $uri->getPath()));
133	}
134	if ($flags & self::SORT_QUERY_PARAMETERS && $uri->getQuery() !== '') {
135	$queryKeyValues = \explode('&', $uri->getQuery());
136	\sort($queryKeyValues);
137	$uri = $uri->withQuery(\implode('&', $queryKeyValues));
138	}
139	return $uri;
140	}
141	/**
142	* Whether two URIs can be considered equivalent.
143	*
144	* Both URIs are normalized automatically before comparison with the given $normalizations bitmask. The method also
145	* accepts relative URI references and returns true when they are equivalent. This of course assumes they will be
146	* resolved against the same base URI. If this is not the case, determination of equivalence or difference of
147	* relative references does not mean anything.
148	*
149	* @param UriInterface $uri1 An URI to compare
150	* @param UriInterface $uri2 An URI to compare
151	* @param int $normalizations A bitmask of normalizations to apply, see constants
152	*
153	* @return bool
154	*
155	* @link https://tools.ietf.org/html/rfc3986#section-6.1
156	*/
157	public static function isEquivalent(\YoastSEO_Vendor\Psr\Http\Message\UriInterface $uri1, \YoastSEO_Vendor\Psr\Http\Message\UriInterface $uri2, $normalizations = self::PRESERVING_NORMALIZATIONS)
158	{
159	return (string) self::normalize($uri1, $normalizations) === (string) self::normalize($uri2, $normalizations);
160	}
161	private static function capitalizePercentEncoding(\YoastSEO_Vendor\Psr\Http\Message\UriInterface $uri)
162	{
163	$regex = '/(?:%[A-Fa-f0-9]{2})++/';
164	$callback = function (array $match) {
165	return \strtoupper($match[0]);
166	};
167	return $uri->withPath(\preg_replace_callback($regex, $callback, $uri->getPath()))->withQuery(\preg_replace_callback($regex, $callback, $uri->getQuery()));
168	}
169	private static function decodeUnreservedCharacters(\YoastSEO_Vendor\Psr\Http\Message\UriInterface $uri)
170	{
171	$regex = '/%(?:2D\|2E\|5F\|7E\|3[0-9]\|[46][1-9A-F]\|[57][0-9A])/i';
172	$callback = function (array $match) {
173	return \rawurldecode($match[0]);
174	};
175	return $uri->withPath(\preg_replace_callback($regex, $callback, $uri->getPath()))->withQuery(\preg_replace_callback($regex, $callback, $uri->getQuery()));
176	}
177	private function __construct()
178	{
179	// cannot be instantiated
180	}
181	}
182