1
|
|
|
<?php |
2
|
|
|
/** |
3
|
|
|
* This file is part of PHP-Typography. |
4
|
|
|
* |
5
|
|
|
* Copyright 2014-2017 Peter Putzer. |
6
|
|
|
* Copyright 2009-2011 KINGdesk, LLC. |
7
|
|
|
* |
8
|
|
|
* This program is free software; you can redistribute it and/or modify |
9
|
|
|
* it under the terms of the GNU General Public License as published by |
10
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
11
|
|
|
* (at your option) any later version. |
12
|
|
|
* |
13
|
|
|
* This program is distributed in the hope that it will be useful, |
14
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
15
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
16
|
|
|
* GNU General Public License for more details. |
17
|
|
|
* |
18
|
|
|
* You should have received a copy of the GNU General Public License along |
19
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
20
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
21
|
|
|
* |
22
|
|
|
* *** |
23
|
|
|
* |
24
|
|
|
* @package mundschenk-at/php-typography |
25
|
|
|
* @license http://www.gnu.org/licenses/gpl-2.0.html |
26
|
|
|
*/ |
27
|
|
|
|
28
|
|
|
namespace PHP_Typography\Fixes\Token_Fixes; |
29
|
|
|
|
30
|
|
|
use PHP_Typography\Fixes\Token_Fix; |
31
|
|
|
use PHP_Typography\Hyphenator\Cache; |
32
|
|
|
use PHP_Typography\RE; |
33
|
|
|
use PHP_Typography\Settings; |
34
|
|
|
use PHP_Typography\Text_Parser; |
35
|
|
|
use PHP_Typography\Text_Parser\Token; |
36
|
|
|
use PHP_Typography\U; |
37
|
|
|
|
38
|
|
|
/** |
39
|
|
|
* Wraps URL parts zero-width spaces (if enabled). |
40
|
|
|
* |
41
|
|
|
* @author Peter Putzer <[email protected]> |
42
|
|
|
* |
43
|
|
|
* @since 5.0.0 |
44
|
|
|
*/ |
45
|
|
|
class Wrap_URLs_Fix extends Hyphenate_Fix { |
46
|
|
|
// Valid URL schemes. |
47
|
|
|
const URL_SCHEME = '(?:https?|ftps?|file|nfs|feed|itms|itpc)'; |
48
|
|
|
|
49
|
|
|
const WRAP_URLS_DOMAIN_PARTS = '#(\-|\.)#'; |
50
|
|
|
|
51
|
|
|
/** |
52
|
|
|
* The URL matching regular expression. |
53
|
|
|
* |
54
|
|
|
* @var string |
55
|
|
|
*/ |
56
|
|
|
protected $url_pattern; |
57
|
|
|
|
58
|
|
|
/** |
59
|
|
|
* Creates a new fix instance. |
60
|
|
|
* |
61
|
|
|
* @param Cache|null $cache Optional. Default null. |
62
|
|
|
* @param bool $feed_compatible Optional. Default false. |
63
|
|
|
*/ |
64
|
1 |
|
public function __construct( Cache $cache = null, $feed_compatible = false ) { |
65
|
1 |
|
parent::__construct( $cache, Token_Fix::OTHER, $feed_compatible ); |
66
|
|
|
|
67
|
|
|
// Combined URL pattern. |
68
|
1 |
|
$this->url_pattern = '`(?: |
69
|
|
|
\A |
70
|
1 |
|
(?<schema>' . self::URL_SCHEME . ':\/\/)? # Subpattern 1: contains _http://_ if it exists |
71
|
|
|
(?<domain> # Subpattern 2: contains subdomains.domain.tld |
72
|
|
|
(?: |
73
|
|
|
[a-z0-9] # first chr of (sub)domain can not be a hyphen |
74
|
|
|
[a-z0-9\-]{0,61} # middle chrs of (sub)domain may be a hyphen; |
75
|
|
|
# limit qty of middle chrs so total domain does not exceed 63 chrs |
76
|
|
|
[a-z0-9] # last chr of (sub)domain can not be a hyphen |
77
|
|
|
\. # dot separator |
78
|
|
|
)+ |
79
|
|
|
(?: |
80
|
1 |
|
' . RE::top_level_domains() . ' # validates top level domain |
81
|
|
|
) |
82
|
|
|
(?: # optional port numbers |
83
|
|
|
: |
84
|
|
|
(?: |
85
|
|
|
[1-5]?[0-9]{1,4} | 6[0-4][0-9]{3} | 65[0-4][0-9]{2} | 655[0-2][0-9] | 6553[0-5] |
86
|
|
|
) |
87
|
|
|
)? |
88
|
|
|
) |
89
|
|
|
(?<path> # Subpattern 3: contains path following domain |
90
|
|
|
(?: |
91
|
|
|
\/ # marks nested directory |
92
|
|
|
[a-z0-9\"\$\-_\.\+!\*\'\(\),;\?:@=&\#]+ # valid characters within directory structure |
93
|
|
|
)* |
94
|
|
|
[\/]? # trailing slash if any |
95
|
|
|
) |
96
|
|
|
\Z |
97
|
|
|
)`xi'; // required modifiers: x (multiline pattern) i (case insensitive). |
98
|
1 |
|
} |
99
|
|
|
|
100
|
|
|
/** |
101
|
|
|
* Apply the tweak to a given textnode. |
102
|
|
|
* |
103
|
|
|
* @param Token[] $tokens Required. |
104
|
|
|
* @param Settings $settings Required. |
105
|
|
|
* @param bool $is_title Optional. Default false. |
106
|
|
|
* @param \DOMText|null $textnode Optional. Default null. |
107
|
|
|
* |
108
|
|
|
* @return Token[] An array of tokens. |
109
|
|
|
*/ |
110
|
10 |
|
public function apply( array $tokens, Settings $settings, $is_title = false, \DOMText $textnode = null ) { |
111
|
10 |
|
if ( empty( $settings[ Settings::URL_WRAP ] ) || empty( $settings[ Settings::URL_MIN_AFTER_WRAP ] ) ) { |
112
|
5 |
|
return $tokens; |
113
|
|
|
} |
114
|
|
|
|
115
|
|
|
// Test for and parse urls. |
116
|
5 |
|
foreach ( $tokens as $token_index => $text_token ) { |
117
|
5 |
|
if ( \preg_match( $this->url_pattern, $text_token->value, $url_match ) ) { |
118
|
|
|
|
119
|
|
|
// $url_match['schema'] holds "http://". |
120
|
|
|
// $url_match['domain'] holds "subdomains.domain.tld". |
121
|
|
|
// $url_match['path'] holds the path after the domain. |
122
|
5 |
|
$http = ( $url_match['schema'] ) ? $url_match[1] . U::ZERO_WIDTH_SPACE : ''; |
123
|
|
|
|
124
|
5 |
|
$domain_parts = \preg_split( self::WRAP_URLS_DOMAIN_PARTS, $url_match['domain'], -1, PREG_SPLIT_DELIM_CAPTURE ); |
125
|
5 |
|
if ( false === $domain_parts ) { |
126
|
|
|
// Should not happen. |
127
|
|
|
continue; // @codeCoverageIgnore |
128
|
|
|
} |
129
|
|
|
|
130
|
|
|
// This is a hack, but it works. |
131
|
|
|
// First, we hyphenate each part, we need it formated like a group of words. |
132
|
5 |
|
$parsed_words_like = []; |
133
|
5 |
|
foreach ( $domain_parts as $key => $part ) { |
134
|
5 |
|
$parsed_words_like[ $key ] = new Text_Parser\Token( $part, Text_Parser\Token::OTHER ); |
135
|
|
|
} |
136
|
|
|
|
137
|
|
|
// Do the hyphenation. |
138
|
5 |
|
$parsed_words_like = $this->do_hyphenate( $parsed_words_like, $settings, U::ZERO_WIDTH_SPACE ); |
139
|
|
|
|
140
|
|
|
// Restore format. |
141
|
5 |
|
foreach ( $parsed_words_like as $key => $parsed_word ) { |
142
|
5 |
|
$value = $parsed_word->value; |
143
|
|
|
|
144
|
5 |
|
if ( $key > 0 && 1 === \strlen( $value ) ) { |
145
|
5 |
|
$domain_parts[ $key ] = U::ZERO_WIDTH_SPACE . $value; |
146
|
|
|
} else { |
147
|
5 |
|
$domain_parts[ $key ] = $value; |
148
|
|
|
} |
149
|
|
|
} |
150
|
|
|
|
151
|
|
|
// Lastly let's recombine. |
152
|
5 |
|
$domain = \implode( '', $domain_parts ); |
153
|
|
|
|
154
|
|
|
// Break up the URL path to individual characters. |
155
|
5 |
|
$path_parts = \str_split( $url_match['path'], 1 ); |
156
|
5 |
|
$path_count = \count( $path_parts ); |
157
|
5 |
|
$path = ''; |
158
|
5 |
|
foreach ( $path_parts as $index => $path_part ) { |
159
|
5 |
|
if ( 0 === $index || $path_count - $index < $settings[ Settings::URL_MIN_AFTER_WRAP ] ) { |
160
|
5 |
|
$path .= $path_part; |
161
|
|
|
} else { |
162
|
1 |
|
$path .= U::ZERO_WIDTH_SPACE . $path_part; |
163
|
|
|
} |
164
|
|
|
} |
165
|
|
|
|
166
|
5 |
|
$tokens[ $token_index ] = $text_token->with_value( $http . $domain . $path ); |
167
|
|
|
} |
168
|
|
|
} |
169
|
|
|
|
170
|
5 |
|
return $tokens; |
171
|
|
|
} |
172
|
|
|
} |
173
|
|
|
|