1
|
|
|
<?php |
2
|
|
|
/** |
3
|
|
|
* This file is part of PHP-Typography. |
4
|
|
|
* |
5
|
|
|
* Copyright 2017 Peter Putzer. |
6
|
|
|
* |
7
|
|
|
* This program is free software; you can redistribute it and/or modify |
8
|
|
|
* it under the terms of the GNU General Public License as published by |
9
|
|
|
* the Free Software Foundation; either version 2 of the License, or |
10
|
|
|
* (at your option) any later version. |
11
|
|
|
* |
12
|
|
|
* This program is distributed in the hope that it will be useful, |
13
|
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of |
14
|
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
15
|
|
|
* GNU General Public License for more details. |
16
|
|
|
* |
17
|
|
|
* You should have received a copy of the GNU General Public License along |
18
|
|
|
* with this program; if not, write to the Free Software Foundation, Inc., |
19
|
|
|
* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
20
|
|
|
* |
21
|
|
|
* *** |
22
|
|
|
* |
23
|
|
|
* @package mundschenk-at/php-typography |
24
|
|
|
* @license http://www.gnu.org/licenses/gpl-2.0.html |
25
|
|
|
*/ |
26
|
|
|
|
27
|
|
|
namespace PHP_Typography\Hyphenator; |
28
|
|
|
|
29
|
|
|
use PHP_Typography\Strings; |
30
|
|
|
|
31
|
|
|
/** |
32
|
|
|
* A hyphenation pattern trie node. |
33
|
|
|
* |
34
|
|
|
* Portions of this code have been inspired by: |
35
|
|
|
* - hyphenator-php (https://nikonyrh.github.io/phphyphenation.html) |
36
|
|
|
* |
37
|
|
|
* @author Peter Putzer <[email protected]> |
38
|
|
|
* |
39
|
|
|
* @since 5.0.0 |
40
|
|
|
*/ |
41
|
|
|
final class Trie_Node { |
42
|
|
|
|
43
|
|
|
/** |
44
|
|
|
* The offsets array. |
45
|
|
|
* |
46
|
|
|
* @var array |
47
|
|
|
*/ |
48
|
|
|
private $offsets = []; |
49
|
|
|
|
50
|
|
|
/** |
51
|
|
|
* Linked trie nodes. |
52
|
|
|
* |
53
|
|
|
* @var array { |
54
|
|
|
* @type Trie_Node $char The next node in the given character path. |
55
|
|
|
* } |
56
|
|
|
*/ |
57
|
|
|
private $links = []; |
58
|
|
|
|
59
|
|
|
/** |
60
|
|
|
* Create new Trie_Node. |
61
|
|
|
*/ |
62
|
1 |
|
private function __construct() { |
63
|
1 |
|
} |
64
|
|
|
|
65
|
|
|
/** |
66
|
|
|
* Retrieves the node for the given letter (or creates it). |
67
|
|
|
* |
68
|
|
|
* @param string $char A single character. |
69
|
|
|
* |
70
|
|
|
* @return Trie_Node |
71
|
|
|
*/ |
72
|
2 |
|
public function get_node( $char ) { |
73
|
2 |
|
if ( ! isset( $this->links[ $char ] ) ) { |
74
|
1 |
|
$this->links[ $char ] = new Trie_Node(); |
75
|
|
|
} |
76
|
|
|
|
77
|
2 |
|
return $this->links[ $char ]; |
78
|
|
|
} |
79
|
|
|
|
80
|
|
|
/** |
81
|
|
|
* Checks if there is a node for the given letter. |
82
|
|
|
* |
83
|
|
|
* @param string $char A single character. |
84
|
|
|
* |
85
|
|
|
* @return bool |
86
|
|
|
*/ |
87
|
1 |
|
public function exists( $char ) { |
88
|
1 |
|
return ! empty( $this->links[ $char ] ); |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
/** |
92
|
|
|
* Retrieves the offsets array. |
93
|
|
|
* |
94
|
|
|
* @return array |
95
|
|
|
*/ |
96
|
1 |
|
public function offsets() { |
97
|
1 |
|
return $this->offsets; |
98
|
|
|
} |
99
|
|
|
|
100
|
|
|
/** |
101
|
|
|
* Builds pattern search trie from pattern list(s). |
102
|
|
|
* |
103
|
|
|
* @param array $patterns An array of hyphenation patterns. |
104
|
|
|
* |
105
|
|
|
* @return Trie_Node The starting node of the trie. |
106
|
|
|
*/ |
107
|
1 |
|
public static function build_trie( array $patterns ) { |
108
|
1 |
|
$trie = new Trie_Node(); |
109
|
|
|
|
110
|
1 |
|
foreach ( $patterns as $key => $pattern ) { |
111
|
1 |
|
$node = $trie; |
112
|
|
|
|
113
|
1 |
|
foreach ( Strings::mb_str_split( $key ) as $char ) { |
114
|
1 |
|
$node = $node->get_node( $char ); |
115
|
|
|
} |
116
|
|
|
|
117
|
1 |
|
\preg_match_all( '/([1-9])/S', $pattern, $offsets, PREG_OFFSET_CAPTURE ); |
118
|
1 |
|
$node->offsets = $offsets[1]; |
119
|
|
|
} |
120
|
|
|
|
121
|
1 |
|
return $trie; |
122
|
|
|
} |
123
|
|
|
} |
124
|
|
|
|