1
|
|
|
<?php |
2
|
|
|
/** |
3
|
|
|
* Copyright (c) 2008-2011 Andreas Heigl<[email protected]> |
4
|
|
|
* |
5
|
|
|
* Permission is hereby granted, free of charge, to any person obtaining a copy |
6
|
|
|
* of this software and associated documentation files (the "Software"), to deal |
7
|
|
|
* in the Software without restriction, including without limitation the rights |
8
|
|
|
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell |
9
|
|
|
* copies of the Software, and to permit persons to whom the Software is |
10
|
|
|
* furnished to do so, subject to the following conditions: |
11
|
|
|
* |
12
|
|
|
* The above copyright notice and this permission notice shall be included in |
13
|
|
|
* all copies or substantial portions of the Software. |
14
|
|
|
* |
15
|
|
|
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR |
16
|
|
|
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
17
|
|
|
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE |
18
|
|
|
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER |
19
|
|
|
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
20
|
|
|
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN |
21
|
|
|
* THE SOFTWARE. |
22
|
|
|
* |
23
|
|
|
* @category Hyphenation |
24
|
|
|
* @package Org_Heigl_Hyphenator |
25
|
|
|
* @subpackage Tokenizer |
26
|
|
|
* @author Andreas Heigl <[email protected]> |
27
|
|
|
* @copyright 2008-2011 Andreas Heigl<[email protected]> |
28
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
29
|
|
|
* @version 2.0.1 |
30
|
|
|
* @link http://github.com/heiglandreas/Hyphenator |
31
|
|
|
* @since 11.11.2011 |
32
|
|
|
*/ |
33
|
|
|
|
34
|
|
|
namespace Org\Heigl\Hyphenator\Tokenizer; |
35
|
|
|
|
36
|
|
|
use Org\Heigl\Hyphenator\Options; |
37
|
|
|
|
38
|
|
|
/** |
39
|
|
|
* Use Punktuation to split any input into tokens |
40
|
|
|
* |
41
|
|
|
* @category Hyphenation |
42
|
|
|
* @package Org_Heigl_Hyphenator |
43
|
|
|
* @subpackage Tokenizer |
44
|
|
|
* @author Andreas Heigl <[email protected]> |
45
|
|
|
* @copyright 2008-2011 Andreas Heigl<[email protected]> |
46
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
47
|
|
|
* @version 2.0.1 |
48
|
|
|
* @link http://github.com/heiglandreas/Hyphenator |
49
|
|
|
* @since 04.11.2011 |
50
|
|
|
*/ |
51
|
|
|
class CustomHyphenationTokenizer implements Tokenizer |
52
|
|
|
{ |
53
|
|
|
|
54
|
|
|
private $options; |
55
|
|
|
|
56
|
|
|
public function __construct(Options $options) |
57
|
|
|
{ |
58
|
|
|
$this->options = $options; |
59
|
|
|
} |
60
|
|
|
|
61
|
|
|
/** |
62
|
|
|
* Split the given input into tokens using punktuation marks as splitter |
63
|
|
|
* |
64
|
|
|
* The input can be a string or a tokenRegistry. If the input is a |
65
|
|
|
* TokenRegistry, each item will be tokenized. |
66
|
|
|
* |
67
|
|
|
* @param string|TokenRegistry $input The |
68
|
|
|
* input to be tokenized |
69
|
|
|
* |
70
|
|
|
* @return TokenRegistry |
71
|
|
|
*/ |
72
|
|
View Code Duplication |
public function run($input) |
73
|
|
|
{ |
74
|
|
|
if ($input instanceof TokenRegistry) { |
75
|
|
|
// Tokenize a TokenRegistry |
76
|
|
|
$f = clone($input); |
77
|
|
|
foreach ($input as $token) { |
78
|
|
|
if (! $token instanceof WordToken) { |
79
|
|
|
continue; |
80
|
|
|
} |
81
|
|
|
$newTokens = $this->tokenize($token->get()); |
82
|
|
|
$f->replace($token, $newTokens); |
83
|
|
|
} |
84
|
|
|
|
85
|
|
|
return $f ; |
86
|
|
|
} |
87
|
|
|
|
88
|
|
|
// Tokenize a simple string. |
89
|
|
|
$array = $this->tokenize($input); |
90
|
|
|
$registry = new TokenRegistry(); |
91
|
|
|
foreach ($array as $item) { |
92
|
|
|
$registry->add($item); |
93
|
|
|
} |
94
|
|
|
|
95
|
|
|
return $registry; |
96
|
|
|
} |
97
|
|
|
|
98
|
|
|
/** |
99
|
|
|
* Split the given string into tokens using whitespace. |
100
|
|
|
* |
101
|
|
|
* Each whitespace is placed in a WhitespaceToken and everything else is |
102
|
|
|
* placed in a WordToken-Object |
103
|
|
|
* |
104
|
|
|
* @param string $input The String to tokenize |
105
|
|
|
* |
106
|
|
|
* @return Token[] |
107
|
|
|
*/ |
108
|
|
|
private function tokenize($input) |
109
|
|
|
{ |
110
|
|
|
$tokens = []; |
111
|
|
|
|
112
|
|
|
$splits = preg_split(sprintf( |
113
|
|
|
'/((?:(?<=\W)%1$s|\b\w+%2$s)\w+?\b)/u', |
114
|
|
|
$this->options->getNoHyphenateString(), |
115
|
|
|
$this->options->getCustomHyphen() |
116
|
|
|
), $input, -1, PREG_SPLIT_DELIM_CAPTURE); |
117
|
|
|
foreach ($splits as $split) { |
118
|
|
|
if ('' == $split) { |
119
|
|
|
continue; |
120
|
|
|
} |
121
|
|
|
if (0 === mb_strpos($split, $this->options->getNoHyphenateString())) { |
122
|
|
|
$tokens[] = new ExcludedWordToken(str_replace( |
123
|
|
|
$this->options->getNoHyphenateString(), |
124
|
|
|
'', |
125
|
|
|
$split |
126
|
|
|
)); |
127
|
|
|
continue; |
128
|
|
|
} |
129
|
|
|
|
130
|
|
|
if (false !== mb_strpos($split, $this->options->getCustomHyphen())) { |
131
|
|
|
$tokens[] = new ExcludedWordToken(str_replace( |
132
|
|
|
$this->options->getCustomHyphen(), |
133
|
|
|
$this->options->getHyphen(), |
134
|
|
|
$split |
135
|
|
|
)); |
136
|
|
|
continue; |
137
|
|
|
} |
138
|
|
|
|
139
|
|
|
$tokens[] = new WordToken($split); |
140
|
|
|
} |
141
|
|
|
|
142
|
|
|
return $tokens; |
143
|
|
|
} |
144
|
|
|
} |
145
|
|
|
|