|
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
|
|
|
/** |
|
37
|
|
|
* Use Punctuation to split any input into tokens |
|
38
|
|
|
* |
|
39
|
|
|
* @category Hyphenation |
|
40
|
|
|
* @package Org_Heigl_Hyphenator |
|
41
|
|
|
* @subpackage Tokenizer |
|
42
|
|
|
* @author Andreas Heigl <[email protected]> |
|
43
|
|
|
* @copyright 2008-2011 Andreas Heigl<[email protected]> |
|
44
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
|
45
|
|
|
* @version 2.0.1 |
|
46
|
|
|
* @link http://github.com/heiglandreas/Hyphenator |
|
47
|
|
|
* @since 04.11.2011 |
|
48
|
|
|
*/ |
|
49
|
|
|
class PunctuationTokenizer implements Tokenizer |
|
50
|
|
|
{ |
|
51
|
|
|
|
|
52
|
|
|
/** |
|
53
|
|
|
* The tokens to be handled by this tokenizer as an array. |
|
54
|
|
|
* |
|
55
|
|
|
* @var string[] $tokens |
|
56
|
|
|
*/ |
|
57
|
|
|
protected $tokens = [ |
|
58
|
|
|
'.', |
|
59
|
|
|
'?', |
|
60
|
|
|
'!', |
|
61
|
|
|
':', |
|
62
|
|
|
';', |
|
63
|
|
|
',', |
|
64
|
|
|
'#', |
|
65
|
|
|
'"', |
|
66
|
|
|
'$', |
|
67
|
|
|
'§', |
|
68
|
|
|
'%', |
|
69
|
|
|
'&', |
|
70
|
|
|
'/', |
|
71
|
|
|
'(', |
|
72
|
|
|
')', |
|
73
|
|
|
'=', |
|
74
|
|
|
'[', |
|
75
|
|
|
']', |
|
76
|
|
|
'|', |
|
77
|
|
|
'{', |
|
78
|
|
|
'}', |
|
79
|
|
|
'\\', |
|
80
|
|
|
'<', |
|
81
|
|
|
'>', |
|
82
|
|
|
'«', |
|
83
|
|
|
'»', |
|
84
|
|
|
'“', |
|
85
|
|
|
'”', |
|
86
|
|
|
'^', |
|
87
|
|
|
'°', |
|
88
|
|
|
'≤', |
|
89
|
|
|
'≥', |
|
90
|
|
|
'¥', |
|
91
|
|
|
'©', |
|
92
|
|
|
'€', |
|
93
|
|
|
"'", |
|
94
|
|
|
'-', |
|
95
|
|
|
'_', |
|
96
|
|
|
]; |
|
97
|
|
|
|
|
98
|
|
|
/** |
|
99
|
|
|
* Split the given input into tokens using punktuation marks as splitter |
|
100
|
|
|
* |
|
101
|
|
|
* The input can be a string or a tokenRegistry. If the input is a |
|
102
|
|
|
* TokenRegistry, each item will be tokenized. |
|
103
|
|
|
* |
|
104
|
|
|
* @param string|TokenRegistry $input The |
|
105
|
|
|
* input to be tokenized |
|
106
|
|
|
* |
|
107
|
|
|
* @return TokenRegistry |
|
108
|
|
|
*/ |
|
109
|
|
View Code Duplication |
public function run($input) |
|
110
|
|
|
{ |
|
111
|
|
|
if ($input instanceof TokenRegistry) { |
|
112
|
|
|
// Tokenize a TokenRegistry |
|
113
|
|
|
$f = clone($input); |
|
114
|
|
|
foreach ($input as $token) { |
|
115
|
|
|
if (! $token instanceof WordToken) { |
|
116
|
|
|
continue; |
|
117
|
|
|
} |
|
118
|
|
|
$newTokens = $this->tokenize($token->get()); |
|
119
|
|
|
if ($newTokens == array($token)) { |
|
120
|
|
|
continue; |
|
121
|
|
|
} |
|
122
|
|
|
$f->replace($token, $newTokens); |
|
123
|
|
|
} |
|
124
|
|
|
|
|
125
|
|
|
return $f ; |
|
126
|
|
|
} |
|
127
|
|
|
|
|
128
|
|
|
// Tokenize a simple string. |
|
129
|
|
|
$array = $this->tokenize($input); |
|
130
|
|
|
$registry = new TokenRegistry(); |
|
131
|
|
|
foreach ($array as $item) { |
|
132
|
|
|
$registry->add($item); |
|
133
|
|
|
} |
|
134
|
|
|
|
|
135
|
|
|
return $registry; |
|
136
|
|
|
} |
|
137
|
|
|
|
|
138
|
|
|
/** |
|
139
|
|
|
* Split the given string into tokens using whitespace. |
|
140
|
|
|
* |
|
141
|
|
|
* Each whitespace is placed in a WhitespaceToken and everything else is |
|
142
|
|
|
* placed in a WordToken-Object |
|
143
|
|
|
* |
|
144
|
|
|
* @param string $input The String to tokenize |
|
145
|
|
|
* |
|
146
|
|
|
* @return Token[] |
|
147
|
|
|
*/ |
|
148
|
|
View Code Duplication |
private function tokenize($input) |
|
149
|
|
|
{ |
|
150
|
|
|
$tokens = array(); |
|
151
|
|
|
$signs = '\\' . implode('\\', $this->tokens); |
|
152
|
|
|
$splits = preg_split('/([' . $signs . ']+)/u', $input, -1, PREG_SPLIT_DELIM_CAPTURE); |
|
153
|
|
|
foreach ($splits as $split) { |
|
154
|
|
|
if ('' == $split) { |
|
155
|
|
|
continue; |
|
156
|
|
|
} |
|
157
|
|
|
if (in_array(mb_substr($split, 0, 1), $this->tokens)) { |
|
158
|
|
|
$tokens[] = new NonWordToken($split); |
|
159
|
|
|
continue; |
|
160
|
|
|
} |
|
161
|
|
|
$tokens[] = new WordToken($split); |
|
162
|
|
|
} |
|
163
|
|
|
|
|
164
|
|
|
return $tokens; |
|
165
|
|
|
} |
|
166
|
|
|
} |
|
167
|
|
|
|
heiglandreas /
Org_Heigl_Hyphenator
