|
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 04.11.2011 |
|
32
|
|
|
*/ |
|
33
|
|
|
|
|
34
|
|
|
namespace Org\Heigl\Hyphenator\Tokenizer; |
|
35
|
|
|
|
|
36
|
|
|
use Countable; |
|
37
|
|
|
use Iterator; |
|
38
|
|
|
|
|
39
|
|
|
/** |
|
40
|
|
|
* This class provides a registry for storing multiple Tokenizers |
|
41
|
|
|
* |
|
42
|
|
|
* @category Hyphenation |
|
43
|
|
|
* @package Org\Heigl\Hyphenator |
|
44
|
|
|
* @subpackage Tokenizer |
|
45
|
|
|
* @author Andreas Heigl <[email protected]> |
|
46
|
|
|
* @copyright 2008-2011 Andreas Heigl<[email protected]> |
|
47
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
|
48
|
|
|
* @version 2.0.1 |
|
49
|
|
|
* @link http://github.com/heiglandreas/Hyphenator |
|
50
|
|
|
* @since 04.11.2011 |
|
51
|
|
|
*/ |
|
52
|
|
|
class TokenizerRegistry implements Iterator, Countable |
|
53
|
|
|
{ |
|
54
|
|
|
/** |
|
55
|
|
|
* Storage for the Tokenizers. |
|
56
|
|
|
* |
|
57
|
|
|
* @var Tokenizer[] $_registry |
|
58
|
|
|
*/ |
|
59
|
|
|
private $registry = array(); |
|
60
|
|
|
|
|
61
|
|
|
/** |
|
62
|
|
|
* Add an item to the registry |
|
63
|
|
|
* |
|
64
|
|
|
* @param Tokenizer $tokenizer The tokeniter to be added |
|
65
|
|
|
* |
|
66
|
|
|
* @return TokenizerRegistry |
|
67
|
|
|
*/ |
|
68
|
|
|
public function add(Tokenizer $tokenizer) |
|
69
|
|
|
{ |
|
70
|
|
|
if (! in_array($tokenizer, $this->registry)) { |
|
71
|
|
|
$this->registry[] = $tokenizer; |
|
72
|
|
|
} |
|
73
|
|
|
|
|
74
|
|
|
return $this; |
|
75
|
|
|
} |
|
76
|
|
|
|
|
77
|
|
|
/** |
|
78
|
|
|
* Get a dictionary entry by its key |
|
79
|
|
|
* |
|
80
|
|
|
* @param mixed $key The key to get the tokenizer for. |
|
81
|
|
|
* |
|
82
|
|
|
* @return Tokenizer|null |
|
83
|
|
|
*/ |
|
84
|
|
|
public function getTokenizerWithKey($key) |
|
85
|
|
|
{ |
|
86
|
|
|
if (array_key_exists($key, $this->registry)) { |
|
87
|
|
|
return $this->registry[$key]; |
|
88
|
|
|
} |
|
89
|
|
|
|
|
90
|
|
|
return null; |
|
91
|
|
|
} |
|
92
|
|
|
|
|
93
|
|
|
/** |
|
94
|
|
|
* Cleanup the registry |
|
95
|
|
|
* |
|
96
|
|
|
* @return TokenizerRegistry |
|
97
|
|
|
*/ |
|
98
|
|
|
public function cleanup() |
|
99
|
|
|
{ |
|
100
|
|
|
$this->registry = array(); |
|
101
|
|
|
|
|
102
|
|
|
return $this; |
|
103
|
|
|
} |
|
104
|
|
|
|
|
105
|
|
|
/** |
|
106
|
|
|
* Pass the given string through the given tokenizers |
|
107
|
|
|
* |
|
108
|
|
|
* @param string|TokenRegistry $string The String to be tokenized |
|
109
|
|
|
* |
|
110
|
|
|
* @return TokenRegistry |
|
111
|
|
|
*/ |
|
112
|
|
|
public function tokenize($string) |
|
113
|
|
|
{ |
|
114
|
|
|
if (! $string instanceof TokenRegistry) { |
|
115
|
|
|
$wt = new WordToken($string); |
|
116
|
|
|
$string = new TokenRegistry(); |
|
117
|
|
|
$string->add($wt); |
|
118
|
|
|
} |
|
119
|
|
|
foreach ($this as $tokenizer) { |
|
120
|
|
|
$string = $tokenizer->run($string); |
|
121
|
|
|
} |
|
122
|
|
|
|
|
123
|
|
|
return $string; |
|
124
|
|
|
} |
|
125
|
|
|
|
|
126
|
|
|
/** |
|
127
|
|
|
* Implementation of Iterator |
|
128
|
|
|
* |
|
129
|
|
|
* @see Iterator::rewind() |
|
130
|
|
|
* |
|
131
|
|
|
* @return void |
|
132
|
|
|
*/ |
|
133
|
|
|
public function rewind() |
|
134
|
|
|
{ |
|
135
|
|
|
reset($this->registry); |
|
136
|
|
|
} |
|
137
|
|
|
|
|
138
|
|
|
/** |
|
139
|
|
|
* Get the current object |
|
140
|
|
|
* |
|
141
|
|
|
* @see Iterator::current() |
|
142
|
|
|
* |
|
143
|
|
|
* @return Tokenizer |
|
144
|
|
|
*/ |
|
145
|
|
|
public function current() |
|
146
|
|
|
{ |
|
147
|
|
|
return current($this->registry); |
|
148
|
|
|
} |
|
149
|
|
|
|
|
150
|
|
|
/** |
|
151
|
|
|
* Get the current key |
|
152
|
|
|
* |
|
153
|
|
|
* @see Iterator::key() |
|
154
|
|
|
* |
|
155
|
|
|
* @return mixed |
|
156
|
|
|
*/ |
|
157
|
|
|
public function key() |
|
158
|
|
|
{ |
|
159
|
|
|
return key($this->registry); |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
|
|
/** |
|
163
|
|
|
* Get the number of items in the registry |
|
164
|
|
|
* |
|
165
|
|
|
* @see Countable::count() |
|
166
|
|
|
* |
|
167
|
|
|
* @return int |
|
168
|
|
|
*/ |
|
169
|
|
|
public function count() |
|
170
|
|
|
{ |
|
171
|
|
|
return count($this->registry); |
|
172
|
|
|
} |
|
173
|
|
|
|
|
174
|
|
|
/** |
|
175
|
|
|
* Push the internal pointer forward one step |
|
176
|
|
|
* |
|
177
|
|
|
* @see Iterator::next() |
|
178
|
|
|
* |
|
179
|
|
|
* @return void |
|
180
|
|
|
*/ |
|
181
|
|
|
public function next() |
|
182
|
|
|
{ |
|
183
|
|
|
next($this->registry); |
|
184
|
|
|
} |
|
185
|
|
|
|
|
186
|
|
|
/** |
|
187
|
|
|
* Check whether the current pointer is in a valid place |
|
188
|
|
|
* |
|
189
|
|
|
* @see Iterator::valid() |
|
190
|
|
|
* |
|
191
|
|
|
* @return boolean |
|
192
|
|
|
*/ |
|
193
|
|
|
public function valid() |
|
194
|
|
|
{ |
|
195
|
|
|
if (false === current($this->registry)) { |
|
196
|
|
|
return false; |
|
197
|
|
|
} |
|
198
|
|
|
|
|
199
|
|
|
return true; |
|
200
|
|
|
} |
|
201
|
|
|
} |
|
202
|
|
|
|
heiglandreas /
Org_Heigl_Hyphenator
