|
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 Options |
|
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 07.09.2011 |
|
32
|
|
|
*/ |
|
33
|
|
|
|
|
34
|
|
|
namespace Org\Heigl\Hyphenator; |
|
35
|
|
|
|
|
36
|
|
|
use \Org\Heigl\Hyphenator\Exception; |
|
37
|
|
|
use \Org\Heigl\Hyphenator\Tokenizer\Tokenizer; |
|
38
|
|
|
use \Org\Heigl\Hyphenator\Filter\Filter; |
|
39
|
|
|
|
|
40
|
|
|
/** |
|
41
|
|
|
* This class provides Options for the Hyphenator. |
|
42
|
|
|
* |
|
43
|
|
|
* @category Hyphenation |
|
44
|
|
|
* @package Org\Heigl\Hyphenator |
|
45
|
|
|
* @subpackage Options |
|
46
|
|
|
* @author Andreas Heigl <[email protected]> |
|
47
|
|
|
* @copyright 2008-2011 Andreas Heigl<[email protected]> |
|
48
|
|
|
* @license http://www.opensource.org/licenses/mit-license.php MIT-License |
|
49
|
|
|
* @version 2.0.1 |
|
50
|
|
|
* @link http://github.com/heiglandreas/Hyphenator |
|
51
|
|
|
* @since 07.09.2011 |
|
52
|
|
|
*/ |
|
53
|
|
|
class Options |
|
54
|
|
|
{ |
|
55
|
|
|
/** |
|
56
|
|
|
* The String that marks a word not to be hyphenated. |
|
57
|
|
|
* |
|
58
|
|
|
* This string has to be prepend to the word in question |
|
59
|
|
|
* |
|
60
|
|
|
* @var string _noHyphenateString |
|
61
|
|
|
*/ |
|
62
|
|
|
protected $_noHyphenateString = null; |
|
63
|
|
|
|
|
64
|
|
|
/** |
|
65
|
|
|
* This property defines the default hyphenation-character. |
|
66
|
|
|
* |
|
67
|
|
|
* By default this is the soft-hyphen character U+00AD |
|
68
|
|
|
* |
|
69
|
|
|
* @var string $_hyphen |
|
70
|
|
|
*/ |
|
71
|
|
|
protected $_hyphen = "\xAD"; |
|
72
|
|
|
|
|
73
|
|
|
/** |
|
74
|
|
|
* How many chars to stay to the left of the first hyphenation of a word. |
|
75
|
|
|
* |
|
76
|
|
|
* By default this is 2 characters |
|
77
|
|
|
* |
|
78
|
|
|
* @var int $_leftmin |
|
79
|
|
|
*/ |
|
80
|
|
|
protected $_leftMin = 2; |
|
81
|
|
|
|
|
82
|
|
|
/** |
|
83
|
|
|
* How many chars to stay to the right of the last hyphenation of a word. |
|
84
|
|
|
* |
|
85
|
|
|
* By default this is 2 characters |
|
86
|
|
|
* |
|
87
|
|
|
* @var int $_rightmin |
|
88
|
|
|
*/ |
|
89
|
|
|
protected $_rightMin = 2; |
|
90
|
|
|
|
|
91
|
|
|
/** |
|
92
|
|
|
* Minimum Word length for Hyphenation. |
|
93
|
|
|
* |
|
94
|
|
|
* This defaults to 6 Characters. |
|
95
|
|
|
* |
|
96
|
|
|
* @var int $_wordMin |
|
97
|
|
|
*/ |
|
98
|
|
|
protected $_wordMin = 6; |
|
99
|
|
|
|
|
100
|
|
|
/** |
|
101
|
|
|
* The currently set quality for hyphenation. |
|
102
|
|
|
* |
|
103
|
|
|
* The higher the number, the better the hyphenation is |
|
104
|
|
|
* |
|
105
|
|
|
* @var int $_quality |
|
106
|
|
|
*/ |
|
107
|
|
|
protected $_quality = 9; |
|
108
|
|
|
|
|
109
|
|
|
/** |
|
110
|
|
|
* The String that shall be searched for as a customHyphen. |
|
111
|
|
|
* |
|
112
|
|
|
* @var string $_customHyphen |
|
113
|
|
|
*/ |
|
114
|
|
|
protected $_customHyphen = '--'; |
|
115
|
|
|
|
|
116
|
|
|
/** |
|
117
|
|
|
* The filters to be used to postprocess the hyphenations. |
|
118
|
|
|
* |
|
119
|
|
|
* @var array $_filters |
|
120
|
|
|
*/ |
|
121
|
|
|
protected $_filters = array(); |
|
122
|
|
|
|
|
123
|
|
|
/** |
|
124
|
|
|
* The tokenizers to use. |
|
125
|
|
|
* |
|
126
|
|
|
* @var array $_tokenizers |
|
127
|
|
|
*/ |
|
128
|
|
|
protected $_tokenizers = array(); |
|
129
|
|
|
|
|
130
|
|
|
/** |
|
131
|
|
|
* THe locale to be used. |
|
132
|
|
|
* |
|
133
|
|
|
* @var string $_locale |
|
134
|
|
|
*/ |
|
135
|
|
|
protected $_defaultLocale = 'en_EN'; |
|
136
|
|
|
|
|
137
|
|
|
/** |
|
138
|
|
|
* Set the String that marks a word as not to be hyphenated |
|
139
|
|
|
* |
|
140
|
|
|
* @param string $noHyphenateString The string that marks a word not to be |
|
141
|
|
|
* hyphenated |
|
142
|
|
|
* |
|
143
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
144
|
|
|
*/ |
|
145
|
|
|
public function setNoHyphenateString($noHyphenateString) |
|
146
|
|
|
{ |
|
147
|
|
|
$this->_noHyphenateString = $noHyphenateString; |
|
148
|
|
|
|
|
149
|
|
|
return $this; |
|
150
|
|
|
} |
|
151
|
|
|
|
|
152
|
|
|
/** |
|
153
|
|
|
* Get the String that marks a word as not to be hyphenated |
|
154
|
|
|
* |
|
155
|
|
|
* @return string |
|
156
|
|
|
*/ |
|
157
|
|
|
public function getNoHyphenateString() |
|
158
|
|
|
{ |
|
159
|
|
|
return $this->_noHyphenateString; |
|
160
|
|
|
} |
|
161
|
|
|
|
|
162
|
|
|
/** |
|
163
|
|
|
* Set the hyphen-string |
|
164
|
|
|
* |
|
165
|
|
|
* @param string $hyphen The hyphen to use |
|
166
|
|
|
* |
|
167
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
168
|
|
|
*/ |
|
169
|
|
|
public function setHyphen($hyphen) |
|
170
|
|
|
{ |
|
171
|
|
|
$this->_hyphen = $hyphen; |
|
172
|
|
|
|
|
173
|
|
|
return $this; |
|
174
|
|
|
} |
|
175
|
|
|
|
|
176
|
|
|
/** |
|
177
|
|
|
* Get the hyphen-string |
|
178
|
|
|
* |
|
179
|
|
|
* @return string |
|
180
|
|
|
*/ |
|
181
|
|
|
public function getHyphen() |
|
182
|
|
|
{ |
|
183
|
|
|
return $this->_hyphen; |
|
184
|
|
|
} |
|
185
|
|
|
|
|
186
|
|
|
/** |
|
187
|
|
|
* Set the Minimum left characters |
|
188
|
|
|
* |
|
189
|
|
|
* @param int $leftMin Left minimum Chars |
|
190
|
|
|
* |
|
191
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
192
|
|
|
*/ |
|
193
|
|
|
public function setLeftMin($leftMin) |
|
194
|
|
|
{ |
|
195
|
|
|
$this->_leftMin = (int) $leftMin; |
|
196
|
|
|
|
|
197
|
|
|
return $this; |
|
198
|
|
|
} |
|
199
|
|
|
|
|
200
|
|
|
/** |
|
201
|
|
|
* Get the minimum left characters |
|
202
|
|
|
* |
|
203
|
|
|
* @return int |
|
204
|
|
|
*/ |
|
205
|
|
|
public function getLeftMin() |
|
206
|
|
|
{ |
|
207
|
|
|
return (int) $this->_leftMin; |
|
208
|
|
|
} |
|
209
|
|
|
|
|
210
|
|
|
/** |
|
211
|
|
|
* Set the Minimum right characters |
|
212
|
|
|
* |
|
213
|
|
|
* @param int $rightMin Right minimum Characters |
|
214
|
|
|
* |
|
215
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
216
|
|
|
*/ |
|
217
|
|
|
public function setRightMin($rightMin) |
|
218
|
|
|
{ |
|
219
|
|
|
$this->_rightMin = (int) $rightMin; |
|
220
|
|
|
|
|
221
|
|
|
return $this; |
|
222
|
|
|
} |
|
223
|
|
|
|
|
224
|
|
|
/** |
|
225
|
|
|
* Get the minimum right characters |
|
226
|
|
|
* |
|
227
|
|
|
* @return int |
|
228
|
|
|
*/ |
|
229
|
|
|
public function getRightMin() |
|
230
|
|
|
{ |
|
231
|
|
|
return (int) $this->_rightMin; |
|
232
|
|
|
} |
|
233
|
|
|
|
|
234
|
|
|
/** |
|
235
|
|
|
* Set the minimum size of a word to be hyphenated |
|
236
|
|
|
* |
|
237
|
|
|
* Words with less characters (not byte!) are not to be hyphenated |
|
238
|
|
|
* |
|
239
|
|
|
* @param int $minLength Minimum Word-Length |
|
240
|
|
|
* |
|
241
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
242
|
|
|
*/ |
|
243
|
|
|
public function setMinWordLength($minLength) |
|
244
|
|
|
{ |
|
245
|
|
|
$this->_wordMin = (int) $minLength; |
|
246
|
|
|
|
|
247
|
|
|
return $this; |
|
248
|
|
|
} |
|
249
|
|
|
|
|
250
|
|
|
/** |
|
251
|
|
|
* This is a wrapper for setMinWordLength |
|
252
|
|
|
* |
|
253
|
|
|
* @param int $wordLength The minimum word Length |
|
254
|
|
|
* |
|
255
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
256
|
|
|
*/ |
|
257
|
|
|
public function setWordMin($wordLength) |
|
258
|
|
|
{ |
|
259
|
|
|
return $this->setMinWordLength($wordLength); |
|
260
|
|
|
} |
|
261
|
|
|
|
|
262
|
|
|
/** |
|
263
|
|
|
* Set the hyphenation quality |
|
264
|
|
|
* |
|
265
|
|
|
* @param int $quality The new Hyphenation Quality |
|
266
|
|
|
* |
|
267
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
268
|
|
|
*/ |
|
269
|
|
|
public function setQuality($quality) |
|
270
|
|
|
{ |
|
271
|
|
|
$this->_quality = (int) $quality; |
|
272
|
|
|
|
|
273
|
|
|
return $this; |
|
274
|
|
|
} |
|
275
|
|
|
|
|
276
|
|
|
/** |
|
277
|
|
|
* Get the hyphenation-quality |
|
278
|
|
|
* |
|
279
|
|
|
* @return int |
|
280
|
|
|
*/ |
|
281
|
|
|
public function getQuality() |
|
282
|
|
|
{ |
|
283
|
|
|
return $this->_quality; |
|
284
|
|
|
} |
|
285
|
|
|
|
|
286
|
|
|
/** |
|
287
|
|
|
* Get the minimum Length of a word to be hyphenated |
|
288
|
|
|
* |
|
289
|
|
|
* @return int |
|
290
|
|
|
*/ |
|
291
|
|
|
public function getMinWordLength() |
|
292
|
|
|
{ |
|
293
|
|
|
return (int) $this->_wordMin; |
|
294
|
|
|
} |
|
295
|
|
|
|
|
296
|
|
|
/** |
|
297
|
|
|
* Set the string that is treated as a custom Hyphenation |
|
298
|
|
|
* |
|
299
|
|
|
* These will be replaced by the set hyphenation character |
|
300
|
|
|
* |
|
301
|
|
|
* @param array $customHyphen The custom hyphenation-character |
|
302
|
|
|
* |
|
303
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
304
|
|
|
*/ |
|
305
|
|
|
public function setCustomHyphen($customHyphen) |
|
306
|
|
|
{ |
|
307
|
|
|
$this->_customHyphen = (string) $customHyphen; |
|
308
|
|
|
|
|
309
|
|
|
return $this; |
|
310
|
|
|
} |
|
311
|
|
|
|
|
312
|
|
|
/** |
|
313
|
|
|
* Get the custom Hyphen |
|
314
|
|
|
* |
|
315
|
|
|
* @return string |
|
316
|
|
|
*/ |
|
317
|
|
|
public function getCustomHyphen() |
|
318
|
|
|
{ |
|
319
|
|
|
return $this->_customHyphen; |
|
320
|
|
|
} |
|
321
|
|
|
|
|
322
|
|
|
/** |
|
323
|
|
|
* Set the filters |
|
324
|
|
|
* |
|
325
|
|
|
* @param string|array $filters The filters to use as comma separated list |
|
326
|
|
|
* or array |
|
327
|
|
|
* |
|
328
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
329
|
|
|
*/ |
|
330
|
|
|
public function setFilters($filters) |
|
331
|
|
|
{ |
|
332
|
|
|
$this->_filters = array(); |
|
333
|
|
|
if (! is_array($filters)) { |
|
334
|
|
|
$filters = explode(',', $filters); |
|
335
|
|
|
} |
|
336
|
|
|
foreach ($filters as $filter) { |
|
337
|
|
|
$this->addFilter($filter); |
|
338
|
|
|
} |
|
339
|
|
|
|
|
340
|
|
|
return $this; |
|
341
|
|
|
} |
|
342
|
|
|
|
|
343
|
|
|
/** |
|
344
|
|
|
* Add a filter to the options-array |
|
345
|
|
|
* |
|
346
|
|
|
* @param string|Filter $filter The filter to be added |
|
347
|
|
|
* |
|
348
|
|
|
* @throws \UnexpectedValueException |
|
349
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
350
|
|
|
*/ |
|
351
|
|
|
public function addFilter($filter) |
|
352
|
|
|
{ |
|
353
|
|
|
if (is_string($filter)) { |
|
354
|
|
|
$filter = trim($filter); |
|
355
|
|
|
} elseif (! $filter instanceof Filter) { |
|
356
|
|
|
throw new \UnexpectedValueException('Expceted instanceof Org\Heigl\Hyphenator\Filter\Filter or string'); |
|
357
|
|
|
} |
|
358
|
|
|
if (! $filter) { |
|
359
|
|
|
return $this; |
|
360
|
|
|
} |
|
361
|
|
|
$this->_filters[] = $filter; |
|
362
|
|
|
|
|
363
|
|
|
return $this; |
|
364
|
|
|
} |
|
365
|
|
|
|
|
366
|
|
|
/** |
|
367
|
|
|
* Get all the filters |
|
368
|
|
|
* |
|
369
|
|
|
* @return array |
|
370
|
|
|
*/ |
|
371
|
|
|
public function getFilters() |
|
372
|
|
|
{ |
|
373
|
|
|
return $this->_filters; |
|
374
|
|
|
} |
|
375
|
|
|
|
|
376
|
|
|
/** |
|
377
|
|
|
* Set the tokenizers to use |
|
378
|
|
|
* |
|
379
|
|
|
* @param string|array $tokenizers The Tokenizers to use |
|
380
|
|
|
* |
|
381
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
382
|
|
|
*/ |
|
383
|
|
|
public function setTokenizers($tokenizers) |
|
384
|
|
|
{ |
|
385
|
|
|
$this->_tokenizers = array(); |
|
386
|
|
|
if (! is_array($tokenizers)) { |
|
387
|
|
|
$tokenizers = explode(',', $tokenizers); |
|
388
|
|
|
} |
|
389
|
|
|
foreach ($tokenizers as $tokenizer) { |
|
390
|
|
|
$this->addTokenizer($tokenizer); |
|
391
|
|
|
} |
|
392
|
|
|
|
|
393
|
|
|
return $this; |
|
394
|
|
|
} |
|
395
|
|
|
|
|
396
|
|
|
/** |
|
397
|
|
|
* Add a tokenizer to the tomeizer-list |
|
398
|
|
|
* |
|
399
|
|
|
* @param string|Tokenizer $tokenizer The tokenizer to add |
|
400
|
|
|
* |
|
401
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
402
|
|
|
*/ |
|
403
|
|
|
public function addTokenizer($tokenizer) |
|
404
|
|
|
{ |
|
405
|
|
|
if (is_string($tokenizer)) { |
|
406
|
|
|
$tokenizer = trim($tokenizer); |
|
407
|
|
|
} elseif (! $tokenizer instanceof Tokenizer) { |
|
408
|
|
|
throw new \UnexpectedValueException('Expceted instanceof Org\Heigl\Hyphenator\Tokenizer\Tokenizer or string'); |
|
409
|
|
|
} |
|
410
|
|
|
|
|
411
|
|
|
if (! $tokenizer) { |
|
412
|
|
|
return $this; |
|
413
|
|
|
} |
|
414
|
|
|
$this->_tokenizers[] = $tokenizer; |
|
415
|
|
|
|
|
416
|
|
|
return $this; |
|
417
|
|
|
} |
|
418
|
|
|
|
|
419
|
|
|
/** |
|
420
|
|
|
* Get all the tokenizers |
|
421
|
|
|
* |
|
422
|
|
|
* @return array |
|
423
|
|
|
*/ |
|
424
|
|
|
public function getTokenizers() |
|
425
|
|
|
{ |
|
426
|
|
|
return $this->_tokenizers; |
|
427
|
|
|
} |
|
428
|
|
|
|
|
429
|
|
|
/** |
|
430
|
|
|
* Create an Option-Object by parsing a given file. |
|
431
|
|
|
* |
|
432
|
|
|
* @param string $file The config-file to be parsed |
|
433
|
|
|
* |
|
434
|
|
|
* @throws \Org\Heigl\Hyphenator\Exception\PathNotFoundException |
|
435
|
|
|
* @throws \Org\Heigl\Hyphenator\Exception\InvalidArgumentException |
|
436
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
437
|
|
|
*/ |
|
438
|
|
|
public static function factory($file) |
|
439
|
|
|
{ |
|
440
|
|
|
if (! file_Exists($file)) { |
|
441
|
|
|
$file = $file . '.dist'; |
|
442
|
|
|
if (! file_exists($file)) { |
|
443
|
|
|
throw new \Org\Heigl\Hyphenator\Exception\PathNotFoundException($file); |
|
444
|
|
|
} |
|
445
|
|
|
} |
|
446
|
|
|
$params = parse_ini_file($file); |
|
447
|
|
|
if (! is_array($params) || 1 > count($params)) { |
|
448
|
|
|
throw new \Org\Heigl\Hyphenator\Exception\InvalidArgumentException($file . ' is not a parseable file'); |
|
449
|
|
|
} |
|
450
|
|
|
|
|
451
|
|
|
$option = new Options(); |
|
452
|
|
|
foreach ($params as $key => $val) { |
|
453
|
|
|
if (! method_Exists($option, 'set' . $key)) { |
|
454
|
|
|
continue; |
|
455
|
|
|
} |
|
456
|
|
|
call_user_Func(array($option,'set' . $key), $val); |
|
457
|
|
|
} |
|
458
|
|
|
|
|
459
|
|
|
return $option; |
|
460
|
|
|
} |
|
461
|
|
|
|
|
462
|
|
|
/** |
|
463
|
|
|
* Set the default locale for this instance |
|
464
|
|
|
* |
|
465
|
|
|
* @param string $locale The locale to be set |
|
466
|
|
|
* |
|
467
|
|
|
* @return \Org\Heigl\Hyphenator\Options |
|
468
|
|
|
*/ |
|
469
|
|
|
public function setDefaultLocale($locale) |
|
470
|
|
|
{ |
|
471
|
|
|
$this->_defaultLocale = (string) $locale; |
|
472
|
|
|
|
|
473
|
|
|
return $this; |
|
474
|
|
|
} |
|
475
|
|
|
|
|
476
|
|
|
/** |
|
477
|
|
|
* Get the default locale for this instance |
|
478
|
|
|
* |
|
479
|
|
|
* @return string |
|
480
|
|
|
*/ |
|
481
|
|
|
public function getDefaultLocale() |
|
482
|
|
|
{ |
|
483
|
|
|
return $this->_defaultLocale; |
|
484
|
|
|
} |
|
485
|
|
|
} |
|
486
|
|
|
|