1
|
|
|
<?php |
2
|
|
|
|
3
|
|
|
/* |
4
|
|
|
* This file is part of the Symfony package. |
5
|
|
|
* |
6
|
|
|
* (c) Fabien Potencier <[email protected]> |
7
|
|
|
* |
8
|
|
|
* For the full copyright and license information, please view the LICENSE |
9
|
|
|
* file that was distributed with this source code. |
10
|
|
|
*/ |
11
|
|
|
|
12
|
|
|
namespace Symfony\Component\String; |
13
|
|
|
|
14
|
|
|
use Symfony\Component\String\Exception\ExceptionInterface; |
15
|
|
|
use Symfony\Component\String\Exception\InvalidArgumentException; |
16
|
|
|
|
17
|
|
|
/** |
18
|
|
|
* Represents a string of Unicode grapheme clusters encoded as UTF-8. |
19
|
|
|
* |
20
|
|
|
* A letter followed by combining characters (accents typically) form what Unicode defines |
21
|
|
|
* as a grapheme cluster: a character as humans mean it in written texts. This class knows |
22
|
|
|
* about the concept and won't split a letter apart from its combining accents. It also |
23
|
|
|
* ensures all string comparisons happen on their canonically-composed representation, |
24
|
|
|
* ignoring e.g. the order in which accents are listed when a letter has many of them. |
25
|
|
|
* |
26
|
|
|
* @see https://unicode.org/reports/tr15/ |
27
|
|
|
* |
28
|
|
|
* @author Nicolas Grekas <[email protected]> |
29
|
|
|
* @author Hugo Hamon <[email protected]> |
30
|
|
|
* |
31
|
|
|
* @throws ExceptionInterface |
32
|
|
|
*/ |
33
|
|
|
class UnicodeString extends AbstractUnicodeString |
34
|
|
|
{ |
35
|
|
|
public function __construct(string $string = '') |
36
|
|
|
{ |
37
|
|
|
if ('' === $string || normalizer_is_normalized($this->string = $string)) { |
38
|
|
|
return; |
39
|
|
|
} |
40
|
|
|
|
41
|
|
|
if (false === $string = normalizer_normalize($string)) { |
42
|
|
|
throw new InvalidArgumentException('Invalid UTF-8 string.'); |
43
|
|
|
} |
44
|
|
|
|
45
|
|
|
$this->string = $string; |
46
|
|
|
} |
47
|
|
|
|
48
|
|
|
public function append(string ...$suffix): static |
49
|
|
|
{ |
50
|
|
|
$str = clone $this; |
51
|
|
|
$str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix)); |
52
|
|
|
|
53
|
|
|
if (normalizer_is_normalized($str->string)) { |
54
|
|
|
return $str; |
55
|
|
|
} |
56
|
|
|
|
57
|
|
|
if (false === $string = normalizer_normalize($str->string)) { |
58
|
|
|
throw new InvalidArgumentException('Invalid UTF-8 string.'); |
59
|
|
|
} |
60
|
|
|
|
61
|
|
|
$str->string = $string; |
62
|
|
|
|
63
|
|
|
return $str; |
64
|
|
|
} |
65
|
|
|
|
66
|
|
|
public function chunk(int $length = 1): array |
67
|
|
|
{ |
68
|
|
|
if (1 > $length) { |
69
|
|
|
throw new InvalidArgumentException('The chunk length must be greater than zero.'); |
70
|
|
|
} |
71
|
|
|
|
72
|
|
|
if ('' === $this->string) { |
73
|
|
|
return []; |
74
|
|
|
} |
75
|
|
|
|
76
|
|
|
$rx = '/('; |
77
|
|
|
while (65535 < $length) { |
78
|
|
|
$rx .= '\X{65535}'; |
79
|
|
|
$length -= 65535; |
80
|
|
|
} |
81
|
|
|
$rx .= '\X{'.$length.'})/u'; |
82
|
|
|
|
83
|
|
|
$str = clone $this; |
84
|
|
|
$chunks = []; |
85
|
|
|
|
86
|
|
|
foreach (preg_split($rx, $this->string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY) as $chunk) { |
87
|
|
|
$str->string = $chunk; |
88
|
|
|
$chunks[] = clone $str; |
89
|
|
|
} |
90
|
|
|
|
91
|
|
|
return $chunks; |
92
|
|
|
} |
93
|
|
|
|
94
|
|
|
public function endsWith(string|iterable|AbstractString $suffix): bool |
95
|
|
|
{ |
96
|
|
|
if ($suffix instanceof AbstractString) { |
97
|
|
|
$suffix = $suffix->string; |
98
|
|
|
} elseif (!\is_string($suffix)) { |
99
|
|
|
return parent::endsWith($suffix); |
100
|
|
|
} |
101
|
|
|
|
102
|
|
|
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
103
|
|
|
normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form); |
104
|
|
|
|
105
|
|
|
if ('' === $suffix || false === $suffix) { |
106
|
|
|
return false; |
107
|
|
|
} |
108
|
|
|
|
109
|
|
|
if ($this->ignoreCase) { |
110
|
|
|
return 0 === mb_stripos(grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)), $suffix, 0, 'UTF-8'); |
111
|
|
|
} |
112
|
|
|
|
113
|
|
|
return $suffix === grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)); |
114
|
|
|
} |
115
|
|
|
|
116
|
|
|
public function equalsTo(string|iterable|AbstractString $string): bool |
117
|
|
|
{ |
118
|
|
|
if ($string instanceof AbstractString) { |
119
|
|
|
$string = $string->string; |
120
|
|
|
} elseif (!\is_string($string)) { |
121
|
|
|
return parent::equalsTo($string); |
122
|
|
|
} |
123
|
|
|
|
124
|
|
|
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
125
|
|
|
normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form); |
126
|
|
|
|
127
|
|
|
if ('' !== $string && false !== $string && $this->ignoreCase) { |
128
|
|
|
return \strlen($string) === \strlen($this->string) && 0 === mb_stripos($this->string, $string, 0, 'UTF-8'); |
129
|
|
|
} |
130
|
|
|
|
131
|
|
|
return $string === $this->string; |
132
|
|
|
} |
133
|
|
|
|
134
|
|
|
public function indexOf(string|iterable|AbstractString $needle, int $offset = 0): ?int |
135
|
|
|
{ |
136
|
|
|
if ($needle instanceof AbstractString) { |
137
|
|
|
$needle = $needle->string; |
138
|
|
|
} elseif (!\is_string($needle)) { |
139
|
|
|
return parent::indexOf($needle, $offset); |
140
|
|
|
} |
141
|
|
|
|
142
|
|
|
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
143
|
|
|
normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
144
|
|
|
|
145
|
|
|
if ('' === $needle || false === $needle) { |
146
|
|
|
return null; |
147
|
|
|
} |
148
|
|
|
|
149
|
|
|
try { |
150
|
|
|
$i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset); |
151
|
|
|
} catch (\ValueError) { |
152
|
|
|
return null; |
153
|
|
|
} |
154
|
|
|
|
155
|
|
|
return false === $i ? null : $i; |
|
|
|
|
156
|
|
|
} |
157
|
|
|
|
158
|
|
|
public function indexOfLast(string|iterable|AbstractString $needle, int $offset = 0): ?int |
159
|
|
|
{ |
160
|
|
|
if ($needle instanceof AbstractString) { |
161
|
|
|
$needle = $needle->string; |
162
|
|
|
} elseif (!\is_string($needle)) { |
163
|
|
|
return parent::indexOfLast($needle, $offset); |
164
|
|
|
} |
165
|
|
|
|
166
|
|
|
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
167
|
|
|
normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
168
|
|
|
|
169
|
|
|
if ('' === $needle || false === $needle) { |
170
|
|
|
return null; |
171
|
|
|
} |
172
|
|
|
|
173
|
|
|
$string = $this->string; |
174
|
|
|
|
175
|
|
|
if (0 > $offset) { |
176
|
|
|
// workaround https://bugs.php.net/74264 |
177
|
|
|
if (0 > $offset += grapheme_strlen($needle)) { |
178
|
|
|
$string = grapheme_substr($string, 0, $offset); |
179
|
|
|
} |
180
|
|
|
$offset = 0; |
181
|
|
|
} |
182
|
|
|
|
183
|
|
|
$i = $this->ignoreCase ? grapheme_strripos($string, $needle, $offset) : grapheme_strrpos($string, $needle, $offset); |
184
|
|
|
|
185
|
|
|
return false === $i ? null : $i; |
|
|
|
|
186
|
|
|
} |
187
|
|
|
|
188
|
|
|
public function join(array $strings, ?string $lastGlue = null): static |
189
|
|
|
{ |
190
|
|
|
$str = parent::join($strings, $lastGlue); |
191
|
|
|
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
192
|
|
|
|
193
|
|
|
return $str; |
|
|
|
|
194
|
|
|
} |
195
|
|
|
|
196
|
|
|
public function length(): int |
197
|
|
|
{ |
198
|
|
|
return grapheme_strlen($this->string); |
|
|
|
|
199
|
|
|
} |
200
|
|
|
|
201
|
|
|
public function normalize(int $form = self::NFC): static |
202
|
|
|
{ |
203
|
|
|
$str = clone $this; |
204
|
|
|
|
205
|
|
|
if (\in_array($form, [self::NFC, self::NFKC], true)) { |
206
|
|
|
normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form); |
207
|
|
|
} elseif (!\in_array($form, [self::NFD, self::NFKD], true)) { |
208
|
|
|
throw new InvalidArgumentException('Unsupported normalization form.'); |
209
|
|
|
} elseif (!normalizer_is_normalized($str->string, $form)) { |
210
|
|
|
$str->string = normalizer_normalize($str->string, $form); |
211
|
|
|
$str->ignoreCase = null; |
212
|
|
|
} |
213
|
|
|
|
214
|
|
|
return $str; |
215
|
|
|
} |
216
|
|
|
|
217
|
|
|
public function prepend(string ...$prefix): static |
218
|
|
|
{ |
219
|
|
|
$str = clone $this; |
220
|
|
|
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string; |
221
|
|
|
|
222
|
|
|
if (normalizer_is_normalized($str->string)) { |
223
|
|
|
return $str; |
224
|
|
|
} |
225
|
|
|
|
226
|
|
|
if (false === $string = normalizer_normalize($str->string)) { |
227
|
|
|
throw new InvalidArgumentException('Invalid UTF-8 string.'); |
228
|
|
|
} |
229
|
|
|
|
230
|
|
|
$str->string = $string; |
231
|
|
|
|
232
|
|
|
return $str; |
233
|
|
|
} |
234
|
|
|
|
235
|
|
|
public function replace(string $from, string $to): static |
236
|
|
|
{ |
237
|
|
|
$str = clone $this; |
238
|
|
|
normalizer_is_normalized($from) ?: $from = normalizer_normalize($from); |
239
|
|
|
|
240
|
|
|
if ('' !== $from && false !== $from) { |
241
|
|
|
$tail = $str->string; |
242
|
|
|
$result = ''; |
243
|
|
|
$indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
244
|
|
|
|
245
|
|
|
while ('' !== $tail && false !== $i = $indexOf($tail, $from)) { |
246
|
|
|
$slice = grapheme_substr($tail, 0, $i); |
247
|
|
|
$result .= $slice.$to; |
248
|
|
|
$tail = substr($tail, \strlen($slice) + \strlen($from)); |
249
|
|
|
} |
250
|
|
|
|
251
|
|
|
$str->string = $result.$tail; |
252
|
|
|
|
253
|
|
|
if (normalizer_is_normalized($str->string)) { |
254
|
|
|
return $str; |
255
|
|
|
} |
256
|
|
|
|
257
|
|
|
if (false === $string = normalizer_normalize($str->string)) { |
258
|
|
|
throw new InvalidArgumentException('Invalid UTF-8 string.'); |
259
|
|
|
} |
260
|
|
|
|
261
|
|
|
$str->string = $string; |
262
|
|
|
} |
263
|
|
|
|
264
|
|
|
return $str; |
265
|
|
|
} |
266
|
|
|
|
267
|
|
|
public function replaceMatches(string $fromRegexp, string|callable $to): static |
268
|
|
|
{ |
269
|
|
|
$str = parent::replaceMatches($fromRegexp, $to); |
270
|
|
|
normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
271
|
|
|
|
272
|
|
|
return $str; |
|
|
|
|
273
|
|
|
} |
274
|
|
|
|
275
|
|
|
public function slice(int $start = 0, ?int $length = null): static |
276
|
|
|
{ |
277
|
|
|
$str = clone $this; |
278
|
|
|
|
279
|
|
|
$str->string = (string) grapheme_substr($this->string, $start, $length ?? 2147483647); |
280
|
|
|
|
281
|
|
|
return $str; |
282
|
|
|
} |
283
|
|
|
|
284
|
|
|
public function splice(string $replacement, int $start = 0, ?int $length = null): static |
285
|
|
|
{ |
286
|
|
|
$str = clone $this; |
287
|
|
|
|
288
|
|
|
$start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0; |
289
|
|
|
$length = $length ? \strlen(grapheme_substr($this->string, $start, $length ?? 2147483647)) : $length; |
290
|
|
|
$str->string = substr_replace($this->string, $replacement, $start, $length ?? 2147483647); |
291
|
|
|
|
292
|
|
|
if (normalizer_is_normalized($str->string)) { |
293
|
|
|
return $str; |
294
|
|
|
} |
295
|
|
|
|
296
|
|
|
if (false === $string = normalizer_normalize($str->string)) { |
297
|
|
|
throw new InvalidArgumentException('Invalid UTF-8 string.'); |
298
|
|
|
} |
299
|
|
|
|
300
|
|
|
$str->string = $string; |
301
|
|
|
|
302
|
|
|
return $str; |
303
|
|
|
} |
304
|
|
|
|
305
|
|
|
public function split(string $delimiter, ?int $limit = null, ?int $flags = null): array |
306
|
|
|
{ |
307
|
|
|
if (1 > $limit ??= 2147483647) { |
308
|
|
|
throw new InvalidArgumentException('Split limit must be a positive integer.'); |
309
|
|
|
} |
310
|
|
|
|
311
|
|
|
if ('' === $delimiter) { |
312
|
|
|
throw new InvalidArgumentException('Split delimiter is empty.'); |
313
|
|
|
} |
314
|
|
|
|
315
|
|
|
if (null !== $flags) { |
316
|
|
|
return parent::split($delimiter.'u', $limit, $flags); |
|
|
|
|
317
|
|
|
} |
318
|
|
|
|
319
|
|
|
normalizer_is_normalized($delimiter) ?: $delimiter = normalizer_normalize($delimiter); |
320
|
|
|
|
321
|
|
|
if (false === $delimiter) { |
|
|
|
|
322
|
|
|
throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.'); |
323
|
|
|
} |
324
|
|
|
|
325
|
|
|
$str = clone $this; |
326
|
|
|
$tail = $this->string; |
327
|
|
|
$chunks = []; |
328
|
|
|
$indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
329
|
|
|
|
330
|
|
|
while (1 < $limit && false !== $i = $indexOf($tail, $delimiter)) { |
331
|
|
|
$str->string = grapheme_substr($tail, 0, $i); |
332
|
|
|
$chunks[] = clone $str; |
333
|
|
|
$tail = substr($tail, \strlen($str->string) + \strlen($delimiter)); |
334
|
|
|
--$limit; |
335
|
|
|
} |
336
|
|
|
|
337
|
|
|
$str->string = $tail; |
338
|
|
|
$chunks[] = clone $str; |
339
|
|
|
|
340
|
|
|
return $chunks; |
341
|
|
|
} |
342
|
|
|
|
343
|
|
|
public function startsWith(string|iterable|AbstractString $prefix): bool |
344
|
|
|
{ |
345
|
|
|
if ($prefix instanceof AbstractString) { |
346
|
|
|
$prefix = $prefix->string; |
347
|
|
|
} elseif (!\is_string($prefix)) { |
348
|
|
|
return parent::startsWith($prefix); |
349
|
|
|
} |
350
|
|
|
|
351
|
|
|
$form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
352
|
|
|
normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form); |
353
|
|
|
|
354
|
|
|
if ('' === $prefix || false === $prefix) { |
355
|
|
|
return false; |
356
|
|
|
} |
357
|
|
|
|
358
|
|
|
if ($this->ignoreCase) { |
359
|
|
|
return 0 === mb_stripos(grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES), $prefix, 0, 'UTF-8'); |
360
|
|
|
} |
361
|
|
|
|
362
|
|
|
return $prefix === grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES); |
363
|
|
|
} |
364
|
|
|
|
365
|
|
|
public function __wakeup(): void |
366
|
|
|
{ |
367
|
|
|
if (!\is_string($this->string)) { |
|
|
|
|
368
|
|
|
throw new \BadMethodCallException('Cannot unserialize '.__CLASS__); |
369
|
|
|
} |
370
|
|
|
|
371
|
|
|
normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
372
|
|
|
} |
373
|
|
|
|
374
|
|
|
public function __clone() |
375
|
|
|
{ |
376
|
|
|
if (null === $this->ignoreCase) { |
377
|
|
|
normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
378
|
|
|
} |
379
|
|
|
|
380
|
|
|
$this->ignoreCase = false; |
381
|
|
|
} |
382
|
|
|
} |
383
|
|
|
|