| 148 |
lars |
1 |
<?php
|
|
|
2 |
|
|
|
3 |
/*
|
|
|
4 |
* This file is part of the Symfony package.
|
|
|
5 |
*
|
|
|
6 |
* (c) Fabien Potencier <fabien@symfony.com>
|
|
|
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 |
use Symfony\Component\String\Exception\RuntimeException;
|
|
|
17 |
|
|
|
18 |
/**
|
|
|
19 |
* Represents a binary-safe string of bytes.
|
|
|
20 |
*
|
|
|
21 |
* @author Nicolas Grekas <p@tchwork.com>
|
|
|
22 |
* @author Hugo Hamon <hugohamon@neuf.fr>
|
|
|
23 |
*
|
|
|
24 |
* @throws ExceptionInterface
|
|
|
25 |
*/
|
|
|
26 |
class ByteString extends AbstractString
|
|
|
27 |
{
|
|
|
28 |
private const ALPHABET_ALPHANUMERIC = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz';
|
|
|
29 |
|
|
|
30 |
public function __construct(string $string = '')
|
|
|
31 |
{
|
|
|
32 |
$this->string = $string;
|
|
|
33 |
}
|
|
|
34 |
|
|
|
35 |
/*
|
|
|
36 |
* The following method was derived from code of the Hack Standard Library (v4.40 - 2020-05-03)
|
|
|
37 |
*
|
|
|
38 |
* https://github.com/hhvm/hsl/blob/80a42c02f036f72a42f0415e80d6b847f4bf62d5/src/random/private.php#L16
|
|
|
39 |
*
|
|
|
40 |
* Code subject to the MIT license (https://github.com/hhvm/hsl/blob/master/LICENSE).
|
|
|
41 |
*
|
|
|
42 |
* Copyright (c) 2004-2020, Facebook, Inc. (https://www.facebook.com/)
|
|
|
43 |
*/
|
|
|
44 |
|
|
|
45 |
public static function fromRandom(int $length = 16, string $alphabet = null): self
|
|
|
46 |
{
|
|
|
47 |
if ($length <= 0) {
|
|
|
48 |
throw new InvalidArgumentException(sprintf('A strictly positive length is expected, "%d" given.', $length));
|
|
|
49 |
}
|
|
|
50 |
|
|
|
51 |
$alphabet ??= self::ALPHABET_ALPHANUMERIC;
|
|
|
52 |
$alphabetSize = \strlen($alphabet);
|
|
|
53 |
$bits = (int) ceil(log($alphabetSize, 2.0));
|
|
|
54 |
if ($bits <= 0 || $bits > 56) {
|
|
|
55 |
throw new InvalidArgumentException('The length of the alphabet must in the [2^1, 2^56] range.');
|
|
|
56 |
}
|
|
|
57 |
|
|
|
58 |
$ret = '';
|
|
|
59 |
while ($length > 0) {
|
|
|
60 |
$urandomLength = (int) ceil(2 * $length * $bits / 8.0);
|
|
|
61 |
$data = random_bytes($urandomLength);
|
|
|
62 |
$unpackedData = 0;
|
|
|
63 |
$unpackedBits = 0;
|
|
|
64 |
for ($i = 0; $i < $urandomLength && $length > 0; ++$i) {
|
|
|
65 |
// Unpack 8 bits
|
|
|
66 |
$unpackedData = ($unpackedData << 8) | \ord($data[$i]);
|
|
|
67 |
$unpackedBits += 8;
|
|
|
68 |
|
|
|
69 |
// While we have enough bits to select a character from the alphabet, keep
|
|
|
70 |
// consuming the random data
|
|
|
71 |
for (; $unpackedBits >= $bits && $length > 0; $unpackedBits -= $bits) {
|
|
|
72 |
$index = ($unpackedData & ((1 << $bits) - 1));
|
|
|
73 |
$unpackedData >>= $bits;
|
|
|
74 |
// Unfortunately, the alphabet size is not necessarily a power of two.
|
|
|
75 |
// Worst case, it is 2^k + 1, which means we need (k+1) bits and we
|
|
|
76 |
// have around a 50% chance of missing as k gets larger
|
|
|
77 |
if ($index < $alphabetSize) {
|
|
|
78 |
$ret .= $alphabet[$index];
|
|
|
79 |
--$length;
|
|
|
80 |
}
|
|
|
81 |
}
|
|
|
82 |
}
|
|
|
83 |
}
|
|
|
84 |
|
|
|
85 |
return new static($ret);
|
|
|
86 |
}
|
|
|
87 |
|
|
|
88 |
public function bytesAt(int $offset): array
|
|
|
89 |
{
|
|
|
90 |
$str = $this->string[$offset] ?? '';
|
|
|
91 |
|
|
|
92 |
return '' === $str ? [] : [\ord($str)];
|
|
|
93 |
}
|
|
|
94 |
|
|
|
95 |
public function append(string ...$suffix): static
|
|
|
96 |
{
|
|
|
97 |
$str = clone $this;
|
|
|
98 |
$str->string .= 1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix);
|
|
|
99 |
|
|
|
100 |
return $str;
|
|
|
101 |
}
|
|
|
102 |
|
|
|
103 |
public function camel(): static
|
|
|
104 |
{
|
|
|
105 |
$str = clone $this;
|
|
|
106 |
|
|
|
107 |
$parts = explode(' ', trim(ucwords(preg_replace('/[^a-zA-Z0-9\x7f-\xff]++/', ' ', $this->string))));
|
|
|
108 |
$parts[0] = 1 !== \strlen($parts[0]) && ctype_upper($parts[0]) ? $parts[0] : lcfirst($parts[0]);
|
|
|
109 |
$str->string = implode('', $parts);
|
|
|
110 |
|
|
|
111 |
return $str;
|
|
|
112 |
}
|
|
|
113 |
|
|
|
114 |
public function chunk(int $length = 1): array
|
|
|
115 |
{
|
|
|
116 |
if (1 > $length) {
|
|
|
117 |
throw new InvalidArgumentException('The chunk length must be greater than zero.');
|
|
|
118 |
}
|
|
|
119 |
|
|
|
120 |
if ('' === $this->string) {
|
|
|
121 |
return [];
|
|
|
122 |
}
|
|
|
123 |
|
|
|
124 |
$str = clone $this;
|
|
|
125 |
$chunks = [];
|
|
|
126 |
|
|
|
127 |
foreach (str_split($this->string, $length) as $chunk) {
|
|
|
128 |
$str->string = $chunk;
|
|
|
129 |
$chunks[] = clone $str;
|
|
|
130 |
}
|
|
|
131 |
|
|
|
132 |
return $chunks;
|
|
|
133 |
}
|
|
|
134 |
|
|
|
135 |
public function endsWith(string|iterable|AbstractString $suffix): bool
|
|
|
136 |
{
|
|
|
137 |
if ($suffix instanceof AbstractString) {
|
|
|
138 |
$suffix = $suffix->string;
|
|
|
139 |
} elseif (!\is_string($suffix)) {
|
|
|
140 |
return parent::endsWith($suffix);
|
|
|
141 |
}
|
|
|
142 |
|
|
|
143 |
return '' !== $suffix && \strlen($this->string) >= \strlen($suffix) && 0 === substr_compare($this->string, $suffix, -\strlen($suffix), null, $this->ignoreCase);
|
|
|
144 |
}
|
|
|
145 |
|
|
|
146 |
public function equalsTo(string|iterable|AbstractString $string): bool
|
|
|
147 |
{
|
|
|
148 |
if ($string instanceof AbstractString) {
|
|
|
149 |
$string = $string->string;
|
|
|
150 |
} elseif (!\is_string($string)) {
|
|
|
151 |
return parent::equalsTo($string);
|
|
|
152 |
}
|
|
|
153 |
|
|
|
154 |
if ('' !== $string && $this->ignoreCase) {
|
|
|
155 |
return 0 === strcasecmp($string, $this->string);
|
|
|
156 |
}
|
|
|
157 |
|
|
|
158 |
return $string === $this->string;
|
|
|
159 |
}
|
|
|
160 |
|
|
|
161 |
public function folded(): static
|
|
|
162 |
{
|
|
|
163 |
$str = clone $this;
|
|
|
164 |
$str->string = strtolower($str->string);
|
|
|
165 |
|
|
|
166 |
return $str;
|
|
|
167 |
}
|
|
|
168 |
|
|
|
169 |
public function indexOf(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
|
|
170 |
{
|
|
|
171 |
if ($needle instanceof AbstractString) {
|
|
|
172 |
$needle = $needle->string;
|
|
|
173 |
} elseif (!\is_string($needle)) {
|
|
|
174 |
return parent::indexOf($needle, $offset);
|
|
|
175 |
}
|
|
|
176 |
|
|
|
177 |
if ('' === $needle) {
|
|
|
178 |
return null;
|
|
|
179 |
}
|
|
|
180 |
|
|
|
181 |
$i = $this->ignoreCase ? stripos($this->string, $needle, $offset) : strpos($this->string, $needle, $offset);
|
|
|
182 |
|
|
|
183 |
return false === $i ? null : $i;
|
|
|
184 |
}
|
|
|
185 |
|
|
|
186 |
public function indexOfLast(string|iterable|AbstractString $needle, int $offset = 0): ?int
|
|
|
187 |
{
|
|
|
188 |
if ($needle instanceof AbstractString) {
|
|
|
189 |
$needle = $needle->string;
|
|
|
190 |
} elseif (!\is_string($needle)) {
|
|
|
191 |
return parent::indexOfLast($needle, $offset);
|
|
|
192 |
}
|
|
|
193 |
|
|
|
194 |
if ('' === $needle) {
|
|
|
195 |
return null;
|
|
|
196 |
}
|
|
|
197 |
|
|
|
198 |
$i = $this->ignoreCase ? strripos($this->string, $needle, $offset) : strrpos($this->string, $needle, $offset);
|
|
|
199 |
|
|
|
200 |
return false === $i ? null : $i;
|
|
|
201 |
}
|
|
|
202 |
|
|
|
203 |
public function isUtf8(): bool
|
|
|
204 |
{
|
|
|
205 |
return '' === $this->string || preg_match('//u', $this->string);
|
|
|
206 |
}
|
|
|
207 |
|
|
|
208 |
public function join(array $strings, string $lastGlue = null): static
|
|
|
209 |
{
|
|
|
210 |
$str = clone $this;
|
|
|
211 |
|
|
|
212 |
$tail = null !== $lastGlue && 1 < \count($strings) ? $lastGlue.array_pop($strings) : '';
|
|
|
213 |
$str->string = implode($this->string, $strings).$tail;
|
|
|
214 |
|
|
|
215 |
return $str;
|
|
|
216 |
}
|
|
|
217 |
|
|
|
218 |
public function length(): int
|
|
|
219 |
{
|
|
|
220 |
return \strlen($this->string);
|
|
|
221 |
}
|
|
|
222 |
|
|
|
223 |
public function lower(): static
|
|
|
224 |
{
|
|
|
225 |
$str = clone $this;
|
|
|
226 |
$str->string = strtolower($str->string);
|
|
|
227 |
|
|
|
228 |
return $str;
|
|
|
229 |
}
|
|
|
230 |
|
|
|
231 |
public function match(string $regexp, int $flags = 0, int $offset = 0): array
|
|
|
232 |
{
|
|
|
233 |
$match = ((\PREG_PATTERN_ORDER | \PREG_SET_ORDER) & $flags) ? 'preg_match_all' : 'preg_match';
|
|
|
234 |
|
|
|
235 |
if ($this->ignoreCase) {
|
|
|
236 |
$regexp .= 'i';
|
|
|
237 |
}
|
|
|
238 |
|
|
|
239 |
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
|
|
240 |
|
|
|
241 |
try {
|
|
|
242 |
if (false === $match($regexp, $this->string, $matches, $flags | \PREG_UNMATCHED_AS_NULL, $offset)) {
|
|
|
243 |
throw new RuntimeException('Matching failed with error: '.preg_last_error_msg());
|
|
|
244 |
}
|
|
|
245 |
} finally {
|
|
|
246 |
restore_error_handler();
|
|
|
247 |
}
|
|
|
248 |
|
|
|
249 |
return $matches;
|
|
|
250 |
}
|
|
|
251 |
|
|
|
252 |
public function padBoth(int $length, string $padStr = ' '): static
|
|
|
253 |
{
|
|
|
254 |
$str = clone $this;
|
|
|
255 |
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_BOTH);
|
|
|
256 |
|
|
|
257 |
return $str;
|
|
|
258 |
}
|
|
|
259 |
|
|
|
260 |
public function padEnd(int $length, string $padStr = ' '): static
|
|
|
261 |
{
|
|
|
262 |
$str = clone $this;
|
|
|
263 |
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_RIGHT);
|
|
|
264 |
|
|
|
265 |
return $str;
|
|
|
266 |
}
|
|
|
267 |
|
|
|
268 |
public function padStart(int $length, string $padStr = ' '): static
|
|
|
269 |
{
|
|
|
270 |
$str = clone $this;
|
|
|
271 |
$str->string = str_pad($this->string, $length, $padStr, \STR_PAD_LEFT);
|
|
|
272 |
|
|
|
273 |
return $str;
|
|
|
274 |
}
|
|
|
275 |
|
|
|
276 |
public function prepend(string ...$prefix): static
|
|
|
277 |
{
|
|
|
278 |
$str = clone $this;
|
|
|
279 |
$str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$str->string;
|
|
|
280 |
|
|
|
281 |
return $str;
|
|
|
282 |
}
|
|
|
283 |
|
|
|
284 |
public function replace(string $from, string $to): static
|
|
|
285 |
{
|
|
|
286 |
$str = clone $this;
|
|
|
287 |
|
|
|
288 |
if ('' !== $from) {
|
|
|
289 |
$str->string = $this->ignoreCase ? str_ireplace($from, $to, $this->string) : str_replace($from, $to, $this->string);
|
|
|
290 |
}
|
|
|
291 |
|
|
|
292 |
return $str;
|
|
|
293 |
}
|
|
|
294 |
|
|
|
295 |
public function replaceMatches(string $fromRegexp, string|callable $to): static
|
|
|
296 |
{
|
|
|
297 |
if ($this->ignoreCase) {
|
|
|
298 |
$fromRegexp .= 'i';
|
|
|
299 |
}
|
|
|
300 |
|
|
|
301 |
$replace = \is_array($to) || $to instanceof \Closure ? 'preg_replace_callback' : 'preg_replace';
|
|
|
302 |
|
|
|
303 |
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
|
|
304 |
|
|
|
305 |
try {
|
|
|
306 |
if (null === $string = $replace($fromRegexp, $to, $this->string)) {
|
|
|
307 |
$lastError = preg_last_error();
|
|
|
308 |
|
|
|
309 |
foreach (get_defined_constants(true)['pcre'] as $k => $v) {
|
|
|
310 |
if ($lastError === $v && str_ends_with($k, '_ERROR')) {
|
|
|
311 |
throw new RuntimeException('Matching failed with '.$k.'.');
|
|
|
312 |
}
|
|
|
313 |
}
|
|
|
314 |
|
|
|
315 |
throw new RuntimeException('Matching failed with unknown error code.');
|
|
|
316 |
}
|
|
|
317 |
} finally {
|
|
|
318 |
restore_error_handler();
|
|
|
319 |
}
|
|
|
320 |
|
|
|
321 |
$str = clone $this;
|
|
|
322 |
$str->string = $string;
|
|
|
323 |
|
|
|
324 |
return $str;
|
|
|
325 |
}
|
|
|
326 |
|
|
|
327 |
public function reverse(): static
|
|
|
328 |
{
|
|
|
329 |
$str = clone $this;
|
|
|
330 |
$str->string = strrev($str->string);
|
|
|
331 |
|
|
|
332 |
return $str;
|
|
|
333 |
}
|
|
|
334 |
|
|
|
335 |
public function slice(int $start = 0, int $length = null): static
|
|
|
336 |
{
|
|
|
337 |
$str = clone $this;
|
|
|
338 |
$str->string = (string) substr($this->string, $start, $length ?? \PHP_INT_MAX);
|
|
|
339 |
|
|
|
340 |
return $str;
|
|
|
341 |
}
|
|
|
342 |
|
|
|
343 |
public function snake(): static
|
|
|
344 |
{
|
|
|
345 |
$str = $this->camel();
|
|
|
346 |
$str->string = strtolower(preg_replace(['/([A-Z]+)([A-Z][a-z])/', '/([a-z\d])([A-Z])/'], '\1_\2', $str->string));
|
|
|
347 |
|
|
|
348 |
return $str;
|
|
|
349 |
}
|
|
|
350 |
|
|
|
351 |
public function splice(string $replacement, int $start = 0, int $length = null): static
|
|
|
352 |
{
|
|
|
353 |
$str = clone $this;
|
|
|
354 |
$str->string = substr_replace($this->string, $replacement, $start, $length ?? \PHP_INT_MAX);
|
|
|
355 |
|
|
|
356 |
return $str;
|
|
|
357 |
}
|
|
|
358 |
|
|
|
359 |
public function split(string $delimiter, int $limit = null, int $flags = null): array
|
|
|
360 |
{
|
|
|
361 |
if (1 > $limit ??= \PHP_INT_MAX) {
|
|
|
362 |
throw new InvalidArgumentException('Split limit must be a positive integer.');
|
|
|
363 |
}
|
|
|
364 |
|
|
|
365 |
if ('' === $delimiter) {
|
|
|
366 |
throw new InvalidArgumentException('Split delimiter is empty.');
|
|
|
367 |
}
|
|
|
368 |
|
|
|
369 |
if (null !== $flags) {
|
|
|
370 |
return parent::split($delimiter, $limit, $flags);
|
|
|
371 |
}
|
|
|
372 |
|
|
|
373 |
$str = clone $this;
|
|
|
374 |
$chunks = $this->ignoreCase
|
|
|
375 |
? preg_split('{'.preg_quote($delimiter).'}iD', $this->string, $limit)
|
|
|
376 |
: explode($delimiter, $this->string, $limit);
|
|
|
377 |
|
|
|
378 |
foreach ($chunks as &$chunk) {
|
|
|
379 |
$str->string = $chunk;
|
|
|
380 |
$chunk = clone $str;
|
|
|
381 |
}
|
|
|
382 |
|
|
|
383 |
return $chunks;
|
|
|
384 |
}
|
|
|
385 |
|
|
|
386 |
public function startsWith(string|iterable|AbstractString $prefix): bool
|
|
|
387 |
{
|
|
|
388 |
if ($prefix instanceof AbstractString) {
|
|
|
389 |
$prefix = $prefix->string;
|
|
|
390 |
} elseif (!\is_string($prefix)) {
|
|
|
391 |
return parent::startsWith($prefix);
|
|
|
392 |
}
|
|
|
393 |
|
|
|
394 |
return '' !== $prefix && 0 === ($this->ignoreCase ? strncasecmp($this->string, $prefix, \strlen($prefix)) : strncmp($this->string, $prefix, \strlen($prefix)));
|
|
|
395 |
}
|
|
|
396 |
|
|
|
397 |
public function title(bool $allWords = false): static
|
|
|
398 |
{
|
|
|
399 |
$str = clone $this;
|
|
|
400 |
$str->string = $allWords ? ucwords($str->string) : ucfirst($str->string);
|
|
|
401 |
|
|
|
402 |
return $str;
|
|
|
403 |
}
|
|
|
404 |
|
|
|
405 |
public function toUnicodeString(string $fromEncoding = null): UnicodeString
|
|
|
406 |
{
|
|
|
407 |
return new UnicodeString($this->toCodePointString($fromEncoding)->string);
|
|
|
408 |
}
|
|
|
409 |
|
|
|
410 |
public function toCodePointString(string $fromEncoding = null): CodePointString
|
|
|
411 |
{
|
|
|
412 |
$u = new CodePointString();
|
|
|
413 |
|
|
|
414 |
if (\in_array($fromEncoding, [null, 'utf8', 'utf-8', 'UTF8', 'UTF-8'], true) && preg_match('//u', $this->string)) {
|
|
|
415 |
$u->string = $this->string;
|
|
|
416 |
|
|
|
417 |
return $u;
|
|
|
418 |
}
|
|
|
419 |
|
|
|
420 |
set_error_handler(static function ($t, $m) { throw new InvalidArgumentException($m); });
|
|
|
421 |
|
|
|
422 |
try {
|
|
|
423 |
try {
|
|
|
424 |
$validEncoding = false !== mb_detect_encoding($this->string, $fromEncoding ?? 'Windows-1252', true);
|
|
|
425 |
} catch (InvalidArgumentException $e) {
|
|
|
426 |
if (!\function_exists('iconv')) {
|
|
|
427 |
throw $e;
|
|
|
428 |
}
|
|
|
429 |
|
|
|
430 |
$u->string = iconv($fromEncoding ?? 'Windows-1252', 'UTF-8', $this->string);
|
|
|
431 |
|
|
|
432 |
return $u;
|
|
|
433 |
}
|
|
|
434 |
} finally {
|
|
|
435 |
restore_error_handler();
|
|
|
436 |
}
|
|
|
437 |
|
|
|
438 |
if (!$validEncoding) {
|
|
|
439 |
throw new InvalidArgumentException(sprintf('Invalid "%s" string.', $fromEncoding ?? 'Windows-1252'));
|
|
|
440 |
}
|
|
|
441 |
|
|
|
442 |
$u->string = mb_convert_encoding($this->string, 'UTF-8', $fromEncoding ?? 'Windows-1252');
|
|
|
443 |
|
|
|
444 |
return $u;
|
|
|
445 |
}
|
|
|
446 |
|
|
|
447 |
public function trim(string $chars = " \t\n\r\0\x0B\x0C"): static
|
|
|
448 |
{
|
|
|
449 |
$str = clone $this;
|
|
|
450 |
$str->string = trim($str->string, $chars);
|
|
|
451 |
|
|
|
452 |
return $str;
|
|
|
453 |
}
|
|
|
454 |
|
|
|
455 |
public function trimEnd(string $chars = " \t\n\r\0\x0B\x0C"): static
|
|
|
456 |
{
|
|
|
457 |
$str = clone $this;
|
|
|
458 |
$str->string = rtrim($str->string, $chars);
|
|
|
459 |
|
|
|
460 |
return $str;
|
|
|
461 |
}
|
|
|
462 |
|
|
|
463 |
public function trimStart(string $chars = " \t\n\r\0\x0B\x0C"): static
|
|
|
464 |
{
|
|
|
465 |
$str = clone $this;
|
|
|
466 |
$str->string = ltrim($str->string, $chars);
|
|
|
467 |
|
|
|
468 |
return $str;
|
|
|
469 |
}
|
|
|
470 |
|
|
|
471 |
public function upper(): static
|
|
|
472 |
{
|
|
|
473 |
$str = clone $this;
|
|
|
474 |
$str->string = strtoupper($str->string);
|
|
|
475 |
|
|
|
476 |
return $str;
|
|
|
477 |
}
|
|
|
478 |
|
|
|
479 |
public function width(bool $ignoreAnsiDecoration = true): int
|
|
|
480 |
{
|
|
|
481 |
$string = preg_match('//u', $this->string) ? $this->string : preg_replace('/[\x80-\xFF]/', '?', $this->string);
|
|
|
482 |
|
|
|
483 |
return (new CodePointString($string))->width($ignoreAnsiDecoration);
|
|
|
484 |
}
|
|
|
485 |
}
|