UnicodeString.php 12.4 KB
Newer Older
冯超鹏's avatar
冯超鹏 committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373
<?php

/*
 * This file is part of the Symfony package.
 *
 * (c) Fabien Potencier <fabien@symfony.com>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

namespace Symfony\Component\String;

use Symfony\Component\String\Exception\ExceptionInterface;
use Symfony\Component\String\Exception\InvalidArgumentException;

/**
 * Represents a string of Unicode grapheme clusters encoded as UTF-8.
 *
 * A letter followed by combining characters (accents typically) form what Unicode defines
 * as a grapheme cluster: a character as humans mean it in written texts. This class knows
 * about the concept and won't split a letter apart from its combining accents. It also
 * ensures all string comparisons happen on their canonically-composed representation,
 * ignoring e.g. the order in which accents are listed when a letter has many of them.
 *
 * @see https://unicode.org/reports/tr15/
 *
 * @author Nicolas Grekas <p@tchwork.com>
 * @author Hugo Hamon <hugohamon@neuf.fr>
 *
 * @throws ExceptionInterface
 */
class UnicodeString extends AbstractUnicodeString
{
    public function __construct(string $string = '')
    {
        $this->string = normalizer_is_normalized($string) ? $string : normalizer_normalize($string);

        if (false === $this->string) {
            throw new InvalidArgumentException('Invalid UTF-8 string.');
        }
    }

    public function append(string ...$suffix): AbstractString
    {
        $str = clone $this;
        $str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix));
        normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

        if (false === $str->string) {
            throw new InvalidArgumentException('Invalid UTF-8 string.');
        }

        return $str;
    }

    public function chunk(int $length = 1): array
    {
        if (1 > $length) {
            throw new InvalidArgumentException('The chunk length must be greater than zero.');
        }

        if ('' === $this->string) {
            return [];
        }

        $rx = '/(';
        while (65535 < $length) {
            $rx .= '\X{65535}';
            $length -= 65535;
        }
        $rx .= '\X{'.$length.'})/u';

        $str = clone $this;
        $chunks = [];

        foreach (preg_split($rx, $this->string, -1, \PREG_SPLIT_DELIM_CAPTURE | \PREG_SPLIT_NO_EMPTY) as $chunk) {
            $str->string = $chunk;
            $chunks[] = clone $str;
        }

        return $chunks;
    }

    public function endsWith($suffix): bool
    {
        if ($suffix instanceof AbstractString) {
            $suffix = $suffix->string;
        } elseif (\is_array($suffix) || $suffix instanceof \Traversable) {
            return parent::endsWith($suffix);
        } else {
            $suffix = (string) $suffix;
        }

        $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
        normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form);

        if ('' === $suffix || false === $suffix) {
            return false;
        }

        if ($this->ignoreCase) {
            return 0 === mb_stripos(grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)), $suffix, 0, 'UTF-8');
        }

        return $suffix === grapheme_extract($this->string, \strlen($suffix), \GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix));
    }

    public function equalsTo($string): bool
    {
        if ($string instanceof AbstractString) {
            $string = $string->string;
        } elseif (\is_array($string) || $string instanceof \Traversable) {
            return parent::equalsTo($string);
        } else {
            $string = (string) $string;
        }

        $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
        normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form);

        if ('' !== $string && false !== $string && $this->ignoreCase) {
            return \strlen($string) === \strlen($this->string) && 0 === mb_stripos($this->string, $string, 0, 'UTF-8');
        }

        return $string === $this->string;
    }

    public function indexOf($needle, int $offset = 0): ?int
    {
        if ($needle instanceof AbstractString) {
            $needle = $needle->string;
        } elseif (\is_array($needle) || $needle instanceof \Traversable) {
            return parent::indexOf($needle, $offset);
        } else {
            $needle = (string) $needle;
        }

        $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
        normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form);

        if ('' === $needle || false === $needle) {
            return null;
        }

        try {
            $i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset);
        } catch (\ValueError $e) {
            return null;
        }

        return false === $i ? null : $i;
    }

    public function indexOfLast($needle, int $offset = 0): ?int
    {
        if ($needle instanceof AbstractString) {
            $needle = $needle->string;
        } elseif (\is_array($needle) || $needle instanceof \Traversable) {
            return parent::indexOfLast($needle, $offset);
        } else {
            $needle = (string) $needle;
        }

        $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
        normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form);

        if ('' === $needle || false === $needle) {
            return null;
        }

        $string = $this->string;

        if (0 > $offset) {
            // workaround https://bugs.php.net/74264
            if (0 > $offset += grapheme_strlen($needle)) {
                $string = grapheme_substr($string, 0, $offset);
            }
            $offset = 0;
        }

        $i = $this->ignoreCase ? grapheme_strripos($string, $needle, $offset) : grapheme_strrpos($string, $needle, $offset);

        return false === $i ? null : $i;
    }

    public function join(array $strings, string $lastGlue = null): AbstractString
    {
        $str = parent::join($strings, $lastGlue);
        normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

        return $str;
    }

    public function length(): int
    {
        return grapheme_strlen($this->string);
    }

    /**
     * @return static
     */
    public function normalize(int $form = self::NFC): parent
    {
        $str = clone $this;

        if (\in_array($form, [self::NFC, self::NFKC], true)) {
            normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form);
        } elseif (!\in_array($form, [self::NFD, self::NFKD], true)) {
            throw new InvalidArgumentException('Unsupported normalization form.');
        } elseif (!normalizer_is_normalized($str->string, $form)) {
            $str->string = normalizer_normalize($str->string, $form);
            $str->ignoreCase = null;
        }

        return $str;
    }

    public function prepend(string ...$prefix): AbstractString
    {
        $str = clone $this;
        $str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string;
        normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

        if (false === $str->string) {
            throw new InvalidArgumentException('Invalid UTF-8 string.');
        }

        return $str;
    }

    public function replace(string $from, string $to): AbstractString
    {
        $str = clone $this;
        normalizer_is_normalized($from) ?: $from = normalizer_normalize($from);

        if ('' !== $from && false !== $from) {
            $tail = $str->string;
            $result = '';
            $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos';

            while ('' !== $tail && false !== $i = $indexOf($tail, $from)) {
                $slice = grapheme_substr($tail, 0, $i);
                $result .= $slice.$to;
                $tail = substr($tail, \strlen($slice) + \strlen($from));
            }

            $str->string = $result.$tail;
            normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

            if (false === $str->string) {
                throw new InvalidArgumentException('Invalid UTF-8 string.');
            }
        }

        return $str;
    }

    public function replaceMatches(string $fromRegexp, $to): AbstractString
    {
        $str = parent::replaceMatches($fromRegexp, $to);
        normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

        return $str;
    }

    public function slice(int $start = 0, int $length = null): AbstractString
    {
        $str = clone $this;

        if (\PHP_VERSION_ID < 80000 && 0 > $start && grapheme_strlen($this->string) < -$start) {
            $start = 0;
        }
        $str->string = (string) grapheme_substr($this->string, $start, $length ?? 2147483647);

        return $str;
    }

    public function splice(string $replacement, int $start = 0, int $length = null): AbstractString
    {
        $str = clone $this;

        if (\PHP_VERSION_ID < 80000 && 0 > $start && grapheme_strlen($this->string) < -$start) {
            $start = 0;
        }
        $start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0;
        $length = $length ? \strlen(grapheme_substr($this->string, $start, $length ?? 2147483647)) : $length;
        $str->string = substr_replace($this->string, $replacement, $start, $length ?? 2147483647);
        normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string);

        if (false === $str->string) {
            throw new InvalidArgumentException('Invalid UTF-8 string.');
        }

        return $str;
    }

    public function split(string $delimiter, int $limit = null, int $flags = null): array
    {
        if (1 > $limit = $limit ?? 2147483647) {
            throw new InvalidArgumentException('Split limit must be a positive integer.');
        }

        if ('' === $delimiter) {
            throw new InvalidArgumentException('Split delimiter is empty.');
        }

        if (null !== $flags) {
            return parent::split($delimiter.'u', $limit, $flags);
        }

        normalizer_is_normalized($delimiter) ?: $delimiter = normalizer_normalize($delimiter);

        if (false === $delimiter) {
            throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.');
        }

        $str = clone $this;
        $tail = $this->string;
        $chunks = [];
        $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos';

        while (1 < $limit && false !== $i = $indexOf($tail, $delimiter)) {
            $str->string = grapheme_substr($tail, 0, $i);
            $chunks[] = clone $str;
            $tail = substr($tail, \strlen($str->string) + \strlen($delimiter));
            --$limit;
        }

        $str->string = $tail;
        $chunks[] = clone $str;

        return $chunks;
    }

    public function startsWith($prefix): bool
    {
        if ($prefix instanceof AbstractString) {
            $prefix = $prefix->string;
        } elseif (\is_array($prefix) || $prefix instanceof \Traversable) {
            return parent::startsWith($prefix);
        } else {
            $prefix = (string) $prefix;
        }

        $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC;
        normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form);

        if ('' === $prefix || false === $prefix) {
            return false;
        }

        if ($this->ignoreCase) {
            return 0 === mb_stripos(grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES), $prefix, 0, 'UTF-8');
        }

        return $prefix === grapheme_extract($this->string, \strlen($prefix), \GRAPHEME_EXTR_MAXBYTES);
    }

    public function __wakeup()
    {
        normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string);
    }

    public function __clone()
    {
        if (null === $this->ignoreCase) {
            normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string);
        }

        $this->ignoreCase = false;
    }
}