| Total Complexity | 104 |
| Total Lines | 327 |
| Duplicated Lines | 0 % |
| Changes | 0 | ||
Complex classes like UnicodeString often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use UnicodeString, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 33 | class UnicodeString extends AbstractUnicodeString |
||
| 34 | { |
||
| 35 | public function __construct(string $string = '') |
||
| 36 | { |
||
| 37 | $this->string = normalizer_is_normalized($string) ? $string : normalizer_normalize($string); |
||
| 38 | |||
| 39 | if (false === $this->string) { |
||
| 40 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
||
| 41 | } |
||
| 42 | } |
||
| 43 | |||
| 44 | public function append(string ...$suffix): AbstractString |
||
| 45 | { |
||
| 46 | $str = clone $this; |
||
| 47 | $str->string = $this->string.(1 >= \count($suffix) ? ($suffix[0] ?? '') : implode('', $suffix)); |
||
| 48 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 49 | |||
| 50 | if (false === $str->string) { |
||
| 51 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
||
| 52 | } |
||
| 53 | |||
| 54 | return $str; |
||
| 55 | } |
||
| 56 | |||
| 57 | public function chunk(int $length = 1): array |
||
| 58 | { |
||
| 59 | if (1 > $length) { |
||
| 60 | throw new InvalidArgumentException('The chunk length must be greater than zero.'); |
||
| 61 | } |
||
| 62 | |||
| 63 | if ('' === $this->string) { |
||
| 64 | return []; |
||
| 65 | } |
||
| 66 | |||
| 67 | $rx = '/('; |
||
| 68 | while (65535 < $length) { |
||
| 69 | $rx .= '\X{65535}'; |
||
| 70 | $length -= 65535; |
||
| 71 | } |
||
| 72 | $rx .= '\X{'.$length.'})/u'; |
||
| 73 | |||
| 74 | $str = clone $this; |
||
| 75 | $chunks = []; |
||
| 76 | |||
| 77 | foreach (preg_split($rx, $this->string, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY) as $chunk) { |
||
| 78 | $str->string = $chunk; |
||
| 79 | $chunks[] = clone $str; |
||
| 80 | } |
||
| 81 | |||
| 82 | return $chunks; |
||
| 83 | } |
||
| 84 | |||
| 85 | public function endsWith($suffix): bool |
||
| 86 | { |
||
| 87 | if ($suffix instanceof AbstractString) { |
||
| 88 | $suffix = $suffix->string; |
||
| 89 | } elseif (\is_array($suffix) || $suffix instanceof \Traversable) { |
||
| 90 | return parent::endsWith($suffix); |
||
| 91 | } else { |
||
| 92 | $suffix = (string) $suffix; |
||
| 93 | } |
||
| 94 | |||
| 95 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
||
| 96 | normalizer_is_normalized($suffix, $form) ?: $suffix = normalizer_normalize($suffix, $form); |
||
| 97 | |||
| 98 | if ('' === $suffix || false === $suffix) { |
||
| 99 | return false; |
||
| 100 | } |
||
| 101 | |||
| 102 | if ($this->ignoreCase) { |
||
| 103 | return 0 === mb_stripos(grapheme_extract($this->string, \strlen($suffix), GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)), $suffix, 0, 'UTF-8'); |
||
| 104 | } |
||
| 105 | |||
| 106 | return $suffix === grapheme_extract($this->string, \strlen($suffix), GRAPHEME_EXTR_MAXBYTES, \strlen($this->string) - \strlen($suffix)); |
||
| 107 | } |
||
| 108 | |||
| 109 | public function equalsTo($string): bool |
||
| 110 | { |
||
| 111 | if ($string instanceof AbstractString) { |
||
| 112 | $string = $string->string; |
||
| 113 | } elseif (\is_array($string) || $string instanceof \Traversable) { |
||
| 114 | return parent::equalsTo($string); |
||
| 115 | } else { |
||
| 116 | $string = (string) $string; |
||
| 117 | } |
||
| 118 | |||
| 119 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
||
| 120 | normalizer_is_normalized($string, $form) ?: $string = normalizer_normalize($string, $form); |
||
| 121 | |||
| 122 | if ('' !== $string && false !== $string && $this->ignoreCase) { |
||
| 123 | return \strlen($string) === \strlen($this->string) && 0 === mb_stripos($this->string, $string, 0, 'UTF-8'); |
||
| 124 | } |
||
| 125 | |||
| 126 | return $string === $this->string; |
||
| 127 | } |
||
| 128 | |||
| 129 | public function indexOf($needle, int $offset = 0): ?int |
||
| 130 | { |
||
| 131 | if ($needle instanceof AbstractString) { |
||
| 132 | $needle = $needle->string; |
||
| 133 | } elseif (\is_array($needle) || $needle instanceof \Traversable) { |
||
| 134 | return parent::indexOf($needle, $offset); |
||
| 135 | } else { |
||
| 136 | $needle = (string) $needle; |
||
| 137 | } |
||
| 138 | |||
| 139 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
||
| 140 | normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
||
| 141 | |||
| 142 | if ('' === $needle || false === $needle) { |
||
| 143 | return null; |
||
| 144 | } |
||
| 145 | |||
| 146 | $i = $this->ignoreCase ? grapheme_stripos($this->string, $needle, $offset) : grapheme_strpos($this->string, $needle, $offset); |
||
| 147 | |||
| 148 | return false === $i ? null : $i; |
||
| 149 | } |
||
| 150 | |||
| 151 | public function indexOfLast($needle, int $offset = 0): ?int |
||
| 152 | { |
||
| 153 | if ($needle instanceof AbstractString) { |
||
| 154 | $needle = $needle->string; |
||
| 155 | } elseif (\is_array($needle) || $needle instanceof \Traversable) { |
||
| 156 | return parent::indexOfLast($needle, $offset); |
||
| 157 | } else { |
||
| 158 | $needle = (string) $needle; |
||
| 159 | } |
||
| 160 | |||
| 161 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
||
| 162 | normalizer_is_normalized($needle, $form) ?: $needle = normalizer_normalize($needle, $form); |
||
| 163 | |||
| 164 | if ('' === $needle || false === $needle) { |
||
| 165 | return null; |
||
| 166 | } |
||
| 167 | |||
| 168 | $string = $this->string; |
||
| 169 | |||
| 170 | if (0 > $offset) { |
||
| 171 | // workaround https://bugs.php.net/74264 |
||
| 172 | if (0 > $offset += grapheme_strlen($needle)) { |
||
| 173 | $string = grapheme_substr($string, 0, $offset); |
||
| 174 | } |
||
| 175 | $offset = 0; |
||
| 176 | } |
||
| 177 | |||
| 178 | $i = $this->ignoreCase ? grapheme_strripos($string, $needle, $offset) : grapheme_strrpos($string, $needle, $offset); |
||
| 179 | |||
| 180 | return false === $i ? null : $i; |
||
| 181 | } |
||
| 182 | |||
| 183 | public function join(array $strings, string $lastGlue = null): AbstractString |
||
| 184 | { |
||
| 185 | $str = parent::join($strings, $lastGlue); |
||
| 186 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 187 | |||
| 188 | return $str; |
||
| 189 | } |
||
| 190 | |||
| 191 | public function length(): int |
||
| 192 | { |
||
| 193 | return grapheme_strlen($this->string); |
||
| 194 | } |
||
| 195 | |||
| 196 | /** |
||
| 197 | * @return static |
||
| 198 | */ |
||
| 199 | public function normalize(int $form = self::NFC): parent |
||
| 200 | { |
||
| 201 | $str = clone $this; |
||
| 202 | |||
| 203 | if (\in_array($form, [self::NFC, self::NFKC], true)) { |
||
| 204 | normalizer_is_normalized($str->string, $form) ?: $str->string = normalizer_normalize($str->string, $form); |
||
| 205 | } elseif (!\in_array($form, [self::NFD, self::NFKD], true)) { |
||
| 206 | throw new InvalidArgumentException('Unsupported normalization form.'); |
||
| 207 | } elseif (!normalizer_is_normalized($str->string, $form)) { |
||
| 208 | $str->string = normalizer_normalize($str->string, $form); |
||
| 209 | $str->ignoreCase = null; |
||
| 210 | } |
||
| 211 | |||
| 212 | return $str; |
||
| 213 | } |
||
| 214 | |||
| 215 | public function prepend(string ...$prefix): AbstractString |
||
| 216 | { |
||
| 217 | $str = clone $this; |
||
| 218 | $str->string = (1 >= \count($prefix) ? ($prefix[0] ?? '') : implode('', $prefix)).$this->string; |
||
| 219 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 220 | |||
| 221 | if (false === $str->string) { |
||
| 222 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
||
| 223 | } |
||
| 224 | |||
| 225 | return $str; |
||
| 226 | } |
||
| 227 | |||
| 228 | public function replace(string $from, string $to): AbstractString |
||
| 229 | { |
||
| 230 | $str = clone $this; |
||
| 231 | normalizer_is_normalized($from) ?: $from = normalizer_normalize($from); |
||
| 232 | |||
| 233 | if ('' !== $from && false !== $from) { |
||
| 234 | $tail = $str->string; |
||
| 235 | $result = ''; |
||
| 236 | $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
||
| 237 | |||
| 238 | while (false !== $i = $indexOf($tail, $from)) { |
||
| 239 | $slice = grapheme_substr($tail, 0, $i); |
||
| 240 | $result .= $slice.$to; |
||
| 241 | $tail = substr($tail, \strlen($slice) + \strlen($from)); |
||
| 242 | } |
||
| 243 | |||
| 244 | $str->string = $result.$tail; |
||
| 245 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 246 | |||
| 247 | if (false === $str->string) { |
||
| 248 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
||
| 249 | } |
||
| 250 | } |
||
| 251 | |||
| 252 | return $str; |
||
| 253 | } |
||
| 254 | |||
| 255 | public function replaceMatches(string $fromRegexp, $to): AbstractString |
||
| 256 | { |
||
| 257 | $str = parent::replaceMatches($fromRegexp, $to); |
||
| 258 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 259 | |||
| 260 | return $str; |
||
| 261 | } |
||
| 262 | |||
| 263 | public function slice(int $start = 0, int $length = null): AbstractString |
||
| 264 | { |
||
| 265 | $str = clone $this; |
||
| 266 | $str->string = (string) grapheme_substr($this->string, $start, $length ?? \PHP_INT_MAX); |
||
| 267 | |||
| 268 | return $str; |
||
| 269 | } |
||
| 270 | |||
| 271 | public function splice(string $replacement, int $start = 0, int $length = null): AbstractString |
||
| 272 | { |
||
| 273 | $str = clone $this; |
||
| 274 | $start = $start ? \strlen(grapheme_substr($this->string, 0, $start)) : 0; |
||
| 275 | $length = $length ? \strlen(grapheme_substr($this->string, $start, $length ?? \PHP_INT_MAX)) : $length; |
||
| 276 | $str->string = substr_replace($this->string, $replacement, $start, $length ?? \PHP_INT_MAX); |
||
| 277 | normalizer_is_normalized($str->string) ?: $str->string = normalizer_normalize($str->string); |
||
| 278 | |||
| 279 | if (false === $str->string) { |
||
| 280 | throw new InvalidArgumentException('Invalid UTF-8 string.'); |
||
| 281 | } |
||
| 282 | |||
| 283 | return $str; |
||
| 284 | } |
||
| 285 | |||
| 286 | public function split(string $delimiter, int $limit = null, int $flags = null): array |
||
| 287 | { |
||
| 288 | if (1 > $limit = $limit ?? \PHP_INT_MAX) { |
||
| 289 | throw new InvalidArgumentException('Split limit must be a positive integer.'); |
||
| 290 | } |
||
| 291 | |||
| 292 | if ('' === $delimiter) { |
||
| 293 | throw new InvalidArgumentException('Split delimiter is empty.'); |
||
| 294 | } |
||
| 295 | |||
| 296 | if (null !== $flags) { |
||
| 297 | return parent::split($delimiter.'u', $limit, $flags); |
||
| 298 | } |
||
| 299 | |||
| 300 | normalizer_is_normalized($delimiter) ?: $delimiter = normalizer_normalize($delimiter); |
||
| 301 | |||
| 302 | if (false === $delimiter) { |
||
| 303 | throw new InvalidArgumentException('Split delimiter is not a valid UTF-8 string.'); |
||
| 304 | } |
||
| 305 | |||
| 306 | $str = clone $this; |
||
| 307 | $tail = $this->string; |
||
| 308 | $chunks = []; |
||
| 309 | $indexOf = $this->ignoreCase ? 'grapheme_stripos' : 'grapheme_strpos'; |
||
| 310 | |||
| 311 | while (1 < $limit && false !== $i = $indexOf($tail, $delimiter)) { |
||
| 312 | $str->string = grapheme_substr($tail, 0, $i); |
||
| 313 | $chunks[] = clone $str; |
||
| 314 | $tail = substr($tail, \strlen($str->string) + \strlen($delimiter)); |
||
| 315 | --$limit; |
||
| 316 | } |
||
| 317 | |||
| 318 | $str->string = $tail; |
||
| 319 | $chunks[] = clone $str; |
||
| 320 | |||
| 321 | return $chunks; |
||
| 322 | } |
||
| 323 | |||
| 324 | public function startsWith($prefix): bool |
||
| 325 | { |
||
| 326 | if ($prefix instanceof AbstractString) { |
||
| 327 | $prefix = $prefix->string; |
||
| 328 | } elseif (\is_array($prefix) || $prefix instanceof \Traversable) { |
||
| 329 | return parent::startsWith($prefix); |
||
| 330 | } else { |
||
| 331 | $prefix = (string) $prefix; |
||
| 332 | } |
||
| 333 | |||
| 334 | $form = null === $this->ignoreCase ? \Normalizer::NFD : \Normalizer::NFC; |
||
| 335 | normalizer_is_normalized($prefix, $form) ?: $prefix = normalizer_normalize($prefix, $form); |
||
| 336 | |||
| 337 | if ('' === $prefix || false === $prefix) { |
||
| 338 | return false; |
||
| 339 | } |
||
| 340 | |||
| 341 | if ($this->ignoreCase) { |
||
| 342 | return 0 === mb_stripos(grapheme_extract($this->string, \strlen($prefix), GRAPHEME_EXTR_MAXBYTES), $prefix, 0, 'UTF-8'); |
||
| 343 | } |
||
| 344 | |||
| 345 | return $prefix === grapheme_extract($this->string, \strlen($prefix), GRAPHEME_EXTR_MAXBYTES); |
||
| 346 | } |
||
| 347 | |||
| 348 | public function __wakeup() |
||
| 349 | { |
||
| 350 | normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
||
| 351 | } |
||
| 352 | |||
| 353 | public function __clone() |
||
| 354 | { |
||
| 355 | if (null === $this->ignoreCase) { |
||
| 356 | normalizer_is_normalized($this->string) ?: $this->string = normalizer_normalize($this->string); |
||
| 357 | } |
||
| 358 | |||
| 359 | $this->ignoreCase = false; |
||
| 360 | } |
||
| 362 |