Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
92.47% |
135 / 146 |
|
81.82% |
9 / 11 |
CRAP | |
0.00% |
0 / 1 |
| StringUtils | |
92.47% |
135 / 146 |
|
81.82% |
9 / 11 |
85.95 | |
0.00% |
0 / 1 |
| __construct | n/a |
0 / 0 |
n/a |
0 / 0 |
1 | |||||
| contains | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
3 | |||
| endsWith | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
6 | |||
| startsWith | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
5 | |||
| countCharacterFromStart | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
3 | |||
| entropy | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| stringify | |
95.45% |
21 / 22 |
|
0.00% |
0 / 1 |
18 | |||
| createDiffMarkup | |
100.00% |
34 / 34 |
|
100.00% |
1 / 1 |
21 | |||
| computeLCSDiff | |
100.00% |
34 / 34 |
|
100.00% |
1 / 1 |
12 | |||
| intHash | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| isShellSafe | |
100.00% |
9 / 9 |
|
100.00% |
1 / 1 |
6 | |||
| intToAlphabet | |
0.00% |
0 / 10 |
|
0.00% |
0 / 1 |
20 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * Jingga |
| 4 | * |
| 5 | * PHP Version 8.1 |
| 6 | * |
| 7 | * @package phpOMS\Utils |
| 8 | * @copyright Dennis Eichhorn |
| 9 | * @license OMS License 2.0 |
| 10 | * @version 1.0.0 |
| 11 | * @link https://jingga.app |
| 12 | */ |
| 13 | declare(strict_types=1); |
| 14 | |
| 15 | namespace phpOMS\Utils; |
| 16 | |
| 17 | use phpOMS\Contract\RenderableInterface; |
| 18 | use phpOMS\Contract\SerializableInterface; |
| 19 | |
| 20 | /** |
| 21 | * String utils class. |
| 22 | * |
| 23 | * This class provides static helper functionalities for strings. |
| 24 | * |
| 25 | * @package phpOMS\Utils |
| 26 | * @license OMS License 2.0 |
| 27 | * @link https://jingga.app |
| 28 | * @since 1.0.0 |
| 29 | * |
| 30 | * @SuppressWarnings(PHPMD.CamelCaseMethodName) |
| 31 | */ |
| 32 | final class StringUtils |
| 33 | { |
| 34 | /** |
| 35 | * Constructor. |
| 36 | * |
| 37 | * This class is purely static and is preventing any initialization |
| 38 | * |
| 39 | * @since 1.0.0 |
| 40 | * @codeCoverageIgnore |
| 41 | */ |
| 42 | private function __construct() |
| 43 | { |
| 44 | } |
| 45 | |
| 46 | /** |
| 47 | * Check if a string contains any of the provided needles (case sensitive). |
| 48 | * |
| 49 | * The validation is done case sensitive. |
| 50 | * |
| 51 | * @param string $haystack Haystack |
| 52 | * @param string[] $needles Needles to check if any of them are part of the haystack |
| 53 | * |
| 54 | * @example StringUtils::contains('This string', ['This', 'test']); // true |
| 55 | * |
| 56 | * @return bool the function returns true if any of the needles is part of the haystack, false otherwise |
| 57 | * |
| 58 | * @since 1.0.0 |
| 59 | */ |
| 60 | public static function contains(string $haystack, array $needles) : bool |
| 61 | { |
| 62 | foreach ($needles as $needle) { |
| 63 | if (\strpos($haystack, $needle) !== false) { |
| 64 | return true; |
| 65 | } |
| 66 | } |
| 67 | |
| 68 | return false; |
| 69 | } |
| 70 | |
| 71 | /** |
| 72 | * Tests if a string ends with a certain string (case sensitive). |
| 73 | * |
| 74 | * The validation is done case sensitive. The function takes strings or an array of strings for the validation. |
| 75 | * In case of an array the function will test if any of the needles is at the end of the haystack string. |
| 76 | * |
| 77 | * @param string $haystack Haystack |
| 78 | * @param array|string $needles needles to check if they are at the end of the haystack |
| 79 | * |
| 80 | * @example StringUtils::endsWith('Test string', ['test1', 'string']); // true |
| 81 | * |
| 82 | * @return bool the function returns true if any of the needles is at the end of the haystack, false otherwise |
| 83 | * |
| 84 | * @since 1.0.0 |
| 85 | */ |
| 86 | public static function endsWith(string $haystack, string | array $needles) : bool |
| 87 | { |
| 88 | if (\is_string($needles)) { |
| 89 | $needles = [$needles]; |
| 90 | } |
| 91 | |
| 92 | foreach ($needles as $needle) { |
| 93 | if ($needle === '' || (($temp = \strlen($haystack) - \strlen($needle)) >= 0 && \strpos($haystack, $needle, $temp) !== false)) { |
| 94 | return true; |
| 95 | } |
| 96 | } |
| 97 | |
| 98 | return false; |
| 99 | } |
| 100 | |
| 101 | /** |
| 102 | * Tests if a string starts with a certain string (case sensitive). |
| 103 | * |
| 104 | * The validation is done case sensitive. The function takes strings or an array of strings for the validation. |
| 105 | * In case of an array the function will test if any of the needles is at the beginning of the haystack string. |
| 106 | * |
| 107 | * @param string $haystack Haystack |
| 108 | * @param array|string $needles needles to check if they are at the beginning of the haystack |
| 109 | * |
| 110 | * @example StringUtils::startsWith('Test string', ['Test', 'something']); // true |
| 111 | * @example StringUtils::startsWith('Test string', 'string'); // false |
| 112 | * @example StringUtils::startsWith('Test string', 'Test'); // true |
| 113 | * |
| 114 | * @return bool the function returns true if any of the needles is at the beginning of the haystack, false otherwise |
| 115 | * |
| 116 | * @since 1.0.0 |
| 117 | */ |
| 118 | public static function startsWith(string $haystack, string | array $needles) : bool |
| 119 | { |
| 120 | if (\is_string($needles)) { |
| 121 | $needles = [$needles]; |
| 122 | } |
| 123 | |
| 124 | foreach ($needles as $needle) { |
| 125 | if ($needle === '' || \strrpos($haystack, $needle, -\strlen($haystack)) !== false) { |
| 126 | return true; |
| 127 | } |
| 128 | } |
| 129 | |
| 130 | return false; |
| 131 | } |
| 132 | |
| 133 | /** |
| 134 | * Count occurences of character at the beginning of a string. |
| 135 | * |
| 136 | * @param string $string string to analyze |
| 137 | * @param string $character character to count at the beginning of the string |
| 138 | * |
| 139 | * @example StringUtils::countCharacterFromStart(' Test string', ' '); // 4 |
| 140 | * @example StringUtils::countCharacterFromStart(' Test string', 's'); // 0 |
| 141 | * |
| 142 | * @return int the amount of repeating occurences at the beginning of the string |
| 143 | * |
| 144 | * @since 1.0.0 |
| 145 | */ |
| 146 | public static function countCharacterFromStart(string $string, string $character) : int |
| 147 | { |
| 148 | $count = 0; |
| 149 | $length = \strlen($string); |
| 150 | |
| 151 | for ($i = 0; $i < $length; ++$i) { |
| 152 | if ($string[$i] !== $character) { |
| 153 | break; |
| 154 | } |
| 155 | |
| 156 | ++$count; |
| 157 | } |
| 158 | |
| 159 | return $count; |
| 160 | } |
| 161 | |
| 162 | /** |
| 163 | * Calculate string entropy |
| 164 | * |
| 165 | * @param string $value string to analyze |
| 166 | * |
| 167 | * @return float |
| 168 | * |
| 169 | * @since 1.0.0 |
| 170 | */ |
| 171 | public static function entropy(string $value) : float |
| 172 | { |
| 173 | $entropy = 0.0; |
| 174 | $size = \strlen($value); |
| 175 | |
| 176 | /** @var array $countChars */ |
| 177 | $countChars = \count_chars($value, 1); |
| 178 | |
| 179 | /** @var int $v */ |
| 180 | foreach ($countChars as $v) { |
| 181 | $p = $v / $size; |
| 182 | $entropy -= $p * \log($p) / \log(2); |
| 183 | } |
| 184 | |
| 185 | return $entropy; |
| 186 | } |
| 187 | |
| 188 | /** |
| 189 | * Turn value into string |
| 190 | * |
| 191 | * @param mixed $element value to stringify |
| 192 | * @param mixed $option Stringify option |
| 193 | * |
| 194 | * @return null|string |
| 195 | * |
| 196 | * @since 1.0.0 |
| 197 | */ |
| 198 | public static function stringify(mixed $element, mixed $option = null) : ?string |
| 199 | { |
| 200 | if ($element instanceof \JsonSerializable || \is_array($element)) { |
| 201 | if ($option !== null && !\is_int($option)) { |
| 202 | return null; |
| 203 | } |
| 204 | |
| 205 | $encoded = \json_encode($element, $option !== null ? $option : 0); |
| 206 | |
| 207 | return $encoded ? $encoded : null; |
| 208 | } elseif ($element instanceof SerializableInterface) { |
| 209 | return $element->serialize(); |
| 210 | } elseif (\is_string($element)) { |
| 211 | return $element; |
| 212 | } elseif (\is_int($element) || \is_float($element)) { |
| 213 | return (string) $element; |
| 214 | } elseif (\is_bool($element)) { |
| 215 | return $element ? '1' : '0'; |
| 216 | } elseif ($element === null) { |
| 217 | return null; |
| 218 | } elseif ($element instanceof \DateTimeInterface) { |
| 219 | return $element->format('Y-m-d H:i:s'); |
| 220 | } elseif ($element instanceof RenderableInterface) { |
| 221 | return $element->render(); |
| 222 | } elseif (\is_object($element) && \method_exists($element, '__toString')) { |
| 223 | return $element->__toString(); |
| 224 | } |
| 225 | |
| 226 | return null; |
| 227 | } |
| 228 | |
| 229 | /** |
| 230 | * Create string difference markup |
| 231 | * |
| 232 | * @param string $old Old strings |
| 233 | * @param string $new New strings |
| 234 | * @param string $delim Delim (e.g '' = compare by character, ' ' = compare by words) |
| 235 | * |
| 236 | * @return string Markup using <del> and <ins> tags |
| 237 | * |
| 238 | * @since 1.0.0 |
| 239 | */ |
| 240 | public static function createDiffMarkup(string $old, string $new, string $delim = '') : string |
| 241 | { |
| 242 | $splitOld = empty($delim) ? \str_split($old) : \explode($delim, $old); |
| 243 | $splitNew = empty($delim) ? \str_split($new) : \explode($delim, $new); |
| 244 | |
| 245 | if ($splitOld === false |
| 246 | || (empty($old) && !empty($new)) |
| 247 | || (!empty($delim) && \count($splitOld) === 1 && $splitOld[0] === '') |
| 248 | ) { |
| 249 | return '<ins>' . $new . '</ins>'; |
| 250 | } |
| 251 | |
| 252 | if ($splitNew === false |
| 253 | || (!empty($old) && empty($new)) |
| 254 | || (!empty($delim) && \count($splitNew) === 1 && $splitNew[0] === '') |
| 255 | ) { |
| 256 | return '<del>' . $old . '</del>'; |
| 257 | } |
| 258 | |
| 259 | $diff = self::computeLCSDiff($splitOld, $splitNew); |
| 260 | |
| 261 | $n = \count($diff['values']); |
| 262 | $result = ''; |
| 263 | $mc = 0; |
| 264 | |
| 265 | for ($i = 0; $i < $n; ++$i) { |
| 266 | $mc = $diff['mask'][$i]; |
| 267 | |
| 268 | if ($mc !== 0) { |
| 269 | switch ($mc) { |
| 270 | case -1: |
| 271 | $result .= '<del>' . $diff['values'][$i] . '</del>' . $delim; |
| 272 | break; |
| 273 | case 1: |
| 274 | $result .= '<ins>' . $diff['values'][$i] . '</ins>' . $delim; |
| 275 | break; |
| 276 | } |
| 277 | } else { |
| 278 | $result .= $diff['values'][$i] . $delim; |
| 279 | } |
| 280 | } |
| 281 | |
| 282 | $result = \rtrim($result, $delim); |
| 283 | |
| 284 | switch ($mc) { |
| 285 | case -1: |
| 286 | $result .= '</del>'; |
| 287 | break; |
| 288 | case 1: |
| 289 | $result .= '</ins>'; |
| 290 | break; |
| 291 | } |
| 292 | |
| 293 | // @todo: This should not be necessary but the algorithm above allows for weird combinations. |
| 294 | return \str_replace( |
| 295 | ['</del></del>', '</ins></ins>', '<ins></ins>', '<del></del>', '</ins><ins>', '</del><del>', '</ins> <del>', '</del> <ins>'], |
| 296 | ['</del>', '</ins>', '', '', '', '', '</ins><del>', '</del><ins>'], |
| 297 | $result |
| 298 | ); |
| 299 | } |
| 300 | |
| 301 | /** |
| 302 | * Create LCS diff masks |
| 303 | * |
| 304 | * @param string[] $from From/old strings |
| 305 | * @param string[] $to To/new strings |
| 306 | * |
| 307 | * @return array |
| 308 | * |
| 309 | * @throws \Exception This exception is thrown if one of the parameters is empty |
| 310 | * |
| 311 | * @since 1.0.0 |
| 312 | */ |
| 313 | private static function computeLCSDiff(array $from, array $to) : array |
| 314 | { |
| 315 | $diffValues = []; |
| 316 | $diffMask = []; |
| 317 | |
| 318 | $dm = []; |
| 319 | $n1 = \count($from); |
| 320 | $n2 = \count($to); |
| 321 | |
| 322 | for ($j = -1; $j < $n2; ++$j) { |
| 323 | $dm[-1][$j] = 0; |
| 324 | } |
| 325 | |
| 326 | for ($i = -1; $i < $n1; ++$i) { |
| 327 | $dm[$i][-1] = 0; |
| 328 | } |
| 329 | |
| 330 | for ($i = 0; $i < $n1; ++$i) { |
| 331 | for ($j = 0; $j < $n2; ++$j) { |
| 332 | $dm[$i][$j] = $from[$i] === $to[$j] |
| 333 | ? $dm[$i - 1][$j - 1] + 1 |
| 334 | : \max($dm[$i - 1][$j], $dm[$i][$j - 1]); |
| 335 | } |
| 336 | } |
| 337 | |
| 338 | $i = $n1 - 1; |
| 339 | $j = $n2 - 1; |
| 340 | while ($i > -1 || $j > -1) { |
| 341 | if ($j > -1 && $dm[$i][$j - 1] === $dm[$i][$j]) { |
| 342 | $diffValues[] = $to[$j]; |
| 343 | $diffMask[] = 1; |
| 344 | --$j; |
| 345 | |
| 346 | continue; |
| 347 | } |
| 348 | |
| 349 | if ($i > -1 && $dm[$i - 1][$j] === $dm[$i][$j]) { |
| 350 | $diffValues[] = $from[$i]; |
| 351 | $diffMask[] = -1; |
| 352 | --$i; |
| 353 | |
| 354 | continue; |
| 355 | } |
| 356 | |
| 357 | $diffValues[] = $from[$i]; |
| 358 | $diffMask[] = 0; |
| 359 | --$i; |
| 360 | --$j; |
| 361 | } |
| 362 | |
| 363 | $diffValues = \array_reverse($diffValues); |
| 364 | $diffMask = \array_reverse($diffMask); |
| 365 | |
| 366 | return ['values' => $diffValues, 'mask' => $diffMask]; |
| 367 | } |
| 368 | |
| 369 | /** |
| 370 | * Create a int hash from a string |
| 371 | * |
| 372 | * @param string $str String to hash |
| 373 | * |
| 374 | * @return int |
| 375 | * |
| 376 | * @since 1.0.0 |
| 377 | */ |
| 378 | public static function intHash(string $str) : int |
| 379 | { |
| 380 | $res = 0; |
| 381 | $pow = 1; |
| 382 | $len = \strlen($str); |
| 383 | |
| 384 | for ($i = 0; $i < $len; ++$i) { |
| 385 | $res = ($res + (\ord($str[$i]) - \ord('a') + 1) * $pow) % (1e9 + 9); |
| 386 | $pow = ($pow * 31) % (1e9 + 9); |
| 387 | } |
| 388 | |
| 389 | return (int) $res; |
| 390 | } |
| 391 | |
| 392 | /** |
| 393 | * Fix CVE-2016-10033 and CVE-2016-10045 by disallowing potentially unsafe shell characters. |
| 394 | * |
| 395 | * @param string $string String to check |
| 396 | * |
| 397 | * @return bool |
| 398 | * |
| 399 | * @since 1.0.0 |
| 400 | */ |
| 401 | public static function isShellSafe(string $string) : bool |
| 402 | { |
| 403 | if (\escapeshellcmd($string) !== $string |
| 404 | || !\in_array(\escapeshellarg($string), ["'{$string}'", "\"{$string}\""]) |
| 405 | ) { |
| 406 | return false; |
| 407 | } |
| 408 | |
| 409 | $length = \strlen($string); |
| 410 | |
| 411 | for ($i = 0; $i < $length; ++$i) { |
| 412 | $c = $string[$i]; |
| 413 | |
| 414 | if (!\ctype_alnum($c) && \strpos('@_-.', $c) === false) { |
| 415 | return false; |
| 416 | } |
| 417 | } |
| 418 | |
| 419 | return true; |
| 420 | } |
| 421 | |
| 422 | /** |
| 423 | * Turn ints into spreadsheet column names |
| 424 | * |
| 425 | * @param int $num Column number (1 = A) |
| 426 | * |
| 427 | * @return string |
| 428 | * |
| 429 | * @since 1.0.0 |
| 430 | */ |
| 431 | public static function intToAlphabet(int $num) : string |
| 432 | { |
| 433 | if ($num < 0) { |
| 434 | return ''; |
| 435 | } |
| 436 | |
| 437 | $result = ''; |
| 438 | while ($num >= 0) { |
| 439 | $remainder = $num % 26; |
| 440 | $result = \chr(64 + $remainder) . $result; |
| 441 | |
| 442 | if ($num < 26) { |
| 443 | break; |
| 444 | } |
| 445 | |
| 446 | $num = (int) \floor($num / 26); |
| 447 | } |
| 448 | |
| 449 | return $result; |
| 450 | } |
| 451 | } |