Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
92.65% |
63 / 68 |
|
91.67% |
11 / 12 |
CRAP | |
0.00% |
0 / 1 |
| MbStringUtils | |
92.65% |
63 / 68 |
|
91.67% |
11 / 12 |
34.46 | |
0.00% |
0 / 1 |
| __construct | n/a |
0 / 0 |
n/a |
0 / 0 |
1 | |||||
| mb_contains | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
3 | |||
| mb_startsWith | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
5 | |||
| mb_endsWith | |
100.00% |
6 / 6 |
|
100.00% |
1 / 1 |
6 | |||
| mb_ucfirst | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| mb_lcfirst | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
1 | |||
| mb_trim | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
2 | |||
| mb_rtrim | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
2 | |||
| mb_ltrim | |
100.00% |
4 / 4 |
|
100.00% |
1 / 1 |
2 | |||
| mb_entropy | |
100.00% |
7 / 7 |
|
100.00% |
1 / 1 |
2 | |||
| mb_count_chars | |
100.00% |
8 / 8 |
|
100.00% |
1 / 1 |
3 | |||
| utf8CharBoundary | |
68.75% |
11 / 16 |
|
0.00% |
0 / 1 |
5.76 | |||
| hasMultiBytes | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| 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\System\CharsetType; |
| 18 | |
| 19 | /** |
| 20 | * String utils class. |
| 21 | * |
| 22 | * This class provides static helper functionalities for strings. |
| 23 | * |
| 24 | * @package phpOMS\Utils |
| 25 | * @license OMS License 2.0 |
| 26 | * @link https://jingga.app |
| 27 | * @since 1.0.0 |
| 28 | * |
| 29 | * @SuppressWarnings(PHPMD.CamelCaseMethodName) |
| 30 | */ |
| 31 | final class MbStringUtils |
| 32 | { |
| 33 | /** |
| 34 | * Constructor. |
| 35 | * |
| 36 | * This class is purely static and is preventing any initialization |
| 37 | * |
| 38 | * @since 1.0.0 |
| 39 | * @codeCoverageIgnore |
| 40 | */ |
| 41 | private function __construct() |
| 42 | { |
| 43 | } |
| 44 | |
| 45 | /** |
| 46 | * Check if a string contains any of the provided needles (case sensitive). |
| 47 | * |
| 48 | * The validation is done case sensitive. |
| 49 | * |
| 50 | * @param string $haystack Haystack |
| 51 | * @param string[] $needles Needles to check if any of them are part of the haystack |
| 52 | * |
| 53 | * @example MbStringUtils::mb_contains('This string', ['This', 'test']); // true |
| 54 | * |
| 55 | * @return bool the function returns true if any of the needles is part of the haystack, false otherwise |
| 56 | * |
| 57 | * @since 1.0.0 |
| 58 | */ |
| 59 | public static function mb_contains(string $haystack, array $needles) : bool |
| 60 | { |
| 61 | foreach ($needles as $needle) { |
| 62 | if (\mb_strpos($haystack, $needle) !== false) { |
| 63 | return true; |
| 64 | } |
| 65 | } |
| 66 | |
| 67 | return false; |
| 68 | } |
| 69 | |
| 70 | /** |
| 71 | * Tests if a multi byte string starts with a certain string (case sensitive). |
| 72 | * |
| 73 | * The validation is done case sensitive. The function takes strings or an array of strings for the validation. |
| 74 | * In case of an array the function will test if any of the needles is at the beginning of the haystack string. |
| 75 | * |
| 76 | * @param string $haystack Haystack |
| 77 | * @param array|string $needles needles to check if they are at the beginning of the haystack |
| 78 | * |
| 79 | * @return bool the function returns true if any of the needles is at the beginning of the haystack, false otherwise |
| 80 | * |
| 81 | * @since 1.0.0 |
| 82 | */ |
| 83 | public static function mb_startsWith(string $haystack, string | array $needles) : bool |
| 84 | { |
| 85 | if (\is_string($needles)) { |
| 86 | $needles = [$needles]; |
| 87 | } |
| 88 | |
| 89 | foreach ($needles as $needle) { |
| 90 | if ($needle === '' || \mb_strrpos($haystack, $needle, -\mb_strlen($haystack)) !== false) { |
| 91 | return true; |
| 92 | } |
| 93 | } |
| 94 | |
| 95 | return false; |
| 96 | } |
| 97 | |
| 98 | /** |
| 99 | * Tests if a multi byte string ends with a certain string (case sensitive). |
| 100 | * |
| 101 | * The validation is done case sensitive. The function takes strings or an array of strings for the validation. |
| 102 | * In case of an array the function will test if any of the needles is at the end of the haystack string. |
| 103 | * |
| 104 | * @param string $haystack Haystack |
| 105 | * @param array|string $needles needles to check if they are at the end of the haystack |
| 106 | * |
| 107 | * @example StringUtils::endsWith('Test string', ['test1', 'string']); // true |
| 108 | * @example StringUtils::endsWith('Test string', 'string'); // true |
| 109 | * @example StringUtils::endsWith('Test string', String); // false |
| 110 | * |
| 111 | * @return bool the function returns true if any of the needles is at the end of the haystack, false otherwise |
| 112 | * |
| 113 | * @since 1.0.0 |
| 114 | */ |
| 115 | public static function mb_endsWith(string $haystack, string | array $needles) : bool |
| 116 | { |
| 117 | if (\is_string($needles)) { |
| 118 | $needles = [$needles]; |
| 119 | } |
| 120 | |
| 121 | foreach ($needles as $needle) { |
| 122 | if ($needle === '' || (($temp = \mb_strlen($haystack) - \mb_strlen($needle)) >= 0 && \mb_strpos($haystack, $needle, $temp) !== false)) { |
| 123 | return true; |
| 124 | } |
| 125 | } |
| 126 | |
| 127 | return false; |
| 128 | } |
| 129 | |
| 130 | /** |
| 131 | * Makes first letter of a multi byte string upper case. |
| 132 | * |
| 133 | * @param string $string string to upper case first letter |
| 134 | * |
| 135 | * @return string multi byte string with first character as upper case |
| 136 | * |
| 137 | * @since 1.0.0 |
| 138 | */ |
| 139 | public static function mb_ucfirst(string $string) : string |
| 140 | { |
| 141 | $strlen = \mb_strlen($string); |
| 142 | $firstChar = \mb_substr($string, 0, 1); |
| 143 | $then = \mb_substr($string, 1, $strlen - 1); |
| 144 | |
| 145 | return \mb_strtoupper($firstChar) . $then; |
| 146 | } |
| 147 | |
| 148 | /** |
| 149 | * Makes first letter of a multi byte string lower case. |
| 150 | * |
| 151 | * @param string $string string to lower case first letter |
| 152 | * |
| 153 | * @return string multi byte string with first character as lower case |
| 154 | * |
| 155 | * @since 1.0.0 |
| 156 | */ |
| 157 | public static function mb_lcfirst(string $string) : string |
| 158 | { |
| 159 | $strlen = \mb_strlen($string); |
| 160 | $firstChar = \mb_substr($string, 0, 1); |
| 161 | $then = \mb_substr($string, 1, $strlen - 1); |
| 162 | |
| 163 | return \mb_strtolower($firstChar) . $then; |
| 164 | } |
| 165 | |
| 166 | /** |
| 167 | * Trim multi byte characters from a multi byte string. |
| 168 | * |
| 169 | * @param string $string multi byte string to trim multi byte characters from |
| 170 | * @param string $charlist Multi byte character list used for trimming |
| 171 | * |
| 172 | * @return string trimmed multi byte string |
| 173 | * |
| 174 | * @since 1.0.0 |
| 175 | */ |
| 176 | public static function mb_trim(string $string, string $charlist = ' ') : string |
| 177 | { |
| 178 | if ($charlist === ' ') { |
| 179 | return \trim($string); |
| 180 | } else { |
| 181 | $charlist = \str_replace('/', '\/', \preg_quote($charlist)); |
| 182 | |
| 183 | return \preg_replace('/(^[' . $charlist . ']+)|([ ' . $charlist . ']+$)/us', '', $string) ?? ''; |
| 184 | } |
| 185 | } |
| 186 | |
| 187 | /** |
| 188 | * Trim multi byte characters from the right of a multi byte string. |
| 189 | * |
| 190 | * @param string $string multi byte string to trim multi byte characters from |
| 191 | * @param string $charlist Multi byte character list used for trimming |
| 192 | * |
| 193 | * @return string trimmed multi byte string |
| 194 | * |
| 195 | * @since 1.0.0 |
| 196 | */ |
| 197 | public static function mb_rtrim(string $string, string $charlist = ' ') : string |
| 198 | { |
| 199 | if ($charlist === ' ') { |
| 200 | return \rtrim($string); |
| 201 | } else { |
| 202 | $charlist = \str_replace('/', '\/', \preg_quote($charlist)); |
| 203 | |
| 204 | return \preg_replace('/([' . $charlist . ']+$)/us', '', $string) ?? ''; |
| 205 | } |
| 206 | } |
| 207 | |
| 208 | /** |
| 209 | * Trim multi byte characters from the left of a multi byte string. |
| 210 | * |
| 211 | * @param string $string multi byte string to trim multi byte characters from |
| 212 | * @param string $charlist Multi byte character list used for trimming |
| 213 | * |
| 214 | * @return string trimmed multi byte string |
| 215 | * |
| 216 | * @since 1.0.0 |
| 217 | */ |
| 218 | public static function mb_ltrim(string $string, string $charlist = ' ') : string |
| 219 | { |
| 220 | if ($charlist === ' ') { |
| 221 | return \ltrim($string); |
| 222 | } else { |
| 223 | $charlist = \str_replace('/', '\/', \preg_quote($charlist)); |
| 224 | |
| 225 | return \preg_replace('/(^[' . $charlist . ']+)/us', '', $string) ?? ''; |
| 226 | } |
| 227 | } |
| 228 | |
| 229 | /** |
| 230 | * Calculate string entropy |
| 231 | * |
| 232 | * @param string $value string to analyze |
| 233 | * |
| 234 | * @return float |
| 235 | * |
| 236 | * @since 1.0.0 |
| 237 | */ |
| 238 | public static function mb_entropy(string $value) : float |
| 239 | { |
| 240 | $entropy = 0.0; |
| 241 | $size = \mb_strlen($value); |
| 242 | $countChars = self::mb_count_chars($value); |
| 243 | |
| 244 | foreach ($countChars as $v) { |
| 245 | $p = $v / $size; |
| 246 | $entropy -= $p * \log($p) / \log(2); |
| 247 | } |
| 248 | |
| 249 | return $entropy; |
| 250 | } |
| 251 | |
| 252 | /** |
| 253 | * Count chars of utf-8 string. |
| 254 | * |
| 255 | * @param string $input string to count chars |
| 256 | * |
| 257 | * @return array<string, int> |
| 258 | * |
| 259 | * @since 1.0.0 |
| 260 | */ |
| 261 | public static function mb_count_chars(string $input) : array |
| 262 | { |
| 263 | $l = \mb_strlen($input, 'UTF-8'); |
| 264 | $unique = []; |
| 265 | |
| 266 | for ($i = 0; $i < $l; ++$i) { |
| 267 | $char = \mb_substr($input, $i, 1, 'UTF-8'); |
| 268 | |
| 269 | if (!\array_key_exists($char, $unique)) { |
| 270 | $unique[$char] = 0; |
| 271 | } |
| 272 | |
| 273 | ++$unique[$char]; |
| 274 | } |
| 275 | |
| 276 | return $unique; |
| 277 | } |
| 278 | |
| 279 | /** |
| 280 | * Get the utf-8 boundary of a string |
| 281 | * |
| 282 | * @param string $text QP text to search for utf-8 boundary |
| 283 | * @param int $length Last character boundary prior to this length |
| 284 | * |
| 285 | * @return int |
| 286 | * |
| 287 | * @since 1.0.0 |
| 288 | */ |
| 289 | public static function utf8CharBoundary(string $text, int $length = 0) : int |
| 290 | { |
| 291 | $reset = 3; |
| 292 | |
| 293 | do { |
| 294 | $lastChunk = \substr($text, $length - $reset, $reset); |
| 295 | $encodedPos = \strpos($lastChunk, '='); |
| 296 | |
| 297 | if ($encodedPos === false) { |
| 298 | break; // @codeCoverageIgnore |
| 299 | } |
| 300 | |
| 301 | $hex = \substr($text, $length - $reset + $encodedPos + 1, 2); |
| 302 | $dec = \hexdec($hex); |
| 303 | |
| 304 | if ($dec < 128) { |
| 305 | if ($encodedPos > 0) { |
| 306 | $length -= $reset - $encodedPos; |
| 307 | } |
| 308 | |
| 309 | break; |
| 310 | } elseif ($dec >= 192) { |
| 311 | $length -= $reset - $encodedPos; |
| 312 | break; |
| 313 | } else { /* $dec < 192 */ |
| 314 | $reset += 3; |
| 315 | } |
| 316 | } while (true); |
| 317 | |
| 318 | return $length; |
| 319 | } |
| 320 | |
| 321 | /** |
| 322 | * Test if a string has multibytes |
| 323 | * |
| 324 | * @param string $text Text to check |
| 325 | * @param string $charset Charset to check |
| 326 | * |
| 327 | * @return bool |
| 328 | * |
| 329 | * @since 1.0.0 |
| 330 | */ |
| 331 | public static function hasMultiBytes(string $text, string $charset = CharsetType::UTF_8) : bool |
| 332 | { |
| 333 | return \strlen($text) > \mb_strlen($text, $charset); |
| 334 | } |
| 335 | } |