Inflector.php 13.8 KB
Newer Older
Antonio Ramirez committed
1 2 3 4 5 6 7 8 9 10 11 12
<?php
/**
 * @copyright Copyright (c) 2008 Yii Software LLC
 * @link http://www.yiiframework.com/
 * @license http://www.yiiframework.com/license/
 */

namespace yii\helpers\base;

use Yii;

/**
Antonio Ramirez committed
13
 * Inflector pluralizes and singularizes English nouns. It also contains some other useful methods.
Antonio Ramirez committed
14 15 16 17 18 19 20
 *
 * @author Antonio Ramirez <amigo.cobos@gmail.com>
 * @since 2.0
 */
class Inflector
{
	/**
Qiang Xue committed
21 22
	 * @var array the rules for converting a word into its plural form.
	 * The keys are the regular expressions and the values are the corresponding replacements.
Antonio Ramirez committed
23
	 */
Qiang Xue committed
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
	public static $plurals = array(
		'/([nrlm]ese|deer|fish|sheep|measles|ois|pox|media)$/i' => '\1',
		'/^(sea[- ]bass)$/i' => '\1',
		'/(m)ove$/i' => '\1oves',
		'/(f)oot$/i' => '\1eet',
		'/(h)uman$/i' => '\1umans',
		'/(s)tatus$/i' => '\1tatuses',
		'/(s)taff$/i' => '\1taff',
		'/(t)ooth$/i' => '\1eeth',
		'/(quiz)$/i' => '\1zes',
		'/^(ox)$/i' => '\1\2en',
		'/([m|l])ouse$/i' => '\1ice',
		'/(matr|vert|ind)(ix|ex)$/i' => '\1ices',
		'/(x|ch|ss|sh)$/i' => '\1es',
		'/([^aeiouy]|qu)y$/i' => '\1ies',
		'/(hive)$/i' => '\1s',
		'/(?:([^f])fe|([lr])f)$/i' => '\1\2ves',
		'/sis$/i' => 'ses',
		'/([ti])um$/i' => '\1a',
		'/(p)erson$/i' => '\1eople',
		'/(m)an$/i' => '\1en',
		'/(c)hild$/i' => '\1hildren',
		'/(buffal|tomat|potat|ech|her|vet)o$/i' => '\1oes',
		'/(alumn|bacill|cact|foc|fung|nucle|radi|stimul|syllab|termin|vir)us$/i' => '\1i',
		'/us$/i' => 'uses',
		'/(alias)$/i' => '\1es',
		'/(ax|cris|test)is$/i' => '\1es',
		'/s$/' => 's',
		'/^$/' => '',
		'/$/' => 's',		
Antonio Ramirez committed
54 55
	);
	/**
Qiang Xue committed
56 57
	 * @var array the rules for converting a word into its singular form.
	 * The keys are the regular expressions and the values are the corresponding replacements.
Antonio Ramirez committed
58
	 */
Qiang Xue committed
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
	public static $singulars = array(
		'/([nrlm]ese|deer|fish|sheep|measles|ois|pox|media|ss)$/i' => '\1',
		'/^(sea[- ]bass)$/i' => '\1',
		'/(s)tatuses$/i' => '\1tatus',
		'/(f)eet$/i' => '\1oot',
		'/(t)eeth$/i' => '\1ooth',
		'/^(.*)(menu)s$/i' => '\1\2',
		'/(quiz)zes$/i' => '\\1',
		'/(matr)ices$/i' => '\1ix',
		'/(vert|ind)ices$/i' => '\1ex',
		'/^(ox)en/i' => '\1',
		'/(alias)(es)*$/i' => '\1',
		'/(alumn|bacill|cact|foc|fung|nucle|radi|stimul|syllab|termin|viri?)i$/i' => '\1us',
		'/([ftw]ax)es/i' => '\1',
		'/(cris|ax|test)es$/i' => '\1is',
		'/(shoe|slave)s$/i' => '\1',
		'/(o)es$/i' => '\1',
		'/ouses$/' => 'ouse',
		'/([^a])uses$/' => '\1us',
		'/([m|l])ice$/i' => '\1ouse',
		'/(x|ch|ss|sh)es$/i' => '\1',
		'/(m)ovies$/i' => '\1\2ovie',
		'/(s)eries$/i' => '\1\2eries',
		'/([^aeiouy]|qu)ies$/i' => '\1y',
		'/([lr])ves$/i' => '\1f',
		'/(tive)s$/i' => '\1',
		'/(hive)s$/i' => '\1',
		'/(drive)s$/i' => '\1',
		'/([^fo])ves$/i' => '\1fe',
		'/(^analy)ses$/i' => '\1sis',
		'/(analy|diagno|^ba|(p)arenthe|(p)rogno|(s)ynop|(t)he)ses$/i' => '\1\2sis',
		'/([ti])a$/i' => '\1um',
		'/(p)eople$/i' => '\1\2erson',
		'/(m)en$/i' => '\1an',
		'/(c)hildren$/i' => '\1\2hild',
		'/(n)ews$/i' => '\1\2ews',
		'/eaus$/' => 'eau',
		'/^(.*us)$/' => '\\1',
		'/s$/i' => '',		
Antonio Ramirez committed
98 99
	);
	/**
Qiang Xue committed
100 101
	 * @var array the special rules for converting a word between its plural form and singular form.
	 * The keys are the special words in singular form, and the values are the corresponding plural form.
Antonio Ramirez committed
102
	 */
Qiang Xue committed
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
	public static $specials = array(
		'atlas' => 'atlases',
		'beef' => 'beefs',
		'brother' => 'brothers',
		'cafe' => 'cafes',
		'child' => 'children',
		'cookie' => 'cookies',
		'corpus' => 'corpuses',
		'cow' => 'cows',
		'curve' => 'curves',
		'foe' => 'foes',
		'ganglion' => 'ganglions',
		'genie' => 'genies',
		'genus' => 'genera',
		'graffito' => 'graffiti',
		'hoof' => 'hoofs',
		'loaf' => 'loaves',
		'man' => 'men',
		'money' => 'monies',
		'mongoose' => 'mongooses',
		'move' => 'moves',
		'mythos' => 'mythoi',
		'niche' => 'niches',
		'numen' => 'numina',
		'occiput' => 'occiputs',
		'octopus' => 'octopuses',
		'opus' => 'opuses',
		'ox' => 'oxen',
		'penis' => 'penises',
		'sex' => 'sexes',
		'soliloquy' => 'soliloquies',
		'testis' => 'testes',
		'trilby' => 'trilbys',
		'turf' => 'turfs',
		'wave' => 'waves',
		'Amoyese' => 'Amoyese',
		'bison' => 'bison',
		'Borghese' => 'Borghese',
		'bream' => 'bream',
		'breeches' => 'breeches',
		'britches' => 'britches',
		'buffalo' => 'buffalo',
		'cantus' => 'cantus',
		'carp' => 'carp',
		'chassis' => 'chassis',
		'clippers' => 'clippers',
		'cod' => 'cod',
		'coitus' => 'coitus',
		'Congoese' => 'Congoese',
		'contretemps' => 'contretemps',
		'corps' => 'corps',
		'debris' => 'debris',
		'diabetes' => 'diabetes',
		'djinn' => 'djinn',
		'eland' => 'eland',
		'elk' => 'elk',
		'equipment' => 'equipment',
		'Faroese' => 'Faroese',
		'flounder' => 'flounder',
		'Foochowese' => 'Foochowese',
		'gallows' => 'gallows',
		'Genevese' => 'Genevese',
		'Genoese' => 'Genoese',
		'Gilbertese' => 'Gilbertese',
		'graffiti' => 'graffiti',
		'headquarters' => 'headquarters',
		'herpes' => 'herpes',
		'hijinks' => 'hijinks',
		'Hottentotese' => 'Hottentotese',
		'information' => 'information',
		'innings' => 'innings',
		'jackanapes' => 'jackanapes',
		'Kiplingese' => 'Kiplingese',
		'Kongoese' => 'Kongoese',
		'Lucchese' => 'Lucchese',
		'mackerel' => 'mackerel',
		'Maltese' => 'Maltese',
		'mews' => 'mews',
		'moose' => 'moose',
		'mumps' => 'mumps',
		'Nankingese' => 'Nankingese',
		'news' => 'news',
		'nexus' => 'nexus',
		'Niasese' => 'Niasese',
		'Pekingese' => 'Pekingese',
		'Piedmontese' => 'Piedmontese',
		'pincers' => 'pincers',
		'Pistoiese' => 'Pistoiese',
		'pliers' => 'pliers',
		'Portuguese' => 'Portuguese',
		'proceedings' => 'proceedings',
		'rabies' => 'rabies',
		'rice' => 'rice',
		'rhinoceros' => 'rhinoceros',
		'salmon' => 'salmon',
		'Sarawakese' => 'Sarawakese',
		'scissors' => 'scissors',
		'series' => 'series',
		'Shavese' => 'Shavese',
		'shears' => 'shears',
		'siemens' => 'siemens',
		'species' => 'species',
		'swine' => 'swine',
		'testes' => 'testes',
		'trousers' => 'trousers',
		'trout' => 'trout',
		'tuna' => 'tuna',
		'Vermontese' => 'Vermontese',
		'Wenchowese' => 'Wenchowese',
		'whiting' => 'whiting',
		'wildebeest' => 'wildebeest',
		'Yengeese' => 'Yengeese',
Antonio Ramirez committed
215 216
	);
	/**
Qiang Xue committed
217
	 * @var array map of special chars and its translation. This is used by [[slug()]].
Antonio Ramirez committed
218
	 */
Qiang Xue committed
219
	public static $transliteration = array(
Antonio Ramirez committed
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
		'/ä|æ|ǽ/' => 'ae',
		'/ö|œ/' => 'oe',
		'/ü/' => 'ue',
		'/Ä/' => 'Ae',
		'/Ü/' => 'Ue',
		'/Ö/' => 'Oe',
		'/À|Á|Â|Ã|Å|Ǻ|Ā|Ă|Ą|Ǎ/' => 'A',
		'/à|á|â|ã|å|ǻ|ā|ă|ą|ǎ|ª/' => 'a',
		'/Ç|Ć|Ĉ|Ċ|Č/' => 'C',
		'/ç|ć|ĉ|ċ|č/' => 'c',
		'/Ð|Ď|Đ/' => 'D',
		'/ð|ď|đ/' => 'd',
		'/È|É|Ê|Ë|Ē|Ĕ|Ė|Ę|Ě/' => 'E',
		'/è|é|ê|ë|ē|ĕ|ė|ę|ě/' => 'e',
		'/Ĝ|Ğ|Ġ|Ģ/' => 'G',
		'/ĝ|ğ|ġ|ģ/' => 'g',
		'/Ĥ|Ħ/' => 'H',
		'/ĥ|ħ/' => 'h',
		'/Ì|Í|Î|Ï|Ĩ|Ī|Ĭ|Ǐ|Į|İ/' => 'I',
		'/ì|í|î|ï|ĩ|ī|ĭ|ǐ|į|ı/' => 'i',
		'/Ĵ/' => 'J',
		'/ĵ/' => 'j',
		'/Ķ/' => 'K',
		'/ķ/' => 'k',
		'/Ĺ|Ļ|Ľ|Ŀ|Ł/' => 'L',
		'/ĺ|ļ|ľ|ŀ|ł/' => 'l',
		'/Ñ|Ń|Ņ|Ň/' => 'N',
		'/ñ|ń|ņ|ň|ʼn/' => 'n',
		'/Ò|Ó|Ô|Õ|Ō|Ŏ|Ǒ|Ő|Ơ|Ø|Ǿ/' => 'O',
		'/ò|ó|ô|õ|ō|ŏ|ǒ|ő|ơ|ø|ǿ|º/' => 'o',
		'/Ŕ|Ŗ|Ř/' => 'R',
		'/ŕ|ŗ|ř/' => 'r',
		'/Ś|Ŝ|Ş|Ș|Š/' => 'S',
		'/ś|ŝ|ş|ș|š|ſ/' => 's',
		'/Ţ|Ț|Ť|Ŧ/' => 'T',
		'/ţ|ț|ť|ŧ/' => 't',
		'/Ù|Ú|Û|Ũ|Ū|Ŭ|Ů|Ű|Ų|Ư|Ǔ|Ǖ|Ǘ|Ǚ|Ǜ/' => 'U',
		'/ù|ú|û|ũ|ū|ŭ|ů|ű|ų|ư|ǔ|ǖ|ǘ|ǚ|ǜ/' => 'u',
		'/Ý|Ÿ|Ŷ/' => 'Y',
		'/ý|ÿ|ŷ/' => 'y',
		'/Ŵ/' => 'W',
		'/ŵ/' => 'w',
		'/Ź|Ż|Ž/' => 'Z',
		'/ź|ż|ž/' => 'z',
		'/Æ|Ǽ/' => 'AE',
		'/ß/' => 'ss',
		'/IJ/' => 'IJ',
		'/ij/' => 'ij',
		'/Œ/' => 'OE',
		'/ƒ/' => 'f'
	);

	/**
273 274 275 276 277
	 * Converts a word to its plural form.
	 * Note that this is for English only!
	 * For example, 'apple' will become 'apples', and 'child' will become 'children'.
	 * @param string $word the word to be pluralized
	 * @return string the pluralized word
Antonio Ramirez committed
278 279 280
	 */
	public static function pluralize($word)
	{
Qiang Xue committed
281 282 283 284
		if (isset(self::$specials[$word])) {
			return self::$specials[$word];
		}
		foreach (static::$plurals as $rule => $replacement) {
Antonio Ramirez committed
285 286 287 288 289 290 291 292 293 294 295 296 297 298
			if (preg_match($rule, $word)) {
				return preg_replace($rule, $replacement, $word);
			}
		}
		return $word;
	}

	/**
	 * Returns the singular of the $word
	 * @param string $word the english word to singularize
	 * @return string Singular noun.
	 */
	public static function singularize($word)
	{
Qiang Xue committed
299 300 301 302 303
		$result = array_search($word, self::$specials, true);
		if ($result !== false) {
			return $result;
		}
		foreach (static::$singulars as $rule => $replacement) {
Antonio Ramirez committed
304 305 306 307 308 309 310 311 312 313
			if (preg_match($rule, $word)) {
				return preg_replace($rule, $replacement, $word);
			}
		}
		return $word;
	}

	/**
	 * Converts an underscored or CamelCase word into a English
	 * sentence.
314 315 316
	 * @param string $words
	 * @param bool $ucAll whether to set all words to uppercase
	 * @return string
Antonio Ramirez committed
317
	 */
318
	public static function titleize($words, $ucAll = false)
Antonio Ramirez committed
319
	{
320 321
		$words = static::humanize(static::underscore($words), $ucAll);
		return $ucAll ? ucwords($words) : ucfirst($words);
Antonio Ramirez committed
322 323 324 325 326 327 328 329
	}

	/**
	 * Returns given word as CamelCased
	 * Converts a word like "send_email" to "SendEmail". It
	 * will remove non alphanumeric character from the word, so
	 * "who's online" will be converted to "WhoSOnline"
	 * @see variablize
330 331
	 * @param string $word the word to CamelCase
	 * @return string
Antonio Ramirez committed
332 333 334 335 336 337
	 */
	public static function camelize($word)
	{
		return str_replace(' ', '', ucwords(preg_replace('/[^A-Z^a-z^0-9]+/', ' ', $word)));
	}

338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
	/**
	 * Converts a CamelCase name into space-separated words.
	 * For example, 'PostTag' will be converted to 'Post Tag'.
	 * @param string $name the string to be converted
	 * @param boolean $ucwords whether to capitalize the first letter in each word
	 * @return string the resulting words
	 */
	public static function camel2words($name, $ucwords = true)
	{
		$label = trim(strtolower(str_replace(array(
			'-',
			'_',
			'.'
		), ' ', preg_replace('/(?<![A-Z])[A-Z]/', ' \0', $name))));
		return $ucwords ? ucwords($label) : $label;
	}

	/**
	 * Converts a CamelCase name into an ID in lowercase.
	 * Words in the ID may be concatenated using the specified character (defaults to '-').
	 * For example, 'PostTag' will be converted to 'post-tag'.
	 * @param string $name the string to be converted
	 * @param string $separator the character used to concatenate the words in the ID
	 * @return string the resulting ID
	 */
	public static function camel2id($name, $separator = '-')
	{
		if ($separator === '_') {
			return trim(strtolower(preg_replace('/(?<![A-Z])[A-Z]/', '_\0', $name)), '_');
		} else {
			return trim(strtolower(str_replace('_', $separator, preg_replace('/(?<![A-Z])[A-Z]/', $separator . '\0', $name))), $separator);
		}
	}

	/**
	 * Converts an ID into a CamelCase name.
	 * Words in the ID separated by `$separator` (defaults to '-') will be concatenated into a CamelCase name.
	 * For example, 'post-tag' is converted to 'PostTag'.
	 * @param string $id the ID to be converted
	 * @param string $separator the character used to separate the words in the ID
	 * @return string the resulting CamelCase name
	 */
	public static function id2camel($id, $separator = '-')
	{
		return str_replace(' ', '', ucwords(implode(' ', explode($separator, $id))));
	}

Antonio Ramirez committed
385
	/**
386
	 * Converts any "CamelCased" into an "underscored_word".
387 388
	 * @param string $words the word(s) to underscore
	 * @return string
Antonio Ramirez committed
389
	 */
390
	public static function underscore($words)
Antonio Ramirez committed
391
	{
392
		return strtolower(preg_replace('/(?<=\\w)([A-Z])/', '_\\1', $words));
Antonio Ramirez committed
393 394 395 396 397
	}

	/**
	 * Returns a human-readable string from $word
	 * @param string $word the string to humanize
398
	 * @param bool $ucAll whether to set all words to uppercase or not
Antonio Ramirez committed
399 400
	 * @return string
	 */
401
	public static function humanize($word, $ucAll = false)
Antonio Ramirez committed
402 403
	{
		$word = str_replace('_', ' ', preg_replace('/_id$/', '', $word));
404
		return $ucAll ? ucwords($word) : ucfirst($word);
Antonio Ramirez committed
405 406 407
	}

	/**
408
	 * Same as camelize but first char is in lowercase.
Antonio Ramirez committed
409 410 411 412 413 414 415 416 417 418 419 420 421
	 * Converts a word like "send_email" to "sendEmail". It
	 * will remove non alphanumeric character from the word, so
	 * "who's online" will be converted to "whoSOnline"
	 * @param string $word to lowerCamelCase
	 * @return string
	 */
	public static function variablize($word)
	{
		$word = static::camelize($word);
		return strtolower($word[0]) . substr($word, 1);
	}

	/**
Antonio Ramirez committed
422 423 424 425
	 * Converts a class name to its table name (pluralized)
	 * naming conventions. For example, converts "Person" to "people"
	 * @param string $class_name the class name for getting related table_name
	 * @return string
Antonio Ramirez committed
426 427 428 429 430 431 432 433 434
	 */
	public static function tableize($class_name)
	{
		return static::pluralize(static::underscore($class_name));
	}

	/**
	 * Returns a string with all spaces converted to given replacement and
	 * non word characters removed.  Maps special characters to ASCII using
435 436 437
	 * `Inflector::$transliteration`
	 * @param string $string An arbitrary string to convert
	 * @param string $replacement The replacement to use for spaces
Antonio Ramirez committed
438 439 440 441 442 443 444 445 446 447 448 449 450 451
	 * @return string The converted string.
	 */
	public static function slug($string, $replacement = '-')
	{
		$map = static::$transliteration + array(
				'/[^\w\s]/' => ' ',
				'/\\s+/' => $replacement,
				'/(?<=[a-z])([A-Z])/' => $replacement . '\\1',
				str_replace(':rep', preg_quote($replacement, '/'), '/^[:rep]+|[:rep]+$/') => ''
			);
		return preg_replace(array_keys($map), array_values($map), $string);
	}

	/**
Antonio Ramirez committed
452 453 454
	 * Converts a table name to its class name. For example, converts "people" to "Person"
	 * @param string $table_name
	 * @return string
Antonio Ramirez committed
455 456 457 458 459 460 461
	 */
	public static function classify($table_name)
	{
		return static::camelize(static::singularize($table_name));
	}

	/**
462
	 * Converts number to its ordinal English form. For example, converts 13 to 13th, 2 to 2nd ...
Antonio Ramirez committed
463 464 465 466 467 468 469
	 * @param int $number the number to get its ordinal value
	 * @return string
	 */
	public static function ordinalize($number)
	{
		if (in_array(($number % 100), range(11, 13))) {
			return $number . 'th';
Qiang Xue committed
470 471 472 473 474 475
		}
		switch (($number % 10)) {
			case 1: return $number . 'st';
			case 2: return $number . 'nd';
			case 3: return $number . 'rd';
			default: return $number . 'th';
Antonio Ramirez committed
476 477 478
		}
	}
}