BaseInflector.php 18.6 KB
Newer Older
Antonio Ramirez committed
1 2 3
<?php
/**
 * @link http://www.yiiframework.com/
Carsten Brandt committed
4
 * @copyright Copyright (c) 2008 Yii Software LLC
Antonio Ramirez committed
5 6 7
 * @license http://www.yiiframework.com/license/
 */

8
namespace yii\helpers;
Antonio Ramirez committed
9 10 11 12

use Yii;

/**
13
 * BaseInflector provides concrete implementation for [[Inflector]].
14
 *
15
 * Do not use BaseInflector. Use [[Inflector]] instead.
Antonio Ramirez committed
16 17
 *
 * @author Antonio Ramirez <amigo.cobos@gmail.com>
18
 * @author Alexander Makarov <sam@rmcreative.ru>
Antonio Ramirez committed
19 20
 * @since 2.0
 */
21
class BaseInflector
Antonio Ramirez committed
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
    /**
     * @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.
     */
    public static $plurals = [
        '/([nrlm]ese|deer|fish|sheep|measles|ois|pox|media)$/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',
    ];
    /**
     * @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.
     */
    public static $singulars = [
        '/([nrlm]ese|deer|fish|sheep|measles|ois|pox|media|ss)$/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' => '',
    ];
    /**
     * @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.
     */
    public static $specials = [
        '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',
    ];
    /**
220
     * @var array fallback map for transliteration used by [[slug()]] when intl isn't available.
221 222 223 224 225 226 227 228 229 230 231 232 233
     */
    public static $transliteration = [
        'À' => 'A', 'Á' => 'A', 'Â' => 'A', 'Ã' => 'A', 'Ä' => 'A', 'Å' => 'A', 'Æ' => 'AE', 'Ç' => 'C',
        'È' => 'E', 'É' => 'E', 'Ê' => 'E', 'Ë' => 'E', 'Ì' => 'I', 'Í' => 'I', 'Î' => 'I', 'Ï' => 'I',
        'Ð' => 'D', 'Ñ' => 'N', 'Ò' => 'O', 'Ó' => 'O', 'Ô' => 'O', 'Õ' => 'O', 'Ö' => 'O', 'Ő' => 'O',
        'Ø' => 'O', 'Ù' => 'U', 'Ú' => 'U', 'Û' => 'U', 'Ü' => 'U', 'Ű' => 'U', 'Ý' => 'Y', 'Þ' => 'TH',
        'ß' => 'ss',
        'à' => 'a', 'á' => 'a', 'â' => 'a', 'ã' => 'a', 'ä' => 'a', 'å' => 'a', 'æ' => 'ae', 'ç' => 'c',
        'è' => 'e', 'é' => 'e', 'ê' => 'e', 'ë' => 'e', 'ì' => 'i', 'í' => 'i', 'î' => 'i', 'ï' => 'i',
        'ð' => 'd', 'ñ' => 'n', 'ò' => 'o', 'ó' => 'o', 'ô' => 'o', 'õ' => 'o', 'ö' => 'o', 'ő' => 'o',
        'ø' => 'o', 'ù' => 'u', 'ú' => 'u', 'û' => 'u', 'ü' => 'u', 'ű' => 'u', 'ý' => 'y', 'þ' => 'th',
        'ÿ' => 'y',
    ];
234 235 236 237 238 239
    /**
     * @var mixed Either a [[Transliterator]] or a string from which a [[Transliterator]]
     * can be built for transliteration used by [[slug()]] when intl is available.
     * @see http://php.net/manual/en/transliterator.transliterate.php
     */
    public static $transliterator = 'Any-Latin; NFKD';
240

241

242 243 244 245
    /**
     * 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'.
246
     * @param string $word the word to be pluralized
247 248 249 250 251 252 253 254 255 256 257 258
     * @return string the pluralized word
     */
    public static function pluralize($word)
    {
        if (isset(static::$specials[$word])) {
            return static::$specials[$word];
        }
        foreach (static::$plurals as $rule => $replacement) {
            if (preg_match($rule, $word)) {
                return preg_replace($rule, $replacement, $word);
            }
        }
Antonio Ramirez committed
259

260 261
        return $word;
    }
Antonio Ramirez committed
262

263 264
    /**
     * Returns the singular of the $word
265
     * @param string $word the english word to singularize
266 267 268 269 270 271 272 273 274 275 276 277 278
     * @return string Singular noun.
     */
    public static function singularize($word)
    {
        $result = array_search($word, static::$specials, true);
        if ($result !== false) {
            return $result;
        }
        foreach (static::$singulars as $rule => $replacement) {
            if (preg_match($rule, $word)) {
                return preg_replace($rule, $replacement, $word);
            }
        }
Antonio Ramirez committed
279

280 281
        return $word;
    }
Antonio Ramirez committed
282

283 284 285
    /**
     * Converts an underscored or CamelCase word into a English
     * sentence.
286 287
     * @param string $words
     * @param boolean $ucAll whether to set all words to uppercase
288 289 290 291 292
     * @return string
     */
    public static function titleize($words, $ucAll = false)
    {
        $words = static::humanize(static::underscore($words), $ucAll);
293

294 295
        return $ucAll ? ucwords($words) : ucfirst($words);
    }
296

297 298 299 300 301 302
    /**
     * 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()
303
     * @param string $word the word to CamelCase
304 305 306 307 308 309
     * @return string
     */
    public static function camelize($word)
    {
        return str_replace(' ', '', ucwords(preg_replace('/[^A-Za-z0-9]+/', ' ', $word)));
    }
310

311 312 313
    /**
     * Converts a CamelCase name into space-separated words.
     * For example, 'PostTag' will be converted to 'Post Tag'.
314 315 316
     * @param string $name the string to be converted
     * @param boolean $ucwords whether to capitalize the first letter in each word
     * @return string the resulting words
317 318 319 320 321 322 323
     */
    public static function camel2words($name, $ucwords = true)
    {
        $label = trim(strtolower(str_replace([
            '-',
            '_',
            '.'
324
        ], ' ', preg_replace('/(?<![A-Z])[A-Z]/', ' \0', $name))));
Antonio Ramirez committed
325

326 327
        return $ucwords ? ucwords($label) : $label;
    }
Antonio Ramirez committed
328

329 330 331 332
    /**
     * 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'.
333 334
     * @param string $name the string to be converted
     * @param string $separator the character used to concatenate the words in the ID
335
     * @param boolean|string $strict whether to insert a separator between two consecutive uppercase chars, defaults to false
336 337
     * @return string the resulting ID
     */
338
    public static function camel2id($name, $separator = '-', $strict = false)
339
    {
Tobias Munk committed
340
        $regex = $strict ? '/[A-Z]/' : '/(?<![A-Z])[A-Z]/';
341
        if ($separator === '_') {
342
            return trim(strtolower(preg_replace($regex, '_\0', $name)), '_');
343
        } else {
344
            return trim(strtolower(str_replace('_', $separator, preg_replace($regex, $separator . '\0', $name))), $separator);
345 346
        }
    }
Antonio Ramirez committed
347

348 349 350 351
    /**
     * 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'.
352 353
     * @param string $id the ID to be converted
     * @param string $separator the character used to separate the words in the ID
354 355 356 357 358 359
     * @return string the resulting CamelCase name
     */
    public static function id2camel($id, $separator = '-')
    {
        return str_replace(' ', '', ucwords(implode(' ', explode($separator, $id))));
    }
Antonio Ramirez committed
360

361 362
    /**
     * Converts any "CamelCased" into an "underscored_word".
363
     * @param string $words the word(s) to underscore
364 365 366 367 368 369
     * @return string
     */
    public static function underscore($words)
    {
        return strtolower(preg_replace('/(?<=\\w)([A-Z])/', '_\\1', $words));
    }
Antonio Ramirez committed
370

371 372
    /**
     * Returns a human-readable string from $word
373 374
     * @param string $word the string to humanize
     * @param boolean $ucAll whether to set all words to uppercase or not
375 376 377 378 379
     * @return string
     */
    public static function humanize($word, $ucAll = false)
    {
        $word = str_replace('_', ' ', preg_replace('/_id$/', '', $word));
Antonio Ramirez committed
380

381 382 383 384 385 386 387 388
        return $ucAll ? ucwords($word) : ucfirst($word);
    }

    /**
     * Same as camelize but first char is in lowercase.
     * 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"
389
     * @param string $word to lowerCamelCase
390 391 392 393 394 395 396 397 398 399 400 401
     * @return string
     */
    public static function variablize($word)
    {
        $word = static::camelize($word);

        return strtolower($word[0]) . substr($word, 1);
    }

    /**
     * Converts a class name to its table name (pluralized)
     * naming conventions. For example, converts "Person" to "people"
402
     * @param string $className the class name for getting related table_name
403 404 405 406 407 408 409 410
     * @return string
     */
    public static function tableize($className)
    {
        return static::pluralize(static::underscore($className));
    }

    /**
411 412 413 414 415 416 417
     * Returns a string with all spaces converted to given replacement,
     * non word characters removed and the rest of characters transliterated.
     *
     * If intl extension isn't available uses fallback that converts latin characters only
     * and removes the rest. You may customize characters map via $transliteration property
     * of the helper.
     *
418 419 420 421
     * @param string $string An arbitrary string to convert
     * @param string $replacement The replacement to use for spaces
     * @param boolean $lowercase whether to return the string in lowercase or not. Defaults to `true`.
     * @return string The converted string.
422 423 424
     */
    public static function slug($string, $replacement = '-', $lowercase = true)
    {
425
        $string = static::transliterate($string);
426
        $string = preg_replace('/[^a-zA-Z0-9=\s—–-]+/u', '', $string);
427
        $string = preg_replace('/[=\s—–-]+/u', $replacement, $string);
428 429 430 431 432
        $string = trim($string, $replacement);

        return $lowercase ? strtolower($string) : $string;
    }

433 434 435 436 437 438 439 440 441 442 443 444 445
    /**
     * Returns transliterated version of a string.
     *
     * If intl extension isn't available uses fallback that converts latin characters only
     * and removes the rest. You may customize characters map via $transliteration property
     * of the helper.
     *
     * @param string $string input string
     * @return string
     */
    protected static function transliterate($string)
    {
        if (static::hasIntl()) {
446
            return transliterator_transliterate(static::$transliterator, $string);
447 448 449 450 451 452 453 454 455 456 457 458 459
        } else {
            return str_replace(array_keys(static::$transliteration), static::$transliteration, $string);
        }
    }

    /**
     * @return boolean if intl extension is loaded
     */
    protected static function hasIntl()
    {
        return extension_loaded('intl');
    }

460 461
    /**
     * Converts a table name to its class name. For example, converts "people" to "Person"
462
     * @param string $tableName
463 464 465 466 467 468 469 470 471
     * @return string
     */
    public static function classify($tableName)
    {
        return static::camelize(static::singularize($tableName));
    }

    /**
     * Converts number to its ordinal English form. For example, converts 13 to 13th, 2 to 2nd ...
472
     * @param integer $number the number to get its ordinal value
473 474 475 476 477 478 479 480
     * @return string
     */
    public static function ordinalize($number)
    {
        if (in_array(($number % 100), range(11, 13))) {
            return $number . 'th';
        }
        switch ($number % 10) {
481 482 483 484 485 486 487 488
            case 1:
                return $number . 'st';
            case 2:
                return $number . 'nd';
            case 3:
                return $number . 'rd';
            default:
                return $number . 'th';
489 490
        }
    }
491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534

    /**
     * Converts a list of words into a sentence.
     *
     * Special treatment is done for the last few words. For example,
     *
     * ```php
     * $words = ['Spain', 'France'];
     * echo Inflector::sentence($words);
     * // output: Spain and France
     *
     * $words = ['Spain', 'France', 'Italy'];
     * echo Inflector::sentence($words);
     * // output: Spain, France and Italy
     *
     * $words = ['Spain', 'France', 'Italy'];
     * echo Inflector::sentence($words, ' & ');
     * // output: Spain, France & Italy
     * ```
     *
     * @param array $words the words to be converted into an string
     * @param string $twoWordsConnector the string connecting words when there are only two
     * @param string $lastWordConnector the string connecting the last two words. If this is null, it will
     * take the value of `$twoWordsConnector`.
     * @param string $connector the string connecting words other than those connected by
     * $lastWordConnector and $twoWordsConnector
     * @return string the generated sentence
     */
    public static function sentence(array $words, $twoWordsConnector = ' and ', $lastWordConnector = null, $connector = ', ')
    {
        if ($lastWordConnector === null) {
            $lastWordConnector = $twoWordsConnector;
        }
        switch (count($words)) {
            case 0:
                return '';
            case 1:
                return reset($words);
            case 2:
                return implode($twoWordsConnector, $words);
            default:
                return implode($connector, array_slice($words, 0, -1)) . $lastWordConnector . end($words);
        }
    }
Antonio Ramirez committed
535
}