How to turn plural words singular?
I\'m preparing some table names for an ORM, and I want to turn plural table names into single entity names. My only problem is finding an algorithm that does it reliably. He
-
Maybe you need this,It works well ,if you know how to use PHP script.It can turn plural words to single words,and turn single words to plural words too.
class BaseInflector { /** * @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', '/(n)etherlands$/i' => '\1\2etherlands', '/eaus$/' => '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', ]; /** * @var array fallback map for transliteration used by [[transliterate()]] when intl isn't available. */ 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', ]; /** * Shortcut for `Any-Latin; NFKD` transliteration rule. The rule is strict, letters will be transliterated with * the closest sound-representation chars. The result may contain any UTF-8 chars. For example: * `获取到 どちら Українська: ґ,є, Српска: ђ, њ, џ! ¿Español?` will be transliterated to * `huò qǔ dào dochira Ukraí̈nsʹka: g̀,ê, Srpska: đ, n̂, d̂! ¿Español?` * * Used in [[transliterate()]]. * For detailed information see [unicode normalization forms](http://unicode.org/reports/tr15/#Normalization_Forms_Table) * @see http://unicode.org/reports/tr15/#Normalization_Forms_Table * @see transliterate() * @since 2.0.7 */ const TRANSLITERATE_STRICT = 'Any-Latin; NFKD'; /** * Shortcut for `Any-Latin; Latin-ASCII` transliteration rule. The rule is medium, letters will be * transliterated to characters of Latin-1 (ISO 8859-1) ASCII table. For example: * `获取到 どちら Українська: ґ,є, Српска: ђ, њ, џ! ¿Español?` will be transliterated to * `huo qu dao dochira Ukrainsʹka: g,e, Srpska: d, n, d! ¿Espanol?` * * Used in [[transliterate()]]. * For detailed information see [unicode normalization forms](http://unicode.org/reports/tr15/#Normalization_Forms_Table) * @see http://unicode.org/reports/tr15/#Normalization_Forms_Table * @see transliterate() * @since 2.0.7 */ const TRANSLITERATE_MEDIUM = 'Any-Latin; Latin-ASCII'; /** * Shortcut for `Any-Latin; Latin-ASCII; [\u0080-\uffff] remove` transliteration rule. The rule is loose, * letters will be transliterated with the characters of Basic Latin Unicode Block. * For example: * `获取到 どちら Українська: ґ,є, Српска: ђ, њ, џ! ¿Español?` will be transliterated to * `huo qu dao dochira Ukrainska: g,e, Srpska: d, n, d! Espanol?` * * Used in [[transliterate()]]. * For detailed information see [unicode normalization forms](http://unicode.org/reports/tr15/#Normalization_Forms_Table) * @see http://unicode.org/reports/tr15/#Normalization_Forms_Table * @see transliterate() * @since 2.0.7 */ const TRANSLITERATE_LOOSE = 'Any-Latin; Latin-ASCII; [\u0080-\uffff] remove'; /** * @var mixed Either a [[\Transliterator]], or a string from which a [[\Transliterator]] can be built * for transliteration. Used by [[transliterate()]] when intl is available. Defaults to [[TRANSLITERATE_LOOSE]] * @see http://php.net/manual/en/transliterator.transliterate.php */ public static $transliterator = self::TRANSLITERATE_LOOSE; /** * 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 $word the word to be pluralized * @return string the pluralized word */ public static function pluralize($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); } } 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) { $result = array_search($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); } } return $word; } /** * Converts an underscored or CamelCase word into a English * sentence. * @param string $words * @param boolean $ucAll whether to set all words to uppercase * @return string */ public static function titleize($words, $ucAll = false) { $words = static::humanize(static::underscore($words), $ucAll); return $ucAll ? ucwords($words) : ucfirst($words); } /** * 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() * @param string $word the word to CamelCase * @return string */ public static function camelize($word) { return str_replace(' ', '', ucwords(preg_replace('/[^A-Za-z0-9]+/', ' ', $word))); } /** * 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) { $label = trim(strtolower(str_replace([ '-', '_', '.' ], ' ', preg_replace('/(?There is some example.
echo "Inflector Test"; require('PhInflector.php'); echo "
"; echo PhInflector::slug('Höäpeäöäich Médsui27:;;,.1! *"29p'); echo "
"; echo PhInflector::slug('HIJO"$(/&T §!"(/&T"§:;;,.1! *"29p'); echo "
"; echo PhInflector::slug('38917 jiodj d ! *"29p'); echo "
"; echo PhInflector::slug('каи циефле ///!!!');And forward github link click here.
加载中...
- 热议问题