diff --git a/framework/yii/base/Model.php b/framework/yii/base/Model.php index 98901bf..c7432f5 100644 --- a/framework/yii/base/Model.php +++ b/framework/yii/base/Model.php @@ -9,7 +9,7 @@ namespace yii\base; use ArrayObject; use ArrayIterator; -use yii\helpers\StringHelper; +use yii\helpers\Inflector; use yii\validators\RequiredValidator; use yii\validators\Validator; @@ -504,7 +504,7 @@ class Model extends Component implements \IteratorAggregate, \ArrayAccess */ public function generateAttributeLabel($name) { - return StringHelper::camel2words($name, true); + return Inflector::camel2words($name, true); } /** diff --git a/framework/yii/db/ActiveRecord.php b/framework/yii/db/ActiveRecord.php index 2b7d2b8..dd90782 100644 --- a/framework/yii/db/ActiveRecord.php +++ b/framework/yii/db/ActiveRecord.php @@ -18,6 +18,7 @@ use yii\db\Connection; use yii\db\TableSchema; use yii\db\Expression; use yii\helpers\StringHelper; +use yii\helpers\Inflector; /** * ActiveRecord is the base class for classes representing relational data in terms of objects. @@ -261,14 +262,14 @@ class ActiveRecord extends Model /** * Declares the name of the database table associated with this AR class. - * By default this method returns the class name as the table name by calling [[StringHelper::camel2id()]] + * By default this method returns the class name as the table name by calling [[Inflector::camel2id()]] * with prefix 'tbl_'. For example, 'Customer' becomes 'tbl_customer', and 'OrderItem' becomes * 'tbl_order_item'. You may override this method if the table is not named after this convention. * @return string the table name */ public static function tableName() { - return 'tbl_' . StringHelper::camel2id(StringHelper::basename(get_called_class()), '_'); + return 'tbl_' . Inflector::camel2id(StringHelper::basename(get_called_class()), '_'); } /** diff --git a/framework/yii/helpers/Inflector.php b/framework/yii/helpers/Inflector.php new file mode 100644 index 0000000..72f77a7 --- /dev/null +++ b/framework/yii/helpers/Inflector.php @@ -0,0 +1,18 @@ + + * @since 2.0 + */ +class Inflector extends base\Inflector +{ +} diff --git a/framework/yii/helpers/base/Inflector.php b/framework/yii/helpers/base/Inflector.php new file mode 100644 index 0000000..3c1927c --- /dev/null +++ b/framework/yii/helpers/base/Inflector.php @@ -0,0 +1,540 @@ + + * @since 2.0 + */ +class Inflector +{ + + /** + * @var array rules of plural words + */ + protected static $plural = array( + 'rules' => array( + '/(m)ove$/i' => '\1oves', + '/(f)oot$/i' => '\1eet', + '/(h)uman$/i' => '\1umans', + '/(s)tatus$/i' => '\1\2tatuses', + '/(s)taff$/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', + ), + 'uninflected' => array( + '.*[nrlm]ese', + '.*deer', + '.*fish', + '.*measles', + '.*ois', + '.*pox', + '.*sheep', + 'people' + ), + 'irregular' => array( + 'atlas' => 'atlases', + 'beef' => 'beefs', + 'brother' => 'brothers', + 'cafe' => 'cafes', + 'child' => 'children', + 'cookie' => 'cookies', + 'corpus' => 'corpuses', + 'cow' => 'cows', + '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', + 'person' => 'people', + 'sex' => 'sexes', + 'soliloquy' => 'soliloquies', + 'testis' => 'testes', + 'trilby' => 'trilbys', + 'turf' => 'turfs' + ) + ); + /** + * @var array the rules to singular inflector + */ + protected static $singular = array( + 'rules' => array( + '/(s)tatuses$/i' => '\1\2tatus', + '/(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' => '' + ), + 'uninflected' => array( + '.*[nrlm]ese', + '.*deer', + '.*fish', + '.*measles', + '.*ois', + '.*pox', + '.*sheep', + '.*ss' + ), + 'irregular' => array( + 'foes' => 'foe', + 'waves' => 'wave', + 'curves' => 'curve' + ) + ); + + /** + * @var array list of words that should not be inflected + */ + protected static $uninflected = array( + 'Amoyese', + 'bison', + 'Borghese', + 'bream', + 'breeches', + 'britches', + 'buffalo', + 'cantus', + 'carp', + 'chassis', + 'clippers', + 'cod', + 'coitus', + 'Congoese', + 'contretemps', + 'corps', + 'debris', + 'diabetes', + 'djinn', + 'eland', + 'elk', + 'equipment', + 'Faroese', + 'flounder', + 'Foochowese', + 'gallows', + 'Genevese', + 'Genoese', + 'Gilbertese', + 'graffiti', + 'headquarters', + 'herpes', + 'hijinks', + 'Hottentotese', + 'information', + 'innings', + 'jackanapes', + 'Kiplingese', + 'Kongoese', + 'Lucchese', + 'mackerel', + 'Maltese', + '.*?media', + 'mews', + 'moose', + 'mumps', + 'Nankingese', + 'news', + 'nexus', + 'Niasese', + 'Pekingese', + 'Piedmontese', + 'pincers', + 'Pistoiese', + 'pliers', + 'Portuguese', + 'proceedings', + 'rabies', + 'rice', + 'rhinoceros', + 'salmon', + 'Sarawakese', + 'scissors', + 'sea[- ]bass', + 'series', + 'Shavese', + 'shears', + 'siemens', + 'species', + 'swine', + 'testes', + 'trousers', + 'trout', + 'tuna', + 'Vermontese', + 'Wenchowese', + 'whiting', + 'wildebeest', + 'Yengeese' + ); + + /** + * @var array map of special chars and its translation + */ + protected static $transliteration = array( + '/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' + ); + + /** + * 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) + { + $unInflected = ArrayHelper::merge(static::$plural['uninflected'], static::$uninflected); + $irregular = array_keys(static::$plural['irregular']); + + $unInflectedRegex = '(?:' . implode('|', $unInflected) . ')'; + $irregularRegex = '(?:' . implode('|', $irregular) . ')'; + + if (preg_match('/(.*)\\b(' . $irregularRegex . ')$/i', $word, $regs)) + return $regs[1] . substr($word, 0, 1) . substr(static::$plural['irregular'][strtolower($regs[2])], 1); + + if (preg_match('/^(' . $unInflectedRegex . ')$/i', $word, $regs)) + return $word; + + foreach (static::$plural['rules'] 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) + { + + $unInflected = ArrayHelper::merge(static::$singular['uninflected'], static::$uninflected); + + $irregular = array_merge( + static::$singular['irregular'], + array_flip(static::$plural['irregular']) + ); + + $unInflectedRegex = '(?:' . implode('|', $unInflected) . ')'; + $irregularRegex = '(?:' . implode('|', array_keys($irregular)) . ')'; + + + if (preg_match('/(.*)\\b(' . $irregularRegex . ')$/i', $word, $regs)) + return $regs[1] . substr($word, 0, 1) . substr($irregular[strtolower($regs[2])], 1); + + + if (preg_match('/^(' . $unInflectedRegex . ')$/i', $word, $regs)) + return $word; + + + foreach (static::$singular['rules'] 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 bool $ucAll whether to set all words to uppercase + * @return string + */ + public static function titleize($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-Z^a-z^0-9]+/', ' ', $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(array( + '-', + '_', + '.' + ), ' ', preg_replace('/(? ' ', + '/\\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); + } + + /** + * Converts a table name to its class name. For example, converts "people" to "Person" + * @param string $table_name + * @return string + */ + public static function classify($table_name) + { + return static::camelize(static::singularize($table_name)); + } + + /** + * Converts number to its ordinal English form. For example, converts 13 to 13th, 2 to 2nd ... + * @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 $number . 'th'; + } else { + switch (($number % 10)) { + case 1: + return $number . 'st'; + break; + case 2: + return $number . 'nd'; + break; + case 3: + return $number . 'rd'; + default: + return $number . 'th'; + break; + } + } + } +} diff --git a/framework/yii/helpers/base/StringHelper.php b/framework/yii/helpers/base/StringHelper.php index 646bcbb..5b854ac 100644 --- a/framework/yii/helpers/base/StringHelper.php +++ b/framework/yii/helpers/base/StringHelper.php @@ -65,84 +65,4 @@ class StringHelper } return $path; } - - /** - * 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 $name the word to be pluralized - * @return string the pluralized word - */ - public static function pluralize($name) - { - static $rules = array( - '/(m)ove$/i' => '\1oves', - '/(f)oot$/i' => '\1eet', - '/(c)hild$/i' => '\1hildren', - '/(h)uman$/i' => '\1umans', - '/(m)an$/i' => '\1en', - '/(s)taff$/i' => '\1taff', - '/(t)ooth$/i' => '\1eeth', - '/(p)erson$/i' => '\1eople', - '/([m|l])ouse$/i' => '\1ice', - '/(x|ch|ss|sh|us|as|is|os)$/i' => '\1es', - '/([^aeiouy]|qu)y$/i' => '\1ies', - '/(?:([^f])fe|([lr])f)$/i' => '\1\2ves', - '/(shea|lea|loa|thie)f$/i' => '\1ves', - '/([ti])um$/i' => '\1a', - '/(tomat|potat|ech|her|vet)o$/i' => '\1oes', - '/(bu)s$/i' => '\1ses', - '/(ax|test)is$/i' => '\1es', - '/s$/' => 's', - ); - foreach ($rules as $rule => $replacement) { - if (preg_match($rule, $name)) { - return preg_replace($rule, $replacement, $name); - } - } - return $name . 's'; - } - - /** - * 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) - { - $label = trim(strtolower(str_replace(array('-', '_', '.'), ' ', preg_replace('/(? 'moves', + 'foot' => 'feet', + 'child' => 'children', + 'human' => 'humans', + 'man' => 'men', + 'staff' => 'staff', + 'tooth' => 'teeth', + 'person' => 'people', + 'mouse' => 'mice', + 'touch' => 'touches', + 'hash' => 'hashes', + 'shelf' => 'shelves', + 'potato' => 'potatoes', + 'bus' => 'buses', + 'test' => 'tests', + 'car' => 'cars', + ); + + foreach ($testData as $testIn => $testOut) { + $this->assertEquals($testOut, Inflector::pluralize($testIn)); + $this->assertEquals(ucfirst($testOut), ucfirst(Inflector::pluralize($testIn))); + } + } + + public function testSingularize() + { + $testData = array( + 'moves' => 'move', + 'feet' => 'foot', + 'children' => 'child', + 'humans' => 'human', + 'men' => 'man', + 'staff' => 'staff', + 'teeth' => 'tooth', + 'people' => 'person', + 'mice' => 'mouse', + 'touches' => 'touch', + 'hashes' => 'hash', + 'shelves' => 'shelf', + 'potatoes' => 'potato', + 'buses' => 'bus', + 'tests' => 'test', + 'cars' => 'car', + ); + foreach ($testData as $testIn => $testOut) { + $this->assertEquals($testOut, Inflector::singularize($testIn)); + $this->assertEquals(ucfirst($testOut), ucfirst(Inflector::singularize($testIn))); + } + } + + public function testTitleize() + { + $this->assertEquals("Me my self and i", Inflector::titleize('MeMySelfAndI')); + $this->assertEquals("Me My Self And I", Inflector::titleize('MeMySelfAndI', true)); + } + + public function testCamelize() + { + $this->assertEquals("MeMySelfAndI", Inflector::camelize('me my_self-andI')); + } + + public function testUnderscore() + { + $this->assertEquals("me_my_self_and_i", Inflector::underscore('MeMySelfAndI')); + } + + public function testCamel2words() + { + $this->assertEquals('Camel Case', Inflector::camel2words('camelCase')); + $this->assertEquals('Lower Case', Inflector::camel2words('lower_case')); + $this->assertEquals('Tricky Stuff It Is Testing', Inflector::camel2words(' tricky_stuff.it-is testing... ')); + } + + public function testCamel2id() + { + $this->assertEquals('post-tag', Inflector::camel2id('PostTag')); + $this->assertEquals('post_tag', Inflector::camel2id('PostTag', '_')); + + $this->assertEquals('post-tag', Inflector::camel2id('postTag')); + $this->assertEquals('post_tag', Inflector::camel2id('postTag', '_')); + } + + public function testId2camel() + { + $this->assertEquals('PostTag', Inflector::id2camel('post-tag')); + $this->assertEquals('PostTag', Inflector::id2camel('post_tag', '_')); + + $this->assertEquals('PostTag', Inflector::id2camel('post-tag')); + $this->assertEquals('PostTag', Inflector::id2camel('post_tag', '_')); + } + + public function testHumanize() + { + $this->assertEquals("Me my self and i", Inflector::humanize('me_my_self_and_i')); + $this->assertEquals("Me My Self And I", Inflector::humanize('me_my_self_and_i', true)); + } + + public function testVariablize() + { + $this->assertEquals("customerTable", Inflector::variablize('customer_table')); + } + + public function testTableize() + { + $this->assertEquals("customer_tables", Inflector::tableize('customerTable')); + } + + public function testSlug() + { + $this->assertEquals("this-is-a-title", Inflector::slug('this is a title')); + } + + public function testClassify() + { + $this->assertEquals("CustomerTable", Inflector::classify('customer_tables')); + } + + public function testOrdinalize() + { + $this->assertEquals('21st', Inflector::ordinalize('21')); + } +} diff --git a/tests/unit/framework/helpers/StringHelperTest.php b/tests/unit/framework/helpers/StringHelperTest.php index fc76a26..ac6ff34 100644 --- a/tests/unit/framework/helpers/StringHelperTest.php +++ b/tests/unit/framework/helpers/StringHelperTest.php @@ -19,58 +19,6 @@ class StringHelperTest extends \yii\test\TestCase $this->assertEquals('э', StringHelper::substr('это', 0, 2)); } - public function testPluralize() - { - $testData = array( - 'move' => 'moves', - 'foot' => 'feet', - 'child' => 'children', - 'human' => 'humans', - 'man' => 'men', - 'staff' => 'staff', - 'tooth' => 'teeth', - 'person' => 'people', - 'mouse' => 'mice', - 'touch' => 'touches', - 'hash' => 'hashes', - 'shelf' => 'shelves', - 'potato' => 'potatoes', - 'bus' => 'buses', - 'test' => 'tests', - 'car' => 'cars', - ); - - foreach ($testData as $testIn => $testOut) { - $this->assertEquals($testOut, StringHelper::pluralize($testIn)); - $this->assertEquals(ucfirst($testOut), ucfirst(StringHelper::pluralize($testIn))); - } - } - - public function testCamel2words() - { - $this->assertEquals('Camel Case', StringHelper::camel2words('camelCase')); - $this->assertEquals('Lower Case', StringHelper::camel2words('lower_case')); - $this->assertEquals('Tricky Stuff It Is Testing', StringHelper::camel2words(' tricky_stuff.it-is testing... ')); - } - - public function testCamel2id() - { - $this->assertEquals('post-tag', StringHelper::camel2id('PostTag')); - $this->assertEquals('post_tag', StringHelper::camel2id('PostTag', '_')); - - $this->assertEquals('post-tag', StringHelper::camel2id('postTag')); - $this->assertEquals('post_tag', StringHelper::camel2id('postTag', '_')); - } - - public function testId2camel() - { - $this->assertEquals('PostTag', StringHelper::id2camel('post-tag')); - $this->assertEquals('PostTag', StringHelper::id2camel('post_tag', '_')); - - $this->assertEquals('PostTag', StringHelper::id2camel('post-tag')); - $this->assertEquals('PostTag', StringHelper::id2camel('post_tag', '_')); - } - public function testBasename() { $this->assertEquals('', StringHelper::basename(''));