core_ext 0.0.1

data/lib/core_ext/inflector/inflections.rb

@@ -0,0 +1,244 @@
+require 'core_ext/array/prepend_and_append'
+require 'i18n'
+
+module CoreExt
+  module Inflector
+    extend self
+
+    # A singleton instance of this class is yielded by Inflector.inflections,
+    # which can then be used to specify additional inflection rules. If passed
+    # an optional locale, rules for other languages can be specified. The
+    # default locale is <tt>:en</tt>. Only rules for English are provided.
+    #
+    #   CoreExt::Inflector.inflections(:en) do |inflect|
+    #     inflect.plural /^(ox)$/i, '\1\2en'
+    #     inflect.singular /^(ox)en/i, '\1'
+    #
+    #     inflect.irregular 'octopus', 'octopi'
+    #
+    #     inflect.uncountable 'equipment'
+    #   end
+    #
+    # New rules are added at the top. So in the example above, the irregular
+    # rule for octopus will now be the first of the pluralization and
+    # singularization rules that is runs. This guarantees that your rules run
+    # before any of the rules that may already have been loaded.
+    class Inflections
+
+      # TODO Add concurrent-ruby to support thread safe
+      # @__instance__ = Concurrent::Map.new
+      @__instance__ = {}
+
+      class Uncountables < Array
+        def initialize
+          @regex_array = []
+          super
+        end
+
+        def delete(entry)
+          super entry
+          @regex_array.delete(to_regex(entry))
+        end
+
+        def <<(*word)
+          add(word)
+        end
+
+        def add(words)
+          self.concat(words.flatten.map(&:downcase))
+          @regex_array += self.map {|word|  to_regex(word) }
+          self
+        end
+
+        def uncountable?(str)
+          @regex_array.any? { |regex| regex === str }
+        end
+
+        private
+          def to_regex(string)
+            /\b#{::Regexp.escape(string)}\Z/i
+          end
+      end
+
+      def self.instance(locale = :en)
+        @__instance__[locale] ||= new
+      end
+
+      attr_reader :plurals, :singulars, :uncountables, :humans, :acronyms, :acronym_regex
+
+      def initialize
+        @plurals, @singulars, @uncountables, @humans, @acronyms, @acronym_regex = [], [], Uncountables.new, [], {}, /(?=a)b/
+      end
+
+      # Private, for the test suite.
+      def initialize_dup(orig) # :nodoc:
+        %w(plurals singulars uncountables humans acronyms acronym_regex).each do |scope|
+          instance_variable_set("@#{scope}", orig.send(scope).dup)
+        end
+      end
+
+      # Specifies a new acronym. An acronym must be specified as it will appear
+      # in a camelized string. An underscore string that contains the acronym
+      # will retain the acronym when passed to +camelize+, +humanize+, or
+      # +titleize+. A camelized string that contains the acronym will maintain
+      # the acronym when titleized or humanized, and will convert the acronym
+      # into a non-delimited single lowercase word when passed to +underscore+.
+      #
+      #   acronym 'HTML'
+      #   titleize 'html'     # => 'HTML'
+      #   camelize 'html'     # => 'HTML'
+      #   underscore 'MyHTML' # => 'my_html'
+      #
+      # The acronym, however, must occur as a delimited unit and not be part of
+      # another word for conversions to recognize it:
+      #
+      #   acronym 'HTTP'
+      #   camelize 'my_http_delimited' # => 'MyHTTPDelimited'
+      #   camelize 'https'             # => 'Https', not 'HTTPs'
+      #   underscore 'HTTPS'           # => 'http_s', not 'https'
+      #
+      #   acronym 'HTTPS'
+      #   camelize 'https'   # => 'HTTPS'
+      #   underscore 'HTTPS' # => 'https'
+      #
+      # Note: Acronyms that are passed to +pluralize+ will no longer be
+      # recognized, since the acronym will not occur as a delimited unit in the
+      # pluralized result. To work around this, you must specify the pluralized
+      # form as an acronym as well:
+      #
+      #    acronym 'API'
+      #    camelize(pluralize('api')) # => 'Apis'
+      #
+      #    acronym 'APIs'
+      #    camelize(pluralize('api')) # => 'APIs'
+      #
+      # +acronym+ may be used to specify any word that contains an acronym or
+      # otherwise needs to maintain a non-standard capitalization. The only
+      # restriction is that the word must begin with a capital letter.
+      #
+      #   acronym 'RESTful'
+      #   underscore 'RESTful'           # => 'restful'
+      #   underscore 'RESTfulController' # => 'restful_controller'
+      #   titleize 'RESTfulController'   # => 'RESTful Controller'
+      #   camelize 'restful'             # => 'RESTful'
+      #   camelize 'restful_controller'  # => 'RESTfulController'
+      #
+      #   acronym 'McDonald'
+      #   underscore 'McDonald' # => 'mcdonald'
+      #   camelize 'mcdonald'   # => 'McDonald'
+      def acronym(word)
+        @acronyms[word.downcase] = word
+        @acronym_regex = /#{@acronyms.values.join("|")}/
+      end
+
+      # Specifies a new pluralization rule and its replacement. The rule can
+      # either be a string or a regular expression. The replacement should
+      # always be a string that may include references to the matched data from
+      # the rule.
+      def plural(rule, replacement)
+        @uncountables.delete(rule) if rule.is_a?(String)
+        @uncountables.delete(replacement)
+        @plurals.prepend([rule, replacement])
+      end
+
+      # Specifies a new singularization rule and its replacement. The rule can
+      # either be a string or a regular expression. The replacement should
+      # always be a string that may include references to the matched data from
+      # the rule.
+      def singular(rule, replacement)
+        @uncountables.delete(rule) if rule.is_a?(String)
+        @uncountables.delete(replacement)
+        @singulars.prepend([rule, replacement])
+      end
+
+      # Specifies a new irregular that applies to both pluralization and
+      # singularization at the same time. This can only be used for strings, not
+      # regular expressions. You simply pass the irregular in singular and
+      # plural form.
+      #
+      #   irregular 'octopus', 'octopi'
+      #   irregular 'person', 'people'
+      def irregular(singular, plural)
+        @uncountables.delete(singular)
+        @uncountables.delete(plural)
+
+        s0 = singular[0]
+        srest = singular[1..-1]
+
+        p0 = plural[0]
+        prest = plural[1..-1]
+
+        if s0.upcase == p0.upcase
+          plural(/(#{s0})#{srest}$/i, '\1' + prest)
+          plural(/(#{p0})#{prest}$/i, '\1' + prest)
+
+          singular(/(#{s0})#{srest}$/i, '\1' + srest)
+          singular(/(#{p0})#{prest}$/i, '\1' + srest)
+        else
+          plural(/#{s0.upcase}(?i)#{srest}$/,   p0.upcase   + prest)
+          plural(/#{s0.downcase}(?i)#{srest}$/, p0.downcase + prest)
+          plural(/#{p0.upcase}(?i)#{prest}$/,   p0.upcase   + prest)
+          plural(/#{p0.downcase}(?i)#{prest}$/, p0.downcase + prest)
+
+          singular(/#{s0.upcase}(?i)#{srest}$/,   s0.upcase   + srest)
+          singular(/#{s0.downcase}(?i)#{srest}$/, s0.downcase + srest)
+          singular(/#{p0.upcase}(?i)#{prest}$/,   s0.upcase   + srest)
+          singular(/#{p0.downcase}(?i)#{prest}$/, s0.downcase + srest)
+        end
+      end
+
+      # Specifies words that are uncountable and should not be inflected.
+      #
+      #   uncountable 'money'
+      #   uncountable 'money', 'information'
+      #   uncountable %w( money information rice )
+      def uncountable(*words)
+        @uncountables.add(words)
+      end
+
+      # Specifies a humanized form of a string by a regular expression rule or
+      # by a string mapping. When using a regular expression based replacement,
+      # the normal humanize formatting is called after the replacement. When a
+      # string is used, the human form should be specified as desired (example:
+      # 'The name', not 'the_name').
+      #
+      #   human /_cnt$/i, '\1_count'
+      #   human 'legacy_col_person_name', 'Name'
+      def human(rule, replacement)
+        @humans.prepend([rule, replacement])
+      end
+
+      # Clears the loaded inflections within a given scope (default is
+      # <tt>:all</tt>). Give the scope as a symbol of the inflection type, the
+      # options are: <tt>:plurals</tt>, <tt>:singulars</tt>, <tt>:uncountables</tt>,
+      # <tt>:humans</tt>.
+      #
+      #   clear :all
+      #   clear :plurals
+      def clear(scope = :all)
+        case scope
+          when :all
+            @plurals, @singulars, @uncountables, @humans = [], [], Uncountables.new, []
+          else
+            instance_variable_set "@#{scope}", []
+        end
+      end
+    end
+
+    # Yields a singleton instance of Inflector::Inflections so you can specify
+    # additional inflector rules. If passed an optional locale, rules for other
+    # languages can be specified. If not specified, defaults to <tt>:en</tt>.
+    # Only rules for English are provided.
+    #
+    #   CoreExt::Inflector.inflections(:en) do |inflect|
+    #     inflect.uncountable 'rails'
+    #   end
+    def inflections(locale = :en)
+      if block_given?
+        yield Inflections.instance(locale)
+      else
+        Inflections.instance(locale)
+      end
+    end
+  end
+end

data/lib/core_ext/inflector/methods.rb

@@ -0,0 +1,381 @@
+require 'core_ext/inflections'
+
+module CoreExt
+  # The Inflector transforms words from singular to plural, class names to table
+  # names, modularized class names to ones without, and class names to foreign
+  # keys. The default inflections for pluralization, singularization, and
+  # uncountable words are kept in inflections.rb.
+  #
+  # The Rails core team has stated patches for the inflections library will not
+  # be accepted in order to avoid breaking legacy applications which may be
+  # relying on errant inflections. If you discover an incorrect inflection and
+  # require it for your application or wish to define rules for languages other
+  # than English, please correct or add them yourself (explained below).
+  module Inflector
+    extend self
+
+    # Returns the plural form of the word in the string.
+    #
+    # If passed an optional +locale+ parameter, the word will be
+    # pluralized using rules defined for that language. By default,
+    # this parameter is set to <tt>:en</tt>.
+    #
+    #   pluralize('post')             # => "posts"
+    #   pluralize('octopus')          # => "octopi"
+    #   pluralize('sheep')            # => "sheep"
+    #   pluralize('words')            # => "words"
+    #   pluralize('CamelOctopus')     # => "CamelOctopi"
+    #   pluralize('ley', :es)         # => "leyes"
+    def pluralize(word, locale = :en)
+      apply_inflections(word, inflections(locale).plurals)
+    end
+
+    # The reverse of #pluralize, returns the singular form of a word in a
+    # string.
+    #
+    # If passed an optional +locale+ parameter, the word will be
+    # singularized using rules defined for that language. By default,
+    # this parameter is set to <tt>:en</tt>.
+    #
+    #   singularize('posts')            # => "post"
+    #   singularize('octopi')           # => "octopus"
+    #   singularize('sheep')            # => "sheep"
+    #   singularize('word')             # => "word"
+    #   singularize('CamelOctopi')      # => "CamelOctopus"
+    #   singularize('leyes', :es)       # => "ley"
+    def singularize(word, locale = :en)
+      apply_inflections(word, inflections(locale).singulars)
+    end
+
+    # Converts strings to UpperCamelCase.
+    # If the +uppercase_first_letter+ parameter is set to false, then produces
+    # lowerCamelCase.
+    #
+    # Also converts '/' to '::' which is useful for converting
+    # paths to namespaces.
+    #
+    #   camelize('active_model')                # => "ActiveModel"
+    #   camelize('active_model', false)         # => "activeModel"
+    #   camelize('active_model/errors')         # => "ActiveModel::Errors"
+    #   camelize('active_model/errors', false)  # => "activeModel::Errors"
+    #
+    # As a rule of thumb you can think of +camelize+ as the inverse of
+    # #underscore, though there are cases where that does not hold:
+    #
+    #   camelize(underscore('SSLError'))        # => "SslError"
+    def camelize(term, uppercase_first_letter = true)
+      string = term.to_s
+      if uppercase_first_letter
+        string = string.sub(/^[a-z\d]*/) { |match| inflections.acronyms[match] || match.capitalize }
+      else
+        string = string.sub(/^(?:#{inflections.acronym_regex}(?=\b|[A-Z_])|\w)/) { |match| match.downcase }
+      end
+      string.gsub!(/(?:_|(\/))([a-z\d]*)/i) { "#{$1}#{inflections.acronyms[$2] || $2.capitalize}" }
+      string.gsub!('/'.freeze, '::'.freeze)
+      string
+    end
+
+    # Makes an underscored, lowercase form from the expression in the string.
+    #
+    # Changes '::' to '/' to convert namespaces to paths.
+    #
+    #   underscore('ActiveModel')         # => "active_model"
+    #   underscore('ActiveModel::Errors') # => "active_model/errors"
+    #
+    # As a rule of thumb you can think of +underscore+ as the inverse of
+    # #camelize, though there are cases where that does not hold:
+    #
+    #   camelize(underscore('SSLError'))  # => "SslError"
+    def underscore(camel_cased_word)
+      return camel_cased_word unless camel_cased_word =~ /[A-Z-]|::/
+      word = camel_cased_word.to_s.gsub('::'.freeze, '/'.freeze)
+      word.gsub!(/(?:(?<=([A-Za-z\d]))|\b)(#{inflections.acronym_regex})(?=\b|[^a-z])/) { "#{$1 && '_'.freeze }#{$2.downcase}" }
+      word.gsub!(/([A-Z\d]+)([A-Z][a-z])/, '\1_\2'.freeze)
+      word.gsub!(/([a-z\d])([A-Z])/, '\1_\2'.freeze)
+      word.tr!("-".freeze, "_".freeze)
+      word.downcase!
+      word
+    end
+
+    # Tweaks an attribute name for display to end users.
+    #
+    # Specifically, performs these transformations:
+    #
+    # * Applies human inflection rules to the argument.
+    # * Deletes leading underscores, if any.
+    # * Removes a "_id" suffix if present.
+    # * Replaces underscores with spaces, if any.
+    # * Downcases all words except acronyms.
+    # * Capitalizes the first word.
+    #
+    # The capitalization of the first word can be turned off by setting the
+    # +:capitalize+ option to false (default is true).
+    #
+    #   humanize('employee_salary')              # => "Employee salary"
+    #   humanize('author_id')                    # => "Author"
+    #   humanize('author_id', capitalize: false) # => "author"
+    #   humanize('_id')                          # => "Id"
+    #
+    # If "SSL" was defined to be an acronym:
+    #
+    #   humanize('ssl_error') # => "SSL error"
+    #
+    def humanize(lower_case_and_underscored_word, options = {})
+      result = lower_case_and_underscored_word.to_s.dup
+
+      inflections.humans.each { |(rule, replacement)| break if result.sub!(rule, replacement) }
+
+      result.sub!(/\A_+/, ''.freeze)
+      result.sub!(/_id\z/, ''.freeze)
+      result.tr!('_'.freeze, ' '.freeze)
+
+      result.gsub!(/([a-z\d]*)/i) do |match|
+        "#{inflections.acronyms[match] || match.downcase}"
+      end
+
+      if options.fetch(:capitalize, true)
+        result.sub!(/\A\w/) { |match| match.upcase }
+      end
+
+      result
+    end
+
+    # Capitalizes all the words and replaces some characters in the string to
+    # create a nicer looking title. +titleize+ is meant for creating pretty
+    # output. It is not used in the Rails internals.
+    #
+    # +titleize+ is also aliased as +titlecase+.
+    #
+    #   titleize('man from the boondocks')   # => "Man From The Boondocks"
+    #   titleize('x-men: the last stand')    # => "X Men: The Last Stand"
+    #   titleize('TheManWithoutAPast')       # => "The Man Without A Past"
+    #   titleize('raiders_of_the_lost_ark')  # => "Raiders Of The Lost Ark"
+    def titleize(word)
+      humanize(underscore(word)).gsub(/\b(?<!['’`])[a-z]/) { |match| match.capitalize }
+    end
+
+    # Creates the name of a table like Rails does for models to table names.
+    # This method uses the #pluralize method on the last word in the string.
+    #
+    #   tableize('RawScaledScorer') # => "raw_scaled_scorers"
+    #   tableize('ham_and_egg')     # => "ham_and_eggs"
+    #   tableize('fancyCategory')   # => "fancy_categories"
+    def tableize(class_name)
+      pluralize(underscore(class_name))
+    end
+
+    # Creates a class name from a plural table name like Rails does for table
+    # names to models. Note that this returns a string and not a Class (To
+    # convert to an actual class follow +classify+ with #constantize).
+    #
+    #   classify('ham_and_eggs') # => "HamAndEgg"
+    #   classify('posts')        # => "Post"
+    #
+    # Singular names are not handled correctly:
+    #
+    #   classify('calculus')     # => "Calculu"
+    def classify(table_name)
+      # strip out any leading schema name
+      camelize(singularize(table_name.to_s.sub(/.*\./, ''.freeze)))
+    end
+
+    # Replaces underscores with dashes in the string.
+    #
+    #   dasherize('puni_puni') # => "puni-puni"
+    def dasherize(underscored_word)
+      underscored_word.tr('_'.freeze, '-'.freeze)
+    end
+
+    # Removes the module part from the expression in the string.
+    #
+    #   demodulize('ActiveRecord::CoreExtensions::String::Inflections') # => "Inflections"
+    #   demodulize('Inflections')                                       # => "Inflections"
+    #   demodulize('::Inflections')                                     # => "Inflections"
+    #   demodulize('')                                                  # => ""
+    #
+    # See also #deconstantize.
+    def demodulize(path)
+      path = path.to_s
+      if i = path.rindex('::')
+        path[(i+2)..-1]
+      else
+        path
+      end
+    end
+
+    # Removes the rightmost segment from the constant expression in the string.
+    #
+    #   deconstantize('Net::HTTP')   # => "Net"
+    #   deconstantize('::Net::HTTP') # => "::Net"
+    #   deconstantize('String')      # => ""
+    #   deconstantize('::String')    # => ""
+    #   deconstantize('')            # => ""
+    #
+    # See also #demodulize.
+    def deconstantize(path)
+      path.to_s[0, path.rindex('::') || 0] # implementation based on the one in facets' Module#spacename
+    end
+
+    # Creates a foreign key name from a class name.
+    # +separate_class_name_and_id_with_underscore+ sets whether
+    # the method should put '_' between the name and 'id'.
+    #
+    #   foreign_key('Message')        # => "message_id"
+    #   foreign_key('Message', false) # => "messageid"
+    #   foreign_key('Admin::Post')    # => "post_id"
+    def foreign_key(class_name, separate_class_name_and_id_with_underscore = true)
+      underscore(demodulize(class_name)) + (separate_class_name_and_id_with_underscore ? "_id" : "id")
+    end
+
+    # Tries to find a constant with the name specified in the argument string.
+    #
+    #   'Module'.constantize   # => Module
+    #   'Foo::Bar'.constantize # => Foo::Bar
+    #
+    # The name is assumed to be the one of a top-level constant, no matter
+    # whether it starts with "::" or not. No lexical context is taken into
+    # account:
+    #
+    #   C = 'outside'
+    #   module M
+    #     C = 'inside'
+    #     C               # => 'inside'
+    #     'C'.constantize # => 'outside', same as ::C
+    #   end
+    #
+    # NameError is raised when the name is not in CamelCase or the constant is
+    # unknown.
+    def constantize(camel_cased_word)
+      names = camel_cased_word.split('::'.freeze)
+
+      # Trigger a built-in NameError exception including the ill-formed constant in the message.
+      Object.const_get(camel_cased_word) if names.empty?
+
+      # Remove the first blank element in case of '::ClassName' notation.
+      names.shift if names.size > 1 && names.first.empty?
+
+      names.inject(Object) do |constant, name|
+        if constant == Object
+          constant.const_get(name)
+        else
+          candidate = constant.const_get(name)
+          next candidate if constant.const_defined?(name, false)
+          next candidate unless Object.const_defined?(name)
+
+          # Go down the ancestors to check if it is owned directly. The check
+          # stops when we reach Object or the end of ancestors tree.
+          constant = constant.ancestors.inject do |const, ancestor|
+            break const    if ancestor == Object
+            break ancestor if ancestor.const_defined?(name, false)
+            const
+          end
+
+          # owner is in Object, so raise
+          constant.const_get(name, false)
+        end
+      end
+    end
+
+    # Tries to find a constant with the name specified in the argument string.
+    #
+    #   safe_constantize('Module')   # => Module
+    #   safe_constantize('Foo::Bar') # => Foo::Bar
+    #
+    # The name is assumed to be the one of a top-level constant, no matter
+    # whether it starts with "::" or not. No lexical context is taken into
+    # account:
+    #
+    #   C = 'outside'
+    #   module M
+    #     C = 'inside'
+    #     C                     # => 'inside'
+    #     safe_constantize('C') # => 'outside', same as ::C
+    #   end
+    #
+    # +nil+ is returned when the name is not in CamelCase or the constant (or
+    # part of it) is unknown.
+    #
+    #   safe_constantize('blargle')                  # => nil
+    #   safe_constantize('UnknownModule')            # => nil
+    #   safe_constantize('UnknownModule::Foo::Bar')  # => nil
+    def safe_constantize(camel_cased_word)
+      constantize(camel_cased_word)
+    rescue NameError => e
+      raise if e.name && !(camel_cased_word.to_s.split("::").include?(e.name.to_s) ||
+        e.name.to_s == camel_cased_word.to_s)
+    rescue ArgumentError => e
+      raise unless e.message =~ /not missing constant #{const_regexp(camel_cased_word)}\!$/
+    end
+
+    # Returns the suffix that should be added to a number to denote the position
+    # in an ordered sequence such as 1st, 2nd, 3rd, 4th.
+    #
+    #   ordinal(1)     # => "st"
+    #   ordinal(2)     # => "nd"
+    #   ordinal(1002)  # => "nd"
+    #   ordinal(1003)  # => "rd"
+    #   ordinal(-11)   # => "th"
+    #   ordinal(-1021) # => "st"
+    def ordinal(number)
+      abs_number = number.to_i.abs
+
+      if (11..13).include?(abs_number % 100)
+        "th"
+      else
+        case abs_number % 10
+          when 1; "st"
+          when 2; "nd"
+          when 3; "rd"
+          else    "th"
+        end
+      end
+    end
+
+    # Turns a number into an ordinal string used to denote the position in an
+    # ordered sequence such as 1st, 2nd, 3rd, 4th.
+    #
+    #   ordinalize(1)     # => "1st"
+    #   ordinalize(2)     # => "2nd"
+    #   ordinalize(1002)  # => "1002nd"
+    #   ordinalize(1003)  # => "1003rd"
+    #   ordinalize(-11)   # => "-11th"
+    #   ordinalize(-1021) # => "-1021st"
+    def ordinalize(number)
+      "#{number}#{ordinal(number)}"
+    end
+
+    private
+
+    # Mounts a regular expression, returned as a string to ease interpolation,
+    # that will match part by part the given constant.
+    #
+    #   const_regexp("Foo::Bar::Baz") # => "Foo(::Bar(::Baz)?)?"
+    #   const_regexp("::")            # => "::"
+    def const_regexp(camel_cased_word) #:nodoc:
+      parts = camel_cased_word.split("::".freeze)
+
+      return Regexp.escape(camel_cased_word) if parts.blank?
+
+      last  = parts.pop
+
+      parts.reverse.inject(last) do |acc, part|
+        part.empty? ? acc : "#{part}(::#{acc})?"
+      end
+    end
+
+    # Applies inflection rules for +singularize+ and +pluralize+.
+    #
+    #  apply_inflections('post', inflections.plurals)    # => "posts"
+    #  apply_inflections('posts', inflections.singulars) # => "post"
+    def apply_inflections(word, rules)
+      result = word.to_s.dup
+
+      if word.empty? || inflections.uncountables.uncountable?(result)
+        result
+      else
+        rules.each { |(rule, replacement)| break if result.sub!(rule, replacement) }
+        result
+      end
+    end
+  end
+end