aboutsummaryrefslogtreecommitdiffstats
path: root/activesupport/lib/active_support/inflector/inflections.rb
blob: 6cfa8bb5aa6dd5b4dd03ec9e3c2dc7458a06edc2 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
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
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
# frozen_string_literal: true

require "concurrent/map"
require "active_support/core_ext/array/prepend_and_append"
require "active_support/core_ext/regexp"
require "active_support/i18n"

module ActiveSupport
  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.
    #
    #   ActiveSupport::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
      @__instance__ = Concurrent::Map.new

      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)
          words = words.flatten.map(&:downcase)
          concat(words)
          @regex_array += words.map { |word| to_regex(word) }
          self
        end

        def uncountable?(str)
          @regex_array.any? { |regex| regex.match? 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
      attr_reader :acronyms_camelize_regex, :acronyms_underscore_regex # :nodoc:

      def initialize
        @plurals, @singulars, @uncountables, @humans, @acronyms = [], [], Uncountables.new, [], {}
        define_acronym_regex_patterns
      end

      # Private, for the test suite.
      def initialize_dup(orig) # :nodoc:
        %w(plurals singulars uncountables humans acronyms).each do |scope|
          instance_variable_set("@#{scope}", orig.send(scope).dup)
        end
        define_acronym_regex_patterns
      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
        define_acronym_regex_patterns
      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

      private

        def define_acronym_regex_patterns
          @acronym_regex             = @acronyms.empty? ? /(?=a)b/ : /#{@acronyms.values.join("|")}/
          @acronyms_camelize_regex   = /^(?:#{@acronym_regex}(?=\b|[A-Z_])|\w)/
          @acronyms_underscore_regex = /(?:(?<=([A-Za-z\d]))|\b)(#{@acronym_regex})(?=\b|[^a-z])/
        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.
    #
    #   ActiveSupport::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