aboutsummaryrefslogtreecommitdiffstats
path: root/activesupport/lib/active_support/multibyte/chars.rb
blob: 8152b8fd2298f9dab9b3833afa685bd1e4abc7ff (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
# frozen_string_literal: true

require "active_support/json"
require "active_support/core_ext/string/access"
require "active_support/core_ext/string/behavior"
require "active_support/core_ext/module/delegation"
require "active_support/core_ext/regexp"

module ActiveSupport #:nodoc:
  module Multibyte #:nodoc:
    # Chars enables you to work transparently with UTF-8 encoding in the Ruby
    # String class without having extensive knowledge about the encoding. A
    # Chars object accepts a string upon initialization and proxies String
    # methods in an encoding safe manner. All the normal String methods are also
    # implemented on the proxy.
    #
    # String methods are proxied through the Chars object, and can be accessed
    # through the +mb_chars+ method. Methods which would normally return a
    # String object now return a Chars object so methods can be chained.
    #
    #   'The Perfect String  '.mb_chars.downcase.strip.normalize
    #   # => #<ActiveSupport::Multibyte::Chars:0x007fdc434ccc10 @wrapped_string="the perfect string">
    #
    # Chars objects are perfectly interchangeable with String objects as long as
    # no explicit class checks are made. If certain methods do explicitly check
    # the class, call +to_s+ before you pass chars objects to them.
    #
    #   bad.explicit_checking_method 'T'.mb_chars.downcase.to_s
    #
    # The default Chars implementation assumes that the encoding of the string
    # is UTF-8, if you want to handle different encodings you can write your own
    # multibyte string handler and configure it through
    # ActiveSupport::Multibyte.proxy_class.
    #
    #   class CharsForUTF32
    #     def size
    #       @wrapped_string.size / 4
    #     end
    #
    #     def self.accepts?(string)
    #       string.length % 4 == 0
    #     end
    #   end
    #
    #   ActiveSupport::Multibyte.proxy_class = CharsForUTF32
    class Chars
      include Comparable
      attr_reader :wrapped_string
      alias to_s wrapped_string
      alias to_str wrapped_string

      delegate :<=>, :=~, :acts_like_string?, to: :wrapped_string

      # Creates a new Chars instance by wrapping _string_.
      def initialize(string)
        @wrapped_string = string
        @wrapped_string.force_encoding(Encoding::UTF_8) unless @wrapped_string.frozen?
      end

      # Forward all undefined methods to the wrapped string.
      def method_missing(method, *args, &block)
        result = @wrapped_string.__send__(method, *args, &block)
        if /!$/.match?(method)
          self if result
        else
          result.kind_of?(String) ? chars(result) : result
        end
      end

      # Returns +true+ if _obj_ responds to the given method. Private methods
      # are included in the search only if the optional second parameter
      # evaluates to +true+.
      def respond_to_missing?(method, include_private)
        @wrapped_string.respond_to?(method, include_private)
      end

      # Returns +true+ when the proxy class can handle the string. Returns
      # +false+ otherwise.
      def self.consumes?(string)
        string.encoding == Encoding::UTF_8
      end

      # Works just like <tt>String#split</tt>, with the exception that the items
      # in the resulting list are Chars instances instead of String. This makes
      # chaining methods easier.
      #
      #   'Café périferôl'.mb_chars.split(/é/).map { |part| part.upcase.to_s } # => ["CAF", " P", "RIFERÔL"]
      def split(*args)
        @wrapped_string.split(*args).map { |i| self.class.new(i) }
      end

      # Works like <tt>String#slice!</tt>, but returns an instance of
      # Chars, or +nil+ if the string was not modified. The string will not be
      # modified if the range given is out of bounds
      #
      #   string = 'Welcome'
      #   string.mb_chars.slice!(3)    # => #<ActiveSupport::Multibyte::Chars:0x000000038109b8 @wrapped_string="c">
      #   string # => 'Welome'
      #   string.mb_chars.slice!(0..3) # => #<ActiveSupport::Multibyte::Chars:0x00000002eb80a0 @wrapped_string="Welo">
      #   string # => 'me'
      def slice!(*args)
        string_sliced = @wrapped_string.slice!(*args)
        if string_sliced
          chars(string_sliced)
        end
      end

      # Reverses all characters in the string.
      #
      #   'Café'.mb_chars.reverse.to_s # => 'éfaC'
      def reverse
        chars(Unicode.unpack_graphemes(@wrapped_string).reverse.flatten.pack("U*"))
      end

      # Limits the byte size of the string to a number of bytes without breaking
      # characters. Usable when the storage for a string is limited for some
      # reason.
      #
      #   'こんにちは'.mb_chars.limit(7).to_s # => "こん"
      def limit(limit)
        slice(0...translate_offset(limit))
      end

      # Converts characters in the string to uppercase.
      #
      #   'Laurent, où sont les tests ?'.mb_chars.upcase.to_s # => "LAURENT, OÙ SONT LES TESTS ?"
      def upcase
        chars Unicode.upcase(@wrapped_string)
      end

      # Converts characters in the string to lowercase.
      #
      #   'VĚDA A VÝZKUM'.mb_chars.downcase.to_s # => "věda a výzkum"
      def downcase
        chars Unicode.downcase(@wrapped_string)
      end

      # Converts characters in the string to the opposite case.
      #
      #    'El Cañón'.mb_chars.swapcase.to_s # => "eL cAÑÓN"
      def swapcase
        chars Unicode.swapcase(@wrapped_string)
      end

      # Converts the first character to uppercase and the remainder to lowercase.
      #
      #  'über'.mb_chars.capitalize.to_s # => "Über"
      def capitalize
        (slice(0) || chars("")).upcase + (slice(1..-1) || chars("")).downcase
      end

      # Capitalizes the first letter of every word, when possible.
      #
      #   "ÉL QUE SE ENTERÓ".mb_chars.titleize.to_s    # => "Él Que Se Enteró"
      #   "日本語".mb_chars.titleize.to_s               # => "日本語"
      def titleize
        chars(downcase.to_s.gsub(/\b('?\S)/u) { Unicode.upcase($1) })
      end
      alias_method :titlecase, :titleize

      # Returns the KC normalization of the string by default. NFKC is
      # considered the best normalization form for passing strings to databases
      # and validations.
      #
      # * <tt>form</tt> - The form you want to normalize in. Should be one of the following:
      #   <tt>:c</tt>, <tt>:kc</tt>, <tt>:d</tt>, or <tt>:kd</tt>. Default is
      #   ActiveSupport::Multibyte::Unicode.default_normalization_form
      def normalize(form = nil)
        chars(Unicode.normalize(@wrapped_string, form))
      end

      # Performs canonical decomposition on all the characters.
      #
      #   'é'.length                         # => 2
      #   'é'.mb_chars.decompose.to_s.length # => 3
      def decompose
        chars(Unicode.decompose(:canonical, @wrapped_string.codepoints.to_a).pack("U*"))
      end

      # Performs composition on all the characters.
      #
      #   'é'.length                       # => 3
      #   'é'.mb_chars.compose.to_s.length # => 2
      def compose
        chars(Unicode.compose(@wrapped_string.codepoints.to_a).pack("U*"))
      end

      # Returns the number of grapheme clusters in the string.
      #
      #   'क्षि'.mb_chars.length   # => 4
      #   'क्षि'.mb_chars.grapheme_length # => 3
      def grapheme_length
        Unicode.unpack_graphemes(@wrapped_string).length
      end

      # Replaces all ISO-8859-1 or CP1252 characters by their UTF-8 equivalent
      # resulting in a valid UTF-8 string.
      #
      # Passing +true+ will forcibly tidy all bytes, assuming that the string's
      # encoding is entirely CP1252 or ISO-8859-1.
      def tidy_bytes(force = false)
        chars(Unicode.tidy_bytes(@wrapped_string, force))
      end

      def as_json(options = nil) #:nodoc:
        to_s.as_json(options)
      end

      %w(capitalize downcase reverse tidy_bytes upcase).each do |method|
        define_method("#{method}!") do |*args|
          @wrapped_string = send(method, *args).to_s
          self
        end
      end

      private

        def translate_offset(byte_offset)
          return nil if byte_offset.nil?
          return 0   if @wrapped_string == ""

          begin
            @wrapped_string.byteslice(0...byte_offset).unpack("U*").length
          rescue ArgumentError
            byte_offset -= 1
            retry
          end
        end

        def chars(string)
          self.class.new(string)
        end
    end
  end
end