Class: Yosina::Transliterators::ProlongedSoundMarks::Transliterator

Inherits:
BaseTransliterator show all
Includes:
CharType
Defined in:
lib/yosina/transliterators/prolonged_sound_marks.rb

Overview

Transliterator for prolonged sound marks

Constant Summary

Constants included from CharType

CharType::HYPHEN_LIKE_CHARS

Instance Attribute Summary collapse

Instance Method Summary collapse

Methods included from CharType

#alphanumeric?, #fullwidth?, #fullwidth_alphanumeric?, #halfwidth?, #halfwidth_alphanumeric?, #hatsuon?, #hiragana?, #hyphen_like?, #katakana?, #prolongable?, #prolonged_sound_mark?, #sokuon?

Constructor Details

#initialize(options = {}) ⇒ Transliterator

Initialize the transliterator with options

Parameters:

  • options (Hash) (defaults to: {})

    Configuration options

Options Hash (options):

  • :skip_already_transliterated_chars (Boolean)

    Skip chars that were already processed. Default: false.

  • :allow_prolonged_hatsuon (Boolean)

    Allow prolonging ん/ン/ン. Default: false.

  • :allow_prolonged_sokuon (Boolean)

    Allow prolonging っ/ッ/ッ. Default: false.

  • :replace_prolonged_marks_following_alnums (Boolean)

    Replace prolonged marks after alphanum with hyphens. Default: false.



99
100
101
102
103
104
105
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 99

def initialize(options = {})
  super()
  @skip_already_transliterated_chars = options.fetch(:skip_already_transliterated_chars, false)
  @allow_prolonged_hatsuon = options.fetch(:allow_prolonged_hatsuon, false)
  @allow_prolonged_sokuon = options.fetch(:allow_prolonged_sokuon, false)
  @replace_prolonged_marks_following_alnums = options.fetch(:replace_prolonged_marks_following_alnums, false)
end

Instance Attribute Details

#allow_prolonged_hatsuonObject (readonly)

Returns the value of attribute allow_prolonged_hatsuon.



85
86
87
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 85

def allow_prolonged_hatsuon
  @allow_prolonged_hatsuon
end

#allow_prolonged_sokuonObject (readonly)

Returns the value of attribute allow_prolonged_sokuon.



85
86
87
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 85

def allow_prolonged_sokuon
  @allow_prolonged_sokuon
end

#replace_prolonged_marks_following_alnumsObject (readonly)

Returns the value of attribute replace_prolonged_marks_following_alnums.



85
86
87
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 85

def replace_prolonged_marks_following_alnums
  @replace_prolonged_marks_following_alnums
end

#skip_already_transliterated_charsObject (readonly)

Returns the value of attribute skip_already_transliterated_chars.



85
86
87
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 85

def skip_already_transliterated_chars
  @skip_already_transliterated_chars
end

Instance Method Details

#call(input_chars) ⇒ Enumerable<Char>

Convert hyphen-like characters to appropriate prolonged sound marks

Parameters:

  • input_chars (Enumerable<Char>)

    The characters to transliterate

Returns:

  • (Enumerable<Char>)

    The transliterated characters



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
# File 'lib/yosina/transliterators/prolonged_sound_marks.rb', line 111

def call(input_chars)
  offset = 0
  processed_char_in_lookahead = false
  lookahead_buf = []
  last_non_prolonged_char = nil

  Chars.enum do |y|
    input_chars.each do |char|
      unless lookahead_buf.empty?
        if !char.c.empty? && hyphen_like?(char.c.ord)
          processed_char_in_lookahead = true unless char.source.nil?
          lookahead_buf << char
          next
        end
        prev_non_prolonged_char = last_non_prolonged_char
        last_non_prolonged_char = char

        if (prev_non_prolonged_char.nil? || alphanumeric?(prev_non_prolonged_char.c.ord)) && (
          !@skip_already_transliterated_chars || !processed_char_in_lookahead
        )
          halfwidth = halfwidth?(
            prev_non_prolonged_char.nil? ? last_non_prolonged_char.c.ord : prev_non_prolonged_char.c.ord
          )
          replacement = halfwidth ? "\u002d" : "\uff0d"
          lookahead_buf.each do |buffered_char|
            y << Char.new(c: replacement, offset: offset, source: buffered_char)
            offset += replacement.length
          end
        else
          lookahead_buf.each do |buffered_char|
            y << buffered_char.with_offset(offset)
            offset += buffered_char.c.length
          end
        end

        lookahead_buf.clear
        y << char.with_offset(offset)
        offset += char.c.length
        last_non_prolonged_char = char
        processed_char_in_lookahead = false
        next
      end
      if !char.c.empty? && hyphen_like?(char.c.ord)
        should_procses = !@skip_already_transliterated_chars || !char.transliterated?
        if should_procses && !last_non_prolonged_char.nil?
          if prolongable_char?(last_non_prolonged_char.c.ord)
            replacement = halfwidth?(last_non_prolonged_char.c.ord) ? "\uff70" : "\u30fc"
            y << Char.new(c: replacement, offset: offset, source: char)
            offset += replacement.length
            next
          elsif @replace_prolonged_marks_following_alnums && alphanumeric?(last_non_prolonged_char.c.ord)
            lookahead_buf << char
            next
          end
        end
      else
        last_non_prolonged_char = char
      end
      y << char.with_offset(offset)
      offset += char.c.length
    end
  end
end