Module: Yosina::Transliterators::JapaneseIterationMarks::CharType

Included in:
Transliterator
Defined in:
lib/yosina/transliterators/japanese_iteration_marks.rb

Overview

Mix-in for character type checks

Instance Method Summary collapse

Instance Method Details

#hatsuon?(char_code) ⇒ Boolean

Check if character is hatsuon (ん/ン)

Returns:

  • (Boolean)


45
46
47
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 45

def hatsuon?(char_code)
  [0x3093, 0x30f3, 0xff9d].include?(char_code)
end

#hiragana?(char_code) ⇒ Boolean

Check if character is hiragana (excluding small forms and special marks)

Returns:

  • (Boolean)


21
22
23
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 21

def hiragana?(char_code)
  char_code >= 0x3041 && char_code <= 0x3096
end

#iteration_mark?(char) ⇒ Boolean

Check if character is an iteration mark

Returns:

  • (Boolean)


55
56
57
58
59
60
61
62
63
64
65
66
67
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 55

def iteration_mark?(char)
  [
    HIRAGANA_ITERATION_MARK,
    HIRAGANA_VOICED_ITERATION_MARK,
    VERTICAL_HIRAGANA_ITERATION_MARK,
    VERTICAL_HIRAGANA_VOICED_ITERATION_MARK,
    KATAKANA_ITERATION_MARK,
    KATAKANA_VOICED_ITERATION_MARK,
    VERTICAL_KATAKANA_ITERATION_MARK,
    VERTICAL_KATAKANA_VOICED_ITERATION_MARK,
    KANJI_ITERATION_MARK
  ].include?(char)
end

#kanji?(char_code) ⇒ Boolean

Check if character is kanji

Returns:

  • (Boolean)


32
33
34
35
36
37
38
39
40
41
42
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 32

def kanji?(char_code)
  # CJK Unified Ideographs (common kanji ranges)
  (char_code >= 0x4e00 && char_code <= 0x9fff) ||
    (char_code >= 0x3400 && char_code <= 0x4dbf) ||
    (char_code >= 0x20000 && char_code <= 0x2a6df) ||
    (char_code >= 0x2a700 && char_code <= 0x2b73f) ||
    (char_code >= 0x2b740 && char_code <= 0x2b81f) ||
    (char_code >= 0x2b820 && char_code <= 0x2ceaf) ||
    (char_code >= 0x2ceb0 && char_code <= 0x2ebef) ||
    (char_code >= 0x30000 && char_code <= 0x3134f)
end

#katakana?(char_code) ⇒ Boolean

Check if character is katakana (including halfwidth)

Returns:

  • (Boolean)


26
27
28
29
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 26

def katakana?(char_code)
  (char_code >= 0x30a1 && char_code <= 0x30fa) ||
    (char_code >= 0xff66 && char_code <= 0xff9f)
end

#semi_voiced?(char) ⇒ Boolean

Check if character is semi-voiced (has handakuten)

Returns:

  • (Boolean)


75
76
77
78
79
80
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 75

def semi_voiced?(char)
  # Hiragana semi-voiced
  %w[    ].include?(char) ||
    # Katakana semi-voiced
    %w[    ].include?(char)
end

#sokuon?(char_code) ⇒ Boolean

Check if character is sokuon (っ/ッ)

Returns:

  • (Boolean)


50
51
52
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 50

def sokuon?(char_code)
  [0x3063, 0x30c3, 0xff6f].include?(char_code)
end

#voiced?(char) ⇒ Boolean

Check if character is voiced (has dakuten)

Returns:

  • (Boolean)


70
71
72
# File 'lib/yosina/transliterators/japanese_iteration_marks.rb', line 70

def voiced?(char)
  VOICED_CHARS.include?(char)
end