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
|
#!/usr/bin/env ruby
require 'open-uri'
require 'csv'
# https://datatracker.ietf.org/doc/html/rfc5892#appendix-A.1
# https://datatracker.ietf.org/doc/html/rfc5892#appendix-A.2
csv_options = { :col_sep => ';', :skip_blanks => true, :skip_lines => /\A#/ }
unicode_data = URI('https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt')
derived_joining_type = URI('https://www.unicode.org/Public/UCD/latest/ucd/extracted/DerivedJoiningType.txt')
# https://www.unicode.org/reports/tr44/#Canonical_Combining_Class_Values
virama_canonical_combining_class = '9'
virama_codes = CSV.new(unicode_data.read, **csv_options).select do |code, _name, _category, canonical_combining_class|
canonical_combining_class == virama_canonical_combining_class
end.map(&:first)
# https://www.unicode.org/reports/tr44/#Default_Values
# https://www.unicode.org/reports/tr44/#Derived_Extracted
codes_by_joining_type = CSV.new(derived_joining_type.read, **csv_options).group_by do |_code, joining_type|
joining_type.gsub(/#.+/, '').strip
end.transform_values do |rows|
rows.map do |code, _joining_type|
code.strip
end
end
def codes_to_character_class(codes)
characters = codes.map do |code|
code.gsub(/(\h+)/, '\u{\1}').gsub('..', '-')
end
"[#{characters.join}]"
end
puts "VIRAMA_CHARACTER_CLASS = '#{codes_to_character_class(virama_codes)}'"
codes_by_joining_type.slice('L', 'D', 'T', 'R').each do |joining_type, codes|
puts "JOINING_TYPE_#{joining_type}_CHARACTER_CLASS = '#{codes_to_character_class(codes)}'"
end
|
