Class: Unicoder::Builder::Types

Inherits:
Object
  • Object
show all
Includes:
Unicoder::Builder, MultiDimensionalArrayBuilder
Defined in:
lib/unicoder/builders/types.rb

Constant Summary collapse

NONCHARACTERS = 
[
    *0xFDD0..0xFDEF,
    0xFFFE,  0xFFFF,
   0x1FFFE, 0x1FFFF,
   0x2FFFE, 0x2FFFF,
   0x3FFFE, 0x3FFFF,
   0x4FFFE, 0x4FFFF,
   0x5FFFE, 0x5FFFF,
   0x6FFFE, 0x6FFFF,
   0x7FFFE, 0x7FFFF,
   0x8FFFE, 0x8FFFF,
   0x9FFFE, 0x9FFFF,
   0xAFFFE, 0xAFFFF,
   0xBFFFE, 0xBFFFF,
   0xCFFFE, 0xCFFFF,
   0xDFFFE, 0xDFFFF,
   0xEFFFE, 0xEFFFF,
   0xFFFFE, 0xFFFFF,
  0x10FFFE, 0x10FFFF,
]

Instance Attribute Summary

Attributes included from Unicoder::Builder

#formats, #index, #option

Instance Method Summary collapse

Methods included from MultiDimensionalArrayBuilder

#assign_codepoint, #compress!, #remove_trailing_nils!

Methods included from Unicoder::Builder

#assign, #assign_codepoint, build, #export, #initialize, #meta, #parse_file

Instance Method Details

#initialize_index ⇒ Object 



28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
 
# File 'lib/unicoder/builders/types.rb', line 28

def initialize_index
  @index = {
    TYPES: [],
    TYPE_NAMES: %w[
      Graphic
      Format
      Control
      Private-use
      Surrogate
      Noncharacter
      Reserved
    ],
    OFFSETS: [
      0x10000,
      0x1000,
      0x100,
      0x10
    ],
  }
end

#parse! ⇒ Object 



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
 
# File 'lib/unicoder/builders/types.rb', line 49

def parse!
  parse_file :general_categories, :line, regex: /^(?<from>[^. ]+)(?:..(?<to>\S+))?\s*; (?<category>\S+).*$/ do |line|
    if line["to"]
      codepoints = Range.new(line["from"].to_i(16), line["to"].to_i(16))
    else
      codepoints = [line["from"].to_i(16)]
    end

    codepoints.each{ |codepoint|
      case line["category"]
      when "Cf", "Zl", "Zp"
        type = 1
      when "Cc"
        type = 2
      when "Co"
        type = 3
      when "Cs"
        type = 4
      when "Cn"
        if NONCHARACTERS.include?(codepoint)
          type = 5
        else
          type = 6
        end
      end
      
      assign :TYPES, codepoint, type
    }
  end

  4.times{ compress! @index[:TYPES] }
end