Class: Unicoder::Builder::Name

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

Constant Summary collapse

JAMO_INITIAL = 
4352
JAMO_MEDIAL = 
4449
JAMO_FINAL = 
4520
JAMO_END = 
4697
CJK = 
"CJK UNIFIED IDEOGRAPH-"
TANGUT = 
"TANGUT IDEOGRAPH-"
REPLACE_COUNT = 
500
REPLACE_BASE = 
?[.ord

Instance Attribute Summary

Attributes included from Unicoder::Builder

#formats, #index, #option

Instance Method Summary collapse

Methods included from ReplaceCommonWords

#replace_common_words!

Methods included from Unicoder::Builder

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

Instance Method Details

#initialize_index ⇒ Object 



19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
 
# File 'lib/unicoder/builders/name.rb', line 19

def initialize_index
  @index = {
    NAMES: {},
    ALIASES: {},
    # HANGUL: [],
    CP_RANGES: {
      CJK => [], # filled while parsing
      TANGUT => [], # filled while parsing
      "EGYPTIAN HIEROGLYPH-" => [[0x13460, 0x143FA]],
      "KHITAN SMALL SCRIPT CHARACTER-" => [[0x18B00, 0x18CFF]],
      "NUSHU CHARACTER-" => [[0x1B170, 0x1B2FB]],
      "CJK COMPATIBILITY IDEOGRAPH-" => [[0xF900, 0xFAFF], [0x2F800, 0x2FA1D]],
    },
    # see https://en.wikipedia.org/wiki/Korean_language_and_computers#Hangul_Syllables_Area
    JAMO: {
      INITIAL: [],
      MEDIAL: [],
      FINAL: [""],
    },
  }
  @words = []
  @range_start = nil
end

#parse! ⇒ Object 



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
 
# File 'lib/unicoder/builders/name.rb', line 43

def parse!
  if option =~ /charkeys/
    get_key = ->(codepoint){ [codepoint].pack("U*") }
  else
    get_key = -> (codepoint){ codepoint }
  end

  parse_file :unicode_data, :line, regex: /^(?<codepoint>.+?);(?<name>.+?);.*$/ do |line|
    if line["name"][0] == "<" && line["name"][-1] == ">"
      if line["name"] =~ /First/
        @range_start = line["codepoint"].to_i(16)
      elsif line["name"] =~ /Last/ && @range_start
        case line["name"]
        when /Hangul/
          # currently not necessary
          # @index[:HANGUL] << [@range_start, line["codepoint"].to_i(16)]
        when /CJK/
          @index[:CP_RANGES][CJK] << [@range_start, line["codepoint"].to_i(16)]
        when /Tangut/
          @index[:CP_RANGES][TANGUT] << [@range_start, line["codepoint"].to_i(16)]
        else
          # no name
          warn "ignoring range: #{line["name"]}"
        end
        @range_start = nil
      elsif line["name"] != "<control>"
        raise ArgumentError, "inconsistent range found in data, don't know what to do"
      end
    elsif line["name"] =~ Regexp.union(@index[:CP_RANGES].keys.map{/^#{_1}/})
      # ignore
    else
      assign :NAMES, line["codepoint"].to_i(16), line["name"]
      @words += line["name"].split
    end
  end

  replace_common_words! :NAMES, @words, REPLACE_COUNT, REPLACE_BASE

  parse_file :name_aliases, :line, regex: /^(?<codepoint>.+?);(?<alias>.+?);(?<type>.*)$/ do |line|
    @index[:ALIASES][get_key[line["codepoint"].to_i(16)]] ||= {}
    @index[:ALIASES][get_key[line["codepoint"].to_i(16)]][line["type"].to_sym] ||= []
    @index[:ALIASES][get_key[line["codepoint"].to_i(16)]][line["type"].to_sym] << line["alias"]
  end

  parse_file :jamo, :line, regex: /^(?<codepoint>.+?); (?<short_name>.*?) +#.*$/ do |line|
    case line["codepoint"].to_i(16)
    when JAMO_INITIAL...JAMO_MEDIAL
      @index[:JAMO][:INITIAL] << line["short_name"]
    when JAMO_MEDIAL...JAMO_FINAL
      @index[:JAMO][:MEDIAL] << line["short_name"]
    when JAMO_FINAL..JAMO_END
      @index[:JAMO][:FINAL] << line["short_name"]
    end
  end
end