Class: Unicoder::Builder::SequenceName

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

Instance Attribute Summary

Attributes included from Unicoder::Builder

#formats, #index, #option

Instance Method Summary collapse

Methods included from Unicoder::Builder

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

Instance Method Details

#assign_codepoint(codepoints, value, idx = @index[:SEQUENCES], combine: false) ⇒ Object 



12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
 
# File 'lib/unicoder/builders/sequence_name.rb', line 12

def assign_codepoint(codepoints, value, idx = @index[:SEQUENCES], combine: false)
  if option =~ /charkeys/
    key = codepoints.pack("U*")
  else
    key = codepoints
  end

  if idx.has_key?(codepoints)
    if combine
      idx[key] << " / #{value}"
    else
      # ignore new one
    end
  else
    idx[key] = value
  end
end

#initialize_index ⇒ Object 



6
7
8
9
10
 
# File 'lib/unicoder/builders/sequence_name.rb', line 6

def initialize_index
  @index = {
    SEQUENCES: {},
  }
end

#parse! ⇒ Object 



30
31
32
33
34
35
36
37
38
39
40
41
42
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
 
# File 'lib/unicoder/builders/sequence_name.rb', line 30

def parse!
  parse_file :named_sequences, :line, regex: /^(?!#)(?<name>.+?);(?<codepoints>.+?)$/ do |line|
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, line["name"]
  end

  parse_file :named_sequences_prov, :line, regex: /^(?!#)(?<name>.+?);(?<codepoints>.+?)$/ do |line|
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, line["name"]
  end

  parse_file :standardized_variants, :line, regex: /^(?<codepoints>.+?);\s*(?<variant>.+?)\s*;\s*(?<context>.*?)\s*# (?<name>.+)$/ do |line|
    name = "#{line["name"].strip} (#{line["variant"]})"
    name << " [#{line["context"]}]" if line["context"] && !line["context"].empty?
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, name, combine: true
  end

  parse_file :standardized_variants, :line, regex: /^(?<codepoints>.+?); (?<name>.+?)\s*;$/ do |line|
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, line["name"]
  end

  parse_file :ivd_sequences, :line, regex: /^(?<codepoints>.+?);.*?; (?<name>.+?)$/ do |line|
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, line["name"], combine: true
  end

  parse_file :emoji_variation_sequences, :line, regex: /^(?<codepoints>.+?)\s*;\s*(?<variant>.+?)\s*;\s*# \(.*\)\s*(?<name>.+?)\s*$/ do |line|
    name = "#{line["name"].strip} (#{line["variant"]})"
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, name
  end

  parse_file :emoji_sequences, :line, regex: /^(?<codepoints>.+?)\s*;\s*(?<type>.+?)\s*; (?<name>.+?)\s*#/ do |line|
    next if line["type"] == "Basic_Emoji"
    name = line["name"].gsub(/\\x{(\h+)}/){ [$1.to_i(16)].pack("U") }.upcase
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, name
  end

  parse_file :emoji_zwj_sequences, :line, regex: /^(?<codepoints>.+?)\s*;.*?; (?<name>.+?)\s*#/ do |line|
    name = line["name"].gsub(/\\x{(\h+)}/){ [$1.to_i(16)].pack("U") }.upcase
    assign_codepoint line["codepoints"].split.map{|cp| cp.to_i(16) }, name
  end
end