summaryrefslogtreecommitdiff
path: root/test/ruby/enc/test_case_comprehensive.rb
blob: da2354f4b9c5b3832817d43ba6b2e86a1c91189c (plain)
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
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
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
# Copyright © 2016 Martin J. Dürst (duerst@it.aoyama.ac.jp)

require "test/unit"
require 'unicode_normalize/normalize'  # only for UNICODE_VERSION

class CaseTest
  attr_reader :method_name, :attributes, :first_data, :follow_data
  def initialize(method_name, attributes, first_data, follow_data=first_data)
    @method_name = method_name
    @attributes  = attributes
    @first_data  = first_data
    @follow_data = follow_data
  end
end

class TestComprehensiveCaseFold < Test::Unit::TestCase
  UNICODE_VERSION = UnicodeNormalize::UNICODE_VERSION
  UNICODE_DATA_PATH = "../../../enc/unicode/data/#{UNICODE_VERSION}"

  def self.hex2utf8(s)
    s.split(' ').map { |c| c.to_i(16) }.pack('U*')
  end

  def self.expand_filename(basename)
    File.expand_path("#{UNICODE_DATA_PATH}/#{basename}.txt", __dir__)
  end

  def self.read_data_file (filename)
    IO.readlines(expand_filename(filename), encoding: Encoding::ASCII_8BIT)
    .tap do |lines|
           raise "File Version Mismatch" unless filename=='UnicodeData' or /#{filename}-#{UNICODE_VERSION}\.txt/ =~ lines[0]
         end
    .reject { |line| line =~ /^[\#@]/ or line =~ /^\s*$/ or line =~ /Surrogate/ }
    .each do |line|
      data = line.chomp.split('#')[0].split /;\s*/, 15
      code = data[0].to_i(16).chr('UTF-8')
      yield code, data
    end
  end

  def self.read_data
    @@codepoints = []

    downcase  = Hash.new { |h, c| c }
    upcase    = Hash.new { |h, c| c }
    titlecase = Hash.new { |h, c| c }
    casefold  = Hash.new { |h, c| c }
    turkic_upcase    = Hash.new { |h, c| upcase[c] }
    turkic_downcase  = Hash.new { |h, c| downcase[c] }
    turkic_titlecase = Hash.new { |h, c| titlecase[c] }
    ascii_upcase     = Hash.new { |h, c| c =~ /^[a-zA-Z]$/ ? upcase[c] : c }
    ascii_downcase   = Hash.new { |h, c| c =~ /^[a-zA-Z]$/ ? downcase[c] : c }
    ascii_titlecase  = Hash.new { |h, c| c =~ /^[a-zA-Z]$/ ? titlecase[c] : c }

    read_data_file('UnicodeData') do |code, data|
      @@codepoints << code
      upcase[code] = hex2utf8 data[12] unless data[12].empty?
      downcase[code] = hex2utf8 data[13] unless data[13].empty?
      titlecase[code] = hex2utf8 data[14] unless data[14].empty?
    end
    read_data_file('CaseFolding') do |code, data|
      casefold[code] = hex2utf8(data[2]) if data[1] =~ /^[CF]$/
    end

    read_data_file('SpecialCasing') do |code, data|
      case data[4]
      when ''
        upcase[code] = hex2utf8 data[3]
        downcase[code] = hex2utf8 data[1]
        titlecase[code] = hex2utf8 data[2]
      when /^tr\s*/
        if data[4]!='tr After_I'
          turkic_upcase[code] = hex2utf8 data[3]
          turkic_downcase[code] = hex2utf8 data[1]
          turkic_titlecase[code] = hex2utf8 data[2]
        end
      end
    end

    tests = [
      CaseTest.new(:downcase,   [:lithuanian], downcase),
      CaseTest.new(:upcase,     [:lithuanian], upcase),
      CaseTest.new(:capitalize, [:lithuanian], titlecase, downcase),
      # swapcase?????!!!!!
      CaseTest.new(:downcase,   [:fold],       casefold),
      CaseTest.new(:upcase,     [:turkic],     turkic_upcase),
      CaseTest.new(:downcase,   [:turkic],     turkic_downcase),
      CaseTest.new(:capitalize, [:turkic],     turkic_titlecase, turkic_downcase),
      CaseTest.new(:upcase,     [:ascii],      ascii_upcase),
      CaseTest.new(:downcase,   [:ascii],      ascii_downcase),
      CaseTest.new(:capitalize, [:ascii],      ascii_titlecase, ascii_downcase),
    ]
  end

  def self.all_tests
    @@tests ||= read_data
  rescue Errno::ENOENT => e
    @@tests ||= []
  end

  def self.generate_casefold_tests (encoding)
    all_tests.each do |test|
      attributes = test.attributes.map(&:to_s).join '-'
      attributes.prepend '_' unless attributes.empty?
      define_method "test_#{encoding}_#{test.method_name}#{attributes}" do
        @@codepoints.each do |code|
          begin
            source = code.encode(encoding) * 5
            target = test.first_data[code].encode(encoding) + test.follow_data[code].encode(encoding) * 4
            result = source.send(test.method_name, *test.attributes)
            assert_equal target, result,
              "from #{source} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
          rescue Encoding::UndefinedConversionError
          end
        end
      end
    end
  end

  def check_file_available(filename)
    expanded = self.class.expand_filename(filename)
    assert File.exist?(expanded), "File #{expanded} missing."
  end

  def test_AAAAA_data_files_available   # AAAAA makes sure this test is run first
    %w[UnicodeData CaseFolding SpecialCasing].each { |f| check_file_available f }
  end

  generate_casefold_tests 'US-ASCII'
  generate_casefold_tests 'ASCII-8BIT'
  generate_casefold_tests 'UTF-8'
end