summaryrefslogtreecommitdiff
path: root/test/ruby/enc/test_case_comprehensive.rb
blob: bc57d57ee4ee651d399da1a747dd63cb3af425d4 (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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
# frozen_string_literal: true
# Copyright © 2016 Martin J. Dürst (duerst@it.aoyama.ac.jp)

require "test/unit"

class TestComprehensiveCaseMapping < Test::Unit::TestCase
  UNICODE_VERSION = RbConfig::CONFIG['UNICODE_VERSION']
  path = File.expand_path("../../../enc/unicode/data/#{UNICODE_VERSION}", __dir__)
  UNICODE_DATA_PATH = File.directory?("#{path}/ucd") ? "#{path}/ucd" : path

  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.data_files_available?
    %w[UnicodeData CaseFolding SpecialCasing].all? do |f|
      File.exist?(expand_filename(f))
    end
  end

  def test_data_files_available
    unless TestComprehensiveCaseMapping.data_files_available?
      omit "Unicode data files not available in #{UNICODE_DATA_PATH}."
    end
  end
end

TestComprehensiveCaseMapping.data_files_available? and  class TestComprehensiveCaseMapping
  (CaseTest = Struct.new(:method_name, :attributes, :first_data, :follow_data)).class_eval do
    def initialize(method_name, attributes, first_data, follow_data=first_data)
      super
    end
  end

  def self.read_data_file(filename)
    IO.foreach(expand_filename(filename), encoding: Encoding::ASCII_8BIT) do |line|
      if $. == 1
        if filename == 'UnicodeData'
        elsif line.start_with?("# #{filename}-#{UNICODE_VERSION}.txt")
        else
          raise "File Version Mismatch"
        end
      end
      next if /\A(?:[\#@]|\s*\z)|Surrogate/.match?(line)
      data = line.chomp.split('#')[0].split(/;\s*/, 15)
      code = data[0].to_i(16).chr(Encoding::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 }
    swapcase  = 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] }
    turkic_swapcase  = Hash.new { |h, c| swapcase[c] }
    ascii_upcase     = Hash.new { |h, c| /\A[a-zA-Z]\z/.match?(c) ? upcase[c] : c }
    ascii_downcase   = Hash.new { |h, c| /\A[a-zA-Z]\z/.match?(c) ? downcase[c] : c }
    ascii_titlecase  = Hash.new { |h, c| /\A[a-zA-Z]\z/.match?(c) ? titlecase[c] : c }
    ascii_swapcase   = Hash.new { |h, c| /\A[a-z]\z/.match?(c) ? upcase[c] : (/\A[A-Z]\z/.match?(c) ? downcase[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?
      if code>="\u1C90" and code<="\u1CBF" # exception for Georgian: use lowercase for titlecase
        titlecase[code] = hex2utf8(data[13]) unless data[13].empty?
      else
        titlecase[code] = hex2utf8 data[14] unless data[14].empty?
      end
    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 /\Atr\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

    @@codepoints.each do |c|
      if upcase[c] != c
        if downcase[c] != c
          swapcase[c] = turkic_swapcase[c] =
            case c
            when "\u01C5" then "\u0064\u017D"
            when "\u01C8" then "\u006C\u004A"
            when "\u01CB" then "\u006E\u004A"
            when "\u01F2" then "\u0064\u005A"
            else # Greek
              downcase[upcase[c][0]] + "\u0399"
            end
        else
          swapcase[c] = upcase[c]
          turkic_swapcase[c] = turkic_upcase[c]
        end
      else
        if downcase[c] != c
          swapcase[c] = downcase[c]
          turkic_swapcase[c] = turkic_downcase[c]
        end
      end
    end

    [
      CaseTest.new(:downcase,   [], downcase),
      CaseTest.new(:upcase,     [], upcase),
      CaseTest.new(:capitalize, [], titlecase, downcase),
      CaseTest.new(:swapcase,   [], 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(:swapcase,   [:turkic],     turkic_swapcase),
      CaseTest.new(:upcase,     [:ascii],      ascii_upcase),
      CaseTest.new(:downcase,   [:ascii],      ascii_downcase),
      CaseTest.new(:capitalize, [:ascii],      ascii_titlecase, ascii_downcase),
      CaseTest.new(:swapcase,   [:ascii],      ascii_swapcase),
    ]
  end

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

  def self.generate_unicode_case_mapping_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|
          source = code.encode(encoding) * 5
          target = "#{test.first_data[code]}#{test.follow_data[code]*4}".encode(encoding)
          result = source.__send__(test.method_name, *test.attributes)
          assert_equal target, result,
            proc{"from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"}
        end
      end
    end
  end

  def self.generate_case_mapping_tests(encoding)
    all_tests
    # preselect codepoints to speed up testing for small encodings
    codepoints = @@codepoints.select do |code|
      begin
        code.encode(encoding)
        true
      rescue Encoding::UndefinedConversionError
        false
      end
    end
    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
            begin
              target = "#{test.first_data[code]}#{test.follow_data[code]*4}".encode(encoding)
            rescue Encoding::UndefinedConversionError
              if test.first_data[code]=="i\u0307" or test.follow_data[code]=="i\u0307" # explicit dot above
                first_data = test.first_data[code]=="i\u0307" ? 'i' : test.first_data[code]
                follow_data = test.follow_data[code]=="i\u0307" ? 'i' : test.follow_data[code]
                target = "#{first_data}#{follow_data*4}".encode(encoding)
              elsif code =~ /i|I/ # special case for Turkic
                raise
              else
                target = source
              end
            end
            result = source.send(test.method_name, *test.attributes)
            assert_equal target, result,
              proc{"from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"}
          rescue Encoding::UndefinedConversionError
          end
        end
      end
    end
  end

  # test for encodings that don't yet (or will never) deal with non-ASCII characters
  def self.generate_ascii_only_case_mapping_tests(encoding)
    all_tests
    # preselect codepoints to speed up testing for small encodings
    codepoints = @@codepoints.select do |code|
      begin
        code.encode(encoding)
        true
      rescue Encoding::UndefinedConversionError
        false
      end
    end
    define_method "test_#{encoding}_upcase" do
      codepoints.each do |code|
        begin
          source = code.encode(encoding) * 5
          target = source.tr 'a-z', 'A-Z'
          result = source.upcase
          assert_equal target, result,
            "from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
        rescue Encoding::UndefinedConversionError
        end
      end
    end
    define_method "test_#{encoding}_downcase" do
      codepoints.each do |code|
        begin
          source = code.encode(encoding) * 5
          target = source.tr 'A-Z', 'a-z'
          result = source.downcase
          assert_equal target, result,
            "from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
        rescue Encoding::UndefinedConversionError
        end
      end
    end
    define_method "test_#{encoding}_capitalize" do
      codepoints.each do |code|
        begin
          source = code.encode(encoding) * 5
          target = source[0].tr('a-z', 'A-Z') + source[1..-1].tr('A-Z', 'a-z')
          result = source.capitalize
          assert_equal target, result,
            "from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
        rescue Encoding::UndefinedConversionError
        end
      end
    end
    define_method "test_#{encoding}_swapcase" do
      codepoints.each do |code|
        begin
          source = code.encode(encoding) * 5
          target = source.tr('a-zA-Z', 'A-Za-z')
          result = source.swapcase
          assert_equal target, result,
            "from #{code*5} (#{source.dump}) expected #{target.dump} but was #{result.dump}"
        rescue Encoding::UndefinedConversionError
        end
      end
    end
  end

  generate_case_mapping_tests 'US-ASCII'
  generate_case_mapping_tests 'ASCII-8BIT'
  generate_case_mapping_tests 'ISO-8859-1'
  generate_case_mapping_tests 'ISO-8859-2'
  generate_case_mapping_tests 'ISO-8859-3'
  generate_case_mapping_tests 'ISO-8859-4'
  generate_case_mapping_tests 'ISO-8859-5'
  generate_case_mapping_tests 'ISO-8859-6'
  generate_case_mapping_tests 'ISO-8859-7'
  generate_case_mapping_tests 'ISO-8859-8'
  generate_case_mapping_tests 'ISO-8859-9'
  generate_case_mapping_tests 'ISO-8859-10'
  generate_case_mapping_tests 'ISO-8859-11'
  generate_case_mapping_tests 'ISO-8859-13'
  generate_case_mapping_tests 'ISO-8859-14'
  generate_case_mapping_tests 'ISO-8859-15'
  generate_case_mapping_tests 'ISO-8859-16'
  generate_ascii_only_case_mapping_tests 'KOI8-R'
  generate_ascii_only_case_mapping_tests 'KOI8-U'
  generate_ascii_only_case_mapping_tests 'Big5'
  generate_ascii_only_case_mapping_tests 'EUC-JP'
  generate_ascii_only_case_mapping_tests 'EUC-KR'
  generate_ascii_only_case_mapping_tests 'GB18030'
  generate_ascii_only_case_mapping_tests 'GB2312'
  generate_ascii_only_case_mapping_tests 'GBK'
  generate_ascii_only_case_mapping_tests 'Shift_JIS'
  generate_ascii_only_case_mapping_tests 'Windows-31J'
  generate_case_mapping_tests 'Windows-1250'
  generate_case_mapping_tests 'Windows-1251'
  generate_case_mapping_tests 'Windows-1252'
  generate_case_mapping_tests 'Windows-1253'
  generate_case_mapping_tests 'Windows-1254'
  generate_case_mapping_tests 'Windows-1255'
  generate_ascii_only_case_mapping_tests 'Windows-1256'
  generate_case_mapping_tests 'Windows-1257'
  generate_unicode_case_mapping_tests 'UTF-8'
  generate_unicode_case_mapping_tests 'UTF-16BE'
  generate_unicode_case_mapping_tests 'UTF-16LE'
  generate_unicode_case_mapping_tests 'UTF-32BE'
  generate_unicode_case_mapping_tests 'UTF-32LE'
end