summaryrefslogtreecommitdiff
path: root/test/csv/test_encodings.rb
blob: 8d7de2e728361dd8c6d3bc2785b3d88ba281eb58 (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
#!/usr/bin/env ruby -w
# encoding: UTF-8

# tc_encodings.rb
#
#  Created by James Edward Gray II on 2008-09-13.
#  Copyright 2008 James Edward Gray II. You can redistribute or modify this code
#  under the terms of Ruby's license.

require "test/unit"

require "csv"

class TestEncodings < Test::Unit::TestCase
  def setup
    @temp_csv_path = File.join(File.dirname(__FILE__), "temp.csv")
  end
  
  def teardown
    File.unlink(@temp_csv_path) if File.exist? @temp_csv_path
  end
  
  ########################################
  ### Hand Test Some Popular Encodings ###
  ########################################
  
  def test_parses_utf8_encoding
    assert_parses( [ %w[ one two … ],
                     %w[ 1   …   3 ],
                     %w[ …   5   6 ] ], "UTF-8" )
  end
  
  def test_parses_latin1_encoding
    assert_parses( [ %w[ one    two    Résumé ],
                     %w[ 1      Résumé 3      ],
                     %w[ Résumé 5      6      ] ], "ISO-8859-1" )
  end
  
  def test_parses_utf16be_encoding
    assert_parses( [ %w[ one two … ],
                     %w[ 1   …   3 ],
                     %w[ …   5   6 ] ], "UTF-16BE" )
  end
  
  def test_parses_shift_jis_encoding
    assert_parses( [ %w[ 一 二 三 ],
                     %w[ 四 五 六 ],
                     %w[ 七 八 九 ] ], "Shift_JIS" )
  end
  
  ###########################################################
  ### Try Simple Reading for All Non-dummy Ruby Encodings ###
  ###########################################################
  
  def test_reading_with_most_encodings
    each_encoding do |encoding|
      begin
        assert_parses( [ %w[ abc def ],
                         %w[ ghi jkl ] ], encoding )
      rescue Encoding::ConverterNotFoundError
        fail("Failed to support #{encoding.name}.")
      end
    end
  end
  
  def test_regular_expression_escaping
    each_encoding do |encoding|
      begin
        assert_parses( [ %w[ abc def ],
                         %w[ ghi jkl ] ], encoding, col_sep: "|" )
      rescue Encoding::ConverterNotFoundError
        fail("Failed to properly escape #{encoding.name}.")
      end
    end
  end
  
  #######################################################################
  ### Stress Test ASCII Compatible and Non-ASCII Compatible Encodings ###
  #######################################################################
  
  def test_auto_line_ending_detection
    # arrange data to place a \r at the end of CSV's read ahead point
    encode_for_tests([["a" * 509]], row_sep: "\r\n") do |data|
      assert_equal("\r\n".encode(data.encoding), CSV.new(data).row_sep)
    end
  end
  
  def test_csv_chars_are_transcoded
    encode_for_tests([%w[abc def]]) do |data|
      %w[col_sep row_sep quote_char].each do |csv_char|
        assert_equal( "|".encode(data.encoding),
                      CSV.new(data, csv_char.to_sym => "|").send(csv_char) )
      end
    end
  end
  
  def test_parser_works_with_encoded_headers
    encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
      parsed = CSV.parse(data, headers: true)
      assert( parsed.headers.all? { |h| h.encoding == data.encoding },
              "Wrong data encoding." )
      parsed.each do |row|
        assert( row.fields.all? { |f| f.encoding == data.encoding },
                "Wrong data encoding." )
      end
    end
  end
  
  def test_built_in_converters_transcode_to_utf_8_then_convert
    encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
      parsed = CSV.parse(data, converters: :integer)
      assert( parsed[0].all? { |f| f.encoding == data.encoding },
              "Wrong data encoding." )
      assert_equal([1, 2, 3], parsed[1])
    end
  end
  
  def test_built_in_header_converters_transcode_to_utf_8_then_convert
    encode_for_tests([%w[one two three], %w[1 2 3]]) do |data|
      parsed = CSV.parse( data, headers:           true,
                                header_converters: :downcase )
      assert( parsed.headers.all? { |h| h.encoding.name == "UTF-8" },
              "Wrong data encoding." )
      assert( parsed[0].fields.all? { |f| f.encoding == data.encoding },
              "Wrong data encoding." )
    end
  end
  
  def test_open_allows_you_to_set_encodings
    encode_for_tests([%w[abc def]]) do |data|
      # read and write in encoding
      File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
      CSV.open(@temp_csv_path, "rb:#{data.encoding.name}") do |csv|
        csv.each do |row|
          assert( row.all? { |f| f.encoding == data.encoding },
                  "Wrong data encoding." )
        end
      end
  
      # read and write with transcoding
      File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
        f << data
      end
      CSV.open(@temp_csv_path, "rb:UTF-32BE:#{data.encoding.name}") do |csv|
        csv.each do |row|
          assert( row.all? { |f| f.encoding == data.encoding },
                  "Wrong data encoding." )
        end
      end
    end
  end
  
  def test_foreach_allows_you_to_set_encodings
    encode_for_tests([%w[abc def]]) do |data|
      # read and write in encoding
      File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
      CSV.foreach(@temp_csv_path, encoding: data.encoding.name) do |row|
        assert( row.all? { |f| f.encoding == data.encoding },
                "Wrong data encoding." )
      end
  
      # read and write with transcoding
      File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
        f << data
      end
      CSV.foreach( @temp_csv_path,
                   encoding: "UTF-32BE:#{data.encoding.name}" ) do |row|
        assert( row.all? { |f| f.encoding == data.encoding },
                "Wrong data encoding." )
      end
    end
  end
  
  def test_read_allows_you_to_set_encodings
    encode_for_tests([%w[abc def]]) do |data|
      # read and write in encoding
      File.open(@temp_csv_path, "wb:#{data.encoding.name}") { |f| f << data }
      rows = CSV.read(@temp_csv_path, encoding: data.encoding.name)
      assert( rows.flatten.all? { |f| f.encoding == data.encoding },
              "Wrong data encoding." )
  
      # read and write with transcoding
      File.open(@temp_csv_path, "wb:UTF-32BE:#{data.encoding.name}") do |f|
        f << data
      end
      rows = CSV.read( @temp_csv_path,
                       encoding: "UTF-32BE:#{data.encoding.name}" )
      assert( rows.flatten.all? { |f| f.encoding == data.encoding },
              "Wrong data encoding." )
    end
  end
  
  #################################
  ### Write CSV in any Encoding ###
  #################################
  
  def test_can_write_csv_in_any_encoding
    each_encoding do |encoding|
      # test generate_line with encoding hint
      begin
        csv = %w[abc d|ef].map { |f| f.encode(encoding) }.
          to_csv(col_sep: "|", encoding: encoding.name)
      rescue Encoding::ConverterNotFoundError
        next
      end
      assert_equal(encoding, csv.encoding)
  
      # test generate_line with encoding guessing from fields
      csv = %w[abc d|ef].map { |f| f.encode(encoding) }.to_csv(col_sep: "|")
      assert_equal(encoding, csv.encoding)
  
      # writing to files
      data = encode_ary([%w[abc d,ef], %w[123 456 ]], encoding)
      CSV.open(@temp_csv_path, "wb:#{encoding.name}") do |f|
        data.each { |row| f << row }
      end
      assert_equal(data, CSV.read(@temp_csv_path, encoding: encoding.name))
    end
  end
  
  def test_encoding_is_upgraded_during_writing_as_needed
    data = ["foo".force_encoding("US-ASCII"), "\u3042"]
    assert_equal("US-ASCII", data.first.encoding.name)
    assert_equal("UTF-8",    data.last.encoding.name)
    assert_equal("UTF-8",    data.join.encoding.name)
    assert_equal("UTF-8",    data.to_csv.encoding.name)
  end

  private
  
  def assert_parses(fields, encoding, options = { })
    encoding = Encoding.find(encoding) unless encoding.is_a? Encoding
    fields   = encode_ary(fields, encoding)
    parsed   = CSV.parse(ary_to_data(fields, options), options)
    assert_equal(fields, parsed)
    parsed.flatten.each_with_index do |field, i|
      assert_equal(encoding, field.encoding, "Field[#{i + 1}] was transcoded.")
    end
  end
  
  def encode_ary(ary, encoding)
    ary.map { |row| row.map { |field| field.encode(encoding) } }
  end
  
  def ary_to_data(ary, options = { })
    encoding   = ary.flatten.first.encoding
    quote_char = (options[:quote_char] || '"').encode(encoding)
    col_sep    = (options[:col_sep]    || ",").encode(encoding)
    row_sep    = (options[:row_sep]    || "\n").encode(encoding)
    ary.map { |row|
      row.map { |field|
        [quote_char, field.encode(encoding), quote_char].join
      }.join(col_sep) + row_sep
    }.join.encode(encoding)
  end
  
  def encode_for_tests(data, options = { })
    yield ary_to_data(encode_ary(data, "UTF-8"),    options)
    yield ary_to_data(encode_ary(data, "UTF-16BE"), options)
  end
  
  def each_encoding
    Encoding.list.each do |encoding|
      next if encoding.dummy?  # skip "dummy" encodings
      yield encoding
    end
  end
end