red-arrow 8.0.0 → 24.0.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (178) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +15 -7
  3. data/ext/arrow/arrow.cpp +67 -0
  4. data/ext/arrow/converters.cpp +10 -0
  5. data/ext/arrow/converters.hpp +310 -46
  6. data/ext/arrow/extconf.rb +41 -22
  7. data/ext/arrow/raw-records.cpp +165 -2
  8. data/ext/arrow/red-arrow.hpp +2 -0
  9. data/ext/arrow/values.cpp +6 -2
  10. data/lib/arrow/array-builder.rb +89 -14
  11. data/{test/test-time32-data-type.rb → lib/arrow/array-computable.rb} +24 -16
  12. data/{test/test-buffer.rb → lib/arrow/array-statistics.rb} +19 -24
  13. data/lib/arrow/array.rb +40 -4
  14. data/lib/arrow/chunked-array.rb +56 -1
  15. data/lib/arrow/column-containable.rb +9 -0
  16. data/lib/arrow/column.rb +49 -4
  17. data/{test/test-tensor.rb → lib/arrow/csv-write-options.rb} +28 -31
  18. data/lib/arrow/data-type.rb +17 -3
  19. data/lib/arrow/decimal128-array-builder.rb +16 -6
  20. data/lib/arrow/decimal128.rb +14 -0
  21. data/lib/arrow/decimal256-array-builder.rb +16 -6
  22. data/lib/arrow/decimal256.rb +14 -0
  23. data/{test/test-float-scalar.rb → lib/arrow/dense-union-array-builder.rb} +27 -24
  24. data/{test/test-boolean-scalar.rb → lib/arrow/dense-union-array.rb} +7 -7
  25. data/lib/arrow/duration-array-builder.rb +27 -0
  26. data/lib/arrow/duration-array.rb +24 -0
  27. data/lib/arrow/duration-data-type.rb +32 -0
  28. data/lib/arrow/expression.rb +6 -2
  29. data/lib/arrow/field-containable.rb +1 -1
  30. data/lib/arrow/field.rb +44 -3
  31. data/lib/arrow/fixed-size-list-array-builder.rb +29 -0
  32. data/lib/arrow/fixed-size-list-data-type.rb +118 -0
  33. data/lib/arrow/function.rb +0 -1
  34. data/lib/arrow/half-float-array-builder.rb +32 -0
  35. data/lib/arrow/half-float-array.rb +24 -0
  36. data/lib/arrow/half-float.rb +118 -0
  37. data/{test/helper/fixture.rb → lib/arrow/input-referable.rb} +7 -6
  38. data/lib/arrow/jruby/array-builder.rb +114 -0
  39. data/lib/arrow/jruby/array.rb +109 -0
  40. data/lib/arrow/jruby/chunked-array.rb +36 -0
  41. data/lib/arrow/jruby/compression-type.rb +26 -0
  42. data/lib/arrow/jruby/csv-read-options.rb +32 -0
  43. data/{test/test-map-data-type.rb → lib/arrow/jruby/data-type.rb} +24 -12
  44. data/lib/arrow/jruby/decimal128.rb +28 -0
  45. data/lib/arrow/jruby/decimal256.rb +28 -0
  46. data/{test/fixture/float-integer.csv → lib/arrow/jruby/error.rb} +7 -4
  47. data/lib/arrow/jruby/file-system.rb +24 -0
  48. data/{test/test-null-array.rb → lib/arrow/jruby/function.rb} +5 -4
  49. data/lib/arrow/jruby/record-batch-iterator.rb +24 -0
  50. data/{test/fixture/null-with-double-quote.csv → lib/arrow/jruby/record-batch.rb} +8 -4
  51. data/{test/fixture/integer-float.csv → lib/arrow/jruby/sort-key.rb} +8 -4
  52. data/lib/arrow/jruby/sort-options.rb +24 -0
  53. data/lib/arrow/jruby/stream-listener-raw.rb +25 -0
  54. data/{test/test-rolling-window.rb → lib/arrow/jruby/table.rb} +19 -19
  55. data/lib/arrow/jruby/writable.rb +24 -0
  56. data/lib/arrow/jruby.rb +52 -0
  57. data/{test/test-date32-array.rb → lib/arrow/large-list-array-builder.rb} +10 -5
  58. data/lib/arrow/large-list-data-type.rb +83 -0
  59. data/lib/arrow/libraries.rb +140 -0
  60. data/lib/arrow/list-array-builder.rb +1 -68
  61. data/lib/arrow/list-data-type.rb +3 -38
  62. data/{test/test-dictionary-array.rb → lib/arrow/list-field-resolvable.rb} +26 -17
  63. data/lib/arrow/list-slice-options.rb +76 -0
  64. data/lib/arrow/list-values-appendable.rb +88 -0
  65. data/lib/arrow/loader.rb +15 -96
  66. data/{test/test-decimal128-array.rb → lib/arrow/make-struct-options.rb} +18 -18
  67. data/lib/arrow/raw-table-converter.rb +10 -3
  68. data/lib/arrow/raw-tensor-converter.rb +89 -0
  69. data/lib/arrow/record-batch-file-reader.rb +2 -0
  70. data/lib/arrow/record-batch-stream-reader.rb +2 -0
  71. data/lib/arrow/record-batch.rb +6 -2
  72. data/{test/fixture/null-without-double-quote.csv → lib/arrow/ruby.rb} +5 -4
  73. data/lib/arrow/scalar.rb +67 -0
  74. data/lib/arrow/slicer.rb +61 -0
  75. data/lib/arrow/sort-key.rb +3 -3
  76. data/lib/arrow/sparse-union-array-builder.rb +56 -0
  77. data/lib/arrow/sparse-union-array.rb +26 -0
  78. data/lib/arrow/stream-decoder.rb +29 -0
  79. data/{test/test-decimal256-data-type.rb → lib/arrow/stream-listener.rb} +25 -9
  80. data/lib/arrow/string-array-builder.rb +30 -0
  81. data/lib/arrow/struct-array-builder.rb +0 -5
  82. data/lib/arrow/table-formatter.rb +38 -8
  83. data/lib/arrow/table-list-formatter.rb +3 -3
  84. data/lib/arrow/table-loader.rb +11 -5
  85. data/lib/arrow/table-saver.rb +4 -3
  86. data/lib/arrow/table-table-formatter.rb +7 -0
  87. data/lib/arrow/table.rb +180 -33
  88. data/lib/arrow/tensor.rb +144 -0
  89. data/lib/arrow/time-unit.rb +31 -0
  90. data/lib/arrow/time32-array-builder.rb +2 -14
  91. data/lib/arrow/time32-data-type.rb +9 -38
  92. data/lib/arrow/time64-array-builder.rb +2 -14
  93. data/lib/arrow/time64-data-type.rb +9 -38
  94. data/lib/arrow/timestamp-array-builder.rb +3 -15
  95. data/lib/arrow/timestamp-data-type.rb +9 -34
  96. data/{test/test-date64-array.rb → lib/arrow/timestamp-parser.rb} +14 -6
  97. data/lib/arrow/union-array-builder.rb +59 -0
  98. data/lib/arrow/union-array.rb +26 -0
  99. data/lib/arrow/version.rb +1 -1
  100. data/lib/arrow.rb +2 -7
  101. data/red-arrow.gemspec +74 -11
  102. metadata +85 -210
  103. data/test/fixture/TestOrcFile.test1.orc +0 -0
  104. data/test/fixture/with-header-float.csv +0 -20
  105. data/test/fixture/with-header.csv +0 -20
  106. data/test/fixture/without-header-float.csv +0 -19
  107. data/test/fixture/without-header.csv +0 -19
  108. data/test/helper/omittable.rb +0 -36
  109. data/test/helper.rb +0 -30
  110. data/test/raw-records/test-basic-arrays.rb +0 -395
  111. data/test/raw-records/test-dense-union-array.rb +0 -521
  112. data/test/raw-records/test-list-array.rb +0 -610
  113. data/test/raw-records/test-map-array.rb +0 -478
  114. data/test/raw-records/test-multiple-columns.rb +0 -65
  115. data/test/raw-records/test-sparse-union-array.rb +0 -511
  116. data/test/raw-records/test-struct-array.rb +0 -515
  117. data/test/raw-records/test-table.rb +0 -47
  118. data/test/run-test.rb +0 -71
  119. data/test/test-array-builder.rb +0 -136
  120. data/test/test-array.rb +0 -325
  121. data/test/test-bigdecimal.rb +0 -40
  122. data/test/test-binary-dictionary-array-builder.rb +0 -103
  123. data/test/test-chunked-array.rb +0 -183
  124. data/test/test-column.rb +0 -92
  125. data/test/test-csv-loader.rb +0 -250
  126. data/test/test-data-type.rb +0 -83
  127. data/test/test-decimal128-array-builder.rb +0 -112
  128. data/test/test-decimal128-data-type.rb +0 -31
  129. data/test/test-decimal128.rb +0 -102
  130. data/test/test-decimal256-array-builder.rb +0 -112
  131. data/test/test-decimal256-array.rb +0 -38
  132. data/test/test-decimal256.rb +0 -102
  133. data/test/test-dense-union-data-type.rb +0 -41
  134. data/test/test-dictionary-data-type.rb +0 -40
  135. data/test/test-expression.rb +0 -40
  136. data/test/test-feather.rb +0 -49
  137. data/test/test-field.rb +0 -91
  138. data/test/test-file-output-stream.rb +0 -54
  139. data/test/test-fixed-size-binary-array-builder.rb +0 -92
  140. data/test/test-fixed-size-binary-array.rb +0 -36
  141. data/test/test-function.rb +0 -210
  142. data/test/test-group.rb +0 -180
  143. data/test/test-list-array-builder.rb +0 -79
  144. data/test/test-list-array.rb +0 -32
  145. data/test/test-list-data-type.rb +0 -69
  146. data/test/test-map-array-builder.rb +0 -110
  147. data/test/test-map-array.rb +0 -33
  148. data/test/test-memory-view.rb +0 -434
  149. data/test/test-orc.rb +0 -173
  150. data/test/test-record-batch-builder.rb +0 -125
  151. data/test/test-record-batch-file-reader.rb +0 -115
  152. data/test/test-record-batch-iterator.rb +0 -37
  153. data/test/test-record-batch-reader.rb +0 -46
  154. data/test/test-record-batch.rb +0 -182
  155. data/test/test-schema.rb +0 -134
  156. data/test/test-slicer.rb +0 -487
  157. data/test/test-sort-indices.rb +0 -40
  158. data/test/test-sort-key.rb +0 -81
  159. data/test/test-sort-options.rb +0 -58
  160. data/test/test-sparse-union-data-type.rb +0 -41
  161. data/test/test-string-dictionary-array-builder.rb +0 -103
  162. data/test/test-struct-array-builder.rb +0 -184
  163. data/test/test-struct-array.rb +0 -94
  164. data/test/test-struct-data-type.rb +0 -112
  165. data/test/test-table.rb +0 -1123
  166. data/test/test-time.rb +0 -288
  167. data/test/test-time32-array.rb +0 -81
  168. data/test/test-time64-array.rb +0 -81
  169. data/test/test-time64-data-type.rb +0 -42
  170. data/test/test-timestamp-array.rb +0 -45
  171. data/test/test-timestamp-data-type.rb +0 -42
  172. data/test/values/test-basic-arrays.rb +0 -325
  173. data/test/values/test-dense-union-array.rb +0 -509
  174. data/test/values/test-dictionary-array.rb +0 -295
  175. data/test/values/test-list-array.rb +0 -571
  176. data/test/values/test-map-array.rb +0 -466
  177. data/test/values/test-sparse-union-array.rb +0 -500
  178. data/test/values/test-struct-array.rb +0 -512
@@ -1,183 +0,0 @@
1
- # Licensed to the Apache Software Foundation (ASF) under one
2
- # or more contributor license agreements. See the NOTICE file
3
- # distributed with this work for additional information
4
- # regarding copyright ownership. The ASF licenses this file
5
- # to you under the Apache License, Version 2.0 (the
6
- # "License"); you may not use this file except in compliance
7
- # with the License. You may obtain a copy of the License at
8
- #
9
- # http://www.apache.org/licenses/LICENSE-2.0
10
- #
11
- # Unless required by applicable law or agreed to in writing,
12
- # software distributed under the License is distributed on an
13
- # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14
- # KIND, either express or implied. See the License for the
15
- # specific language governing permissions and limitations
16
- # under the License.
17
-
18
- class ChunkedArrayTest < Test::Unit::TestCase
19
- test("#each") do
20
- arrays = [
21
- Arrow::BooleanArray.new([true, false]),
22
- Arrow::BooleanArray.new([nil, true]),
23
- ]
24
- chunked_array = Arrow::ChunkedArray.new(arrays)
25
- assert_equal([true, false, nil, true],
26
- chunked_array.to_a)
27
- end
28
-
29
- sub_test_case("#pack") do
30
- test("basic array") do
31
- arrays = [
32
- Arrow::BooleanArray.new([true, false]),
33
- Arrow::BooleanArray.new([nil, true]),
34
- ]
35
- chunked_array = Arrow::ChunkedArray.new(arrays)
36
- packed_chunked_array = chunked_array.pack
37
- assert_equal([
38
- Arrow::BooleanArray,
39
- [true, false, nil, true],
40
- ],
41
- [
42
- packed_chunked_array.class,
43
- packed_chunked_array.to_a,
44
- ])
45
- end
46
-
47
- test("TimestampArray") do
48
- type = Arrow::TimestampDataType.new(:nano)
49
- arrays = [
50
- Arrow::TimestampArrayBuilder.new(type).build([Time.at(0)]),
51
- Arrow::TimestampArrayBuilder.new(type).build([Time.at(1)]),
52
- ]
53
- chunked_array = Arrow::ChunkedArray.new(arrays)
54
- packed_chunked_array = chunked_array.pack
55
- assert_equal([
56
- Arrow::TimestampArray,
57
- [Time.at(0), Time.at(1)],
58
- ],
59
- [
60
- packed_chunked_array.class,
61
- packed_chunked_array.to_a,
62
- ])
63
- end
64
- end
65
-
66
- sub_test_case("#==") do
67
- def setup
68
- arrays = [
69
- Arrow::BooleanArray.new([true]),
70
- Arrow::BooleanArray.new([false, true]),
71
- ]
72
- @chunked_array = Arrow::ChunkedArray.new(arrays)
73
- end
74
-
75
- test("Arrow::ChunkedArray") do
76
- assert do
77
- @chunked_array == @chunked_array
78
- end
79
- end
80
-
81
- test("not Arrow::ChunkedArray") do
82
- assert do
83
- not (@chunked_array == 29)
84
- end
85
- end
86
- end
87
-
88
- sub_test_case("#filter") do
89
- def setup
90
- arrays = [
91
- Arrow::BooleanArray.new([false, true]),
92
- Arrow::BooleanArray.new([false, true, false]),
93
- ]
94
- @chunked_array = Arrow::ChunkedArray.new(arrays)
95
- @options = Arrow::FilterOptions.new
96
- @options.null_selection_behavior = :emit_null
97
- end
98
-
99
- test("Array: boolean") do
100
- filter = [nil, true, true, false, true]
101
- chunks = [
102
- Arrow::BooleanArray.new([nil, true]),
103
- Arrow::BooleanArray.new([false, false]),
104
- ]
105
- filtered_chunked_array = Arrow::ChunkedArray.new(chunks)
106
- assert_equal(filtered_chunked_array,
107
- @chunked_array.filter(filter, @options))
108
- end
109
-
110
- test("Arrow::BooleanArray") do
111
- filter = Arrow::BooleanArray.new([nil, true, true, false, true])
112
- chunks = [
113
- Arrow::BooleanArray.new([nil, true]),
114
- Arrow::BooleanArray.new([false, false]),
115
- ]
116
- filtered_chunked_array = Arrow::ChunkedArray.new(chunks)
117
- assert_equal(filtered_chunked_array,
118
- @chunked_array.filter(filter, @options))
119
- end
120
-
121
- test("Arrow::ChunkedArray") do
122
- chunks = [
123
- Arrow::BooleanArray.new([nil, true]),
124
- Arrow::BooleanArray.new([true, false, true]),
125
- ]
126
- filter = Arrow::ChunkedArray.new(chunks)
127
- filtered_chunks = [
128
- Arrow::BooleanArray.new([nil, true]),
129
- Arrow::BooleanArray.new([false, false]),
130
- ]
131
- filtered_chunked_array = Arrow::ChunkedArray.new(filtered_chunks)
132
- assert_equal(filtered_chunked_array,
133
- @chunked_array.filter(filter, @options))
134
- end
135
- end
136
-
137
- sub_test_case("#take") do
138
- def setup
139
- chunks = [
140
- Arrow::Int16Array.new([1, 0]),
141
- Arrow::Int16Array.new([2]),
142
- ]
143
- @chunked_array = Arrow::ChunkedArray.new(chunks)
144
- end
145
-
146
- test("Arrow: boolean") do
147
- chunks = [
148
- Arrow::Int16Array.new([0, 1]),
149
- Arrow::Int16Array.new([2])
150
- ]
151
- taken_chunked_array = Arrow::ChunkedArray.new(chunks)
152
- indices = [1, 0, 2]
153
- assert_equal(taken_chunked_array,
154
- @chunked_array.take(indices))
155
- end
156
-
157
- test("Arrow::Array") do
158
- chunks = [
159
- Arrow::Int16Array.new([0, 1]),
160
- Arrow::Int16Array.new([2])
161
- ]
162
- taken_chunked_array = Arrow::ChunkedArray.new(chunks)
163
- indices = Arrow::Int16Array.new([1, 0, 2])
164
- assert_equal(taken_chunked_array,
165
- @chunked_array.take(indices))
166
- end
167
-
168
- test("Arrow::ChunkedArray") do
169
- taken_chunks = [
170
- Arrow::Int16Array.new([0, 1]),
171
- Arrow::Int16Array.new([2])
172
- ]
173
- taken_chunked_array = Arrow::ChunkedArray.new(taken_chunks)
174
- indices_chunks = [
175
- Arrow::Int16Array.new([1, 0]),
176
- Arrow::Int16Array.new([2])
177
- ]
178
- indices = Arrow::ChunkedArray.new(indices_chunks)
179
- assert_equal(taken_chunked_array,
180
- @chunked_array.take(indices))
181
- end
182
- end
183
- end
data/test/test-column.rb DELETED
@@ -1,92 +0,0 @@
1
- # Licensed to the Apache Software Foundation (ASF) under one
2
- # or more contributor license agreements. See the NOTICE file
3
- # distributed with this work for additional information
4
- # regarding copyright ownership. The ASF licenses this file
5
- # to you under the Apache License, Version 2.0 (the
6
- # "License"); you may not use this file except in compliance
7
- # with the License. You may obtain a copy of the License at
8
- #
9
- # http://www.apache.org/licenses/LICENSE-2.0
10
- #
11
- # Unless required by applicable law or agreed to in writing,
12
- # software distributed under the License is distributed on an
13
- # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14
- # KIND, either express or implied. See the License for the
15
- # specific language governing permissions and limitations
16
- # under the License.
17
-
18
- class ColumnTest < Test::Unit::TestCase
19
- def setup
20
- table = Arrow::Table.new("visible" => [true, nil, false])
21
- @column = table.visible
22
- end
23
-
24
- test("#name") do
25
- assert_equal("visible", @column.name)
26
- end
27
-
28
- test("#data_type") do
29
- assert_equal(Arrow::BooleanDataType.new, @column.data_type)
30
- end
31
-
32
- test("#null?") do
33
- assert do
34
- @column.null?(1)
35
- end
36
- end
37
-
38
- test("#valid?") do
39
- assert do
40
- @column.valid?(0)
41
- end
42
- end
43
-
44
- test("#each") do
45
- assert_equal([true, nil, false], @column.each.to_a)
46
- end
47
-
48
- test("#reverse_each") do
49
- assert_equal([false, nil, true], @column.reverse_each.to_a)
50
- end
51
-
52
- test("#n_rows") do
53
- assert_equal(3, @column.n_rows)
54
- end
55
-
56
- test("#n_nulls") do
57
- assert_equal(1, @column.n_nulls)
58
- end
59
-
60
- sub_test_case("#==") do
61
- test("same value") do
62
- table1 = Arrow::Table.new("visible" => [true, false])
63
- table2 = Arrow::Table.new("visible" => [true, false])
64
- assert do
65
- table1.visible == table2.visible
66
- end
67
- end
68
-
69
- test("different name") do
70
- table1 = Arrow::Table.new("visible" => [true, false])
71
- table2 = Arrow::Table.new("invisible" => [true, false])
72
- assert do
73
- not table1.visible == table2.invisible
74
- end
75
- end
76
-
77
- test("different value") do
78
- table1 = Arrow::Table.new("visible" => [true, false])
79
- table2 = Arrow::Table.new("visible" => [true, true])
80
- assert do
81
- not table1.visible == table2.visible
82
- end
83
- end
84
-
85
- test("not Arrow::Column") do
86
- table = Arrow::Table.new("visible" => [true, false])
87
- assert do
88
- not table.visible == 29
89
- end
90
- end
91
- end
92
- end
@@ -1,250 +0,0 @@
1
- # Licensed to the Apache Software Foundation (ASF) under one
2
- # or more contributor license agreements. See the NOTICE file
3
- # distributed with this work for additional information
4
- # regarding copyright ownership. The ASF licenses this file
5
- # to you under the Apache License, Version 2.0 (the
6
- # "License"); you may not use this file except in compliance
7
- # with the License. You may obtain a copy of the License at
8
- #
9
- # http://www.apache.org/licenses/LICENSE-2.0
10
- #
11
- # Unless required by applicable law or agreed to in writing,
12
- # software distributed under the License is distributed on an
13
- # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14
- # KIND, either express or implied. See the License for the
15
- # specific language governing permissions and limitations
16
- # under the License.
17
-
18
- class CSVLoaderTest < Test::Unit::TestCase
19
- include Helper::Fixture
20
-
21
- def load_csv(input)
22
- Arrow::CSVLoader.load(input, skip_lines: /^#/)
23
- end
24
-
25
- sub_test_case(".load") do
26
- test("String: data: with header") do
27
- data = fixture_path("with-header-float.csv").read
28
- assert_equal(<<-TABLE, load_csv(data).to_s)
29
- name score
30
- 0 alice 10.100000
31
- 1 bob 29.200000
32
- 2 chris -1.300000
33
- TABLE
34
- end
35
-
36
- test("String: data: without header") do
37
- data = fixture_path("without-header-float.csv").read
38
- assert_equal(<<-TABLE, load_csv(data).to_s)
39
- 0 1
40
- 0 alice 10.100000
41
- 1 bob 29.200000
42
- 2 chris -1.300000
43
- TABLE
44
- end
45
-
46
- test("String: path: with header") do
47
- path = fixture_path("with-header-float.csv").to_s
48
- assert_equal(<<-TABLE, load_csv(path).to_s)
49
- name score
50
- 0 alice 10.100000
51
- 1 bob 29.200000
52
- 2 chris -1.300000
53
- TABLE
54
- end
55
-
56
- test("String: path: without header") do
57
- path = fixture_path("without-header-float.csv").to_s
58
- assert_equal(<<-TABLE, load_csv(path).to_s)
59
- 0 1
60
- 0 alice 10.100000
61
- 1 bob 29.200000
62
- 2 chris -1.300000
63
- TABLE
64
- end
65
-
66
- test("Pathname: with header") do
67
- path = fixture_path("with-header-float.csv")
68
- assert_equal(<<-TABLE, load_csv(path).to_s)
69
- name score
70
- 0 alice 10.100000
71
- 1 bob 29.200000
72
- 2 chris -1.300000
73
- TABLE
74
- end
75
-
76
- test("Pathname: without header") do
77
- path = fixture_path("without-header-float.csv")
78
- assert_equal(<<-TABLE, load_csv(path).to_s)
79
- 0 1
80
- 0 alice 10.100000
81
- 1 bob 29.200000
82
- 2 chris -1.300000
83
- TABLE
84
- end
85
-
86
- test("null: with double quote") do
87
- path = fixture_path("null-with-double-quote.csv").to_s
88
- assert_equal(<<-TABLE, load_csv(path).to_s)
89
- name score
90
- 0 alice 10
91
- 1 bob (null)
92
- 2 chris -1
93
- TABLE
94
- end
95
-
96
- test("null: without double quote") do
97
- path = fixture_path("null-without-double-quote.csv").to_s
98
- assert_equal(<<-TABLE, load_csv(path).to_s)
99
- name score
100
- 0 alice 10
101
- 1 bob (null)
102
- 2 chris -1
103
- TABLE
104
- end
105
-
106
- test("number: float, integer") do
107
- path = fixture_path("float-integer.csv").to_s
108
- assert_equal([2.9, 10, -1.1],
109
- load_csv(path)[:score].to_a)
110
- end
111
-
112
- test("number: integer, float") do
113
- path = fixture_path("integer-float.csv").to_s
114
- assert_equal([10.0, 2.9, -1.1],
115
- load_csv(path)[:score].to_a)
116
- end
117
- end
118
-
119
- sub_test_case("CSVReader") do
120
- def load_csv(data, **options)
121
- Arrow::CSVLoader.load(data, **options)
122
- end
123
-
124
- sub_test_case(":headers") do
125
- test("true") do
126
- values = Arrow::StringArray.new(["a", "b", "c"])
127
- assert_equal(Arrow::Table.new(value: values),
128
- load_csv(<<-CSV, headers: true))
129
- value
130
- a
131
- b
132
- c
133
- CSV
134
- end
135
-
136
- test(":first_line") do
137
- values = Arrow::StringArray.new(["a", "b", "c"])
138
- assert_equal(Arrow::Table.new(value: values),
139
- load_csv(<<-CSV, headers: :first_line))
140
- value
141
- a
142
- b
143
- c
144
- CSV
145
- end
146
-
147
- test("truthy") do
148
- values = Arrow::StringArray.new(["a", "b", "c"])
149
- assert_equal(Arrow::Table.new(value: values),
150
- load_csv(<<-CSV, headers: 0))
151
- value
152
- a
153
- b
154
- c
155
- CSV
156
- end
157
-
158
- test("Array of column names") do
159
- values = Arrow::StringArray.new(["a", "b", "c"])
160
- assert_equal(Arrow::Table.new(column: values),
161
- load_csv(<<-CSV, headers: ["column"]))
162
- a
163
- b
164
- c
165
- CSV
166
- end
167
-
168
- test("false") do
169
- values = Arrow::StringArray.new(["a", "b", "c"])
170
- assert_equal(Arrow::Table.new(f0: values),
171
- load_csv(<<-CSV, headers: false))
172
- a
173
- b
174
- c
175
- CSV
176
- end
177
-
178
- test("nil") do
179
- values = Arrow::StringArray.new(["a", "b", "c"])
180
- assert_equal(Arrow::Table.new(f0: values),
181
- load_csv(<<-CSV, headers: nil))
182
- a
183
- b
184
- c
185
- CSV
186
- end
187
-
188
- test("string") do
189
- values = Arrow::StringArray.new(["a", "b", "c"])
190
- assert_equal(Arrow::Table.new(column: values),
191
- load_csv(<<-CSV, headers: "column"))
192
- a
193
- b
194
- c
195
- CSV
196
- end
197
- end
198
-
199
- test(":column_types") do
200
- assert_equal(Arrow::Table.new(:count => Arrow::UInt16Array.new([1, 2, 4])),
201
- load_csv(<<-CSV, column_types: {count: :uint16}))
202
- count
203
- 1
204
- 2
205
- 4
206
- CSV
207
- end
208
-
209
- test(":schema") do
210
- table = Arrow::Table.new(:count => Arrow::UInt16Array.new([1, 2, 4]))
211
- assert_equal(table,
212
- load_csv(<<-CSV, schema: table.schema))
213
- count
214
- 1
215
- 2
216
- 4
217
- CSV
218
- end
219
-
220
- test(":encoding") do
221
- messages = [
222
- "\u3042", # U+3042 HIRAGANA LETTER A
223
- "\u3044", # U+3044 HIRAGANA LETTER I
224
- "\u3046", # U+3046 HIRAGANA LETTER U
225
- ]
226
- table = Arrow::Table.new(:message => Arrow::StringArray.new(messages))
227
- encoding = "cp932"
228
- assert_equal(table,
229
- load_csv((["message"] + messages).join("\n").encode(encoding),
230
- schema: table.schema,
231
- encoding: encoding))
232
- end
233
-
234
- test(":encoding and :compression") do
235
- messages = [
236
- "\u3042", # U+3042 HIRAGANA LETTER A
237
- "\u3044", # U+3044 HIRAGANA LETTER I
238
- "\u3046", # U+3046 HIRAGANA LETTER U
239
- ]
240
- table = Arrow::Table.new(:message => Arrow::StringArray.new(messages))
241
- encoding = "cp932"
242
- csv = (["message"] + messages).join("\n").encode(encoding)
243
- assert_equal(table,
244
- load_csv(Zlib::Deflate.deflate(csv),
245
- schema: table.schema,
246
- encoding: encoding,
247
- compression: :gzip))
248
- end
249
- end
250
- end
@@ -1,83 +0,0 @@
1
- # Licensed to the Apache Software Foundation (ASF) under one
2
- # or more contributor license agreements. See the NOTICE file
3
- # distributed with this work for additional information
4
- # regarding copyright ownership. The ASF licenses this file
5
- # to you under the Apache License, Version 2.0 (the
6
- # "License"); you may not use this file except in compliance
7
- # with the License. You may obtain a copy of the License at
8
- #
9
- # http://www.apache.org/licenses/LICENSE-2.0
10
- #
11
- # Unless required by applicable law or agreed to in writing,
12
- # software distributed under the License is distributed on an
13
- # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14
- # KIND, either express or implied. See the License for the
15
- # specific language governing permissions and limitations
16
- # under the License.
17
-
18
- class DataTypeTest < Test::Unit::TestCase
19
- sub_test_case(".resolve") do
20
- test("DataType") do
21
- assert_equal(Arrow::BooleanDataType.new,
22
- Arrow::DataType.resolve(Arrow::BooleanDataType.new))
23
- end
24
-
25
- test("String") do
26
- assert_equal(Arrow::BooleanDataType.new,
27
- Arrow::DataType.resolve("boolean"))
28
- end
29
-
30
- test("Symbol") do
31
- assert_equal(Arrow::BooleanDataType.new,
32
- Arrow::DataType.resolve(:boolean))
33
- end
34
-
35
- test("Array") do
36
- field = Arrow::Field.new(:visible, :boolean)
37
- assert_equal(Arrow::ListDataType.new(field),
38
- Arrow::DataType.resolve([:list, field]))
39
- end
40
-
41
- test("Hash") do
42
- field = Arrow::Field.new(:visible, :boolean)
43
- assert_equal(Arrow::ListDataType.new(field),
44
- Arrow::DataType.resolve(type: :list, field: field))
45
- end
46
-
47
- test("_") do
48
- assert_equal(Arrow::FixedSizeBinaryDataType.new(10),
49
- Arrow::DataType.resolve([:fixed_size_binary, 10]))
50
- end
51
-
52
- test("abstract") do
53
- message =
54
- "abstract type: <:floating_point>: " +
55
- "use one of not abstract type: [" +
56
- "Arrow::DoubleDataType, " +
57
- "Arrow::FloatDataType]"
58
- assert_raise(ArgumentError.new(message)) do
59
- Arrow::DataType.resolve(:floating_point)
60
- end
61
- end
62
- end
63
-
64
- sub_test_case("instance methods") do
65
- def setup
66
- @data_type = Arrow::StringDataType.new
67
- end
68
-
69
- sub_test_case("#==") do
70
- test("Arrow::DataType") do
71
- assert do
72
- @data_type == @data_type
73
- end
74
- end
75
-
76
- test("not Arrow::DataType") do
77
- assert do
78
- not (@data_type == 29)
79
- end
80
- end
81
- end
82
- end
83
- end