red-arrow 18.1.0 → 19.0.1

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 (133) hide show
  1. checksums.yaml +4 -4
  2. data/lib/arrow/array.rb +7 -4
  3. data/lib/arrow/column.rb +4 -4
  4. data/lib/arrow/jruby/array-builder.rb +114 -0
  5. data/lib/arrow/jruby/array.rb +109 -0
  6. data/{test/helper/fixture.rb → lib/arrow/jruby/chunked-array.rb} +14 -6
  7. data/lib/arrow/jruby/compression-type.rb +26 -0
  8. data/{test/test-boolean-scalar.rb → lib/arrow/jruby/csv-read-options.rb} +12 -6
  9. data/{test/test-map-data-type.rb → lib/arrow/jruby/data-type.rb} +24 -12
  10. data/lib/arrow/jruby/decimal128.rb +28 -0
  11. data/lib/arrow/jruby/decimal256.rb +28 -0
  12. data/{test/fixture/null-with-double-quote.csv → lib/arrow/jruby/error.rb} +7 -4
  13. data/lib/arrow/jruby/file-system.rb +24 -0
  14. data/{test/test-null-array.rb → lib/arrow/jruby/function.rb} +5 -4
  15. data/lib/arrow/jruby/record-batch-iterator.rb +24 -0
  16. data/{test/fixture/integer-float.csv → lib/arrow/jruby/record-batch.rb} +8 -4
  17. data/{test/fixture/float-integer.csv → lib/arrow/jruby/sort-key.rb} +8 -4
  18. data/lib/arrow/jruby/sort-options.rb +24 -0
  19. data/lib/arrow/jruby/stream-listener-raw.rb +25 -0
  20. data/{test/test-rolling-window.rb → lib/arrow/jruby/table.rb} +19 -19
  21. data/lib/arrow/jruby/writable.rb +24 -0
  22. data/lib/arrow/jruby.rb +52 -0
  23. data/lib/arrow/libraries.rb +126 -0
  24. data/lib/arrow/list-array-builder.rb +1 -0
  25. data/lib/arrow/loader.rb +3 -111
  26. data/{test/fixture/null-without-double-quote.csv → lib/arrow/ruby.rb} +6 -4
  27. data/lib/arrow/version.rb +1 -1
  28. data/lib/arrow.rb +2 -7
  29. data/red-arrow.gemspec +15 -6
  30. metadata +26 -229
  31. data/test/each-raw-record/test-basic-arrays.rb +0 -411
  32. data/test/each-raw-record/test-dense-union-array.rb +0 -566
  33. data/test/each-raw-record/test-dictionary-array.rb +0 -341
  34. data/test/each-raw-record/test-list-array.rb +0 -628
  35. data/test/each-raw-record/test-map-array.rb +0 -507
  36. data/test/each-raw-record/test-multiple-columns.rb +0 -72
  37. data/test/each-raw-record/test-sparse-union-array.rb +0 -528
  38. data/test/each-raw-record/test-struct-array.rb +0 -529
  39. data/test/each-raw-record/test-table.rb +0 -47
  40. data/test/fixture/TestOrcFile.test1.orc +0 -0
  41. data/test/fixture/with-header-float.csv +0 -20
  42. data/test/fixture/with-header.csv +0 -20
  43. data/test/fixture/without-header-float.csv +0 -19
  44. data/test/fixture/without-header.csv +0 -19
  45. data/test/helper/omittable.rb +0 -49
  46. data/test/helper.rb +0 -31
  47. data/test/raw-records/test-basic-arrays.rb +0 -405
  48. data/test/raw-records/test-dense-union-array.rb +0 -566
  49. data/test/raw-records/test-dictionary-array.rb +0 -341
  50. data/test/raw-records/test-list-array.rb +0 -628
  51. data/test/raw-records/test-map-array.rb +0 -507
  52. data/test/raw-records/test-multiple-columns.rb +0 -65
  53. data/test/raw-records/test-sparse-union-array.rb +0 -556
  54. data/test/raw-records/test-struct-array.rb +0 -529
  55. data/test/raw-records/test-table.rb +0 -47
  56. data/test/run-test.rb +0 -71
  57. data/test/test-array-builder.rb +0 -198
  58. data/test/test-array.rb +0 -332
  59. data/test/test-bigdecimal.rb +0 -40
  60. data/test/test-binary-dictionary-array-builder.rb +0 -103
  61. data/test/test-buffer.rb +0 -49
  62. data/test/test-chunked-array.rb +0 -198
  63. data/test/test-column.rb +0 -123
  64. data/test/test-csv-loader.rb +0 -297
  65. data/test/test-data-type.rb +0 -84
  66. data/test/test-date32-array.rb +0 -24
  67. data/test/test-date64-array.rb +0 -25
  68. data/test/test-decimal128-array-builder.rb +0 -126
  69. data/test/test-decimal128-array.rb +0 -47
  70. data/test/test-decimal128-data-type.rb +0 -31
  71. data/test/test-decimal128.rb +0 -126
  72. data/test/test-decimal256-array-builder.rb +0 -126
  73. data/test/test-decimal256-array.rb +0 -47
  74. data/test/test-decimal256-data-type.rb +0 -31
  75. data/test/test-decimal256.rb +0 -126
  76. data/test/test-dense-union-array.rb +0 -42
  77. data/test/test-dense-union-data-type.rb +0 -41
  78. data/test/test-dictionary-array.rb +0 -41
  79. data/test/test-dictionary-data-type.rb +0 -40
  80. data/test/test-expression.rb +0 -51
  81. data/test/test-feather.rb +0 -49
  82. data/test/test-field.rb +0 -117
  83. data/test/test-file-output-stream.rb +0 -54
  84. data/test/test-fixed-size-binary-array-builder.rb +0 -92
  85. data/test/test-fixed-size-binary-array.rb +0 -36
  86. data/test/test-float-scalar.rb +0 -46
  87. data/test/test-function.rb +0 -210
  88. data/test/test-group.rb +0 -193
  89. data/test/test-half-float-array.rb +0 -43
  90. data/test/test-half-float.rb +0 -130
  91. data/test/test-list-array-builder.rb +0 -79
  92. data/test/test-list-array.rb +0 -32
  93. data/test/test-list-data-type.rb +0 -69
  94. data/test/test-map-array-builder.rb +0 -110
  95. data/test/test-map-array.rb +0 -33
  96. data/test/test-memory-view.rb +0 -434
  97. data/test/test-orc.rb +0 -173
  98. data/test/test-ractor.rb +0 -34
  99. data/test/test-record-batch-builder.rb +0 -125
  100. data/test/test-record-batch-file-reader.rb +0 -136
  101. data/test/test-record-batch-iterator.rb +0 -37
  102. data/test/test-record-batch-reader.rb +0 -46
  103. data/test/test-record-batch-stream-reader.rb +0 -129
  104. data/test/test-record-batch.rb +0 -182
  105. data/test/test-scalar.rb +0 -65
  106. data/test/test-schema.rb +0 -134
  107. data/test/test-slicer.rb +0 -589
  108. data/test/test-sort-indices.rb +0 -40
  109. data/test/test-sort-key.rb +0 -81
  110. data/test/test-sort-options.rb +0 -58
  111. data/test/test-sparse-union-array.rb +0 -38
  112. data/test/test-sparse-union-data-type.rb +0 -41
  113. data/test/test-stream-listener.rb +0 -60
  114. data/test/test-string-dictionary-array-builder.rb +0 -103
  115. data/test/test-struct-array-builder.rb +0 -184
  116. data/test/test-struct-array.rb +0 -94
  117. data/test/test-struct-data-type.rb +0 -112
  118. data/test/test-table.rb +0 -1530
  119. data/test/test-tensor.rb +0 -297
  120. data/test/test-time.rb +0 -288
  121. data/test/test-time32-array.rb +0 -81
  122. data/test/test-time32-data-type.rb +0 -42
  123. data/test/test-time64-array.rb +0 -81
  124. data/test/test-time64-data-type.rb +0 -42
  125. data/test/test-timestamp-array.rb +0 -45
  126. data/test/test-timestamp-data-type.rb +0 -42
  127. data/test/values/test-basic-arrays.rb +0 -335
  128. data/test/values/test-dense-union-array.rb +0 -552
  129. data/test/values/test-dictionary-array.rb +0 -325
  130. data/test/values/test-list-array.rb +0 -587
  131. data/test/values/test-map-array.rb +0 -489
  132. data/test/values/test-sparse-union-array.rb +0 -543
  133. data/test/values/test-struct-array.rb +0 -524
@@ -1,325 +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
- module ValuesDictionaryArrayTests
19
- def test_null
20
- target = build(Arrow::NullArray.new(4))
21
- assert_equal([nil] * 4, target.values)
22
- end
23
-
24
- def test_boolean
25
- values = [true, nil, false]
26
- target = build(Arrow::BooleanArray.new(values))
27
- assert_equal(values, target.values)
28
- end
29
-
30
- def test_int8
31
- values = [
32
- -(2 ** 7),
33
- nil,
34
- (2 ** 7) - 1,
35
- ]
36
- target = build(Arrow::Int8Array.new(values))
37
- assert_equal(values, target.values)
38
- end
39
-
40
- def test_uint8
41
- values = [
42
- 0,
43
- nil,
44
- (2 ** 8) - 1,
45
- ]
46
- target = build(Arrow::UInt8Array.new(values))
47
- assert_equal(values, target.values)
48
- end
49
-
50
- def test_int16
51
- values = [
52
- -(2 ** 15),
53
- nil,
54
- (2 ** 15) - 1,
55
- ]
56
- target = build(Arrow::Int16Array.new(values))
57
- assert_equal(values, target.values)
58
- end
59
-
60
- def test_uint16
61
- values = [
62
- 0,
63
- nil,
64
- (2 ** 16) - 1,
65
- ]
66
- target = build(Arrow::UInt16Array.new(values))
67
- assert_equal(values, target.values)
68
- end
69
-
70
- def test_int32
71
- values = [
72
- -(2 ** 31),
73
- nil,
74
- (2 ** 31) - 1,
75
- ]
76
- target = build(Arrow::Int32Array.new(values))
77
- assert_equal(values, target.values)
78
- end
79
-
80
- def test_uint32
81
- values = [
82
- 0,
83
- nil,
84
- (2 ** 32) - 1,
85
- ]
86
- target = build(Arrow::UInt32Array.new(values))
87
- assert_equal(values, target.values)
88
- end
89
-
90
- def test_int64
91
- values = [
92
- -(2 ** 63),
93
- nil,
94
- (2 ** 63) - 1,
95
- ]
96
- target = build(Arrow::Int64Array.new(values))
97
- assert_equal(values, target.values)
98
- end
99
-
100
- def test_uint64
101
- values = [
102
- 0,
103
- nil,
104
- (2 ** 64) - 1,
105
- ]
106
- target = build(Arrow::UInt64Array.new(values))
107
- assert_equal(values, target.values)
108
- end
109
-
110
- def test_float
111
- values = [
112
- -1.0,
113
- nil,
114
- 1.0,
115
- ]
116
- target = build(Arrow::FloatArray.new(values))
117
- assert_equal(values, target.values)
118
- end
119
-
120
- def test_double
121
- values = [
122
- -1.0,
123
- nil,
124
- 1.0,
125
- ]
126
- target = build(Arrow::DoubleArray.new(values))
127
- assert_equal(values, target.values)
128
- end
129
-
130
- def test_binary
131
- values = [
132
- "\x00".b,
133
- nil,
134
- "\xff".b,
135
- ]
136
- target = build(Arrow::BinaryArray.new(values))
137
- assert_equal(values, target.values)
138
- end
139
-
140
- def test_string
141
- values = [
142
- "Ruby",
143
- nil,
144
- "\u3042", # U+3042 HIRAGANA LETTER A
145
- ]
146
- target = build(Arrow::StringArray.new(values))
147
- assert_equal(values, target.values)
148
- end
149
-
150
- def test_date32
151
- values = [
152
- Date.new(1960, 1, 1),
153
- nil,
154
- Date.new(2017, 8, 23),
155
- ]
156
- target = build(Arrow::Date32Array.new(values))
157
- assert_equal(values, target.values)
158
- end
159
-
160
- def test_date64
161
- values = [
162
- DateTime.new(1960, 1, 1, 2, 9, 30),
163
- nil,
164
- DateTime.new(2017, 8, 23, 14, 57, 2),
165
- ]
166
- target = build(Arrow::Date64Array.new(values))
167
- assert_equal(values, target.values)
168
- end
169
-
170
- def test_timestamp_second
171
- values = [
172
- Time.parse("1960-01-01T02:09:30Z"),
173
- nil,
174
- Time.parse("2017-08-23T14:57:02Z"),
175
- ]
176
- target = build(Arrow::TimestampArray.new(:second, values))
177
- assert_equal(values, target.values)
178
- end
179
-
180
- def test_timestamp_milli
181
- values = [
182
- Time.parse("1960-01-01T02:09:30.123Z"),
183
- nil,
184
- Time.parse("2017-08-23T14:57:02.987Z"),
185
- ]
186
- target = build(Arrow::TimestampArray.new(:milli, values))
187
- assert_equal(values, target.values)
188
- end
189
-
190
- def test_timestamp_micro
191
- values = [
192
- Time.parse("1960-01-01T02:09:30.123456Z"),
193
- nil,
194
- Time.parse("2017-08-23T14:57:02.987654Z"),
195
- ]
196
- target = build(Arrow::TimestampArray.new(:micro, values))
197
- assert_equal(values, target.values)
198
- end
199
-
200
- def test_timestamp_nano
201
- values = [
202
- Time.parse("1960-01-01T02:09:30.123456789Z"),
203
- nil,
204
- Time.parse("2017-08-23T14:57:02.987654321Z"),
205
- ]
206
- target = build(Arrow::TimestampArray.new(:nano, values))
207
- assert_equal(values, target.values)
208
- end
209
-
210
- def test_time32_second
211
- unit = Arrow::TimeUnit::SECOND
212
- values = [
213
- Arrow::Time.new(unit, 60 * 10), # 00:10:00
214
- nil,
215
- Arrow::Time.new(unit, 60 * 60 * 2 + 9), # 02:00:09
216
- ]
217
- target = build(Arrow::Time32Array.new(unit, values))
218
- assert_equal(values, target.values)
219
- end
220
-
221
- def test_time32_milli
222
- unit = Arrow::TimeUnit::MILLI
223
- values = [
224
- Arrow::Time.new(unit, (60 * 10) * 1000 + 123), # 00:10:00.123
225
- nil,
226
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1000 + 987), # 02:00:09.987
227
- ]
228
- target = build(Arrow::Time32Array.new(unit, values))
229
- assert_equal(values, target.values)
230
- end
231
-
232
- def test_time64_micro
233
- unit = Arrow::TimeUnit::MICRO
234
- values = [
235
- # 00:10:00.123456
236
- Arrow::Time.new(unit, (60 * 10) * 1_000_000 + 123_456),
237
- nil,
238
- # 02:00:09.987654
239
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1_000_000 + 987_654),
240
- ]
241
- target = build(Arrow::Time64Array.new(unit, values))
242
- assert_equal(values, target.values)
243
- end
244
-
245
- def test_time64_nano
246
- unit = Arrow::TimeUnit::NANO
247
- values = [
248
- # 00:10:00.123456789
249
- Arrow::Time.new(unit, (60 * 10) * 1_000_000_000 + 123_456_789),
250
- nil,
251
- # 02:00:09.987654321
252
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1_000_000_000 + 987_654_321),
253
- ]
254
- target = build(Arrow::Time64Array.new(unit, values))
255
- assert_equal(values, target.values)
256
- end
257
-
258
- def test_decimal128
259
- values = [
260
- BigDecimal("92.92"),
261
- nil,
262
- BigDecimal("29.29"),
263
- ]
264
- data_type = Arrow::Decimal128DataType.new(8, 2)
265
- target = build(Arrow::Decimal128Array.new(data_type, values))
266
- assert_equal(values, target.values)
267
- end
268
-
269
- def test_decimal256
270
- values = [
271
- BigDecimal("92.92"),
272
- nil,
273
- BigDecimal("29.29"),
274
- ]
275
- data_type = Arrow::Decimal256DataType.new(38, 2)
276
- target = build(Arrow::Decimal256Array.new(data_type, values))
277
- assert_equal(values, target.values)
278
- end
279
-
280
- def test_month_interval
281
- values = [
282
- 1,
283
- nil,
284
- 12,
285
- ]
286
- target = build(Arrow::MonthIntervalArray.new(values))
287
- assert_equal(values, target.values)
288
- end
289
-
290
- def test_day_time_interval
291
- values = [
292
- {day: 1, millisecond: 100},
293
- nil,
294
- {day: 2, millisecond: 300},
295
- ]
296
- target = build(Arrow::DayTimeIntervalArray.new(values))
297
- assert_equal(values, target.values)
298
- end
299
-
300
- def test_month_day_nano_interval
301
- values = [
302
- {month: 1, day: 1, nanosecond: 100},
303
- nil,
304
- {month: 2, day: 3, nanosecond: 400},
305
- ]
306
- target = build(Arrow::MonthDayNanoIntervalArray.new(values))
307
- assert_equal(values, target.values)
308
- end
309
- end
310
-
311
- class ValuesArrayDictionaryArrayTest < Test::Unit::TestCase
312
- include ValuesDictionaryArrayTests
313
-
314
- def build(values)
315
- values.dictionary_encode
316
- end
317
- end
318
-
319
- class ValuesChunkedArrayDictionaryArrayTest < Test::Unit::TestCase
320
- include ValuesDictionaryArrayTests
321
-
322
- def build(values)
323
- Arrow::ChunkedArray.new([values.dictionary_encode])
324
- end
325
- end