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
@@ -1,524 +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 ValuesStructArrayTests
19
- def build_data_type(type)
20
- field_description = {
21
- name: :field,
22
- }
23
- if type.is_a?(Hash)
24
- field_description = field_description.merge(type)
25
- else
26
- field_description[:type] = type
27
- end
28
- Arrow::StructDataType.new([field_description])
29
- end
30
-
31
- def build_array(type, values)
32
- Arrow::StructArray.new(build_data_type(type), values)
33
- end
34
-
35
- def test_null
36
- values = [
37
- {"field" => nil},
38
- nil,
39
- ]
40
- target = build(:null, values)
41
- assert_equal(values, target.values)
42
- end
43
-
44
- def test_boolean
45
- values = [
46
- {"field" => true},
47
- nil,
48
- {"field" => nil},
49
- ]
50
- target = build(:boolean, values)
51
- assert_equal(values, target.values)
52
- end
53
-
54
- def test_int8
55
- values = [
56
- {"field" => -(2 ** 7)},
57
- nil,
58
- {"field" => nil},
59
- ]
60
- target = build(:int8, values)
61
- assert_equal(values, target.values)
62
- end
63
-
64
- def test_uint8
65
- values = [
66
- {"field" => (2 ** 8) - 1},
67
- nil,
68
- {"field" => nil},
69
- ]
70
- target = build(:uint8, values)
71
- assert_equal(values, target.values)
72
- end
73
-
74
- def test_int16
75
- values = [
76
- {"field" => -(2 ** 15)},
77
- nil,
78
- {"field" => nil},
79
- ]
80
- target = build(:int16, values)
81
- assert_equal(values, target.values)
82
- end
83
-
84
- def test_uint16
85
- values = [
86
- {"field" => (2 ** 16) - 1},
87
- nil,
88
- {"field" => nil},
89
- ]
90
- target = build(:uint16, values)
91
- assert_equal(values, target.values)
92
- end
93
-
94
- def test_int32
95
- values = [
96
- {"field" => -(2 ** 31)},
97
- nil,
98
- {"field" => nil},
99
- ]
100
- target = build(:int32, values)
101
- assert_equal(values, target.values)
102
- end
103
-
104
- def test_uint32
105
- values = [
106
- {"field" => (2 ** 32) - 1},
107
- nil,
108
- {"field" => nil},
109
- ]
110
- target = build(:uint32, values)
111
- assert_equal(values, target.values)
112
- end
113
-
114
- def test_int64
115
- values = [
116
- {"field" => -(2 ** 63)},
117
- nil,
118
- {"field" => nil},
119
- ]
120
- target = build(:int64, values)
121
- assert_equal(values, target.values)
122
- end
123
-
124
- def test_uint64
125
- values = [
126
- {"field" => (2 ** 64) - 1},
127
- nil,
128
- {"field" => nil},
129
- ]
130
- target = build(:uint64, values)
131
- assert_equal(values, target.values)
132
- end
133
-
134
- def test_float
135
- values = [
136
- {"field" => -1.0},
137
- nil,
138
- {"field" => nil},
139
- ]
140
- target = build(:float, values)
141
- assert_equal(values, target.values)
142
- end
143
-
144
- def test_double
145
- values = [
146
- {"field" => -1.0},
147
- nil,
148
- {"field" => nil},
149
- ]
150
- target = build(:double, values)
151
- assert_equal(values, target.values)
152
- end
153
-
154
- def test_binary
155
- values = [
156
- {"field" => "\xff".b},
157
- nil,
158
- {"field" => nil},
159
- ]
160
- target = build(:binary, values)
161
- assert_equal(values, target.values)
162
- end
163
-
164
- def test_string
165
- values = [
166
- {"field" => "Ruby"},
167
- nil,
168
- {"field" => nil},
169
- ]
170
- target = build(:string, values)
171
- assert_equal(values, target.values)
172
- end
173
-
174
- def test_date32
175
- values = [
176
- {"field" => Date.new(1960, 1, 1)},
177
- nil,
178
- {"field" => nil},
179
- ]
180
- target = build(:date32, values)
181
- assert_equal(values, target.values)
182
- end
183
-
184
- def test_date64
185
- values = [
186
- {"field" => DateTime.new(1960, 1, 1, 2, 9, 30)},
187
- nil,
188
- {"field" => nil},
189
- ]
190
- target = build(:date64, values)
191
- assert_equal(values, target.values)
192
- end
193
-
194
- def test_timestamp_second
195
- values = [
196
- {"field" => Time.parse("1960-01-01T02:09:30Z")},
197
- nil,
198
- {"field" => nil},
199
- ]
200
- target = build({
201
- type: :timestamp,
202
- unit: :second,
203
- },
204
- values)
205
- assert_equal(values, target.values)
206
- end
207
-
208
- def test_timestamp_milli
209
- values = [
210
- {"field" => Time.parse("1960-01-01T02:09:30.123Z")},
211
- nil,
212
- {"field" => nil},
213
- ]
214
- target = build({
215
- type: :timestamp,
216
- unit: :milli,
217
- },
218
- values)
219
- assert_equal(values, target.values)
220
- end
221
-
222
- def test_timestamp_micro
223
- values = [
224
- {"field" => Time.parse("1960-01-01T02:09:30.123456Z")},
225
- nil,
226
- {"field" => nil},
227
- ]
228
- target = build({
229
- type: :timestamp,
230
- unit: :micro,
231
- },
232
- values)
233
- assert_equal(values, target.values)
234
- end
235
-
236
- def test_timestamp_nano
237
- values = [
238
- {"field" => Time.parse("1960-01-01T02:09:30.123456789Z")},
239
- nil,
240
- {"field" => nil},
241
- ]
242
- target = build({
243
- type: :timestamp,
244
- unit: :nano,
245
- },
246
- values)
247
- assert_equal(values, target.values)
248
- end
249
-
250
- def test_time32_second
251
- unit = Arrow::TimeUnit::SECOND
252
- values = [
253
- # 00:10:00
254
- {"field" => Arrow::Time.new(unit, 60 * 10)},
255
- nil,
256
- {"field" => nil},
257
- ]
258
- target = build({
259
- type: :time32,
260
- unit: :second,
261
- },
262
- values)
263
- assert_equal(values, target.values)
264
- end
265
-
266
- def test_time32_milli
267
- unit = Arrow::TimeUnit::MILLI
268
- values = [
269
- # 00:10:00.123
270
- {"field" => Arrow::Time.new(unit, (60 * 10) * 1000 + 123)},
271
- nil,
272
- {"field" => nil},
273
- ]
274
- target = build({
275
- type: :time32,
276
- unit: :milli,
277
- },
278
- values)
279
- assert_equal(values, target.values)
280
- end
281
-
282
- def test_time64_micro
283
- unit = Arrow::TimeUnit::MICRO
284
- values = [
285
- # 00:10:00.123456
286
- {"field" => Arrow::Time.new(unit, (60 * 10) * 1_000_000 + 123_456)},
287
- nil,
288
- {"field" => nil},
289
- ]
290
- target = build({
291
- type: :time64,
292
- unit: :micro,
293
- },
294
- values)
295
- assert_equal(values, target.values)
296
- end
297
-
298
- def test_time64_nano
299
- unit = Arrow::TimeUnit::NANO
300
- values = [
301
- # 00:10:00.123456789
302
- {"field" => Arrow::Time.new(unit, (60 * 10) * 1_000_000_000 + 123_456_789)},
303
- nil,
304
- {"field" => nil},
305
- ]
306
- target = build({
307
- type: :time64,
308
- unit: :nano,
309
- },
310
- values)
311
- assert_equal(values, target.values)
312
- end
313
-
314
- def test_decimal128
315
- values = [
316
- {"field" => BigDecimal("92.92")},
317
- nil,
318
- {"field" => nil},
319
- ]
320
- target = build({
321
- type: :decimal128,
322
- precision: 8,
323
- scale: 2,
324
- },
325
- values)
326
- assert_equal(values, target.values)
327
- end
328
-
329
- def test_decimal256
330
- values = [
331
- {"field" => BigDecimal("92.92")},
332
- nil,
333
- {"field" => nil},
334
- ]
335
- target = build({
336
- type: :decimal256,
337
- precision: 38,
338
- scale: 2,
339
- },
340
- values)
341
- assert_equal(values, target.values)
342
- end
343
-
344
- def test_month_interval
345
- values = [
346
- {"field" => 1},
347
- nil,
348
- {"field" => nil},
349
- ]
350
- target = build(:month_interval, values)
351
- assert_equal(values, target.values)
352
- end
353
-
354
- def test_day_time_interval
355
- values = [
356
- {"field" => {day: 1, millisecond: 100}},
357
- nil,
358
- {"field" => nil},
359
- ]
360
- target = build(:day_time_interval, values)
361
- assert_equal(values, target.values)
362
- end
363
-
364
- def test_month_day_nano_interval
365
- values = [
366
- {"field" => {month: 1, day: 1, nanosecond: 100}},
367
- nil,
368
- {"field" => nil},
369
- ]
370
- target = build(:month_day_nano_interval, values)
371
- assert_equal(values, target.values)
372
- end
373
-
374
- def test_list
375
- values = [
376
- {"field" => [true, nil, false]},
377
- nil,
378
- {"field" => nil},
379
- ]
380
- target = build({
381
- type: :list,
382
- field: {
383
- name: :sub_element,
384
- type: :boolean,
385
- },
386
- },
387
- values)
388
- assert_equal(values, target.values)
389
- end
390
-
391
- def test_struct
392
- values = [
393
- {"field" => {"sub_field" => true}},
394
- nil,
395
- {"field" => nil},
396
- {"field" => {"sub_field" => nil}},
397
- ]
398
- target = build({
399
- type: :struct,
400
- fields: [
401
- {
402
- name: :sub_field,
403
- type: :boolean,
404
- },
405
- ],
406
- },
407
- values)
408
- assert_equal(values, target.values)
409
- end
410
-
411
- def test_map
412
- values = [
413
- {"field" => {"key1" => true, "key2" => nil}},
414
- nil,
415
- {"field" => nil},
416
- ]
417
- target = build({
418
- type: :map,
419
- key: :string,
420
- item: :boolean,
421
- },
422
- values)
423
- assert_equal(values, target.values)
424
- end
425
-
426
- def remove_union_field_names(values)
427
- values.collect do |value|
428
- if value.nil?
429
- value
430
- else
431
- v = value["field"]
432
- v = v.values[0] unless v.nil?
433
- {"field" => v}
434
- end
435
- end
436
- end
437
-
438
- def test_sparse_union
439
- values = [
440
- {"field" => {"field1" => true}},
441
- nil,
442
- {"field" => nil},
443
- {"field" => {"field2" => 29}},
444
- {"field" => {"field2" => nil}},
445
- ]
446
- target = build({
447
- type: :sparse_union,
448
- fields: [
449
- {
450
- name: :field1,
451
- type: :boolean,
452
- },
453
- {
454
- name: :field2,
455
- type: :uint8,
456
- },
457
- ],
458
- type_codes: [0, 1],
459
- },
460
- values)
461
- assert_equal(remove_union_field_names(values),
462
- target.values)
463
- end
464
-
465
- def test_dense_union
466
- values = [
467
- {"field" => {"field1" => true}},
468
- nil,
469
- {"field" => nil},
470
- {"field" => {"field2" => 29}},
471
- {"field" => {"field2" => nil}},
472
- ]
473
- target = build({
474
- type: :dense_union,
475
- fields: [
476
- {
477
- name: :field1,
478
- type: :boolean,
479
- },
480
- {
481
- name: :field2,
482
- type: :uint8,
483
- },
484
- ],
485
- type_codes: [0, 1],
486
- },
487
- values)
488
- assert_equal(remove_union_field_names(values),
489
- target.values)
490
- end
491
-
492
- def test_dictionary
493
- values = [
494
- {"field" => "Ruby"},
495
- nil,
496
- {"field" => nil},
497
- {"field" => "GLib"},
498
- ]
499
- target = build({
500
- type: :dictionary,
501
- index_data_type: :int8,
502
- value_data_type: :string,
503
- ordered: false,
504
- },
505
- values)
506
- assert_equal(values, target.values)
507
- end
508
- end
509
-
510
- class ValuesArrayStructArrayTest < Test::Unit::TestCase
511
- include ValuesStructArrayTests
512
-
513
- def build(type, values)
514
- build_array(type, values)
515
- end
516
- end
517
-
518
- class ValuesChunkedArrayStructArrayTest < Test::Unit::TestCase
519
- include ValuesStructArrayTests
520
-
521
- def build(type, values)
522
- Arrow::ChunkedArray.new([build_array(type, values)])
523
- end
524
- end