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
@@ -1,587 +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 ValuesListArrayTests
19
- def build_data_type(type)
20
- field_description = {
21
- name: :element,
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::ListDataType.new(field: field_description)
29
- end
30
-
31
- def build_array(type, values)
32
- Arrow::ListArray.new(build_data_type(type), values)
33
- end
34
-
35
- def test_null
36
- values = [
37
- [nil, nil, 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
- [true, nil, false],
47
- nil,
48
- ]
49
- target = build(:boolean, values)
50
- assert_equal(values, target.values)
51
- end
52
-
53
- def test_int8
54
- values = [
55
- [-(2 ** 7), nil, (2 ** 7) - 1],
56
- nil,
57
- ]
58
- target = build(:int8, values)
59
- assert_equal(values, target.values)
60
- end
61
-
62
- def test_uint8
63
- values = [
64
- [0, nil, (2 ** 8) - 1],
65
- nil,
66
- ]
67
- target = build(:uint8, values)
68
- assert_equal(values, target.values)
69
- end
70
-
71
- def test_int16
72
- values = [
73
- [-(2 ** 15), nil, (2 ** 15) - 1],
74
- nil,
75
- ]
76
- target = build(:int16, values)
77
- assert_equal(values, target.values)
78
- end
79
-
80
- def test_uint16
81
- values = [
82
- [0, nil, (2 ** 16) - 1],
83
- nil,
84
- ]
85
- target = build(:uint16, values)
86
- assert_equal(values, target.values)
87
- end
88
-
89
- def test_int32
90
- values = [
91
- [-(2 ** 31), nil, (2 ** 31) - 1],
92
- nil,
93
- ]
94
- target = build(:int32, values)
95
- assert_equal(values, target.values)
96
- end
97
-
98
- def test_uint32
99
- values = [
100
- [0, nil, (2 ** 32) - 1],
101
- nil,
102
- ]
103
- target = build(:uint32, values)
104
- assert_equal(values, target.values)
105
- end
106
-
107
- def test_int64
108
- values = [
109
- [-(2 ** 63), nil, (2 ** 63) - 1],
110
- nil,
111
- ]
112
- target = build(:int64, values)
113
- assert_equal(values, target.values)
114
- end
115
-
116
- def test_uint64
117
- values = [
118
- [0, nil, (2 ** 64) - 1],
119
- nil,
120
- ]
121
- target = build(:uint64, values)
122
- assert_equal(values, target.values)
123
- end
124
-
125
- def test_float
126
- values = [
127
- [-1.0, nil, 1.0],
128
- nil,
129
- ]
130
- target = build(:float, values)
131
- assert_equal(values, target.values)
132
- end
133
-
134
- def test_double
135
- values = [
136
- [-1.0, nil, 1.0],
137
- nil,
138
- ]
139
- target = build(:double, values)
140
- assert_equal(values, target.values)
141
- end
142
-
143
- def test_binary
144
- values = [
145
- ["\x00".b, nil, "\xff".b],
146
- nil,
147
- ]
148
- target = build(:binary, values)
149
- assert_equal(values, target.values)
150
- end
151
-
152
- def test_string
153
- values = [
154
- [
155
- "Ruby",
156
- nil,
157
- "\u3042", # U+3042 HIRAGANA LETTER A
158
- ],
159
- nil,
160
- ]
161
- target = build(:string, values)
162
- assert_equal(values, target.values)
163
- end
164
-
165
- def test_date32
166
- values = [
167
- [
168
- Date.new(1960, 1, 1),
169
- nil,
170
- Date.new(2017, 8, 23),
171
- ],
172
- nil,
173
- ]
174
- target = build(:date32, values)
175
- assert_equal(values, target.values)
176
- end
177
-
178
- def test_date64
179
- values = [
180
- [
181
- DateTime.new(1960, 1, 1, 2, 9, 30),
182
- nil,
183
- DateTime.new(2017, 8, 23, 14, 57, 2),
184
- ],
185
- nil,
186
- ]
187
- target = build(:date64, values)
188
- assert_equal(values, target.values)
189
- end
190
-
191
- def test_timestamp_second
192
- values = [
193
- [
194
- Time.parse("1960-01-01T02:09:30Z"),
195
- nil,
196
- Time.parse("2017-08-23T14:57:02Z"),
197
- ],
198
- 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
- [
211
- Time.parse("1960-01-01T02:09:30.123Z"),
212
- nil,
213
- Time.parse("2017-08-23T14:57:02.987Z"),
214
- ],
215
- nil,
216
- ]
217
- target = build({
218
- type: :timestamp,
219
- unit: :milli,
220
- },
221
- values)
222
- assert_equal(values, target.values)
223
- end
224
-
225
- def test_timestamp_micro
226
- values = [
227
- [
228
- Time.parse("1960-01-01T02:09:30.123456Z"),
229
- nil,
230
- Time.parse("2017-08-23T14:57:02.987654Z"),
231
- ],
232
- nil,
233
- ]
234
- target = build({
235
- type: :timestamp,
236
- unit: :micro,
237
- },
238
- values)
239
- assert_equal(values, target.values)
240
- end
241
-
242
- def test_timestamp_nano
243
- values = [
244
- [
245
- Time.parse("1960-01-01T02:09:30.123456789Z"),
246
- nil,
247
- Time.parse("2017-08-23T14:57:02.987654321Z"),
248
- ],
249
- nil,
250
- ]
251
- target = build({
252
- type: :timestamp,
253
- unit: :nano,
254
- },
255
- values)
256
- assert_equal(values, target.values)
257
- end
258
-
259
- def test_time32_second
260
- unit = Arrow::TimeUnit::SECOND
261
- values = [
262
- [
263
- # 00:10:00
264
- Arrow::Time.new(unit, 60 * 10),
265
- nil,
266
- # 02:00:09
267
- Arrow::Time.new(unit, 60 * 60 * 2 + 9),
268
- ],
269
- nil,
270
- ]
271
- target = build({
272
- type: :time32,
273
- unit: :second,
274
- },
275
- values)
276
- assert_equal(values, target.values)
277
- end
278
-
279
- def test_time32_milli
280
- unit = Arrow::TimeUnit::MILLI
281
- values = [
282
- [
283
- # 00:10:00.123
284
- Arrow::Time.new(unit, (60 * 10) * 1000 + 123),
285
- nil,
286
- # 02:00:09.987
287
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1000 + 987),
288
- ],
289
- nil,
290
- ]
291
- target = build({
292
- type: :time32,
293
- unit: :milli,
294
- },
295
- values)
296
- assert_equal(values, target.values)
297
- end
298
-
299
- def test_time64_micro
300
- unit = Arrow::TimeUnit::MICRO
301
- values = [
302
- [
303
- # 00:10:00.123456
304
- Arrow::Time.new(unit, (60 * 10) * 1_000_000 + 123_456),
305
- nil,
306
- # 02:00:09.987654
307
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1_000_000 + 987_654),
308
- ],
309
- nil,
310
- ]
311
- target = build({
312
- type: :time64,
313
- unit: :micro,
314
- },
315
- values)
316
- assert_equal(values, target.values)
317
- end
318
-
319
- def test_time64_nano
320
- unit = Arrow::TimeUnit::NANO
321
- values = [
322
- [
323
- # 00:10:00.123456789
324
- Arrow::Time.new(unit, (60 * 10) * 1_000_000_000 + 123_456_789),
325
- nil,
326
- # 02:00:09.987654321
327
- Arrow::Time.new(unit, (60 * 60 * 2 + 9) * 1_000_000_000 + 987_654_321),
328
- ],
329
- nil,
330
- ]
331
- target = build({
332
- type: :time64,
333
- unit: :nano,
334
- },
335
- values)
336
- assert_equal(values, target.values)
337
- end
338
-
339
- def test_decimal128
340
- values = [
341
- [
342
- BigDecimal("92.92"),
343
- nil,
344
- BigDecimal("29.29"),
345
- ],
346
- nil,
347
- ]
348
- target = build({
349
- type: :decimal128,
350
- precision: 8,
351
- scale: 2,
352
- },
353
- values)
354
- assert_equal(values, target.values)
355
- end
356
-
357
- def test_decimal256
358
- values = [
359
- [
360
- BigDecimal("92.92"),
361
- nil,
362
- BigDecimal("29.29"),
363
- ],
364
- nil,
365
- ]
366
- target = build({
367
- type: :decimal256,
368
- precision: 38,
369
- scale: 2,
370
- },
371
- values)
372
- assert_equal(values, target.values)
373
- end
374
-
375
- def test_month_interval
376
- values = [
377
- [
378
- 1,
379
- nil,
380
- 12,
381
- ],
382
- nil,
383
- ]
384
- target = build(:month_interval, values)
385
- assert_equal(values, target.values)
386
- end
387
-
388
- def test_day_time_interval
389
- values = [
390
- [
391
- {day: 1, millisecond: 100},
392
- nil,
393
- {day: 2, millisecond: 300},
394
- ],
395
- nil,
396
- ]
397
- target = build(:day_time_interval, values)
398
- assert_equal(values, target.values)
399
- end
400
-
401
- def test_month_day_nano_interval
402
- values = [
403
- [
404
- {month: 1, day: 1, nanosecond: 100},
405
- nil,
406
- {month: 2, day: 3, nanosecond: 400},
407
- ],
408
- nil,
409
- ]
410
- target = build(:month_day_nano_interval, values)
411
- assert_equal(values, target.values)
412
- end
413
-
414
- def test_list
415
- values = [
416
- [
417
- [
418
- true,
419
- nil,
420
- ],
421
- nil,
422
- [
423
- nil,
424
- false,
425
- ],
426
- ],
427
- nil,
428
- ]
429
- target = build({
430
- type: :list,
431
- field: {
432
- name: :sub_element,
433
- type: :boolean,
434
- },
435
- },
436
- values)
437
- assert_equal(values, target.values)
438
- end
439
-
440
- def test_struct
441
- values = [
442
- [
443
- {"field" => true},
444
- nil,
445
- {"field" => nil},
446
- ],
447
- nil,
448
- ]
449
- target = build({
450
- type: :struct,
451
- fields: [
452
- {
453
- name: :field,
454
- type: :boolean,
455
- },
456
- ],
457
- },
458
- values)
459
- assert_equal(values, target.values)
460
- end
461
-
462
- def test_map
463
- values = [
464
- [
465
- {"key1" => true, "key2" => nil},
466
- nil,
467
- ],
468
- nil,
469
- ]
470
- target = build({
471
- type: :map,
472
- key: :string,
473
- item: :boolean,
474
- },
475
- values)
476
- assert_equal(values, target.values)
477
- end
478
-
479
- def remove_union_field_names(values)
480
- values.collect do |value|
481
- if value.nil?
482
- value
483
- else
484
- value.collect do |v|
485
- if v.nil?
486
- v
487
- else
488
- v.values[0]
489
- end
490
- end
491
- end
492
- end
493
- end
494
-
495
- def test_sparse_union
496
- values = [
497
- [
498
- {"field1" => true},
499
- nil,
500
- {"field2" => 29},
501
- {"field2" => nil},
502
- ],
503
- nil,
504
- ]
505
- target = build({
506
- type: :sparse_union,
507
- fields: [
508
- {
509
- name: :field1,
510
- type: :boolean,
511
- },
512
- {
513
- name: :field2,
514
- type: :uint8,
515
- },
516
- ],
517
- type_codes: [0, 1],
518
- },
519
- values)
520
- assert_equal(remove_union_field_names(values),
521
- target.values)
522
- end
523
-
524
- def test_dense_union
525
- values = [
526
- [
527
- {"field1" => true},
528
- nil,
529
- {"field2" => 29},
530
- {"field2" => nil},
531
- ],
532
- nil,
533
- ]
534
- target = build({
535
- type: :dense_union,
536
- fields: [
537
- {
538
- name: :field1,
539
- type: :boolean,
540
- },
541
- {
542
- name: :field2,
543
- type: :uint8,
544
- },
545
- ],
546
- type_codes: [0, 1],
547
- },
548
- values)
549
- assert_equal(remove_union_field_names(values),
550
- target.values)
551
- end
552
-
553
- def test_dictionary
554
- values = [
555
- [
556
- "Ruby",
557
- nil,
558
- "GLib",
559
- ],
560
- nil,
561
- ]
562
- target = build({
563
- type: :dictionary,
564
- index_data_type: :int8,
565
- value_data_type: :string,
566
- ordered: false,
567
- },
568
- values)
569
- assert_equal(values, target.values)
570
- end
571
- end
572
-
573
- class ValuesArrayListArrayTest < Test::Unit::TestCase
574
- include ValuesListArrayTests
575
-
576
- def build(type, values)
577
- build_array(type, values)
578
- end
579
- end
580
-
581
- class ValuesChunkedArrayListArrayTest < Test::Unit::TestCase
582
- include ValuesListArrayTests
583
-
584
- def build(type, values)
585
- Arrow::ChunkedArray.new([build_array(type, values)])
586
- end
587
- end