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
@@ -1,489 +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 ValuesMapArrayTests
19
- def build_data_type(item_type)
20
- Arrow::MapDataType.new(
21
- key: :string,
22
- item: item_type
23
- )
24
- end
25
-
26
- def build_array(item_type, values)
27
- Arrow::MapArray.new(build_data_type(item_type), values)
28
- end
29
-
30
- def test_null
31
- values = [
32
- {"key1" => nil},
33
- nil,
34
- ]
35
- target = build(:null, values)
36
- assert_equal(values, target.values)
37
- end
38
-
39
- def test_boolean
40
- values = [
41
- {"key1" => false, "key2" => nil},
42
- nil,
43
- ]
44
- target = build(:boolean, values)
45
- assert_equal(values, target.values)
46
- end
47
-
48
- def test_int8
49
- values = [
50
- {"key1" => (2 ** 7) - 1, "key2" => nil},
51
- nil,
52
- ]
53
- target = build(:int8, values)
54
- assert_equal(values, target.values)
55
- end
56
-
57
- def test_uint8
58
- values = [
59
- {"key1" => (2 ** 8) - 1, "key2" => nil},
60
- nil,
61
- ]
62
- target = build(:uint8, values)
63
- assert_equal(values, target.values)
64
- end
65
-
66
- def test_uint16
67
- values = [
68
- {"key1" => (2 ** 16) - 1, "key2" => nil},
69
- nil,
70
- ]
71
- target = build(:uint16, values)
72
- assert_equal(values, target.values)
73
- end
74
-
75
- def test_int32
76
- values = [
77
- {"key1" => -(2 ** 31), "key2" => nil},
78
- nil,
79
- ]
80
- target = build(:int32, values)
81
- assert_equal(values, target.values)
82
- end
83
-
84
- def test_uint32
85
- values = [
86
- {"key1" => (2 ** 32) - 1, "key2" => nil},
87
- nil,
88
- ]
89
- target = build(:uint32, values)
90
- assert_equal(values, target.values)
91
- end
92
-
93
- def test_int64
94
- values = [
95
- {"key1" => -(2 ** 63), "key2" => nil},
96
- nil,
97
- ]
98
- target = build(:int64, values)
99
- assert_equal(values, target.values)
100
- end
101
-
102
- def test_uint64
103
- values = [
104
- {"key1" => (2 ** 64) - 1, "key2" => nil},
105
- nil,
106
- ]
107
- target = build(:uint64, values)
108
- assert_equal(values, target.values)
109
- end
110
-
111
- def test_float
112
- values = [
113
- {"key1" => -1.0, "key2" => nil},
114
- nil,
115
- ]
116
- target = build(:float, values)
117
- assert_equal(values, target.values)
118
- end
119
-
120
- def test_double
121
- values = [
122
- {"key1" => -1.0, "key2" => nil},
123
- nil,
124
- ]
125
- target = build(:double, values)
126
- assert_equal(values, target.values)
127
- end
128
-
129
- def test_binary
130
- values = [
131
- {"key1" => "\xff".b, "key2" => nil},
132
- nil,
133
- ]
134
- target = build(:binary, values)
135
- assert_equal(values, target.values)
136
- end
137
-
138
- def test_string
139
- values = [
140
- {"key1" => "Ruby", "key2" => nil},
141
- nil,
142
- ]
143
- target = build(:string, values)
144
- assert_equal(values, target.values)
145
- end
146
-
147
- def test_date32
148
- values = [
149
- {"key1" => Date.new(1960, 1, 1), "key2" => nil},
150
- nil,
151
- ]
152
- target = build(:date32, values)
153
- assert_equal(values, target.values)
154
- end
155
-
156
- def test_date64
157
- values = [
158
- {"key1" => DateTime.new(1960, 1, 1, 2, 9, 30), "key2" => nil},
159
- nil,
160
- ]
161
- target = build(:date64, values)
162
- assert_equal(values, target.values)
163
- end
164
-
165
- def test_timestamp_second
166
- values = [
167
- {"key1" => Time.parse("1960-01-01T02:09:30Z"), "key2" => nil},
168
- nil,
169
- ]
170
- target = build({
171
- type: :timestamp,
172
- unit: :second,
173
- },
174
- values)
175
- assert_equal(values, target.values)
176
- end
177
-
178
- def test_timestamp_milli
179
- values = [
180
- {"key1" => Time.parse("1960-01-01T02:09:30.123Z"), "key2" => nil},
181
- nil,
182
- ]
183
- target = build({
184
- type: :timestamp,
185
- unit: :milli,
186
- },
187
- values)
188
- assert_equal(values, target.values)
189
- end
190
-
191
- def test_timestamp_micro
192
- values = [
193
- {"key1" => Time.parse("1960-01-01T02:09:30.123456Z"), "key2" => nil},
194
- nil,
195
- ]
196
- target = build({
197
- type: :timestamp,
198
- unit: :micro,
199
- },
200
- values)
201
- assert_equal(values, target.values)
202
- end
203
-
204
- def test_timestamp_nano
205
- values = [
206
- {"key1" => Time.parse("1960-01-01T02:09:30.123456789Z"), "key2" => nil},
207
- nil,
208
- ]
209
- target = build({
210
- type: :timestamp,
211
- unit: :nano,
212
- },
213
- values)
214
- assert_equal(values, target.values)
215
- end
216
-
217
- def test_time32_second
218
- unit = Arrow::TimeUnit::SECOND
219
- values = [
220
- # 00:10:00
221
- {"key1" => Arrow::Time.new(unit, 60 * 10), "key2" => nil},
222
- nil,
223
- ]
224
- target = build({
225
- type: :time32,
226
- unit: :second,
227
- },
228
- values)
229
- assert_equal(values, target.values)
230
- end
231
-
232
- def test_time32_milli
233
- unit = Arrow::TimeUnit::MILLI
234
- values = [
235
- # 00:10:00.123
236
- {"key1" => Arrow::Time.new(unit, (60 * 10) * 1000 + 123), "key2" => nil},
237
- nil,
238
- ]
239
- target = build({
240
- type: :time32,
241
- unit: :milli,
242
- },
243
- values)
244
- assert_equal(values, target.values)
245
- end
246
-
247
- def test_time64_micro
248
- unit = Arrow::TimeUnit::MICRO
249
- values = [
250
- # 00:10:00.123456
251
- {"key1" => Arrow::Time.new(unit, (60 * 10) * 1_000_000 + 123_456), "key2" => nil},
252
- nil,
253
- ]
254
- target = build({
255
- type: :time64,
256
- unit: :micro,
257
- },
258
- values)
259
- assert_equal(values, target.values)
260
- end
261
-
262
- def test_time64_nano
263
- unit = Arrow::TimeUnit::NANO
264
- values = [
265
- # 00:10:00.123456789
266
- {"key1" => Arrow::Time.new(unit, (60 * 10) * 1_000_000_000 + 123_456_789), "key2" => nil},
267
- nil,
268
- ]
269
- target = build({
270
- type: :time64,
271
- unit: :nano,
272
- },
273
- values)
274
- assert_equal(values, target.values)
275
- end
276
-
277
- def test_decimal128
278
- values = [
279
- {"key1" => BigDecimal("92.92"), "key2" => nil},
280
- nil,
281
- ]
282
- target = build({
283
- type: :decimal128,
284
- precision: 8,
285
- scale: 2,
286
- },
287
- values)
288
- assert_equal(values, target.values)
289
- end
290
-
291
- def test_decimal256
292
- values = [
293
- {"key1" => BigDecimal("92.92"), "key2" => nil},
294
- nil,
295
- ]
296
- target = build({
297
- type: :decimal256,
298
- precision: 38,
299
- scale: 2,
300
- },
301
- values)
302
- assert_equal(values, target.values)
303
- end
304
-
305
- def test_month_interval
306
- values = [
307
- {"key1" => 1, "key2" => nil},
308
- nil,
309
- ]
310
- target = build(:month_interval, values)
311
- assert_equal(values, target.values)
312
- end
313
-
314
- def test_day_time_interval
315
- values = [
316
- {
317
- "key1" => {day: 1, millisecond: 100},
318
- "key2" => nil,
319
- },
320
- nil,
321
- ]
322
- target = build(:day_time_interval, values)
323
- assert_equal(values, target.values)
324
- end
325
-
326
- def test_month_day_nano_interval
327
- values = [
328
- {
329
- "key1" => {month: 1, day: 1, nanosecond: 100},
330
- "key2" => nil,
331
- },
332
- nil,
333
- ]
334
- target = build(:month_day_nano_interval, values)
335
- assert_equal(values, target.values)
336
- end
337
-
338
- def test_list
339
- values = [
340
- {"key1" => [true, nil, false], "key2" => nil},
341
- nil,
342
- ]
343
- target = build({
344
- type: :list,
345
- field: {
346
- name: :sub_element,
347
- type: :boolean,
348
- },
349
- },
350
- values)
351
- assert_equal(values, target.values)
352
- end
353
-
354
- def test_struct
355
- values = [
356
- {"key1" => {"field" => true}, "key2" => nil, "key3" => {"field" => nil}},
357
- nil,
358
- ]
359
- target = build({
360
- type: :struct,
361
- fields: [
362
- {
363
- name: :field,
364
- type: :boolean,
365
- },
366
- ],
367
- },
368
- values)
369
- assert_equal(values, target.values)
370
- end
371
-
372
- def test_map
373
- values = [
374
- {"key1" => {"sub_key1" => true, "sub_key2" => nil}, "key2" => nil},
375
- nil,
376
- ]
377
- target = build({
378
- type: :map,
379
- key: :string,
380
- item: :boolean,
381
- },
382
- values)
383
- assert_equal(values, target.values)
384
- end
385
-
386
- def remove_union_field_names(values)
387
- values.collect do |value|
388
- if value.nil?
389
- value
390
- else
391
- val = {}
392
- value.each do |k, v|
393
- v = v.values[0] unless v.nil?
394
- val[k] = v
395
- end
396
- val
397
- end
398
- end
399
- end
400
-
401
- def test_sparse_union
402
- values = [
403
- {
404
- "key1" => {"field1" => true},
405
- "key2" => nil,
406
- "key3" => {"field2" => 29},
407
- "key4" => {"field2" => nil},
408
- },
409
- nil,
410
- ]
411
- target = build({
412
- type: :sparse_union,
413
- fields: [
414
- {
415
- name: :field1,
416
- type: :boolean,
417
- },
418
- {
419
- name: :field2,
420
- type: :uint8,
421
- },
422
- ],
423
- type_codes: [0, 1],
424
- },
425
- values)
426
- assert_equal(remove_union_field_names(values),
427
- target.values)
428
- end
429
-
430
- def test_dense_union
431
- values = [
432
- {
433
- "key1" => {"field1" => true},
434
- "key2" => nil,
435
- "key3" => {"field2" => 29},
436
- "key4" => {"field2" => nil},
437
- },
438
- nil,
439
- ]
440
- target = build({
441
- type: :dense_union,
442
- fields: [
443
- {
444
- name: :field1,
445
- type: :boolean,
446
- },
447
- {
448
- name: :field2,
449
- type: :uint8,
450
- },
451
- ],
452
- type_codes: [0, 1],
453
- },
454
- values)
455
- assert_equal(remove_union_field_names(values),
456
- target.values)
457
- end
458
-
459
- def test_dictionary
460
- values = [
461
- {"key1" => "Ruby", "key2" => nil, "key3" => "GLib"},
462
- nil,
463
- ]
464
- target = build({
465
- type: :dictionary,
466
- index_data_type: :int8,
467
- value_data_type: :string,
468
- ordered: false,
469
- },
470
- values)
471
- assert_equal(values, target.values)
472
- end
473
- end
474
-
475
- class ValuesArrayMapArrayTest < Test::Unit::TestCase
476
- include ValuesMapArrayTests
477
-
478
- def build(item_type, values)
479
- build_array(item_type, values)
480
- end
481
- end
482
-
483
- class ValuesChunkedArrayMapArrayTest < Test::Unit::TestCase
484
- include ValuesMapArrayTests
485
-
486
- def build(item_type, values)
487
- Arrow::ChunkedArray.new([build_array(item_type, values)])
488
- end
489
- end