deltacat 1.1.12__py3-none-any.whl → 1.1.14__py3-none-any.whl

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.
@@ -23,12 +23,16 @@ from deltacat.tests.compute.test_util_constant import (
23
23
  from deltacat.compute.compactor import (
24
24
  RoundCompletionInfo,
25
25
  )
26
+ from deltacat.compute.compactor.model.compaction_session_audit_info import (
27
+ CompactionSessionAuditInfo,
28
+ )
26
29
 
27
30
  from deltacat.storage.model.partition import PartitionLocator
28
31
  from deltacat.storage.model.stream import StreamLocator
29
32
  from deltacat.storage.model.table_version import TableVersionLocator
30
33
  from deltacat.storage.model.table import TableLocator
31
34
  from deltacat.storage.model.namespace import NamespaceLocator
35
+ from deltacat.compute.compactor.model.compactor_version import CompactorVersion
32
36
 
33
37
 
34
38
  class PartitionKeyType(str, Enum):
@@ -215,3 +219,100 @@ def offer_iso8601_timestamp_list(
215
219
  )
216
220
  )
217
221
  return res
222
+
223
+
224
+ def assert_compaction_audit(
225
+ compactor_version: CompactorVersion, compaction_audit: CompactionSessionAuditInfo
226
+ ):
227
+ if compactor_version == CompactorVersion.V2:
228
+ audit_entries = [
229
+ compaction_audit.deltacat_version,
230
+ compaction_audit.ray_version,
231
+ compaction_audit.audit_url,
232
+ compaction_audit.hash_bucket_count,
233
+ compaction_audit.compactor_version,
234
+ compaction_audit.input_size_bytes,
235
+ compaction_audit.input_file_count,
236
+ compaction_audit.estimated_in_memory_size_bytes_during_discovery,
237
+ compaction_audit.uniform_deltas_created,
238
+ compaction_audit.delta_discovery_time_in_seconds,
239
+ compaction_audit.hash_bucket_time_in_seconds,
240
+ compaction_audit.hash_bucket_invoke_time_in_seconds,
241
+ compaction_audit.hash_bucket_result_size_bytes,
242
+ compaction_audit.total_cluster_object_store_memory_bytes,
243
+ compaction_audit.total_cluster_memory_bytes,
244
+ compaction_audit.total_object_store_memory_used_bytes,
245
+ compaction_audit.hash_bucket_post_object_store_memory_used_bytes,
246
+ compaction_audit.hash_bucket_result_wait_time_in_seconds,
247
+ compaction_audit.peak_memory_used_bytes_per_hash_bucket_task,
248
+ compaction_audit.hash_bucket_processed_size_bytes,
249
+ compaction_audit.input_records,
250
+ compaction_audit.merge_time_in_seconds,
251
+ compaction_audit.merge_invoke_time_in_seconds,
252
+ compaction_audit.merge_result_size,
253
+ compaction_audit.merge_post_object_store_memory_used_bytes,
254
+ compaction_audit.merge_result_wait_time_in_seconds,
255
+ compaction_audit.peak_memory_used_bytes_per_merge_task,
256
+ compaction_audit.records_deduped,
257
+ compaction_audit.records_deleted,
258
+ compaction_audit.compaction_time_in_seconds,
259
+ compaction_audit.peak_memory_used_bytes_by_compaction_session_process,
260
+ compaction_audit.untouched_file_count,
261
+ compaction_audit.untouched_file_ratio,
262
+ compaction_audit.untouched_record_count,
263
+ compaction_audit.untouched_size_bytes,
264
+ compaction_audit.output_file_count,
265
+ compaction_audit.output_size_bytes,
266
+ compaction_audit.output_size_pyarrow_bytes,
267
+ compaction_audit.peak_memory_used_bytes_per_task,
268
+ compaction_audit.pyarrow_version,
269
+ compaction_audit.telemetry_time_in_seconds,
270
+ ]
271
+ for entry in audit_entries:
272
+ assert entry is not None
273
+ return True
274
+
275
+
276
+ def assert_compaction_audit_no_hash_bucket(
277
+ compactor_version: CompactorVersion, compaction_audit: CompactionSessionAuditInfo
278
+ ):
279
+ if compactor_version == CompactorVersion.V2:
280
+ audit_entries = [
281
+ compaction_audit.deltacat_version,
282
+ compaction_audit.ray_version,
283
+ compaction_audit.audit_url,
284
+ compaction_audit.hash_bucket_count,
285
+ compaction_audit.compactor_version,
286
+ compaction_audit.input_size_bytes,
287
+ compaction_audit.input_file_count,
288
+ compaction_audit.estimated_in_memory_size_bytes_during_discovery,
289
+ compaction_audit.uniform_deltas_created,
290
+ compaction_audit.delta_discovery_time_in_seconds,
291
+ compaction_audit.total_cluster_object_store_memory_bytes,
292
+ compaction_audit.total_cluster_memory_bytes,
293
+ compaction_audit.total_object_store_memory_used_bytes,
294
+ compaction_audit.input_records,
295
+ compaction_audit.merge_time_in_seconds,
296
+ compaction_audit.merge_invoke_time_in_seconds,
297
+ compaction_audit.merge_result_size,
298
+ compaction_audit.merge_post_object_store_memory_used_bytes,
299
+ compaction_audit.merge_result_wait_time_in_seconds,
300
+ compaction_audit.peak_memory_used_bytes_per_merge_task,
301
+ compaction_audit.records_deduped,
302
+ compaction_audit.records_deleted,
303
+ compaction_audit.compaction_time_in_seconds,
304
+ compaction_audit.peak_memory_used_bytes_by_compaction_session_process,
305
+ compaction_audit.untouched_file_count,
306
+ compaction_audit.untouched_file_ratio,
307
+ compaction_audit.untouched_record_count,
308
+ compaction_audit.untouched_size_bytes,
309
+ compaction_audit.output_file_count,
310
+ compaction_audit.output_size_bytes,
311
+ compaction_audit.output_size_pyarrow_bytes,
312
+ compaction_audit.peak_memory_used_bytes_per_task,
313
+ compaction_audit.pyarrow_version,
314
+ compaction_audit.telemetry_time_in_seconds,
315
+ ]
316
+ for entry in audit_entries:
317
+ assert entry is not None
318
+ return True
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: deltacat
3
- Version: 1.1.12
3
+ Version: 1.1.14
4
4
  Summary: A scalable, fast, ACID-compliant Data Catalog powered by Ray.
5
5
  Home-page: https://github.com/ray-project/deltacat
6
6
  Author: Ray Team
@@ -15,20 +15,20 @@ Classifier: Operating System :: OS Independent
15
15
  Requires-Python: >=3.9
16
16
  Description-Content-Type: text/markdown
17
17
  License-File: LICENSE
18
- Requires-Dist: aws-embedded-metrics ==3.2.0
19
- Requires-Dist: boto3 ~=1.34
20
- Requires-Dist: numpy ==1.21.5
21
- Requires-Dist: pandas ==1.3.5
22
- Requires-Dist: pyarrow ==12.0.1
23
- Requires-Dist: pydantic ==1.10.4
24
- Requires-Dist: ray >=2.20.0
25
- Requires-Dist: s3fs ==2024.5.0
26
- Requires-Dist: tenacity ==8.1.0
27
- Requires-Dist: typing-extensions ==4.4.0
28
- Requires-Dist: pymemcache ==4.0.0
29
- Requires-Dist: redis ==4.6.0
30
- Requires-Dist: getdaft ==0.2.31
31
- Requires-Dist: schedule ==1.2.0
18
+ Requires-Dist: aws-embedded-metrics==3.2.0
19
+ Requires-Dist: boto3~=1.34
20
+ Requires-Dist: numpy==1.21.5
21
+ Requires-Dist: pandas==1.3.5
22
+ Requires-Dist: pyarrow==12.0.1
23
+ Requires-Dist: pydantic==1.10.4
24
+ Requires-Dist: ray>=2.20.0
25
+ Requires-Dist: s3fs==2024.5.0
26
+ Requires-Dist: tenacity==8.1.0
27
+ Requires-Dist: typing-extensions==4.4.0
28
+ Requires-Dist: pymemcache==4.0.0
29
+ Requires-Dist: redis==4.6.0
30
+ Requires-Dist: getdaft==0.2.31
31
+ Requires-Dist: schedule==1.2.0
32
32
 
33
33
  # DeltaCAT
34
34
 
@@ -1,9 +1,9 @@
1
- deltacat/__init__.py,sha256=jtrgQAzzZxq5YU_9RwtH0N4p8k4_ACd_vcjuWJf934Q,1778
1
+ deltacat/__init__.py,sha256=dvd9BOMviyQgIHFPVSN_kQV6dAuyud4WZ6kUJyuO9go,1778
2
2
  deltacat/constants.py,sha256=_6oRI-3yp5c8J1qKGQZrt89I9-ttT_gSSvVsJ0h8Duc,1939
3
3
  deltacat/exceptions.py,sha256=yWM4RXK7uRrQc1VgJv6Lv2UiNZWAx2wolLq7cBwjlkg,12770
4
4
  deltacat/logs.py,sha256=6g16VkEFidbaMjgenAjggE1r2l664drMVhreRs8B1IQ,8438
5
5
  deltacat/aws/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
6
- deltacat/aws/clients.py,sha256=VgddlV3AEjlBGIFmhhHxokYzwJ-lXnmHAeprVyADduI,6948
6
+ deltacat/aws/clients.py,sha256=4eQvpkV1PzFfxog7EriuglOGGwNFHR5hbGYpjsNNPxk,6949
7
7
  deltacat/aws/constants.py,sha256=1HnDXrSokW-G3YA3qKEiv7fZVntDs1uSk6a7On-VG5k,1223
8
8
  deltacat/aws/s3u.py,sha256=IdT0XqDXVOkPdo5Em5u3qAkV1UXFpXaE1rTkUDKv4f4,28578
9
9
  deltacat/aws/redshift/__init__.py,sha256=7SvjG-dqox8zZUhFicTsUvpG5vXYDl_QQ3ohlHOgTKc,342
@@ -24,7 +24,7 @@ deltacat/compute/compactor/__init__.py,sha256=ivpOPve1yKi3Vz3tVgp-eeFMNEeUSf-dlR
24
24
  deltacat/compute/compactor/compaction_session.py,sha256=sGlSpfZaC_RYG2n8NGpT9z2X8V521nlLJktYtzafpmg,27715
25
25
  deltacat/compute/compactor/repartition_session.py,sha256=AAPwNZtPpC_Mtoja855_alBdXDA6efp7zcvkE-MANaQ,7254
26
26
  deltacat/compute/compactor/model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
27
- deltacat/compute/compactor/model/compact_partition_params.py,sha256=yBBm4gk3y-ZdFz22KeBrVruF0GauHk9ZL3xPjuM4Kt4,15593
27
+ deltacat/compute/compactor/model/compact_partition_params.py,sha256=RuyYQVuoxKlt4vYTbVpCgoM6K8S_-TFhVuOnPVkxLfE,15850
28
28
  deltacat/compute/compactor/model/compaction_session_audit_info.py,sha256=Aoae5KNmbdYt48utFQR_zrjHTkC9JNd4jPhQmyJji-A,30547
29
29
  deltacat/compute/compactor/model/compactor_version.py,sha256=RwRvManiCxZmzjAWzm1OPDxjB1BEHu1d0fBJyGhXKxA,87
30
30
  deltacat/compute/compactor/model/dedupe_result.py,sha256=1OCV944qJdLQ_-8scisVKl45ej1eRv9OV539QYZtQ-U,292
@@ -50,7 +50,7 @@ deltacat/compute/compactor/utils/round_completion_file.py,sha256=_rl8lBSO9KFW07Z
50
50
  deltacat/compute/compactor/utils/sort_key.py,sha256=oK6otg-CSsma6zlGPaKg-KNEvcZRG2NqBlCw1X3_FBc,2397
51
51
  deltacat/compute/compactor/utils/system_columns.py,sha256=CNIgAGos0xAGEpdaQIH7KfbSRrGZgjRbItXMararqXQ,9399
52
52
  deltacat/compute/compactor_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
53
- deltacat/compute/compactor_v2/compaction_session.py,sha256=WUfWYZuQBCxA5RQ0qgAZjUE7tHORWemWZaUIwVwFsC8,27950
53
+ deltacat/compute/compactor_v2/compaction_session.py,sha256=1V7EgtSF3gmqoaN6iRQ1Yw66Epvmlh2Hj6-y_rE83zI,7755
54
54
  deltacat/compute/compactor_v2/constants.py,sha256=RoVJb86km-0ghtEFB0z24H7yuCJCbQ2t7_-LuXFNYak,2304
55
55
  deltacat/compute/compactor_v2/deletes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
56
56
  deltacat/compute/compactor_v2/deletes/delete_file_envelope.py,sha256=AeuH9JRMwp6mvQf6P2cqL92hUEtResQq6qUTS0kIKac,3111
@@ -65,6 +65,8 @@ deltacat/compute/compactor_v2/model/hash_bucket_result.py,sha256=EsY9BPPywhmxlcL
65
65
  deltacat/compute/compactor_v2/model/merge_file_group.py,sha256=1o86t9lc3K6ZvtViVO1SVljCj6f0B3MfB3hqtGm2S0s,7410
66
66
  deltacat/compute/compactor_v2/model/merge_input.py,sha256=-SxTE0e67z2V7MiMEVz5aMu4E0k8h3-vqohvUUOC0do,5659
67
67
  deltacat/compute/compactor_v2/model/merge_result.py,sha256=_IZTCStpb4UKiRCJYA3g6EhAqjrw0t9vmoDAN8kIK-Y,436
68
+ deltacat/compute/compactor_v2/private/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
69
+ deltacat/compute/compactor_v2/private/compaction_utils.py,sha256=3ukQx50xH810XJu1KzKdxY95lGuZGerHhHTJ89ns-jg,27622
68
70
  deltacat/compute/compactor_v2/steps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
69
71
  deltacat/compute/compactor_v2/steps/hash_bucket.py,sha256=1R5xLUkl7GqL1nY-apAgY1czKDEHjIVYSRi9qLOMass,6726
70
72
  deltacat/compute/compactor_v2/steps/merge.py,sha256=ukCn312igxq7jNiCn7a2Vzk309LKdYZ902HTcEZhjM4,21774
@@ -75,7 +77,7 @@ deltacat/compute/compactor_v2/utils/delta.py,sha256=8hjkDeIIkSX-gAQ2utQSp2sZcO2t
75
77
  deltacat/compute/compactor_v2/utils/io.py,sha256=autXlE3uHICdCCuJoS7mfdeJbRRiz2_xlz-3izlccB4,5264
76
78
  deltacat/compute/compactor_v2/utils/merge.py,sha256=7UHxm71iJ1dgRoz8v73CqoeylNzO36t90OJsVVBDFxk,5312
77
79
  deltacat/compute/compactor_v2/utils/primary_key_index.py,sha256=ghyIifjXtqXgi8lN3lfnVQ2vi8uk_ny0FE7hsQlLjRQ,11538
78
- deltacat/compute/compactor_v2/utils/task_options.py,sha256=XFvZ_8mCq3cDnFlopFG84IahcYEddilZDmU1PkKq-zg,14067
80
+ deltacat/compute/compactor_v2/utils/task_options.py,sha256=VXvoVVUq5re8NiOoyrfz34qSRiOTB0IkxHJlMqKsBmk,14066
79
81
  deltacat/compute/merge_on_read/__init__.py,sha256=ckbgngmqPjYBYz_NySsR1vNTOb_hNpeL1sYkZKvBI9M,214
80
82
  deltacat/compute/merge_on_read/daft.py,sha256=1oC38u5ig_aTrq7EzyWBo8Ui54rb6yERYMk-vEFbpxM,1400
81
83
  deltacat/compute/merge_on_read/model/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -143,14 +145,14 @@ deltacat/tests/aws/test_s3u.py,sha256=FsYCH8K8DsDRPOtTp-w1Nu3ATqt4p1mqDo6aVJV-Sb
143
145
  deltacat/tests/catalog/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
144
146
  deltacat/tests/catalog/test_default_catalog_impl.py,sha256=2l5uwmtLlUJ9yH1LDggtj81fa-pHqbE0-VBt6G4Hyc0,3180
145
147
  deltacat/tests/compute/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
146
- deltacat/tests/compute/compact_partition_rebase_test_cases.py,sha256=NCMgZ5d9YyTb4Irp8Rnx8GLbvod08TshpiblFkZ5ItE,3105
147
- deltacat/tests/compute/compact_partition_rebase_then_incremental_test_cases.py,sha256=XP0rwMLgQRFt4aNblLT250tVjQqTYNtO2VXnD7CqugQ,73673
148
- deltacat/tests/compute/compact_partition_test_cases.py,sha256=H6CEXiRoHTIql3Z2_xMztY4YKoqqn9ZycpAnJyZooTU,25103
149
- deltacat/tests/compute/test_compact_partition_incremental.py,sha256=vH2z9F18QdjpQmNKTUk4IIrwRC5Uj7z41Ox7q1rFxZU,13995
148
+ deltacat/tests/compute/compact_partition_rebase_test_cases.py,sha256=NfcB1aTq6HeYMFrtooIIoifzLp5U0xFTN6F7Lpk8cYQ,3143
149
+ deltacat/tests/compute/compact_partition_rebase_then_incremental_test_cases.py,sha256=Kl5A7hoJ0pVOE-rZna_4XcuIjhuzQbJudvnfNYKHgGo,75436
150
+ deltacat/tests/compute/compact_partition_test_cases.py,sha256=R9eiKvxCLqcoHjAx3iOogdnXZEO9TvLbRf0wA7bcJN4,26170
151
+ deltacat/tests/compute/test_compact_partition_incremental.py,sha256=Z0hyQGhMZjCaOn1Vk4qUbgDiS7HDhtdNeFQyG1PJhqA,14559
150
152
  deltacat/tests/compute/test_compact_partition_params.py,sha256=Dm5eLyHo8oGMeO3XBbpj1rZqHtPZ1hAB7z2qvzc4Lxk,8497
151
- deltacat/tests/compute/test_compact_partition_rebase.py,sha256=qciMqIw-viNi6sdhSPWo2s3pK-cP00J6jz16h4vz2kY,10186
152
- deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py,sha256=NvXjgrYAB5zq_SzwjYMYwsTqseAMPNlDjaA6LEBJRbg,14159
153
- deltacat/tests/compute/test_util_common.py,sha256=qarWBIrRK0daZ_p7O-SlSx2U-3ma5uOBQAyHuqreBTE,6703
153
+ deltacat/tests/compute/test_compact_partition_rebase.py,sha256=hKMSQ-BQG6w0O_4TlzESY6pA5Ft5c5WSHLIFvj5hePI,11434
154
+ deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py,sha256=CHHfNFEJW8S1We7NE1Gg6EaoKEWnaOMRxWrLyirrahc,14643
155
+ deltacat/tests/compute/test_util_common.py,sha256=oTkTuo6wscVN8hmoQASIKP_DJN-M0um_ySCOcXv9AJA,11699
154
156
  deltacat/tests/compute/test_util_constant.py,sha256=4o-W3E7r7jhFl1A3OFLLrdKnwcF46zx4lEIDY8ONJ3c,929
155
157
  deltacat/tests/compute/test_util_create_table_deltas_repo.py,sha256=oY7ZMrvooDVOkhoAJnfdLGO0ejQAwgkqKrt7UmgiObU,9037
156
158
  deltacat/tests/compute/compactor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -216,8 +218,8 @@ deltacat/utils/ray_utils/concurrency.py,sha256=JDVwMiQWrmuSlyCWAoiq9ctoJ0XADEfDD
216
218
  deltacat/utils/ray_utils/dataset.py,sha256=waHdtH0c835a-2t51HYRHnulfC0_zBxx8mFSAPvPSPM,3274
217
219
  deltacat/utils/ray_utils/performance.py,sha256=d7JFM7vTXHzkGx9qNQcZzUWajnqINvYRwaM088_FpsE,464
218
220
  deltacat/utils/ray_utils/runtime.py,sha256=rB0A-tU9WZHz0J11LzJdANYtL397YyuemcA1l-K9dAw,5029
219
- deltacat-1.1.12.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
220
- deltacat-1.1.12.dist-info/METADATA,sha256=fqP5NYc_4wrfWcsQXO1Aht8xM22LrmDZLHfMAqq2opQ,1748
221
- deltacat-1.1.12.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
222
- deltacat-1.1.12.dist-info/top_level.txt,sha256=RWdIcid4Bv2i2ozLVh-70kJpyB61xEKXod9XXGpiono,9
223
- deltacat-1.1.12.dist-info/RECORD,,
221
+ deltacat-1.1.14.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
222
+ deltacat-1.1.14.dist-info/METADATA,sha256=orKTHhgUb74RXGlgcKhu-M36EmYd3-41AH7V1IP2jEI,1734
223
+ deltacat-1.1.14.dist-info/WHEEL,sha256=eOLhNAGa2EW3wWl_TU484h7q1UNgy0JXjjoqKoxAAQc,92
224
+ deltacat-1.1.14.dist-info/top_level.txt,sha256=RWdIcid4Bv2i2ozLVh-70kJpyB61xEKXod9XXGpiono,9
225
+ deltacat-1.1.14.dist-info/RECORD,,
@@ -1,5 +1,5 @@
1
1
  Wheel-Version: 1.0
2
- Generator: bdist_wheel (0.43.0)
2
+ Generator: bdist_wheel (0.44.0)
3
3
  Root-Is-Purelib: true
4
4
  Tag: py3-none-any
5
5