deltacat 2.0.0b11__py3-none-any.whl → 2.0.0b12__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.
- deltacat/__init__.py +78 -3
- deltacat/api.py +122 -67
- deltacat/aws/constants.py +0 -23
- deltacat/aws/s3u.py +4 -631
- deltacat/benchmarking/conftest.py +0 -18
- deltacat/catalog/__init__.py +2 -0
- deltacat/catalog/delegate.py +445 -63
- deltacat/catalog/interface.py +188 -62
- deltacat/catalog/main/impl.py +2417 -271
- deltacat/catalog/model/catalog.py +49 -10
- deltacat/catalog/model/properties.py +38 -0
- deltacat/compute/compactor/compaction_session.py +97 -75
- deltacat/compute/compactor/model/compact_partition_params.py +75 -30
- deltacat/compute/compactor/model/compaction_session_audit_info.py +17 -0
- deltacat/compute/compactor/model/round_completion_info.py +16 -6
- deltacat/compute/compactor/repartition_session.py +8 -21
- deltacat/compute/compactor/steps/hash_bucket.py +5 -5
- deltacat/compute/compactor/steps/materialize.py +9 -7
- deltacat/compute/compactor/steps/repartition.py +12 -11
- deltacat/compute/compactor/utils/io.py +6 -5
- deltacat/compute/compactor/utils/round_completion_reader.py +117 -0
- deltacat/compute/compactor/utils/system_columns.py +3 -1
- deltacat/compute/compactor_v2/compaction_session.py +17 -14
- deltacat/compute/compactor_v2/constants.py +30 -1
- deltacat/compute/compactor_v2/model/evaluate_compaction_result.py +0 -1
- deltacat/compute/compactor_v2/model/hash_bucket_input.py +9 -3
- deltacat/compute/compactor_v2/model/merge_file_group.py +5 -2
- deltacat/compute/compactor_v2/model/merge_input.py +33 -8
- deltacat/compute/compactor_v2/private/compaction_utils.py +167 -68
- deltacat/compute/compactor_v2/steps/hash_bucket.py +5 -2
- deltacat/compute/compactor_v2/steps/merge.py +267 -55
- deltacat/compute/compactor_v2/utils/content_type_params.py +34 -6
- deltacat/compute/compactor_v2/utils/dedupe.py +1 -1
- deltacat/compute/compactor_v2/utils/delta.py +5 -3
- deltacat/compute/compactor_v2/utils/io.py +11 -4
- deltacat/compute/compactor_v2/utils/merge.py +15 -2
- deltacat/compute/compactor_v2/utils/primary_key_index.py +28 -4
- deltacat/compute/compactor_v2/utils/task_options.py +45 -33
- deltacat/compute/converter/converter_session.py +145 -32
- deltacat/compute/converter/model/convert_input.py +26 -19
- deltacat/compute/converter/model/convert_input_files.py +33 -16
- deltacat/compute/converter/model/convert_result.py +35 -16
- deltacat/compute/converter/model/converter_session_params.py +24 -21
- deltacat/compute/converter/pyiceberg/catalog.py +21 -18
- deltacat/compute/converter/pyiceberg/overrides.py +18 -9
- deltacat/compute/converter/pyiceberg/update_snapshot_overrides.py +148 -100
- deltacat/compute/converter/steps/convert.py +157 -50
- deltacat/compute/converter/steps/dedupe.py +24 -11
- deltacat/compute/converter/utils/convert_task_options.py +27 -12
- deltacat/compute/converter/utils/converter_session_utils.py +126 -60
- deltacat/compute/converter/utils/iceberg_columns.py +8 -8
- deltacat/compute/converter/utils/io.py +101 -12
- deltacat/compute/converter/utils/s3u.py +33 -27
- deltacat/compute/janitor.py +205 -0
- deltacat/compute/jobs/client.py +19 -8
- deltacat/compute/resource_estimation/delta.py +38 -6
- deltacat/compute/resource_estimation/model.py +8 -0
- deltacat/constants.py +44 -0
- deltacat/docs/autogen/schema/__init__.py +0 -0
- deltacat/docs/autogen/schema/inference/__init__.py +0 -0
- deltacat/docs/autogen/schema/inference/generate_type_mappings.py +687 -0
- deltacat/docs/autogen/schema/inference/parse_json_type_mappings.py +673 -0
- deltacat/examples/compactor/__init__.py +0 -0
- deltacat/examples/compactor/aws/__init__.py +1 -0
- deltacat/examples/compactor/bootstrap.py +863 -0
- deltacat/examples/compactor/compactor.py +373 -0
- deltacat/examples/compactor/explorer.py +473 -0
- deltacat/examples/compactor/gcp/__init__.py +1 -0
- deltacat/examples/compactor/job_runner.py +439 -0
- deltacat/examples/compactor/utils/__init__.py +1 -0
- deltacat/examples/compactor/utils/common.py +261 -0
- deltacat/examples/experimental/iceberg/converter/__init__.py +0 -0
- deltacat/examples/experimental/iceberg/converter/beam/__init__.py +0 -0
- deltacat/examples/experimental/iceberg/converter/beam/app.py +226 -0
- deltacat/examples/experimental/iceberg/converter/beam/main.py +133 -0
- deltacat/examples/experimental/iceberg/converter/beam/test_workflow.py +113 -0
- deltacat/examples/experimental/iceberg/converter/beam/utils/__init__.py +3 -0
- deltacat/examples/experimental/iceberg/converter/beam/utils/common.py +174 -0
- deltacat/examples/experimental/iceberg/converter/beam/utils/spark.py +263 -0
- deltacat/exceptions.py +66 -4
- deltacat/experimental/catalog/iceberg/impl.py +2 -2
- deltacat/experimental/compatibility/__init__.py +0 -0
- deltacat/experimental/compatibility/backfill_locator_to_id_mappings.py +201 -0
- deltacat/experimental/converter_agent/__init__.py +0 -0
- deltacat/experimental/converter_agent/beam/__init__.py +0 -0
- deltacat/experimental/converter_agent/beam/managed.py +173 -0
- deltacat/experimental/converter_agent/table_monitor.py +479 -0
- deltacat/experimental/storage/iceberg/iceberg_scan_planner.py +105 -4
- deltacat/experimental/storage/iceberg/impl.py +5 -3
- deltacat/experimental/storage/iceberg/model.py +7 -3
- deltacat/experimental/storage/iceberg/visitor.py +119 -0
- deltacat/experimental/storage/rivulet/dataset.py +0 -3
- deltacat/experimental/storage/rivulet/metastore/delta.py +0 -2
- deltacat/experimental/storage/rivulet/reader/dataset_metastore.py +3 -2
- deltacat/io/datasource/deltacat_datasource.py +0 -1
- deltacat/storage/__init__.py +20 -2
- deltacat/storage/interface.py +54 -32
- deltacat/storage/main/impl.py +1494 -541
- deltacat/storage/model/delta.py +27 -3
- deltacat/storage/model/locator.py +6 -12
- deltacat/storage/model/manifest.py +182 -6
- deltacat/storage/model/metafile.py +151 -78
- deltacat/storage/model/namespace.py +8 -1
- deltacat/storage/model/partition.py +117 -42
- deltacat/storage/model/schema.py +2427 -159
- deltacat/storage/model/sort_key.py +40 -0
- deltacat/storage/model/stream.py +9 -2
- deltacat/storage/model/table.py +12 -1
- deltacat/storage/model/table_version.py +11 -0
- deltacat/storage/model/transaction.py +1184 -208
- deltacat/storage/model/transform.py +81 -2
- deltacat/storage/model/types.py +48 -26
- deltacat/tests/_io/test_cloudpickle_bug_fix.py +8 -4
- deltacat/tests/aws/test_s3u.py +2 -31
- deltacat/tests/catalog/main/test_catalog_impl_table_operations.py +1606 -70
- deltacat/tests/catalog/test_catalogs.py +54 -11
- deltacat/tests/catalog/test_default_catalog_impl.py +12152 -71
- deltacat/tests/compute/compact_partition_test_cases.py +35 -8
- deltacat/tests/compute/compactor/steps/test_repartition.py +12 -12
- deltacat/tests/compute/compactor/utils/test_io.py +124 -120
- deltacat/tests/compute/compactor/utils/test_round_completion_reader.py +254 -0
- deltacat/tests/compute/compactor_v2/test_compaction_session.py +423 -312
- deltacat/tests/compute/compactor_v2/utils/test_content_type_params.py +266 -0
- deltacat/tests/compute/compactor_v2/utils/test_primary_key_index.py +45 -0
- deltacat/tests/compute/compactor_v2/utils/test_task_options.py +270 -1
- deltacat/tests/compute/conftest.py +8 -44
- deltacat/tests/compute/converter/test_convert_session.py +675 -490
- deltacat/tests/compute/converter/utils.py +15 -6
- deltacat/tests/compute/resource_estimation/test_delta.py +145 -79
- deltacat/tests/compute/test_compact_partition_incremental.py +103 -70
- deltacat/tests/compute/test_compact_partition_multiple_rounds.py +89 -66
- deltacat/tests/compute/test_compact_partition_params.py +13 -8
- deltacat/tests/compute/test_compact_partition_rebase.py +77 -62
- deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py +263 -193
- deltacat/tests/compute/test_janitor.py +236 -0
- deltacat/tests/compute/test_util_common.py +716 -43
- deltacat/tests/compute/test_util_constant.py +0 -1
- deltacat/tests/{storage/conftest.py → conftest.py} +1 -1
- deltacat/tests/experimental/__init__.py +1 -0
- deltacat/tests/experimental/compatibility/__init__.py +1 -0
- deltacat/tests/experimental/compatibility/test_backfill_locator_to_id_mappings.py +582 -0
- deltacat/tests/storage/main/test_main_storage.py +6900 -95
- deltacat/tests/storage/model/test_metafile_io.py +78 -173
- deltacat/tests/storage/model/test_partition_scheme.py +85 -0
- deltacat/tests/storage/model/test_schema.py +171 -0
- deltacat/tests/storage/model/test_schema_update.py +1925 -0
- deltacat/tests/storage/model/test_sort_scheme.py +90 -0
- deltacat/tests/storage/model/test_transaction.py +393 -48
- deltacat/tests/storage/model/test_transaction_history.py +886 -0
- deltacat/tests/test_deltacat_api.py +988 -4
- deltacat/tests/test_exceptions.py +9 -5
- deltacat/tests/test_utils/pyarrow.py +52 -21
- deltacat/tests/test_utils/storage.py +23 -34
- deltacat/tests/types/__init__.py +0 -0
- deltacat/tests/types/test_tables.py +104 -0
- deltacat/tests/utils/exceptions.py +22 -0
- deltacat/tests/utils/main_deltacat_storage_mock.py +31 -0
- deltacat/tests/utils/ray_utils/test_dataset.py +123 -5
- deltacat/tests/utils/test_daft.py +121 -31
- deltacat/tests/utils/test_numpy.py +1193 -0
- deltacat/tests/utils/test_pandas.py +1106 -0
- deltacat/tests/utils/test_polars.py +1040 -0
- deltacat/tests/utils/test_pyarrow.py +1370 -89
- deltacat/types/media.py +221 -11
- deltacat/types/tables.py +2329 -59
- deltacat/utils/arguments.py +33 -1
- deltacat/utils/daft.py +411 -150
- deltacat/utils/filesystem.py +100 -0
- deltacat/utils/metafile_locator.py +2 -1
- deltacat/utils/numpy.py +118 -26
- deltacat/utils/pandas.py +577 -48
- deltacat/utils/polars.py +658 -27
- deltacat/utils/pyarrow.py +1258 -213
- deltacat/utils/ray_utils/dataset.py +101 -10
- deltacat/utils/reader_compatibility_mapping.py +3083 -0
- deltacat/utils/url.py +56 -15
- deltacat-2.0.0b12.dist-info/METADATA +1163 -0
- {deltacat-2.0.0b11.dist-info → deltacat-2.0.0b12.dist-info}/RECORD +183 -145
- {deltacat-2.0.0b11.dist-info → deltacat-2.0.0b12.dist-info}/WHEEL +1 -1
- deltacat/compute/compactor/utils/round_completion_file.py +0 -97
- deltacat/compute/merge_on_read/__init__.py +0 -4
- deltacat/compute/merge_on_read/daft.py +0 -40
- deltacat/compute/merge_on_read/model/merge_on_read_params.py +0 -66
- deltacat/compute/merge_on_read/utils/delta.py +0 -42
- deltacat/tests/compute/compactor/utils/test_round_completion_file.py +0 -231
- deltacat/tests/compute/test_util_create_table_deltas_repo.py +0 -388
- deltacat/tests/local_deltacat_storage/__init__.py +0 -1236
- deltacat/tests/local_deltacat_storage/exceptions.py +0 -10
- deltacat/utils/s3fs.py +0 -21
- deltacat-2.0.0b11.dist-info/METADATA +0 -67
- /deltacat/{compute/merge_on_read/model → docs}/__init__.py +0 -0
- /deltacat/{compute/merge_on_read/utils → docs/autogen}/__init__.py +0 -0
- {deltacat-2.0.0b11.dist-info → deltacat-2.0.0b12.dist-info/licenses}/LICENSE +0 -0
- {deltacat-2.0.0b11.dist-info → deltacat-2.0.0b12.dist-info}/top_level.txt +0 -0
@@ -7,11 +7,6 @@ import pytest
|
|
7
7
|
from _pytest.terminal import TerminalReporter
|
8
8
|
|
9
9
|
from deltacat.benchmarking.benchmark_report import BenchmarkReport
|
10
|
-
from deltacat.utils.pyarrow import s3_file_to_table
|
11
|
-
from deltacat.types.media import (
|
12
|
-
ContentEncoding,
|
13
|
-
ContentType,
|
14
|
-
)
|
15
10
|
|
16
11
|
|
17
12
|
@pytest.fixture(autouse=True, scope="function")
|
@@ -42,17 +37,6 @@ def pyarrow_read(path: str, columns: list[str] | None = None) -> pa.Table:
|
|
42
37
|
return papq.read_table(path, columns=columns, filesystem=fs)
|
43
38
|
|
44
39
|
|
45
|
-
def deltacat_read(path: str, columns: list[str] | None = None) -> pa.Table:
|
46
|
-
assert path.startswith("s3://")
|
47
|
-
return s3_file_to_table(
|
48
|
-
path,
|
49
|
-
content_type=ContentType.PARQUET,
|
50
|
-
content_encoding=ContentEncoding.IDENTITY,
|
51
|
-
column_names=None, # Parquet files are schemaful
|
52
|
-
include_columns=columns,
|
53
|
-
)
|
54
|
-
|
55
|
-
|
56
40
|
def daft_table_read(path: str, columns: list[str] | None = None) -> pa.Table:
|
57
41
|
try:
|
58
42
|
import daft
|
@@ -69,12 +53,10 @@ def daft_table_read(path: str, columns: list[str] | None = None) -> pa.Table:
|
|
69
53
|
params=[
|
70
54
|
daft_table_read,
|
71
55
|
pyarrow_read,
|
72
|
-
deltacat_read,
|
73
56
|
],
|
74
57
|
ids=[
|
75
58
|
"daft_table",
|
76
59
|
"pyarrow",
|
77
|
-
"deltacat",
|
78
60
|
],
|
79
61
|
)
|
80
62
|
def read_fn(request):
|
deltacat/catalog/__init__.py
CHANGED
@@ -21,6 +21,7 @@ from deltacat.catalog.delegate import (
|
|
21
21
|
from deltacat.catalog.model.catalog import ( # noqa: F401
|
22
22
|
all_catalogs,
|
23
23
|
init,
|
24
|
+
init_local,
|
24
25
|
is_initialized,
|
25
26
|
clear_catalogs,
|
26
27
|
get_catalog,
|
@@ -57,6 +58,7 @@ __all__ = [
|
|
57
58
|
"write_to_table",
|
58
59
|
"all_catalogs",
|
59
60
|
"init",
|
61
|
+
"init_local",
|
60
62
|
"is_initialized",
|
61
63
|
"clear_catalogs",
|
62
64
|
"get_catalog",
|