acryl-datahub 0.15.0.6rc2__py3-none-any.whl → 1.0.0__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.

Potentially problematic release.


This version of acryl-datahub might be problematic. Click here for more details.

Files changed (205) hide show
  1. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/METADATA +2522 -2493
  2. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/RECORD +205 -192
  3. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/WHEEL +1 -1
  4. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/entry_points.txt +1 -0
  5. datahub/_version.py +1 -1
  6. datahub/api/entities/common/serialized_value.py +4 -3
  7. datahub/api/entities/dataset/dataset.py +731 -42
  8. datahub/api/entities/structuredproperties/structuredproperties.py +2 -2
  9. datahub/cli/check_cli.py +72 -19
  10. datahub/cli/docker_cli.py +3 -3
  11. datahub/cli/iceberg_cli.py +31 -7
  12. datahub/cli/ingest_cli.py +30 -93
  13. datahub/cli/lite_cli.py +4 -2
  14. datahub/cli/specific/dataproduct_cli.py +1 -1
  15. datahub/cli/specific/dataset_cli.py +128 -14
  16. datahub/configuration/common.py +10 -2
  17. datahub/configuration/git.py +1 -3
  18. datahub/configuration/kafka.py +1 -1
  19. datahub/emitter/mce_builder.py +28 -13
  20. datahub/emitter/mcp_builder.py +4 -1
  21. datahub/emitter/response_helper.py +145 -0
  22. datahub/emitter/rest_emitter.py +323 -10
  23. datahub/ingestion/api/decorators.py +1 -1
  24. datahub/ingestion/api/source_helpers.py +4 -0
  25. datahub/ingestion/fs/s3_fs.py +2 -2
  26. datahub/ingestion/glossary/classification_mixin.py +1 -5
  27. datahub/ingestion/graph/client.py +41 -22
  28. datahub/ingestion/graph/entity_versioning.py +3 -3
  29. datahub/ingestion/graph/filters.py +64 -37
  30. datahub/ingestion/reporting/datahub_ingestion_run_summary_provider.py +1 -6
  31. datahub/ingestion/run/pipeline.py +112 -148
  32. datahub/ingestion/run/sink_callback.py +77 -0
  33. datahub/ingestion/sink/datahub_rest.py +8 -0
  34. datahub/ingestion/source/abs/config.py +2 -4
  35. datahub/ingestion/source/bigquery_v2/bigquery_audit.py +1 -1
  36. datahub/ingestion/source/bigquery_v2/bigquery_config.py +2 -46
  37. datahub/ingestion/source/bigquery_v2/bigquery_schema.py +6 -1
  38. datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py +7 -4
  39. datahub/ingestion/source/cassandra/cassandra.py +152 -233
  40. datahub/ingestion/source/cassandra/cassandra_api.py +13 -5
  41. datahub/ingestion/source/common/gcp_credentials_config.py +53 -0
  42. datahub/ingestion/source/common/subtypes.py +12 -0
  43. datahub/ingestion/source/csv_enricher.py +3 -3
  44. datahub/ingestion/source/data_lake_common/path_spec.py +1 -3
  45. datahub/ingestion/source/dbt/dbt_common.py +8 -5
  46. datahub/ingestion/source/dbt/dbt_core.py +11 -9
  47. datahub/ingestion/source/dbt/dbt_tests.py +4 -8
  48. datahub/ingestion/source/delta_lake/config.py +8 -1
  49. datahub/ingestion/source/delta_lake/report.py +4 -2
  50. datahub/ingestion/source/delta_lake/source.py +20 -5
  51. datahub/ingestion/source/dremio/dremio_api.py +4 -8
  52. datahub/ingestion/source/dremio/dremio_aspects.py +3 -5
  53. datahub/ingestion/source/dynamodb/dynamodb.py +6 -0
  54. datahub/ingestion/source/elastic_search.py +26 -6
  55. datahub/ingestion/source/feast.py +27 -8
  56. datahub/ingestion/source/file.py +6 -3
  57. datahub/ingestion/source/gc/dataprocess_cleanup.py +1 -1
  58. datahub/ingestion/source/gc/execution_request_cleanup.py +2 -1
  59. datahub/ingestion/source/ge_data_profiler.py +12 -15
  60. datahub/ingestion/source/iceberg/iceberg.py +46 -12
  61. datahub/ingestion/source/iceberg/iceberg_common.py +71 -21
  62. datahub/ingestion/source/identity/okta.py +37 -7
  63. datahub/ingestion/source/kafka/kafka.py +1 -1
  64. datahub/ingestion/source/kafka_connect/common.py +2 -7
  65. datahub/ingestion/source/kafka_connect/kafka_connect.py +97 -4
  66. datahub/ingestion/source/kafka_connect/sink_connectors.py +2 -2
  67. datahub/ingestion/source/kafka_connect/source_connectors.py +6 -9
  68. datahub/ingestion/source/looker/looker_common.py +6 -5
  69. datahub/ingestion/source/looker/looker_file_loader.py +2 -2
  70. datahub/ingestion/source/looker/looker_lib_wrapper.py +2 -1
  71. datahub/ingestion/source/looker/looker_source.py +1 -1
  72. datahub/ingestion/source/looker/looker_template_language.py +4 -2
  73. datahub/ingestion/source/looker/lookml_source.py +3 -2
  74. datahub/ingestion/source/metabase.py +57 -35
  75. datahub/ingestion/source/metadata/business_glossary.py +45 -3
  76. datahub/ingestion/source/metadata/lineage.py +2 -2
  77. datahub/ingestion/source/mlflow.py +365 -35
  78. datahub/ingestion/source/mode.py +18 -8
  79. datahub/ingestion/source/neo4j/neo4j_source.py +27 -7
  80. datahub/ingestion/source/nifi.py +37 -11
  81. datahub/ingestion/source/openapi.py +1 -1
  82. datahub/ingestion/source/openapi_parser.py +49 -17
  83. datahub/ingestion/source/powerbi/m_query/parser.py +3 -2
  84. datahub/ingestion/source/powerbi/m_query/tree_function.py +2 -1
  85. datahub/ingestion/source/powerbi/powerbi.py +1 -3
  86. datahub/ingestion/source/powerbi/rest_api_wrapper/data_resolver.py +2 -1
  87. datahub/ingestion/source/powerbi_report_server/report_server.py +26 -7
  88. datahub/ingestion/source/powerbi_report_server/report_server_domain.py +1 -1
  89. datahub/ingestion/source/preset.py +7 -4
  90. datahub/ingestion/source/pulsar.py +3 -2
  91. datahub/ingestion/source/qlik_sense/websocket_connection.py +4 -2
  92. datahub/ingestion/source/redash.py +31 -7
  93. datahub/ingestion/source/redshift/config.py +4 -0
  94. datahub/ingestion/source/redshift/datashares.py +236 -0
  95. datahub/ingestion/source/redshift/lineage.py +6 -2
  96. datahub/ingestion/source/redshift/lineage_v2.py +24 -9
  97. datahub/ingestion/source/redshift/profile.py +1 -1
  98. datahub/ingestion/source/redshift/query.py +133 -33
  99. datahub/ingestion/source/redshift/redshift.py +46 -73
  100. datahub/ingestion/source/redshift/redshift_schema.py +186 -6
  101. datahub/ingestion/source/redshift/report.py +3 -0
  102. datahub/ingestion/source/s3/config.py +5 -5
  103. datahub/ingestion/source/s3/source.py +20 -41
  104. datahub/ingestion/source/salesforce.py +550 -275
  105. datahub/ingestion/source/schema_inference/object.py +1 -1
  106. datahub/ingestion/source/sigma/sigma.py +1 -1
  107. datahub/ingestion/source/slack/slack.py +31 -10
  108. datahub/ingestion/source/snowflake/snowflake_connection.py +2 -2
  109. datahub/ingestion/source/snowflake/snowflake_queries.py +19 -13
  110. datahub/ingestion/source/snowflake/snowflake_query.py +6 -4
  111. datahub/ingestion/source/snowflake/snowflake_schema.py +3 -4
  112. datahub/ingestion/source/snowflake/snowflake_v2.py +1 -1
  113. datahub/ingestion/source/sql/athena.py +10 -16
  114. datahub/ingestion/source/sql/druid.py +1 -5
  115. datahub/ingestion/source/sql/hive.py +15 -6
  116. datahub/ingestion/source/sql/hive_metastore.py +3 -2
  117. datahub/ingestion/source/sql/mssql/job_models.py +29 -0
  118. datahub/ingestion/source/sql/mssql/source.py +11 -5
  119. datahub/ingestion/source/sql/oracle.py +127 -63
  120. datahub/ingestion/source/sql/sql_common.py +16 -18
  121. datahub/ingestion/source/sql/sql_types.py +2 -2
  122. datahub/ingestion/source/sql/teradata.py +19 -5
  123. datahub/ingestion/source/sql/trino.py +2 -2
  124. datahub/ingestion/source/state/stale_entity_removal_handler.py +4 -8
  125. datahub/ingestion/source/superset.py +222 -62
  126. datahub/ingestion/source/tableau/tableau.py +22 -6
  127. datahub/ingestion/source/tableau/tableau_common.py +3 -2
  128. datahub/ingestion/source/unity/ge_profiler.py +2 -1
  129. datahub/ingestion/source/unity/source.py +11 -1
  130. datahub/ingestion/source/vertexai.py +697 -0
  131. datahub/ingestion/source_config/pulsar.py +3 -1
  132. datahub/ingestion/transformer/pattern_cleanup_ownership.py +25 -7
  133. datahub/lite/duckdb_lite.py +3 -10
  134. datahub/lite/lite_local.py +1 -1
  135. datahub/lite/lite_util.py +4 -3
  136. datahub/metadata/_schema_classes.py +714 -417
  137. datahub/metadata/_urns/urn_defs.py +1673 -1649
  138. datahub/metadata/com/linkedin/pegasus2avro/incident/__init__.py +4 -0
  139. datahub/metadata/schema.avsc +16438 -16603
  140. datahub/metadata/schemas/AssertionInfo.avsc +3 -1
  141. datahub/metadata/schemas/BusinessAttributeInfo.avsc +6 -2
  142. datahub/metadata/schemas/BusinessAttributes.avsc +6 -0
  143. datahub/metadata/schemas/ChartInfo.avsc +1 -0
  144. datahub/metadata/schemas/CorpGroupKey.avsc +2 -1
  145. datahub/metadata/schemas/CorpUserInfo.avsc +13 -0
  146. datahub/metadata/schemas/CorpUserKey.avsc +2 -1
  147. datahub/metadata/schemas/DataHubIngestionSourceInfo.avsc +8 -3
  148. datahub/metadata/schemas/DataProcessInstanceInput.avsc +129 -1
  149. datahub/metadata/schemas/DataProcessInstanceOutput.avsc +131 -3
  150. datahub/metadata/schemas/DataProcessKey.avsc +2 -1
  151. datahub/metadata/schemas/DataProductKey.avsc +2 -1
  152. datahub/metadata/schemas/DomainKey.avsc +2 -1
  153. datahub/metadata/schemas/EditableSchemaMetadata.avsc +6 -2
  154. datahub/metadata/schemas/GlossaryNodeKey.avsc +3 -1
  155. datahub/metadata/schemas/GlossaryTermKey.avsc +2 -1
  156. datahub/metadata/schemas/GlossaryTerms.avsc +3 -1
  157. datahub/metadata/schemas/IncidentInfo.avsc +130 -46
  158. datahub/metadata/schemas/InputFields.avsc +3 -1
  159. datahub/metadata/schemas/MLFeatureKey.avsc +2 -1
  160. datahub/metadata/schemas/MLFeatureTableKey.avsc +2 -1
  161. datahub/metadata/schemas/MLModelDeploymentKey.avsc +2 -1
  162. datahub/metadata/schemas/MLModelGroupKey.avsc +3 -1
  163. datahub/metadata/schemas/MLModelKey.avsc +3 -1
  164. datahub/metadata/schemas/MLPrimaryKeyKey.avsc +2 -1
  165. datahub/metadata/schemas/MetadataChangeEvent.avsc +20 -2
  166. datahub/metadata/schemas/PostKey.avsc +2 -1
  167. datahub/metadata/schemas/SchemaFieldKey.avsc +2 -1
  168. datahub/metadata/schemas/SchemaMetadata.avsc +3 -1
  169. datahub/metadata/schemas/StructuredPropertyDefinition.avsc +14 -0
  170. datahub/metadata/schemas/VersionProperties.avsc +18 -0
  171. datahub/metadata/schemas/VersionSetProperties.avsc +5 -0
  172. datahub/pydantic/__init__.py +0 -0
  173. datahub/pydantic/compat.py +58 -0
  174. datahub/sdk/__init__.py +30 -12
  175. datahub/sdk/_all_entities.py +1 -1
  176. datahub/sdk/_attribution.py +4 -0
  177. datahub/sdk/_shared.py +258 -16
  178. datahub/sdk/_utils.py +35 -0
  179. datahub/sdk/container.py +30 -6
  180. datahub/sdk/dataset.py +118 -20
  181. datahub/sdk/{_entity.py → entity.py} +24 -1
  182. datahub/sdk/entity_client.py +1 -1
  183. datahub/sdk/main_client.py +23 -0
  184. datahub/sdk/resolver_client.py +17 -29
  185. datahub/sdk/search_client.py +50 -0
  186. datahub/sdk/search_filters.py +374 -0
  187. datahub/specific/dataset.py +3 -4
  188. datahub/sql_parsing/_sqlglot_patch.py +2 -10
  189. datahub/sql_parsing/schema_resolver.py +1 -1
  190. datahub/sql_parsing/split_statements.py +220 -126
  191. datahub/sql_parsing/sql_parsing_common.py +7 -0
  192. datahub/sql_parsing/sqlglot_lineage.py +1 -1
  193. datahub/sql_parsing/sqlglot_utils.py +1 -4
  194. datahub/testing/check_sql_parser_result.py +5 -6
  195. datahub/testing/compare_metadata_json.py +7 -6
  196. datahub/testing/pytest_hooks.py +56 -0
  197. datahub/upgrade/upgrade.py +2 -2
  198. datahub/utilities/file_backed_collections.py +3 -14
  199. datahub/utilities/ingest_utils.py +106 -0
  200. datahub/utilities/mapping.py +1 -1
  201. datahub/utilities/memory_footprint.py +3 -2
  202. datahub/utilities/sentinels.py +22 -0
  203. datahub/utilities/unified_diff.py +5 -1
  204. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/LICENSE +0 -0
  205. {acryl_datahub-0.15.0.6rc2.dist-info → acryl_datahub-1.0.0.dist-info}/top_level.txt +0 -0
@@ -33,7 +33,9 @@ def _is_valid_hostname(hostname: str) -> bool:
33
33
 
34
34
 
35
35
  class PulsarSourceConfig(
36
- StatefulIngestionConfigBase, PlatformInstanceConfigMixin, EnvConfigMixin
36
+ StatefulIngestionConfigBase,
37
+ PlatformInstanceConfigMixin,
38
+ EnvConfigMixin,
37
39
  ):
38
40
  web_service_url: str = Field(
39
41
  default="http://localhost:8080", description="The web URL for the cluster."
@@ -1,3 +1,4 @@
1
+ import logging
1
2
  import re
2
3
  from typing import List, Optional, Set, cast
3
4
 
@@ -10,8 +11,11 @@ from datahub.metadata.schema_classes import (
10
11
  OwnershipClass,
11
12
  OwnershipTypeClass,
12
13
  )
14
+ from datahub.metadata.urns import CorpGroupUrn, CorpUserUrn
15
+ from datahub.utilities.urns._urn_base import Urn
16
+ from datahub.utilities.urns.error import InvalidUrnError
13
17
 
14
- _USER_URN_PREFIX: str = "urn:li:corpuser:"
18
+ logger = logging.getLogger(__name__)
15
19
 
16
20
 
17
21
  class PatternCleanUpOwnershipConfig(ConfigModel):
@@ -49,6 +53,11 @@ class PatternCleanUpOwnership(OwnershipTransformer):
49
53
  else:
50
54
  return set()
51
55
 
56
+ def _process_owner(self, name: str) -> str:
57
+ for value in self.config.pattern_for_cleanup:
58
+ name = re.sub(value, "", name)
59
+ return name
60
+
52
61
  def transform_aspect(
53
62
  self, entity_urn: str, aspect_name: str, aspect: Optional[builder.Aspect]
54
63
  ) -> Optional[builder.Aspect]:
@@ -58,14 +67,23 @@ class PatternCleanUpOwnership(OwnershipTransformer):
58
67
  # clean all the owners based on the parameters received from config
59
68
  cleaned_owner_urns: List[str] = []
60
69
  for owner_urn in current_owner_urns:
61
- user_id: str = owner_urn.split(_USER_URN_PREFIX)[1]
62
- for value in self.config.pattern_for_cleanup:
63
- user_id = re.sub(value, "", user_id)
64
-
65
- cleaned_owner_urns.append(_USER_URN_PREFIX + user_id)
70
+ username = ""
71
+ try:
72
+ owner: Urn = Urn.from_string(owner_urn)
73
+ if isinstance(owner, CorpUserUrn):
74
+ username = str(CorpUserUrn(self._process_owner(owner.username)))
75
+ elif isinstance(owner, CorpGroupUrn):
76
+ username = str(CorpGroupUrn(self._process_owner(owner.name)))
77
+ else:
78
+ logger.warning(f"{owner_urn} is not a supported owner type.")
79
+ username = owner_urn
80
+ except InvalidUrnError:
81
+ logger.warning(f"Could not parse {owner_urn} from {entity_urn}")
82
+ username = owner_urn
83
+ cleaned_owner_urns.append(username)
66
84
 
67
85
  ownership_type, ownership_type_urn = builder.validate_ownership_type(
68
- OwnershipTypeClass.DATAOWNER
86
+ OwnershipTypeClass.TECHNICAL_OWNER
69
87
  )
70
88
  owners = [
71
89
  OwnerClass(
@@ -284,9 +284,10 @@ class DuckDBLite(DataHubLiteLocal[DuckDBLiteConfig]):
284
284
  self,
285
285
  query: str,
286
286
  flavor: SearchFlavor,
287
- aspects: List[str] = [],
287
+ aspects: Optional[List[str]] = None,
288
288
  snippet: bool = True,
289
289
  ) -> Iterable[Searchable]:
290
+ aspects = aspects or []
290
291
  if flavor == SearchFlavor.FREE_TEXT:
291
292
  base_query = f"SELECT distinct(urn), 'urn', NULL from metadata_aspect_v2 where urn ILIKE '%{query}%' UNION SELECT urn, aspect_name, metadata from metadata_aspect_v2 where metadata->>'$.name' ILIKE '%{query}%'"
292
293
  for r in self.duckdb_client.execute(base_query).fetchall():
@@ -759,15 +760,7 @@ class DuckDBLite(DataHubLiteLocal[DuckDBLiteConfig]):
759
760
  entity_id=[str(data_platform_urn), data_platform_instance],
760
761
  )
761
762
  self._create_edges_from_data_platform_instance(data_platform_instance_urn)
762
- elif isinstance(aspect, ChartInfoClass):
763
- urn = Urn.from_string(entity_urn)
764
- self.add_edge(
765
- entity_urn,
766
- "name",
767
- aspect.title + f" ({urn.get_entity_id()[-1]})",
768
- remove_existing=True,
769
- )
770
- elif isinstance(aspect, DashboardInfoClass):
763
+ elif isinstance(aspect, (ChartInfoClass, DashboardInfoClass)):
771
764
  urn = Urn.from_string(entity_urn)
772
765
  self.add_edge(
773
766
  entity_urn,
@@ -90,7 +90,7 @@ class DataHubLiteLocal(Generic[LiteConfig], Closeable, metaclass=ABCMeta):
90
90
  self,
91
91
  query: str,
92
92
  flavor: SearchFlavor,
93
- aspects: List[str] = [],
93
+ aspects: Optional[List[str]] = None,
94
94
  snippet: bool = True,
95
95
  ) -> Iterable[Searchable]:
96
96
  pass
datahub/lite/lite_util.py CHANGED
@@ -70,9 +70,10 @@ class DataHubLiteWrapper(DataHubLiteLocal):
70
70
  self,
71
71
  query: str,
72
72
  flavor: SearchFlavor,
73
- aspects: List[str] = [],
73
+ aspects: Optional[List[str]] = None,
74
74
  snippet: bool = True,
75
75
  ) -> Iterable[Searchable]:
76
+ aspects = aspects or []
76
77
  yield from self.lite.search(query, flavor, aspects, snippet)
77
78
 
78
79
  def ls(self, path: str) -> List[Browseable]:
@@ -96,10 +97,10 @@ def get_datahub_lite(config_dict: dict, read_only: bool = False) -> "DataHubLite
96
97
  lite_type = lite_local_config.type
97
98
  try:
98
99
  lite_class = lite_registry.get(lite_type)
99
- except KeyError:
100
+ except KeyError as e:
100
101
  raise Exception(
101
102
  f"Failed to find a registered lite implementation for {lite_type}. Valid values are {[k for k in lite_registry.mapping.keys()]}"
102
- )
103
+ ) from e
103
104
 
104
105
  lite_specific_config = lite_class.get_config_class().parse_obj(
105
106
  lite_local_config.config