acryl-datahub 1.0.0rc9__py3-none-any.whl → 1.0.0rc11__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 (36) hide show
  1. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/METADATA +2445 -2446
  2. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/RECORD +36 -35
  3. datahub/_version.py +1 -1
  4. datahub/api/entities/common/serialized_value.py +4 -3
  5. datahub/emitter/mce_builder.py +28 -13
  6. datahub/ingestion/source/common/subtypes.py +7 -0
  7. datahub/ingestion/source/iceberg/iceberg_common.py +40 -1
  8. datahub/ingestion/source/identity/okta.py +22 -0
  9. datahub/ingestion/source/metabase.py +3 -3
  10. datahub/ingestion/source/metadata/business_glossary.py +45 -3
  11. datahub/ingestion/source/mode.py +1 -1
  12. datahub/ingestion/source/redshift/config.py +4 -0
  13. datahub/ingestion/source/redshift/datashares.py +236 -0
  14. datahub/ingestion/source/redshift/lineage.py +6 -2
  15. datahub/ingestion/source/redshift/lineage_v2.py +7 -4
  16. datahub/ingestion/source/redshift/profile.py +1 -1
  17. datahub/ingestion/source/redshift/query.py +125 -33
  18. datahub/ingestion/source/redshift/redshift.py +41 -72
  19. datahub/ingestion/source/redshift/redshift_schema.py +166 -6
  20. datahub/ingestion/source/redshift/report.py +3 -0
  21. datahub/ingestion/source/sql/mssql/job_models.py +29 -0
  22. datahub/ingestion/source/sql/mssql/source.py +10 -4
  23. datahub/ingestion/source/sql/oracle.py +93 -63
  24. datahub/metadata/_schema_classes.py +5 -5
  25. datahub/metadata/_urns/urn_defs.py +24 -0
  26. datahub/metadata/schema.avsc +2 -1
  27. datahub/metadata/schemas/DomainKey.avsc +2 -1
  28. datahub/metadata/schemas/GlossaryNodeKey.avsc +2 -1
  29. datahub/metadata/schemas/MLModelDeploymentKey.avsc +2 -1
  30. datahub/metadata/schemas/MLModelGroupKey.avsc +2 -1
  31. datahub/metadata/schemas/MLModelKey.avsc +2 -1
  32. datahub/sql_parsing/sql_parsing_common.py +7 -0
  33. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/LICENSE +0 -0
  34. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/WHEEL +0 -0
  35. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/entry_points.txt +0 -0
  36. {acryl_datahub-1.0.0rc9.dist-info → acryl_datahub-1.0.0rc11.dist-info}/top_level.txt +0 -0
datahub/metadata/schemas/DomainKey.avsc CHANGED
@@ -10,7 +10,8 @@
10
10
  "ownership",
11
11
  "structuredProperties",
12
12
  "forms",
13
- "testResults"
13
+ "testResults",
14
+ "displayProperties"
14
15
  ],
15
16
  "entityDoc": "A data domain within an organization."
16
17
  },
datahub/metadata/schemas/GlossaryNodeKey.avsc CHANGED
@@ -12,7 +12,8 @@
12
12
  "structuredProperties",
13
13
  "forms",
14
14
  "testResults",
15
- "subTypes"
15
+ "subTypes",
16
+ "displayProperties"
16
17
  ]
17
18
  },
18
19
  "name": "GlossaryNodeKey",
datahub/metadata/schemas/MLModelDeploymentKey.avsc CHANGED
@@ -11,7 +11,8 @@
11
11
  "deprecation",
12
12
  "globalTags",
13
13
  "dataPlatformInstance",
14
- "testResults"
14
+ "testResults",
15
+ "container"
15
16
  ]
16
17
  },
17
18
  "name": "MLModelDeploymentKey",
datahub/metadata/schemas/MLModelGroupKey.avsc CHANGED
@@ -19,7 +19,8 @@
19
19
  "structuredProperties",
20
20
  "forms",
21
21
  "testResults",
22
- "subTypes"
22
+ "subTypes",
23
+ "container"
23
24
  ]
24
25
  },
25
26
  "name": "MLModelGroupKey",
datahub/metadata/schemas/MLModelKey.avsc CHANGED
@@ -31,7 +31,8 @@
31
31
  "forms",
32
32
  "testResults",
33
33
  "versionProperties",
34
- "subTypes"
34
+ "subTypes",
35
+ "container"
35
36
  ]
36
37
  },
37
38
  "name": "MLModelKey",
datahub/sql_parsing/sql_parsing_common.py CHANGED
@@ -24,12 +24,19 @@ DIALECTS_WITH_CASE_INSENSITIVE_COLS = {
24
24
  # For SQL server, the default collation rules mean that all identifiers (schema, table, column names)
25
25
  # are case preserving but case insensitive.
26
26
  "mssql",
27
+ # Oracle automatically converts unquoted identifiers to uppercase.
28
+ # https://docs.oracle.com/en/database/oracle/oracle-database/19/sqlrf/Database-Object-Names-and-Qualifiers.html#GUID-3C59E44A-5140-4BCA-B9E1-3039C8050C49
29
+ # In our Oracle connector, we then normalize column names to lowercase. This behavior
30
+ # actually comes from the underlying Oracle sqlalchemy dialect.
31
+ # https://github.com/sqlalchemy/sqlalchemy/blob/d9b4d8ff3aae504402d324f3ebf0b8faff78f5dc/lib/sqlalchemy/dialects/oracle/base.py#L2579
32
+ "oracle",
27
33
  }
28
34
  DIALECTS_WITH_DEFAULT_UPPERCASE_COLS = {
29
35
  # In some dialects, column identifiers are effectively case insensitive
30
36
  # because they are automatically converted to uppercase. Most other systems
31
37
  # automatically lowercase unquoted identifiers.
32
38
  "snowflake",
39
+ "oracle",
33
40
  }
34
41
  assert DIALECTS_WITH_DEFAULT_UPPERCASE_COLS.issubset(
35
42
  DIALECTS_WITH_CASE_INSENSITIVE_COLS