acryl-datahub 1.2.0.2rc1__py3-none-any.whl → 1.2.0.2rc2__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.

@@ -1,7 +1,7 @@
1
- acryl_datahub-1.2.0.2rc1.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
1
+ acryl_datahub-1.2.0.2rc2.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
2
2
  datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
3
3
  datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
4
- datahub/_version.py,sha256=1ST8gBZ8wWcQFJrAhpY_re_rMWhON0s6EftssFUvWKw,323
4
+ datahub/_version.py,sha256=s5EXV3hpRB9lksOH0jiXRfUJ3S-nVAJuPv3eQl88tSg,323
5
5
  datahub/entrypoints.py,sha256=9Qf-37rNnTzbGlx8S75OCDazIclFp6zWNcCEL1zCZto,9015
6
6
  datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
7
7
  datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -211,7 +211,7 @@ datahub/ingestion/source/demo_data.py,sha256=PbtCHlZx3wrKlOPPgkWhDQuPm7ZfIx2neXJ
211
211
  datahub/ingestion/source/elastic_search.py,sha256=2dwIcSbYMaq_RoSnxLGz4Q_20oJ8AGgMKunVIBIgYM8,23406
212
212
  datahub/ingestion/source/feast.py,sha256=rAqT7huVgi4c7iRU9qSbohPbNRrxZVw4PIvnfxNsiUk,18798
213
213
  datahub/ingestion/source/file.py,sha256=sHCWbtrQcXMMYPs_LUqofx0mk6IFN0G7Lyk9b0yRZMI,16082
214
- datahub/ingestion/source/ge_data_profiler.py,sha256=TnAupfORYFzcgP7akQEqeuvy1qO0sxMetb0B75f95jM,67980
214
+ datahub/ingestion/source/ge_data_profiler.py,sha256=zPh8u-42KUVzCDGYONn7bGtIHMfa4S4gdg60ZsB3Vlc,68448
215
215
  datahub/ingestion/source/ge_profiling_config.py,sha256=sG_0BwPDRG3I4PnhfWGHf9AbePLDWG0kKcKEtlXHTuk,11544
216
216
  datahub/ingestion/source/glue_profiling_config.py,sha256=vpMJH4Lf_qgR32BZy58suabri1yV5geaAPjzg2eORDc,2559
217
217
  datahub/ingestion/source/ldap.py,sha256=PKoA5pVjuIxFfW1TcbYNIWSm7-C7shK2FDn7Zo5mrVM,18705
@@ -550,7 +550,7 @@ datahub/ingestion/source/unity/config.py,sha256=7QosoBthg9kirHfXev_vhefkobUxYnp1
550
550
  datahub/ingestion/source/unity/connection_test.py,sha256=B143Wb28fS0V4GhygU9hzKqiArWBjsQO54IUCPf23dc,2586
551
551
  datahub/ingestion/source/unity/ge_profiler.py,sha256=NBRHZceq-f95iUn7u0h7cgcd9nAc48Aa-lmp_BqE0As,8409
552
552
  datahub/ingestion/source/unity/hive_metastore_proxy.py,sha256=IAWWJjaW0si_UF52Se2D7wmdYRY_afUG4QlVmQu6xaw,15351
553
- datahub/ingestion/source/unity/proxy.py,sha256=i15xEfjt7sbajbDIA9cbrxKWLByoL2drI8lnvWPceqc,22787
553
+ datahub/ingestion/source/unity/proxy.py,sha256=jfQ1N8Xrp08zeYN2j74YTweusygXtK4Q-5_FBbwCVTE,22803
554
554
  datahub/ingestion/source/unity/proxy_profiling.py,sha256=WLqvYP6MziaisA4LYL4T_GA-kPt6Xdde7bfaYsjYw40,9663
555
555
  datahub/ingestion/source/unity/proxy_types.py,sha256=qrvHiwPzl5cPX-KRvcIGGeJVdr0I8XUQmoAI6ErZ-v8,9371
556
556
  datahub/ingestion/source/unity/report.py,sha256=XFT9oQfvEB4RkTvWGgFOoQuLPUN_AIoPXZ79xeDhGHQ,2831
@@ -1093,8 +1093,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
1093
1093
  datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
1094
1094
  datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
1095
1095
  datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
1096
- acryl_datahub-1.2.0.2rc1.dist-info/METADATA,sha256=dvJ_JwbJKfu4voRemOG8bC2x4cXQUyNPu9cmz68Ehvg,181893
1097
- acryl_datahub-1.2.0.2rc1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
1098
- acryl_datahub-1.2.0.2rc1.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
1099
- acryl_datahub-1.2.0.2rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
1100
- acryl_datahub-1.2.0.2rc1.dist-info/RECORD,,
1096
+ acryl_datahub-1.2.0.2rc2.dist-info/METADATA,sha256=64TPAfHEb-OAhjxYsRmqo60prTnAuSLNP5kvOLk7Z0E,181893
1097
+ acryl_datahub-1.2.0.2rc2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
1098
+ acryl_datahub-1.2.0.2rc2.dist-info/entry_points.txt,sha256=bnGf6eX9UhiW8yVHtt6MJCVcmLErvrVQxTJAayA-PKc,9885
1099
+ acryl_datahub-1.2.0.2rc2.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
1100
+ acryl_datahub-1.2.0.2rc2.dist-info/RECORD,,
datahub/_version.py CHANGED
@@ -1,6 +1,6 @@
1
1
  # Published at https://pypi.org/project/acryl-datahub/.
2
2
  __package_name__ = "acryl-datahub"
3
- __version__ = "1.2.0.2rc1"
3
+ __version__ = "1.2.0.2rc2"
4
4
 
5
5
 
6
6
  def is_dev_mode() -> bool:
@@ -1497,9 +1497,17 @@ class DatahubGEProfiler:
1497
1497
  logger.error(
1498
1498
  f"Unexpected {pretty_name} while profiling. Should have 3 parts but has {len(name_parts)} parts."
1499
1499
  )
1500
+ if platform == DATABRICKS:
1501
+ # TODO: Review logic for BigQuery as well, probably project.dataset.table should be quoted there as well
1502
+ quoted_name = ".".join(
1503
+ batch.engine.dialect.identifier_preparer.quote(part)
1504
+ for part in name_parts
1505
+ )
1506
+ batch._table = sa.text(quoted_name)
1507
+ logger.debug(f"Setting quoted table name to be {batch._table}")
1500
1508
  # If we only have two parts that means the project_id is missing from the table name and we add it
1501
1509
  # Temp tables has 3 parts while normal tables only has 2 parts
1502
- if len(str(batch._table).split(".")) == 2:
1510
+ elif len(str(batch._table).split(".")) == 2:
1503
1511
  batch._table = sa.text(f"{name_parts[0]}.{str(batch._table)}")
1504
1512
  logger.debug(f"Setting table name to be {batch._table}")
1505
1513
 
@@ -521,9 +521,9 @@ class UnityCatalogApiProxy(UnityCatalogProxyProfilingMixin):
521
521
  @cached(cachetools.FIFOCache(maxsize=100))
522
522
  def get_schema_tags(self, catalog: str) -> Dict[str, List[UnityCatalogTag]]:
523
523
  """Optimized version using databricks-sql"""
524
- logger.info(f"Fetching schema tags for catalog: {catalog}")
524
+ logger.info(f"Fetching schema tags for catalog: `{catalog}`")
525
525
 
526
- query = f"SELECT * FROM {catalog}.information_schema.schema_tags"
526
+ query = f"SELECT * FROM `{catalog}`.information_schema.schema_tags"
527
527
  rows = self._execute_sql_query(query)
528
528
 
529
529
  result_dict: Dict[str, List[UnityCatalogTag]] = {}
@@ -544,9 +544,9 @@ class UnityCatalogApiProxy(UnityCatalogProxyProfilingMixin):
544
544
  @cached(cachetools.FIFOCache(maxsize=100))
545
545
  def get_catalog_tags(self, catalog: str) -> Dict[str, List[UnityCatalogTag]]:
546
546
  """Optimized version using databricks-sql"""
547
- logger.info(f"Fetching table tags for catalog: {catalog}")
547
+ logger.info(f"Fetching table tags for catalog: `{catalog}`")
548
548
 
549
- query = f"SELECT * FROM {catalog}.information_schema.catalog_tags"
549
+ query = f"SELECT * FROM `{catalog}`.information_schema.catalog_tags"
550
550
  rows = self._execute_sql_query(query)
551
551
 
552
552
  result_dict: Dict[str, List[UnityCatalogTag]] = {}
@@ -566,9 +566,9 @@ class UnityCatalogApiProxy(UnityCatalogProxyProfilingMixin):
566
566
  @cached(cachetools.FIFOCache(maxsize=100))
567
567
  def get_table_tags(self, catalog: str) -> Dict[str, List[UnityCatalogTag]]:
568
568
  """Optimized version using databricks-sql"""
569
- logger.info(f"Fetching table tags for catalog: {catalog}")
569
+ logger.info(f"Fetching table tags for catalog: `{catalog}`")
570
570
 
571
- query = f"SELECT * FROM {catalog}.information_schema.table_tags"
571
+ query = f"SELECT * FROM `{catalog}`.information_schema.table_tags"
572
572
  rows = self._execute_sql_query(query)
573
573
 
574
574
  result_dict: Dict[str, List[UnityCatalogTag]] = {}
@@ -589,9 +589,9 @@ class UnityCatalogApiProxy(UnityCatalogProxyProfilingMixin):
589
589
  @cached(cachetools.FIFOCache(maxsize=100))
590
590
  def get_column_tags(self, catalog: str) -> Dict[str, List[UnityCatalogTag]]:
591
591
  """Optimized version using databricks-sql"""
592
- logger.info(f"Fetching column tags for catalog: {catalog}")
592
+ logger.info(f"Fetching column tags for catalog: `{catalog}`")
593
593
 
594
- query = f"SELECT * FROM {catalog}.information_schema.column_tags"
594
+ query = f"SELECT * FROM `{catalog}`.information_schema.column_tags"
595
595
  rows = self._execute_sql_query(query)
596
596
 
597
597
  result_dict: Dict[str, List[UnityCatalogTag]] = {}