acryl-datahub 1.1.1rc2__py3-none-any.whl → 1.1.1rc3__py3-none-any.whl

{acryl_datahub-1.1.1rc2.dist-info → acryl_datahub-1.1.1rc3.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.1.1rc2.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.1.1rc3.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
 datahub/__init__.py,sha256=aq_i5lVREmoLfYIqcx_pEQicO855YlhD19tWc1eZZNI,59
 datahub/__main__.py,sha256=pegIvQ9hzK7IhqVeUi1MeADSZ2QlP-D3K0OQdEg55RU,106
-datahub/_version.py,sha256=DKcjhwmDecfgLuBvtigWjIpy1_XPd7kbxrjvQhUCCoE,321
+datahub/_version.py,sha256=YKv9NztkHrTZ4_8dkC02c7V9Al8mWiRqMfERfcuZjRA,321
 datahub/entrypoints.py,sha256=H-YFTvxTJOgpWsFBVlxyb1opjkq-hjTzNmjy5Fq3RHg,8992
 datahub/errors.py,sha256=p5rFAdAGVCk4Lqolol1YvthceadUSwpaCxLXRcyCCFQ,676
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -48,14 +48,14 @@ datahub/api/entities/dataprocess/dataprocess_instance.py,sha256=IhY-rcXs-r8EatwW
 datahub/api/entities/dataproduct/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/api/entities/dataproduct/dataproduct.py,sha256=148TmItxDDyGNzfZdL8aDreSEtyAw79IN8N8oSmNOPE,21461
 datahub/api/entities/dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/api/entities/dataset/dataset.py,sha256=se2tv6jsvS5BmH5b53mKs8lEPF4LNzVRrd9PDovPIQk,49627
+datahub/api/entities/dataset/dataset.py,sha256=Aa89GZA1R3kY6o5YahFC2YF3pq9B0pipWcKThrhY5l4,49481
 datahub/api/entities/forms/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/api/entities/forms/forms.py,sha256=B1KnoMmaXwznWdbjltoLq3sH9qj-BpzyC7z7FcwwOM4,15812
 datahub/api/entities/forms/forms_graphql_constants.py,sha256=DKpnKlMKTjmnyrCTvp63V4LX4THGTAMq3ep8THrSGP4,537
 datahub/api/entities/platformresource/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/api/entities/platformresource/platform_resource.py,sha256=pVAjv6NoH746Mfvdak7ji0eqlEcEeV-Ji7M5gyNXmds,10603
 datahub/api/entities/structuredproperties/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/api/entities/structuredproperties/structuredproperties.py,sha256=FU50bB1bgGDbitdzK9gHxWMj83KUuxK80mhpK1KmGZQ,8535
+datahub/api/entities/structuredproperties/structuredproperties.py,sha256=CUAMxgQXhlTJThkidyfGiMIeVto4aveThaG2DfDIhZI,8547
 datahub/api/graphql/__init__.py,sha256=5yl0dJxO-2d_QuykdJrDIbWq4ja9bo0t2dAEh89JOog,142
 datahub/api/graphql/assertion.py,sha256=o_q6SV7N1rJTVMNKSUBGJnZPk6TcVYoVShgDmPw65dE,2817
 datahub/api/graphql/base.py,sha256=zk724_oYSJ0nK7X7Z80MijnA6ry9JqpxnBsJeYuONKA,1737
@@ -120,7 +120,7 @@ datahub/emitter/composite_emitter.py,sha256=ZU-IdlAXKGPtmyT0JJgYC09vRn-TmeNaA6VP
 datahub/emitter/enum_helpers.py,sha256=QBOEUu_hDCvyL_v4ayNQV8XwJbf5zKyu0Xat0mI1Kgo,376
 datahub/emitter/generic_emitter.py,sha256=i37ZFm9VR_tmiZm9kIypEkQEB_cLKbzj_tJvViN-fm8,828
 datahub/emitter/kafka_emitter.py,sha256=Uix1W1WaXF8VqUTUfzdRZKca2XrR1w50Anx2LVkROlc,5822
-datahub/emitter/mce_builder.py,sha256=i-iLLdnuy7h1JrzwC2sCtQthbso-cNj1uijOQZKHbeA,16717
+datahub/emitter/mce_builder.py,sha256=tAd3_hsGi94RGR0H8gFgAeW8dloKt6TXF45xPh6bu_M,16823
 datahub/emitter/mcp.py,sha256=u6LphyhpbdFqboTAL_9MzXhGjc45o_BePoDFBkEEYWo,10484
 datahub/emitter/mcp_builder.py,sha256=8IwJAlolQkPpMqQJPLtGrsUqAcuFNs98nrI5iYUxgaU,11920
 datahub/emitter/mcp_patch_builder.py,sha256=u7cpW6DkiN7KpLapmMaXgL_FneoN69boxiANbVgMdSI,4564
@@ -290,7 +290,7 @@ datahub/ingestion/source/datahub/report.py,sha256=VHBfCbwFRzdLdB7hQG9ST4EiZxl_vB
 datahub/ingestion/source/datahub/state.py,sha256=PZoT7sSK1wadVf5vN6phrgr7I6LL7ePP-EJjP1OO0bQ,3507
 datahub/ingestion/source/dbt/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/dbt/dbt_cloud.py,sha256=_17ZX6WDzg3lKo0J5XukiaZ8AiJVFsg7y2IcMLMOUAQ,17785
-datahub/ingestion/source/dbt/dbt_common.py,sha256=yk5iF671kFI3BQ9pY2HvMq6mkiEKPT5ARkf13Ydr2TE,81098
+datahub/ingestion/source/dbt/dbt_common.py,sha256=Hgdu6yisAOQ4mn98GjhnhTreUJffskMKD-tvYDMQ0bQ,82045
 datahub/ingestion/source/dbt/dbt_core.py,sha256=qtfNQk28r4_hkf5sIkjfWfrvZbW8Q0NIFPi67NpPeB4,24824
 datahub/ingestion/source/dbt/dbt_tests.py,sha256=pOZJaP4VsbaE5j4qVlE_E3ifno_KQpidfGTvOi5fr6I,9839
 datahub/ingestion/source/delta_lake/__init__.py,sha256=u5oqUeus81ONAtdl6o9Puw33ODSMun-0wLIamrZ4BUM,71
@@ -335,7 +335,7 @@ datahub/ingestion/source/hex/constants.py,sha256=8hUTMWyG5keTNfXoLu_Dh413Hw_mGGJ
 datahub/ingestion/source/hex/hex.py,sha256=hpMCkwH_RWdb0MG1U2-N71wc6vPUVQ3fAkTiudplzrQ,12968
 datahub/ingestion/source/hex/mapper.py,sha256=N3mTlEcrOmhv9ia1dnHGFgFJD2ddyTtU3H5IUbb-UxU,13344
 datahub/ingestion/source/hex/model.py,sha256=S9bUhfFcjzuio2dBS6HzSyRVPiSJvRvMQ0qyVrjV5-E,1766
-datahub/ingestion/source/hex/query_fetcher.py,sha256=m9A9xzxJipGD-nJU_lItyLF7Q5VYOm11wuM3fMyvm4I,12594
+datahub/ingestion/source/hex/query_fetcher.py,sha256=0VqDfviyfR14gUHvIBovCXEqwW4ftFehPSB2VzaYk14,13312
 datahub/ingestion/source/iceberg/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/iceberg/iceberg.py,sha256=-8uaBerljvonaT7Gn9Evokq6-SSDiMRf8kKo7Hg1qY4,35414
 datahub/ingestion/source/iceberg/iceberg_common.py,sha256=CD_yHQ_wEgivyLQUTRO9BZJB29S7j5fUVllki-BPwUU,12292
@@ -489,7 +489,7 @@ datahub/ingestion/source/sql/sql_config.py,sha256=u3nGZYYl1WtaxfNsDU5bglgZ5Jq3Fx
 datahub/ingestion/source/sql/sql_generic.py,sha256=9AERvkK8kdJUeDOzCYJDb93xdv6Z4DGho0NfeHj5Uyg,2740
 datahub/ingestion/source/sql/sql_generic_profiler.py,sha256=8cDmNpT_UXzYmP8-RWoDCnewmVGCj2cYCzH9_gSsF3o,11590
 datahub/ingestion/source/sql/sql_report.py,sha256=gw-OPHSExp_b6DRjvwqE1U6BpkwekxGrsvNMGYSGDio,2671
-datahub/ingestion/source/sql/sql_types.py,sha256=TYz6N2-3j3Rj8gBVZxNuQAGbDBb0hdNfhhIj0q5UIQs,15009
+datahub/ingestion/source/sql/sql_types.py,sha256=TZSuK29Y5TPFIjzEXbwTbbkSQAS6Dnzuq8mCbJa5fK4,15119
 datahub/ingestion/source/sql/sql_utils.py,sha256=q-Bsk6WxlsRtrw9RXBxvqI3zuaMTC_F25T2VrCziR9I,8418
 datahub/ingestion/source/sql/sqlalchemy_data_reader.py,sha256=FvHZ4JEK3aR2DYOBZiT_ZsAy12RjTu4t_KIR_92B11k,2644
 datahub/ingestion/source/sql/sqlalchemy_uri.py,sha256=u0ZvgdJjXZdo_vl7YIQfYuuWbGwpnH6OSozI2e8ZV4I,858
@@ -598,8 +598,8 @@ datahub/lite/lite_registry.py,sha256=bpH0kasP-LtwwUFNA2QsOIehfekAYfJtN-AkQLmSWnw
 datahub/lite/lite_server.py,sha256=p9Oa2nNs65mqcssSIVOr7VOzWqfVstz6ZQEdT4f82S0,1949
 datahub/lite/lite_util.py,sha256=G0LQHKkyEb1pc_q183g6hflShclGx7kikgMaOxtVVcs,4545
 datahub/metadata/__init__.py,sha256=AjhXPjI6cnpdcrBRrE5gOWo15vv2TTl2ctU4UAnUN7A,238
-datahub/metadata/_internal_schema_classes.py,sha256=tl0FUKLebvTk766QFVUerWKFf0OpaSSY0o-w-vqPNsA,1013133
-datahub/metadata/schema.avsc,sha256=F4cl2V81M75_GVEu-zHL8a8KoM_dI62irB-1lAI147w,701582
+datahub/metadata/_internal_schema_classes.py,sha256=zFi0q-OOxdhPXr6ril8nEZhgChzXY_a3BkVwH3h_8bo,1013146
+datahub/metadata/schema.avsc,sha256=dnBmtikhHW7neORZOUoiH21MZXoXRaw5E1gwwfyCnqs,701603
 datahub/metadata/schema_classes.py,sha256=tPT8iHCak4IsZi_oL0nirbPpI8ETTPTZzapqLRpeKU4,1326
 datahub/metadata/urns.py,sha256=nfrCTExR-k2P9w272WVtWSN3xW1VUJngPwP3xnvULjU,1217
 datahub/metadata/_urns/__init__.py,sha256=cOF3GHMDgPhmbLKbN02NPpuLGHSu0qNgQyBRv08eqF0,243
@@ -722,7 +722,7 @@ datahub/metadata/schemas/DataHubActionKey.avsc,sha256=bjiKcoyvUPQKaGUi2ICBMJ_ukw
 datahub/metadata/schemas/DataHubConnectionDetails.avsc,sha256=IvZj6OA7HRvy-ZIIn0UbXdJNnyt_oTn16XIe5ZlcqGk,1661
 datahub/metadata/schemas/DataHubConnectionKey.avsc,sha256=VwbamVFoEdp6epz1lJm_UShBl6ksBxoA7jAYuPI5u3M,522
 datahub/metadata/schemas/DataHubIngestionSourceInfo.avsc,sha256=4wac7sluRIq-0ZjODE5SmuVKuQeW8ajLJNRpqEBRyio,4601
-datahub/metadata/schemas/DataHubIngestionSourceKey.avsc,sha256=CSmoOx_Eqa1-he5dRaVOUQWIv1l2e2lraEPIixKK-lo,526
+datahub/metadata/schemas/DataHubIngestionSourceKey.avsc,sha256=TGmm9WEGTaABs7kt5Uc-N-kbc5Sd-2sQwx-JpfAptvw,545
 datahub/metadata/schemas/DataHubOpenAPISchemaKey.avsc,sha256=q6ZyMoxInwmrkrXkUgMe-i-WZzAxbjcvJ-EI99SnEp8,599
 datahub/metadata/schemas/DataHubPersonaInfo.avsc,sha256=OUvbTgPQsBtzkDDb9pxHXpQ6A7dkL77ZnCXZ-MLEG14,227
 datahub/metadata/schemas/DataHubPersonaKey.avsc,sha256=ddj-DhXa0_YMdLaGkKLLSklfIeDRvSwPXu8o__YEXUE,448
@@ -1057,8 +1057,8 @@ datahub_provider/operators/datahub_assertion_operator.py,sha256=uvTQ-jk2F0sbqqxp
 datahub_provider/operators/datahub_assertion_sensor.py,sha256=lCBj_3x1cf5GMNpHdfkpHuyHfVxsm6ff5x2Z5iizcAo,140
 datahub_provider/operators/datahub_operation_operator.py,sha256=aevDp2FzX7FxGlXrR0khoHNbxbhKR2qPEX5e8O2Jyzw,174
 datahub_provider/operators/datahub_operation_sensor.py,sha256=8fcdVBCEPgqy1etTXgLoiHoJrRt_nzFZQMdSzHqSG7M,168
-acryl_datahub-1.1.1rc2.dist-info/METADATA,sha256=6YaQUpDtFdwJ2Ih1wopQxjfHZ-h7lTjJNNixDR2kp3o,180529
-acryl_datahub-1.1.1rc2.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
-acryl_datahub-1.1.1rc2.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
-acryl_datahub-1.1.1rc2.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.1.1rc2.dist-info/RECORD,,
+acryl_datahub-1.1.1rc3.dist-info/METADATA,sha256=EU7551u1heqvgQuRO_U-7JIPE1hnZzewnH-c3EaWkyY,180694
+acryl_datahub-1.1.1rc3.dist-info/WHEEL,sha256=zaaOINJESkSfm_4HQVc5ssNzHCPXhJm0kEUakpsEHaU,91
+acryl_datahub-1.1.1rc3.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
+acryl_datahub-1.1.1rc3.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.1.1rc3.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.1.1rc2"
+__version__ = "1.1.1rc3"
 
 
 def is_dev_mode() -> bool:

datahub/api/entities/dataset/dataset.py

@@ -15,7 +15,13 @@ from typing import (
 
 import avro
 import yaml
-from pydantic import BaseModel, Field, root_validator, validator
+from pydantic import (
+    BaseModel,
+    Field,
+    StrictStr,
+    root_validator,
+    validator,
+)
 from ruamel.yaml import YAML
 from typing_extensions import TypeAlias
 
@@ -90,7 +96,7 @@ class StrictModel(BaseModel):
 
 
 # Define type aliases for the complex types
-PropertyValue: TypeAlias = Union[float, str]
+PropertyValue: TypeAlias = Union[StrictStr, float]
 PropertyValueList: TypeAlias = List[PropertyValue]
 StructuredProperties: TypeAlias = Dict[str, Union[PropertyValue, PropertyValueList]]
 
@@ -366,12 +372,6 @@ class Ownership(ConfigModel):
         return v
 
 
-class StructuredPropertyValue(ConfigModel):
-    value: Union[str, int, float, List[str], List[int], List[float]]
-    created: Optional[str] = None
-    lastModified: Optional[str] = None
-
-
 class DatasetRetrievalConfig(BaseModel):
     include_downstreams: Optional[bool] = False
 

datahub/api/entities/structuredproperties/structuredproperties.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from typing import Iterable, List, Optional, Union
 
 import yaml
-from pydantic import validator
+from pydantic import StrictStr, validator
 from ruamel.yaml import YAML
 
 from datahub.configuration.common import ConfigModel
@@ -38,7 +38,7 @@ class AllowedTypes(Enum):
 
 
 class AllowedValue(ConfigModel):
-    value: Union[int, float, str]
+    value: Union[StrictStr, float]
     description: Optional[str] = None
 
 

datahub/emitter/mce_builder.py

@@ -59,6 +59,7 @@ from datahub.metadata.urns import (
     DataJobUrn,
     DataPlatformUrn,
     DatasetUrn,
+    OwnershipTypeUrn,
     TagUrn,
 )
 from datahub.utilities.urn_encoder import UrnEncoder
@@ -406,7 +407,8 @@ def make_ml_model_group_urn(platform: str, group_name: str, env: str) -> str:
 
 def validate_ownership_type(ownership_type: str) -> Tuple[str, Optional[str]]:
     if ownership_type.startswith("urn:li:"):
-        return OwnershipTypeClass.CUSTOM, ownership_type
+        ownership_type_urn = OwnershipTypeUrn.from_string(ownership_type)
+        return OwnershipTypeClass.CUSTOM, ownership_type_urn.urn()
     ownership_type = ownership_type.upper()
     if ownership_type in get_enum_options(OwnershipTypeClass):
         return ownership_type, None

datahub/ingestion/source/dbt/dbt_common.py

@@ -132,6 +132,12 @@ class DBTSourceReport(StaleEntityRemovalSourceReport):
     sql_parser_column_errors: int = 0
     sql_parser_successes: int = 0
 
+    # Details on where column info comes from.
+    nodes_with_catalog_columns: int = 0
+    nodes_with_inferred_columns: int = 0
+    nodes_with_graph_columns: int = 0
+    nodes_with_no_columns: int = 0
+
     sql_parser_parse_failures_list: LossyList[str] = field(default_factory=LossyList)
     sql_parser_detach_ctes_failures_list: LossyList[str] = field(
         default_factory=LossyList
@@ -619,14 +625,8 @@ class DBTNode:
     def exists_in_target_platform(self):
         return not (self.is_ephemeral_model() or self.node_type == "test")
 
-    def columns_setdefault(self, schema_fields: List[SchemaField]) -> None:
-        """
-        Update the column list if they are not already set.
-        """
-
-        if self.columns:
-            # If we already have columns, don't overwrite them.
-            return
+    def set_columns(self, schema_fields: List[SchemaField]) -> None:
+        """Update the column list."""
 
         self.columns = [
             DBTColumn(
@@ -1248,9 +1248,28 @@ class DBTSourceBase(StatefulIngestionSourceBase):
                     target_node_urn, self._to_schema_info(inferred_schema_fields)
                 )
 
-            # Save the inferred schema fields into the dbt node.
-            if inferred_schema_fields:
-                node.columns_setdefault(inferred_schema_fields)
+            # When updating the node's columns, our order of preference is:
+            # 1. Schema from the dbt catalog
+            # 2. Inferred schema
+            # 3. Schema fetched from the graph
+            if node.columns:
+                self.report.nodes_with_catalog_columns += 1
+                pass  # we already have columns from the dbt catalog
+            elif inferred_schema_fields:
+                logger.debug(
+                    f"Using {len(inferred_schema_fields)} inferred columns for {node.dbt_name}"
+                )
+                self.report.nodes_with_inferred_columns += 1
+                node.set_columns(inferred_schema_fields)
+            elif schema_fields:
+                logger.debug(
+                    f"Using {len(schema_fields)} graph columns for {node.dbt_name}"
+                )
+                self.report.nodes_with_graph_columns += 1
+                node.set_columns(schema_fields)
+            else:
+                logger.debug(f"No columns found for {node.dbt_name}")
+                self.report.nodes_with_no_columns += 1
 
     def _parse_cll(
         self,

datahub/ingestion/source/hex/query_fetcher.py

@@ -18,8 +18,12 @@ from datahub.utilities.time import datetime_to_ts_millis
 logger = logging.getLogger(__name__)
 
 # Pattern to extract both project_id and workspace_name from Hex metadata in SQL comments
-# Only match metadata with "context": "SCHEDULED_RUN" to filter out non-scheduled runs
-HEX_METADATA_PATTERN = r'-- Hex query metadata: \{.*?"context": "SCHEDULED_RUN".*?"project_id": "([^"]+)".*?"project_url": "https?://[^/]+/([^/]+)/hex/.*?\}'
+# Context values:
+# - SCHEDULED_RUN: The query was executed during a scheduled run of a published Hex app.
+# - LOGIC_VIEW: The query was executed from the Hex project's notebook view. This happens when a user is actively editing a Hex notebook: When they first open and run it or when they rerun without cached results.
+# - APP_VIEW: The query was executed during a published app session. This happens when a user opens up a published app or reruns the app without cached results.
+# Only match metadata with "context": "SCHEDULED_RUN|APP_VIEW" to filter out those from notebook, which may bring more noise from development than value
+HEX_METADATA_PATTERN = r'-- Hex query metadata: \{.*?"context": "(?:SCHEDULED_RUN|APP_VIEW)".*?"project_id": "([^"]+)".*?"project_url": "https?://[^/]+/([^/]+)/hex/.*?\}'
 
 
 @dataclass
@@ -197,13 +201,15 @@ class HexQueryFetcher:
         Example:
         -- Hex query metadata: {"categories": ["Scratchpad"], "cell_type": "SQL", "connection": "Long Tail Companions", "context": "SCHEDULED_RUN", "project_id": "d73da67d-c87b-4dd8-9e7f-b79cb7f822cf", "project_url": "https://app.hex.tech/acryl-partnership/hex/d73da67d-c87b-4dd8-9e7f-b79cb7f822cf/draft/logic?selectedCellId=67c38da0-e631-4005-9750-5bdae2a2ef3f"}
 
-        # TODO: Consider supporting multiline metadata format in the future:
+        TODO: Consider supporting multiline metadata format in the future:
         # -- Hex query metadata: {
         # --   "categories": ["Scratchpad"],
         # --   "project_id": "d73da67d-c87b-4dd8-9e7f-b79cb7f822cf",
         # --   ...
         # -- }
 
+        TODO: Extract based on pattern matching is strict on the order of the keys in the metadata. Consider using a more flexible approach like JSON parsing.
+
         Returns:
             A tuple of (project_id, workspace_name) if both are successfully extracted
             None if extraction fails for any reason

datahub/ingestion/source/sql/sql_types.py

@@ -284,6 +284,8 @@ SNOWFLAKE_TYPES_MAP: Dict[str, Any] = {
     "INTEGER": NumberType,
     "BIGINT": NumberType,
     "SMALLINT": NumberType,
+    "TINYINT": NumberType,
+    "BYTEINT": NumberType,
     "FLOAT": NumberType,
     "FLOAT4": NumberType,
     "FLOAT8": NumberType,
@@ -291,6 +293,7 @@ SNOWFLAKE_TYPES_MAP: Dict[str, Any] = {
     "DOUBLE PRECISION": NumberType,
     "REAL": NumberType,
     "VARCHAR": StringType,
+    "CHARACTER VARYING": StringType,
     "CHAR": StringType,
     "CHARACTER": StringType,
     "STRING": StringType,
@@ -313,8 +316,8 @@ SNOWFLAKE_TYPES_MAP: Dict[str, Any] = {
 
 
 def resolve_snowflake_modified_type(type_string: str) -> Any:
-    # Match types with precision and scale, e.g., 'DECIMAL(38,0)'
-    match = re.match(r"([a-zA-Z_]+)\(\d+,\s\d+\)", type_string)
+    # Match types with precision and scale, e.g., 'DECIMAL(38,0)' or TIME(3)
+    match = re.match(r"([a-z A-Z_]+)\(\d+(,(\s+)?\d+)?\)", type_string)
     if match:
         modified_type_base = match.group(1)  # Extract the base type
         return SNOWFLAKE_TYPES_MAP.get(modified_type_base)

datahub/metadata/_internal_schema_classes.py

@@ -15431,7 +15431,7 @@ class DataHubIngestionSourceKeyClass(_Aspect):
 
 
     ASPECT_NAME = 'dataHubIngestionSourceKey'
-    ASPECT_INFO = {'keyForEntity': 'dataHubIngestionSource', 'entityCategory': 'internal', 'entityAspects': ['dataHubIngestionSourceInfo']}
+    ASPECT_INFO = {'keyForEntity': 'dataHubIngestionSource', 'entityCategory': 'internal', 'entityAspects': ['dataHubIngestionSourceInfo', 'ownership']}
     RECORD_SCHEMA = get_schema_type("com.linkedin.pegasus2avro.metadata.key.DataHubIngestionSourceKey")
 
     def __init__(self,

datahub/metadata/schema.avsc

@@ -3768,7 +3768,8 @@
       "keyForEntity": "dataHubIngestionSource",
       "entityCategory": "internal",
       "entityAspects": [
-        "dataHubIngestionSourceInfo"
+        "dataHubIngestionSourceInfo",
+        "ownership"
       ]
     },
     "name": "DataHubIngestionSourceKey",

datahub/metadata/schemas/DataHubIngestionSourceKey.avsc

@@ -5,7 +5,8 @@
     "keyForEntity": "dataHubIngestionSource",
     "entityCategory": "internal",
     "entityAspects": [
-      "dataHubIngestionSourceInfo"
+      "dataHubIngestionSourceInfo",
+      "ownership"
     ]
   },
   "name": "DataHubIngestionSourceKey",