acryl-datahub 1.0.0.3rc1__py3-none-any.whl → 1.0.0.3rc2__py3-none-any.whl

{acryl_datahub-1.0.0.3rc1.dist-info → acryl_datahub-1.0.0.3rc2.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.0.0.3rc1.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.0.0.3rc2.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=R-5q2sde87sdyofKBpzMGjN_yrh8SbPAoOTVYlH3CuU,323
+datahub/_version.py,sha256=wKoNLhdfRXZqqQqju-C7yvPFz3YKQceonahT8wrZq6Y,323
 datahub/entrypoints.py,sha256=2TYgHhs3sCxJlojIHjqfxzt3_ImPwPzq4vBtsUuMqu4,8885
 datahub/errors.py,sha256=BzKdcmYseHOt36zfjJXc17WNutFhp9Y23cU_L6cIkxc,612
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -121,7 +121,7 @@ datahub/emitter/enum_helpers.py,sha256=QBOEUu_hDCvyL_v4ayNQV8XwJbf5zKyu0Xat0mI1K
 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/mcp.py,sha256=hAAYziDdkwjazQU0DtWMbQWY8wS09ACrKJbqxoWXdgc,9637
+datahub/emitter/mcp.py,sha256=v7tKlIFX4s7f77KQYeFww8QbOQu6-qU609VeQiUkcsY,9796
 datahub/emitter/mcp_builder.py,sha256=8IwJAlolQkPpMqQJPLtGrsUqAcuFNs98nrI5iYUxgaU,11920
 datahub/emitter/mcp_patch_builder.py,sha256=u7cpW6DkiN7KpLapmMaXgL_FneoN69boxiANbVgMdSI,4564
 datahub/emitter/request_helper.py,sha256=HpI9a9W0TzoVbrs584rF8P8w-IT_iKLmvYmO_6IHhXs,1008
@@ -205,7 +205,7 @@ datahub/ingestion/source/ge_profiling_config.py,sha256=FlWfXoVoayabVXNMB9qETEU0G
 datahub/ingestion/source/glue_profiling_config.py,sha256=vpMJH4Lf_qgR32BZy58suabri1yV5geaAPjzg2eORDc,2559
 datahub/ingestion/source/ldap.py,sha256=CNr3foofIpoCXu_GGqfcajlQE2qkHr5isYwVcDutdkk,18695
 datahub/ingestion/source/metabase.py,sha256=j8DRV2GvisezidL1JZ5HJLF_hdFdtvaoyDoEdEyh0Ks,32603
-datahub/ingestion/source/mlflow.py,sha256=2K5D95HLUhnx8jP54hK8aKNB0nPaCgXaUgO2PdL6Gto,32539
+datahub/ingestion/source/mlflow.py,sha256=fh7izN9jlSwbpGIrEyJktlmwFZR5vNG9z9L5VQ31k_4,33141
 datahub/ingestion/source/mode.py,sha256=_FKZutF-59w0pYhko6HSVL3yjjYNd329-2DJmyfDqF8,64492
 datahub/ingestion/source/mongodb.py,sha256=2C2Cxn8DXL53IbNiywIuKt8UT_EMcPg9f8su-OPSNGU,21237
 datahub/ingestion/source/nifi.py,sha256=D1gBXxdpLuUQ0eurwofIR_SGg1rHGhwk3qxsWI1PT9c,56882
@@ -376,15 +376,16 @@ datahub/ingestion/source/metadata/lineage.py,sha256=2iK-hsORWm7NSvMZcG4D5hb8_PH5
 datahub/ingestion/source/neo4j/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/ingestion/source/neo4j/neo4j_source.py,sha256=O3jjdnsx7IyYPBLbxowL85Qo4zs4H-maMOH4-6ZNCk4,13063
 datahub/ingestion/source/powerbi/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/powerbi/config.py,sha256=bflLIq6rpZeJ7ULvN2gaAVcSHO5jTJ6vdNPvwo1LH7M,24212
+datahub/ingestion/source/powerbi/config.py,sha256=-gof-85gqS_cft2blp5Uw5TVypii4T_bl8XhTZUVlgc,24707
 datahub/ingestion/source/powerbi/dataplatform_instance_resolver.py,sha256=-njW1kJOy-LY5JFwJLhVQ0bMBj9NQz5TZhQqsSi_KsM,2285
 datahub/ingestion/source/powerbi/powerbi-lexical-grammar.rule,sha256=5df3qvalCS9hZ46DPXs6XDcw9-IofGf8Eol_rUC7LHI,20329
 datahub/ingestion/source/powerbi/powerbi.py,sha256=b9zNeT9aS7v2GWUL1SROnIMwQwAFX0YTO2UNQMLWItc,56450
 datahub/ingestion/source/powerbi/m_query/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/powerbi/m_query/data_classes.py,sha256=yDi0C13ko2dVxdLJBYvUuGbT4Q2hxQRse3sL7Ul1ZU0,2050
+datahub/ingestion/source/powerbi/m_query/data_classes.py,sha256=l_L6DzOWMShOWGtVclcf4JtNWzSINuwJka59LjwRLCk,2091
 datahub/ingestion/source/powerbi/m_query/native_sql_parser.py,sha256=zzKVDGeUM3Yv3-zNah4D6mSnr6jXsstNuLmzczcPQEE,3683
+datahub/ingestion/source/powerbi/m_query/odbc.py,sha256=fZgl8-M5s3Y-3U9OVQs7ttc8FTDbzodIM2HJtFmPNI8,5405
 datahub/ingestion/source/powerbi/m_query/parser.py,sha256=5KqhUwj9H9yL9ZMPP9oSeVGiZjvXjw6Iu_HrGr95E5M,5876
-datahub/ingestion/source/powerbi/m_query/pattern_handler.py,sha256=aOhAb8U4OEZnO4ufnb-Cm3KMpdy-JF6r9YMK3RNZs5A,35906
+datahub/ingestion/source/powerbi/m_query/pattern_handler.py,sha256=MqZj7VBf9ppKYrA-dRaOVGFpotLFqZditwOD-6ynkFg,41635
 datahub/ingestion/source/powerbi/m_query/resolver.py,sha256=ISH8Xjx51q2S81fn2v5RhCCU-kRAW3juxM0rMFs4TDo,17413
 datahub/ingestion/source/powerbi/m_query/tree_function.py,sha256=NIKNNHAE4kTJefTM1WR-StJi9NuingaRYn_mS_kV6A8,6180
 datahub/ingestion/source/powerbi/m_query/validator.py,sha256=crG-VZy2XPieiDliP9yVMgiFcc8b2xbZyDFEATXqEAQ,1155
@@ -450,7 +451,7 @@ datahub/ingestion/source/snowflake/constants.py,sha256=XCW3vw4JfLn_s8-oXBX6WFNMP
 datahub/ingestion/source/snowflake/oauth_config.py,sha256=ol9D3RmruGStJAeL8PYSQguSqcD2HfkjPkMF2AB_eZs,1277
 datahub/ingestion/source/snowflake/oauth_generator.py,sha256=fu2VnREGuJXeTqIV2jx4TwieVnznf83HQkrE0h2DGGM,3423
 datahub/ingestion/source/snowflake/snowflake_assertion.py,sha256=_l3k4aI9wvioE81xxdeizJn9nJCZ_nMIXgk9N6pEk5o,4803
-datahub/ingestion/source/snowflake/snowflake_config.py,sha256=Jm3TW7ed9LYNOZ9egUwkHs2bQv_WlCD6D2QoVxIzxsI,20729
+datahub/ingestion/source/snowflake/snowflake_config.py,sha256=SD2agFE64WgEDbQHPXQjAIP4gsHT1G9H8X_r-RvKGas,20804
 datahub/ingestion/source/snowflake/snowflake_connection.py,sha256=pEw2O9xoTSIWDiROlkF8k4oj5zBjkqTnynLvut08yhc,17796
 datahub/ingestion/source/snowflake/snowflake_data_reader.py,sha256=ffR5E2uhD71FUMXd3XOg2rHwrp1rbbGEFTAbqKcmI2s,2195
 datahub/ingestion/source/snowflake/snowflake_lineage_v2.py,sha256=FBmiONx4EGHWV8RNJT6zHZyntKinPFFyd2oKbTUIbhE,21319
@@ -462,7 +463,7 @@ datahub/ingestion/source/snowflake/snowflake_schema.py,sha256=1yGBbs2aWIdHnrwgeT
 datahub/ingestion/source/snowflake/snowflake_schema_gen.py,sha256=_37-AQyI4uGt4fu-d3v2eAWzQ3uG835ZQxMjFwGYCng,57193
 datahub/ingestion/source/snowflake/snowflake_shares.py,sha256=maZyFkfrbVogEFM0tTKRiNp9c_1muv6YfleSd3q0umI,6341
 datahub/ingestion/source/snowflake/snowflake_summary.py,sha256=kTmuCtRnvHqM8WBYhWeK4XafJq3ssFL9kcS03jEeWT4,5506
-datahub/ingestion/source/snowflake/snowflake_tag.py,sha256=1eLYTcgmfzDs9xktMTTE74L5SeNP48Qg3uLr9y-Ez3Y,8733
+datahub/ingestion/source/snowflake/snowflake_tag.py,sha256=eA9xh-G1Ydr1OwUUtrbXUWp26hE1jF0zvyKNky_i_nQ,8887
 datahub/ingestion/source/snowflake/snowflake_usage_v2.py,sha256=ySFm7WDk8FW9KjCnX4HQfTqObIrlUS-V8WIHl3j0CTI,24848
 datahub/ingestion/source/snowflake/snowflake_utils.py,sha256=2lmvAeZELTjAzg4Y5E0oY41r1IzVEvg6OHAvVJftSFk,14081
 datahub/ingestion/source/snowflake/snowflake_v2.py,sha256=nAbudDVh9A0kqao3jnIdgBlFNhNk1WIxoU1cofeXkFQ,33905
@@ -952,7 +953,7 @@ datahub/testing/check_str_enum.py,sha256=yqk0XXHOGteN-IGqCp5JHy0Kca13BnI09ZqKc4N
 datahub/testing/compare_metadata_json.py,sha256=mTU5evu7KLS3cx8OLOC1fFxj0eY1J1CGV2PEQZmapos,5361
 datahub/testing/docker_utils.py,sha256=g169iy_jNR_mg0p8X31cChZqjOryutAIHUYLq3xqueY,2415
 datahub/testing/doctest.py,sha256=1_8WEhHZ2eRQtw8vsXKzr9L5zzvs0Tcr6q4mnkyyvtw,295
-datahub/testing/mcp_diff.py,sha256=Jk1NluXkKWEMLOE11mHE98lfYE_Gn2GeFuu5TNB3YSs,10198
+datahub/testing/mcp_diff.py,sha256=1BpQ3hST46cOQi1SmKdsto3j6x6Sk6yHm0vG1w9IDL0,10749
 datahub/testing/pytest_hooks.py,sha256=eifmj0M68AIfjTn_-0vtaBkKl75vNKMjsbYX-pJqmGY,1417
 datahub/upgrade/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/upgrade/upgrade.py,sha256=lf60_dCu51twObAL5E8NqdrW3_2lsnUJUaB9MSEVXwI,16638
@@ -1045,8 +1046,8 @@ 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-1.0.0.3rc1.dist-info/METADATA,sha256=43mPIcmD4ByKfyR6rn8PPgaKNUBSmDmVJnGm1KhBZuo,176855
-acryl_datahub-1.0.0.3rc1.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-acryl_datahub-1.0.0.3rc1.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
-acryl_datahub-1.0.0.3rc1.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.0.0.3rc1.dist-info/RECORD,,
+acryl_datahub-1.0.0.3rc2.dist-info/METADATA,sha256=Iez_7GLl0EEt7MEDlMXlVb-A_-YB-RO4IZJRWSwuLjI,176855
+acryl_datahub-1.0.0.3rc2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+acryl_datahub-1.0.0.3rc2.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
+acryl_datahub-1.0.0.3rc2.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.0.0.3rc2.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.0.0.3rc1"
+__version__ = "1.0.0.3rc2"
 
 
 def is_dev_mode() -> bool:

datahub/emitter/mcp.py

@@ -1,6 +1,6 @@
 import dataclasses
 import json
-from typing import TYPE_CHECKING, List, Optional, Sequence, Tuple, Union
+from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple, Union
 
 from datahub.emitter.aspect import ASPECT_MAP, JSON_CONTENT_TYPE
 from datahub.emitter.serialization_helper import post_json_transform, pre_json_transform
@@ -69,6 +69,7 @@ class MetadataChangeProposalWrapper:
     aspectName: Union[None, str] = None
     aspect: Union[None, _Aspect] = None
     systemMetadata: Union[None, SystemMetadataClass] = None
+    headers: Union[None, Dict[str, str]] = None
 
     def __post_init__(self) -> None:
         if self.entityUrn and self.entityType == _ENTITY_TYPE_UNSET:
@@ -112,6 +113,7 @@ class MetadataChangeProposalWrapper:
             auditHeader=self.auditHeader,
             aspectName=self.aspectName,
             systemMetadata=self.systemMetadata,
+            headers=self.headers,
         )
 
     def make_mcp(self) -> MetadataChangeProposalClass:
@@ -211,6 +213,7 @@ class MetadataChangeProposalWrapper:
                 aspectName=mcpc.aspectName,
                 aspect=aspect,
                 systemMetadata=mcpc.systemMetadata,
+                headers=mcpc.headers,
             )
         else:
             return None
@@ -228,6 +231,7 @@ class MetadataChangeProposalWrapper:
             changeType=mcl.changeType,
             auditHeader=mcl.auditHeader,
             systemMetadata=mcl.systemMetadata,
+            headers=mcl.headers,
         )
         return cls.try_from_mcpc(mcpc) or mcpc
 

datahub/ingestion/source/mlflow.py

@@ -7,6 +7,7 @@ from typing import Any, Callable, Iterable, List, Optional, Tuple, TypeVar, Unio
 from mlflow import MlflowClient
 from mlflow.entities import Dataset as MlflowDataset, Experiment, Run
 from mlflow.entities.model_registry import ModelVersion, RegisteredModel
+from mlflow.exceptions import MlflowException
 from mlflow.store.entities import PagedList
 from pydantic.fields import Field
 
@@ -589,8 +590,8 @@ class MLflowSource(StatefulIngestionSourceBase):
         )
         return runs
 
-    @staticmethod
     def _traverse_mlflow_search_func(
+        self,
         search_func: Callable[..., PagedList[T]],
         **kwargs: Any,
     ) -> Iterable[T]:
@@ -598,12 +599,24 @@ class MLflowSource(StatefulIngestionSourceBase):
         Utility to traverse an MLflow search_* functions which return PagedList.
         """
         next_page_token = None
-        while True:
-            paged_list = search_func(page_token=next_page_token, **kwargs)
-            yield from paged_list.to_list()
-            next_page_token = paged_list.token
-            if not next_page_token:
+        try:
+            while True:
+                paged_list = search_func(page_token=next_page_token, **kwargs)
+                yield from paged_list.to_list()
+                next_page_token = paged_list.token
+                if not next_page_token:
+                    return
+        except MlflowException as e:
+            if e.error_code == "ENDPOINT_NOT_FOUND":
+                self.report.warning(
+                    title="MLflow API Endpoint Not Found for Experiments.",
+                    message="Please upgrade to version 1.28.0 or higher to ensure compatibility. Skipping ingestion for experiments and runs.",
+                    context=None,
+                    exc=e,
+                )
                 return
+            else:
+                raise  # Only re-raise other exceptions
 
     def _get_latest_version(self, registered_model: RegisteredModel) -> Optional[str]:
         return (

datahub/ingestion/source/powerbi/config.py

@@ -192,6 +192,11 @@ class SupportedDataPlatform(Enum):
         datahub_data_platform_name="mysql",
     )
 
+    ODBC = DataPlatformPair(
+        powerbi_data_platform_name="Odbc",
+        datahub_data_platform_name="odbc",
+    )
+
 
 @dataclass
 class PowerBiDashboardSourceReport(StaleEntityRemovalSourceReport):
@@ -341,6 +346,13 @@ class PowerBiDashboardSourceConfig(
         "For Google BigQuery the datasource's server is google bigquery project name. "
         "For Databricks Unity Catalog the datasource's server is workspace FQDN.",
     )
+    # ODBC DSN to platform mapping
+    dsn_to_platform_name: Dict[str, str] = pydantic.Field(
+        default={},
+        description="A mapping of ODBC DSN to DataHub data platform name. "
+        "For example with an ODBC connection string 'DSN=database' where the database type "
+        "is 'PostgreSQL' you would configure the mapping as 'database: postgres'.",
+    )
     # deprecated warning
     _dataset_type_mapping = pydantic_field_deprecated(
         "dataset_type_mapping",

datahub/ingestion/source/powerbi/m_query/data_classes.py

@@ -75,3 +75,4 @@ class FunctionName(Enum):
     AMAZON_REDSHIFT_DATA_ACCESS = "AmazonRedshift.Database"
     DATABRICK_MULTI_CLOUD_DATA_ACCESS = "DatabricksMultiCloud.Catalogs"
     MYSQL_DATA_ACCESS = "MySQL.Database"
+    ODBC_DATA_ACCESS = "Odbc.DataSource"

datahub/ingestion/source/powerbi/m_query/odbc.py

@@ -0,0 +1,185 @@
+import re
+from typing import Optional, Tuple, Union
+
+server_patterns = [
+    r"Server=([^:]+)[:][0-9]+/.*",
+    r"SERVER=\{([^}]*)\}",
+    r"SERVER=([^;]*)",
+    r"HOST=\{([^}]*)\}",
+    r"HOST=([^;]*)",
+    r"DATA SOURCE=\{([^}]*)\}",
+    r"DATA SOURCE=([^;]*)",
+    r"DSN=\{([^}]*)\}",
+    r"DSN=([^;]*)",
+    r"Server=([^;]*)",
+    r"S3OutputLocation=([^;]*)",
+    r"HTTPPath=([^;]*)",
+    r"Host=([^;]*)",
+]
+
+dsn_patterns = [
+    r"DSN\s*=\s*\"([^\"]+)\"",
+    r"DSN\s*=\s*\'([^\']+)\'",
+    r"DSN\s*=\s*([^;]+)",
+]
+
+platform_patterns = {
+    "mysql": r"mysql",
+    "postgres": r"post(gre(s|sql)?|gres)",
+    "mssql": r"(sql\s*server|mssql|sqlncli)",
+    "oracle": r"oracle",
+    "db2": r"db2",
+    "sqlite": r"sqlite",
+    "access": r"(access|\.mdb|\.accdb)",
+    "excel": r"(excel|\.xls)",
+    "firebird": r"firebird",
+    "informix": r"informix",
+    "sybase": r"sybase",
+    "teradata": r"teradata",
+    "hadoop": r"(hadoop|hive)",
+    "snowflake": r"snowflake",
+    "redshift": r"redshift",
+    "bigquery": r"bigquery",
+    "athena": r"(athena|aws\s*athena)",
+    "databricks": r"(databricks|spark)",
+}
+
+powerbi_platform_names = {
+    "mysql": "MySQL",
+    "postgres": "PostgreSQL",
+    "mssql": "SQL Server",
+    "oracle": "Oracle",
+    "db2": "IBM DB2",
+    "sqlite": "SQLite",
+    "access": "Microsoft Access",
+    "excel": "Microsoft Excel",
+    "firebird": "Firebird",
+    "informix": "IBM Informix",
+    "sybase": "SAP Sybase",
+    "teradata": "Teradata",
+    "hadoop": "Hadoop",
+    "snowflake": "Snowflake",
+    "redshift": "Amazon Redshift",
+    "bigquery": "Google BigQuery",
+    "athena": "Amazon Athena",
+    "databricks": "Databricks",
+}
+
+
+def extract_driver(connection_string: str) -> Union[str, None]:
+    """
+    Parse an ODBC connection string and extract the driver name.
+    Handles whitespace in driver names and various connection string formats.
+
+    Args:
+        connection_string (str): The ODBC connection string
+
+    Returns:
+        str: The extracted driver name, or None if not found
+    """
+    # Match DRIVER={driver name} pattern
+    driver_match = re.search(r"DRIVER=\{([^}]*)}", connection_string, re.IGNORECASE)
+
+    if driver_match:
+        return driver_match.group(1).strip()
+
+    # Alternative pattern for DRIVER=driver
+    driver_match = re.search(r"DRIVER=([^;]*)", connection_string, re.IGNORECASE)
+
+    if driver_match:
+        return driver_match.group(1).strip()
+
+    return None
+
+
+def extract_dsn(connection_string: str) -> Union[str, None]:
+    """
+    Extract the DSN value from an ODBC connection string.
+
+    Args:
+        connection_string (str): The ODBC connection string
+
+    Returns:
+        str or None: The extracted DSN value, or None if not found
+    """
+    for pattern in dsn_patterns:
+        match = re.search(pattern, connection_string, re.IGNORECASE)
+        if match:
+            return match.group(1).strip()
+
+    return None
+
+
+def extract_server(connection_string: str) -> Union[str, None]:
+    """
+    Parse an ODBC connection string and extract the server name.
+    Handles various parameter names for server (SERVER, Host, Data Source, etc.)
+
+    Args:
+        connection_string (str): The ODBC connection string
+
+    Returns:
+        str: The extracted server name, or None if not found
+    """
+    for pattern in server_patterns:
+        server_match = re.search(pattern, connection_string, re.IGNORECASE)
+        if server_match:
+            return server_match.group(1).strip()
+
+    # Special case for Athena: extract from AwsRegion if no server found
+    region_match = re.search(r"AwsRegion=([^;]*)", connection_string, re.IGNORECASE)
+    if region_match:
+        return f"aws-athena-{region_match.group(1).strip()}"
+
+    # Special case for Databricks: try to extract hostname from JDBC URL
+    jdbc_match = re.search(r"jdbc:spark://([^:;/]+)", connection_string, re.IGNORECASE)
+    if jdbc_match:
+        return jdbc_match.group(1).strip()
+
+    return None
+
+
+def extract_platform(connection_string: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    Extract the database platform name from the ODBC driver name.
+    Returns the lowercase platform name.
+
+    Args:
+        connection_string (str): The ODBC connection string
+
+    Returns:
+        tuple: A tuple containing the normalized platform name and the corresponding
+        Power BI platform name, or None if not recognized.
+    """
+    driver_name = extract_driver(connection_string)
+    if not driver_name:
+        return None, None
+
+    driver_lower = driver_name.lower()
+
+    for platform, pattern in platform_patterns.items():
+        if re.search(pattern, driver_lower):
+            return platform, powerbi_platform_names.get(platform)
+
+    return None, None
+
+
+def normalize_platform_name(platform: str) -> Tuple[Optional[str], Optional[str]]:
+    """
+    Normalizes the platform name by matching it with predefined patterns and maps it to
+    a corresponding Power BI platform name.
+
+    Args:
+        platform (str): The platform name to normalize
+
+    Returns:
+        tuple: A tuple containing the normalized platform name and the corresponding
+        Power BI platform name, or None if not recognized.
+    """
+    platform_lower = platform.lower()
+
+    for platform, pattern in platform_patterns.items():
+        if re.search(pattern, platform_lower):
+            return platform, powerbi_platform_names.get(platform)
+
+    return None, None

datahub/ingestion/source/powerbi/m_query/pattern_handler.py

@@ -29,6 +29,12 @@ from datahub.ingestion.source.powerbi.m_query.data_classes import (
     Lineage,
     ReferencedTable,
 )
+from datahub.ingestion.source.powerbi.m_query.odbc import (
+    extract_dsn,
+    extract_platform,
+    extract_server,
+    normalize_platform_name,
+)
 from datahub.ingestion.source.powerbi.rest_api_wrapper.data_classes import Table
 from datahub.metadata.schema_classes import SchemaFieldDataTypeClass
 from datahub.sql_parsing.sqlglot_lineage import (
@@ -155,6 +161,7 @@ class AbstractLineage(ABC):
                 tree_function.token_values(arg_list)
             ),
         )
+        logger.debug(f"DB Details: {arguments}")
 
         if len(arguments) < 2:
             logger.debug(f"Expected minimum 2 arguments, but got {len(arguments)}")
@@ -940,6 +947,147 @@ class NativeQueryLineage(AbstractLineage):
         )
 
 
+class OdbcLineage(AbstractLineage):
+    def create_lineage(
+        self, data_access_func_detail: DataAccessFunctionDetail
+    ) -> Lineage:
+        logger.debug(
+            f"Processing {self.get_platform_pair().powerbi_data_platform_name} "
+            f"data-access function detail {data_access_func_detail}"
+        )
+
+        connect_string, _ = self.get_db_detail_from_argument(
+            data_access_func_detail.arg_list
+        )
+
+        if not connect_string:
+            self.reporter.warning(
+                title="Can not extract ODBC connect string",
+                message="Can not extract ODBC connect string from data access function. Skipping Lineage creation.",
+                context=f"table-name={self.table.full_name}, data-access-func-detail={data_access_func_detail}",
+            )
+            return Lineage.empty()
+
+        logger.debug(f"ODBC connect string: {connect_string}")
+        data_platform, powerbi_platform = extract_platform(connect_string)
+        server_name = extract_server(connect_string)
+
+        if not data_platform:
+            dsn = extract_dsn(connect_string)
+            if dsn:
+                logger.debug(f"Extracted DSN: {dsn}")
+                server_name = dsn
+            if dsn and self.config.dsn_to_platform_name:
+                logger.debug(f"Attempting to map DSN {dsn} to platform")
+                name = self.config.dsn_to_platform_name.get(dsn)
+                if name:
+                    logger.debug(f"Found DSN {dsn} mapped to platform {name}")
+                    data_platform, powerbi_platform = normalize_platform_name(name)
+
+        if not data_platform or not powerbi_platform:
+            self.reporter.warning(
+                title="Can not determine ODBC platform",
+                message="Can not determine platform from ODBC connect string. Skipping Lineage creation.",
+                context=f"table-name={self.table.full_name}, connect-string={connect_string}",
+            )
+            return Lineage.empty()
+
+        platform_pair: DataPlatformPair = self.create_platform_pair(
+            data_platform, powerbi_platform
+        )
+
+        if not server_name and self.config.server_to_platform_instance:
+            self.reporter.warning(
+                title="Can not determine ODBC server name",
+                message="Can not determine server name with server_to_platform_instance mapping. Skipping Lineage creation.",
+                context=f"table-name={self.table.full_name}",
+            )
+            return Lineage.empty()
+        elif not server_name:
+            server_name = "unknown"
+
+        database_name = None
+        schema_name = None
+        table_name = None
+        qualified_table_name = None
+
+        temp_accessor: Optional[IdentifierAccessor] = (
+            data_access_func_detail.identifier_accessor
+        )
+
+        while temp_accessor:
+            logger.debug(
+                f"identifier = {temp_accessor.identifier} items = {temp_accessor.items}"
+            )
+            if temp_accessor.items.get("Kind") == "Database":
+                database_name = temp_accessor.items["Name"]
+
+            if temp_accessor.items.get("Kind") == "Schema":
+                schema_name = temp_accessor.items["Name"]
+
+            if temp_accessor.items.get("Kind") == "Table":
+                table_name = temp_accessor.items["Name"]
+
+            if temp_accessor.next is not None:
+                temp_accessor = temp_accessor.next
+            else:
+                break
+
+        if (
+            database_name is not None
+            and schema_name is not None
+            and table_name is not None
+        ):
+            qualified_table_name = f"{database_name}.{schema_name}.{table_name}"
+        elif database_name is not None and table_name is not None:
+            qualified_table_name = f"{database_name}.{table_name}"
+
+        if not qualified_table_name:
+            self.reporter.warning(
+                title="Can not determine qualified table name",
+                message="Can not determine qualified table name for ODBC data source. Skipping Lineage creation.",
+                context=f"table-name={self.table.full_name}, data-platform={data_platform}",
+            )
+            logger.warning(
+                f"Can not determine qualified table name for ODBC data source {data_platform} "
+                f"table {self.table.full_name}."
+            )
+            return Lineage.empty()
+
+        logger.debug(
+            f"ODBC Platform {data_platform} found qualified table name {qualified_table_name}"
+        )
+
+        urn = make_urn(
+            config=self.config,
+            platform_instance_resolver=self.platform_instance_resolver,
+            data_platform_pair=platform_pair,
+            server=server_name,
+            qualified_table_name=qualified_table_name,
+        )
+
+        column_lineage = self.create_table_column_lineage(urn)
+
+        return Lineage(
+            upstreams=[
+                DataPlatformTable(
+                    data_platform_pair=platform_pair,
+                    urn=urn,
+                )
+            ],
+            column_lineage=column_lineage,
+        )
+
+    @staticmethod
+    def create_platform_pair(
+        data_platform: str, powerbi_platform: str
+    ) -> DataPlatformPair:
+        return DataPlatformPair(data_platform, powerbi_platform)
+
+    def get_platform_pair(self) -> DataPlatformPair:
+        return SupportedDataPlatform.ODBC.value
+
+
 class SupportedPattern(Enum):
     DATABRICKS_QUERY = (
         DatabricksLineage,
@@ -991,6 +1139,11 @@ class SupportedPattern(Enum):
         FunctionName.NATIVE_QUERY,
     )
 
+    ODBC = (
+        OdbcLineage,
+        FunctionName.ODBC_DATA_ACCESS,
+    )
+
     def handler(self) -> Type[AbstractLineage]:
         return self.value[0]
 

datahub/ingestion/source/snowflake/snowflake_config.py

@@ -301,6 +301,7 @@ class SnowflakeV2Config(
         default=AllowDenyPattern.allow_all(),
         description=(
             "List of regex patterns for structured properties to include in ingestion."
+            " Applied to tags with form `<database>.<schema>.<tag_name>`."
             " Only used if `extract_tags` and `extract_tags_as_structured_properties` are enabled."
         ),
     )

datahub/ingestion/source/snowflake/snowflake_tag.py

@@ -23,6 +23,7 @@ from datahub.metadata.com.linkedin.pegasus2avro.common import AuditStamp
 from datahub.metadata.com.linkedin.pegasus2avro.structured import (
     StructuredPropertyDefinition,
 )
+from datahub.metadata.schema_classes import ChangeTypeClass
 from datahub.metadata.urns import (
     ContainerUrn,
     DatasetUrn,
@@ -81,7 +82,7 @@ class SnowflakeTagExtractor(SnowflakeCommonMixin):
     def create_structured_property_templates(self) -> Iterable[MetadataWorkUnit]:
         for tag in self.data_dictionary.get_all_tags():
             if not self.config.structured_property_pattern.allowed(
-                tag.tag_identifier()
+                tag._id_prefix_as_str()
             ):
                 continue
             if self.config.extract_tags_as_structured_properties:
@@ -111,6 +112,8 @@ class SnowflakeTagExtractor(SnowflakeCommonMixin):
         yield MetadataChangeProposalWrapper(
             entityUrn=urn,
             aspect=aspect,
+            changeType=ChangeTypeClass.CREATE,
+            headers={"If-None-Match": "*"},
         ).as_workunit()
 
     def _get_tags_on_object_with_propagation(

datahub/testing/mcp_diff.py

@@ -2,7 +2,7 @@ import dataclasses
 import json
 import re
 from collections import defaultdict
-from typing import Any, Dict, List, Sequence, Set, Tuple, Union
+from typing import Any, Dict, List, Optional, Sequence, Set, Tuple, Union
 
 import deepdiff.serialization
 import yaml
@@ -34,6 +34,7 @@ class AspectForDiff:
     aspect_name: str
     aspect: Dict[str, Any] = dataclasses.field(hash=False)
     delta_info: "DeltaInfo" = dataclasses.field(hash=False, repr=False)
+    headers: Optional[Dict[str, str]] = dataclasses.field(default=None, hash=False)
 
     @classmethod
     def create_from_mcp(cls, idx: int, obj: Dict[str, Any]) -> "AspectForDiff":
@@ -44,6 +45,7 @@ class AspectForDiff:
             aspect_name=obj["aspectName"],
             aspect=aspect.get("json", aspect),
             delta_info=DeltaInfo(idx=idx, original=obj),
+            headers=obj.get("headers"),
         )
 
     def __repr__(self):
@@ -240,9 +242,12 @@ class MCPDiff:
                         s.append(serialize_aspect(ga.aspect))
                 for (i, old, new), diffs in aspect_diffs.aspects_changed.items():
                     s.append(self.report_aspect(old, i, "changed") + ":")
+
+                    print_aspects = False
                     for diff_level in diffs:
                         s.append(self.report_diff_level(diff_level, i))
-                    if verbose:
+                        print_aspects |= self.is_diff_level_on_aspect(diff_level)
+                    if verbose and print_aspects:
                         s.append(f"Old aspect:\n{serialize_aspect(old.aspect)}")
                         s.append(f"New aspect:\n{serialize_aspect(new.aspect)}")
 
@@ -271,6 +276,14 @@ class MCPDiff:
             f"root[{idx}].", ""
         )
 
+    @staticmethod
+    def is_diff_level_on_aspect(diff: DiffLevel) -> bool:
+        skip_print_fields = ["changeType", "headers"]
+        try:
+            return diff.path(output_format="list")[1] not in skip_print_fields
+        except IndexError:
+            return True
+
 
 def serialize_aspect(aspect: Union[AspectForDiff, Dict[str, Any]]) -> str:
     if isinstance(aspect, AspectForDiff):  # Unpack aspect