acryl-datahub 1.0.0.3rc6__py3-none-any.whl → 1.0.0.3rc7__py3-none-any.whl

{acryl_datahub-1.0.0.3rc6.dist-info → acryl_datahub-1.0.0.3rc7.dist-info}/RECORD

@@ -1,7 +1,7 @@
-acryl_datahub-1.0.0.3rc6.dist-info/licenses/LICENSE,sha256=9xNHpsD0uYF5ONzXsKDCuHHB-xbiCrSbueWXqrTNsxk,11365
+acryl_datahub-1.0.0.3rc7.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=VrjEJq0-eU07ihy36V-x_6VzO_ae3ZtXi7aMCbdTSZw,323
+datahub/_version.py,sha256=n49MhTfoZh6lQvQMYp45DAwrexBWePxkeHMtc0_gSGk,323
 datahub/entrypoints.py,sha256=2TYgHhs3sCxJlojIHjqfxzt3_ImPwPzq4vBtsUuMqu4,8885
 datahub/errors.py,sha256=BzKdcmYseHOt36zfjJXc17WNutFhp9Y23cU_L6cIkxc,612
 datahub/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -334,7 +334,7 @@ datahub/ingestion/source/hex/mapper.py,sha256=N3mTlEcrOmhv9ia1dnHGFgFJD2ddyTtU3H
 datahub/ingestion/source/hex/model.py,sha256=S9bUhfFcjzuio2dBS6HzSyRVPiSJvRvMQ0qyVrjV5-E,1766
 datahub/ingestion/source/hex/query_fetcher.py,sha256=ZaRrja05mK0VlIvpsFi-8-EBoJr0GSLbUxBUjycibIU,12505
 datahub/ingestion/source/iceberg/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-datahub/ingestion/source/iceberg/iceberg.py,sha256=s69XzCGD5oV_hqTyvzCt5eLKZVEzVIJo_DiAEDk3p6A,34759
+datahub/ingestion/source/iceberg/iceberg.py,sha256=-8uaBerljvonaT7Gn9Evokq6-SSDiMRf8kKo7Hg1qY4,35414
 datahub/ingestion/source/iceberg/iceberg_common.py,sha256=VGosqYPmn_j6GETSnDHZ8Ay1BVOedmx2x5LHxw16I3A,12278
 datahub/ingestion/source/iceberg/iceberg_profiler.py,sha256=9iwp2vpQTi4OMbIKoDZV5lAdvjMR0ls6Llpck9grJIE,9875
 datahub/ingestion/source/identity/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -901,13 +901,14 @@ datahub/pydantic/compat.py,sha256=TUEo4kSEeOWVAhV6LQtst1phrpVgGtK4uif4OI5vQ2M,19
 datahub/sdk/__init__.py,sha256=QeutS6Th8K4E4ZxXuoGrmvahN6zA9Oh9asKk5mw9AIk,1670
 datahub/sdk/_all_entities.py,sha256=inbLFv2T7dhZpGfBY5FPhCWbyE0P0G8umOt0Bc7V4XA,520
 datahub/sdk/_attribution.py,sha256=0Trh8steVd27GOr9MKCZeawbuDD2_q3GIsZlCtHqEUg,1321
-datahub/sdk/_shared.py,sha256=5L1IkihLc7Pd2x0ypDs96kZ8ecm6o0-UZEn0J1Sffqw,24808
-datahub/sdk/_utils.py,sha256=aGE665Su8SGtj2CRDiTaXNYrJ8ADBsS0m4DmaXw79b8,1027
+datahub/sdk/_shared.py,sha256=64m4Q7D5QdS-Z9Te0uOFwsZMBZEfwZ__2sZ8uCTHa7w,24770
+datahub/sdk/_utils.py,sha256=oXE2BzsXE5zmSkCP3R1tObD4RHnPeH_ps83D_Dw9JaQ,1169
 datahub/sdk/container.py,sha256=yw_vw9Jl1wOYNwMHxQHLz5ZvVQVDWWHi9CWBR3hOCd8,7547
-datahub/sdk/dataset.py,sha256=5LG4c_8bHeSPYrW88KNXRgiPD8frBjR0OBVrrwdquU4,29152
+datahub/sdk/dataset.py,sha256=7PlmqKDROJvsh1CtlhG8owOhLdelHVbSSg5hA5Kbwp0,29150
 datahub/sdk/entity.py,sha256=Q29AbpS58L4gD8ETwoNIwG-ouytz4c0MSSFi6-jLl_4,6742
 datahub/sdk/entity_client.py,sha256=1AC9J7-jv3rD-MFEPz2PnFrT8nFkj_WO0M-4nyVOtQk,5319
-datahub/sdk/main_client.py,sha256=h2MKRhR-BO0zGCMhF7z2bTncX4hagKrAYwR3wTNTtzA,3666
+datahub/sdk/lineage_client.py,sha256=1JPxQx5pZYQwnzL_VX3KjAbX2QWdvjSKm8S8Bya2IAc,8617
+datahub/sdk/main_client.py,sha256=EeFZw4ot6L8DP4xHMiy07n7yICTjBn080YtW8ub5mBk,3781
 datahub/sdk/mlmodel.py,sha256=amS-hHg5tT7zAqEHG17kSA60Q7td2DFtO-W2rEfb2rY,10206
 datahub/sdk/mlmodelgroup.py,sha256=_7IkqkLVeyqYVEUHTVePSDLQyESsnwht5ca1lcMODAg,7842
 datahub/sdk/resolver_client.py,sha256=nKMAZJt2tRSGfKSzoREIh43PXqjM3umLiYkYHJjo1io,3243
@@ -936,14 +937,15 @@ datahub/sql_parsing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 datahub/sql_parsing/_models.py,sha256=il-xm1RcLdi1phJUV3xrTecdOGH31akqheuSC2N4YhQ,3141
 datahub/sql_parsing/_sqlglot_patch.py,sha256=dpTiGj4Jxzvbi6HkYiOTbZ81CTFwEEo6JgYOd-dnCMA,6788
 datahub/sql_parsing/datajob.py,sha256=1X8KpEk-y3_8xJuA_Po27EHZgOcxK9QADI6Om9gSGn0,1751
+datahub/sql_parsing/fingerprint_utils.py,sha256=3hGiexaQXnE7eZLxo-t7hlTyVQz7wombAcQELnN-yDY,185
 datahub/sql_parsing/query_types.py,sha256=FKjDzszZzsrCfYfm7dgD6T_8865qxWl767fdGyHWBh4,2720
 datahub/sql_parsing/schema_resolver.py,sha256=ISuingLcQnOJZkNXBkc73uPwYUbbOtERAjgGhJajDiQ,10782
 datahub/sql_parsing/split_statements.py,sha256=OIQXA9e4k3G9Z1y7rbgdtZhMWt4FPnq41cE8Jkm9cBY,9542
-datahub/sql_parsing/sql_parsing_aggregator.py,sha256=A3_0wSxBJSRowEaslptDpBoKO42XXx5UyTEK9PkekIs,70317
+datahub/sql_parsing/sql_parsing_aggregator.py,sha256=zKxIffMWK8YKIN0A7wzOfVkMGC7Cd_9nB6gWc-6BHuw,70671
 datahub/sql_parsing/sql_parsing_common.py,sha256=cZ4WvVyHZuXDGjnBvKMX2_fz2EMextB5WQWcK0_saBo,3155
 datahub/sql_parsing/sql_parsing_result_utils.py,sha256=prwWTj1EB2fRPv1eMB4EkpFNafIYAt-X8TIK0NWqank,796
 datahub/sql_parsing/sqlglot_lineage.py,sha256=l0kT8MuRIg96X7BNJaboMznF54b-yvM2nMTLyF2d0Nw,47446
-datahub/sql_parsing/sqlglot_utils.py,sha256=5cUiEWLWfVTI7uIxolAfOfNVo50qnklzhj86gxSFWqg,14943
+datahub/sql_parsing/sqlglot_utils.py,sha256=TI11oBu1wrGeUuUGBg7hGTr6lTvztahdqiqXNJYRfbQ,14823
 datahub/sql_parsing/tool_meta_extractor.py,sha256=EV_g7sOchTSUm2p6wluNJqND7-rDYokVTqqFCM7hQ6c,7599
 datahub/telemetry/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 datahub/telemetry/stats.py,sha256=TwaQisQlD2Bk0uw__pP6u3Ovz9r-Ip4pCwpnto4r5e0,959
@@ -1048,8 +1050,8 @@ 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-1.0.0.3rc6.dist-info/METADATA,sha256=ZOld7fZ4VTL1L7DczapOhGc9llaIYX4yscDrNUACf-g,176989
-acryl_datahub-1.0.0.3rc6.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-acryl_datahub-1.0.0.3rc6.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
-acryl_datahub-1.0.0.3rc6.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
-acryl_datahub-1.0.0.3rc6.dist-info/RECORD,,
+acryl_datahub-1.0.0.3rc7.dist-info/METADATA,sha256=cS9ynN7khxxthJ9wKCRUKd8-_EHBy-cjhxBPx-KqCu0,176989
+acryl_datahub-1.0.0.3rc7.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+acryl_datahub-1.0.0.3rc7.dist-info/entry_points.txt,sha256=o3mDeJXSKhsy7XLkuogihraiabBdLn9HaizYXPrxmk0,9710
+acryl_datahub-1.0.0.3rc7.dist-info/top_level.txt,sha256=iLjSrLK5ox1YVYcglRUkcvfZPvKlobBWx7CTUXx8_GI,25
+acryl_datahub-1.0.0.3rc7.dist-info/RECORD,,

datahub/_version.py

@@ -1,6 +1,6 @@
 # Published at https://pypi.org/project/acryl-datahub/.
 __package_name__ = "acryl-datahub"
-__version__ = "1.0.0.3rc6"
+__version__ = "1.0.0.3rc7"
 
 
 def is_dev_mode() -> bool:

datahub/ingestion/source/iceberg/iceberg.py

@@ -16,7 +16,7 @@ from pyiceberg.exceptions import (
 )
 from pyiceberg.schema import Schema, SchemaVisitorPerPrimitiveType, visit
 from pyiceberg.table import Table
-from pyiceberg.typedef import Identifier
+from pyiceberg.typedef import Identifier, Properties
 from pyiceberg.types import (
     BinaryType,
     BooleanType,
@@ -387,8 +387,13 @@ class IcebergSource(StatefulIngestionSourceBase):
                         env=self.config.env,
                     )
                 )
+                namespace_properties: Properties = catalog.load_namespace_properties(
+                    namespace
+                )
                 namespaces.append((namespace, namespace_urn))
-                for aspect in self._create_iceberg_namespace_aspects(namespace):
+                for aspect in self._create_iceberg_namespace_aspects(
+                    namespace, namespace_properties
+                ):
                     yield stamping_processor.stamp_wu(
                         MetadataChangeProposalWrapper(
                             entityUrn=namespace_urn, aspect=aspect
@@ -608,12 +613,23 @@ class IcebergSource(StatefulIngestionSourceBase):
         return self.report
 
     def _create_iceberg_namespace_aspects(
-        self, namespace: Identifier
+        self, namespace: Identifier, properties: Properties
     ) -> Iterable[_Aspect]:
         namespace_repr = ".".join(namespace)
+        custom_properties: Dict[str, str] = {}
+        for k, v in properties.items():
+            try:
+                custom_properties[str(k)] = str(v)
+            except Exception as e:
+                LOGGER.warning(
+                    f"Exception when trying to parse namespace properties for {namespace_repr}. Exception: {e}"
+                )
         yield Status(removed=False)
         yield ContainerProperties(
-            name=namespace_repr, qualifiedName=namespace_repr, env=self.config.env
+            name=namespace_repr,
+            qualifiedName=namespace_repr,
+            env=self.config.env,
+            customProperties=custom_properties,
         )
         yield SubTypes(typeNames=[DatasetContainerSubTypes.NAMESPACE])
         dpi = self._get_dataplatform_instance_aspect()

datahub/sdk/_shared.py

@@ -41,7 +41,7 @@ from datahub.metadata.urns import (
     Urn,
     VersionSetUrn,
 )
-from datahub.sdk._utils import add_list_unique, remove_list_unique
+from datahub.sdk._utils import DEFAULT_ACTOR_URN, add_list_unique, remove_list_unique
 from datahub.sdk.entity import Entity
 from datahub.utilities.urns.error import InvalidUrnError
 
@@ -54,8 +54,6 @@ DatajobUrnOrStr: TypeAlias = Union[str, DataJobUrn]
 
 ActorUrn: TypeAlias = Union[CorpUserUrn, CorpGroupUrn]
 
-_DEFAULT_ACTOR_URN = CorpUserUrn("__ingestion").urn()
-
 TrainingMetricsInputType: TypeAlias = Union[
     List[models.MLMetricClass], Dict[str, Optional[str]]
 ]
@@ -475,7 +473,7 @@ class HasTerms(Entity):
     def _terms_audit_stamp(self) -> models.AuditStampClass:
         return models.AuditStampClass(
             time=0,
-            actor=_DEFAULT_ACTOR_URN,
+            actor=DEFAULT_ACTOR_URN,
         )
 
     def set_terms(self, terms: TermsInputType) -> None:
@@ -563,7 +561,7 @@ class HasInstitutionalMemory(Entity):
     def _institutional_memory_audit_stamp(self) -> models.AuditStampClass:
         return models.AuditStampClass(
             time=0,
-            actor=_DEFAULT_ACTOR_URN,
+            actor=DEFAULT_ACTOR_URN,
         )
 
     @classmethod

datahub/sdk/_utils.py

@@ -1,6 +1,10 @@
 from typing import Any, Callable, List, Protocol, TypeVar
 
 from datahub.errors import ItemNotFoundError
+from datahub.metadata.urns import CorpUserUrn
+
+# TODO: Change __ingestion to _ingestion.
+DEFAULT_ACTOR_URN = CorpUserUrn("__ingestion").urn()
 
 
 class _SupportsEq(Protocol):

datahub/sdk/dataset.py

@@ -87,7 +87,7 @@ def _parse_upstream_input(
         assert_never(upstream_input)
 
 
-def _parse_cll_mapping(
+def parse_cll_mapping(
     *,
     upstream: DatasetUrnOrStr,
     downstream: DatasetUrnOrStr,
@@ -142,7 +142,7 @@ def _parse_upstream_lineage_input(
                 )
             )
             cll.extend(
-                _parse_cll_mapping(
+                parse_cll_mapping(
                     upstream=dataset_urn,
                     downstream=downstream_urn,
                     cll_mapping=column_lineage,

datahub/sdk/lineage_client.py

@@ -0,0 +1,235 @@
+from __future__ import annotations
+
+import difflib
+import logging
+from typing import TYPE_CHECKING, List, Literal, Optional, Set, Union
+
+import datahub.metadata.schema_classes as models
+from datahub.emitter.mcp import MetadataChangeProposalWrapper
+from datahub.errors import SdkUsageError
+from datahub.metadata.schema_classes import SchemaMetadataClass
+from datahub.metadata.urns import DatasetUrn, QueryUrn
+from datahub.sdk._shared import DatasetUrnOrStr
+from datahub.sdk._utils import DEFAULT_ACTOR_URN
+from datahub.sdk.dataset import ColumnLineageMapping, parse_cll_mapping
+from datahub.specific.dataset import DatasetPatchBuilder
+from datahub.sql_parsing.fingerprint_utils import generate_hash
+from datahub.utilities.ordered_set import OrderedSet
+
+if TYPE_CHECKING:
+    from datahub.sdk.main_client import DataHubClient
+
+logger = logging.getLogger(__name__)
+
+_empty_audit_stamp = models.AuditStampClass(
+    time=0,
+    actor=DEFAULT_ACTOR_URN,
+)
+
+
+class LineageClient:
+    def __init__(self, client: DataHubClient):
+        self._client = client
+
+    def _get_fields_from_dataset_urn(self, dataset_urn: DatasetUrn) -> Set[str]:
+        schema_metadata = self._client._graph.get_aspect(
+            str(dataset_urn), SchemaMetadataClass
+        )
+        if schema_metadata is None:
+            return Set()
+
+        return {field.fieldPath for field in schema_metadata.fields}
+
+    @classmethod
+    def _get_strict_column_lineage(
+        cls,
+        upstream_fields: Set[str],
+        downstream_fields: Set[str],
+    ) -> ColumnLineageMapping:
+        """Find matches between upstream and downstream fields with case-insensitive matching."""
+        strict_column_lineage: ColumnLineageMapping = {}
+
+        # Create case-insensitive mapping of upstream fields
+        case_insensitive_map = {field.lower(): field for field in upstream_fields}
+
+        # Match downstream fields using case-insensitive comparison
+        for downstream_field in downstream_fields:
+            lower_field = downstream_field.lower()
+            if lower_field in case_insensitive_map:
+                # Use the original case of the upstream field
+                strict_column_lineage[downstream_field] = [
+                    case_insensitive_map[lower_field]
+                ]
+
+        return strict_column_lineage
+
+    @classmethod
+    def _get_fuzzy_column_lineage(
+        cls,
+        upstream_fields: Set[str],
+        downstream_fields: Set[str],
+    ) -> ColumnLineageMapping:
+        """Generate fuzzy matches between upstream and downstream fields."""
+
+        # Simple normalization function for better matching
+        def normalize(s: str) -> str:
+            return s.lower().replace("_", "")
+
+        # Create normalized lookup for upstream fields
+        normalized_upstream = {normalize(field): field for field in upstream_fields}
+
+        fuzzy_column_lineage = {}
+        for downstream_field in downstream_fields:
+            # Try exact match first
+            if downstream_field in upstream_fields:
+                fuzzy_column_lineage[downstream_field] = [downstream_field]
+                continue
+
+            # Try normalized match
+            norm_downstream = normalize(downstream_field)
+            if norm_downstream in normalized_upstream:
+                fuzzy_column_lineage[downstream_field] = [
+                    normalized_upstream[norm_downstream]
+                ]
+                continue
+
+            # If no direct match, find closest match using similarity
+            matches = difflib.get_close_matches(
+                norm_downstream,
+                normalized_upstream.keys(),
+                n=1,  # Return only the best match
+                cutoff=0.8,  # Adjust cutoff for sensitivity
+            )
+
+            if matches:
+                fuzzy_column_lineage[downstream_field] = [
+                    normalized_upstream[matches[0]]
+                ]
+
+        return fuzzy_column_lineage
+
+    def add_dataset_copy_lineage(
+        self,
+        *,
+        upstream: DatasetUrnOrStr,
+        downstream: DatasetUrnOrStr,
+        column_lineage: Union[
+            None, ColumnLineageMapping, Literal["auto_fuzzy", "auto_strict"]
+        ] = "auto_fuzzy",
+    ) -> None:
+        upstream = DatasetUrn.from_string(upstream)
+        downstream = DatasetUrn.from_string(downstream)
+
+        if column_lineage is None:
+            cll = None
+        elif column_lineage in ["auto_fuzzy", "auto_strict"]:
+            upstream_schema = self._get_fields_from_dataset_urn(upstream)
+            downstream_schema = self._get_fields_from_dataset_urn(downstream)
+            if column_lineage == "auto_fuzzy":
+                mapping = self._get_fuzzy_column_lineage(
+                    upstream_schema, downstream_schema
+                )
+            else:
+                mapping = self._get_strict_column_lineage(
+                    upstream_schema, downstream_schema
+                )
+            cll = parse_cll_mapping(
+                upstream=upstream,
+                downstream=downstream,
+                cll_mapping=mapping,
+            )
+        elif isinstance(column_lineage, dict):
+            cll = parse_cll_mapping(
+                upstream=upstream,
+                downstream=downstream,
+                cll_mapping=column_lineage,
+            )
+
+        updater = DatasetPatchBuilder(str(downstream))
+        updater.add_upstream_lineage(
+            models.UpstreamClass(
+                dataset=str(upstream),
+                type=models.DatasetLineageTypeClass.COPY,
+            )
+        )
+        for cl in cll or []:
+            updater.add_fine_grained_upstream_lineage(cl)
+
+        self._client.entities.update(updater)
+
+    def add_dataset_transform_lineage(
+        self,
+        *,
+        upstream: DatasetUrnOrStr,
+        downstream: DatasetUrnOrStr,
+        column_lineage: Optional[ColumnLineageMapping] = None,
+        query_text: Optional[str] = None,
+    ) -> None:
+        upstream = DatasetUrn.from_string(upstream)
+        downstream = DatasetUrn.from_string(downstream)
+
+        cll = None
+        if column_lineage is not None:
+            cll = parse_cll_mapping(
+                upstream=upstream,
+                downstream=downstream,
+                cll_mapping=column_lineage,
+            )
+
+        fields_involved = OrderedSet([str(upstream), str(downstream)])
+        if cll is not None:
+            for c in cll:
+                for field in c.upstreams or []:
+                    fields_involved.add(field)
+                for field in c.downstreams or []:
+                    fields_involved.add(field)
+
+        query_urn = None
+        query_entity = None
+        if query_text:
+            # Eventually we might want to use our regex-based fingerprinting instead.
+            fingerprint = generate_hash(query_text)
+            query_urn = QueryUrn(fingerprint).urn()
+
+            from datahub.sql_parsing.sql_parsing_aggregator import make_query_subjects
+
+            query_entity = MetadataChangeProposalWrapper.construct_many(
+                query_urn,
+                aspects=[
+                    models.QueryPropertiesClass(
+                        statement=models.QueryStatementClass(
+                            value=query_text, language=models.QueryLanguageClass.SQL
+                        ),
+                        source=models.QuerySourceClass.SYSTEM,
+                        created=_empty_audit_stamp,
+                        lastModified=_empty_audit_stamp,
+                    ),
+                    make_query_subjects(list(fields_involved)),
+                ],
+            )
+
+        updater = DatasetPatchBuilder(str(downstream))
+        updater.add_upstream_lineage(
+            models.UpstreamClass(
+                dataset=str(upstream),
+                type=models.DatasetLineageTypeClass.TRANSFORMED,
+                query=query_urn,
+            )
+        )
+        for cl in cll or []:
+            cl.query = query_urn
+            updater.add_fine_grained_upstream_lineage(cl)
+
+        # Throw if the dataset does not exist.
+        # We need to manually call .build() instead of reusing client.update()
+        # so that we make just one emit_mcps call.
+        if not self._client._graph.exists(updater.urn):
+            raise SdkUsageError(
+                f"Dataset {updater.urn} does not exist, and hence cannot be updated."
+            )
+        mcps: List[
+            Union[MetadataChangeProposalWrapper, models.MetadataChangeProposalClass]
+        ] = list(updater.build())
+        if query_entity:
+            mcps.extend(query_entity)
+        self._client._graph.emit_mcps(mcps)

datahub/sdk/main_client.py

@@ -6,6 +6,7 @@ from datahub.errors import SdkUsageError
 from datahub.ingestion.graph.client import DataHubGraph, get_default_graph
 from datahub.ingestion.graph.config import DatahubClientConfig
 from datahub.sdk.entity_client import EntityClient
+from datahub.sdk.lineage_client import LineageClient
 from datahub.sdk.resolver_client import ResolverClient
 from datahub.sdk.search_client import SearchClient
 
@@ -99,4 +100,6 @@ class DataHubClient:
     def search(self) -> SearchClient:
         return SearchClient(self)
 
-    # TODO: lineage client
+    @property
+    def lineage(self) -> LineageClient:
+        return LineageClient(self)

datahub/sql_parsing/fingerprint_utils.py

@@ -0,0 +1,6 @@
+import hashlib
+
+
+def generate_hash(text: str) -> str:
+    # Once we move to Python 3.9+, we can set `usedforsecurity=False`.
+    return hashlib.sha256(text.encode("utf-8")).hexdigest()

datahub/sql_parsing/sql_parsing_aggregator.py

@@ -32,6 +32,7 @@ from datahub.metadata.urns import (
     SchemaFieldUrn,
     Urn,
 )
+from datahub.sql_parsing.fingerprint_utils import generate_hash
 from datahub.sql_parsing.schema_resolver import (
     SchemaResolver,
     SchemaResolverInterface,
@@ -49,7 +50,6 @@ from datahub.sql_parsing.sqlglot_lineage import (
 )
 from datahub.sql_parsing.sqlglot_utils import (
     _parse_statement,
-    generate_hash,
     get_query_fingerprint,
     try_format_query,
 )
@@ -155,6 +155,47 @@ class QueryMetadata:
             actor=(self.actor or _DEFAULT_USER_URN).urn(),
         )
 
+    def get_subjects(
+        self,
+        downstream_urn: Optional[str],
+        include_fields: bool,
+    ) -> List[UrnStr]:
+        query_subject_urns = OrderedSet[UrnStr]()
+        for upstream in self.upstreams:
+            query_subject_urns.add(upstream)
+            if include_fields:
+                for column in sorted(self.column_usage.get(upstream, [])):
+                    query_subject_urns.add(
+                        builder.make_schema_field_urn(upstream, column)
+                    )
+        if downstream_urn:
+            query_subject_urns.add(downstream_urn)
+            if include_fields:
+                for column_lineage in self.column_lineage:
+                    query_subject_urns.add(
+                        builder.make_schema_field_urn(
+                            downstream_urn, column_lineage.downstream.column
+                        )
+                    )
+        return list(query_subject_urns)
+
+    def make_query_properties(self) -> models.QueryPropertiesClass:
+        return models.QueryPropertiesClass(
+            statement=models.QueryStatementClass(
+                value=self.formatted_query_string,
+                language=models.QueryLanguageClass.SQL,
+            ),
+            source=models.QuerySourceClass.SYSTEM,
+            created=self.make_created_audit_stamp(),
+            lastModified=self.make_last_modified_audit_stamp(),
+        )
+
+
+def make_query_subjects(urns: List[UrnStr]) -> models.QuerySubjectsClass:
+    return models.QuerySubjectsClass(
+        subjects=[models.QuerySubjectClass(entity=urn) for urn in urns]
+    )
+
 
 @dataclasses.dataclass
 class KnownQueryLineageInfo:
@@ -1440,42 +1481,15 @@ class SqlParsingAggregator(Closeable):
             self.report.num_queries_skipped_due_to_filters += 1
             return
 
-        query_subject_urns = OrderedSet[UrnStr]()
-        for upstream in query.upstreams:
-            query_subject_urns.add(upstream)
-            if self.generate_query_subject_fields:
-                for column in sorted(query.column_usage.get(upstream, [])):
-                    query_subject_urns.add(
-                        builder.make_schema_field_urn(upstream, column)
-                    )
-        if downstream_urn:
-            query_subject_urns.add(downstream_urn)
-            if self.generate_query_subject_fields:
-                for column_lineage in query.column_lineage:
-                    query_subject_urns.add(
-                        builder.make_schema_field_urn(
-                            downstream_urn, column_lineage.downstream.column
-                        )
-                    )
-
         yield from MetadataChangeProposalWrapper.construct_many(
             entityUrn=self._query_urn(query_id),
             aspects=[
-                models.QueryPropertiesClass(
-                    statement=models.QueryStatementClass(
-                        value=query.formatted_query_string,
-                        language=models.QueryLanguageClass.SQL,
-                    ),
-                    source=models.QuerySourceClass.SYSTEM,
-                    created=query.make_created_audit_stamp(),
-                    lastModified=query.make_last_modified_audit_stamp(),
-                    origin=query.origin.urn() if query.origin else None,
-                ),
-                models.QuerySubjectsClass(
-                    subjects=[
-                        models.QuerySubjectClass(entity=urn)
-                        for urn in query_subject_urns
-                    ]
+                query.make_query_properties(),
+                make_query_subjects(
+                    query.get_subjects(
+                        downstream_urn=downstream_urn,
+                        include_fields=self.generate_query_subject_fields,
+                    )
                 ),
                 models.DataPlatformInstanceClass(
                     platform=self.platform.urn(),

datahub/sql_parsing/sqlglot_utils.py

@@ -1,7 +1,6 @@
 from datahub.sql_parsing._sqlglot_patch import SQLGLOT_PATCHED
 
 import functools
-import hashlib
 import logging
 import re
 from typing import Dict, Iterable, Optional, Tuple, Union
@@ -10,6 +9,8 @@ import sqlglot
 import sqlglot.errors
 import sqlglot.optimizer.eliminate_ctes
 
+from datahub.sql_parsing.fingerprint_utils import generate_hash
+
 assert SQLGLOT_PATCHED
 
 logger = logging.getLogger(__name__)
@@ -251,11 +252,6 @@ def generalize_query(expression: sqlglot.exp.ExpOrStr, dialect: DialectOrStr) ->
     return expression.transform(_strip_expression, copy=True).sql(dialect=dialect)
 
 
-def generate_hash(text: str) -> str:
-    # Once we move to Python 3.9+, we can set `usedforsecurity=False`.
-    return hashlib.sha256(text.encode("utf-8")).hexdigest()
-
-
 def get_query_fingerprint_debug(
     expression: sqlglot.exp.ExpOrStr,
     platform: DialectOrStr,