acryl-datahub 1.0.0.1rc7__py3-none-any.whl → 1.0.0.2rc2__py3-none-any.whl

datahub/ingestion/source/hex/query_fetcher.py

@@ -0,0 +1,297 @@
+import logging
+import re
+from dataclasses import dataclass, field
+from datetime import datetime
+from typing import Dict, Iterable, List, Optional, Tuple
+
+from datahub.ingestion.api.source import SourceReport
+from datahub.ingestion.source.hex.constants import (
+    DATAHUB_API_PAGE_SIZE_DEFAULT,
+    HEX_PLATFORM_URN,
+)
+from datahub.metadata.schema_classes import QueryPropertiesClass, QuerySubjectsClass
+from datahub.metadata.urns import DatasetUrn, QueryUrn, SchemaFieldUrn
+from datahub.sdk.main_client import DataHubClient
+from datahub.sdk.search_filters import FilterDsl as F
+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
+HEX_METADATA_PATTERN = r'-- Hex query metadata: \{.*?"project_id": "([^"]+)".*?"project_url": "https?://[^/]+/([^/]+)/hex/.*?\}'
+
+
+@dataclass
+class QueryResponse:
+    """This is the public response model for the HexQueryFetcher."""
+
+    urn: QueryUrn
+    hex_project_id: str
+    dataset_subjects: List[DatasetUrn] = field(default_factory=list)
+    schema_field_subjects: List[SchemaFieldUrn] = field(default_factory=list)
+
+
+@dataclass
+class HexQueryFetcherReport(SourceReport):
+    start_datetime: Optional[datetime] = None
+    end_datetime: Optional[datetime] = None
+    fetched_query_urns: int = 0
+    fetched_query_objects: int = 0
+    filtered_out_queries_missing_metadata: int = 0
+    filtered_out_queries_different_workspace: int = 0
+    filtered_out_queries_no_subjects: int = 0
+    total_queries: int = 0
+    total_dataset_subjects: int = 0
+    total_schema_field_subjects: int = 0
+    num_calls_fetch_query_entities: int = 0
+
+
+class HexQueryFetcher:
+    def __init__(
+        self,
+        datahub_client: DataHubClient,
+        workspace_name: str,
+        start_datetime: datetime,
+        end_datetime: datetime,
+        report: HexQueryFetcherReport,
+        page_size: int = DATAHUB_API_PAGE_SIZE_DEFAULT,
+    ):
+        self.datahub_client = datahub_client
+        self.workspace_name = workspace_name
+        self.start_datetime = start_datetime
+        self.end_datetime = end_datetime
+        self.report = report
+        self.page_size = page_size
+
+        self.report.start_datetime = start_datetime
+        self.report.end_datetime = end_datetime
+
+    def fetch(self) -> Iterable[QueryResponse]:
+        try:
+            query_urns = self._fetch_query_urns_filter_hex_and_last_modified()
+            assert all(isinstance(urn, QueryUrn) for urn in query_urns)
+            self.report.fetched_query_urns = len(query_urns)
+
+            entities_by_urn = self._fetch_query_entities(query_urns)
+            self.report.fetched_query_objects = len(entities_by_urn)
+        except Exception as e:
+            self.report.failure(
+                title="Error fetching Queries for lineage",
+                message="Error fetching Queries will result on missing lineage",
+                context=str(
+                    dict(
+                        workspace_name=self.workspace_name,
+                        start_datetime=self.start_datetime,
+                        end_datetime=self.end_datetime,
+                    )
+                ),
+                exc=e,
+            )
+        else:
+            if not query_urns or not entities_by_urn:
+                self.report.warning(
+                    title="No Queries found with Hex as origin",
+                    message="No lineage because of no Queries found with Hex as origin in the given time range; you may consider extending the time range to fetch more queries.",
+                    context=str(
+                        dict(
+                            workspace_name=self.workspace_name,
+                            start_datetime=self.start_datetime,
+                            end_datetime=self.end_datetime,
+                        )
+                    ),
+                )
+                return
+
+            for query_urn, (
+                query_properties,
+                query_subjects,
+            ) in entities_by_urn.items():
+                maybe_query_response = self._build_query_response(
+                    query_urn=query_urn,
+                    query_properties=query_properties,
+                    query_subjects=query_subjects,
+                )
+                if maybe_query_response:
+                    yield maybe_query_response
+
+    def _fetch_query_entities(
+        self, query_urns: List[QueryUrn]
+    ) -> Dict[
+        QueryUrn, Tuple[Optional[QueryPropertiesClass], Optional[QuerySubjectsClass]]
+    ]:
+        entities_by_urn: Dict[
+            QueryUrn,
+            Tuple[Optional[QueryPropertiesClass], Optional[QuerySubjectsClass]],
+        ] = {}
+        for i in range(0, len(query_urns), self.page_size):
+            batch = query_urns[i : i + self.page_size]
+
+            logger.debug(f"Fetching query entities for {len(batch)} queries: {batch}")
+            entities = self.datahub_client._graph.get_entities(
+                entity_name=QueryUrn.ENTITY_TYPE,
+                urns=[urn.urn() for urn in batch],
+                aspects=[
+                    QueryPropertiesClass.ASPECT_NAME,
+                    QuerySubjectsClass.ASPECT_NAME,
+                ],
+                with_system_metadata=False,
+            )
+            self.report.num_calls_fetch_query_entities += 1
+            logger.debug(f"Get entities response: {entities}")
+
+            for urn, entity in entities.items():
+                query_urn = QueryUrn.from_string(urn)
+
+                properties_tuple = entity.get(
+                    QueryPropertiesClass.ASPECT_NAME, (None, None)
+                )
+                query_properties: Optional[QueryPropertiesClass] = None
+                if properties_tuple and properties_tuple[0]:
+                    assert isinstance(properties_tuple[0], QueryPropertiesClass)
+                    query_properties = properties_tuple[0]
+
+                subjects_tuple = entity.get(
+                    QuerySubjectsClass.ASPECT_NAME, (None, None)
+                )
+                query_subjects: Optional[QuerySubjectsClass] = None
+                if subjects_tuple and subjects_tuple[0]:
+                    assert isinstance(subjects_tuple[0], QuerySubjectsClass)
+                    query_subjects = subjects_tuple[0]
+
+                entities_by_urn[query_urn] = (query_properties, query_subjects)
+
+        return entities_by_urn
+
+    def _fetch_query_urns_filter_hex_and_last_modified(self) -> List[QueryUrn]:
+        last_modified_start_at_millis = datetime_to_ts_millis(self.start_datetime)
+        last_modified_end_at_millis = datetime_to_ts_millis(self.end_datetime)
+
+        urns = self.datahub_client.search.get_urns(
+            filter=F.and_(
+                F.entity_type(QueryUrn.ENTITY_TYPE),
+                F.custom_filter("origin", "EQUAL", [HEX_PLATFORM_URN.urn()]),
+                F.custom_filter(
+                    "lastModifiedAt",
+                    "GREATER_THAN_OR_EQUAL_TO",
+                    [str(last_modified_start_at_millis)],
+                ),
+                F.custom_filter(
+                    "lastModifiedAt",
+                    "LESS_THAN_OR_EQUAL_TO",
+                    [str(last_modified_end_at_millis)],
+                ),
+            ),
+        )
+        logger.debug(f"Get URNS by filter: {urns}")
+        return [QueryUrn.from_string(urn.urn()) for urn in urns]
+
+    def _extract_hex_metadata(self, sql_statement: str) -> Optional[Tuple[str, str]]:
+        """
+        Extract project ID and workspace name from SQL statement.
+
+        Looks for Hex metadata in SQL comments in the format:
+        -- Hex query metadata: {"project_id": "...", "project_url": "https://app.hex.tech/{workspace_name}/hex/..."}
+
+        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:
+        # -- Hex query metadata: {
+        # --   "categories": ["Scratchpad"],
+        # --   "project_id": "d73da67d-c87b-4dd8-9e7f-b79cb7f822cf",
+        # --   ...
+        # -- }
+
+        Returns:
+            A tuple of (project_id, workspace_name) if both are successfully extracted
+            None if extraction fails for any reason
+        """
+        # Extract both project_id and workspace name in a single regex operation
+        match = re.search(HEX_METADATA_PATTERN, sql_statement)
+
+        if not match:
+            return None
+
+        try:
+            project_id = match.group(1)
+            workspace_name = match.group(2)
+            return project_id, workspace_name
+        except (IndexError, AttributeError) as e:
+            self.report.warning(
+                title="Failed to extract information from Hex query metadata",
+                message="Failed to extract information from Hex query metadata will result on missing lineage",
+                context=sql_statement,
+                exc=e,
+            )
+
+        return None
+
+    def _build_query_response(
+        self,
+        query_urn: QueryUrn,
+        query_properties: Optional[QueryPropertiesClass],
+        query_subjects: Optional[QuerySubjectsClass],
+    ) -> Optional[QueryResponse]:
+        # Skip if missing required aspects
+        if (
+            not query_properties
+            or not query_properties.statement
+            or not query_properties.statement.value
+            or not query_subjects
+            or query_subjects.subjects is None  # empty list is allowed
+        ):
+            logger.debug(
+                f"Skipping query {query_urn} - missing required fields: {(query_properties, query_subjects)}"
+            )
+            self.report.filtered_out_queries_missing_metadata += 1
+            return None
+
+        # Extract hex metadata (project_id and workspace_name)
+        metadata_result = self._extract_hex_metadata(query_properties.statement.value)
+        if not metadata_result:
+            logger.debug(f"Skipping query {query_urn} - failed to extract Hex metadata")
+            self.report.filtered_out_queries_missing_metadata += 1
+            return None
+
+        hex_project_id, workspace_from_url = metadata_result
+
+        # Validate workspace
+        if workspace_from_url != self.workspace_name:
+            logger.debug(
+                f"Skipping query {query_urn} - workspace '{workspace_from_url}' doesn't match '{self.workspace_name}'"
+            )
+            self.report.filtered_out_queries_different_workspace += 1
+            return None
+
+        # Extract subjects
+        dataset_subjects: List[DatasetUrn] = []
+        schema_field_subjects: List[SchemaFieldUrn] = []
+        for subject in query_subjects.subjects:
+            if subject.entity and subject.entity.startswith("urn:li:dataset:"):
+                dataset_subjects.append(DatasetUrn.from_string(subject.entity))
+            elif subject.entity and subject.entity.startswith("urn:li:schemaField:"):
+                schema_field_subjects.append(SchemaFieldUrn.from_string(subject.entity))
+
+        if not dataset_subjects and not schema_field_subjects:
+            self.report.filtered_out_queries_no_subjects += 1
+            return None
+
+        # Create response
+        response = QueryResponse(
+            urn=query_urn,
+            hex_project_id=hex_project_id,
+            dataset_subjects=dataset_subjects,
+            schema_field_subjects=schema_field_subjects,
+        )
+        logger.debug(
+            f"Succesfully extracted {len(dataset_subjects)} dataset subjects and {len(schema_field_subjects)} schema field subjects for query {query_urn}: {dataset_subjects} {schema_field_subjects}"
+        )
+        self.report.total_queries += 1
+        self.report.total_dataset_subjects += len(dataset_subjects)
+        self.report.total_schema_field_subjects += len(schema_field_subjects)
+
+        logger.debug(
+            f"Processed query {query_urn} with Hex project ID {hex_project_id}"
+        )
+
+        return response

datahub/ingestion/source/iceberg/iceberg.py

@@ -425,23 +425,21 @@ class IcebergSource(StatefulIngestionSourceBase):
     def _get_dataset_properties_aspect(
         self, dataset_name: str, table: Table
     ) -> DatasetPropertiesClass:
-        additional_properties = {}
+        created: Optional[TimeStampClass] = None
         custom_properties = table.metadata.properties.copy()
         custom_properties["location"] = table.metadata.location
         custom_properties["format-version"] = str(table.metadata.format_version)
         custom_properties["partition-spec"] = str(self._get_partition_aspect(table))
+        last_modified: Optional[int] = table.metadata.last_updated_ms
         if table.current_snapshot():
             custom_properties["snapshot-id"] = str(table.current_snapshot().snapshot_id)
             custom_properties["manifest-list"] = table.current_snapshot().manifest_list
-            additional_properties["lastModified"] = TimeStampClass(
-                int(table.current_snapshot().timestamp_ms)
-            )
+            if not last_modified:
+                last_modified = int(table.current_snapshot().timestamp_ms)
         if "created-at" in custom_properties:
             try:
                 dt = dateutil_parser.isoparse(custom_properties["created-at"])
-                additional_properties["created"] = TimeStampClass(
-                    int(dt.timestamp() * 1000)
-                )
+                created = TimeStampClass(int(dt.timestamp() * 1000))
             except Exception as ex:
                 LOGGER.warning(
                     f"Exception while trying to parse creation date {custom_properties['created-at']}, ignoring: {ex}"
@@ -451,8 +449,10 @@ class IcebergSource(StatefulIngestionSourceBase):
             name=table.name()[-1],
             description=table.metadata.properties.get("comment", None),
             customProperties=custom_properties,
-            lastModified=additional_properties.get("lastModified"),
-            created=additional_properties.get("created"),
+            lastModified=TimeStampClass(last_modified)
+            if last_modified is not None
+            else None,
+            created=created,
             qualifiedName=dataset_name,
         )
 

datahub/ingestion/source/mlflow.py

@@ -16,7 +16,7 @@ from datahub.api.entities.dataprocess.dataprocess_instance import (
 )
 from datahub.configuration.source_common import EnvConfigMixin
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
-from datahub.emitter.mcp_builder import ContainerKey
+from datahub.emitter.mcp_builder import ExperimentKey
 from datahub.ingestion.api.common import PipelineContext
 from datahub.ingestion.api.decorators import (
     SupportStatus,
@@ -77,10 +77,6 @@ from datahub.sdk.dataset import Dataset
 T = TypeVar("T")
 
 
-class ContainerKeyWithId(ContainerKey):
-    id: str
-
-
 class MLflowConfig(StatefulIngestionConfigBase, EnvConfigMixin):
     tracking_uri: Optional[str] = Field(
         default=None,
@@ -252,7 +248,7 @@ class MLflowSource(StatefulIngestionSourceBase):
         self, experiment: Experiment
     ) -> Iterable[MetadataWorkUnit]:
         experiment_container = Container(
-            container_key=ContainerKeyWithId(
+            container_key=ExperimentKey(
                 platform=str(DataPlatformUrn(platform_name=self.platform)),
                 id=experiment.name,
             ),
@@ -470,7 +466,7 @@ class MLflowSource(StatefulIngestionSourceBase):
     def _get_run_workunits(
         self, experiment: Experiment, run: Run
     ) -> Iterable[MetadataWorkUnit]:
-        experiment_key = ContainerKeyWithId(
+        experiment_key = ExperimentKey(
             platform=str(DataPlatformUrn(self.platform)), id=experiment.name
         )
 

datahub/ingestion/source/powerbi/powerbi.py

@@ -94,7 +94,7 @@ from datahub.metadata.schema_classes import (
     UpstreamLineageClass,
     ViewPropertiesClass,
 )
-from datahub.metadata.urns import ChartUrn
+from datahub.metadata.urns import ChartUrn, DatasetUrn
 from datahub.sql_parsing.sqlglot_lineage import ColumnLineageInfo
 from datahub.utilities.dedup_list import deduplicate_list
 from datahub.utilities.urns.urn_iter import lowercase_dataset_urn
@@ -1083,6 +1083,7 @@ class Mapper:
         report: powerbi_data_classes.Report,
         chart_mcps: List[MetadataChangeProposalWrapper],
         user_mcps: List[MetadataChangeProposalWrapper],
+        dataset_edges: List[EdgeClass],
     ) -> List[MetadataChangeProposalWrapper]:
         """
         Map PowerBi report to Datahub dashboard
@@ -1104,6 +1105,7 @@ class Mapper:
             charts=chart_urn_list,
             lastModified=ChangeAuditStamps(),
             dashboardUrl=report.webUrl,
+            datasetEdges=dataset_edges,
         )
 
         info_mcp = self.new_mcp(
@@ -1197,12 +1199,23 @@ class Mapper:
         ds_mcps = self.to_datahub_dataset(report.dataset, workspace)
         chart_mcps = self.pages_to_chart(report.pages, workspace, ds_mcps)
 
+        # collect all upstream datasets; using a set to retain unique urns
+        dataset_urns = {
+            dataset.entityUrn
+            for dataset in ds_mcps
+            if dataset.entityType == DatasetUrn.ENTITY_TYPE and dataset.entityUrn
+        }
+        dataset_edges = [
+            EdgeClass(destinationUrn=dataset_urn) for dataset_urn in dataset_urns
+        ]
+
         # Let's convert report to datahub dashboard
         report_mcps = self.report_to_dashboard(
             workspace=workspace,
             report=report,
             chart_mcps=chart_mcps,
             user_mcps=user_mcps,
+            dataset_edges=dataset_edges,
         )
 
         # Now add MCPs in sequence

datahub/ingestion/source/sql/trino.py

@@ -128,9 +128,10 @@ def get_table_comment(self, connection, table_name: str, schema: str = None, **k
         if catalog_name is None:
             raise exc.NoSuchTableError("catalog is required in connection")
         connector_name = get_catalog_connector_name(connection.engine, catalog_name)
-        if connector_name is None:
-            return {}
-        if connector_name in PROPERTIES_TABLE_SUPPORTED_CONNECTORS:
+        if (
+            connector_name is not None
+            and connector_name in PROPERTIES_TABLE_SUPPORTED_CONNECTORS
+        ):
             properties_table = self._get_full_table(f"{table_name}$properties", schema)
             query = f"SELECT * FROM {properties_table}"
             row = connection.execute(sql.text(query)).fetchone()

datahub/ingestion/source/state/stale_entity_removal_handler.py

@@ -45,7 +45,6 @@ class StatefulStaleMetadataRemovalConfig(StatefulIngestionConfig):
         description="Prevents large amount of soft deletes & the state from committing from accidental changes to the source configuration if the relative change percent in entities compared to the previous state is above the 'fail_safe_threshold'.",
         le=100.0,
         ge=0.0,
-        hidden_from_docs=True,
     )