acryl-datahub 1.3.0.1rc6__py3-none-any.whl → 1.3.0.1rc7__py3-none-any.whl

datahub/ingestion/source/fivetran/fivetran.py

@@ -1,5 +1,6 @@
 import logging
 from typing import Dict, Iterable, List, Optional, Union
+from urllib.parse import urlparse
 
 import datahub.emitter.mce_builder as builder
 from datahub.api.entities.datajob import DataJob as DataJobV1
@@ -22,6 +23,7 @@ from datahub.ingestion.api.source import (
     StructuredLogCategory,
 )
 from datahub.ingestion.api.workunit import MetadataWorkUnit
+from datahub.ingestion.source.common.subtypes import DatasetSubTypes
 from datahub.ingestion.source.fivetran.config import (
     KNOWN_DATA_PLATFORM_MAPPING,
     Constant,
@@ -35,29 +37,39 @@ from datahub.ingestion.source.fivetran.fivetran_query import (
     MAX_JOBS_PER_CONNECTOR,
     MAX_TABLE_LINEAGE_PER_CONNECTOR,
 )
+from datahub.ingestion.source.fivetran.fivetran_rest_api import FivetranAPIClient
+from datahub.ingestion.source.fivetran.response_models import FivetranConnectionDetails
 from datahub.ingestion.source.state.stale_entity_removal_handler import (
     StaleEntityRemovalHandler,
 )
 from datahub.ingestion.source.state.stateful_ingestion_base import (
     StatefulIngestionSourceBase,
 )
+from datahub.metadata.com.linkedin.pegasus2avro.common import AuditStamp
 from datahub.metadata.com.linkedin.pegasus2avro.dataset import (
     FineGrainedLineage,
     FineGrainedLineageDownstreamType,
     FineGrainedLineageUpstreamType,
+    UpstreamLineage,
+)
+from datahub.metadata.schema_classes import (
+    DatasetLineageTypeClass,
+    UpstreamClass,
 )
 from datahub.metadata.urns import CorpUserUrn, DataFlowUrn, DatasetUrn
 from datahub.sdk.dataflow import DataFlow
 from datahub.sdk.datajob import DataJob
+from datahub.sdk.dataset import Dataset
 from datahub.sdk.entity import Entity
 
 # Logger instance
 logger = logging.getLogger(__name__)
+CORPUSER_DATAHUB = "urn:li:corpuser:datahub"
 
 
 @platform_name("Fivetran")
 @config_class(FivetranSourceConfig)
-@support_status(SupportStatus.INCUBATING)
+@support_status(SupportStatus.CERTIFIED)
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")
 @capability(
     SourceCapability.LINEAGE_FINE,
@@ -76,8 +88,12 @@ class FivetranSource(StatefulIngestionSourceBase):
         super().__init__(config, ctx)
         self.config = config
         self.report = FivetranSourceReport()
-
         self.audit_log = FivetranLogAPI(self.config.fivetran_log_config)
+        self.api_client: Optional[FivetranAPIClient] = None
+        self._connection_details_cache: Dict[str, FivetranConnectionDetails] = {}
+
+        if self.config.api_config:
+            self.api_client = FivetranAPIClient(self.config.api_config)
 
     def _extend_lineage(self, connector: Connector, datajob: DataJob) -> Dict[str, str]:
         input_dataset_urn_list: List[Union[str, DatasetUrn]] = []
@@ -131,17 +147,43 @@ class FivetranSource(StatefulIngestionSourceBase):
                 if source_details.include_schema_in_urn
                 else lineage.source_table.split(".", 1)[1]
             )
-            input_dataset_urn = DatasetUrn.create_from_ids(
-                platform_id=source_details.platform,
-                table_name=(
-                    f"{source_details.database.lower()}.{source_table}"
-                    if source_details.database
-                    else source_table
-                ),
-                env=source_details.env,
-                platform_instance=source_details.platform_instance,
-            )
-            input_dataset_urn_list.append(input_dataset_urn)
+            input_dataset_urn: Optional[DatasetUrn] = None
+            # Special Handling for Google Sheets Connectors
+            if connector.connector_type == Constant.GOOGLE_SHEETS_CONNECTOR_TYPE:
+                # Get Google Sheet dataset details from Fivetran API
+                # This is cached in the api_client
+                gsheets_conn_details: Optional[FivetranConnectionDetails] = (
+                    self._get_connection_details_by_id(connector.connector_id)
+                )
+
+                if gsheets_conn_details:
+                    input_dataset_urn = DatasetUrn.create_from_ids(
+                        platform_id=Constant.GOOGLE_SHEETS_CONNECTOR_TYPE,
+                        table_name=self._get_gsheet_named_range_dataset_id(
+                            gsheets_conn_details
+                        ),
+                        env=source_details.env,
+                    )
+                else:
+                    self.report.warning(
+                        title="Failed to extract lineage for Google Sheets Connector",
+                        message="Unable to extract lineage for Google Sheets Connector, as the connector details are not available from Fivetran API.",
+                        context=f"{connector.connector_name} (connector_id: {connector.connector_id})",
+                    )
+            else:
+                input_dataset_urn = DatasetUrn.create_from_ids(
+                    platform_id=source_details.platform,
+                    table_name=(
+                        f"{source_details.database.lower()}.{source_table}"
+                        if source_details.database
+                        else source_table
+                    ),
+                    env=source_details.env,
+                    platform_instance=source_details.platform_instance,
+                )
+
+            if input_dataset_urn:
+                input_dataset_urn_list.append(input_dataset_urn)
 
             destination_table = (
                 lineage.destination_table
@@ -262,6 +304,67 @@ class FivetranSource(StatefulIngestionSourceBase):
             clone_outlets=True,
         )
 
+    def _get_connection_details_by_id(
+        self, connection_id: str
+    ) -> Optional[FivetranConnectionDetails]:
+        if self.api_client is None:
+            self.report.warning(
+                title="Fivetran API client is not initialized",
+                message="Google Sheets Connector details cannot be extracted, as Fivetran API client is not initialized.",
+                context=f"connector_id: {connection_id}",
+            )
+            return None
+
+        if connection_id in self._connection_details_cache:
+            return self._connection_details_cache[connection_id]
+
+        try:
+            self.report.report_fivetran_rest_api_call_count()
+            conn_details = self.api_client.get_connection_details_by_id(connection_id)
+            # Update Cache
+            if conn_details:
+                self._connection_details_cache[connection_id] = conn_details
+
+            return conn_details
+        except Exception as e:
+            self.report.warning(
+                title="Failed to get connection details for Google Sheets Connector",
+                message=f"Exception occurred while getting connection details from Fivetran API. {e}",
+                context=f"connector_id: {connection_id}",
+            )
+            return None
+
+    def _get_gsheet_sheet_id_from_url(
+        self, gsheets_conn_details: FivetranConnectionDetails
+    ) -> str:
+        # Extracting the sheet_id (1A82PdLAE7NXLLb5JcLPKeIpKUMytXQba5Z-Ei-mbXLo) from the sheet_id url
+        # "https://docs.google.com/spreadsheets/d/1A82PdLAE7NXLLb5JcLPKeIpKUMytXQba5Z-Ei-mbXLo/edit?gid=0#gid=0",
+        try:
+            parsed = urlparse(gsheets_conn_details.config.sheet_id)
+            # Example: https://docs.google.com/spreadsheets/d/<spreadsheetId>/edit
+            parts = parsed.path.split("/")
+            return parts[3] if len(parts) > 2 else ""
+        except Exception as e:
+            logger.warning(
+                f"Failed to extract sheet_id from the sheet_id url: {gsheets_conn_details.config.sheet_id}, {e}"
+            )
+
+        return ""
+
+    def _get_gsheet_named_range_dataset_id(
+        self, gsheets_conn_details: FivetranConnectionDetails
+    ) -> str:
+        sheet_id = self._get_gsheet_sheet_id_from_url(gsheets_conn_details)
+        named_range_id = (
+            f"{sheet_id}.{gsheets_conn_details.config.named_range}"
+            if sheet_id
+            else gsheets_conn_details.config.named_range
+        )
+        logger.debug(
+            f"Using gsheet_named_range_dataset_id: {named_range_id} for connector: {gsheets_conn_details.id}"
+        )
+        return named_range_id
+
     def _get_dpi_workunits(
         self, job: Job, dpi: DataProcessInstance
     ) -> Iterable[MetadataWorkUnit]:
@@ -295,6 +398,74 @@ class FivetranSource(StatefulIngestionSourceBase):
         self, connector: Connector
     ) -> Iterable[Union[MetadataWorkUnit, Entity]]:
         self.report.report_connectors_scanned()
+
+        """
+        -------------------------------------------------------
+        Special Handling for Google Sheets Connectors
+        -------------------------------------------------------
+        Google Sheets source is not supported by Datahub yet.   
+        As a workaround, we are emitting a dataset entity for the Google Sheet
+        and adding it to the lineage. This workaround needs to be removed once 
+        Datahub supports Google Sheets source natively.
+        -------------------------------------------------------
+        """
+        if connector.connector_type == Constant.GOOGLE_SHEETS_CONNECTOR_TYPE:
+            # Get Google Sheet dataset details from Fivetran API
+            gsheets_conn_details: Optional[FivetranConnectionDetails] = (
+                self._get_connection_details_by_id(connector.connector_id)
+            )
+
+            if gsheets_conn_details:
+                gsheets_dataset = Dataset(
+                    name=self._get_gsheet_sheet_id_from_url(gsheets_conn_details),
+                    platform=Constant.GOOGLE_SHEETS_CONNECTOR_TYPE,
+                    env=self.config.env,
+                    display_name=self._get_gsheet_sheet_id_from_url(
+                        gsheets_conn_details
+                    ),
+                    external_url=gsheets_conn_details.config.sheet_id,
+                    created=gsheets_conn_details.created_at,
+                    last_modified=gsheets_conn_details.source_sync_details.last_synced,
+                    subtype=DatasetSubTypes.GOOGLE_SHEETS,
+                    custom_properties={
+                        "ingested_by": "fivetran source",
+                        "connector_id": gsheets_conn_details.id,
+                    },
+                )
+                gsheets_named_range_dataset = Dataset(
+                    name=self._get_gsheet_named_range_dataset_id(gsheets_conn_details),
+                    platform=Constant.GOOGLE_SHEETS_CONNECTOR_TYPE,
+                    env=self.config.env,
+                    display_name=gsheets_conn_details.config.named_range,
+                    external_url=gsheets_conn_details.config.sheet_id,
+                    created=gsheets_conn_details.created_at,
+                    last_modified=gsheets_conn_details.source_sync_details.last_synced,
+                    subtype=DatasetSubTypes.GOOGLE_SHEETS_NAMED_RANGE,
+                    custom_properties={
+                        "ingested_by": "fivetran source",
+                        "connector_id": gsheets_conn_details.id,
+                    },
+                    upstreams=UpstreamLineage(
+                        upstreams=[
+                            UpstreamClass(
+                                dataset=str(gsheets_dataset.urn),
+                                type=DatasetLineageTypeClass.VIEW,
+                                auditStamp=AuditStamp(
+                                    time=int(
+                                        gsheets_conn_details.created_at.timestamp()
+                                        * 1000
+                                    ),
+                                    actor=CORPUSER_DATAHUB,
+                                ),
+                            )
+                        ],
+                        fineGrainedLineages=None,
+                    ),
+                )
+
+                yield gsheets_dataset
+                yield gsheets_named_range_dataset
+
         # Create dataflow entity with same name as connector name
         dataflow = self._generate_dataflow_from_connector(connector)
         yield dataflow

datahub/ingestion/source/fivetran/fivetran_log_api.py

@@ -9,6 +9,7 @@ from sqlalchemy import create_engine
 
 from datahub.configuration.common import AllowDenyPattern, ConfigurationError
 from datahub.ingestion.source.fivetran.config import (
+    DISABLE_COL_LINEAGE_FOR_CONNECTOR_TYPES,
     Constant,
     FivetranLogConfig,
     FivetranSourceReport,
@@ -112,7 +113,11 @@ class FivetranLogAPI:
         """
         Returns dict of column lineage metadata with key as (<SOURCE_TABLE_ID>, <DESTINATION_TABLE_ID>)
         """
-        all_column_lineage = defaultdict(list)
+        all_column_lineage: Dict[Tuple[str, str], List] = defaultdict(list)
+
+        if not connector_ids:
+            return dict(all_column_lineage)
+
         column_lineage_result = self._query(
             self.fivetran_log_query.get_column_lineage_query(
                 connector_ids=connector_ids
@@ -130,7 +135,11 @@ class FivetranLogAPI:
         """
         Returns dict of table lineage metadata with key as 'CONNECTOR_ID'
         """
-        connectors_table_lineage_metadata = defaultdict(list)
+        connectors_table_lineage_metadata: Dict[str, List] = defaultdict(list)
+
+        if not connector_ids:
+            return dict(connectors_table_lineage_metadata)
+
         table_lineage_result = self._query(
             self.fivetran_log_query.get_table_lineage_query(connector_ids=connector_ids)
         )
@@ -246,9 +255,15 @@ class FivetranLogAPI:
         return self._get_users().get(user_id)
 
     def _fill_connectors_lineage(self, connectors: List[Connector]) -> None:
-        connector_ids = [connector.connector_id for connector in connectors]
-        table_lineage_metadata = self._get_table_lineage_metadata(connector_ids)
-        column_lineage_metadata = self._get_column_lineage_metadata(connector_ids)
+        # Create 2 filtered connector_ids lists - one for table lineage and one for column lineage
+        tll_connector_ids: List[str] = []
+        cll_connector_ids: List[str] = []
+        for connector in connectors:
+            tll_connector_ids.append(connector.connector_id)
+            if connector.connector_type not in DISABLE_COL_LINEAGE_FOR_CONNECTOR_TYPES:
+                cll_connector_ids.append(connector.connector_id)
+        table_lineage_metadata = self._get_table_lineage_metadata(tll_connector_ids)
+        column_lineage_metadata = self._get_column_lineage_metadata(cll_connector_ids)
         for connector in connectors:
             connector.lineage = self._extract_connector_lineage(
                 table_lineage_result=table_lineage_metadata.get(connector.connector_id),

datahub/ingestion/source/fivetran/fivetran_rest_api.py

@@ -0,0 +1,65 @@
+import logging
+
+import requests
+from requests.adapters import HTTPAdapter
+from urllib3.util import Retry
+
+from datahub.ingestion.source.fivetran.config import (
+    FivetranAPIConfig,
+)
+from datahub.ingestion.source.fivetran.response_models import FivetranConnectionDetails
+
+logger = logging.getLogger(__name__)
+
+# Retry configuration constants
+RETRY_MAX_TIMES = 3
+RETRY_STATUS_CODES = [429, 500, 502, 503, 504]
+RETRY_BACKOFF_FACTOR = 1
+RETRY_ALLOWED_METHODS = ["GET"]
+
+
+class FivetranAPIClient:
+    """Client for interacting with the Fivetran REST API."""
+
+    def __init__(self, config: FivetranAPIConfig) -> None:
+        self.config = config
+        self._session = self._create_session()
+
+    def _create_session(self) -> requests.Session:
+        """
+        Create a session with retry logic and basic authentication
+        """
+        requests_session = requests.Session()
+
+        # Configure retry strategy for transient failures
+        retry_strategy = Retry(
+            total=RETRY_MAX_TIMES,
+            backoff_factor=RETRY_BACKOFF_FACTOR,
+            status_forcelist=RETRY_STATUS_CODES,
+            allowed_methods=RETRY_ALLOWED_METHODS,
+            raise_on_status=True,
+        )
+
+        adapter = HTTPAdapter(max_retries=retry_strategy)
+        requests_session.mount("http://", adapter)
+        requests_session.mount("https://", adapter)
+
+        # Set up basic authentication
+        requests_session.auth = (self.config.api_key, self.config.api_secret)
+        requests_session.headers.update(
+            {
+                "Content-Type": "application/json",
+                "Accept": "application/json",
+            }
+        )
+        return requests_session
+
+    def get_connection_details_by_id(
+        self, connection_id: str
+    ) -> FivetranConnectionDetails:
+        """Get details for a specific connection."""
+        connection_details = self._session.get(
+            f"{self.config.base_url}/v1/connections/{connection_id}",
+            timeout=self.config.request_timeout_sec,
+        )
+        return FivetranConnectionDetails(**connection_details.json().get("data", {}))

datahub/ingestion/source/fivetran/response_models.py

@@ -0,0 +1,97 @@
+import datetime
+from typing import Dict, List
+
+from pydantic import BaseModel
+
+
+class FivetranConnectionWarnings(BaseModel):
+    code: str  # Warning Code
+    message: str  # Warning Message
+    details: Dict  # Warning Details
+
+
+class FivetranConnectionStatus(BaseModel):
+    setup_state: str  # Setup State
+    schema_status: str  # Schema Status
+    sync_state: str  # Sync State
+    update_state: str  # Update State
+    is_historical_sync: bool  # Is Historical Sync
+    warnings: List[FivetranConnectionWarnings]  # Warnings
+
+
+class FivetranConnectionConfig(BaseModel):
+    # Note: Connection Config is different for different connectors
+    auth_type: str  # Auth Type
+    sheet_id: str  # Sheet ID - URL to the Google Sheet
+    named_range: str  # Named Range
+
+
+class FivetranConnectionSourceSyncDetails(BaseModel):
+    last_synced: datetime.datetime  # Last Synced
+
+
+class FivetranConnectionDetails(BaseModel):
+    """
+    Note: This reponse class only captures fields that are relevant to the Google Sheets Connector
+    """
+
+    id: str  # Source ID
+    group_id: str  # Destination ID
+    service: str  # Connector Type
+    created_at: datetime.datetime
+    succeeded_at: datetime.datetime
+    paused: bool  # Paused Status
+    sync_frequency: int  # Sync Frequency (minutes)
+    status: FivetranConnectionStatus  # Status
+    config: FivetranConnectionConfig  # Connection Config
+    source_sync_details: FivetranConnectionSourceSyncDetails  # Source Sync Details
+
+    """
+    # Sample Response for Google Sheets Connector
+    {
+        "code": "Success",
+        "data": {
+            "id": "dialectical_remindful",
+            "group_id": "empties_classification",
+            "service": "google_sheets",
+            "service_version": 1,
+            "schema": "fivetran_google_sheets.fivetran_google_sheets",
+            "connected_by": "sewn_restrained",
+            "created_at": "2025-10-06T17:53:01.554289Z",
+            "succeeded_at": "2025-10-06T22:55:45.275000Z",
+            "failed_at": null,
+            "paused": true,
+            "pause_after_trial": false,
+            "sync_frequency": 360,
+            "data_delay_threshold": 0,
+            "data_delay_sensitivity": "NORMAL",
+            "private_link_id": null,
+            "networking_method": "Directly",
+            "proxy_agent_id": null,
+            "schedule_type": "auto",
+            "status": {
+                "setup_state": "connected",
+                "schema_status": "ready",
+                "sync_state": "paused",
+                "update_state": "on_schedule",
+                "is_historical_sync": false,
+                "tasks": [],
+                "warnings": [
+                    {
+                        "code": "snowflake_discontinuing_password_auth",
+                        "message": "Snowflake is discontinuing username/password authentication",
+                        "details": {}
+                    }
+                ]
+            },
+            "config": {
+                "auth_type": "ServiceAccount",
+                "sheet_id": "https://docs.google.com/spreadsheets/d/1A82PdLAE7NXLLb5JcLPKeIpKUMytXQba5Z-Ei-mbXLo/edit?gid=0#gid=0",
+                "named_range": "Fivetran_Test_Range"
+            },
+            "source_sync_details": {
+                "last_synced": "2025-10-06T22:55:27.371Z"
+            }
+        }
+    }
+    """

datahub/ingestion/source/hex/hex.py

@@ -178,7 +178,7 @@ class HexReport(
 
 @platform_name("Hex")
 @config_class(HexSourceConfig)
-@support_status(SupportStatus.TESTING)
+@support_status(SupportStatus.INCUBATING)
 @capability(SourceCapability.DESCRIPTIONS, "Supported by default")
 @capability(SourceCapability.OWNERSHIP, "Supported by default")
 @capability(SourceCapability.PLATFORM_INSTANCE, "Enabled by default")

datahub/ingestion/source/iceberg/iceberg.py

@@ -118,7 +118,7 @@ logging.getLogger("azure.core.pipeline.policies.http_logging_policy").setLevel(
 
 
 @platform_name("Iceberg")
-@support_status(SupportStatus.TESTING)
+@support_status(SupportStatus.INCUBATING)
 @config_class(IcebergSourceConfig)
 @capability(
     SourceCapability.PLATFORM_INSTANCE,

datahub/ingestion/source/metabase.py

@@ -52,6 +52,7 @@ from datahub.metadata.schema_classes import (
     ChartQueryTypeClass,
     ChartTypeClass,
     DashboardInfoClass,
+    EdgeClass,
     OwnerClass,
     OwnershipClass,
     OwnershipTypeClass,
@@ -338,19 +339,25 @@ class MetabaseSource(StatefulIngestionSourceBase):
             lastModified=AuditStamp(time=modified_ts, actor=modified_actor),
         )
 
-        chart_urns = []
+        # Convert chart URNs to chart edges (instead of deprecated charts field)
+        chart_edges = []
         cards_data = dashboard_details.get("dashcards", {})
         for card_info in cards_data:
             card_id = card_info.get("card").get("id", "")
             if not card_id:
                 continue  # most likely a virtual card without an id (text or heading), not relevant.
             chart_urn = builder.make_chart_urn(self.platform, str(card_id))
-            chart_urns.append(chart_urn)
+            chart_edges.append(
+                EdgeClass(
+                    destinationUrn=chart_urn,
+                    lastModified=last_modified.lastModified,
+                )
+            )
 
         dashboard_info_class = DashboardInfoClass(
             description=description,
             title=title,
-            charts=chart_urns,
+            chartEdges=chart_edges,
             lastModified=last_modified,
             dashboardUrl=f"{self.config.display_uri}/dashboard/{dashboard_id}",
             customProperties={},
@@ -488,13 +495,25 @@ class MetabaseSource(StatefulIngestionSourceBase):
         datasource_urn = self.get_datasource_urn(card_details)
         custom_properties = self.construct_card_custom_properties(card_details)
 
+        input_edges = (
+            [
+                EdgeClass(
+                    destinationUrn=urn,
+                    lastModified=last_modified.lastModified,
+                )
+                for urn in datasource_urn
+            ]
+            if datasource_urn
+            else None
+        )
+
         chart_info = ChartInfoClass(
             type=chart_type,
             description=description,
             title=title,
             lastModified=last_modified,
             chartUrl=f"{self.config.display_uri}/card/{card_id}",
-            inputs=datasource_urn,
+            inputEdges=input_edges,
             customProperties=custom_properties,
         )
         chart_snapshot.aspects.append(chart_info)

datahub/ingestion/source/mlflow.py

@@ -136,7 +136,7 @@ class MLflowRegisteredModelStageInfo:
 
 @platform_name("MLflow")
 @config_class(MLflowConfig)
-@support_status(SupportStatus.TESTING)
+@support_status(SupportStatus.INCUBATING)
 @capability(
     SourceCapability.DESCRIPTIONS,
     "Extract descriptions for MLflow Registered Models and Model Versions",

datahub/ingestion/source/s3/source.py

@@ -188,7 +188,7 @@ class TableData:
 
 @platform_name("S3 / Local Files", id="s3")
 @config_class(DataLakeSourceConfig)
-@support_status(SupportStatus.INCUBATING)
+@support_status(SupportStatus.CERTIFIED)
 @capability(
     SourceCapability.CONTAINERS,
     "Enabled by default",

datahub/ingestion/source/salesforce.py

@@ -527,7 +527,7 @@ class SalesforceApi:
 
 @platform_name("Salesforce")
 @config_class(SalesforceConfig)
-@support_status(SupportStatus.INCUBATING)
+@support_status(SupportStatus.CERTIFIED)
 @capability(
     capability_name=SourceCapability.PLATFORM_INSTANCE,
     description="Can be equivalent to Salesforce organization",

datahub/ingestion/source/slack/slack.py

@@ -245,7 +245,7 @@ DATA_PLATFORM_SLACK_URN: str = builder.make_data_platform_urn(PLATFORM_NAME)
 
 @platform_name("Slack")
 @config_class(SlackSourceConfig)
-@support_status(SupportStatus.TESTING)
+@support_status(SupportStatus.CERTIFIED)
 class SlackSource(StatefulIngestionSourceBase):
     def __init__(self, ctx: PipelineContext, config: SlackSourceConfig):
         super().__init__(config, ctx)

datahub/ingestion/source/snowflake/snowflake_queries.py

@@ -21,6 +21,7 @@ from datahub.configuration.time_window_config import (
 )
 from datahub.ingestion.api.closeable import Closeable
 from datahub.ingestion.api.common import PipelineContext
+from datahub.ingestion.api.decorators import SupportStatus, config_class, support_status
 from datahub.ingestion.api.report import Report
 from datahub.ingestion.api.source import Source, SourceReport
 from datahub.ingestion.api.source_helpers import auto_workunit
@@ -750,6 +751,8 @@ class SnowflakeQueriesExtractor(SnowflakeStructuredReportMixin, Closeable):
         self._exit_stack.close()
 
 
+@support_status(SupportStatus.CERTIFIED)
+@config_class(SnowflakeQueriesSourceConfig)
 class SnowflakeQueriesSource(Source):
     def __init__(self, ctx: PipelineContext, config: SnowflakeQueriesSourceConfig):
         self.ctx = ctx

datahub/ingestion/source/snowflake/snowflake_summary.py

@@ -59,7 +59,7 @@ class SnowflakeSummaryReport(SourceReport, BaseTimeWindowReport):
 
 
 @config_class(SnowflakeSummaryConfig)
-@support_status(SupportStatus.INCUBATING)
+@support_status(SupportStatus.CERTIFIED)
 class SnowflakeSummarySource(Source):
     def __init__(self, ctx: PipelineContext, config: SnowflakeSummaryConfig):
         super().__init__(ctx)

datahub/ingestion/source/sql_queries.py

@@ -93,7 +93,7 @@ class SqlQueriesSourceReport(SourceReport):
     sql_aggregator: Optional[SqlAggregatorReport] = None
 
 
-@platform_name("SQL Queries")
+@platform_name("SQL Queries", id="sql-queries")
 @config_class(SqlQueriesSourceConfig)
 @support_status(SupportStatus.INCUBATING)
 @capability(SourceCapability.LINEAGE_COARSE, "Parsed from SQL queries")

datahub/ingestion/source/unity/source.py

@@ -176,7 +176,7 @@ logger: logging.Logger = logging.getLogger(__name__)
     supported=True,
 )
 @capability(SourceCapability.TEST_CONNECTION, "Enabled by default")
-@support_status(SupportStatus.INCUBATING)
+@support_status(SupportStatus.CERTIFIED)
 class UnityCatalogSource(StatefulIngestionSourceBase, TestableSource):
     """
     This plugin extracts the following metadata from Databricks Unity Catalog:

datahub/ingestion/source/vertexai/vertexai.py

@@ -145,7 +145,7 @@ class PipelineMetadata:
 
 @platform_name("Vertex AI", id="vertexai")
 @config_class(VertexAIConfig)
-@support_status(SupportStatus.TESTING)
+@support_status(SupportStatus.INCUBATING)
 @capability(
     SourceCapability.DESCRIPTIONS,
     "Extract descriptions for Vertex AI Registered Models and Model Versions",