acryl-datahub 1.0.0.2rc4__py3-none-any.whl → 1.0.0.3__py3-none-any.whl

datahub/ingestion/graph/links.py

@@ -0,0 +1,53 @@
+from typing import Optional
+
+import datahub.metadata.urns as urns
+from datahub.utilities.urns.urn import guess_entity_type
+
+_url_prefixes = {
+    # Atypical mappings.
+    urns.DataJobUrn.ENTITY_TYPE: "tasks",
+    urns.DataFlowUrn.ENTITY_TYPE: "pipelines",
+    urns.CorpUserUrn.ENTITY_TYPE: "user",
+    urns.CorpGroupUrn.ENTITY_TYPE: "group",
+    # Normal mappings - matches the entity type.
+    urns.ChartUrn.ENTITY_TYPE: "chart",
+    urns.ContainerUrn.ENTITY_TYPE: "container",
+    urns.DataProductUrn.ENTITY_TYPE: "dataProduct",
+    urns.DatasetUrn.ENTITY_TYPE: "dataset",
+    urns.DashboardUrn.ENTITY_TYPE: "dashboard",
+    urns.DomainUrn.ENTITY_TYPE: "domain",
+    urns.GlossaryNodeUrn.ENTITY_TYPE: "glossaryNode",
+    urns.GlossaryTermUrn.ENTITY_TYPE: "glossaryTerm",
+    urns.TagUrn.ENTITY_TYPE: "tag",
+}
+
+
+def make_url_for_urn(
+    frontend_base_url: str,
+    entity_urn: str,
+    *,
+    tab: Optional[str] = None,
+) -> str:
+    """Build the public-facing URL for an entity urn.
+
+    Args:
+        frontend_url: The public-facing base url of the frontend.
+        entity_urn: The urn of the entity to get the url for.
+        tab: The tab to deep link into. If not provided, the default tab for the entity will be shown.
+
+    Returns:
+        The public-facing url for the entity.
+
+    Examples:
+        >>> make_url_for_urn("https://demo.datahub.com", "urn:li:container:b41c14bc5cb3ccfbb0433c8cbdef2992", tab="Contents")
+        'https://demo.datahub.com/container/urn:li:container:b41c14bc5cb3ccfbb0433c8cbdef2992/Contents'
+        >>> make_url_for_urn("https://demo.datahub.com", "urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.adoption.actuating,PROD)")
+        'https://demo.datahub.com/dataset/urn:li:dataset:(urn:li:dataPlatform:snowflake,long_tail_companions.adoption.actuating,PROD)/'
+    """
+    entity_type = guess_entity_type(entity_urn)
+
+    url_prefix = _url_prefixes.get(entity_type, entity_type)
+    url = f"{frontend_base_url}/{url_prefix}/{entity_urn}/"
+    if tab:
+        url += f"{tab}"
+    return url

datahub/ingestion/run/pipeline.py

@@ -31,6 +31,7 @@ from datahub.ingestion.api.source import Extractor, Source
 from datahub.ingestion.api.transform import Transformer
 from datahub.ingestion.extractor.extractor_registry import extractor_registry
 from datahub.ingestion.graph.client import DataHubGraph, get_default_graph
+from datahub.ingestion.graph.config import ClientMode
 from datahub.ingestion.reporting.reporting_provider_registry import (
     reporting_provider_registry,
 )
@@ -136,9 +137,8 @@ class CliReport(Report):
 
 
 def _make_default_rest_sink(ctx: PipelineContext) -> DatahubRestSink:
-    graph = get_default_graph()
+    graph = get_default_graph(ClientMode.INGESTION)
     sink_config = graph._make_rest_sink_config()
-
     return DatahubRestSink(ctx, sink_config)
 
 
@@ -175,6 +175,7 @@ class Pipeline:
             self.graph: Optional[DataHubGraph] = None
             with _add_init_error_context("connect to DataHub"):
                 if self.config.datahub_api:
+                    self.config.datahub_api.client_mode = ClientMode.INGESTION
                     self.graph = exit_stack.enter_context(
                         DataHubGraph(self.config.datahub_api)
                     )
@@ -555,18 +556,20 @@ class Pipeline:
     def raise_from_status(self, raise_warnings: bool = False) -> None:
         if self.source.get_report().failures:
             raise PipelineExecutionError(
-                "Source reported errors", self.source.get_report()
+                "Source reported errors", self.source.get_report().failures
             )
         if self.sink.get_report().failures:
-            raise PipelineExecutionError("Sink reported errors", self.sink.get_report())
+            raise PipelineExecutionError(
+                "Sink reported errors", self.sink.get_report().failures
+            )
         if raise_warnings:
             if self.source.get_report().warnings:
                 raise PipelineExecutionError(
-                    "Source reported warnings", self.source.get_report()
+                    "Source reported warnings", self.source.get_report().warnings
                 )
             if self.sink.get_report().warnings:
                 raise PipelineExecutionError(
-                    "Sink reported warnings", self.sink.get_report()
+                    "Sink reported warnings", self.sink.get_report().warnings
                 )
 
     def log_ingestion_stats(self) -> None:

datahub/ingestion/run/pipeline_config.py

@@ -7,7 +7,7 @@ from typing import Any, Dict, List, Optional
 from pydantic import Field, validator
 
 from datahub.configuration.common import ConfigModel, DynamicTypedConfig
-from datahub.ingestion.graph.client import DatahubClientConfig
+from datahub.ingestion.graph.config import DatahubClientConfig
 from datahub.ingestion.sink.file import FileSinkConfig
 
 logger = logging.getLogger(__name__)

datahub/ingestion/sink/datahub_rest.py

@@ -34,7 +34,7 @@ from datahub.ingestion.api.sink import (
     WriteCallback,
 )
 from datahub.ingestion.api.workunit import MetadataWorkUnit
-from datahub.ingestion.graph.client import DatahubClientConfig
+from datahub.ingestion.graph.config import ClientMode, DatahubClientConfig
 from datahub.metadata.com.linkedin.pegasus2avro.mxe import (
     MetadataChangeEvent,
     MetadataChangeProposal,
@@ -140,11 +140,7 @@ class DatahubRestSink(Sink[DatahubRestSinkConfig, DataHubRestSinkReport]):
                 f"💥 Failed to connect to DataHub with {repr(self.emitter)}"
             ) from exc
 
-        self.report.gms_version = (
-            gms_config.get("versions", {})
-            .get("acryldata/datahub", {})
-            .get("version", None)
-        )
+        self.report.gms_version = gms_config.service_version
         self.report.mode = self.config.mode
         self.report.max_threads = self.config.max_threads
         logger.debug("Setting env variables to override config")
@@ -180,6 +176,8 @@ class DatahubRestSink(Sink[DatahubRestSinkConfig, DataHubRestSinkReport]):
             disable_ssl_verification=config.disable_ssl_verification,
             openapi_ingestion=config.endpoint == RestSinkEndpoint.OPENAPI,
             default_trace_mode=config.default_trace_mode == RestTraceMode.ENABLED,
+            client_mode=config.client_mode,
+            datahub_component=config.datahub_component,
         )
 
     @property
@@ -190,6 +188,7 @@ class DatahubRestSink(Sink[DatahubRestSinkConfig, DataHubRestSinkReport]):
         # https://github.com/psf/requests/issues/1871#issuecomment-32751346
         thread_local = self._emitter_thread_local
         if not hasattr(thread_local, "emitter"):
+            self.config.client_mode = ClientMode.INGESTION
             thread_local.emitter = DatahubRestSink._make_emitter(self.config)
         return thread_local.emitter
 

datahub/ingestion/source/apply/datahub_apply.py

@@ -18,6 +18,7 @@ from datahub.ingestion.api.source import MetadataWorkUnitProcessor, Source, Sour
 from datahub.ingestion.api.source_helpers import auto_workunit_reporter
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.graph.client import DataHubGraph, get_default_graph
+from datahub.ingestion.graph.config import ClientMode
 from datahub.metadata.schema_classes import (
     DomainsClass,
     GlossaryTermAssociationClass,
@@ -48,7 +49,7 @@ def apply_association_to_container(
     """
     urns: List[str] = [container_urn]
     if not graph:
-        graph = get_default_graph()
+        graph = get_default_graph(ClientMode.INGESTION)
     logger.info(f"Using {graph}")
     urns.extend(
         graph.get_urns_by_filter(

datahub/ingestion/source/aws/sagemaker_processors/feature_groups.py

@@ -205,7 +205,7 @@ class FeatureGroupProcessor:
                     textwrap.dedent(
                         f"""Note: table {full_table_name} is an AWS Glue object. This source does not ingest all metadata for Glue tables.
                         To view full table metadata, run Glue ingestion
-                        (see https://datahubproject.io/docs/generated/ingestion/sources/glue)"""
+                        (see https://docs.datahub.com/docs/generated/ingestion/sources/glue)"""
                     )
                 )
 

datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -270,29 +270,30 @@ class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
             ):
                 return
 
-            with self.report.new_stage(f"*: {QUERIES_EXTRACTION}"):
-                with BigQueryQueriesExtractor(
-                    connection=self.config.get_bigquery_client(),
-                    schema_api=self.bq_schema_extractor.schema_api,
-                    config=BigQueryQueriesExtractorConfig(
-                        window=self.config,
-                        user_email_pattern=self.config.usage.user_email_pattern,
-                        include_lineage=self.config.include_table_lineage,
-                        include_usage_statistics=self.config.include_usage_statistics,
-                        include_operations=self.config.usage.include_operational_stats,
-                        include_queries=self.config.include_queries,
-                        include_query_usage_statistics=self.config.include_query_usage_statistics,
-                        top_n_queries=self.config.usage.top_n_queries,
-                        region_qualifiers=self.config.region_qualifiers,
-                    ),
-                    structured_report=self.report,
-                    filters=self.filters,
-                    identifiers=self.identifiers,
-                    schema_resolver=self.sql_parser_schema_resolver,
-                    discovered_tables=self.bq_schema_extractor.table_refs,
-                ) as queries_extractor:
-                    self.report.queries_extractor = queries_extractor.report
-                    yield from queries_extractor.get_workunits_internal()
+            with self.report.new_stage(
+                f"*: {QUERIES_EXTRACTION}"
+            ), BigQueryQueriesExtractor(
+                connection=self.config.get_bigquery_client(),
+                schema_api=self.bq_schema_extractor.schema_api,
+                config=BigQueryQueriesExtractorConfig(
+                    window=self.config,
+                    user_email_pattern=self.config.usage.user_email_pattern,
+                    include_lineage=self.config.include_table_lineage,
+                    include_usage_statistics=self.config.include_usage_statistics,
+                    include_operations=self.config.usage.include_operational_stats,
+                    include_queries=self.config.include_queries,
+                    include_query_usage_statistics=self.config.include_query_usage_statistics,
+                    top_n_queries=self.config.usage.top_n_queries,
+                    region_qualifiers=self.config.region_qualifiers,
+                ),
+                structured_report=self.report,
+                filters=self.filters,
+                identifiers=self.identifiers,
+                schema_resolver=self.sql_parser_schema_resolver,
+                discovered_tables=self.bq_schema_extractor.table_refs,
+            ) as queries_extractor:
+                self.report.queries_extractor = queries_extractor.report
+                yield from queries_extractor.get_workunits_internal()
         else:
             if self.config.include_usage_statistics:
                 yield from self.usage_extractor.get_usage_workunits(

datahub/ingestion/source/bigquery_v2/bigquery_config.py

@@ -2,10 +2,8 @@ import logging
 import os
 import re
 from datetime import timedelta
-from typing import Any, Dict, List, Optional, Union
+from typing import Dict, List, Optional, Union
 
-from google.cloud import bigquery, datacatalog_v1, resourcemanager_v3
-from google.cloud.logging_v2.client import Client as GCPLoggingClient
 from pydantic import Field, PositiveInt, PrivateAttr, root_validator, validator
 
 from datahub.configuration.common import AllowDenyPattern, ConfigModel
@@ -18,7 +16,9 @@ from datahub.configuration.validate_field_removal import pydantic_removed_field
 from datahub.ingestion.glossary.classification_mixin import (
     ClassificationSourceConfigMixin,
 )
-from datahub.ingestion.source.common.gcp_credentials_config import GCPCredential
+from datahub.ingestion.source.bigquery_v2.bigquery_connection import (
+    BigQueryConnectionConfig,
+)
 from datahub.ingestion.source.data_lake_common.path_spec import PathSpec
 from datahub.ingestion.source.sql.sql_config import SQLCommonConfig, SQLFilterConfig
 from datahub.ingestion.source.state.stateful_ingestion_base import (
@@ -105,64 +105,6 @@ class BigQueryUsageConfig(BaseUsageConfig):
     )
 
 
-class BigQueryConnectionConfig(ConfigModel):
-    credential: Optional[GCPCredential] = Field(
-        default=None, description="BigQuery credential informations"
-    )
-
-    _credentials_path: Optional[str] = PrivateAttr(None)
-
-    extra_client_options: Dict[str, Any] = Field(
-        default={},
-        description="Additional options to pass to google.cloud.logging_v2.client.Client.",
-    )
-
-    project_on_behalf: Optional[str] = Field(
-        default=None,
-        description="[Advanced] The BigQuery project in which queries are executed. Will be passed when creating a job. If not passed, falls back to the project associated with the service account.",
-    )
-
-    def __init__(self, **data: Any):
-        super().__init__(**data)
-
-        if self.credential:
-            self._credentials_path = self.credential.create_credential_temp_file()
-            logger.debug(
-                f"Creating temporary credential file at {self._credentials_path}"
-            )
-            os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self._credentials_path
-
-    def get_bigquery_client(self) -> bigquery.Client:
-        client_options = self.extra_client_options
-        return bigquery.Client(self.project_on_behalf, **client_options)
-
-    def get_projects_client(self) -> resourcemanager_v3.ProjectsClient:
-        return resourcemanager_v3.ProjectsClient()
-
-    def get_policy_tag_manager_client(self) -> datacatalog_v1.PolicyTagManagerClient:
-        return datacatalog_v1.PolicyTagManagerClient()
-
-    def make_gcp_logging_client(
-        self, project_id: Optional[str] = None
-    ) -> GCPLoggingClient:
-        # See https://github.com/googleapis/google-cloud-python/issues/2674 for
-        # why we disable gRPC here.
-        client_options = self.extra_client_options.copy()
-        client_options["_use_grpc"] = False
-        if project_id is not None:
-            return GCPLoggingClient(**client_options, project=project_id)
-        else:
-            return GCPLoggingClient(**client_options)
-
-    def get_sql_alchemy_url(self) -> str:
-        if self.project_on_behalf:
-            return f"bigquery://{self.project_on_behalf}"
-        # When project_id is not set, we will attempt to detect the project ID
-        # based on the credentials or environment variables.
-        # See https://github.com/mxmzdlv/pybigquery#authentication.
-        return "bigquery://"
-
-
 class GcsLineageProviderConfig(ConfigModel):
     """
     Any source that produces gcs lineage from/to Datasets should inherit this class.

datahub/ingestion/source/bigquery_v2/bigquery_connection.py

@@ -0,0 +1,70 @@
+import logging
+import os
+from typing import Any, Dict, Optional
+
+from google.cloud import bigquery, datacatalog_v1, resourcemanager_v3
+from google.cloud.logging_v2.client import Client as GCPLoggingClient
+from pydantic import Field, PrivateAttr
+
+from datahub.configuration.common import ConfigModel
+from datahub.ingestion.source.common.gcp_credentials_config import GCPCredential
+
+logger = logging.getLogger(__name__)
+
+
+class BigQueryConnectionConfig(ConfigModel):
+    credential: Optional[GCPCredential] = Field(
+        default=None, description="BigQuery credential informations"
+    )
+
+    _credentials_path: Optional[str] = PrivateAttr(None)
+
+    extra_client_options: Dict[str, Any] = Field(
+        default={},
+        description="Additional options to pass to google.cloud.logging_v2.client.Client.",
+    )
+
+    project_on_behalf: Optional[str] = Field(
+        default=None,
+        description="[Advanced] The BigQuery project in which queries are executed. Will be passed when creating a job. If not passed, falls back to the project associated with the service account.",
+    )
+
+    def __init__(self, **data: Any):
+        super().__init__(**data)
+
+        if self.credential:
+            self._credentials_path = self.credential.create_credential_temp_file()
+            logger.debug(
+                f"Creating temporary credential file at {self._credentials_path}"
+            )
+            os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self._credentials_path
+
+    def get_bigquery_client(self) -> bigquery.Client:
+        client_options = self.extra_client_options
+        return bigquery.Client(self.project_on_behalf, **client_options)
+
+    def get_projects_client(self) -> resourcemanager_v3.ProjectsClient:
+        return resourcemanager_v3.ProjectsClient()
+
+    def get_policy_tag_manager_client(self) -> datacatalog_v1.PolicyTagManagerClient:
+        return datacatalog_v1.PolicyTagManagerClient()
+
+    def make_gcp_logging_client(
+        self, project_id: Optional[str] = None
+    ) -> GCPLoggingClient:
+        # See https://github.com/googleapis/google-cloud-python/issues/2674 for
+        # why we disable gRPC here.
+        client_options = self.extra_client_options.copy()
+        client_options["_use_grpc"] = False
+        if project_id is not None:
+            return GCPLoggingClient(**client_options, project=project_id)
+        else:
+            return GCPLoggingClient(**client_options)
+
+    def get_sql_alchemy_url(self) -> str:
+        if self.project_on_behalf:
+            return f"bigquery://{self.project_on_behalf}"
+        # When project_id is not set, we will attempt to detect the project ID
+        # based on the credentials or environment variables.
+        # See https://github.com/mxmzdlv/pybigquery#authentication.
+        return "bigquery://"

datahub/ingestion/source/bigquery_v2/bigquery_queries.py

@@ -10,10 +10,12 @@ from datahub.ingestion.api.common import PipelineContext
 from datahub.ingestion.api.source import Source, SourceReport
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.source.bigquery_v2.bigquery_config import (
-    BigQueryConnectionConfig,
     BigQueryFilterConfig,
     BigQueryIdentifierConfig,
 )
+from datahub.ingestion.source.bigquery_v2.bigquery_connection import (
+    BigQueryConnectionConfig,
+)
 from datahub.ingestion.source.bigquery_v2.bigquery_report import (
     BigQueryQueriesExtractorReport,
     BigQuerySchemaApiPerfReport,

datahub/ingestion/source/cassandra/cassandra_profiling.py

@@ -70,30 +70,31 @@ class CassandraProfiler:
     ) -> Iterable[MetadataWorkUnit]:
         for keyspace_name in cassandra_data.keyspaces:
             tables = cassandra_data.tables.get(keyspace_name, [])
-            with self.report.new_stage(f"{keyspace_name}: {PROFILING}"):
-                with ThreadPoolExecutor(
-                    max_workers=self.config.profiling.max_workers
-                ) as executor:
-                    future_to_dataset = {
-                        executor.submit(
-                            self.generate_profile,
-                            keyspace_name,
-                            table_name,
-                            cassandra_data.columns.get(table_name, []),
-                        ): table_name
-                        for table_name in tables
-                    }
-                    for future in as_completed(future_to_dataset):
-                        table_name = future_to_dataset[future]
-                        try:
-                            yield from future.result()
-                        except Exception as exc:
-                            self.report.profiling_skipped_other[table_name] += 1
-                            self.report.failure(
-                                message="Failed to profile for table",
-                                context=f"{keyspace_name}.{table_name}",
-                                exc=exc,
-                            )
+            with self.report.new_stage(
+                f"{keyspace_name}: {PROFILING}"
+            ), ThreadPoolExecutor(
+                max_workers=self.config.profiling.max_workers
+            ) as executor:
+                future_to_dataset = {
+                    executor.submit(
+                        self.generate_profile,
+                        keyspace_name,
+                        table_name,
+                        cassandra_data.columns.get(table_name, []),
+                    ): table_name
+                    for table_name in tables
+                }
+                for future in as_completed(future_to_dataset):
+                    table_name = future_to_dataset[future]
+                    try:
+                        yield from future.result()
+                    except Exception as exc:
+                        self.report.profiling_skipped_other[table_name] += 1
+                        self.report.failure(
+                            message="Failed to profile for table",
+                            context=f"{keyspace_name}.{table_name}",
+                            exc=exc,
+                        )
 
     def generate_profile(
         self,

datahub/ingestion/source/common/subtypes.py

@@ -113,3 +113,6 @@ class MLAssetSubTypes(StrEnum):
     VERTEX_ENDPOINT = "Endpoint"
     VERTEX_DATASET = "Dataset"
     VERTEX_PROJECT = "Project"
+    VERTEX_PIPELINE = "Pipeline Job"
+    VERTEX_PIPELINE_TASK = "Pipeline Task"
+    VERTEX_PIPELINE_TASK_RUN = "Pipeline Task Run"

datahub/ingestion/source/datahub/datahub_database_reader.py

@@ -195,17 +195,18 @@ class DataHubDatabaseReader:
         Yields:
             Row objects containing URNs of soft-deleted entities
         """
-        with self.engine.connect() as conn:
-            with contextlib.closing(conn.connection.cursor()) as cursor:
-                logger.debug("Polling soft-deleted urns from database")
-                cursor.execute(self.soft_deleted_urns_query)
-                columns = [desc[0] for desc in cursor.description]
-                while True:
-                    rows = cursor.fetchmany(self.config.database_query_batch_size)
-                    if not rows:
-                        return
-                    for row in rows:
-                        yield dict(zip(columns, row))
+        with self.engine.connect() as conn, contextlib.closing(
+            conn.connection.cursor()
+        ) as cursor:
+            logger.debug("Polling soft-deleted urns from database")
+            cursor.execute(self.soft_deleted_urns_query)
+            columns = [desc[0] for desc in cursor.description]
+            while True:
+                rows = cursor.fetchmany(self.config.database_query_batch_size)
+                if not rows:
+                    return
+                for row in rows:
+                    yield dict(zip(columns, row))
 
     def _parse_row(
         self, row: Dict[str, Any]

datahub/ingestion/source/dbt/dbt_cloud.py

@@ -10,14 +10,12 @@ from pydantic import Field, root_validator
 
 from datahub.ingestion.api.decorators import (
     SupportStatus,
-    capability,
     config_class,
     platform_name,
     support_status,
 )
 from datahub.ingestion.api.source import (
     CapabilityReport,
-    SourceCapability,
     TestableSource,
     TestConnectionReport,
 )
@@ -262,16 +260,14 @@ query DatahubMetadataQuery_{type}($jobId: BigInt!, $runId: BigInt) {{
 
 @platform_name("dbt")
 @config_class(DBTCloudConfig)
-@support_status(SupportStatus.INCUBATING)
-@capability(SourceCapability.DELETION_DETECTION, "Enabled via stateful ingestion")
-@capability(SourceCapability.LINEAGE_COARSE, "Enabled by default")
+@support_status(SupportStatus.CERTIFIED)
 class DBTCloudSource(DBTSourceBase, TestableSource):
     config: DBTCloudConfig
 
     @classmethod
     def create(cls, config_dict, ctx):
         config = DBTCloudConfig.parse_obj(config_dict)
-        return cls(config, ctx, "dbt")
+        return cls(config, ctx)
 
     @staticmethod
     def test_connection(config_dict: dict) -> TestConnectionReport:

datahub/ingestion/source/dbt/dbt_common.py

@@ -125,6 +125,7 @@ _DEFAULT_ACTOR = mce_builder.make_user_urn("unknown")
 @dataclass
 class DBTSourceReport(StaleEntityRemovalSourceReport):
     sql_parser_skipped_missing_code: LossyList[str] = field(default_factory=LossyList)
+    sql_parser_skipped_non_sql_model: LossyList[str] = field(default_factory=LossyList)
     sql_parser_parse_failures: int = 0
     sql_parser_detach_ctes_failures: int = 0
     sql_parser_table_errors: int = 0
@@ -829,11 +830,13 @@ def get_column_type(
     "Enabled by default, configure using `include_column_lineage`",
 )
 class DBTSourceBase(StatefulIngestionSourceBase):
-    def __init__(self, config: DBTCommonConfig, ctx: PipelineContext, platform: str):
+    def __init__(self, config: DBTCommonConfig, ctx: PipelineContext):
         super().__init__(config, ctx)
+        self.platform: str = "dbt"
+
         self.config = config
-        self.platform: str = platform
         self.report: DBTSourceReport = DBTSourceReport()
+
         self.compiled_owner_extraction_pattern: Optional[Any] = None
         if self.config.owner_extraction_pattern:
             self.compiled_owner_extraction_pattern = re.compile(
@@ -1177,6 +1180,11 @@ class DBTSourceBase(StatefulIngestionSourceBase):
                 logger.debug(
                     f"Not generating CLL for {node.dbt_name} because we don't need it."
                 )
+            elif node.language != "sql":
+                logger.debug(
+                    f"Not generating CLL for {node.dbt_name} because it is not a SQL model."
+                )
+                self.report.sql_parser_skipped_non_sql_model.append(node.dbt_name)
             elif node.compiled_code:
                 # Add CTE stops based on the upstreams list.
                 cte_mapping = {