acryl-datahub 0.15.0rc25__py3-none-any.whl → 0.15.0.1__py3-none-any.whl

datahub/ingestion/reporting/datahub_ingestion_run_summary_provider.py

@@ -146,12 +146,55 @@ class DatahubIngestionRunSummaryProvider(PipelineRunListener):
             aspect_value=source_info_aspect,
         )
 
+    @staticmethod
+    def _convert_sets_to_lists(obj: Any) -> Any:
+        """
+        Recursively converts all sets to lists in a Python object.
+        Works with nested dictionaries, lists, and sets.
+
+        Args:
+            obj: Any Python object that might contain sets
+
+        Returns:
+            The object with all sets converted to lists
+        """
+        if isinstance(obj, dict):
+            return {
+                key: DatahubIngestionRunSummaryProvider._convert_sets_to_lists(value)
+                for key, value in obj.items()
+            }
+        elif isinstance(obj, list):
+            return [
+                DatahubIngestionRunSummaryProvider._convert_sets_to_lists(element)
+                for element in obj
+            ]
+        elif isinstance(obj, set):
+            return [
+                DatahubIngestionRunSummaryProvider._convert_sets_to_lists(element)
+                for element in obj
+            ]
+        elif isinstance(obj, tuple):
+            return tuple(
+                DatahubIngestionRunSummaryProvider._convert_sets_to_lists(element)
+                for element in obj
+            )
+        else:
+            return obj
+
     def _get_recipe_to_report(self, ctx: PipelineContext) -> str:
         assert ctx.pipeline_config
         if not self.report_recipe or not ctx.pipeline_config.get_raw_dict():
             return ""
         else:
-            return json.dumps(redact_raw_config(ctx.pipeline_config.get_raw_dict()))
+            redacted_recipe = redact_raw_config(ctx.pipeline_config.get_raw_dict())
+            # This is required otherwise json dumps will fail
+            # with a TypeError: Object of type set is not JSON serializable
+            converted_recipe = (
+                DatahubIngestionRunSummaryProvider._convert_sets_to_lists(
+                    redacted_recipe
+                )
+            )
+            return json.dumps(converted_recipe)
 
     def _emit_aspect(self, entity_urn: Urn, aspect_value: _Aspect) -> None:
         self.sink.write_record_async(

datahub/ingestion/source/aws/aws_common.py

@@ -1,7 +1,12 @@
+import logging
+import os
 from datetime import datetime, timedelta, timezone
-from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Union
+from enum import Enum
+from http import HTTPStatus
+from typing import TYPE_CHECKING, Any, Dict, List, Literal, Optional, Tuple, Union
 
 import boto3
+import requests
 from boto3.session import Session
 from botocore.config import DEFAULT_TIMEOUT, Config
 from botocore.utils import fix_s3_host
@@ -14,6 +19,8 @@ from datahub.configuration.common import (
 )
 from datahub.configuration.source_common import EnvConfigMixin
 
+logger = logging.getLogger(__name__)
+
 if TYPE_CHECKING:
     from mypy_boto3_dynamodb import DynamoDBClient
     from mypy_boto3_glue import GlueClient
@@ -22,6 +29,26 @@ if TYPE_CHECKING:
     from mypy_boto3_sts import STSClient
 
 
+class AwsEnvironment(Enum):
+    EC2 = "EC2"
+    ECS = "ECS"
+    EKS = "EKS"
+    LAMBDA = "LAMBDA"
+    APP_RUNNER = "APP_RUNNER"
+    BEANSTALK = "ELASTIC_BEANSTALK"
+    CLOUD_FORMATION = "CLOUD_FORMATION"
+    UNKNOWN = "UNKNOWN"
+
+
+class AwsServicePrincipal(Enum):
+    LAMBDA = "lambda.amazonaws.com"
+    EKS = "eks.amazonaws.com"
+    APP_RUNNER = "apprunner.amazonaws.com"
+    ECS = "ecs.amazonaws.com"
+    ELASTIC_BEANSTALK = "elasticbeanstalk.amazonaws.com"
+    EC2 = "ec2.amazonaws.com"
+
+
 class AwsAssumeRoleConfig(PermissiveConfigModel):
     # Using the PermissiveConfigModel to allow the user to pass additional arguments.
 
@@ -34,6 +61,163 @@ class AwsAssumeRoleConfig(PermissiveConfigModel):
     )
 
 
+def get_instance_metadata_token() -> Optional[str]:
+    """Get IMDSv2 token"""
+    try:
+        response = requests.put(
+            "http://169.254.169.254/latest/api/token",
+            headers={"X-aws-ec2-metadata-token-ttl-seconds": "21600"},
+            timeout=1,
+        )
+        if response.status_code == HTTPStatus.OK:
+            return response.text
+    except requests.exceptions.RequestException:
+        logger.debug("Failed to get IMDSv2 token")
+    return None
+
+
+def is_running_on_ec2() -> bool:
+    """Check if code is running on EC2 using IMDSv2"""
+    token = get_instance_metadata_token()
+    if not token:
+        return False
+
+    try:
+        response = requests.get(
+            "http://169.254.169.254/latest/meta-data/instance-id",
+            headers={"X-aws-ec2-metadata-token": token},
+            timeout=1,
+        )
+        return response.status_code == HTTPStatus.OK
+    except requests.exceptions.RequestException:
+        return False
+
+
+def detect_aws_environment() -> AwsEnvironment:
+    """
+    Detect the AWS environment we're running in.
+    Order matters as some environments may have multiple indicators.
+    """
+    # Check Lambda first as it's most specific
+    if os.getenv("AWS_LAMBDA_FUNCTION_NAME"):
+        if os.getenv("AWS_EXECUTION_ENV", "").startswith("CloudFormation"):
+            return AwsEnvironment.CLOUD_FORMATION
+        return AwsEnvironment.LAMBDA
+
+    # Check EKS (IRSA)
+    if os.getenv("AWS_WEB_IDENTITY_TOKEN_FILE") and os.getenv("AWS_ROLE_ARN"):
+        return AwsEnvironment.EKS
+
+    # Check App Runner
+    if os.getenv("AWS_APP_RUNNER_SERVICE_ID"):
+        return AwsEnvironment.APP_RUNNER
+
+    # Check ECS
+    if os.getenv("ECS_CONTAINER_METADATA_URI_V4") or os.getenv(
+        "ECS_CONTAINER_METADATA_URI"
+    ):
+        return AwsEnvironment.ECS
+
+    # Check Elastic Beanstalk
+    if os.getenv("ELASTIC_BEANSTALK_ENVIRONMENT_NAME"):
+        return AwsEnvironment.BEANSTALK
+
+    if is_running_on_ec2():
+        return AwsEnvironment.EC2
+
+    return AwsEnvironment.UNKNOWN
+
+
+def get_instance_role_arn() -> Optional[str]:
+    """Get role ARN from EC2 instance metadata using IMDSv2"""
+    token = get_instance_metadata_token()
+    if not token:
+        return None
+
+    try:
+        response = requests.get(
+            "http://169.254.169.254/latest/meta-data/iam/security-credentials/",
+            headers={"X-aws-ec2-metadata-token": token},
+            timeout=1,
+        )
+        if response.status_code == 200:
+            role_name = response.text.strip()
+            if role_name:
+                sts = boto3.client("sts")
+                identity = sts.get_caller_identity()
+                return identity.get("Arn")
+    except Exception as e:
+        logger.debug(f"Failed to get instance role ARN: {e}")
+    return None
+
+
+def get_lambda_role_arn() -> Optional[str]:
+    """Get the Lambda function's role ARN"""
+    try:
+        function_name = os.getenv("AWS_LAMBDA_FUNCTION_NAME")
+        if not function_name:
+            return None
+
+        lambda_client = boto3.client("lambda")
+        function_config = lambda_client.get_function_configuration(
+            FunctionName=function_name
+        )
+        return function_config.get("Role")
+    except Exception as e:
+        logger.debug(f"Failed to get Lambda role ARN: {e}")
+        return None
+
+
+def get_current_identity() -> Tuple[Optional[str], Optional[str]]:
+    """
+    Get the current role ARN and source type based on the runtime environment.
+    Returns (role_arn, credential_source)
+    """
+    env = detect_aws_environment()
+
+    if env == AwsEnvironment.LAMBDA:
+        role_arn = get_lambda_role_arn()
+        return role_arn, AwsServicePrincipal.LAMBDA.value
+
+    elif env == AwsEnvironment.EKS:
+        role_arn = os.getenv("AWS_ROLE_ARN")
+        return role_arn, AwsServicePrincipal.EKS.value
+
+    elif env == AwsEnvironment.APP_RUNNER:
+        try:
+            sts = boto3.client("sts")
+            identity = sts.get_caller_identity()
+            return identity.get("Arn"), AwsServicePrincipal.APP_RUNNER.value
+        except Exception as e:
+            logger.debug(f"Failed to get App Runner role: {e}")
+
+    elif env == AwsEnvironment.ECS:
+        try:
+            metadata_uri = os.getenv("ECS_CONTAINER_METADATA_URI_V4") or os.getenv(
+                "ECS_CONTAINER_METADATA_URI"
+            )
+            if metadata_uri:
+                response = requests.get(f"{metadata_uri}/task", timeout=1)
+                if response.status_code == HTTPStatus.OK:
+                    task_metadata = response.json()
+                    if "TaskARN" in task_metadata:
+                        return (
+                            task_metadata.get("TaskARN"),
+                            AwsServicePrincipal.ECS.value,
+                        )
+        except Exception as e:
+            logger.debug(f"Failed to get ECS task role: {e}")
+
+    elif env == AwsEnvironment.BEANSTALK:
+        # Beanstalk uses EC2 instance metadata
+        return get_instance_role_arn(), AwsServicePrincipal.ELASTIC_BEANSTALK.value
+
+    elif env == AwsEnvironment.EC2:
+        return get_instance_role_arn(), AwsServicePrincipal.EC2.value
+
+    return None, None
+
+
 def assume_role(
     role: AwsAssumeRoleConfig,
     aws_region: Optional[str],
@@ -95,7 +279,7 @@ class AwsConnectionConfig(ConfigModel):
     )
     aws_profile: Optional[str] = Field(
         default=None,
-        description="Named AWS profile to use. Only used if access key / secret are unset. If not set the default will be used",
+        description="The [named profile](https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-profiles.html) to use from AWS credentials. Falls back to default profile if not specified and no access keys provided. Profiles are configured in ~/.aws/credentials or ~/.aws/config.",
     )
     aws_region: Optional[str] = Field(None, description="AWS region code.")
 
@@ -145,6 +329,7 @@ class AwsConnectionConfig(ConfigModel):
 
     def get_session(self) -> Session:
         if self.aws_access_key_id and self.aws_secret_access_key:
+            # Explicit credentials take precedence
             session = Session(
                 aws_access_key_id=self.aws_access_key_id,
                 aws_secret_access_key=self.aws_secret_access_key,
@@ -152,38 +337,57 @@ class AwsConnectionConfig(ConfigModel):
                 region_name=self.aws_region,
             )
         elif self.aws_profile:
+            # Named profile is second priority
             session = Session(
                 region_name=self.aws_region, profile_name=self.aws_profile
             )
         else:
-            # Use boto3's credential autodetection.
+            # Use boto3's credential autodetection
             session = Session(region_name=self.aws_region)
 
-        if self._normalized_aws_roles():
-            # Use existing session credentials to start the chain of role assumption.
-            current_credentials = session.get_credentials()
-            credentials = {
-                "AccessKeyId": current_credentials.access_key,
-                "SecretAccessKey": current_credentials.secret_key,
-                "SessionToken": current_credentials.token,
-            }
-
-            for role in self._normalized_aws_roles():
-                if self._should_refresh_credentials():
-                    credentials = assume_role(
-                        role,
-                        self.aws_region,
-                        credentials=credentials,
+            target_roles = self._normalized_aws_roles()
+            if target_roles:
+                current_role_arn, credential_source = get_current_identity()
+
+                # Only assume role if:
+                # 1. We're not in a known AWS environment with a role, or
+                # 2. We need to assume a different role than our current one
+                should_assume_role = current_role_arn is None or any(
+                    role.RoleArn != current_role_arn for role in target_roles
+                )
+
+                if should_assume_role:
+                    env = detect_aws_environment()
+                    logger.debug(f"Assuming role(s) from {env.value} environment")
+
+                    current_credentials = session.get_credentials()
+                    if current_credentials is None:
+                        raise ValueError("No credentials available for role assumption")
+
+                    credentials = {
+                        "AccessKeyId": current_credentials.access_key,
+                        "SecretAccessKey": current_credentials.secret_key,
+                        "SessionToken": current_credentials.token,
+                    }
+
+                    for role in target_roles:
+                        if self._should_refresh_credentials():
+                            credentials = assume_role(
+                                role=role,
+                                aws_region=self.aws_region,
+                                credentials=credentials,
+                            )
+                            if isinstance(credentials["Expiration"], datetime):
+                                self._credentials_expiration = credentials["Expiration"]
+
+                    session = Session(
+                        aws_access_key_id=credentials["AccessKeyId"],
+                        aws_secret_access_key=credentials["SecretAccessKey"],
+                        aws_session_token=credentials["SessionToken"],
+                        region_name=self.aws_region,
                     )
-                    if isinstance(credentials["Expiration"], datetime):
-                        self._credentials_expiration = credentials["Expiration"]
-
-            session = Session(
-                aws_access_key_id=credentials["AccessKeyId"],
-                aws_secret_access_key=credentials["SecretAccessKey"],
-                aws_session_token=credentials["SessionToken"],
-                region_name=self.aws_region,
-            )
+                else:
+                    logger.debug(f"Using existing role from {credential_source}")
 
         return session
 

datahub/ingestion/source/aws/glue.py

@@ -52,6 +52,7 @@ from datahub.ingestion.api.decorators import (
     platform_name,
     support_status,
 )
+from datahub.ingestion.api.report import EntityFilterReport
 from datahub.ingestion.api.source import MetadataWorkUnitProcessor
 from datahub.ingestion.api.workunit import MetadataWorkUnit
 from datahub.ingestion.source.aws import s3_util
@@ -115,7 +116,6 @@ from datahub.utilities.hive_schema_to_avro import get_schema_fields_for_hive_col
 
 logger = logging.getLogger(__name__)
 
-
 DEFAULT_PLATFORM = "glue"
 VALID_PLATFORMS = [DEFAULT_PLATFORM, "athena"]
 
@@ -220,6 +220,7 @@ class GlueSourceConfig(
 class GlueSourceReport(StaleEntityRemovalSourceReport):
     tables_scanned = 0
     filtered: List[str] = dataclass_field(default_factory=list)
+    databases: EntityFilterReport = EntityFilterReport.field(type="database")
 
     num_job_script_location_missing: int = 0
     num_job_script_location_invalid: int = 0
@@ -668,6 +669,7 @@ class GlueSource(StatefulIngestionSourceBase):
         return MetadataWorkUnit(id=f'{job_name}-{node["Id"]}', mce=mce)
 
     def get_all_databases(self) -> Iterable[Mapping[str, Any]]:
+        logger.debug("Getting all databases")
         # see https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/glue/paginator/GetDatabases.html
         paginator = self.glue_client.get_paginator("get_databases")
 
@@ -684,10 +686,18 @@ class GlueSource(StatefulIngestionSourceBase):
             pattern += "[?!TargetDatabase]"
 
         for database in paginator_response.search(pattern):
-            if self.source_config.database_pattern.allowed(database["Name"]):
+            if (not self.source_config.database_pattern.allowed(database["Name"])) or (
+                self.source_config.catalog_id
+                and database.get("CatalogId")
+                and database.get("CatalogId") != self.source_config.catalog_id
+            ):
+                self.report.databases.dropped(database["Name"])
+            else:
+                self.report.databases.processed(database["Name"])
                 yield database
 
     def get_tables_from_database(self, database: Mapping[str, Any]) -> Iterable[Dict]:
+        logger.debug(f"Getting tables from database {database['Name']}")
         # see https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/glue/paginator/GetTables.html
         paginator = self.glue_client.get_paginator("get_tables")
         database_name = database["Name"]

datahub/ingestion/source/bigquery_v2/bigquery.py

@@ -206,9 +206,7 @@ class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
 
     def _init_schema_resolver(self) -> SchemaResolver:
         schema_resolution_required = (
-            self.config.use_queries_v2
-            or self.config.lineage_parse_view_ddl
-            or self.config.lineage_use_sql_parser
+            self.config.use_queries_v2 or self.config.lineage_use_sql_parser
         )
         schema_ingestion_enabled = (
             self.config.include_schema_metadata
@@ -255,18 +253,16 @@ class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
         for project in projects:
             yield from self.bq_schema_extractor.get_project_workunits(project)
 
-        if self.config.use_queries_v2:
-            # Always ingest View and Snapshot lineage with schema ingestion
-            self.report.set_ingestion_stage("*", "View and Snapshot Lineage")
-
-            yield from self.lineage_extractor.get_lineage_workunits_for_views_and_snapshots(
-                [p.id for p in projects],
-                self.bq_schema_extractor.view_refs_by_project,
-                self.bq_schema_extractor.view_definitions,
-                self.bq_schema_extractor.snapshot_refs_by_project,
-                self.bq_schema_extractor.snapshots_by_ref,
-            )
+        self.report.set_ingestion_stage("*", "View and Snapshot Lineage")
+        yield from self.lineage_extractor.get_lineage_workunits_for_views_and_snapshots(
+            [p.id for p in projects],
+            self.bq_schema_extractor.view_refs_by_project,
+            self.bq_schema_extractor.view_definitions,
+            self.bq_schema_extractor.snapshot_refs_by_project,
+            self.bq_schema_extractor.snapshots_by_ref,
+        )
 
+        if self.config.use_queries_v2:
             # if both usage and lineage are disabled then skip queries extractor piece
             if (
                 not self.config.include_usage_statistics
@@ -306,10 +302,6 @@ class BigqueryV2Source(StatefulIngestionSourceBase, TestableSource):
             if self.config.include_table_lineage:
                 yield from self.lineage_extractor.get_lineage_workunits(
                     [p.id for p in projects],
-                    self.bq_schema_extractor.view_refs_by_project,
-                    self.bq_schema_extractor.view_definitions,
-                    self.bq_schema_extractor.snapshot_refs_by_project,
-                    self.bq_schema_extractor.snapshots_by_ref,
                     self.bq_schema_extractor.table_refs,
                 )
 

datahub/ingestion/source/bigquery_v2/bigquery_config.py

@@ -463,10 +463,6 @@ class BigQueryV2Config(
         default=True,
         description="Use sql parser to resolve view/table lineage.",
     )
-    lineage_parse_view_ddl: bool = Field(
-        default=True,
-        description="Sql parse view ddl to get lineage.",
-    )
 
     lineage_sql_parser_use_raw_names: bool = Field(
         default=False,
@@ -572,11 +568,9 @@ class BigQueryV2Config(
         "See [this](https://cloud.google.com/bigquery/docs/information-schema-jobs#scope_and_syntax) for details.",
     )
 
-    # include_view_lineage and include_view_column_lineage are inherited from SQLCommonConfig
-    # but not used in bigquery so we hide them from docs.
-    include_view_lineage: bool = Field(default=True, hidden_from_docs=True)
-
-    include_view_column_lineage: bool = Field(default=True, hidden_from_docs=True)
+    _include_view_lineage = pydantic_removed_field("include_view_lineage")
+    _include_view_column_lineage = pydantic_removed_field("include_view_column_lineage")
+    _lineage_parse_view_ddl = pydantic_removed_field("lineage_parse_view_ddl")
 
     @root_validator(pre=True)
     def set_include_schema_metadata(cls, values: Dict) -> Dict:

datahub/ingestion/source/bigquery_v2/bigquery_schema.py

@@ -1,7 +1,7 @@
 import logging
 from collections import defaultdict
 from dataclasses import dataclass, field
-from datetime import datetime, timezone
+from datetime import datetime
 from functools import lru_cache
 from typing import Any, Dict, FrozenSet, Iterable, Iterator, List, Optional
 
@@ -15,6 +15,7 @@ from google.cloud.bigquery.table import (
     TimePartitioningType,
 )
 
+from datahub.emitter.mce_builder import parse_ts_millis
 from datahub.ingestion.api.source import SourceReport
 from datahub.ingestion.source.bigquery_v2.bigquery_audit import BigqueryTableIdentifier
 from datahub.ingestion.source.bigquery_v2.bigquery_helper import parse_labels
@@ -393,13 +394,7 @@ class BigQuerySchemaApi:
             name=table.table_name,
             created=table.created,
             table_type=table.table_type,
-            last_altered=(
-                datetime.fromtimestamp(
-                    table.get("last_altered") / 1000, tz=timezone.utc
-                )
-                if table.get("last_altered") is not None
-                else None
-            ),
+            last_altered=parse_ts_millis(table.get("last_altered")),
             size_in_bytes=table.get("bytes"),
             rows_count=table.get("row_count"),
             comment=table.comment,
@@ -460,11 +455,7 @@ class BigQuerySchemaApi:
         return BigqueryView(
             name=view.table_name,
             created=view.created,
-            last_altered=(
-                datetime.fromtimestamp(view.get("last_altered") / 1000, tz=timezone.utc)
-                if view.get("last_altered") is not None
-                else None
-            ),
+            last_altered=(parse_ts_millis(view.get("last_altered"))),
             comment=view.comment,
             view_definition=view.view_definition,
             materialized=view.table_type == BigqueryTableType.MATERIALIZED_VIEW,
@@ -705,13 +696,7 @@ class BigQuerySchemaApi:
         return BigqueryTableSnapshot(
             name=snapshot.table_name,
             created=snapshot.created,
-            last_altered=(
-                datetime.fromtimestamp(
-                    snapshot.get("last_altered") / 1000, tz=timezone.utc
-                )
-                if snapshot.get("last_altered") is not None
-                else None
-            ),
+            last_altered=parse_ts_millis(snapshot.get("last_altered")),
             comment=snapshot.comment,
             ddl=snapshot.ddl,
             snapshot_time=snapshot.snapshot_time,

datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py

@@ -653,14 +653,11 @@ class BigQuerySchemaGenerator:
             self.report.report_dropped(table_identifier.raw_table_name())
             return
 
-        if self.store_table_refs:
-            table_ref = str(
-                BigQueryTableRef(table_identifier).get_sanitized_table_ref()
-            )
-            self.table_refs.add(table_ref)
-            if self.config.lineage_parse_view_ddl and view.view_definition:
-                self.view_refs_by_project[project_id].add(table_ref)
-                self.view_definitions[table_ref] = view.view_definition
+        table_ref = str(BigQueryTableRef(table_identifier).get_sanitized_table_ref())
+        self.table_refs.add(table_ref)
+        if view.view_definition:
+            self.view_refs_by_project[project_id].add(table_ref)
+            self.view_definitions[table_ref] = view.view_definition
 
         view.column_count = len(columns)
         if not view.column_count:
@@ -701,14 +698,11 @@ class BigQuerySchemaGenerator:
                 f"Snapshot doesn't have any column or unable to get columns for snapshot: {table_identifier}"
             )
 
-        if self.store_table_refs:
-            table_ref = str(
-                BigQueryTableRef(table_identifier).get_sanitized_table_ref()
-            )
-            self.table_refs.add(table_ref)
-            if snapshot.base_table_identifier:
-                self.snapshot_refs_by_project[project_id].add(table_ref)
-                self.snapshots_by_ref[table_ref] = snapshot
+        table_ref = str(BigQueryTableRef(table_identifier).get_sanitized_table_ref())
+        self.table_refs.add(table_ref)
+        if snapshot.base_table_identifier:
+            self.snapshot_refs_by_project[project_id].add(table_ref)
+            self.snapshots_by_ref[table_ref] = snapshot
 
         yield from self.gen_snapshot_dataset_workunits(
             table=snapshot,
@@ -1148,7 +1142,7 @@ class BigQuerySchemaGenerator:
             foreignKeys=foreign_keys if foreign_keys else None,
         )
 
-        if self.config.lineage_parse_view_ddl or self.config.lineage_use_sql_parser:
+        if self.config.lineage_use_sql_parser:
             self.sql_parser_schema_resolver.add_schema_metadata(
                 dataset_urn, schema_metadata
             )

datahub/ingestion/source/bigquery_v2/lineage.py

@@ -291,16 +291,15 @@ class BigqueryLineageExtractor:
         snapshots_by_ref: FileBackedDict[BigqueryTableSnapshot],
     ) -> Iterable[MetadataWorkUnit]:
         for project in projects:
-            if self.config.lineage_parse_view_ddl:
-                for view in view_refs_by_project[project]:
-                    self.datasets_skip_audit_log_lineage.add(view)
-                    self.aggregator.add_view_definition(
-                        view_urn=self.identifiers.gen_dataset_urn_from_raw_ref(
-                            BigQueryTableRef.from_string_name(view)
-                        ),
-                        view_definition=view_definitions[view],
-                        default_db=project,
-                    )
+            for view in view_refs_by_project[project]:
+                self.datasets_skip_audit_log_lineage.add(view)
+                self.aggregator.add_view_definition(
+                    view_urn=self.identifiers.gen_dataset_urn_from_raw_ref(
+                        BigQueryTableRef.from_string_name(view)
+                    ),
+                    view_definition=view_definitions[view],
+                    default_db=project,
+                )
 
             for snapshot_ref in snapshot_refs_by_project[project]:
                 snapshot = snapshots_by_ref[snapshot_ref]
@@ -322,23 +321,11 @@ class BigqueryLineageExtractor:
     def get_lineage_workunits(
         self,
         projects: List[str],
-        view_refs_by_project: Dict[str, Set[str]],
-        view_definitions: FileBackedDict[str],
-        snapshot_refs_by_project: Dict[str, Set[str]],
-        snapshots_by_ref: FileBackedDict[BigqueryTableSnapshot],
         table_refs: Set[str],
     ) -> Iterable[MetadataWorkUnit]:
         if not self._should_ingest_lineage():
             return
 
-        yield from self.get_lineage_workunits_for_views_and_snapshots(
-            projects,
-            view_refs_by_project,
-            view_definitions,
-            snapshot_refs_by_project,
-            snapshots_by_ref,
-        )
-
         if self.config.use_exported_bigquery_audit_metadata:
             projects = ["*"]  # project_id not used when using exported metadata