acryl-datahub 0.15.0.4rc3__py3-none-any.whl → 0.15.0.5__py3-none-any.whl

datahub/ingestion/source/apply/datahub_apply.py

@@ -0,0 +1,223 @@
+import logging
+from functools import partial
+from typing import Any, Iterable, List, Optional, Union
+
+import progressbar
+from pydantic import Field
+
+from datahub.configuration.common import ConfigModel
+from datahub.emitter.mcp import MetadataChangeProposalWrapper
+from datahub.ingestion.api.common import PipelineContext
+from datahub.ingestion.api.decorators import (
+    SupportStatus,
+    config_class,
+    platform_name,
+    support_status,
+)
+from datahub.ingestion.api.source import MetadataWorkUnitProcessor, Source, SourceReport
+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.metadata.schema_classes import (
+    DomainsClass,
+    GlossaryTermAssociationClass,
+    MetadataChangeProposalClass,
+    OwnerClass,
+    OwnershipTypeClass,
+    TagAssociationClass,
+)
+from datahub.specific.dataset import DatasetPatchBuilder
+
+logger = logging.getLogger(__name__)
+
+
+def apply_association_to_container(
+    container_urn: str,
+    association_urn: str,
+    association_type: str,
+    emit: bool = True,
+    graph: Optional[DataHubGraph] = None,
+) -> Optional[List[Union[MetadataChangeProposalWrapper, MetadataChangeProposalClass]]]:
+    """
+    Common function to add either tags, terms, domains, or owners to child datasets (for now).
+
+    Args:
+        container_urn: The URN of the container
+        association_urn: The URN of the tag, term, or user to apply
+        association_type: One of 'tag', 'term', 'domain' or 'owner'
+    """
+    urns: List[str] = [container_urn]
+    if not graph:
+        graph = get_default_graph()
+    logger.info(f"Using {graph}")
+    urns.extend(
+        graph.get_urns_by_filter(
+            container=container_urn,
+            batch_size=1000,
+            entity_types=["dataset", "container"],
+        )
+    )
+
+    all_patches: List[Any] = []
+    for urn in urns:
+        builder = DatasetPatchBuilder(urn)
+        patches: List[Any] = []
+        if association_type == "tag":
+            patches = builder.add_tag(TagAssociationClass(association_urn)).build()
+        elif association_type == "term":
+            patches = builder.add_term(
+                GlossaryTermAssociationClass(association_urn)
+            ).build()
+        elif association_type == "owner":
+            patches = builder.add_owner(
+                OwnerClass(
+                    owner=association_urn,
+                    type=OwnershipTypeClass.TECHNICAL_OWNER,
+                )
+            ).build()
+        elif association_type == "domain":
+            patches = [
+                MetadataChangeProposalWrapper(
+                    entityUrn=urn,
+                    aspect=DomainsClass(domains=[association_urn]),
+                )
+            ]
+        all_patches.extend(patches)
+    if emit:
+        mcps_iter = progressbar.progressbar(all_patches, redirect_stdout=True)
+        for mcp in mcps_iter:
+            graph.emit(mcp)
+        return None
+    else:
+        return all_patches
+
+
+class DomainApplyConfig(ConfigModel):
+    assets: List[str] = Field(
+        default_factory=list,
+        description="List of assets to apply domain hierarchichaly. Currently only containers and datasets are supported",
+    )
+    domain_urn: str = Field(default="")
+
+
+class TagApplyConfig(ConfigModel):
+    assets: List[str] = Field(
+        default_factory=list,
+        description="List of assets to apply tag hierarchichaly. Currently only containers and datasets are supported",
+    )
+    tag_urn: str = Field(default="")
+
+
+class TermApplyConfig(ConfigModel):
+    assets: List[str] = Field(
+        default_factory=list,
+        description="List of assets to apply term hierarchichaly. Currently only containers and datasets are supported",
+    )
+    term_urn: str = Field(default="")
+
+
+class OwnerApplyConfig(ConfigModel):
+    assets: List[str] = Field(
+        default_factory=list,
+        description="List of assets to apply owner hierarchichaly. Currently only containers and datasets are supported",
+    )
+    owner_urn: str = Field(default="")
+
+
+class DataHubApplyConfig(ConfigModel):
+    domain_apply: Optional[List[DomainApplyConfig]] = Field(
+        default=None,
+        description="List to apply domains to assets",
+    )
+    tag_apply: Optional[List[TagApplyConfig]] = Field(
+        default=None,
+        description="List to apply tags to assets",
+    )
+    term_apply: Optional[List[TermApplyConfig]] = Field(
+        default=None,
+        description="List to apply terms to assets",
+    )
+    owner_apply: Optional[List[OwnerApplyConfig]] = Field(
+        default=None,
+        description="List to apply owners to assets",
+    )
+
+
+@platform_name("DataHubApply")
+@config_class(DataHubApplyConfig)
+@support_status(SupportStatus.TESTING)
+class DataHubApplySource(Source):
+    """
+    This source is a helper over CLI
+    so people can use the helper to apply various metadata changes to DataHub
+    via Managed Ingestion
+    """
+
+    def __init__(self, ctx: PipelineContext, config: DataHubApplyConfig):
+        self.ctx = ctx
+        self.config = config
+        self.report = SourceReport()
+        self.graph = ctx.require_graph()
+
+    def _yield_workunits(
+        self,
+        proposals: List[
+            Union[MetadataChangeProposalWrapper, MetadataChangeProposalClass]
+        ],
+    ) -> Iterable[MetadataWorkUnit]:
+        for proposal in proposals:
+            if isinstance(proposal, MetadataChangeProposalWrapper):
+                yield proposal.as_workunit()
+            else:
+                yield MetadataWorkUnit(
+                    id=MetadataWorkUnit.generate_workunit_id(proposal),
+                    mcp_raw=proposal,
+                )
+
+    def _handle_assets(
+        self, assets: List[str], apply_urn: str, apply_type: str
+    ) -> Iterable[MetadataWorkUnit]:
+        for asset in assets:
+            change_proposals = apply_association_to_container(
+                asset, apply_urn, apply_type, emit=False, graph=self.graph
+            )
+            assert change_proposals is not None
+            yield from self._yield_workunits(change_proposals)
+
+    def _yield_domain(self) -> Iterable[MetadataWorkUnit]:
+        if not self.config.domain_apply:
+            return
+        for apply in self.config.domain_apply:
+            yield from self._handle_assets(apply.assets, apply.domain_urn, "domain")
+
+    def _yield_tag(self) -> Iterable[MetadataWorkUnit]:
+        if not self.config.tag_apply:
+            return
+        for apply in self.config.tag_apply:
+            yield from self._handle_assets(apply.assets, apply.tag_urn, "tag")
+
+    def _yield_term(self) -> Iterable[MetadataWorkUnit]:
+        if not self.config.term_apply:
+            return
+        for apply in self.config.term_apply:
+            yield from self._handle_assets(apply.assets, apply.term_urn, "term")
+
+    def _yield_owner(self) -> Iterable[MetadataWorkUnit]:
+        if not self.config.owner_apply:
+            return
+        for apply in self.config.owner_apply:
+            yield from self._handle_assets(apply.assets, apply.owner_urn, "owner")
+
+    def get_workunits_internal(
+        self,
+    ) -> Iterable[MetadataWorkUnit]:
+        yield from self._yield_domain()
+        yield from self._yield_tag()
+        yield from self._yield_term()
+        yield from self._yield_owner()
+
+    def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:
+        return [partial(auto_workunit_reporter, self.get_report())]
+
+    def get_report(self) -> SourceReport:
+        return self.report

datahub/ingestion/source/aws/glue.py

@@ -113,6 +113,7 @@ from datahub.metadata.schema_classes import (
 )
 from datahub.utilities.delta import delta_type_to_hive_type
 from datahub.utilities.hive_schema_to_avro import get_schema_fields_for_hive_column
+from datahub.utilities.lossy_collections import LossyList
 
 logger = logging.getLogger(__name__)
 
@@ -218,8 +219,9 @@ class GlueSourceConfig(
 
 @dataclass
 class GlueSourceReport(StaleEntityRemovalSourceReport):
+    catalog_id: Optional[str] = None
     tables_scanned = 0
-    filtered: List[str] = dataclass_field(default_factory=list)
+    filtered: LossyList[str] = dataclass_field(default_factory=LossyList)
     databases: EntityFilterReport = EntityFilterReport.field(type="database")
 
     num_job_script_location_missing: int = 0
@@ -315,6 +317,7 @@ class GlueSource(StatefulIngestionSourceBase):
         self.extract_owners = config.extract_owners
         self.source_config = config
         self.report = GlueSourceReport()
+        self.report.catalog_id = self.source_config.catalog_id
         self.glue_client = config.glue_client
         self.s3_client = config.s3_client
         self.extract_transforms = config.extract_transforms
@@ -744,7 +747,7 @@ class GlueSource(StatefulIngestionSourceBase):
                 for tables in self.get_tables_from_database(database):
                     all_tables.append(tables)
             except Exception as e:
-                self.report.failure(
+                self.report.warning(
                     message="Failed to get tables from database",
                     context=database["Name"],
                     exc=e,

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

@@ -1,5 +1,5 @@
 from dataclasses import dataclass, field
-from typing import Dict, List, Optional, Union
+from typing import Dict, Optional, Union
 
 from pydantic.fields import Field
 
@@ -9,6 +9,7 @@ from datahub.ingestion.source.state.stale_entity_removal_handler import (
     StatefulIngestionConfigBase,
     StatefulStaleMetadataRemovalConfig,
 )
+from datahub.utilities.lossy_collections import LossyList
 
 
 class SagemakerSourceConfig(
@@ -42,7 +43,7 @@ class SagemakerSourceReport(StaleEntityRemovalSourceReport):
     jobs_scanned = 0
     jobs_processed = 0
     datasets_scanned = 0
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
     model_endpoint_lineage = 0
     model_group_lineage = 0
 

datahub/ingestion/source/bigquery_v2/bigquery_report.py

@@ -141,7 +141,7 @@ class BigQueryV2Report(
     profiling_skipped_invalid_partition_type: Dict[str, str] = field(
         default_factory=TopKDict
     )
-    profiling_skipped_partition_profiling_disabled: List[str] = field(
+    profiling_skipped_partition_profiling_disabled: LossyList[str] = field(
         default_factory=LossyList
     )
     allow_pattern: Optional[str] = None

datahub/ingestion/source/dbt/dbt_core.py

@@ -488,7 +488,7 @@ class DBTCoreSource(DBTSourceBase, TestableSource):
     ) -> Dict:
         if re.match("^https?://", uri):
             return json.loads(requests.get(uri).text)
-        elif re.match("^s3://", uri):
+        elif is_s3_uri(uri):
             u = urlparse(uri)
             assert aws_connection
             response = aws_connection.get_s3_client().get_object(

datahub/ingestion/source/delta_lake/report.py

@@ -1,14 +1,14 @@
 import dataclasses
 from dataclasses import field as dataclass_field
-from typing import List
 
 from datahub.ingestion.api.source import SourceReport
+from datahub.utilities.lossy_collections import LossyList
 
 
 @dataclasses.dataclass
 class DeltaLakeSourceReport(SourceReport):
     files_scanned = 0
-    filtered: List[str] = dataclass_field(default_factory=list)
+    filtered: LossyList[str] = dataclass_field(default_factory=LossyList)
 
     def report_file_scanned(self) -> None:
         self.files_scanned += 1

datahub/ingestion/source/dynamodb/dynamodb.py

@@ -68,6 +68,7 @@ from datahub.metadata.schema_classes import (
     StringTypeClass,
     UnionTypeClass,
 )
+from datahub.utilities.lossy_collections import LossyList
 from datahub.utilities.registries.domain_registry import DomainRegistry
 
 MAX_ITEMS_TO_RETRIEVE = 100
@@ -120,7 +121,7 @@ class DynamoDBConfig(
 
 @dataclass
 class DynamoDBSourceReport(StaleEntityRemovalSourceReport, ClassificationReportMixin):
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_dropped(self, name: str) -> None:
         self.filtered.append(name)

datahub/ingestion/source/elastic_search.py

@@ -62,6 +62,7 @@ from datahub.metadata.schema_classes import (
     SubTypesClass,
 )
 from datahub.utilities.config_clean import remove_protocol
+from datahub.utilities.lossy_collections import LossyList
 from datahub.utilities.urns.dataset_urn import DatasetUrn
 
 logger = logging.getLogger(__name__)
@@ -189,7 +190,7 @@ class ElasticToSchemaFieldConverter:
 @dataclass
 class ElasticsearchSourceReport(SourceReport):
     index_scanned: int = 0
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_index_scanned(self, index: str) -> None:
         self.index_scanned += 1

datahub/ingestion/source/ge_profiling_config.py

@@ -115,26 +115,30 @@ class GEProfilingConfig(GEProfilingBaseConfig):
     )
     max_number_of_fields_to_profile: Optional[pydantic.PositiveInt] = Field(
         default=None,
-        description="A positive integer that specifies the maximum number of columns to profile for any table. `None` implies all columns. The cost of profiling goes up significantly as the number of columns to profile goes up.",
+        description="A positive integer that specifies the maximum number of columns to profile for "
+        "any table. `None` implies all columns. The cost of profiling goes up significantly as the "
+        "number of columns to profile goes up.",
     )
 
     profile_if_updated_since_days: Optional[pydantic.PositiveFloat] = Field(
         default=None,
-        description="Profile table only if it has been updated since these many number of days. If set to `null`, no constraint of last modified time for tables to profile. Supported only in `snowflake` and `BigQuery`.",
+        description="Profile table only if it has been updated since these many number of days. "
+        "If set to `null`, no constraint of last modified time for tables to profile. "
+        "Supported only in `snowflake` and `BigQuery`.",
     )
 
     profile_table_size_limit: Optional[int] = Field(
         default=5,
         description="Profile tables only if their size is less than specified GBs. If set to `null`, "
-        "no limit on the size of tables to profile. Supported only in `snowflake` and `BigQuery`"
-        "Supported for `oracle` based on calculated size from gathered stats.",
+        "no limit on the size of tables to profile. Supported only in `Snowflake`, `BigQuery` and "
+        "`Databricks`. Supported for `Oracle` based on calculated size from gathered stats.",
     )
 
     profile_table_row_limit: Optional[int] = Field(
         default=5000000,
-        description="Profile tables only if their row count is less than specified count. If set to `null`, "
-        "no limit on the row count of tables to profile. Supported only in `snowflake` and `BigQuery`"
-        "Supported for `oracle` based on gathered stats.",
+        description="Profile tables only if their row count is less than specified count. "
+        "If set to `null`, no limit on the row count of tables to profile. Supported only in "
+        "`Snowflake`, `BigQuery`. Supported for `Oracle` based on gathered stats.",
     )
 
     profile_table_row_count_estimate_only: bool = Field(

datahub/ingestion/source/iceberg/iceberg_common.py

@@ -1,6 +1,6 @@
 import logging
 from dataclasses import dataclass, field
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, Optional
 
 from humanfriendly import format_timespan
 from pydantic import Field, validator
@@ -20,6 +20,7 @@ from datahub.ingestion.source_config.operation_config import (
     OperationConfig,
     is_profiling_enabled,
 )
+from datahub.utilities.lossy_collections import LossyList
 from datahub.utilities.stats_collections import TopKDict, int_top_k_dict
 
 logger = logging.getLogger(__name__)
@@ -198,7 +199,7 @@ class TimingClass:
 class IcebergSourceReport(StaleEntityRemovalSourceReport):
     tables_scanned: int = 0
     entities_profiled: int = 0
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
     load_table_timings: TimingClass = field(default_factory=TimingClass)
     processing_table_timings: TimingClass = field(default_factory=TimingClass)
     profiling_table_timings: TimingClass = field(default_factory=TimingClass)

datahub/ingestion/source/identity/azure_ad.py

@@ -13,6 +13,7 @@ from requests.adapters import HTTPAdapter, Retry
 
 from datahub.configuration.common import AllowDenyPattern
 from datahub.configuration.source_common import DatasetSourceConfigMixin
+from datahub.configuration.validate_field_removal import pydantic_removed_field
 from datahub.emitter.mce_builder import make_group_urn, make_user_urn
 from datahub.emitter.mcp import MetadataChangeProposalWrapper
 from datahub.ingestion.api.common import PipelineContext
@@ -51,6 +52,7 @@ from datahub.metadata.schema_classes import (
     OriginTypeClass,
     StatusClass,
 )
+from datahub.utilities.lossy_collections import LossyList
 
 logger = logging.getLogger(__name__)
 
@@ -132,11 +134,7 @@ class AzureADConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin):
         description="regex patterns for groups to include in ingestion.",
     )
 
-    # If enabled, report will contain names of filtered users and groups.
-    filtered_tracking: bool = Field(
-        default=True,
-        description="If enabled, report will contain names of filtered users and groups.",
-    )
+    _remove_filtered_tracking = pydantic_removed_field("filtered_tracking")
 
     # Optional: Whether to mask sensitive information from workunit ID's. On by default.
     mask_group_id: bool = Field(
@@ -156,14 +154,10 @@ class AzureADConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin):
 
 @dataclass
 class AzureADSourceReport(StaleEntityRemovalSourceReport):
-    filtered: List[str] = field(default_factory=list)
-    filtered_tracking: bool = field(default=True, repr=False)
-    filtered_count: int = field(default=0)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_filtered(self, name: str) -> None:
-        self.filtered_count += 1
-        if self.filtered_tracking:
-            self.filtered.append(name)
+        self.filtered.append(name)
 
 
 # Source that extracts Azure AD users, groups and group memberships using Microsoft Graph REST API
@@ -266,9 +260,7 @@ class AzureADSource(StatefulIngestionSourceBase):
     def __init__(self, config: AzureADConfig, ctx: PipelineContext):
         super().__init__(config, ctx)
         self.config = config
-        self.report = AzureADSourceReport(
-            filtered_tracking=self.config.filtered_tracking
-        )
+        self.report = AzureADSourceReport()
         session = requests.Session()
         retries = Retry(
             total=5, backoff_factor=1, status_forcelist=[429, 500, 502, 503, 504]

datahub/ingestion/source/identity/okta.py

@@ -50,6 +50,7 @@ from datahub.metadata.schema_classes import (
     OriginTypeClass,
     StatusClass,
 )
+from datahub.utilities.lossy_collections import LossyList
 
 logger = logging.getLogger(__name__)
 nest_asyncio.apply()
@@ -173,7 +174,7 @@ class OktaConfig(StatefulIngestionConfigBase, ConfigModel):
 
 @dataclass
 class OktaSourceReport(StaleEntityRemovalSourceReport):
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_filtered(self, name: str) -> None:
         self.filtered.append(name)

datahub/ingestion/source/kafka/kafka.py

@@ -73,6 +73,7 @@ from datahub.metadata.schema_classes import (
     OwnershipSourceTypeClass,
     SubTypesClass,
 )
+from datahub.utilities.lossy_collections import LossyList
 from datahub.utilities.mapping import Constants, OperationProcessor
 from datahub.utilities.registries.domain_registry import DomainRegistry
 from datahub.utilities.str_enum import StrEnum
@@ -190,7 +191,7 @@ def get_kafka_admin_client(
 @dataclass
 class KafkaSourceReport(StaleEntityRemovalSourceReport):
     topics_scanned: int = 0
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_topic_scanned(self, topic: str) -> None:
         self.topics_scanned += 1

datahub/ingestion/source/kafka_connect/common.py

@@ -16,6 +16,7 @@ from datahub.ingestion.source.state.stale_entity_removal_handler import (
 from datahub.ingestion.source.state.stateful_ingestion_base import (
     StatefulIngestionConfigBase,
 )
+from datahub.utilities.lossy_collections import LossyList
 
 logger = logging.getLogger(__name__)
 
@@ -83,7 +84,7 @@ class KafkaConnectSourceConfig(
 @dataclass
 class KafkaConnectSourceReport(StaleEntityRemovalSourceReport):
     connectors_scanned: int = 0
-    filtered: List[str] = field(default_factory=list)
+    filtered: LossyList[str] = field(default_factory=LossyList)
 
     def report_connector_scanned(self, connector: str) -> None:
         self.connectors_scanned += 1

datahub/ingestion/source/ldap.py

@@ -37,6 +37,7 @@ from datahub.metadata.schema_classes import (
     CorpUserSnapshotClass,
     GroupMembershipClass,
 )
+from datahub.utilities.lossy_collections import LossyList
 
 # default mapping for attrs
 user_attrs_map: Dict[str, Any] = {}
@@ -160,7 +161,7 @@ class LDAPSourceConfig(StatefulIngestionConfigBase, DatasetSourceConfigMixin):
 
 @dataclasses.dataclass
 class LDAPSourceReport(StaleEntityRemovalSourceReport):
-    dropped_dns: List[str] = dataclasses.field(default_factory=list)
+    dropped_dns: LossyList[str] = dataclasses.field(default_factory=LossyList)
 
     def report_dropped(self, dn: str) -> None:
         self.dropped_dns.append(dn)

datahub/ingestion/source/looker/looker_config.py

@@ -177,7 +177,9 @@ def _get_generic_definition(
 class LookerConnectionDefinition(ConfigModel):
     platform: str
     default_db: str
-    default_schema: Optional[str]  # Optional since some sources are two-level only
+    default_schema: Optional[str] = (
+        None  # Optional since some sources are two-level only
+    )
     platform_instance: Optional[str] = None
     platform_env: Optional[str] = Field(
         default=None,

datahub/ingestion/source/looker/looker_dataclasses.py

@@ -32,6 +32,12 @@ class LookerField:
     sql: Optional[str]
 
 
+@dataclass
+class LookerConstant:
+    name: str
+    value: str
+
+
 @dataclass
 class LookerModel:
     connection: str
@@ -75,6 +81,7 @@ class LookerModel:
             try:
                 parsed = load_and_preprocess_file(
                     path=included_file,
+                    reporter=reporter,
                     source_config=source_config,
                 )
                 included_explores = parsed.get("explores", [])
@@ -217,6 +224,7 @@ class LookerModel:
                 try:
                     parsed = load_and_preprocess_file(
                         path=included_file,
+                        reporter=reporter,
                         source_config=source_config,
                     )
                     seen_so_far.add(included_file)

datahub/ingestion/source/looker/looker_file_loader.py

@@ -4,7 +4,10 @@ from dataclasses import replace
 from typing import Dict, Optional
 
 from datahub.ingestion.source.looker.looker_config import LookerConnectionDefinition
-from datahub.ingestion.source.looker.looker_dataclasses import LookerViewFile
+from datahub.ingestion.source.looker.looker_dataclasses import (
+    LookerConstant,
+    LookerViewFile,
+)
 from datahub.ingestion.source.looker.looker_template_language import (
     load_and_preprocess_file,
 )
@@ -30,12 +33,14 @@ class LookerViewFileLoader:
         base_projects_folder: Dict[str, pathlib.Path],
         reporter: LookMLSourceReport,
         source_config: LookMLSourceConfig,
+        manifest_constants: Dict[str, LookerConstant] = {},
     ) -> None:
         self.viewfile_cache: Dict[str, Optional[LookerViewFile]] = {}
         self._root_project_name = root_project_name
         self._base_projects_folder = base_projects_folder
         self.reporter = reporter
         self.source_config = source_config
+        self.manifest_constants = manifest_constants
 
     def _load_viewfile(
         self, project_name: str, path: str, reporter: LookMLSourceReport
@@ -60,7 +65,7 @@ class LookerViewFileLoader:
             with open(path) as file:
                 raw_file_content = file.read()
         except Exception as e:
-            self.reporter.failure(
+            self.reporter.report_warning(
                 title="LKML File Loading Error",
                 message="A lookml file is not present on local storage or GitHub",
                 context=f"file path: {path}",
@@ -71,9 +76,15 @@ class LookerViewFileLoader:
         try:
             logger.debug(f"Loading viewfile {path}")
 
+            # load_and preprocess_file is called multiple times for loading view file from multiple flows.
+            # Flag resolve_constants is a hack to avoid passing around manifest_constants from all of the flows.
+            # This is fine as rest of flows do not need resolution of constants.
             parsed = load_and_preprocess_file(
                 path=path,
+                reporter=self.reporter,
                 source_config=self.source_config,
+                resolve_constants=True,
+                manifest_constants=self.manifest_constants,
             )
 
             looker_viewfile = LookerViewFile.from_looker_dict(
@@ -90,7 +101,7 @@ class LookerViewFileLoader:
             self.viewfile_cache[path] = looker_viewfile
             return looker_viewfile
         except Exception as e:
-            self.reporter.failure(
+            self.reporter.report_warning(
                 title="LKML File Parsing Error",
                 message="The input file is not lookml file",
                 context=f"file path: {path}",