Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(ingest/looker): Record observed lineage timestamps for Looker and LookML sources #7735

Merged
merged 4 commits into from
Aug 24, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@
from datahub.ingestion.source.state.stale_entity_removal_handler import (
StaleEntityRemovalSourceReport,
)
from datahub.metadata.com.linkedin.pegasus2avro.common import AuditStamp
from datahub.metadata.com.linkedin.pegasus2avro.dataset import (
DatasetLineageTypeClass,
FineGrainedLineageDownstreamType,
Expand Down Expand Up @@ -76,6 +77,8 @@
from datahub.utilities.lossy_collections import LossyList, LossySet
from datahub.utilities.url_util import remove_port_from_url

CORPUSER_DATAHUB = "urn:li:corpuser:datahub"

if TYPE_CHECKING:
from datahub.ingestion.source.looker.lookml_source import (
LookerViewFileLoader,
Expand Down Expand Up @@ -786,6 +789,7 @@ def _to_metadata_events( # noqa: C901
if self.upstream_views is not None:
assert self.project_name is not None
upstreams = []
observed_lineage_ts = datetime.datetime.now(tz=datetime.timezone.utc)
for view_ref in sorted(self.upstream_views):
view_urn = LookerViewId(
project_name=view_ref.project
Expand All @@ -799,6 +803,10 @@ def _to_metadata_events( # noqa: C901
UpstreamClass(
dataset=view_urn,
type=DatasetLineageTypeClass.VIEW,
auditStamp=AuditStamp(
time=int(observed_lineage_ts.timestamp() * 1000),
actor=CORPUSER_DATAHUB,
),
)
)
view_name_to_urn_map[view_ref.include] = view_urn
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
import re
import tempfile
from dataclasses import dataclass, field as dataclass_field, replace
from datetime import datetime, timedelta
from datetime import datetime, timedelta, timezone
from typing import (
Any,
ClassVar,
Expand Down Expand Up @@ -50,6 +50,7 @@
from datahub.ingestion.source.common.subtypes import DatasetSubTypes
from datahub.ingestion.source.git.git_import import GitClone
from datahub.ingestion.source.looker.looker_common import (
CORPUSER_DATAHUB,
LookerCommonConfig,
LookerExplore,
LookerUtil,
Expand Down Expand Up @@ -83,6 +84,7 @@
from datahub.metadata.com.linkedin.pegasus2avro.metadata.snapshot import DatasetSnapshot
from datahub.metadata.com.linkedin.pegasus2avro.mxe import MetadataChangeEvent
from datahub.metadata.schema_classes import (
AuditStampClass,
DatasetPropertiesClass,
FineGrainedLineageClass,
FineGrainedLineageUpstreamTypeClass,
Expand Down Expand Up @@ -1615,11 +1617,16 @@ def _get_upstream_lineage(

# Generate the upstream + fine grained lineage objects.
upstreams = []
observed_lineage_ts = datetime.now(tz=timezone.utc)
fine_grained_lineages: List[FineGrainedLineageClass] = []
for upstream_dataset_urn in upstream_dataset_urns:
upstream = UpstreamClass(
dataset=upstream_dataset_urn,
type=DatasetLineageTypeClass.VIEW,
auditStamp=AuditStampClass(
time=int(observed_lineage_ts.timestamp() * 1000),
actor=CORPUSER_DATAHUB,
),
)
upstreams.append(upstream)

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -262,8 +262,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down Expand Up @@ -412,8 +412,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,8 +206,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,8 +206,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,datahub-demo.view.faa_flights,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -279,8 +279,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down Expand Up @@ -429,8 +429,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,8 +206,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,32 +206,32 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_joined_view,PROD)",
"type": "VIEW"
},
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_joined_view_original_name,PROD)",
"type": "VIEW"
},
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_view_has_no_fields,PROD)",
"type": "VIEW"
},
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,24 +206,24 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_joined_view_original_name,PROD)",
"type": "VIEW"
},
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_view,PROD)",
"type": "VIEW"
},
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.my_view_has_no_fields,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -206,8 +206,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -158,8 +158,8 @@
"upstreams": [
{
"auditStamp": {
"time": 0,
"actor": "urn:li:corpuser:unknown"
"time": 1586847600000,
"actor": "urn:li:corpuser:datahub"
},
"dataset": "urn:li:dataset:(urn:li:dataPlatform:looker,lkml_samples.view.underlying_view,PROD)",
"type": "VIEW"
Expand Down
Loading