Skip to content

fix(ingestion): use default generate_browse_path_v2 even if no pipeline_config #13117

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.

Sign up for GitHub

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

Draft
wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

fix(ingestion): use default generate_browse_path_v2 even if no pipeline_config #13117

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9cfe9d4
fix(ingestion): use default generate_browse_path_v2 even if no pipeli…
sgomezvillamor Apr 8, 2025
129bf6d
Merge branch 'master' into fix-ingestion-default-generate-browse-path-v2
sgomezvillamor Apr 8, 2025
5510bd4
fix golden files unit tests
sgomezvillamor Apr 8, 2025
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
7 changes: 2 additions & 5 deletions metadata-ingestion/src/datahub/ingestion/api/source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -420,12 +420,9 @@ def get_workunit_processors(self) -> List[Optional[MetadataWorkUnitProcessor]]:
Run in order, first in list is applied first. Be careful with order when overriding.
"""
browse_path_processor: Optional[MetadataWorkUnitProcessor] = None
if (
self.ctx.pipeline_config
and self.ctx.pipeline_config.flags.generate_browse_path_v2
):
if self.ctx.flags.generate_browse_path_v2:
browse_path_processor = self._get_browse_path_processor(
self.ctx.pipeline_config.flags.generate_browse_path_v2_dry_run
self.ctx.flags.generate_browse_path_v2_dry_run
)

auto_lowercase_dataset_urns: Optional[MetadataWorkUnitProcessor] = None
Expand Down
60 changes: 53 additions & 7 deletions metadata-ingestion/tests/unit/glue/glue_delta_mces_golden.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402207,
"lastObserved": 1744091634014,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -35,7 +35,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402207,
"lastObserved": 1744091634014,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -52,7 +52,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402207,
"lastObserved": 1744091634014,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -70,7 +70,28 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402207,
"lastObserved": 1744091634014,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)",
"urn": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)"
}
]
}
},
"systemMetadata": {
"lastObserved": 1744091634014,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand Down Expand Up @@ -1543,7 +1564,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402228,
"lastObserved": 1744091634026,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -1561,7 +1582,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402228,
"lastObserved": 1744091634026,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -1577,7 +1598,32 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402228,
"lastObserved": 1744091634026,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:glue,delta_platform_instance.delta-database.delta_table_1,PROD)",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)",
"urn": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)"
},
{
"id": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a",
"urn": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a"
}
]
}
},
"systemMetadata": {
"lastObserved": 1744091634027,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand Down
60 changes: 53 additions & 7 deletions metadata-ingestion/tests/unit/glue/glue_malformed_delta_mces_golden.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402490,
"lastObserved": 1744091635205,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -35,7 +35,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402490,
"lastObserved": 1744091635205,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -52,7 +52,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402491,
"lastObserved": 1744091635205,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -70,7 +70,28 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402491,
"lastObserved": 1744091635205,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)",
"urn": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)"
}
]
}
},
"systemMetadata": {
"lastObserved": 1744091635205,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand Down Expand Up @@ -123,7 +144,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402491,
"lastObserved": 1744091635206,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -141,7 +162,7 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402491,
"lastObserved": 1744091635206,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand All @@ -157,7 +178,32 @@
}
},
"systemMetadata": {
"lastObserved": 1743454402491,
"lastObserved": 1744091635206,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:glue,delta_platform_instance.delta-database.delta_table_1,PROD)",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)",
"urn": "urn:li:dataPlatformInstance:(urn:li:dataPlatform:glue,delta_platform_instance)"
},
{
"id": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a",
"urn": "urn:li:container:275c7ea5ecf956fd8d45e14228757a8a"
}
]
}
},
"systemMetadata": {
"lastObserved": 1744091635206,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
Expand Down
111 changes: 111 additions & 0 deletions metadata-ingestion/tests/unit/glue/glue_mces_golden.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,6 +76,22 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:0b9f1f731ecf6743be6207fec3dc9cba",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": []
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7",
Expand Down Expand Up @@ -150,6 +166,22 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": []
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:110bc08849d1c1bde5fc345dab5c3ae7",
Expand Down Expand Up @@ -224,6 +256,22 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "container",
"entityUrn": "urn:li:container:110bc08849d1c1bde5fc345dab5c3ae7",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": []
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"proposedSnapshot": {
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
Expand Down Expand Up @@ -467,6 +515,27 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:glue,flights-database.avro,PROD)",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:container:0b9f1f731ecf6743be6207fec3dc9cba",
"urn": "urn:li:container:0b9f1f731ecf6743be6207fec3dc9cba"
}
]
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"proposedSnapshot": {
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
Expand Down Expand Up @@ -667,6 +736,27 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:glue,test-database.test_jsons_markers,PROD)",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7",
"urn": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7"
}
]
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"proposedSnapshot": {
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
Expand Down Expand Up @@ -868,6 +958,27 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:glue,test-database.test_parquet,PROD)",
"changeType": "UPSERT",
"aspectName": "browsePathsV2",
"aspect": {
"json": {
"path": [
{
"id": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7",
"urn": "urn:li:container:bdf4342ea6899d162eae685bfe9074a7"
}
]
}
},
"systemMetadata": {
"lastObserved": 1586847600000,
"runId": "glue-source-tes",
"lastRunId": "no-run-id-provided"
}
},
{
"proposedSnapshot": {
"com.linkedin.pegasus2avro.metadata.snapshot.DataFlowSnapshot": {
Expand Down
Loading
Loading