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.

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

fix column lineage returning multiple entries for job run multiple times #2176

Merged
merged 1 commit into from
Oct 10, 2022
Merged

fix column lineage returning multiple entries for job run multiple times #2176

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 6 additions & 3 deletions api/src/main/java/marquez/db/ColumnLineageDao.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,9 +105,12 @@ dataset_fields_view AS (
INNER JOIN datasets_view d ON d.uuid = df.dataset_uuid
),
column_lineage_recursive AS (
SELECT *, 0 as depth
FROM column_lineage
WHERE output_dataset_field_uuid IN (<datasetFieldUuids>) AND created_at <= :createdAtUntil
(
SELECT DISTINCT ON (output_dataset_field_uuid, input_dataset_field_uuid) *, 0 as depth
FROM column_lineage
WHERE output_dataset_field_uuid IN (<datasetFieldUuids>) AND created_at <= :createdAtUntil
ORDER BY output_dataset_field_uuid, input_dataset_field_uuid, updated_at DESC, updated_at
)
UNION
SELECT
upstream_node.output_dataset_version_uuid,
Expand Down
28 changes: 28 additions & 0 deletions api/src/test/java/marquez/db/ColumnLineageDaoTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -565,4 +565,32 @@ void testGetLineagePointInTime() {
20, Collections.singletonList(field_col_b), columnLineageCreatedAt.plusSeconds(1)))
.hasSize(1);
}

@Test
void testGetLineageWhenJobRunMultipleTimes() {
Dataset dataset_A = getDatasetA();
Dataset dataset_B = getDatasetB();

LineageTestUtils.createLineageRow(
openLineageDao,
"job1",
"COMPLETE",
jobFacet,
Arrays.asList(dataset_A),
Arrays.asList(dataset_B));
UpdateLineageRow lineageRow =
LineageTestUtils.createLineageRow(
openLineageDao,
"job1",
"COMPLETE",
jobFacet,
Arrays.asList(dataset_A),
Arrays.asList(dataset_B));

UpdateLineageRow.DatasetRecord datasetRecord_b = lineageRow.getOutputs().get().get(0);
UUID field_col_b = fieldDao.findUuid(datasetRecord_b.getDatasetRow().getUuid(), "col_c").get();

assertThat(dao.getLineage(20, Collections.singletonList(field_col_b), Instant.now()))
.hasSize(1);
}
}