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 for Google Dataplex system tests #38737

Merged
merged 1 commit into from
Apr 5, 2024
Merged

Fix for Google Dataplex system tests #38737

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
28 changes: 13 additions & 15 deletions tests/system/providers/google/cloud/dataplex/example_dataplex_dp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,10 +56,10 @@

DAG_ID = "example_dataplex_data_profile"

LAKE_ID = f"test-lake-{ENV_ID}"
LAKE_ID = f"lake-{DAG_ID}-{ENV_ID}".replace("_", "-")
REGION = "us-central1"

DATASET_NAME = f"dataset_bq_{ENV_ID}"
DATASET = f"dataset_bq_{DAG_ID}_{ENV_ID}"

TABLE_1 = "table0"
TABLE_2 = "table1"
Expand All @@ -70,15 +70,14 @@
{"name": "dt", "type": "STRING", "mode": "NULLABLE"},
]

DATASET = DATASET_NAME
INSERT_DATE = datetime.now().strftime("%Y-%m-%d")
INSERT_ROWS_QUERY = f"INSERT {DATASET}.{TABLE_1} VALUES (1, 'test test2', '{INSERT_DATE}');"
LOCATION = "us"

TRIGGER_SPEC_TYPE = "ON_DEMAND"

ZONE_ID = "test-zone-id"
DATA_SCAN_ID = "test-data-scan-id"
ZONE_ID = f"zone-id-{DAG_ID}-{ENV_ID}".replace("_", "-")
DATA_SCAN_ID = f"data-scan-id-{DAG_ID}-{ENV_ID}".replace("_", "-")

EXAMPLE_LAKE_BODY = {
"display_name": "test_display_name",
Expand All @@ -94,11 +93,11 @@
}
# [END howto_dataplex_zone_configuration]

ASSET_ID = "test-asset-id"
ASSET_ID = f"asset-id-{DAG_ID}-{ENV_ID}".replace("_", "-")

# [START howto_dataplex_asset_configuration]
EXAMPLE_ASSET = {
"resource_spec": {"name": f"projects/{PROJECT_ID}/datasets/{DATASET_NAME}", "type_": "BIGQUERY_DATASET"},
"resource_spec": {"name": f"projects/{PROJECT_ID}/datasets/{DATASET}", "type_": "BIGQUERY_DATASET"},
"discovery_spec": {"enabled": True},
}
# [END howto_dataplex_asset_configuration]
Expand Down Expand Up @@ -130,17 +129,17 @@
schedule="@once",
tags=["example", "dataplex", "data_profile"],
) as dag:
create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET_NAME)
create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET)
create_table_1 = BigQueryCreateEmptyTableOperator(
task_id="create_table_1",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
table_id=TABLE_1,
schema_fields=SCHEMA,
location=LOCATION,
)
create_table_2 = BigQueryCreateEmptyTableOperator(
task_id="create_table_2",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
table_id=TABLE_2,
schema_fields=SCHEMA,
location=LOCATION,
Expand Down Expand Up @@ -265,28 +264,28 @@
lake_id=LAKE_ID,
zone_id=ZONE_ID,
asset_id=ASSET_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_asset_operator]
delete_asset.trigger_rule = TriggerRule.ALL_DONE
# [START howto_dataplex_delete_zone_operator]
delete_zone = DataplexDeleteZoneOperator(
task_id="delete_zone",
project_id=PROJECT_ID,
region=REGION,
lake_id=LAKE_ID,
zone_id=ZONE_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_zone_operator]
delete_zone.trigger_rule = TriggerRule.ALL_DONE
# [START howto_dataplex_delete_data_profile_operator]
delete_data_scan = DataplexDeleteDataProfileScanOperator(
task_id="delete_data_scan",
project_id=PROJECT_ID,
region=REGION,
data_scan_id=DATA_SCAN_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_data_profile_operator]
delete_data_scan.trigger_rule = TriggerRule.ALL_DONE
delete_lake = DataplexDeleteLakeOperator(
project_id=PROJECT_ID,
region=REGION,
Expand All @@ -296,7 +295,7 @@
)
delete_dataset = BigQueryDeleteDatasetOperator(
task_id="delete_dataset",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
project_id=PROJECT_ID,
delete_contents=True,
trigger_rule=TriggerRule.ALL_DONE,
Expand All @@ -321,7 +320,6 @@
get_data_scan_job_result_2,
run_data_scan_def,
run_data_scan_async_2,
# get_data_scan_job_result_def,
# TEST TEARDOWN
delete_asset,
delete_zone,
Expand Down
27 changes: 13 additions & 14 deletions tests/system/providers/google/cloud/dataplex/example_dataplex_dq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,10 +56,10 @@

DAG_ID = "example_dataplex_data_quality"

LAKE_ID = f"test-lake-{ENV_ID}"
LAKE_ID = f"lake-{DAG_ID}-{ENV_ID}".replace("_", "-")
REGION = "us-central1"

DATASET_NAME = f"dataset_bq_{ENV_ID}"
DATASET = f"dataset_bq_{DAG_ID}_{ENV_ID}"

TABLE_1 = "table0"
TABLE_2 = "table1"
Expand All @@ -70,15 +70,14 @@
{"name": "dt", "type": "STRING", "mode": "NULLABLE"},
]

DATASET = DATASET_NAME
INSERT_DATE = datetime.now().strftime("%Y-%m-%d")
INSERT_ROWS_QUERY = f"INSERT {DATASET}.{TABLE_1} VALUES (1, 'test test2', '{INSERT_DATE}');"
LOCATION = "us"

TRIGGER_SPEC_TYPE = "ON_DEMAND"

ZONE_ID = "test-zone-id"
DATA_SCAN_ID = "test-data-scan-id"
ZONE_ID = f"zone-id-{DAG_ID}-{ENV_ID}".replace("_", "-")
DATA_SCAN_ID = f"data-scan-id-{DAG_ID}-{ENV_ID}".replace("_", "-")

EXAMPLE_LAKE_BODY = {
"display_name": "test_display_name",
Expand All @@ -94,11 +93,11 @@
}
# [END howto_dataplex_zone_configuration]

ASSET_ID = "test-asset-id"
ASSET_ID = f"asset-id-{DAG_ID}-{ENV_ID}".replace("_", "-")

# [START howto_dataplex_asset_configuration]
EXAMPLE_ASSET = {
"resource_spec": {"name": f"projects/{PROJECT_ID}/datasets/{DATASET_NAME}", "type_": "BIGQUERY_DATASET"},
"resource_spec": {"name": f"projects/{PROJECT_ID}/datasets/{DATASET}", "type_": "BIGQUERY_DATASET"},
"discovery_spec": {"enabled": True},
}
# [END howto_dataplex_asset_configuration]
Expand Down Expand Up @@ -154,17 +153,17 @@
schedule="@once",
tags=["example", "dataplex", "data_quality"],
) as dag:
create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET_NAME)
create_dataset = BigQueryCreateEmptyDatasetOperator(task_id="create_dataset", dataset_id=DATASET)
create_table_1 = BigQueryCreateEmptyTableOperator(
task_id="create_table_1",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
table_id=TABLE_1,
schema_fields=SCHEMA,
location=LOCATION,
)
create_table_2 = BigQueryCreateEmptyTableOperator(
task_id="create_table_2",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
table_id=TABLE_2,
schema_fields=SCHEMA,
location=LOCATION,
Expand Down Expand Up @@ -298,28 +297,28 @@
lake_id=LAKE_ID,
zone_id=ZONE_ID,
asset_id=ASSET_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_asset_operator]
delete_asset.trigger_rule = TriggerRule.ALL_DONE
# [START howto_dataplex_delete_zone_operator]
delete_zone = DataplexDeleteZoneOperator(
task_id="delete_zone",
project_id=PROJECT_ID,
region=REGION,
lake_id=LAKE_ID,
zone_id=ZONE_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_zone_operator]
delete_zone.trigger_rule = TriggerRule.ALL_DONE
# [START howto_dataplex_delete_data_quality_operator]
delete_data_scan = DataplexDeleteDataQualityScanOperator(
task_id="delete_data_scan",
project_id=PROJECT_ID,
region=REGION,
data_scan_id=DATA_SCAN_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
# [END howto_dataplex_delete_data_quality_operator]
delete_data_scan.trigger_rule = TriggerRule.ALL_DONE
delete_lake = DataplexDeleteLakeOperator(
project_id=PROJECT_ID,
region=REGION,
Expand All @@ -329,7 +328,7 @@
)
delete_dataset = BigQueryDeleteDatasetOperator(
task_id="delete_dataset",
dataset_id=DATASET_NAME,
dataset_id=DATASET,
project_id=PROJECT_ID,
delete_contents=True,
trigger_rule=TriggerRule.ALL_DONE,
Expand Down