added skips

Author: Michael Myaskovsky

integration_tests/tests/test_all_columns_anomalies.py

@@ -1,5 +1,6 @@
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -28,6 +29,7 @@ def test_anomalyless_all_columns_anomalies(test_id: str, dbt_project: DbtProject
     assert all([res["status"] == "pass" for res in test_results])
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalous_all_columns_anomalies(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -52,6 +54,7 @@ def test_anomalous_all_columns_anomalies(test_id: str, dbt_project: DbtProject):
     assert col_to_status == {"superhero": "fail", TIMESTAMP_COLUMN: "pass"}
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_all_columns_anomalies_with_where_expression(
     test_id: str, dbt_project: DbtProject
 ):

integration_tests/tests/test_anomalies_backfill_logic.py

@@ -1,5 +1,6 @@
 import json
 from datetime import datetime, time, timedelta
+import pytest
 
 import dateutil.parser
 from data_generator import DATE_FORMAT, generate_dates
@@ -106,6 +107,7 @@ def test_full_backfill_for_non_incremental_model(dbt_project: DbtProject, test_i
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_partial_backfill_for_incremental_models(dbt_project: DbtProject, test_id: str):
     utc_today = datetime.utcnow().date()
     data_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -152,6 +154,7 @@ def test_partial_backfill_for_incremental_models(dbt_project: DbtProject, test_i
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_longer_backfill_in_case_of_a_gap(dbt_project: DbtProject, test_id: str):
     date_gap_size = 5
     utc_today = datetime.utcnow().date()
@@ -204,6 +207,7 @@ def test_longer_backfill_in_case_of_a_gap(dbt_project: DbtProject, test_id: str)
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_full_backfill_if_metric_not_updated_for_a_long_time(
     dbt_project: DbtProject, test_id: str
 ):
@@ -263,6 +267,7 @@ def test_full_backfill_if_metric_not_updated_for_a_long_time(
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_backfill_when_metric_doesnt_exist_back_enough(
     dbt_project: DbtProject, test_id: str
 ):
@@ -307,6 +312,7 @@ def test_backfill_when_metric_doesnt_exist_back_enough(
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_backfill_with_middle_buckets_gap(dbt_project: DbtProject, test_id: str):
     utc_today = datetime.utcnow().date()
     data_start = utc_today - timedelta(21)
@@ -375,6 +381,7 @@ def test_backfill_with_middle_buckets_gap(dbt_project: DbtProject, test_id: str)
     }
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_bucket_size_not_aligned_with_days(dbt_project: DbtProject, test_id: str):
     """
     In this test we choose a bucket size that is not aligned with one day - specifically 7 hours.

integration_tests/tests/test_anomalies_ranges.py

@@ -1,6 +1,7 @@
 import json
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -33,6 +34,7 @@ def get_latest_anomaly_test_points(dbt_project: DbtProject, test_id: str):
     return [json.loads(result["result_row"]) for result in results]
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomaly_ranges_are_valid(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -66,6 +68,7 @@ def test_anomaly_ranges_are_valid(test_id: str, dbt_project: DbtProject):
     assert all([row["min_value"] == row["max_value"] for row in anomaly_test_points])
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomaly_ranges_are_valid_with_seasonality(
     test_id: str, dbt_project: DbtProject
 ):

integration_tests/tests/test_anomaly_exclude_metrics.py

@@ -1,5 +1,6 @@
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -24,6 +25,7 @@
     time_bucket={"period": "hour", "count": 6},
     dates_step=timedelta(hours=6),
 )
+@pytest.mark.skip_targets(["clickhouse"])
 def test_exclude_specific_dates(
     test_id: str, dbt_project: DbtProject, time_bucket: dict, dates_step: timedelta
 ):
@@ -123,6 +125,7 @@ def test_exclude_specific_timestamps(test_id: str, dbt_project: DbtProject):
     assert test_result["status"] == "fail"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_exclude_date_range(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -158,6 +161,7 @@ def test_exclude_date_range(test_id: str, dbt_project: DbtProject):
     assert test_result["status"] == "fail"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_exclude_by_metric_value(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))

integration_tests/tests/test_collect_metrics.py

@@ -1,6 +1,7 @@
 from collections import defaultdict
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -91,6 +92,7 @@ def test_collect_no_timestamp_metrics(test_id: str, dbt_project: DbtProject):
     assert col_to_metric_names == EXPECTED_COL_TO_METRIC_NAMES
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_collect_group_by_metrics(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     data: List[Dict[str, Any]] = [

integration_tests/tests/test_column_anomalies.py

@@ -1,5 +1,6 @@
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -29,6 +30,7 @@ def test_anomalyless_column_anomalies(test_id: str, dbt_project: DbtProject):
     assert test_result["status"] == "pass"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalyless_no_timestamp_column_anomalies(
     test_id: str, dbt_project: DbtProject
 ):
@@ -49,6 +51,7 @@ def test_anomalyless_no_timestamp_column_anomalies(
     assert test_result["status"] == "pass"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalous_column_anomalies(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -72,6 +75,7 @@ def test_anomalous_column_anomalies(test_id: str, dbt_project: DbtProject):
     assert test_result["status"] == "fail"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_column_anomalies_with_where_parameter(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -172,6 +176,7 @@ def test_column_anomalies_with_timestamp_as_sql_expression(
     drop_failure_percent_threshold=5,
     metric_value=1,
 )
+@pytest.mark.skip_targets(["clickhouse"])
 def test_volume_anomaly_static_data_drop(
     test_id: str,
     dbt_project: DbtProject,
@@ -236,6 +241,7 @@ def test_anomalyless_column_anomalies_group(test_id: str, dbt_project: DbtProjec
     assert test_result["status"] == "pass"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_column_anomalies_group_by(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -289,6 +295,7 @@ def test_column_anomalies_group_by(test_id: str, dbt_project: DbtProject):
     assert test_result["failures"] == 2
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalyless_column_anomalies_group_by_none_dimension(
     test_id: str, dbt_project: DbtProject
 ):
@@ -333,6 +340,7 @@ def test_anomalyless_column_anomalies_group_by_none_dimension(
     assert test_result["failures"] == 2
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalyless_column_anomalies_group_by_multi(
     test_id: str, dbt_project: DbtProject
 ):
@@ -384,6 +392,7 @@ def test_anomalyless_column_anomalies_group_by_multi(
     assert test_result["failures"] == 3
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalyless_column_anomalies_group_by_description(
     test_id: str, dbt_project: DbtProject
 ):
@@ -418,6 +427,7 @@ def test_anomalyless_column_anomalies_group_by_description(
     assert "not enough data" not in test_result["test_results_description"].lower()
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalous_boolean_column_anomalies(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))

integration_tests/tests/test_dbt_artifacts/test_artifacts.py

@@ -23,6 +23,7 @@ def test_artifacts_caching(dbt_project: DbtProject):
     assert first_row == second_row, "Artifacts are not cached at the on-run-end."
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_artifacts_updating(dbt_project: DbtProject):
     # Disabled by default in the tests for performance reasons.
     dbt_project.dbt_runner.vars["disable_dbt_artifacts_autoupload"] = False

integration_tests/tests/test_dimension_anomalies.py

@@ -1,6 +1,7 @@
 import json
 from datetime import datetime, timedelta
 from typing import Any, Dict, List
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -68,6 +69,7 @@ def test_dimension_anomalies_with_timestamp_as_sql_expression(
     assert test_result["status"] == "pass"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_anomalous_dimension_anomalies(test_id: str, dbt_project: DbtProject):
     utc_today = datetime.utcnow().date()
     test_date, *training_dates = generate_dates(base_date=utc_today - timedelta(1))
@@ -99,6 +101,7 @@ def test_anomalous_dimension_anomalies(test_id: str, dbt_project: DbtProject):
     assert anomaly_test_points[0]["dimension_value"] == "Superman"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_dimensions_anomalies_with_where_parameter(
     test_id: str, dbt_project: DbtProject
 ):
@@ -144,6 +147,7 @@ def test_dimensions_anomalies_with_where_parameter(
     assert test_result["status"] == "fail"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_dimension_anomalies_with_timestamp_exclude_final_results(
     test_id: str, dbt_project: DbtProject
 ):

integration_tests/tests/test_event_freshness_anomalies.py

@@ -1,4 +1,5 @@
 from datetime import datetime, timedelta
+import pytest
 
 from data_generator import DATE_FORMAT, generate_dates
 from dbt_project import DbtProject
@@ -29,6 +30,7 @@ def test_anomalyless_event_freshness(test_id: str, dbt_project: DbtProject):
     assert result["status"] == "pass"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_stop_event_freshness(test_id: str, dbt_project: DbtProject):
     anomaly_date = datetime.now() - timedelta(days=2)
     data = [
@@ -50,6 +52,7 @@ def test_stop_event_freshness(test_id: str, dbt_project: DbtProject):
     assert result["status"] == "fail"
 
 
+@pytest.mark.skip_targets(["clickhouse"])
 def test_slower_rate_event_freshness(test_id: str, dbt_project: DbtProject):
     # To avoid races, set the "custom_started_at" to the beginning of the day
     test_started_at = datetime.utcnow().replace(hour=0, minute=0, second=0)

integration_tests/tests/test_exposure_schema_validity.py

@@ -50,7 +50,7 @@ def test_exposure_schema_validity_no_exposures(test_id: str, dbt_project: DbtPro
     assert test_result["status"] == "pass"
 
 
-@pytest.mark.skip_targets(["spark"])
+@pytest.mark.skip_targets(["spark", "clickhouse"])
 def test_exposure_schema_validity_correct_columns_and_types(
     test_id: str, dbt_project: DbtProject
 ):
@@ -115,7 +115,7 @@ def test_exposure_schema_validity_correct_columns_and_invalid_type(
     assert test_result["status"] == "fail"
 
 
-@pytest.mark.skip_targets(["spark"])
+@pytest.mark.skip_targets(["spark", "clickhouse"])
 def test_exposure_schema_validity_invalid_type_name_present_in_error(
     test_id: str, dbt_project: DbtProject
 ):