fixesadded for fmt

Author: jominjohny

tests/integration/test_dataset_checks.py

@@ -17,6 +17,7 @@
     is_aggr_not_equal,
     foreign_key,
     compare_datasets,
+    DatasetComparisonConfig,
     is_data_fresh_per_time_window,
     has_valid_schema,
 )
@@ -550,7 +551,7 @@ def test_dataset_compare(spark: SparkSession, set_utc_timezone):
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=False,
+        config=DatasetComparisonConfig(check_missing_records=False),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -659,8 +660,10 @@ def test_compare_datasets_with_diff_col_names_and_check_missing(spark: SparkSess
         columns=columns,
         ref_columns=ref_columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
-        exclude_columns=[F.col("score")],
+        config=DatasetComparisonConfig(
+            check_missing_records=True,
+            exclude_columns=[F.col("score")],
+        ),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -863,7 +866,7 @@ def test_dataset_compare_ref_as_table_and_skip_map_col(spark: SparkSession, set_
         columns=columns,
         ref_columns=columns,
         ref_table=ref_table,
-        check_missing_records=False,
+        config=DatasetComparisonConfig(check_missing_records=False),
     )
 
     actual: DataFrame = apply(df, spark, {})
@@ -955,7 +958,7 @@ def test_dataset_compare_with_no_columns_to_compare_and_check_missing(spark: Spa
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
+        config=DatasetComparisonConfig(check_missing_records=True),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -988,7 +991,7 @@ def test_dataset_compare_with_empty_ref_and_check_missing(spark: SparkSession):
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
+        config=DatasetComparisonConfig(check_missing_records=True),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -1042,7 +1045,7 @@ def test_dataset_compare_with_empty_df_and_check_missing(spark: SparkSession):
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
+        config=DatasetComparisonConfig(check_missing_records=True),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -1097,7 +1100,7 @@ def test_dataset_compare_with_empty_df_and_ref(spark: SparkSession):
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
+        config=DatasetComparisonConfig(check_missing_records=True),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -1155,7 +1158,7 @@ def test_dataset_compare_unsorted_df_columns(spark: SparkSession):
         columns=columns,
         ref_columns=columns,  # columns are matched by position, so the order of columns must align exactly
         ref_df_name="df_ref",
-        check_missing_records=True,
+        config=DatasetComparisonConfig(check_missing_records=True),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -1204,9 +1207,11 @@ def test_compare_dataset_disabled_null_safe_row_matching(spark: SparkSession):
         columns=columns,
         ref_columns=columns,  # columns are matched by position, so the order of columns must align exactly
         ref_df_name="df_ref",
-        check_missing_records=True,
-        null_safe_row_matching=False,
-        null_safe_column_value_matching=True,
+        config=DatasetComparisonConfig(
+            check_missing_records=True,
+            null_safe_row_matching=False,
+            null_safe_column_value_matching=True,
+        ),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})
@@ -1304,8 +1309,10 @@ def test_compare_dataset_disabled_null_safe_column_value_matching(spark: SparkSe
         columns=columns,
         ref_columns=columns,
         ref_df_name="df_ref",
-        check_missing_records=True,
-        null_safe_column_value_matching=False,
+        config=DatasetComparisonConfig(
+            check_missing_records=True,
+            null_safe_column_value_matching=False,
+        ),
     )
 
     actual: DataFrame = apply(df, spark, {"df_ref": df_ref})