Using fix seed to unblock 23.12 release; Move the blocked issues to 2…

…4.02 (#10009) Signed-off-by: Chong Gao <[email protected]> Co-authored-by: Chong Gao <[email protected]>
NVIDIA · Dec 11, 2023 · ac0e292 · ac0e292
1 parent d6bc300
commit ac0e292
Show file tree

Hide file tree

Showing 5 changed files with 7 additions and 1 deletion.
diff --git a/integration_tests/src/main/python/conditionals_test.py b/integration_tests/src/main/python/conditionals_test.py
@@ -219,6 +219,7 @@ def test_conditional_with_side_effects_col_scalar(data_gen):
 
 @pytest.mark.parametrize('data_gen', [mk_str_gen('[0-9]{1,20}')], ids=idfn)
 @pytest.mark.skipif(not is_jvm_charset_utf8(), reason="regular expressions require UTF-8")
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9992')
 def test_conditional_with_side_effects_cast(data_gen):
     test_conf=copy_and_update(
         ansi_enabled_conf, {'spark.rapids.sql.regexp.enabled': True})

diff --git a/integration_tests/src/main/python/delta_lake_delete_test.py b/integration_tests/src/main/python/delta_lake_delete_test.py
@@ -153,6 +153,7 @@ def generate_dest_data(spark):
 @pytest.mark.parametrize("use_cdf", [True, False], ids=idfn)
 @pytest.mark.parametrize("partition_columns", [None, ["a"]], ids=idfn)
 @pytest.mark.skipif(is_before_spark_320(), reason="Delta Lake writes are not supported before Spark 3.2.x")
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9884')
 def test_delta_delete_rows(spark_tmp_path, use_cdf, partition_columns):
     # Databricks changes the number of files being written, so we cannot compare logs unless there's only one slice
     num_slices_to_test = 1 if is_databricks_runtime() else 10
@@ -171,6 +172,7 @@ def generate_dest_data(spark):
 @pytest.mark.parametrize("use_cdf", [True, False], ids=idfn)
 @pytest.mark.parametrize("partition_columns", [None, ["a"]], ids=idfn)
 @pytest.mark.skipif(is_before_spark_320(), reason="Delta Lake writes are not supported before Spark 3.2.x")
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9884')
 def test_delta_delete_dataframe_api(spark_tmp_path, use_cdf, partition_columns):
     from delta.tables import DeltaTable
     data_path = spark_tmp_path + "/DELTA_DATA"

diff --git a/integration_tests/src/main/python/delta_lake_update_test.py b/integration_tests/src/main/python/delta_lake_update_test.py
@@ -122,6 +122,7 @@ def generate_dest_data(spark):
 @pytest.mark.parametrize("use_cdf", [True, False], ids=idfn)
 @pytest.mark.parametrize("partition_columns", [None, ["a"]], ids=idfn)
 @pytest.mark.skipif(is_before_spark_320(), reason="Delta Lake writes are not supported before Spark 3.2.x")
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9884')
 def test_delta_update_rows(spark_tmp_path, use_cdf, partition_columns):
     # Databricks changes the number of files being written, so we cannot compare logs unless there's only one slice
     num_slices_to_test = 1 if is_databricks_runtime() else 10

diff --git a/integration_tests/src/main/python/hash_aggregate_test.py b/integration_tests/src/main/python/hash_aggregate_test.py
@@ -396,6 +396,7 @@ def test_hash_reduction_sum(data_gen, conf):
 @pytest.mark.parametrize('data_gen', numeric_gens + decimal_gens + [
     DecimalGen(precision=38, scale=0), DecimalGen(precision=38, scale=-10)], ids=idfn)
 @pytest.mark.parametrize('conf', get_params(_confs, params_markers_for_confs), ids=idfn)
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9779')
 def test_hash_reduction_sum_full_decimal(data_gen, conf):
     assert_gpu_and_cpu_are_equal_collect(
         lambda spark: unary_op_df(spark, data_gen, length=100).selectExpr("SUM(a)"),

diff --git a/integration_tests/src/main/python/schema_evolution_test.py b/integration_tests/src/main/python/schema_evolution_test.py
@@ -16,7 +16,7 @@
 from conftest import is_not_utc
 from data_gen import *
 from datetime import date, datetime, timezone
-from marks import ignore_order
+from marks import ignore_order, datagen_overrides
 import pytest
 from spark_session import is_databricks_runtime, is_databricks113_or_later
 
@@ -63,6 +63,7 @@ def get_ddl(col_gen_pairs):
 @ignore_order(local=True)
 @pytest.mark.parametrize("format", _formats)
 @pytest.mark.xfail(condition = is_not_utc(), reason = 'xfail non-UTC time zone tests because of https://github.com/NVIDIA/spark-rapids/issues/9653')
+@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9807')
 def test_column_add_after_partition(spark_tmp_table_factory, format):
     # Databricks 10.4 appears to be missing https://issues.apache.org/jira/browse/SPARK-39417
     # so avoid generating nulls for numeric partitions