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

Jump to bottom

Skip from_json overflow tests for [databricks] 14.3 #11719

Open
wants to merge 3 commits into
base: branch-24.12
Choose a base branch
from
+37 −3
Open

Skip from_json overflow tests for [databricks] 14.3 #11719

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
89fbe4f
Skip from_json overflow tests for [databricks] 14.3
mythrocks Nov 12, 2024
c59a007
Renamed the test input file.
mythrocks Nov 13, 2024
00372d6
Added the new "problematic" input file to all tests.
mythrocks Nov 14, 2024
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
37 changes: 35 additions & 2 deletions integration_tests/src/main/python/json_matrix_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -577,6 +577,7 @@ def test_json_tuple_dec_locale_non_aribic(std_input_path):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -671,6 +672,7 @@ def test_from_json_longs(std_input_path, input_file):
"invalid_ridealong_columns.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -702,6 +704,7 @@ def test_scan_json_decs(std_input_path, read_func, spark_tmp_table_factory, inpu
"invalid_ridealong_columns.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -731,6 +734,7 @@ def test_from_json_decs(std_input_path, input_file, dt):
"invalid_ridealong_columns.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/rapidsai/cudf/issues/15318')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(condition=is_spark_400_or_later(), reason='https://github.com/NVIDIA/spark-rapids/issues/11154')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -761,6 +765,7 @@ def test_scan_json_strings(std_input_path, read_func, spark_tmp_table_factory, i
"invalid_ridealong_columns.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/rapidsai/cudf/issues/15318')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -789,6 +794,7 @@ def test_from_json_strings(std_input_path, input_file):
"invalid_ridealong_columns.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -818,6 +824,7 @@ def test_get_json_object_formats(std_input_path, input_file):
"invalid_ridealong_columns.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -857,6 +864,7 @@ def test_get_json_object_child_formats(std_input_path, input_file):
"invalid_ridealong_columns.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
pytest.param("escaped_strings.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/11386')),
Expand Down Expand Up @@ -905,6 +913,7 @@ def test_from_json_bools(std_input_path, input_file):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -935,6 +944,7 @@ def test_scan_json_floats(std_input_path, read_func, spark_tmp_table_factory, in
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -963,6 +973,7 @@ def test_from_json_floats(std_input_path, input_file):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -993,6 +1004,7 @@ def test_scan_json_doubles(std_input_path, read_func, spark_tmp_table_factory, i
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1020,6 +1032,7 @@ def test_from_json_doubles(std_input_path, input_file):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
pytest.param("escaped_strings.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/9664')),
Expand Down Expand Up @@ -1053,6 +1066,7 @@ def test_scan_json_corrected_dates(std_input_path, read_func, spark_tmp_table_fa
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
pytest.param("escaped_strings.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/9664')),
Expand Down Expand Up @@ -1083,6 +1097,7 @@ def test_from_json_corrected_dates(std_input_path, input_file):
pytest.param("boolean_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10535')),
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1116,6 +1131,7 @@ def test_scan_json_corrected_timestamps(std_input_path, read_func, spark_tmp_tab
pytest.param("boolean_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10535')),
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1146,6 +1162,7 @@ def test_from_json_corrected_timestamps(std_input_path, input_file):
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10573')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/11491')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1175,6 +1192,7 @@ def test_scan_json_long_arrays(std_input_path, read_func, spark_tmp_table_factor
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10573')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/11491')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1202,6 +1220,7 @@ def test_from_json_long_arrays(std_input_path, input_file):
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10574')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1231,6 +1250,7 @@ def test_scan_json_string_arrays(std_input_path, read_func, spark_tmp_table_fact
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10574')),
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand All @@ -1257,7 +1277,11 @@ def test_from_json_string_arrays(std_input_path, input_file):
"single_quoted_strings.json",
"boolean_formatted.json",
"int_array_formatted.json",
pytest.param("int_struct_formatted.json", marks=pytest.mark.xfail(condition=is_before_spark_342(),reason='https://github.com/NVIDIA/spark-rapids/issues/10588')),
"int_struct_formatted.json",
mythrocks marked this conversation as resolved.
Show resolved Hide resolved
pytest.param("int_struct_formatted_problematic_rows.json", marks=pytest.mark.xfail(
condition=is_before_spark_342() or is_databricks_version_or_later(14, 3),
reason='Before Spark 3.4.2? https://github.com/NVIDIA/spark-rapids/issues/10588. '
'Databricks 14.3 or later? https://github.com/NVIDIA/spark-rapids/issues/11711.')),
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(condition=is_before_spark_342(),reason='https://github.com/NVIDIA/spark-rapids/issues/10588')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1286,7 +1310,11 @@ def test_scan_json_long_structs(std_input_path, read_func, spark_tmp_table_facto
"single_quoted_strings.json",
"boolean_formatted.json",
"int_array_formatted.json",
pytest.param("int_struct_formatted.json", marks=pytest.mark.xfail(condition=is_before_spark_342(),reason='https://github.com/NVIDIA/spark-rapids/issues/10588')),
"int_struct_formatted.json",
pytest.param("int_struct_formatted_problematic_rows.json", marks=pytest.mark.xfail(
condition=is_before_spark_342() or is_databricks_version_or_later(14, 3),
reason='Before Spark 3.4.2? https://github.com/NVIDIA/spark-rapids/issues/10588. '
'Databricks 14.3 or later? https://github.com/NVIDIA/spark-rapids/issues/11711.')),
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(condition=is_before_spark_342(),reason='https://github.com/NVIDIA/spark-rapids/issues/10588')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1314,6 +1342,7 @@ def test_from_json_long_structs(std_input_path, input_file):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1343,6 +1372,7 @@ def test_scan_json_string_structs(std_input_path, read_func, spark_tmp_table_fac
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1371,6 +1401,7 @@ def test_from_json_string_structs(std_input_path, input_file):
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10573')), # This does not fail on 38,0
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/11491')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1400,6 +1431,7 @@ def test_scan_json_dec_arrays(std_input_path, read_func, spark_tmp_table_factory
"boolean_formatted.json",
pytest.param("int_array_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/10573')), # This does not fail on 38,0
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
pytest.param("int_mixed_array_struct_formatted.json", marks=pytest.mark.xfail(reason='https://github.com/NVIDIA/spark-rapids/issues/11491')),
"bad_whitespace.json",
"escaped_strings.json",
Expand Down Expand Up @@ -1427,6 +1459,7 @@ def test_from_json_dec_arrays(std_input_path, input_file, dt):
"boolean_formatted.json",
"int_array_formatted.json",
"int_struct_formatted.json",
"int_struct_formatted_problematic_rows.json",
"int_mixed_array_struct_formatted.json",
"bad_whitespace.json",
"escaped_strings.json",
Expand Down
1 change: 0 additions & 1 deletion integration_tests/src/test/resources/int_struct_formatted.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,4 +2,3 @@
{"data": {"A": 1}}
{"data": {"B": 50}}
{"data": {"B": -128, "A": 127}}
{"data": {"B": 99999999999999999999, "A": -9999999999999999999}}
2 changes: 2 additions & 0 deletions integration_tests/src/test/resources/int_struct_formatted_problematic_rows.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
{"data": {"B": 99999999999999999999, "A": -9999999999999999999}}
{"data": {"A": 0, "B": "0"}}
Loading