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

Fix year 0 is out of range in test_from_json_struct_timestamp #9972

Merged
merged 4 commits into from
Dec 7, 2023
Merged

Fix year 0 is out of range in test_from_json_struct_timestamp #9972

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5e1229a
Fix year 0 is out of range for test_from_json_struct_timestamp
thirtiseven Dec 6, 2023
eb19108
clean up
thirtiseven Dec 6, 2023
7e75ca2
address comments
thirtiseven Dec 6, 2023
bca3fbc
fix nit and typo
thirtiseven Dec 7, 2023
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
10 changes: 4 additions & 6 deletions integration_tests/src/main/python/cast_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,13 +61,11 @@ def test_cast_nested(data_gen, to_type):
assert_gpu_and_cpu_are_equal_collect(
lambda spark : unary_op_df(spark, data_gen).select(f.col('a').cast(to_type)))

date_after_1_2_1 = '(0{0,3}1-(0?[2-9]|[1-3][0-9]))|(([0-9]{0,3}[2-9]|[1-9][0-9]{0,2}[01])-[0-3]?[0-9])-[0-5]?[0-9]'

def test_cast_string_date_valid_format():
# In Spark 3.2.0+ the valid format changed, and we cannot support all of the format.
# This provides values that are valid in all of those formats.
assert_gpu_and_cpu_are_equal_collect(
lambda spark : unary_op_df(spark, StringGen(date_after_1_2_1)).select(f.col('a').cast(DateType())),
lambda spark : unary_op_df(spark, StringGen(date_start_1_2_1)).select(f.col('a').cast(DateType())),
conf = {'spark.rapids.sql.hasExtendedYearValues': 'false'})

invalid_values_string_to_date = ['200', ' 1970A', '1970 A', '1970T', # not conform to "yyyy" after trim
Expand Down Expand Up @@ -148,9 +146,9 @@ def test_cast_string_date_non_ansi():
lambda spark: spark.createDataFrame(data_rows, "a string").select(f.col('a').cast(DateType())),
conf={'spark.rapids.sql.hasExtendedYearValues': 'false'})

@pytest.mark.parametrize('data_gen', [StringGen(date_after_1_2_1),
StringGen(date_after_1_2_1 + '[ |T][0-3][0-9]:[0-6][0-9]:[0-6][0-9]'),
StringGen(date_after_1_2_1 + '[ |T][0-3][0-9]:[0-6][0-9]:[0-6][0-9]\.[0-9]{0,6}Z?')
@pytest.mark.parametrize('data_gen', [StringGen(date_start_1_2_1),
StringGen(date_start_1_2_1 + '[ |T][0-3][0-9]:[0-6][0-9]:[0-6][0-9]'),
StringGen(date_start_1_2_1 + '[ |T][0-3][0-9]:[0-6][0-9]:[0-6][0-9]\.[0-9]{0,6}Z?')
],
ids=idfn)
@allow_non_gpu(*non_utc_allow)
Expand Down
10 changes: 9 additions & 1 deletion integration_tests/src/main/python/data_gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1200,4 +1200,12 @@ def get_25_partitions_df(spark):
# This will be deprecated and replaced case specified non GPU allow list
non_utc_allow = ['ProjectExec', 'FilterExec', 'FileSourceScanExec', 'BatchScanExec', 'CollectLimitExec',
'DeserializeToObjectExec', 'DataWritingCommandExec', 'WriteFilesExec', 'ShuffleExchangeExec',
'ExecutedCommandExec'] if is_not_utc() else []
'ExecutedCommandExec'] if is_not_utc() else []

# date related regexps for generating date strings within python's range limits

# regexp to generate date from 0001-02-01, format is yyyy-MM-dd
date_start_1_2_1 = '(0{0,3}1-(0?[2-9]|[1-3][0-9]))|(([0-9]{0,3}[2-9]|[1-9][0-9]{0,2}[01])-[0-3]?[0-9])-[0-5]?[0-9]'
Copy link
Collaborator

@res-life res-life Dec 6, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Add comment like: regexp to generate date from 0001-02-01, format is yyyy-MM-dd

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done.


# regexp to generate year from 0002, forat is yyyy
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

typo: format

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

BTW, why starting from 0002?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think 0001 will be convert to 0001-01-01 as timestamp in this case, which is out of range.

yyyy_start_0002 = '([0-9]{3}[2-9]|([1-9][0-9]{2}|0[1-9][0-9]|00[1-9])[0-1])'
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: empty tailing line is missed

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

3 changes: 1 addition & 2 deletions integration_tests/src/main/python/json_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -637,7 +637,7 @@ def test_from_json_struct_date_fallback_non_default_format(date_gen, date_format
# "yyyy-MM"
"\"[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?[1-8]{1}[0-9]{3}-[0-3]{1,2}[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?\"",
# "yyyy"
"\"[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?[0-9]{4}[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?\"",
"\"[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?" + yyyy_start_0002 + "[ \t\xA0\u1680\u180e\u2000-\u200a\u202f\u205f\u3000]?\"",
# "dd/MM/yyyy"
"\"[0-9]{2}/[0-9]{2}/[1-8]{1}[0-9]{3}\"",
# special constant values
Expand All @@ -664,7 +664,6 @@ def test_from_json_struct_date_fallback_non_default_format(date_gen, date_format
pytest.param("LEGACY", marks=pytest.mark.allow_non_gpu('ProjectExec')),
"CORRECTED"
])
@datagen_overrides(seed=0, reason='https://github.com/NVIDIA/spark-rapids/issues/9747')
@pytest.mark.parametrize('ansi_enabled', [ True, False ])
def test_from_json_struct_timestamp(timestamp_gen, timestamp_format, time_parser_policy, ansi_enabled):
json_string_gen = StringGen(r'{ "a": ' + timestamp_gen + ' }') \
Expand Down