This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch branch-3.4
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/branch-3.4 by this push:
new 6e22f1108bf4 [SPARK-48248][PYTHON] Fix nested array to respect legacy
conf of inferArrayTypeFromFirstElement
6e22f1108bf4 is described below
commit 6e22f1108bf4c0d28b03f2618e308cde6fc7faa0
Author: Hyukjin Kwon <gurwls...@apache.org>
AuthorDate: Mon May 13 17:15:28 2024 +0900
[SPARK-48248][PYTHON] Fix nested array to respect legacy conf of
inferArrayTypeFromFirstElement
This PR fixes a bug that does not respect
`spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled` in nested
arrays, introduced by https://github.com/apache/spark/pull/36545.
To have a way to restore the original behaviour.
Yes, it fixes the regression when
`spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled` is set to
`True`.
Unittest added.
No.
Closes #46548 from HyukjinKwon/SPARK-48248.
Authored-by: Hyukjin Kwon <gurwls...@apache.org>
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
(cherry picked from commit b2140d0f25d81e64a968df83c5da5089051acaac)
Signed-off-by: Hyukjin Kwon <gurwls...@apache.org>
---
python/pyspark/sql/tests/test_types.py | 7 +++++++
python/pyspark/sql/types.py | 18 ++++++++++++++++--
2 files changed, 23 insertions(+), 2 deletions(-)
diff --git a/python/pyspark/sql/tests/test_types.py
b/python/pyspark/sql/tests/test_types.py
index c5a6a1756976..02e3476ffd3b 100644
--- a/python/pyspark/sql/tests/test_types.py
+++ b/python/pyspark/sql/tests/test_types.py
@@ -1192,6 +1192,13 @@ class TypesTestsMixin:
for n, (a, e) in enumerate(zip(actual, expected)):
self.assertEqual(a, e, "%s does not match with %s" % (exprs[n],
expected[n]))
+ def test_infer_array_element_type_with_struct(self):
+ # SPARK-48248: Nested array to respect legacy conf of
inferArrayTypeFromFirstElement
+ with self.sql_conf(
+
{"spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled": True}
+ ):
+ self.assertEqual([[1, None]], self.spark.createDataFrame([[[[1,
"a"]]]]).first()[0])
+
class DataTypeTests(unittest.TestCase):
# regression test for SPARK-6055
diff --git a/python/pyspark/sql/types.py b/python/pyspark/sql/types.py
index 21fef0a2c08a..c668c5c59eca 100644
--- a/python/pyspark/sql/types.py
+++ b/python/pyspark/sql/types.py
@@ -1508,13 +1508,27 @@ def _infer_type(
if len(obj) > 0:
if infer_array_from_first_element:
return ArrayType(
- _infer_type(obj[0], infer_dict_as_struct,
prefer_timestamp_ntz), True
+ _infer_type(
+ obj[0],
+ infer_dict_as_struct,
+ infer_array_from_first_element,
+ prefer_timestamp_ntz,
+ ),
+ True,
)
else:
return ArrayType(
reduce(
_merge_type,
- (_infer_type(v, infer_dict_as_struct,
prefer_timestamp_ntz) for v in obj),
+ (
+ _infer_type(
+ v,
+ infer_dict_as_struct,
+ infer_array_from_first_element,
+ prefer_timestamp_ntz,
+ )
+ for v in obj
+ ),
),
True,
)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscr...@spark.apache.org
For additional commands, e-mail: commits-h...@spark.apache.org
