This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new b2140d0f25d8 [SPARK-48248][PYTHON] Fix nested array to respect legacy
conf of inferArrayTypeFromFirstElement
b2140d0f25d8 is described below
commit b2140d0f25d81e64a968df83c5da5089051acaac
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
### What changes were proposed in this pull request?
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.
### Why are the changes needed?
To have a way to restore the original behaviour.
### Does this PR introduce _any_ user-facing change?
Yes, it fixes the regression when
`spark.sql.pyspark.legacy.inferArrayTypeFromFirstElement.enabled` is set to
`True`.
### How was this patch tested?
Unittest added.
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #46548 from HyukjinKwon/SPARK-48248.
Authored-by: Hyukjin Kwon <gurwls...@apache.org>
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 9c931d861c18..bd99804ec565 100644
--- a/python/pyspark/sql/tests/test_types.py
+++ b/python/pyspark/sql/tests/test_types.py
@@ -1621,6 +1621,13 @@ class TypesTestsMixin:
StringType("UTF8_BINARY_LCASE"),
)
+ 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 41be12620fd5..fbd4987713e2 100644
--- a/python/pyspark/sql/types.py
+++ b/python/pyspark/sql/types.py
@@ -1951,13 +1951,27 @@ 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
