This is an automated email from the ASF dual-hosted git repository.
ruifengz 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 91ca9cb89b59 [SPARK-54493][PYTHON] Fix assertSchemaEqual for MapType
91ca9cb89b59 is described below
commit 91ca9cb89b59376137c94e948be71bb024f6519b
Author: Tian Gao <[email protected]>
AuthorDate: Wed Nov 26 11:25:22 2025 +0800
[SPARK-54493][PYTHON] Fix assertSchemaEqual for MapType
### What changes were proposed in this pull request?
Deal with `MapType` in
`assertSchemaEqual.compare_datatypes_ignore_nullable`.
### Why are the changes needed?
Otherwise all `MapType` will be considered equal when `ignore_nullable ==
True`
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
A regression test is added
### Was this patch authored or co-authored using generative AI tooling?
No.
Closes #53216 from gaogaotiantian/fix-assert-schema-equal.
Authored-by: Tian Gao <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>
---
python/pyspark/sql/tests/test_utils.py | 7 +++++++
python/pyspark/testing/utils.py | 4 ++++
2 files changed, 11 insertions(+)
diff --git a/python/pyspark/sql/tests/test_utils.py
b/python/pyspark/sql/tests/test_utils.py
index 9ec977c2552e..08d360a19e81 100644
--- a/python/pyspark/sql/tests/test_utils.py
+++ b/python/pyspark/sql/tests/test_utils.py
@@ -1264,6 +1264,13 @@ class UtilsTestsMixin:
assertSchemaEqual(s1, s2)
+ def test_schema_ignore_nullable_map_unequal(self):
+ s1 = StructType([StructField("m", MapType(StringType(),
IntegerType()), True)])
+ s2 = StructType([StructField("m", MapType(IntegerType(),
StringType()), True)])
+
+ with self.assertRaises(PySparkAssertionError):
+ assertSchemaEqual(s1, s2, ignoreNullable=True)
+
def test_schema_ignore_nullable_struct_equal(self):
s1 = StructType(
[StructField("names", StructType([StructField("age",
IntegerType(), True)]), True)]
diff --git a/python/pyspark/testing/utils.py b/python/pyspark/testing/utils.py
index 2c13d2f74026..4ea3dbf30178 100644
--- a/python/pyspark/testing/utils.py
+++ b/python/pyspark/testing/utils.py
@@ -592,6 +592,10 @@ def assertSchemaEqual(
if dt1.typeName() == dt2.typeName():
if dt1.typeName() == "array":
return compare_datatypes_ignore_nullable(dt1.elementType,
dt2.elementType)
+ elif dt1.typeName() == "map":
+ return compare_datatypes_ignore_nullable(
+ dt1.keyType, dt2.keyType
+ ) and compare_datatypes_ignore_nullable(dt1.valueType,
dt2.valueType)
elif dt1.typeName() == "decimal":
# Fix for SPARK-51062: Compare precision and scale for decimal
types
return dt1.precision == dt2.precision and dt1.scale ==
dt2.scale
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
