Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/20307#discussion_r162260194
--- Diff: python/pyspark/sql/udf.py ---
@@ -310,14 +310,22 @@ def registerJavaFunction(self, name, javaClassName,
returnType=None):
... "javaStringLength",
"test.org.apache.spark.sql.JavaStringLength", IntegerType())
>>> spark.sql("SELECT javaStringLength('test')").collect()
[Row(UDF:javaStringLength(test)=4)]
+
>>> spark.udf.registerJavaFunction(
... "javaStringLength2",
"test.org.apache.spark.sql.JavaStringLength")
>>> spark.sql("SELECT javaStringLength2('test')").collect()
[Row(UDF:javaStringLength2(test)=4)]
+
+ >>> spark.udf.registerJavaFunction(
+ ... "javaStringLength3",
"test.org.apache.spark.sql.JavaStringLength", "integer")
+ >>> spark.sql("SELECT javaStringLength3('test')").collect()
+ [Row(UDF:javaStringLength3(test)=4)]
"""
jdt = None
if returnType is not None:
+ if not isinstance(returnType, DataType):
+ returnType = _parse_datatype_string(returnType)
--- End diff --
The param doc needs to be modified too.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
