HyukjinKwon commented on a change in pull request #28648:
URL: https://github.com/apache/spark/pull/28648#discussion_r432928220
##########
File path: python/pyspark/context.py
##########
@@ -864,8 +865,21 @@ def union(self, rdds):
first_jrdd_deserializer = rdds[0]._jrdd_deserializer
if any(x._jrdd_deserializer != first_jrdd_deserializer for x in rdds):
rdds = [x._reserialize() for x in rdds]
- cls = SparkContext._jvm.org.apache.spark.api.java.JavaRDD
- jrdds = SparkContext._gateway.new_array(cls, len(rdds))
+ gw = SparkContext._gateway
+ jvm = SparkContext._jvm
+ jrdd_cls = jvm.org.apache.spark.api.java.JavaRDD
+ jpair_rdd_cls = jvm.org.apache.spark.api.java.JavaPairRDD
+ jdouble_rdd_cls = jvm.org.apache.spark.api.java.JavaDoubleRDD
+ if is_instance_of(gw, rdds[0]._jrdd, jrdd_cls):
+ cls = jrdd_cls
+ elif is_instance_of(gw, rdds[0]._jrdd, jpair_rdd_cls):
+ cls = jpair_rdd_cls
+ elif is_instance_of(gw, rdds[0]._jrdd, jdouble_rdd_cls):
+ cls = jdouble_rdd_cls
+ else:
+ cls_name = rdds[0]._jrdd.getClass().getCanonicalName()
+ raise TypeError("Unsupported Java RDD class %s" % cls_name)
+ jrdds = gw.new_array(cls, len(rdds))
Review comment:
Nope, it seems not working:
```
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/.../spark/python/pyspark/context.py", line 885, in union
return RDD(self._jsc.union(jrdds), self, rdds[0]._jrdd_deserializer)
File "/.../spark/python/lib/py4j-0.10.9-src.zip/py4j/java_gateway.py",
line 1305, in __call__
File "/.../spark/python/pyspark/sql/utils.py", line 98, in deco
return f(*a, **kw)
File "/.../spark/python/lib/py4j-0.10.9-src.zip/py4j/protocol.py", line
332, in get_return_value
py4j.protocol.Py4JError: An error occurred while calling o15.union. Trace:
py4j.Py4JException: Method union([class
[Lorg.apache.spark.api.java.AbstractJavaRDDLike;]) does not exist
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:318)
at py4j.reflection.ReflectionEngine.getMethod(ReflectionEngine.java:326)
at py4j.Gateway.invoke(Gateway.java:274)
at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132)
at py4j.commands.CallCommand.execute(CallCommand.java:79)
at py4j.GatewayConnection.run(GatewayConnection.java:238)
at java.lang.Thread.run(Thread.java:748)
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]