Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/2538#discussion_r18554701
--- Diff: python/pyspark/streaming/util.py ---
@@ -0,0 +1,113 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements. See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+import time
+from datetime import datetime
+import traceback
+
+from pyspark import SparkContext, RDD
+
+
+class TransformFunction(object):
+ """
+ This class is for py4j callback.
+ """
+ _emptyRDD = None
+
+ def __init__(self, ctx, func, *deserializers):
+ self.ctx = ctx
+ self.func = func
+ self.deserializers = deserializers
+
+ def call(self, milliseconds, jrdds):
+ try:
+ if self.ctx is None:
+ self.ctx = SparkContext._active_spark_context
+ if not self.ctx or not self.ctx._jsc:
+ # stopped
+ return
+
+ # extend deserializers with the first one
+ sers = self.deserializers
+ if len(sers) < len(jrdds):
+ sers += (sers[0],) * (len(jrdds) - len(sers))
+
+ rdds = [RDD(jrdd, self.ctx, ser) if jrdd else None
+ for jrdd, ser in zip(jrdds, sers)]
+ t = datetime.fromtimestamp(milliseconds / 1000.0)
+ r = self.func(t, *rdds)
+ if r:
+ return r._jrdd
+ except Exception:
+ traceback.print_exc()
+
+ def __repr__(self):
+ return "TransformFunction(%s)" % self.func
+
+ class Java:
+ implements =
['org.apache.spark.streaming.api.python.PythonTransformFunction']
+
+
+class TransformFunctionSerializer(object):
--- End diff --
This class could also use a docstring:
> This class implements a serializer for `PythonTransformFunction` Java
objects. This is necessary because the Java PythonTransformFunction objects
are actually Py4J references to Python objects and thus are not directly
serializable. When Java needs to serialize a PythonTransformFunction, it uses
this class to invoke Python, which returns the serialized function as a byte
array.
Does this sound okay (feel free to correct / amend if it's not)?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
