Github user giwa commented on a diff in the pull request: https://github.com/apache/spark/pull/2538#discussion_r18079928 --- Diff: python/pyspark/streaming/dstream.py --- @@ -0,0 +1,400 @@ +# +# 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. +# + +from itertools import chain, ifilter, imap +import operator + +from pyspark import RDD +from pyspark.storagelevel import StorageLevel +from pyspark.streaming.util import rddToFileName, RDDFunction, RDDFunction2 +from pyspark.rdd import portable_hash +from pyspark.streaming.duration import Seconds + + +__all__ = ["DStream"] + + +class DStream(object): + def __init__(self, jdstream, ssc, jrdd_deserializer): + self._jdstream = jdstream + self._ssc = ssc + self.ctx = ssc._sc + self._jrdd_deserializer = jrdd_deserializer + self.is_cached = False + self.is_checkpointed = False + + def context(self): + """ + Return the StreamingContext associated with this DStream + """ + return self._ssc + + def count(self): + """ + Return a new DStream which contains the number of elements in this DStream. + """ + return self.mapPartitions(lambda i: [sum(1 for _ in i)]).sum() + + def sum(self): + """ + Add up the elements in this DStream. + """ + return self.mapPartitions(lambda x: [sum(x)]).reduce(operator.add) + + def print_(self, label=None): + """ + Since print is reserved name for python, we cannot define a "print" method function. + This function prints serialized data in RDD in DStream because Scala and Java cannot + deserialized pickled python object. Please use DStream.pyprint() to print results. + + Call DStream.print() and this function will print byte array in the DStream + """ + # a hack to call print function in DStream + getattr(self._jdstream, "print")(label) --- End diff -- I am not sure print_ is needed for PythonSparkStreaming. Please remove "(label)" ``` getattr(self._jdstream, "print")(label) ``` I put this input parameter for debugging purpose to make sure which print is called when I use many print operation. ``` ------------------------------------------- Time: 123456789 ------------------------------------------- called after reduce ("a", 1) ("b", 22) ```
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org