From 0561c4544967fb853419f32e014fac9b8879b0db Mon Sep 17 00:00:00 2001 From: Davies Liu Date: Mon, 2 Feb 2015 19:16:27 -0800 Subject: [SPARK-5154] [PySpark] [Streaming] Kafka streaming support in Python This PR brings the Python API for Spark Streaming Kafka data source. ``` class KafkaUtils(__builtin__.object) | Static methods defined here: | | createStream(ssc, zkQuorum, groupId, topics, storageLevel=StorageLevel(True, True, False, False, 2), keyDecoder=, valueDecoder=) | Create an input stream that pulls messages from a Kafka Broker. | | :param ssc: StreamingContext object | :param zkQuorum: Zookeeper quorum (hostname:port,hostname:port,..). | :param groupId: The group id for this consumer. | :param topics: Dict of (topic_name -> numPartitions) to consume. | Each partition is consumed in its own thread. | :param storageLevel: RDD storage level. | :param keyDecoder: A function used to decode key | :param valueDecoder: A function used to decode value | :return: A DStream object ``` run the example: ``` bin/spark-submit --driver-class-path external/kafka-assembly/target/scala-*/spark-streaming-kafka-assembly-*.jar examples/src/main/python/streaming/kafka_wordcount.py localhost:2181 test ``` Author: Davies Liu Author: Tathagata Das Closes #3715 from davies/kafka and squashes the following commits: d93bfe0 [Davies Liu] Update make-distribution.sh 4280d04 [Davies Liu] address comments e6d0427 [Davies Liu] Merge branch 'master' of github.com:apache/spark into kafka f257071 [Davies Liu] add tests for null in RDD 23b039a [Davies Liu] address comments 9af51c4 [Davies Liu] Merge branch 'kafka' of github.com:davies/spark into kafka a74da87 [Davies Liu] address comments dc1eed0 [Davies Liu] Update kafka_wordcount.py 31e2317 [Davies Liu] Update kafka_wordcount.py 370ba61 [Davies Liu] Update kafka.py 97386b3 [Davies Liu] address comment 2c567a5 [Davies Liu] update logging and comment 33730d1 [Davies Liu] Merge branch 'master' of github.com:apache/spark into kafka adeeb38 [Davies Liu] Merge pull request #3 from tdas/kafka-python-api aea8953 [Tathagata Das] Kafka-assembly for Python API eea16a7 [Davies Liu] refactor f6ce899 [Davies Liu] add example and fix bugs 98c8d17 [Davies Liu] fix python style 5697a01 [Davies Liu] bypass decoder in scala 048dbe6 [Davies Liu] fix python style 75d485e [Davies Liu] add mqtt 07923c4 [Davies Liu] support kafka in Python --- python/pyspark/streaming/kafka.py | 83 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) create mode 100644 python/pyspark/streaming/kafka.py (limited to 'python/pyspark/streaming/kafka.py') diff --git a/python/pyspark/streaming/kafka.py b/python/pyspark/streaming/kafka.py new file mode 100644 index 0000000000..19ad71f99d --- /dev/null +++ b/python/pyspark/streaming/kafka.py @@ -0,0 +1,83 @@ +# +# 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 py4j.java_collections import MapConverter +from py4j.java_gateway import java_import, Py4JError + +from pyspark.storagelevel import StorageLevel +from pyspark.serializers import PairDeserializer, NoOpSerializer +from pyspark.streaming import DStream + +__all__ = ['KafkaUtils', 'utf8_decoder'] + + +def utf8_decoder(s): + """ Decode the unicode as UTF-8 """ + return s and s.decode('utf-8') + + +class KafkaUtils(object): + + @staticmethod + def createStream(ssc, zkQuorum, groupId, topics, kafkaParams={}, + storageLevel=StorageLevel.MEMORY_AND_DISK_SER_2, + keyDecoder=utf8_decoder, valueDecoder=utf8_decoder): + """ + Create an input stream that pulls messages from a Kafka Broker. + + :param ssc: StreamingContext object + :param zkQuorum: Zookeeper quorum (hostname:port,hostname:port,..). + :param groupId: The group id for this consumer. + :param topics: Dict of (topic_name -> numPartitions) to consume. + Each partition is consumed in its own thread. + :param kafkaParams: Additional params for Kafka + :param storageLevel: RDD storage level. + :param keyDecoder: A function used to decode key (default is utf8_decoder) + :param valueDecoder: A function used to decode value (default is utf8_decoder) + :return: A DStream object + """ + java_import(ssc._jvm, "org.apache.spark.streaming.kafka.KafkaUtils") + + kafkaParams.update({ + "zookeeper.connect": zkQuorum, + "group.id": groupId, + "zookeeper.connection.timeout.ms": "10000", + }) + if not isinstance(topics, dict): + raise TypeError("topics should be dict") + jtopics = MapConverter().convert(topics, ssc.sparkContext._gateway._gateway_client) + jparam = MapConverter().convert(kafkaParams, ssc.sparkContext._gateway._gateway_client) + jlevel = ssc._sc._getJavaStorageLevel(storageLevel) + + def getClassByName(name): + return ssc._jvm.org.apache.spark.util.Utils.classForName(name) + + try: + array = getClassByName("[B") + decoder = getClassByName("kafka.serializer.DefaultDecoder") + jstream = ssc._jvm.KafkaUtils.createStream(ssc._jssc, array, array, decoder, decoder, + jparam, jtopics, jlevel) + except Py4JError, e: + # TODO: use --jar once it also work on driver + if not e.message or 'call a package' in e.message: + print "No kafka package, please put the assembly jar into classpath:" + print " $ bin/spark-submit --driver-class-path external/kafka-assembly/target/" + \ + "scala-*/spark-streaming-kafka-assembly-*.jar" + raise e + ser = PairDeserializer(NoOpSerializer(), NoOpSerializer()) + stream = DStream(jstream, ssc, ser) + return stream.map(lambda (k, v): (keyDecoder(k), valueDecoder(v))) -- cgit v1.2.3