07cb323e7a
This patch upgrades Py4J from 0.9.1 to 0.9.2 in order to include a patch which modifies Py4J to use the current thread's ContextClassLoader when performing reflection / class loading. This is necessary in order to fix [SPARK-5185](https://issues.apache.org/jira/browse/SPARK-5185), a longstanding issue affecting the use of `--jars` and `--packages` in PySpark. In order to demonstrate that the fix works, I removed the workarounds which were added as part of [SPARK-6027](https://issues.apache.org/jira/browse/SPARK-6027) / #4779 and other patches. Py4J diff: https://github.com/bartdag/py4j/compare/0.9.1...0.9.2 /cc zsxwing tdas davies brkyvz Author: Josh Rosen <joshrosen@databricks.com> Closes #11687 from JoshRosen/py4j-0.9.2.
71 lines
2.7 KiB
Python
71 lines
2.7 KiB
Python
#
|
|
# 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.protocol import Py4JJavaError
|
|
|
|
from pyspark.storagelevel import StorageLevel
|
|
from pyspark.serializers import UTF8Deserializer
|
|
from pyspark.streaming import DStream
|
|
|
|
__all__ = ['MQTTUtils']
|
|
|
|
|
|
class MQTTUtils(object):
|
|
|
|
@staticmethod
|
|
def createStream(ssc, brokerUrl, topic,
|
|
storageLevel=StorageLevel.MEMORY_AND_DISK_2):
|
|
"""
|
|
Create an input stream that pulls messages from a Mqtt Broker.
|
|
|
|
:param ssc: StreamingContext object
|
|
:param brokerUrl: Url of remote mqtt publisher
|
|
:param topic: topic name to subscribe to
|
|
:param storageLevel: RDD storage level.
|
|
:return: A DStream object
|
|
"""
|
|
try:
|
|
helper = ssc._jvm.org.apache.spark.streaming.mqtt.MQTTUtilsPythonHelper()
|
|
except TypeError as e:
|
|
if str(e) == "'JavaPackage' object is not callable":
|
|
MQTTUtils._printErrorMsg(ssc.sparkContext)
|
|
raise
|
|
|
|
jlevel = ssc._sc._getJavaStorageLevel(storageLevel)
|
|
jstream = helper.createStream(ssc._jssc, brokerUrl, topic, jlevel)
|
|
return DStream(jstream, ssc, UTF8Deserializer())
|
|
|
|
@staticmethod
|
|
def _printErrorMsg(sc):
|
|
print("""
|
|
________________________________________________________________________________________________
|
|
|
|
Spark Streaming's MQTT libraries not found in class path. Try one of the following.
|
|
|
|
1. Include the MQTT library and its dependencies with in the
|
|
spark-submit command as
|
|
|
|
$ bin/spark-submit --packages org.apache.spark:spark-streaming-mqtt:%s ...
|
|
|
|
2. Download the JAR of the artifact from Maven Central http://search.maven.org/,
|
|
Group Id = org.apache.spark, Artifact Id = spark-streaming-mqtt-assembly, Version = %s.
|
|
Then, include the jar in the spark-submit command as
|
|
|
|
$ bin/spark-submit --jars <spark-streaming-mqtt-assembly.jar> ...
|
|
________________________________________________________________________________________________
|
|
""" % (sc.version, sc.version))
|