04e44b37cc
This PR update PySpark to support Python 3 (tested with 3.4). Known issue: unpickle array from Pyrolite is broken in Python 3, those tests are skipped. TODO: ec2/spark-ec2.py is not fully tested with python3. Author: Davies Liu <davies@databricks.com> Author: twneale <twneale@gmail.com> Author: Josh Rosen <joshrosen@databricks.com> Closes #5173 from davies/python3 and squashes the following commits: d7d6323 [Davies Liu] fix tests 6c52a98 [Davies Liu] fix mllib test 99e334f [Davies Liu] update timeout b716610 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 cafd5ec [Davies Liu] adddress comments from @mengxr bf225d7 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 179fc8d [Davies Liu] tuning flaky tests 8c8b957 [Davies Liu] fix ResourceWarning in Python 3 5c57c95 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 4006829 [Davies Liu] fix test 2fc0066 [Davies Liu] add python3 path 71535e9 [Davies Liu] fix xrange and divide 5a55ab4 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 125f12c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ed498c8 [Davies Liu] fix compatibility with python 3 820e649 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 e8ce8c9 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ad7c374 [Davies Liu] fix mllib test and warning ef1fc2f [Davies Liu] fix tests 4eee14a [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 20112ff [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 59bb492 [Davies Liu] fix tests 1da268c [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 ca0fdd3 [Davies Liu] fix code style 9563a15 [Davies Liu] add imap back for python 2 0b1ec04 [Davies Liu] make python examples work with Python 3 d2fd566 [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 a716d34 [Davies Liu] test with python 3.4 f1700e8 [Davies Liu] fix test in python3 671b1db [Davies Liu] fix test in python3 692ff47 [Davies Liu] fix flaky test 7b9699f [Davies Liu] invalidate import cache for Python 3.3+ 9c58497 [Davies Liu] fix kill worker 309bfbf [Davies Liu] keep compatibility 5707476 [Davies Liu] cleanup, fix hash of string in 3.3+ 8662d5b [Davies Liu] Merge branch 'master' of github.com:apache/spark into python3 f53e1f0 [Davies Liu] fix tests 70b6b73 [Davies Liu] compile ec2/spark_ec2.py in python 3 a39167e [Davies Liu] support customize class in __main__ 814c77b [Davies Liu] run unittests with python 3 7f4476e [Davies Liu] mllib tests passed d737924 [Davies Liu] pass ml tests 375ea17 [Davies Liu] SQL tests pass 6cc42a9 [Davies Liu] rename 431a8de [Davies Liu] streaming tests pass 78901a7 [Davies Liu] fix hash of serializer in Python 3 24b2f2e [Davies Liu] pass all RDD tests 35f48fe [Davies Liu] run future again 1eebac2 [Davies Liu] fix conflict in ec2/spark_ec2.py 6e3c21d [Davies Liu] make cloudpickle work with Python3 2fb2db3 [Josh Rosen] Guard more changes behind sys.version; still doesn't run 1aa5e8f [twneale] Turned out `pickle.DictionaryType is dict` == True, so swapped it out 7354371 [twneale] buffer --> memoryview I'm not super sure if this a valid change, but the 2.7 docs recommend using memoryview over buffer where possible, so hoping it'll work. b69ccdf [twneale] Uses the pure python pickle._Pickler instead of c-extension _pickle.Pickler. It appears pyspark 2.7 uses the pure python pickler as well, so this shouldn't degrade pickling performance (?). f40d925 [twneale] xrange --> range e104215 [twneale] Replaces 2.7 types.InstsanceType with 3.4 `object`....could be horribly wrong depending on how types.InstanceType is used elsewhere in the package--see http://bugs.python.org/issue8206 79de9d0 [twneale] Replaces python2.7 `file` with 3.4 _io.TextIOWrapper 2adb42d [Josh Rosen] Fix up some import differences between Python 2 and 3 854be27 [Josh Rosen] Run `futurize` on Python code: 7c5b4ce [Josh Rosen] Remove Python 3 check in shell.py.
96 lines
4.2 KiB
Python
96 lines
4.2 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.java_collections import MapConverter
|
|
from py4j.java_gateway import java_import, Py4JError, Py4JJavaError
|
|
|
|
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
|
|
"""
|
|
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)
|
|
|
|
try:
|
|
# Use KafkaUtilsPythonHelper to access Scala's KafkaUtils (see SPARK-6027)
|
|
helperClass = ssc._jvm.java.lang.Thread.currentThread().getContextClassLoader()\
|
|
.loadClass("org.apache.spark.streaming.kafka.KafkaUtilsPythonHelper")
|
|
helper = helperClass.newInstance()
|
|
jstream = helper.createStream(ssc._jssc, jparam, jtopics, jlevel)
|
|
except Py4JJavaError as e:
|
|
# TODO: use --jar once it also work on driver
|
|
if 'ClassNotFoundException' in str(e.java_exception):
|
|
print("""
|
|
________________________________________________________________________________________________
|
|
|
|
Spark Streaming's Kafka libraries not found in class path. Try one of the following.
|
|
|
|
1. Include the Kafka library and its dependencies with in the
|
|
spark-submit command as
|
|
|
|
$ bin/spark-submit --packages org.apache.spark:spark-streaming-kafka:%s ...
|
|
|
|
2. Download the JAR of the artifact from Maven Central http://search.maven.org/,
|
|
Group Id = org.apache.spark, Artifact Id = spark-streaming-kafka-assembly, Version = %s.
|
|
Then, include the jar in the spark-submit command as
|
|
|
|
$ bin/spark-submit --jars <spark-streaming-kafka-assembly.jar> ...
|
|
|
|
________________________________________________________________________________________________
|
|
|
|
""" % (ssc.sparkContext.version, ssc.sparkContext.version))
|
|
raise e
|
|
ser = PairDeserializer(NoOpSerializer(), NoOpSerializer())
|
|
stream = DStream(jstream, ssc, ser)
|
|
return stream.map(lambda k_v: (keyDecoder(k_v[0]), valueDecoder(k_v[1])))
|