5d16d5bbfd
This pull request aims to resolve all outstanding PEP8 violations in PySpark. Author: Nicholas Chammas <nicholas.chammas@gmail.com> Author: nchammas <nicholas.chammas@gmail.com> Closes #1505 from nchammas/master and squashes the following commits: 98171af [Nicholas Chammas] [SPARK-2470] revert PEP 8 fixes to cloudpickle cba7768 [Nicholas Chammas] [SPARK-2470] wrap expression list in parentheses e178dbe [Nicholas Chammas] [SPARK-2470] style - change position of line break 9127d2b [Nicholas Chammas] [SPARK-2470] wrap expression lists in parentheses 22132a4 [Nicholas Chammas] [SPARK-2470] wrap conditionals in parentheses 24639bc [Nicholas Chammas] [SPARK-2470] fix whitespace for doctest 7d557b7 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to tests.py 8f8e4c0 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to storagelevel.py b3b96cf [Nicholas Chammas] [SPARK-2470] PEP8 fixes to statcounter.py d644477 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to worker.py aa3a7b6 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to sql.py 1916859 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to shell.py 95d1d95 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to serializers.py a0fec2e [Nicholas Chammas] [SPARK-2470] PEP8 fixes to mllib c85e1e5 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to join.py d14f2f1 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to __init__.py 81fcb20 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to resultiterable.py 1bde265 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to java_gateway.py 7fc849c [Nicholas Chammas] [SPARK-2470] PEP8 fixes to daemon.py ca2d28b [Nicholas Chammas] [SPARK-2470] PEP8 fixes to context.py f4e0039 [Nicholas Chammas] [SPARK-2470] PEP8 fixes to conf.py a6d5e4b [Nicholas Chammas] [SPARK-2470] PEP8 fixes to cloudpickle.py f0a7ebf [Nicholas Chammas] [SPARK-2470] PEP8 fixes to rddsampler.py 4dd148f [nchammas] Merge pull request #5 from apache/master f7e4581 [Nicholas Chammas] unrelated pep8 fix a36eed0 [Nicholas Chammas] name ec2 instances and security groups consistently de7292a [nchammas] Merge pull request #4 from apache/master 2e4fe00 [nchammas] Merge pull request #3 from apache/master 89fde08 [nchammas] Merge pull request #2 from apache/master 69f6e22 [Nicholas Chammas] PEP8 fixes 2627247 [Nicholas Chammas] broke up lines before they hit 100 chars 6544b7e [Nicholas Chammas] [SPARK-2065] give launched instances names 69da6cf [nchammas] Merge pull request #1 from apache/master
94 lines
3.9 KiB
Python
94 lines
3.9 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.
|
|
#
|
|
|
|
import os
|
|
import sys
|
|
import signal
|
|
import shlex
|
|
import platform
|
|
from subprocess import Popen, PIPE
|
|
from threading import Thread
|
|
from py4j.java_gateway import java_import, JavaGateway, GatewayClient
|
|
|
|
|
|
def launch_gateway():
|
|
SPARK_HOME = os.environ["SPARK_HOME"]
|
|
|
|
gateway_port = -1
|
|
if "PYSPARK_GATEWAY_PORT" in os.environ:
|
|
gateway_port = int(os.environ["PYSPARK_GATEWAY_PORT"])
|
|
else:
|
|
# Launch the Py4j gateway using Spark's run command so that we pick up the
|
|
# proper classpath and settings from spark-env.sh
|
|
on_windows = platform.system() == "Windows"
|
|
script = "./bin/spark-submit.cmd" if on_windows else "./bin/spark-submit"
|
|
submit_args = os.environ.get("PYSPARK_SUBMIT_ARGS")
|
|
submit_args = submit_args if submit_args is not None else ""
|
|
submit_args = shlex.split(submit_args)
|
|
command = [os.path.join(SPARK_HOME, script), "pyspark-shell"] + submit_args
|
|
if not on_windows:
|
|
# Don't send ctrl-c / SIGINT to the Java gateway:
|
|
def preexec_func():
|
|
signal.signal(signal.SIGINT, signal.SIG_IGN)
|
|
proc = Popen(command, stdout=PIPE, stdin=PIPE, preexec_fn=preexec_func)
|
|
else:
|
|
# preexec_fn not supported on Windows
|
|
proc = Popen(command, stdout=PIPE, stdin=PIPE)
|
|
|
|
try:
|
|
# Determine which ephemeral port the server started on:
|
|
gateway_port = proc.stdout.readline()
|
|
gateway_port = int(gateway_port)
|
|
except ValueError:
|
|
(stdout, _) = proc.communicate()
|
|
exit_code = proc.poll()
|
|
error_msg = "Launching GatewayServer failed"
|
|
error_msg += " with exit code %d! " % exit_code if exit_code else "! "
|
|
error_msg += "(Warning: unexpected output detected.)\n\n"
|
|
error_msg += gateway_port + stdout
|
|
raise Exception(error_msg)
|
|
|
|
# Create a thread to echo output from the GatewayServer, which is required
|
|
# for Java log output to show up:
|
|
class EchoOutputThread(Thread):
|
|
def __init__(self, stream):
|
|
Thread.__init__(self)
|
|
self.daemon = True
|
|
self.stream = stream
|
|
|
|
def run(self):
|
|
while True:
|
|
line = self.stream.readline()
|
|
sys.stderr.write(line)
|
|
EchoOutputThread(proc.stdout).start()
|
|
|
|
# Connect to the gateway
|
|
gateway = JavaGateway(GatewayClient(port=gateway_port), auto_convert=False)
|
|
|
|
# Import the classes used by PySpark
|
|
java_import(gateway.jvm, "org.apache.spark.SparkConf")
|
|
java_import(gateway.jvm, "org.apache.spark.api.java.*")
|
|
java_import(gateway.jvm, "org.apache.spark.api.python.*")
|
|
java_import(gateway.jvm, "org.apache.spark.mllib.api.python.*")
|
|
java_import(gateway.jvm, "org.apache.spark.sql.SQLContext")
|
|
java_import(gateway.jvm, "org.apache.spark.sql.hive.HiveContext")
|
|
java_import(gateway.jvm, "org.apache.spark.sql.hive.LocalHiveContext")
|
|
java_import(gateway.jvm, "org.apache.spark.sql.hive.TestHiveContext")
|
|
java_import(gateway.jvm, "scala.Tuple2")
|
|
|
|
return gateway
|