c99bcb7fea
An initial API that exposes SparkSQL functionality in PySpark. A PythonRDD composed of dictionaries, with string keys and primitive values (boolean, float, int, long, string) can be converted into a SchemaRDD that supports sql queries. ``` from pyspark.context import SQLContext sqlCtx = SQLContext(sc) rdd = sc.parallelize([{"field1" : 1, "field2" : "row1"}, {"field1" : 2, "field2": "row2"}, {"field1" : 3, "field2": "row3"}]) srdd = sqlCtx.applySchema(rdd) sqlCtx.registerRDDAsTable(srdd, "table1") srdd2 = sqlCtx.sql("SELECT field1 AS f1, field2 as f2 from table1") srdd2.collect() ``` The last line yields ```[{"f1" : 1, "f2" : "row1"}, {"f1" : 2, "f2": "row2"}, {"f1" : 3, "f2": "row3"}]``` Author: Ahir Reddy <ahirreddy@gmail.com> Author: Michael Armbrust <michael@databricks.com> Closes #363 from ahirreddy/pysql and squashes the following commits: 0294497 [Ahir Reddy] Updated log4j properties to supress Hive Warns 307d6e0 [Ahir Reddy] Style fix 6f7b8f6 [Ahir Reddy] Temporary fix MIMA checker. Since we now assemble Spark jar with Hive, we don't want to check the interfaces of all of our hive dependencies 3ef074a [Ahir Reddy] Updated documentation because classes moved to sql.py 29245bf [Ahir Reddy] Cache underlying SchemaRDD instead of generating and caching PythonRDD f2312c7 [Ahir Reddy] Moved everything into sql.py a19afe4 [Ahir Reddy] Doc fixes 6d658ba [Ahir Reddy] Remove the metastore directory created by the HiveContext tests in SparkSQL 521ff6d [Ahir Reddy] Trying to get spark to build with hive ab95eba [Ahir Reddy] Set SPARK_HIVE=true on jenkins ded03e7 [Ahir Reddy] Added doc test for HiveContext 22de1d4 [Ahir Reddy] Fixed maven pyrolite dependency e4da06c [Ahir Reddy] Display message if hive is not built into spark 227a0be [Michael Armbrust] Update API links. Fix Hive example. 58e2aa9 [Michael Armbrust] Build Docs for pyspark SQL Api. Minor fixes. 4285340 [Michael Armbrust] Fix building of Hive API Docs. 38a92b0 [Michael Armbrust] Add note to future non-python developers about python docs. 337b201 [Ahir Reddy] Changed com.clearspring.analytics stream version from 2.4.0 to 2.5.1 to match SBT build, and added pyrolite to maven build 40491c9 [Ahir Reddy] PR Changes + Method Visibility 1836944 [Michael Armbrust] Fix comments. e00980f [Michael Armbrust] First draft of python sql programming guide. b0192d3 [Ahir Reddy] Added Long, Double and Boolean as usable types + unit test f98a422 [Ahir Reddy] HiveContexts 79621cf [Ahir Reddy] cleaning up cruft b406ba0 [Ahir Reddy] doctest formatting 20936a5 [Ahir Reddy] Added tests and documentation e4d21b4 [Ahir Reddy] Added pyrolite dependency 79f739d [Ahir Reddy] added more tests 7515ba0 [Ahir Reddy] added more tests :) d26ec5e [Ahir Reddy] added test e9f5b8d [Ahir Reddy] adding tests 906d180 [Ahir Reddy] added todo explaining cost of creating Row object in python 251f99d [Ahir Reddy] for now only allow dictionaries as input 09b9980 [Ahir Reddy] made jrdd explicitly lazy c608947 [Ahir Reddy] SchemaRDD now has all RDD operations 725c91e [Ahir Reddy] awesome row objects 55d1c76 [Ahir Reddy] return row objects 4fe1319 [Ahir Reddy] output dictionaries correctly be079de [Ahir Reddy] returning dictionaries works cd5f79f [Ahir Reddy] Switched to using Scala SQLContext e948bd9 [Ahir Reddy] yippie 4886052 [Ahir Reddy] even better c0fb1c6 [Ahir Reddy] more working 043ca85 [Ahir Reddy] working 5496f9f [Ahir Reddy] doesn't crash b8b904b [Ahir Reddy] Added schema rdd class 67ba875 [Ahir Reddy] java to python, and python to java bcc0f23 [Ahir Reddy] Java to python ab6025d [Ahir Reddy] compiling
73 lines
3 KiB
Python
73 lines
3 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 platform
|
|
from subprocess import Popen, PIPE
|
|
from threading import Thread
|
|
from py4j.java_gateway import java_import, JavaGateway, GatewayClient
|
|
|
|
|
|
SPARK_HOME = os.environ["SPARK_HOME"]
|
|
|
|
|
|
def launch_gateway():
|
|
# 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-class.cmd" if on_windows else "./bin/spark-class"
|
|
command = [os.path.join(SPARK_HOME, script), "py4j.GatewayServer",
|
|
"--die-on-broken-pipe", "0"]
|
|
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)
|
|
# Determine which ephemeral port the server started on:
|
|
port = int(proc.stdout.readline())
|
|
# 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=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
|