New port: Apache Spark.

Apache Spark is a fast and general-purpose cluster computing system. It provides high-level APIs in Java, Scala and Python, and an optimized engine that supports general execution graphs. It also supports a rich set of higher-level tools including Spark SQL for SQL and structured data processing, MLlib for machine learning, GraphX for graph processing, and Spark Streaming. WWW: http://spark.apache.org/
svn path=/head/; revision=375075
2014-12-20 18:26:31 +00:00 · 2014-12-20 18:26:31 +00:00 · ba9632cb5b · 2021-03-31 03:12:20 +00:00
commit ba9632cb5b
parent 04deb4a5b7
8 changed files with 402 additions and 0 deletions
--- a/devel/Makefile
+++ b/devel/Makefile
@ -4691,6 +4691,7 @@
    SUBDIR += sparc64-binutils
    SUBDIR += sparc64-gcc
    SUBDIR += sparc64-xtoolchain-gcc
+    SUBDIR += spark
    SUBDIR += spatialindex
    SUBDIR += spdict
    SUBDIR += spin
--- a/devel/spark/Makefile
+++ b/devel/spark/Makefile
@ -0,0 +1,56 @@
+# Created by: Dmitry Sivachenko <demon@FreeBSD.org>
+# $FreeBSD$
+
+PORTNAME=	spark
+PORTVERSION=	1.2.0
+CATEGORIES=	devel java
+MASTER_SITES=	${MASTER_SITE_APACHE} \
+		LOCAL/demon/:maven \
+		http://people.freebsd.org/~demon/:maven
+MASTER_SITE_SUBDIR=${PORTNAME}/${PORTNAME}-${PORTVERSION}
+PKGNAMEPREFIX=	apache-
+DISTFILES=	${PORTNAME}-${PORTVERSION}.tgz FreeBSD-${PORTNAME}-${PORTVERSION}-maven-repository.tar.gz:maven
+DIST_SUBDIR=	hadoop
+
+MAINTAINER=	demon@FreeBSD.org
+COMMENT=	Fast big data processing engine
+
+LICENSE=	APACHE20
+
+BUILD_DEPENDS=	${LOCALBASE}/share/java/maven3/bin/mvn:${PORTSDIR}/devel/maven3
+RUN_DEPENDS=	bash:${PORTSDIR}/shells/bash \
+		${LOCALBASE}/share/hadoop/common/hadoop-common-2.4.1.jar:${PORTSDIR}/devel/hadoop2
+
+USES=		python:2
+USE_JAVA=	yes
+JAVA_VERSION=	1.7+
+MAKE_ENV+=	MAVEN_OPTS="-Xmx2g -XX:MaxPermSize=512M -XX:ReservedCodeCacheSize=512m"
+NO_ARCH=	YES
+
+USERS=		spark
+GROUPS=		spark
+
+USE_RC_SUBR=	spark_master spark_worker
+PLIST_SUB+=	SPARK_USER=spark SPARK_GROUP=spark VER=${PORTVERSION}
+SUB_LIST+=	SPARK_USER=spark SPARK_GROUP=spark
+
+do-build:
+	cd ${WRKSRC} && ${SETENV} ${MAKE_ENV} ${LOCALBASE}/share/java/maven3/bin/mvn --offline -Dmaven.repo.local=${WRKDIR}/m2 clean package -Dhadoop.version=2.4.1 -Pyarn -Phadoop-2.4 -DskipTests
+
+post-build:
+	${RM} ${WRKSRC}/bin/*.cmd ${WRKSRC}/sbin/spark-daemon.sh.orig
+
+do-install:
+	${MKDIR} ${STAGEDIR}${DATADIR}/lib ${STAGEDIR}${DATADIR}/examples ${STAGEDIR}${DATADIR}/bin ${STAGEDIR}${DATADIR}/sbin ${STAGEDIR}${DATADIR}/conf
+	${ECHO_CMD} "Spark $PORTVERSION built for Hadoop 2.4.1" > ${STAGEDIR}${DATADIR}/RELEASE
+	${INSTALL_DATA} ${WRKSRC}/assembly/target/scala*/*assembly*hadoop*.jar ${STAGEDIR}${DATADIR}/lib/
+	${INSTALL_DATA} ${WRKSRC}/examples/target/scala*/spark-examples*.jar ${STAGEDIR}${DATADIR}/lib/
+	cd ${WRKSRC}/examples && ${COPYTREE_SHARE} src ${STAGEDIR}${DATADIR}/examples/
+	cd ${WRKSRC}/bin && ${INSTALL_SCRIPT} * ${STAGEDIR}${DATADIR}/bin/
+	cd ${WRKSRC}/sbin && ${INSTALL_SCRIPT} * ${STAGEDIR}${DATADIR}/sbin/
+	cd ${WRKSRC} && ${COPYTREE_SHARE} python ${STAGEDIR}${DATADIR}/
+	${INSTALL_DATA} ${WRKSRC}/conf/*.template ${STAGEDIR}${DATADIR}/conf/
+	${MKDIR} ${STAGEDIR}/var/run/spark
+	${MKDIR} ${STAGEDIR}/var/log/spark
+
+.include <bsd.port.mk>
--- a/devel/spark/distinfo
+++ b/devel/spark/distinfo
@ -0,0 +1,4 @@
+SHA256 (hadoop/spark-1.2.0.tgz) = 3aa6a53c82413ccbc47c08ce942301e89a42de713554d8f7d6b0382bda12bf8c
+SIZE (hadoop/spark-1.2.0.tgz) = 10290089
+SHA256 (hadoop/FreeBSD-spark-1.2.0-maven-repository.tar.gz) = 1900449092a4262b63e5e18faa601fb89b9bcfb3e4da05b511b04cf005722289
+SIZE (hadoop/FreeBSD-spark-1.2.0-maven-repository.tar.gz) = 256573504
--- a/devel/spark/files/patch-sbin-spark-daemon.sh
+++ b/devel/spark/files/patch-sbin-spark-daemon.sh
@ -0,0 +1,26 @@
+--- sbin/spark-daemon.sh.orig	2014-12-20 14:07:28.000000000 +0300
+++ sbin/spark-daemon.sh	2014-12-20 14:07:31.000000000 +0300
+@@ -99,14 +99,6 @@
+ if [ "$SPARK_LOG_DIR" = "" ]; then
+   export SPARK_LOG_DIR="$SPARK_HOME/logs"
+ fi
+-mkdir -p "$SPARK_LOG_DIR"
+-touch "$SPARK_LOG_DIR"/.spark_test > /dev/null 2>&1
+-TEST_LOG_DIR=$?
+-if [ "${TEST_LOG_DIR}" = "0" ]; then
+-  rm -f "$SPARK_LOG_DIR"/.spark_test
+-else
+-  chown "$SPARK_IDENT_STRING" "$SPARK_LOG_DIR"
+-fi
+ 
+ if [ "$SPARK_PID_DIR" = "" ]; then
+   SPARK_PID_DIR=/tmp
+@@ -126,8 +118,6 @@
+ 
+   (start|spark-submit)
+ 
+-    mkdir -p "$SPARK_PID_DIR"
+-
+     if [ -f $pid ]; then
+       if kill -0 `cat $pid` > /dev/null 2>&1; then
+         echo $command running as process `cat $pid`.  Stop it first.
--- a/devel/spark/files/spark_master.in
+++ b/devel/spark/files/spark_master.in
@ -0,0 +1,30 @@
+#!/bin/sh
+#
+# PROVIDE: spark_master
+# REQUIRE: LOGIN
+# KEYWORD: shutdown
+#
+
+. /etc/rc.subr
+
+name=spark_master
+rcvar=spark_master_enable
+load_rc_config $name
+
+: ${spark_master_enable:=NO}
+: ${spark_master_port:=7077}
+: ${spark_master_webui_port:=8080}
+
+export SPARK_PID_DIR=/var/run/spark
+export SPARK_LOG_DIR=/var/log/spark
+export SPARK_MASTER_PORT=${spark_master_port}
+export SPARK_MASTER_WEBUI_PORT=${spark_master_webui_port}
+export SPARK_IDENT_STRING=%%SPARK_USER%%
+
+pidfile=${SPARK_PID_DIR}/spark-${SPARK_IDENT_STRING}-org.apache.spark.deploy.master.Master-1.pid
+start_cmd="/usr/bin/su -m %%SPARK_USER%% -c %%DATADIR%%/sbin/start-master.sh"
+stop_cmd="/usr/bin/su -m %%SPARK_USER%% -c %%DATADIR%%/sbin/stop-master.sh"
+
+export PATH=$PATH:%%LOCALBASE%%/bin
+
+run_rc_command "$1"
--- a/devel/spark/files/spark_worker.in
+++ b/devel/spark/files/spark_worker.in
@ -0,0 +1,29 @@
+#!/bin/sh
+#
+# PROVIDE: spark_worker
+# REQUIRE: LOGIN
+# KEYWORD: shutdown
+#
+
+. /etc/rc.subr
+
+name=spark_worker
+rcvar=spark_worker_enable
+load_rc_config $name
+
+: ${spark_worker_enable:=NO}
+: ${spark_worker_master:="spark://`hostname`:7077"}
+: ${spark_worker_dir:="/tmp/spark/worker"}
+
+export SPARK_PID_DIR=/var/run/spark
+export SPARK_LOG_DIR=/var/log/spark
+export SPARK_IDENT_STRING=%%SPARK_USER%%
+export SPARK_WORKER_DIR=${spark_worker_dir}
+
+pidfile=${SPARK_PID_DIR}/spark-${SPARK_IDENT_STRING}-org.apache.spark.deploy.worker.Worker-1.pid
+start_cmd="/usr/bin/su -m %%SPARK_USER%% -c \"%%DATADIR%%/sbin/start-slave.sh 1 ${spark_worker_master}\""
+stop_cmd='/usr/bin/su -m %%SPARK_USER%% -c "%%DATADIR%%/sbin/spark-daemon.sh stop org.apache.spark.deploy.worker.Worker 1"'
+
+export PATH=$PATH:%%LOCALBASE%%/bin
+
+run_rc_command "$1"
--- a/devel/spark/pkg-descr
+++ b/devel/spark/pkg-descr
@ -0,0 +1,7 @@
+Apache Spark is a fast and general-purpose cluster computing system.  It
+provides high-level APIs in Java, Scala and Python, and an optimized engine
+that supports general execution graphs.  It also supports a rich set of
+higher-level tools including Spark SQL for SQL and structured data processing,
+MLlib for machine learning, GraphX for graph processing, and Spark Streaming.
+
+WWW: http://spark.apache.org/
--- a/devel/spark/pkg-plist
+++ b/devel/spark/pkg-plist
@ -0,0 +1,249 @@
+%%DATADIR%%/RELEASE
+%%DATADIR%%/bin/beeline
+%%DATADIR%%/bin/compute-classpath.sh
+%%DATADIR%%/bin/load-spark-env.sh
+%%DATADIR%%/bin/pyspark
+%%DATADIR%%/bin/run-example
+%%DATADIR%%/bin/spark-class
+%%DATADIR%%/bin/spark-shell
+%%DATADIR%%/bin/spark-sql
+%%DATADIR%%/bin/spark-submit
+%%DATADIR%%/bin/utils.sh
+%%DATADIR%%/conf/fairscheduler.xml.template
+%%DATADIR%%/conf/log4j.properties.template
+%%DATADIR%%/conf/metrics.properties.template
+%%DATADIR%%/conf/slaves.template
+%%DATADIR%%/conf/spark-defaults.conf.template
+%%DATADIR%%/conf/spark-env.sh.template
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaHdfsLR.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaLogQuery.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaPageRank.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaSparkPi.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaStatusTrackerDemo.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaTC.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/JavaWordCount.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/ml/JavaCrossValidatorExample.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleParamsExample.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/ml/JavaSimpleTextClassificationPipeline.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaALS.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaDecisionTree.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaGradientBoostedTreesRunner.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaKMeans.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaLR.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/mllib/JavaRandomForestExample.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/sql/JavaSparkSQL.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/streaming/JavaCustomReceiver.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/streaming/JavaFlumeEventCount.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/streaming/JavaNetworkWordCount.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/streaming/JavaQueueStream.java
+%%DATADIR%%/examples/src/main/java/org/apache/spark/examples/streaming/JavaRecoverableNetworkWordCount.java
+%%DATADIR%%/examples/src/main/python/als.py
+%%DATADIR%%/examples/src/main/python/avro_inputformat.py
+%%DATADIR%%/examples/src/main/python/cassandra_inputformat.py
+%%DATADIR%%/examples/src/main/python/cassandra_outputformat.py
+%%DATADIR%%/examples/src/main/python/hbase_inputformat.py
+%%DATADIR%%/examples/src/main/python/hbase_outputformat.py
+%%DATADIR%%/examples/src/main/python/kmeans.py
+%%DATADIR%%/examples/src/main/python/logistic_regression.py
+%%DATADIR%%/examples/src/main/python/mllib/correlations.py
+%%DATADIR%%/examples/src/main/python/mllib/dataset_example.py
+%%DATADIR%%/examples/src/main/python/mllib/decision_tree_runner.py
+%%DATADIR%%/examples/src/main/python/mllib/kmeans.py
+%%DATADIR%%/examples/src/main/python/mllib/logistic_regression.py
+%%DATADIR%%/examples/src/main/python/mllib/random_forest_example.py
+%%DATADIR%%/examples/src/main/python/mllib/random_rdd_generation.py
+%%DATADIR%%/examples/src/main/python/mllib/sampled_rdds.py
+%%DATADIR%%/examples/src/main/python/mllib/word2vec.py
+%%DATADIR%%/examples/src/main/python/pagerank.py
+%%DATADIR%%/examples/src/main/python/parquet_inputformat.py
+%%DATADIR%%/examples/src/main/python/pi.py
+%%DATADIR%%/examples/src/main/python/sort.py
+%%DATADIR%%/examples/src/main/python/sql.py
+%%DATADIR%%/examples/src/main/python/streaming/hdfs_wordcount.py
+%%DATADIR%%/examples/src/main/python/streaming/network_wordcount.py
+%%DATADIR%%/examples/src/main/python/streaming/recoverable_network_wordcount.py
+%%DATADIR%%/examples/src/main/python/streaming/stateful_network_wordcount.py
+%%DATADIR%%/examples/src/main/python/transitive_closure.py
+%%DATADIR%%/examples/src/main/python/wordcount.py
+%%DATADIR%%/examples/src/main/resources/full_user.avsc
+%%DATADIR%%/examples/src/main/resources/kv1.txt
+%%DATADIR%%/examples/src/main/resources/people.json
+%%DATADIR%%/examples/src/main/resources/people.txt
+%%DATADIR%%/examples/src/main/resources/user.avsc
+%%DATADIR%%/examples/src/main/resources/users.avro
+%%DATADIR%%/examples/src/main/resources/users.parquet
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/BroadcastTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/CassandraCQLTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/CassandraTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/DriverSubmissionTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/ExceptionHandlingTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/GroupByTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/HBaseTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/HdfsTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LocalALS.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LocalFileLR.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LocalKMeans.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LocalLR.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LocalPi.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/LogQuery.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/MultiBroadcastTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SimpleSkewedGroupByTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SkewedGroupByTest.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkALS.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkHdfsLR.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkKMeans.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkLR.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkPageRank.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkPi.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkTC.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkTachyonHdfsLR.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/SparkTachyonPi.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/bagel/PageRankUtils.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRank.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/bagel/WikipediaPageRankStandalone.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/graphx/Analytics.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/graphx/LiveJournalPageRank.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/graphx/SynthBenchmark.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/ml/CrossValidatorExample.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/ml/SimpleParamsExample.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/ml/SimpleTextClassificationPipeline.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/AbstractParams.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/BinaryClassification.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/Correlations.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/CosineSimilarity.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/DatasetExample.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/DecisionTreeRunner.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/DenseKMeans.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/GradientBoostedTreesRunner.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/LinearRegression.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/MovieLensALS.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/MultivariateSummarizer.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/RandomRDDGeneration.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/SampledRDDs.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/SparseNaiveBayes.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingKMeansExample.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/StreamingLinearRegression.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnyPCA.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/mllib/TallSkinnySVD.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/pythonconverters/AvroConverters.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/pythonconverters/CassandraConverters.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/pythonconverters/HBaseConverters.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/sql/RDDRelation.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/sql/hive/HiveFromSpark.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/ActorWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/CustomReceiver.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/FlumeEventCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/FlumePollingEventCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/HdfsWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/MQTTWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/NetworkWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/QueueStream.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/RawNetworkGrep.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/RecoverableNetworkWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/StatefulNetworkWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/StreamingExamples.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterAlgebirdCMS.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterAlgebirdHLL.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/TwitterPopularTags.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/ZeroMQWordCount.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewGenerator.scala
+%%DATADIR%%/examples/src/main/scala/org/apache/spark/examples/streaming/clickstream/PageViewStream.scala
+%%DATADIR%%/lib/spark-assembly-%%VER%%-hadoop2.4.1.jar
+%%DATADIR%%/lib/spark-examples-%%VER%%-hadoop2.4.1.jar
+%%DATADIR%%/python/.gitignore
+%%DATADIR%%/python/build/py4j/__init__.py
+%%DATADIR%%/python/build/py4j/compat.py
+%%DATADIR%%/python/build/py4j/finalizer.py
+%%DATADIR%%/python/build/py4j/java_collections.py
+%%DATADIR%%/python/build/py4j/java_gateway.py
+%%DATADIR%%/python/build/py4j/protocol.py
+%%DATADIR%%/python/build/py4j/tests/__init__.py
+%%DATADIR%%/python/build/py4j/tests/byte_string_test.py
+%%DATADIR%%/python/build/py4j/tests/finalizer_test.py
+%%DATADIR%%/python/build/py4j/tests/java_array_test.py
+%%DATADIR%%/python/build/py4j/tests/java_callback_test.py
+%%DATADIR%%/python/build/py4j/tests/java_gateway_test.py
+%%DATADIR%%/python/build/py4j/tests/java_list_test.py
+%%DATADIR%%/python/build/py4j/tests/java_map_test.py
+%%DATADIR%%/python/build/py4j/tests/java_set_test.py
+%%DATADIR%%/python/build/py4j/tests/multithreadtest.py
+%%DATADIR%%/python/build/py4j/tests/py4j_callback_example.py
+%%DATADIR%%/python/build/py4j/tests/py4j_callback_example2.py
+%%DATADIR%%/python/build/py4j/tests/py4j_example.py
+%%DATADIR%%/python/build/py4j/version.py
+%%DATADIR%%/python/docs/Makefile
+%%DATADIR%%/python/docs/conf.py
+%%DATADIR%%/python/docs/epytext.py
+%%DATADIR%%/python/docs/index.rst
+%%DATADIR%%/python/docs/make.bat
+%%DATADIR%%/python/docs/make2.bat
+%%DATADIR%%/python/docs/pyspark.mllib.rst
+%%DATADIR%%/python/docs/pyspark.rst
+%%DATADIR%%/python/docs/pyspark.sql.rst
+%%DATADIR%%/python/docs/pyspark.streaming.rst
+%%DATADIR%%/python/lib/PY4J_LICENSE.txt
+%%DATADIR%%/python/lib/py4j-0.8.2.1-src.zip
+%%DATADIR%%/python/pyspark/__init__.py
+%%DATADIR%%/python/pyspark/accumulators.py
+%%DATADIR%%/python/pyspark/broadcast.py
+%%DATADIR%%/python/pyspark/cloudpickle.py
+%%DATADIR%%/python/pyspark/conf.py
+%%DATADIR%%/python/pyspark/context.py
+%%DATADIR%%/python/pyspark/daemon.py
+%%DATADIR%%/python/pyspark/files.py
+%%DATADIR%%/python/pyspark/heapq3.py
+%%DATADIR%%/python/pyspark/java_gateway.py
+%%DATADIR%%/python/pyspark/join.py
+%%DATADIR%%/python/pyspark/mllib/__init__.py
+%%DATADIR%%/python/pyspark/mllib/classification.py
+%%DATADIR%%/python/pyspark/mllib/clustering.py
+%%DATADIR%%/python/pyspark/mllib/common.py
+%%DATADIR%%/python/pyspark/mllib/feature.py
+%%DATADIR%%/python/pyspark/mllib/linalg.py
+%%DATADIR%%/python/pyspark/mllib/rand.py
+%%DATADIR%%/python/pyspark/mllib/recommendation.py
+%%DATADIR%%/python/pyspark/mllib/regression.py
+%%DATADIR%%/python/pyspark/mllib/stat.py
+%%DATADIR%%/python/pyspark/mllib/tests.py
+%%DATADIR%%/python/pyspark/mllib/tree.py
+%%DATADIR%%/python/pyspark/mllib/util.py
+%%DATADIR%%/python/pyspark/rdd.py
+%%DATADIR%%/python/pyspark/rddsampler.py
+%%DATADIR%%/python/pyspark/resultiterable.py
+%%DATADIR%%/python/pyspark/serializers.py
+%%DATADIR%%/python/pyspark/shell.py
+%%DATADIR%%/python/pyspark/shuffle.py
+%%DATADIR%%/python/pyspark/sql.py
+%%DATADIR%%/python/pyspark/statcounter.py
+%%DATADIR%%/python/pyspark/storagelevel.py
+%%DATADIR%%/python/pyspark/streaming/__init__.py
+%%DATADIR%%/python/pyspark/streaming/context.py
+%%DATADIR%%/python/pyspark/streaming/dstream.py
+%%DATADIR%%/python/pyspark/streaming/tests.py
+%%DATADIR%%/python/pyspark/streaming/util.py
+%%DATADIR%%/python/pyspark/tests.py
+%%DATADIR%%/python/pyspark/traceback_utils.py
+%%DATADIR%%/python/pyspark/worker.py
+%%DATADIR%%/python/run-tests
+%%DATADIR%%/python/test_support/SimpleHTTPServer.py
+%%DATADIR%%/python/test_support/hello.txt
+%%DATADIR%%/python/test_support/userlib-0.1-py%%PYTHON_VER%%.egg
+%%DATADIR%%/python/test_support/userlibrary.py
+%%DATADIR%%/sbin/slaves.sh
+%%DATADIR%%/sbin/spark-config.sh
+%%DATADIR%%/sbin/spark-daemon.sh
+%%DATADIR%%/sbin/spark-daemons.sh
+%%DATADIR%%/sbin/spark-executor
+%%DATADIR%%/sbin/start-all.sh
+%%DATADIR%%/sbin/start-history-server.sh
+%%DATADIR%%/sbin/start-master.sh
+%%DATADIR%%/sbin/start-slave.sh
+%%DATADIR%%/sbin/start-slaves.sh
+%%DATADIR%%/sbin/start-thriftserver.sh
+%%DATADIR%%/sbin/stop-all.sh
+%%DATADIR%%/sbin/stop-history-server.sh
+%%DATADIR%%/sbin/stop-master.sh
+%%DATADIR%%/sbin/stop-slaves.sh
+%%DATADIR%%/sbin/stop-thriftserver.sh
+@dir(%%SPARK_USER%%,%%SPARK_GROUP%%,) /var/log/spark
+@dir(%%SPARK_USER%%,%%SPARK_GROUP%%,) /var/run/spark