Initial Commit

The completed code is provided.

Author: braunsonm

.env.template

@@ -0,0 +1,38 @@
+# Cluster environment; location of different resources on the driver
+CLUSTER_USER=
+REMOTE_PROJECT_ROOT=
+LOCAL_PROJECT_ROOT=
+SPARK_ROOT=
+HDFS_ROOT=
+JAVA_HOME=
+
+# Data paths
+LOCAL_DATA_DIR=
+HDFS_DATA_DIR=
+INGEST_SRC=$LOCAL_DATA_DIR/hdf5
+INGEST_DST=$HDFS_DATA_DIR/binary
+BENCHMARK_SRC=$HDFS_DATA_DIR/binary
+BENCHMARK_DST=$HDFS_DATA_DIR/benchmark-output
+
+# Run modifiers
+JAR=target/scala-2.11/hdf5-on-spark-assembly-1.0.jar
+BRANCH=master
+INGEST_SUBDIRS=""
+BENCHMARK_SUBDIRS=""
+BENCHMARKS="count threshold filter filterWithoutES"
+FILTER_ARGS=""
+
+# Cluster tunnel; ssh connection to reach cluster driver
+TUNNEL_SPEC=
+
+# Spark cluster configuration; overrides spark-defaults.conf
+SPARK_MASTER=spark://$(hostname):7077
+DRIVER_CORES=
+DRIVER_MEMORY=
+NUM_EXECUTORS=
+TOTAL_EXECUTOR_CORES=
+CORES_PER_EXECUTOR=
+TOTAL_EXECUTOR_CORES=
+MEMORY_PER_EXECUTOR=
+MEMORY_FRACTION=
+ELASTICSEARCH_HOSTS=localhost

.gitignore

@@ -0,0 +1,34 @@
+# Compiled class file
+*.class
+
+# Log file
+*.log
+
+# BlueJ files
+*.ctxt
+
+# Mobile Tools for Java (J2ME)
+.mtj.tmp/
+
+# Package Files #xw
+*.war
+*.nar
+*.ear
+*.zip
+*.tar.gz
+*.rar
+
+# virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
+hs_err_pid*
+
+target/
+.idea/
+/null/
+
+# Ignore hdf5 data
+/hdf5/
+/output/
+
+#ignore environment file
+.env
+*.python-version