Github user nickwallen commented on a diff in the pull request: https://github.com/apache/metron/pull/1150#discussion_r208320208 --- Diff: metron-analytics/metron-profiler-spark/src/main/java/org/apache/metron/profiler/spark/BatchProfiler.java --- @@ -0,0 +1,188 @@ +/* + * + * 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. + * + */ +package org.apache.metron.profiler.spark; + +import com.google.common.collect.Maps; +import org.apache.metron.common.configuration.profiler.ProfilerConfig; +import org.apache.metron.profiler.MessageRoute; +import org.apache.metron.profiler.ProfilePeriod; +import org.apache.metron.profiler.spark.function.HBaseWriterFunction; +import org.apache.metron.profiler.spark.function.MessageRouterFunction; +import org.apache.metron.profiler.spark.function.ProfileBuilderFunction; +import org.apache.spark.api.java.function.MapFunction; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Encoders; +import org.apache.spark.sql.KeyValueGroupedDataset; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import java.io.Serializable; +import java.lang.invoke.MethodHandles; +import java.util.Map; +import java.util.Properties; +import java.util.concurrent.TimeUnit; + +import static org.apache.metron.profiler.spark.BatchProfilerConfig.PERIOD_DURATION; +import static org.apache.metron.profiler.spark.BatchProfilerConfig.PERIOD_DURATION_UNITS; +import static org.apache.metron.profiler.spark.BatchProfilerConfig.TELEMETRY_INPUT_FORMAT; +import static org.apache.metron.profiler.spark.BatchProfilerConfig.TELEMETRY_INPUT_PATH; +import static org.apache.spark.sql.functions.sum; + +/** + * A Profiler that generates profiles by consuming data in batch from archived telemetry. + * + * <p>The Batch Profiler is executed in Spark. + */ +public class BatchProfiler implements Serializable { + + protected static final Logger LOG = LoggerFactory.getLogger(MethodHandles.lookup().lookupClass()); + + /** + * Execute the Batch Profiler. + * + * @param spark The spark session. + * @param properties The profiler configuration properties. + * @param profiles The profile definitions. + * @return The number of profile measurements produced. + */ + public long execute(SparkSession spark, --- End diff -- This is the main method that drives the Batch Profiler. Its a good place to start reviewing.
---