package mobvista.dmp.datasource.tracking.mapreduce; import mobvista.dmp.common.CommonMapReduce; import mobvista.dmp.common.InstallTotalReducer; import mobvista.dmp.datasource.age.mapreduce.CalcDeviceAgeMR; import mobvista.dmp.util.MRUtils; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.LongWritable; import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.compress.GzipCodec; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; import java.io.IOException; /** * Created by liushuai on 2017/3/20 0020. */ public class TrackingInstallTotalMR { public static void main(String[] args) throws InterruptedException, IOException, ClassNotFoundException { Configuration conf = new Configuration(); conf.set("mapreduce.map.speculative", "true"); conf.set("mapreduce.reduce.speculative", "true"); conf.set("mapreduce.task.io.sort.mb", "500"); conf.set("mapreduce.reduce.java.opts", "-Xmx1536m"); conf.set("mapreduce.reduce.memory.mb", "2048"); conf.set("mapreduce.reduce.shuffle.parallelcopies", "50"); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); Job job = Job.getInstance(conf, "TrackingInstallTotalMR"); job.setJarByClass(CalcDeviceAgeMR.class); FileOutputFormat.setCompressOutput(job, true); FileOutputFormat.setOutputCompressorClass(job, GzipCodec.class); job.setMapperClass(TrackingInstallDailyMapper.class); job.setReducerClass(InstallTotalReducer.class); job.setMapOutputKeyClass(Text.class); job.setMapOutputValueClass(Text.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(NullWritable.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileInputFormat.addInputPath(job, new Path(otherArgs[1])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[2])); System.exit(job.waitForCompletion(true) ? 0 : 1); } public static class TrackingInstallDailyMapper extends Mapper<LongWritable, Text, Text, Text> { Text outKey = new Text(); Text outValue = new Text(); public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException { String[] array = MRUtils.SPLITTER.split(value.toString(), -1); if (array.length == 6) { // 3s install daily outKey.set(MRUtils.JOINER.join(array[0], array[1], array[2])); outValue.set(MRUtils.JOINER.join(array[3], array[4])); } else if (array.length == 4) { // 3s install total outKey.set(MRUtils.JOINER.join(array[0], array[1], array[2])); outValue.set(array[3]); } else { CommonMapReduce.setMetrics(context,"DMP","column_num_error", 1); return; } context.write(outKey, outValue); } } }