2022. 08. 01(월) Spark & Hadoop 초격차 6일차

정렬 실습 1

SortWordCount

package com.fastcampus.hadoop;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
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.input.KeyValueTextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.hadoop.io.Text;

import java.io.IOException;

/** input Format을 기존에 사용했던 텍스트인풋포맷이 아닌 키밸류텍스트인풋포맷을 사용할 예정
 *  키밸류텍스트인풋포맷같은 경우 라인별로 데이터를 읽어서 키와 밸류로 파싱을 할 수 있게 인풋포맷이다.
 *  키와 밸류를 구분하기 위한 새퍼레이터 값을 지정해주어야 한다
 * */
public class SortWordCount extends Configured implements Tool {
    public static class SortMapper extends Mapper<Text, Text, LongWritable, Text> {
        @Override
        protected void map(Text key, Text value, Context context) throws IOException, InterruptedException {
            // (hadoop 3)
            context.write(new LongWritable(Long.parseLong(value.toString())), key);
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        Configuration conf = getConf();
        conf.set("mapreduce.input.keyvaluelinerecordreader.key.value.separator", "\t");

        Job job = Job.getInstance(conf, "SortWordCount");

        job.setJarByClass(SortWordCount.class);
        job.setMapperClass(SortMapper.class);
        job.setInputFormatClass(KeyValueTextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        job.setNumReduceTasks(1);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new SortWordCount(), args);
        System.exit(exitCode);
    }
}

Map-side join 실습

MapSideJoinDistCache

package com.fastcampus.hadoop;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.net.URI;
import java.util.HashMap;

/** Java API를 이용하여 분산캐시 등록하기 */
public class MapSideJoinDistCache extends Configured implements Tool {
    public static class MapSideJoinMapper extends Mapper<LongWritable, Text, Text, Text> {
        HashMap<String, String> departmentsMap = new HashMap<>();
        Text outKey = new Text();
        Text outValue = new Text();

        @Override
        protected void setup(Context context) throws IOException, InterruptedException {
            URI[] uris = context.getCacheFiles();
            for (URI uri : uris) {
                Path path = new Path(uri.getPath());
                loadDepartmentMap(path.getName());
            }
        }

        private void loadDepartmentMap(String fileName) throws FileNotFoundException, IOException {
            String line = "";
            try (BufferedReader br = new BufferedReader(new FileReader(fileName))) {
                while ((line = br.readLine()) != null) {
                    String[] split = line.split(",");
                    departmentsMap.put(split[0], split[1]);
                }
            }
        }

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // emp_no, birth_date, first_name, last_name, gender, hire_date, dept_no
            String[] split = value.toString().split(",");

            outKey.set(split[0]);
            String department = departmentsMap.get(split[6]);
            department = department == null ? "Not Found" : department;

            outValue.set(split[2] + "\t" + split[4] + "\t" + department);
            context.write(outKey, outValue);
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(getConf(), "MapSideJoinDistCache");
        job.addCacheFile(new URI("/user/fastcampus/join/input/departments"));

        job.setJarByClass(MapSideJoinDistCache.class);

        job.setMapperClass(MapSideJoinMapper.class);
        job.setNumReduceTasks(0);

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        return job.waitForCompletion(true) ? 0 : 1;
    }

    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new MapSideJoinDistCache(), args);
        System.exit(exitCode);
    }
}

Reduce-side join 실습 1

ReduceSideJoin

package com.fastcampus.hadoop;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.input.MultipleInputs;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

import java.io.IOException;
import java.util.HashMap;
import java.util.Map;

public class ReduceSideJoin extends Configured implements Tool {
    public static class EmployeeMapper extends Mapper<LongWritable, Text, Text, Text> {
        Text outKey = new Text();
        Text outValue = new Text();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // emp_no, birth_date, first_name, last_name, gender, hire_date, dept_no
            String[] split = value.toString().split(",");

            outKey.set(split[6]);
            outValue.set("1\t" + split[0] + "\t" + split[2] + "\t" + split[4]);
            context.write(outKey, outValue);
        }
    }

    public static class DepartmentMapper extends Mapper<LongWritable, Text, Text, Text> {
        Text outKey = new Text();
        Text outValue = new Text();

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
            // dept_no, dept_name
            String[] split = value.toString().split(",");

            outKey.set(split[0]);
            outValue.set("0\t" + split[1]);
            context.write(outKey, outValue);
        }
    }
    public static class ReduceJoinReducer extends Reducer<Text, Text, Text, Text> {
        Text outKey = new Text();
        Text outValue = new Text();

        @Override
        protected void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException {
            HashMap<String, String> employeeMap = new HashMap<>();
            String department = "";

            for (Text t : values) {
                String[] split = t.toString().split("\t");
                if (split[0].equals("0")) {
                    department = split[1];
                } else {
                    employeeMap.put(split[1], split[2] + "\t" + split[3]);
                }
            }

            for (Map.Entry<String, String> e : employeeMap.entrySet()) {
                outKey.set(e.getKey());
                // department 이름이 join 된 값으로 셋팅
                outValue.set(e.getValue() + "\t" + department);
                context.write(outKey, outValue);
            }
        }
    }

    @Override
    public int run(String[] args) throws Exception {
        Job job = Job.getInstance(getConf(), "ReduceSideJoin");

        job.setJarByClass(ReduceSideJoin.class);
        job.setReducerClass(ReduceJoinReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, EmployeeMapper.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, DepartmentMapper.class);

        FileOutputFormat.setOutputPath(job, new Path(args[2]));

        return job.waitForCompletion(true) ? 0 : 1;
    }
    public static void main(String[] args) throws Exception {
        int exitCode = ToolRunner.run(new ReduceSideJoin(), args);
        System.exit(exitCode);
    }
}