[hadoop](3) MapReduce:创建计数器、任务状态和写入日志

前言

本章主要讲述了如何在mapreduce任务中添加自定义的计数器，从所有任务中聚合信息，并且最终输出到mapreduce web ui中得到统计信息。

准备工作

数据集：ufo-60000条记录，这个数据集有一系列包含下列字段的UFO目击事件记录组成，每条记录的字段都是以tab键分割，请看http://www.cnblogs.com/cafebabe-yun/p/8679994.html

• sighting date：UFO目击事件发生时间
• Recorded date：报告目击事件的时间
• Location：目击事件发生的地点
• Shape：UFO形状
• Duration：目击事件持续时间
• Dexcription：目击事件的大致描述

例子：

19950915 19950915 Redmond, WA 6 min. Young man w/ 2 co-workers witness tiny, distinctly white round disc drifting slowly toward NE. Flew in dir. 90 deg. to winds.

需要共享的数据：州名缩写与全称的对应关系

数据：

AL      Alabama

AK      Alaska

AZ      Arizona

AR      Arkansas

CA      California

自定义计数器的使用

• 将数据集 ufo.tsv 上传到hdfs上

hadoop dfs -put ufo.tsv ufo.tsv

• 将共享数据数据上传到hdfs上，命令同上
• 创建文件 UFOCountingRecordValidationMapper.java ，并且输入以下代码：

import java.io.IOException;

import org.apache.hadoop.io.*;

import org.apache.hadoop.mapred.*;

import org.apache.hadoop.mapred.lib.*;

public class UFOCountingRecordValidationMapper extends MapReduceBase implements Mapper<LongWritable, Text, LongWritable, Text> {

    public enum LineCounters {

        BAD_LINES,

        TOO_MANY_TABS,

        TOO_FEW_TABS

    };

    @Override

    public void map(LongWritable key, Text value, OutputCollector<LongWritable, Text> output, Reporter reporter) throws IOException {

        String line = value.toString();

        if(validate(line, reporter)) {

            output.collect(key, value);

        }

    }

    private boolean validate(String line, Reporter reporter) {

        String[] words = line.split("\t");

        if (words.length != 6) {

            if (words.length < 6) {

                reporter.incrCounter(LineCounters.TOO_MANY_TABS

, 1);

              } else {

                reporter.incrCounter(LineCounters.TOO_FEW_TABS, 1);

            }

            reporter.incrCounter(LineCounters.BAD_LINES, 1);

            if ((reporter.getCounter(LineCounters.BAD_LINES).getCounter() % 10) == 0) {

                reporter.setStatus("Got 10 bad lines.");

                System.err.println("Read another 10 bad lines.");

            }

            return false;

        }

        return true;

    }

}

• 创建文件 UFOLocation3.java ，并输入以下代码：

import java.io.*;

import java.util.*;

import java.net.*;

import java.util.regex.*;

import org.apache.hadoop.conf.*;

import org.apache.hadoop.fs.Path;

import org.apache.hadoop.filecache.DistributedCache;

import org.apache.hadoop.io.*;

import org.apache.hadoop.mapred.*;

import org.apache.hadoop.mapred.lib.*;

public class UFOLocation3 {

    public static class MapClass extends MapReduceBase implements Mapper<LongWritable, Text, Text, LongWritable> {

        private final static LongWritable one = new LongWritable(1);

        private static Pattern locationPattern = Pattern.compile("[a-zA-Z]{2}[^a-zA-Z]*$");

        private Map<String, String> stateNames;

        @Override

        public void configure(JobConf job) {

            try {

                Path[] cacheFiles = DistributedCache.getLocalCacheFiles(job);

                setupStateMap(cacheFiles[0].toString());

            } catch (IOException e) {

                System.err.println("Error reading state file.");

                System.exit(1);

            }

        }

        private void setupStateMap(String fileName) throws IOException {

            Map<String, String> stateCache = new HashMap<String, String>();

            BufferedReader reader = new BufferedReader(new FileReader(fileName));

            String line = null;

            while((line = reader.readLine()) != null) {

                String[] splits = line.split("\t");

                stateCache.put(splits[0], splits[1]);

            }

            stateNames = stateCache;

        }

        @Override

        public void map(LongWritable key, Text value, OutputCollector<Text, LongWritable> output, Reporter reporter) throws IOException {

            String line = value.toString();

            String[] fields = line.split("\t");

            String location = fields[2].trim();

            if(location.length() >= 2) {

                Matcher matcher = locationPattern.matcher(location);

                if(matcher.find()) {

                    int start = matcher.start();

                    String state = location.substring(start, start + 2);

                    output.collect(new Text(lookupState(state.toUpperCase())), one);

                }

            }

        }

        private String lookupState(String state) {

            String fullName = stateNames.get(state);

            if(fullName == null || "".equals(fullName)) {

                fullName = state;

            }

            return fullName;

        }

    }

    public static void main(String...args) throws Exception {

        Configuration config = new Configuration();

        JobConf conf = new JobConf(config, UFOLocation3.class);

        conf.setJobName("UFOLocation3");

        DistributedCache.addCacheFile(new URI("/user/root/states.txt"), conf);

        conf.setOutputKeyClass(Text.class);

        conf.setOutputValueClass(LongWritable.class);

        JobConf mapconf1 = new JobConf(false);

        ChainMapper.addMapper(conf, UFOCountingRecordValidationMapper.class, LongWritable.class, Text.class, LongWritable.class, Text.class, true, mapconf1);

        JobConf mapconf2 = new JobConf(false);

        ChainMapper.addMapper(conf, MapClass.class, LongWritable.class, Text.class, Text.class, LongWritable.class, true, mapconf2);

        conf.setMapperClass(ChainMapper.class);

        conf.setCombinerClass(LongSumReducer.class);

        conf.setReducerClass(LongSumReducer.class);

        FileInputFormat.setInputPaths(conf, args[0]);

        FileOutputFormat.setOutputPath(conf, new Path(args[1]));

        JobClient.runJob(conf);

    }

}

• 编译上述的两个文件

javac UFOCountingRecordValidationMapper.java UFOLocation3.java

• 将编译好的文件打包成jar文件

jar cvf ufo3.jar UFO*class

• 在hadoop上执行jar包

hadoop cvf ufo3.jar UFOLocation3 ufo.tsv output

• 查看输出结果

hadoop dfs -cat output/part-00000

• 在mapreduce web ui页面上查看统计信息
  • 　　相应的job，进入job的统计信息页面

• • 　　查看统计信息