Hadoop系列（二）MaxTemperature

《Hadoop权威指南（第三版）》全书示例代码可以在这里找到，参考readme中的步骤进行编译。

MaxTemperatureMapper代码如下：

package com.nasuf.maxtemperature;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class MaxTemperatureMapper
  extends Mapper<LongWritable, Text, Text, IntWritable> {

  private static final int MISSING = 9999;
  
  @Override
  public void map(LongWritable key, Text value, Context context)
      throws IOException, InterruptedException {
    
    String line = value.toString();
    String year = line.substring(15, 19);
    int airTemperature;
    if (line.charAt(87) == '+') { // parseInt doesn't like leading plus signs
      airTemperature = Integer.parseInt(line.substring(88, 92));
    } else {
      airTemperature = Integer.parseInt(line.substring(87, 92));
    }
    String quality = line.substring(92, 93);
    if (airTemperature != MISSING && quality.matches("[01459]")) {
      context.write(new Text(year), new IntWritable(airTemperature));
    }
  }
}

MaxTemperatureReducer代码如下：

package com.nasuf.maxtemperature;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class MaxTemperatureReducer
  extends Reducer<Text, IntWritable, Text, IntWritable> {
  
  @Override
  public void reduce(Text key, Iterable<IntWritable> values,
      Context context)
      throws IOException, InterruptedException {
    
    int maxValue = Integer.MIN_VALUE;
    for (IntWritable value : values) {
      maxValue = Math.max(maxValue, value.get());
    }
    context.write(key, new IntWritable(maxValue));
  }
}

MaxTemperature代码如下：

package com.nasuf.maxtemperature;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MaxTemperature {

  public static void main(String[] args) throws Exception {
    if (args.length != 2) {
      System.err.println("Usage: MaxTemperature <input path> <output path>");
      System.exit(-1);
    }
    
    Job job = new Job();
    job.setJarByClass(MaxTemperature.class);
    job.setJobName("Max temperature");

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    
    job.setMapperClass(MaxTemperatureMapper.class);
    job.setReducerClass(MaxTemperatureReducer.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

如何按照原书中执行成功呢？
export HADOOP_CLASSPATH=hadoop-examples.jar
hadoop MaxTemperature input/ncdc/sample.txt output

首先应将sample.txt数据文件提交到hdfs中。
在保证hadoop运行下，将实例代码中的input/ncdc/sample.txt提交到hdfs中：
hadoop fs -mkdir /data
hadoop fs -copyFromLocal input/ncdc/sample.txt /data
添加HADOOP_CLASSPATH环境变量到~/.bash_profile
export HADOOP_CLASSPATH=/Users/nasuf/Project/hadoop-book/hadoop-examples.jar
添加完成保存退出后，记得执行source ~/.bash_profile

然后执行
hadoop MaxTemperature input/ncdc/sample.txt output 即可。