(1) 源代码
package cn.edu.xjtu.temperature;
import java.io.IOException;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
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.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
public class MaxTemperature {
static class MaxTemperatureMapper extends
Mapper<LongWritable, Text, Text, IntWritable> {
private static final int MISSING = 9999;
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException{
String line = value.toString();
String year = line.substring(15, 19);
System.out.println(year);
int airTemperature;
if(line.charAt(40) == '+'){
airTemperature = Integer.parseInt(line.substring(41,45));
}else{
airTemperature = Integer.parseInt(line.substring(40,45));
}
String quality = line.substring(45,46);
if(airTemperature != MISSING && quality.matches("[01459]")){
context.write(new Text(year), new IntWritable(airTemperature));
}
}
}
static class MaxTemperatureReducer extends
Reducer<Text, IntWritable, Text, IntWritable> {
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));
}
}
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);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(MaxTemperatureMapper.class);
job.setCombinerClass(MaxTemperatureReducer.class);
job.setReducerClass(MaxTemperatureReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
System.exit(job.waitForCompletion(true)? 0 : 1);
}
}
2. 测试数据 record.txt,传到node14
0067011990999991950051507004...9999999N9+00001+99999999999...
0043011990999991950051512004...9999999N9+00221+99999999999...
0043011990999991950051518004...9999999N9-00111+99999999999...
0043012650999991949032412004...0500001N9+01111+99999999999...
0043012650999991949032418004...0500001N9+00781+99999999999...
3. 从eclipse中export出 maxTemperature.jar,传到node14
4. 执行
(1) [hadoop@node14 app]$ hadoop fs -put record.txt input.txt
(2) [hadoop@node14 app]$ hadoop jar maxTemperature.jar cn.edu.xjtu.temperature.MaxTemperature input.txt outputDir
(3) 查看执行结果
[hadoop@node14 app]$ hadoop fs -ls outputDir
[hadoop@node14 app]$ hadoop fs -cat outputDir/part-r-00000
1949 111
1950 22