//编写Mapper类 TokenizerMapper.java
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class TokenizerMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
StringTokenizer itr = new StringTokenizer(value.toString());
while(itr.hasMoreTokens()) {
word.set(itr.nextToken());
context.write(word, one);
}
}
}
//编写Reducer类 IntSumReducer.java
import java.io.IOException;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
public class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
//编写main函数 WordCount.java
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
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 WordCount {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Configuration conf = new Configuration();
if (args.length != 2) {
System.err.println("Usage:wordcount<in><out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
//测试数据 input.txt
hello world
hello world
hello hadoop
#在HDFS上创建文件夹
hadoop fs -mkdir -p /class
#复制本地数据到HDFS
hadoop fs -copyFromLocal input.txt /class/input.txt
#编译源码
javac -classpath ../hadoop-core-1.2.1.jar *.java
#将类文件打包成jar
jar cvf WordCount.jar *.class
#运行程序,并将结果输出到HDFS上的/class/out文件夹
hadoop jar WordCount.jar WordCount /class/input.txt /class/out
#罗列HDFS上文件夹里的文件
hadoop fs -ls /class/out
#查看运行结果
hadoop fs -cat /class/out/part-r-00000
#运行结果
hadoop 1
hello 3
world 2
欢迎来到这里!
我们正在构建一个小众社区,大家在这里相互信任,以平等 • 自由 • 奔放的价值观进行分享交流。最终,希望大家能够找到与自己志同道合的伙伴,共同成长。
注册 关于