1. 新建java project
2. 在pom.xml中引入hadoop
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.5</version>
</dependency>
3. 编写wordcount类
3.1 编写mapper类
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(2);
private Text word = new Text();
public void map(Object 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);
}
}
}
3.2 编写Reduce类
public static 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);
}
}
3.3 编写main函数
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
/*String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: wordcount <in> <out>");
System.exit(2);
}*/
System.err.println(args.length);
System.err.println(args[0]);
System.err.println(args[1]);
//System.err.println(args[2]);
Job job = new Job(conf, "word count");
job.setJarByClass(WordCount.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.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);
}
3.4 运行程序
将代码打包成jar，然后放到linux执行
bin/hadoop jar share/hadoop/mapreduce/WordCount4.jar com.iluxday.WordCount.WordCount /user/hadoopuser/mapreduce/wordcount/input /user/hadoopuser/mapreduce/wordcount/output3