package hadoop;
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#加载java的io抛错类
import java.io.IOException;
#字符串按令牌格式化类
import java.util.StringTokenizer;
#读配置参数类
import org.apache.hadoop.conf.Configuration;
#文件系统路径类
import org.apache.hadoop.fs.Path;
#整数的WritableComparable类
import org.apache.hadoop.io.IntWritable;
#存储字符串类
import org.apache.hadoop.io.Text;
#job类
import org.apache.hadoop.mapreduce.Job;
#mapper类
import org.apache.hadoop.mapreduce.Mapper;
#reducer类
import org.apache.hadoop.mapreduce.Reducer;
#文件InputFormat类
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
#文件OutputFormat类
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
#输入参数解析类
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
#实现自己的TokenizerMapper类,继承自Mapper
public static class TokenizerMapper
extends Mapper<Object, Text, Text, IntWritable>{
#创建one整数1实例
private final static IntWritable one = new IntWritable(1);
#创建Text的实例word
private Text word = new Text();
#重写父类Mapper类的map方法
public void map(Object key, Text value, Context context
) throws IOException, InterruptedException {
#对输入值value按令牌方式StringTokenizer
StringTokenizer itr = new StringTokenizer(value.toString());
#循环有tokens
while (itr.hasMoreTokens()) {
#循环获取下一个token
word.set(itr.nextToken());
#写入word和one数量
context.write(word, one);
}
}
}
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);
}
}
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);
}
//conf.set("fs.defaultFS", "hdfs://192.168.6.77:9000");
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(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}