MRwordCount

mapreduce代码部分：wordcount
新建工程，导入jar包：
C:\hadoop-2.7.1\share\hadoop\common （公共jar包）：
hadoop-common-2.7.1、
C:\hadoop-2.7.1\share\hadoop\common\lib下所有
C:\hadoop-2.7.1\share\hadoop\hdfs （hdfs部分jar包）：
hadoop-hdfs-2.7.1、
C:\hadoop-2.7.1\share\hadoop\hdfs\lib下所有
C:\hadoop-2.7.1\share\hadoop\mapreduce （mapreduce部分jar包）：
C:\hadoop-2.7.1\share\hadoop\mapreduce下所有单独的jar包（hadoop-mapreduce-examples-2.7.1可以不要）、
C:\hadoop-2.7.1\share\hadoop\mapreduce\lib下所有
C:\hadoop-2.7.1\share\hadoop\yarn （yarn部分jar包）
C:\hadoop-2.7.1\share\hadoop\yarn下除了server的其他所有、
C:\hadoop-2.7.1\share\hadoop\yarn\lib下的所有
打包时，若打成普通jar包（而不是runnerbale的jar），是不会把该项目中lib中的jar包打进去的~~~


代码：
分为3个部分：Mapper、Reducer、Driver


package cn.bigdata.wordcount;


import java.io.IOException;


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 WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
@Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
String[] words = line.split(" ");
for (String word: words)  {
context.write(new Text(word), new IntWritable(1));
}
}
}




package cn.bigdata.wordcount;


import java.io.IOException;


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


public class WordCountReducer extends Reducer<Text, IntWritable, Text, LongWritable>{
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
long count = 0;
for (IntWritable value: values) {
count += value.get();
}
context.write(key, new LongWritable(count));
}
}




package cn.bigdata.wordcount;


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.LongWritable;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;




public class WordCountDriver {
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {

Configuration conf = new Configuration();
Job wcJob = Job.getInstance(conf);

wcJob.setJarByClass(WordCountDriver.class);

wcJob.setMapperClass(WordCountMapper.class);
wcJob.setReducerClass(WordCountReducer.class);

wcJob.setMapOutputKeyClass(Text.class);
wcJob.setMapOutputValueClass(IntWritable.class);
wcJob.setOutputKeyClass(Text.class);
wcJob.setOutputValueClass(LongWritable.class);

wcJob.setInputFormatClass(TextInputFormat.class);
FileInputFormat.setInputPaths(wcJob, new Path("hdfs://hadoop-01-server:9000/wordcount/srcdata"));
wcJob.setOutputFormatClass(TextOutputFormat.class);
FileOutputFormat.setOutputPath(wcJob, new Path("hdfs://hadoop-01-server:9000/wordcount/outdata"));

boolean res = wcJob.waitForCompletion(true);
System.exit(res ? 0 : 1);
}
}