目录:
1.先上案例代码
WordCount.java:
import java.io.IOException;
import java.util.StringTokenizer; 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.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser; public class WordCount {
//WordCOuntMap方法接收LongWritable,Text的参数,返回<Text, IntWriatable>键值对。
public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{
private final static IntWritable one = new IntWritable(1);
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);
}
}
} 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 {
System.setProperty("hadoop.home.dir", "D:\\hadoop-2.7.6");//这一行一定要
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);
}
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);
}
}
如下图,至于NativeIO,可从https://download.csdn.net/download/xiaoliu123586/10551225里下载
2.新建input文件夹,里面放w.txt
yaojiale hahaha
yaojiale llllll
3.运行时可能的报错
需要加winutils.exe,libwinutils.lib 拷贝到%HADOOP_HOME%\bin目录 ,可能还要下载hadoop.dll,并拷贝到c:\windows\system32目录中。
以上所需,可在https://download.csdn.net/download/xiaoliu123586/10551225里下载
附:eclipse 中运行 Hadoop2.7.3 map reduce程序 出现错误(null) entry in command string: null chmod 0700
4.运行加main参数:input output5
分别代表读取本地本项目input文件夹(内有w.txt,见图一),以及输出到output5文件夹
5.至于网上说的project structure>module>添加本地hadoop jar包,这个不是必须,比如,使用maven pom.xml的话,就能得到库支持 ,
而上述把winutils.exe等东西 添加到本地hadoop_home下(bin下)(如,我的是 D:/hadoop-2.7.6/),
使添加进去的东西起作用的,是以下代码:
System.setProperty("hadoop.home.dir", "D:\\hadoop-2.7.6");