此次介绍有关在eclipse当中进行文件操作及wordcount的运行
按照我写的顺序进行讲述
新建Map/Reduce Project项目WordCountDemo
新建类WordCountDemo,包为org.hadoop.examples
将hadoop源码中的wordcount粘贴过来
设置arguments
运行,结果出现output文件已存在的错误,在hadoop中删除output文件
hadoop fs -rmdir /input/test/output
然后再次运行出现错误如下:
Exception in thread "main" java.lang.NullPointerException........
进行如下修改
下载hadoop.dll和winutils.exe,添加到hadoop的bin目录下,版本一定要对应,我刚开始下的64位的,结果还是运行不了
还要修改环境变量,增加一个HADOOP_HOME为当前hadoop目录,在Path中添加%HADOOP_HOME%\bin
重启eclipse,运行
现在倒是不出错了,但是没反应,既不显示有什么错误,也不显示正确结果,让人很是头疼
然后想换个方式,试一下hdfs文件操作吧
写了一个有关文件操作的类operateHdfs
运行,显示当前用户权限受限,无法进行操作,想到更改用户名,将提示错误信息中的用户名改成登录linux操作hadoop的用户名,我的为spark
重启机器,打开eclipse,运行operateHdfs类,执行成功
接着在此尝试运行WordCountDemo类,运行成功
相关代码如下:
wordcountDemo
package org.hadoop.examples;
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 WordCountDemo {
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 {
Configuration conf = new Configuration();
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length < 2) {
System.err.println("Usage: wordcount <in> [<in>...] <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCountDemo.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
for (int i = 0; i < otherArgs.length - 1; ++i) {
FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
}
FileOutputFormat.setOutputPath(job,
new Path(otherArgs[otherArgs.length - 1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
operateHdfs
public class operateHdfs {
public static void main(String args[]) throws IOException {
//测试 创建新文件
byte[] contents = "hello world\n--created by eclipse\n".getBytes();
createFile("/input/first.txt", contents); //或 createFile("hdfs://192.168.137.56:9000/eclipse/first.txt", contents);
}
//1、创建新文件(直接生成指定路径下的first.txt,即:/eclipse/first.txt)
public static void createFile(String dst, byte[] contents) throws IOException {
Configuration conf = new Configuration();
System.out.println("-----------:"+conf);
conf.set("fs.defaultFS", "hdfs://192.168.16.60:9000"); //master
FileSystem fs = FileSystem.get(conf);
Path dstPath = new Path(dst); // 目标路径
// 打开一个输出流
FSDataOutputStream outputStream = fs.create(dstPath);
outputStream.write(contents);
outputStream.close();
fs.close();
System.out.println("文件创建成功!");
}
}