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 {
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", "E:\\hadoop2.2\\");
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("hdfs://master:9000/input"));
FileOutputFormat.setOutputPath(job, new Path("hdfs://master:9000/output"));
boolean flag = job.waitForCompletion(true);
System.out.print("SUCCEED!" + flag);
System.exit(flag ? 0 : 1);
System.out.println();
}
}
，这里面的hadoop installation directory并非你windows上装的hadoop文件夹，而不过你在centos上编译好的源代码，在windows上的解压路径而已，该路径不过用于在创建MapReduce Project能从这个地方自己主动引入MapReduce所须要的jar
，右击选择。New Hadoop location。这个时候会出现
Map/Reduce(V2)中的配置相应于mapred-site.xml中的port配置，DFS Master中的配置相应于core-site.xml中的port配置，配置完毕之后finish就可以，这个时候能够查看
，要解决问题，你必需要完毕例如以下几个步骤，在windows上配置HADOOP_HOME。然后将%HADOOP_HOME%\bin增加到path之中。然后去https://github.com/srccodes/hadoop-common-2.2.0-bin下载一个，下载之后将这个bin文件夹里面的东西所有复制到你自己windows上的HADOOP的bin文件夹下，覆盖就可以，同一时候把hadoop.dll加到C盘下的system32中，假设这些都完毕之后还是碰到：Exception in thread "main" java.lang.UnsatisfiedLinkError: org.apache.hadoop.io.nativeio.NativeIO$Windows.access0(Ljava/lang/String;I)Z，那么就检查一下你的JDK，有可能是32位的JDK导致的。须要下载64位安装JDK。而且在eclipse将jre环境配置为你新安装的64位JRE环境
。
