189 8069 5689
wordcount程序
package org.robby.mr;
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.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
public class WordCount {
public static class Map
extends Mapper{
//object是每一行的行表、text是每一行的内容，使用的是hadoop内置的数据结构
//后面的text是指输出的行，也就是单词，IntWritable是单词的个数
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())
{
//选出单词放在word里，然后用context输出，对应单词加1
word.set(itr.nextToken());
context.write(word, one);
}
}
}
public static class Reduce
extends Reducer {
private IntWritable result = new IntWritable();
//传入一个单词和其对于的次数迭代器
public void reduce(Text key, Iterable 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 ");
System.exit(2);
}
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
// Set up the input
job.setInputFormatClass(TextInputFormat.class);
TextInputFormat.addInputPath(job, new Path(args[0]));
// Mapper
job.setMapperClass(Map.class);
// Reducer
job.setReducerClass(Reduce.class);
// Output
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
TextOutputFormat.setOutputPath(job, new Path(args[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
} 使用hadoop jar web.jar [类的全名称] [输入目录] [输出目录]
输入和输出目录都是hdfs的目录。
另外有需要云服务器可以了解下创新互联scvps.cn，海内外云服务器15元起步，三天无理由+7*72小时售后在线，公司持有idc许可证，提供“云服务器、裸金属服务器、高防服务器、香港服务器、美国服务器、虚拟主机、免备案服务器”等云主机租用服务以及企业上云的综合解决方案，具有“安全稳定、简单易用、服务可用性高、性价比高”等特点与优势，专为企业上云打造定制，能够满足用户丰富、多元化的应用场景需求。