hadoop开发应用

hadoop开发应用

一、文件上传

• 创建input文件夹

  # hadoop fs -mkdir /input

• 上传文件到input文件夹下

  # hadoop fs -put dat0102.dat /input/

二、查询指定字符串出现次数

1. 编写代码

如果忘记了，可以查看：

$HADOOP_HOME/share/doc/hadoop/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

代码如下：

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;

public class WordCount {

    public static class TokenizerMapper
            extends Mapper{

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();
        private static String findStr = "";
      
        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {
            Configuration conf=context.getConfiguration();
            findStr = conf.get("findStr");
            StringTokenizer itr = new StringTokenizer(value.toString());
            while (itr.hasMoreTokens()) {
                String wordStr = itr.nextToken();
                if(!findStr.equals(wordStr)) continue;
                word.set(wordStr);
                context.write(word, one);
            }
        }

    }

    public static class IntSumReducer
            extends Reducer {
        private IntWritable result = new IntWritable();

        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();
        conf.set("findStr", args[2]);
        Job job = Job.getInstance(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(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

2. 编译代码与打包

# hadoop com.sun.tools.javac.Main WordCount.java

# jar cf wc.jar WordCount*.class

3. 运行与输出存储

# #第一个参数为输入目录，第二个参数为输出目录，第三个参数为需要查找的字符串
# hadoop jar wc.jar WordCount /input/ /output/ Hadoop

# hadoop fs -cat /output/part-r-00000

输出结果： Hadoop 986

4. 远程使用windows客户端

添加JVM属性： -DHADOOP_USER_NAME=hadoop （hadoop为hdfs目录权限用户）

程序运行参数： hdfs://192.168.17.128:9000/input/ hdfs://192.168.17.128:9000/output/wc7/ Hadoop