分享

eclipse开发hbase程序时报错,该怎样解决

xiaobaiyang 发表于 2015-7-8 21:29:59 [显示全部楼层] 回帖奖励 阅读模式 关闭右栏 1 11942
package com.it.hbase;

import java.text.SimpleDateFormat;
import java.util.Date;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Counter;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

/**
* 将数据批量的导入到HBase中(HDFS)
* @author hanyueyue
*
*/
public class BatchImport {
   
    public static void main(String[] args) throws Exception {
        final Configuration configuration = new Configuration();
        //设置zookeeper   的代理节点
        configuration.set("hbase.zookeeper.quorum", "hadoop");
        //设置hbase表名称   
        configuration.set(TableOutputFormat.OUTPUT_TABLE, "wlan_log");
        //将该值改大,防止hbase超时退出
        configuration.set("dfs.socket.timeout", "180000");
        
        final Job job = new Job(configuration, "HBaseBatchImport");
        
        job.setMapperClass(BatchImportMapper.class);
        job.setReducerClass(BatchImportReducer.class);
        //设置map的输出,不设置reduce的输出类型           reduce没有输出
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(Text.class);
        
        //设置输入路径
        FileInputFormat.setInputPaths(job, "hdfs://hadoop:9000/http.dat");
        job.setInputFormatClass(TextInputFormat.class);
        //不再设置输出路径,而是设置输出格式类型
        job.setOutputFormatClass(TableOutputFormat.class);
        
        job.waitForCompletion(true);
    }
   
    static class BatchImportMapper extends Mapper<LongWritable, Text, LongWritable, Text>{
        SimpleDateFormat dateformat1=new SimpleDateFormat("yyyyMMddHHmmss");
        Text v2 = new Text();
        
        protected void map(LongWritable key, Text value, Context context) throws java.io.IOException ,InterruptedException {
            final String[] splited = value.toString().split("\t");
            try {
                final Date date = new Date(Long.parseLong(splited[0].trim()));
                final String dateFormat = dateformat1.format(date);
                String rowKey = splited[1]+":"+dateFormat;//手机号+时间      行键格式
                v2.set(rowKey+"\t"+value.toString());
                context.write(key, v2);
            } catch (NumberFormatException e) {
                Counter counter = context.getCounter("BatchImport", "ErrorFormat");
                counter.increment(1L);
                System.out.println("出错了"+splited[0]+" "+e.getMessage());
            }
        };
    }
   
    static class BatchImportReducer extends TableReducer<LongWritable, Text, NullWritable>{
        protected void reduce(LongWritable key, java.lang.Iterable<Text> values,     Context context) throws java.io.IOException ,InterruptedException {
            for (Text text : values) {
                String[] splited = text.toString().split("\t");
               
                //设置行键
                Put put = new Put(Bytes.toBytes(splited[0]));
                //列族名称,列名称,值             插入数据
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("date"), Bytes.toBytes(splited[1]));
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("msisdn"), Bytes.toBytes(splited[2]));
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("apmac"), Bytes.toBytes(splited[3]));
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("acmac"), Bytes.toBytes(splited[4]));
                //省略其他字段,调用put.add(....)即可
                context.write(NullWritable.get(), put);//写入
            }
        };
    }

}



Exception in thread "main" java.net.UnknownHostException: unknown host: hadoop
    at org.apache.hadoop.ipc.Client$Connection.<init>(Client.java:214)
    at org.apache.hadoop.ipc.Client.getConnection(Client.java:1196)
    at org.apache.hadoop.ipc.Client.call(Client.java:1050)
    at org.apache.hadoop.ipc.RPC$Invoker.invoke(RPC.java:225)
    at $Proxy1.getProtocolVersion(Unknown Source)
    at org.apache.hadoop.ipc.RPC.getProxy(RPC.java:396)
    at org.apache.hadoop.ipc.RPC.getProxy(RPC.java:379)
    at org.apache.hadoop.hdfs.DFSClient.createRPCNamenode(DFSClient.java:119)
    at org.apache.hadoop.hdfs.DFSClient.<init>(DFSClient.java:238)
    at org.apache.hadoop.hdfs.DFSClient.<init>(DFSClient.java:203)
    at org.apache.hadoop.hdfs.DistributedFileSystem.initialize(DistributedFileSystem.java:89)
    at org.apache.hadoop.fs.FileSystem.createFileSystem(FileSystem.java:1386)
    at org.apache.hadoop.fs.FileSystem.access$200(FileSystem.java:66)
    at org.apache.hadoop.fs.FileSystem$Cache.get(FileSystem.java:1404)
    at org.apache.hadoop.fs.FileSystem.get(FileSystem.java:254)
    at org.apache.hadoop.fs.Path.getFileSystem(Path.java:187)
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.setInputPaths(FileInputFormat.java:352)
    at org.apache.hadoop.mapreduce.lib.input.FileInputFormat.setInputPaths(FileInputFormat.java:321)
    at com.it.hbase.BatchImport.main(BatchImport.java:45)






已有(1)人评论

跳转到指定楼层
arsenduan 发表于 2015-7-8 21:45:05
//设置输入路径
        FileInputFormat.setInputPaths(job, "hdfs://hadoop:9000/http.dat");

这里的hadoop记得给跟core-site.xml文件对应
<property>
                <name>fs.defaultFS</name>
                <value>hdfs://hadoop:9000</value>
       </property>

同时注意的问题是:楼主是在win7,还是Linux
如果win7,记得在下面修改hosts。下面对应的是master,楼主需要修改成hadoop

C:\Windows\System32\drivers\etc







回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

关闭

推荐上一条 /2 下一条