用MR生成HFile文件格式后,数据批量导入HBase
环境hadoop cdh5.4.7 hbase1.0.0
测试数据:
topsid uid roler_num typ
10 111111 255 0
在Hbase 创建t2数据库: create 't2','info'。创建数据库t2, columnFamily:info
import java.io.IOException;
import java.net.URI;
import java.text.SimpleDateFormat;
import java.util.Date;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat2;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; public class HFileCreate { static class HFileImportMapper2 extends
Mapper<LongWritable, Text, ImmutableBytesWritable, KeyValue> {
protected SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd");
protected final String CF_KQ = "info";
protected final int ONE = 1; @Override
protected void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
System.out.println("line : " + line);
String[] datas = line.split("\\s+");
// row格式为:yyyyMMdd-sid-uid-role_num-timestamp-typ
String row =
datas[0] + "-" + datas[1] + "-" + datas[2] + "-"
+ "-" + datas[3];
ImmutableBytesWritable rowkey = new ImmutableBytesWritable(
Bytes.toBytes(row));
KeyValue kv = new KeyValue(Bytes.toBytes(row),
this.CF_KQ.getBytes(), datas[3].getBytes(),
Bytes.toBytes(this.ONE));
context.write(rowkey, kv);
}
} public static void main(String[] args) {
Configuration conf = new Configuration();
conf.addResource("hbase-site.xml");
String tableName = "t2";
String input = "hdfs://node11:9000/datas/t3";
String output = "hdfs://node11:9000/datas/out12";
System.out.println("table : " + tableName);
HTable table;
try {
// 运行前,删除已存在的中间输出目录
try {
FileSystem fs = FileSystem.get(URI.create(output), conf);
fs.delete(new Path(output), true);
fs.close();
} catch (IOException e1) {
e1.printStackTrace();
} table = new HTable(conf, tableName.getBytes());
Job job = new Job(conf);
job.setJobName("Generate HFile"); job.setJarByClass(HFileCreate.class);
job.setInputFormatClass(TextInputFormat.class);
job.setMapperClass(HFileImportMapper2.class);
FileInputFormat.setInputPaths(job, input); job.getConfiguration().set("mapred.mapoutput.key.class",
"org.apache.hadoop.hbase.io.ImmutableBytesWritable");
job.getConfiguration().set("mapred.mapoutput.value.class",
"org.apache.hadoop.hbase.KeyValue"); FileOutputFormat.setOutputPath(job, new Path(output)); HFileOutputFormat2.configureIncrementalLoad(job, table);
try {
job.waitForCompletion(true);
} catch (InterruptedException e) {
e.printStackTrace();
} catch (ClassNotFoundException e) {
e.printStackTrace();
}
} catch (IOException e) {
e.printStackTrace();
} } }
输出目录要有带columnFamily的文件HFile才生成成功:

4、需要先配置自己HBase_HOME 在配置文件中自己查看。
echo $HBase_HOME
5、我的配置:export HBASE_HOME=/home/hbase-1.0.0-cdh5.4.7
输入:
HADOOP_CLASSPATH=`${HBASE_HOME}/bin/hbase classpath` hadoop jar ${HBASE_HOME}/lib/hbase-server-1.0.0-cdh5.4.7.jar
例如我的:
HADOOP_CLASSPATH=`${HBASE_HOME}/bin/hbase classpath` hadoop jar /home/hbase-1.0.0-cdh5.4.7/lib/hbase-server-1.0.0-cdh5.4.7.jar completebulkload /datas/out12 t2

一般执行到这步就 成功导入。
6、查询HBase
7、HBase-site.xml
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<!--
/**
*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
-->
<configuration>
<property>
<name>hbase.rootdir</name>
<value>hdfs://node11:9000/hbase</value>
</property>
<property>
<name>hbase.cluster.distributed</name>
<value>true</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>node11</value>
</property>
<property>
<name>dfs.replication</name>
<value>1</value>
</property> <property>
<name>hbase.regionserver.wal.codec</name>
<value>org.apache.hadoop.hbase.regionserver.wal.IndexedWALEditCodec</value>
</property> <property>
<name>hbase.region.server.rpc.scheduler.factory.class</name>
<value>org.apache.hadoop.hbase.ipc.PhoenixRpcSchedulerFactory</value>
<description>Factory to create the Phoenix RPC Scheduler that uses separate queues for index and metadata updates</description>
</property> <property>
<name>hbase.rpc.controllerfactory.class</name>
<value>org.apache.hadoop.hbase.ipc.controller.ServerRpcControllerFactory</value>
<description>Factory to create the Phoenix RPC Scheduler that uses separate queues for index and metadata updates</description>
</property> <property>
<name>hbase.coprocessor.regionserver.classes</name>
<value>org.apache.hadoop.hbase.regionserver.LocalIndexMerger</value>
</property> <property>
<name>hbase.master.loadbalancer.class</name>
<value>org.apache.phoenix.hbase.index.balancer.IndexLoadBalancer</value>
</property>
<property>
<name>hbase.coprocessor.master.classes</name>
<value>org.apache.phoenix.hbase.index.master.IndexMasterObserver</value>
</property> </configuration>
用MR生成HFile文件格式后,数据批量导入HBase的更多相关文章
- 数据批量导入HBase
测试数据: datas 1001 lilei 17 13800001111 1002 lily 16 13800001112 1003 lucy 16 13800001113 1004 meimei ...
- SQL Server中bcp命令的用法以及数据批量导入导出
原文:SQL Server中bcp命令的用法以及数据批量导入导出 1.bcp命令参数解析 bcp命令有许多参数,下面给出bcp命令参数的简要解析 用法: bcp {dbtable | query} { ...
- .net core利用MySqlBulkLoader大数据批量导入MySQL
最近用core写了一个数据迁移小工具,从SQLServer读取数据,加工后导入MySQL,由于数据量太过庞大,数据表都过百万,常用的dapper已经无法满足.三大数据库都有自己的大数据批量导入数据的方 ...
- 将execl里的数据批量导入数据库
本文将采用NPOI插件来读取execl文件里的数据,将数据加载到内存中的DataTable中 /// <summary> /// 将Excel转换为DataTable /// </s ...
- mysql中把一个表的数据批量导入另一个表中
mysql中把一个表的数据批量导入另一个表中 不管是在网站开发还是在应用程序开发中,我们经常会碰到需要将MySQL或MS SQLServer某个表的数据批量导入到另一个表的情况,甚至有时还需要指定 ...
- ELK数据批量导入
数据批量导入 • 使用 _bulk 批量导入数据 – 批 ...
- [Django]数据批量导入
前言:历经一个月的复习,考试终于结束了.这期间上班的时候有研究了Django网页制作过程中,如何将数据批量导入到数据库中. 这个过程真的是惨不忍睹,犯了很多的低级错误,这会在正文中说到的.再者导入数据 ...
- 将Excle中的数据批量导入数据库
namespace 将Excle中的数据批量导入数据库{ class Program { static void Main(string[] args) { S ...
- Java实现Excel数据批量导入数据库
Java实现Excel数据批量导入数据库 概述: 这个小工具类是工作中的一个小插曲哦,因为提数的时候需要跨数据库导数... 有的是需要从oracle导入mysql ,有的是从mysql导入oracle ...
随机推荐
- window下 nginx 80端口被占用
问题:启动nginx没有反应,查看日志提示 bind() to 0.0.0.0:80 failed (10013: An attempt was made to access a socket in ...
- 攻防世界--open-source
1.打开源码 打开源码 #include <stdio.h> #include <string.h> int main(int argc, char *argv[]) { ) ...
- windos忘记密码登陆如何修复
一.简单的方法: 开机启动windows,进入欢迎界面后,会出现输入用户名密码提示框,这时候,同时按住Ctrl+Alt+Delete,会跳出一个账号窗口,输入用户名:administer,按回车即可. ...
- LeetCode Array Easy 448. Find All Numbers Disappeared in an Array
Description Given an array of integers where 1 ≤ a[i] ≤ n (n = size of array), some elements appear ...
- 2019-1-5-Windows-的-Pen-协议
title author date CreateTime categories Windows 的 Pen 协议 lindexi 2019-01-05 11:14:49 +0800 2019-01-0 ...
- Linux就该这么学09学习笔记
参考链接:https://www.linuxprobe.com/chapter-09.html 配置网卡服务 配置网卡参数 1.执行nmtui命令运行网络配置工具 2.选中Edit a connect ...
- C# 生成word文档(NPOI.XWPF)
一.基础 1.创建Word using NPOI.XWPF.UserModel XWPFDocument doc = new XWPFDocument(); //创建新的word文档 XWPFPara ...
- pandas-同时处理两行数据
pandas-同时处理两行数据 假设数据集data如下所示: 如果我们想要将user_id 和 item_id两列进行对应元素相加的操作,该怎么办呢? 显然我们先定义一个加法函数,然后使用apply函 ...
- canvas 点击图片播放视频
canvas.js window.onload=function() { var canvas = document.getElementById('canvas'); var ctx= canvas ...
- python-字符串的处理
s1 = '###12314##231###' print(s1.split('#')) #split,从左往右遇见# 就拆分一次['', '', '', '12314', '', '231', '' ...