hive over hbase方式将微博用户数据导入hbase

1，创建hbase表 WeiboUserData

>>

create 'WeiboUserData','CF'

2，创建hive->hbase外表logic_WeiboUserData,并对应hbase中的 WeiboUser表

>>

CREATE EXTERNAL TABLE logic_WeiboUserData (

rowkey string,

screenName string,

location string,

description string,

gender string,

weiboLevel string,

VIPLevel string,

birthday string,

identityAuthentication string,

educationBackground string,

workingExperience string,

followersCount int,

friendsCount int,

statusesCount int,

favouritesCount int,

biFollowersCount int,

userTags string,

statusTexts string)

STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'

WITH SERDEPROPERTIES ("hbase.columns.mapping" = ":key,

CF:screenName,

CF:location,

CF:description,

CF:gender,

CF:weiboLevel,

CF:VIPLevel,

CF:birthday,

CF:identityAuthentication,

CF:educationBackground,

CF:workingExperience,

CF:followersCount,

CF:friendsCount,

CF:statusesCount,

CF:favouritesCount,

CF:biFollowersCount,

CF:userTags,

CF:statusTexts")

TBLPROPERTIES("hbase.table.name" = "WeiboUserData"); 

//创建目录

hadoop fs -mkdir -p  /user/maoxiao/2015/aud/weiboUserData/input

//上传文件

hadoop fs -put weiboUserData.txt /user/maoxiao/2015/aud/weiboUserData/input

3，创建数据外表

CREATE EXTERNAL TABLE data_weiboUserData (

rowkey string,

screenName string,

location string,

description string,

gender string,

weiboLevel string,

VIPLevel string,

birthday string,

identityAuthentication string,

educationBackground string,

workingExperience string,

followersCount int,

friendsCount int,

statusesCount int,

favouritesCount int,

biFollowersCount int,

userTags string,

statusTexts string

)

ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' 

LOCATION '/user/maoxiao/2015/aud/weiboUserData/input';

4，通过数据外表导入到hbase外表

SET hive.hbase.bulk=true;

INSERT OVERWRITE TABLE logic_WeiboUserData SELECT 

rowkey, screenName, location, description, gender, weiboLevel, VIPLevel, birthday, identityAuthentication, educationBackground, workingExperience, followersCount,  friendsCount,  statusesCount,  favouritesCount,  biFollowersCount,  userTags, statusTexts 

FROM data_weiboUserData ; 

put 'WeiboUserData', 'rowkey1', 'CF:UserId', 'value'

rowkey, screenName, location, description, gender, weiboLevel, VIPLevel, birthday, identityAuthentication, educationBackground, workingExperience, followersCount,  friendsCount,  statusesCount,  favouritesCount,  biFollowersCount,  userTags, statusTexts