用Sqoop将mysql中的表和数据导入到Hive中

1、安装mysql
  查询以前安装的mysql相关包
  rpm -qa | grep mysql
  暴力删除这个包
  rpm -e mysql-libs-5.1.66-2.el6_3.i686 --nodeps

  rpm -ivh MySQL-server-5.1.73-1.glibc23.i386.rpm
  rpm -ivh MySQL-client-5.1.73-1.glibc23.i386.rpm

  执行命令设置mysql
  /usr/bin/mysql_secure_installation


  GRANT ALL PRIVILEGES ON hive.* TO

5、hive当中创建两张表
  create table trade_detail (id bigint, account string, income double, expenses double, time string) row format delimited fields terminated by '\t';
  create table user_info (id bigint, account string, name string, age int) row format delimited fields terminated by '\t';

6、将mysql当中的数据直接导入到hive当中
  sqoop import --connect jdbc:mysql://192.168.1.10:3306/itcast --username root --password 123 --table trade_detail --hive-import --hive-overwrite --hive-table trade_detail --fields-terminated-by '\t'
  sqoop import --connect jdbc:mysql://192.168.1.10:3306/itcast --username root --password 123 --table user_info --hive-import --hive-overwrite --hive-table user_info --fields-terminated-by '\t'

7、创建一个result表保存前一个sql执行的结果
  create table result row format delimited fields terminated by '\t' as select t2.account, t2.name, t1.income, t1.expenses, t1.surplus from user_info t2 join (select account, sum(income) as income, sum(expenses) as expenses, sum(income-expenses) as surplus from trade_detail group by account) t1 on (t1.account = t2.account);

  create table user (id int, name string) row format delimited fields terminated by '\t'
  将本地文件系统上的数据导入到HIVE当中
  load data local inpath '/root/user.txt' into table user;

  创建外部表
  create external table stubak (id int, name string) row format delimited fields terminated by '\t' location '/stubak';

  创建分区表
  普通表和分区表区别：有大量数据增加的需要建分区表
  create table book (id bigint, name string) partitioned by (pubdate string) row format delimited fields terminated by '\t';

分区表加载数据
load data local inpath './book.txt' overwrite into table book partition (pubdate='2010-08-22');

------------------------------- 附上mysql中创建表的脚本--------------------------------------

-- 导出表 mydb.trade_detail 结构
CREATE TABLE IF NOT EXISTS `trade_detail` (
`id` int(11) NOT NULL,
`account` varchar(100) DEFAULT NULL,
`income` double DEFAULT NULL,
`expenses` double DEFAULT NULL,
`time` timestamp NULL DEFAULT CURRENT_TIMESTAMP ON UPDATE CURRENT_TIMESTAMP,
PRIMARY KEY (`id`)
) ENGINE=InnoDB DEFAULT CHARSET=utf8;

-- 正在导出表 mydb.trade_detail 的数据：~10 rows (大约)
/*!40000 ALTER TABLE `trade_detail` DISABLE KEYS */;
INSERT INTO `trade_detail` (`id`, `account`, `income`, `expenses`, `time`) VALUES
(1,

使用sqoop，将mysql数据库中的数据导入到hdfs中

./sqoop import --connect jdbc:mysql://192.168.7.7:3306/asto_ec_web --username root --password password --table shop_tb --target-dir /ysf/input/shop_tb --fields-terminated-by ','

用Sqoop将mysql中的表和数据导入到Hive中

猜你喜欢