Hive学习笔记（5）- Hive 中数据库的基本操作
1 创建表
1.1 建表方式1
create table IF NOT EXISTS default.web_log
(
ip string COMMENT 'remote ip address',
user string,
req_url string COMMENT 'user request url'
)
COMMENT 'Web Access Logs'
ROW FORMAT DELIMITED FIELDS TERMINATED BY ' '
STORED AS TEXTFILE
LOCATION '/user/hive/warehouse/web_log'
1.2 建表方式2
create table IF NOT EXISTS default.web_log_2
AS select ip,user from default.web_log;
1.3 建表方式3
create table IF NOT EXISTS default.web_log_3
like default.web_log
1.4 测试
create table IF NOT EXISTS default.web_log(
ip string COMMENT 'remote ip address',
user string,
req_url string COMMENT 'user request url')
COMMENT 'Web Access Logs'
ROW FORMAT DELIMITED FIELDS TERMINATED BY ' '
STORED AS TEXTFILE;
hive (default)> desc formatted default.web_log;
OK
col_name data_type comment
# col_name data_type comment
ip string remote ip address
user string
req_url string user request url
# Detailed Table Information
Database: default
Owner: hadoop
CreateTime: Wed Jan 16 17:09:17 CST 2019
LastAccessTime: UNKNOWN
Protect Mode: None
Retention: 0
Location: hdfs://node1:8020/user/hive/warehouse/web_log
Table Type: MANAGED_TABLE
Table Parameters:
comment Web Access Logs
transient_lastDdlTime 1547629757
# Storage Information
SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
InputFormat: org.apache.hadoop.mapred.TextInputFormat
OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
Compressed: No
Num Buckets: -1
Bucket Columns: []
Sort Columns: []
Storage Desc Params:
field.delim
serialization.format
Time taken: 0.18 seconds, Fetched: 30 row(s)
- 导入数据
load data local inpath '/home/hadoop/test_log.txt' into table default.web_log;
hive (default)> select * from default.web_log;
OK
web_log.ip web_log.user web_log.req_url
"27.38.5.159" "-" "31/Aug/2015:00:04:37
"27.38.5.159" "-" "31/Aug/2015:00:04:37
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:53
"27.38.5.159" "-" "31/Aug/2015:00:04:54
"27.38.5.159" "-" "31/Aug/2015:00:04:54
"27.38.5.159" "-" "31/Aug/2015:00:04:54
Time taken: 0.251 seconds, Fetched: 15 row(s)
hive (default)> create table IF NOT EXISTS default.web_log_3 like default.web_log;
OK
Time taken: 0.109 seconds
hive (default)> select * from default.web_log_3;
OK
web_log_3.ip web_log_3.user web_log_3.req_url
Time taken: 0.082 seconds
2 创建数据库
https://cwiki.apache.org/confluence/display/Hive/LanguageManual+DDL
create database mybase_01;
create database if not exists mybase_02; ----> 标准
create database if not exists mybase_03 location '/user/hive/warehouse';
show databases like 'mybase*';
hive (default)> show databases like 'mybase*';
OK
database_name
mybase_01
mybase_02
mybase_03
Time taken: 0.061 seconds, Fetched: 3 row(s)
2.1 查看数据库信息
hive (default)> desc database mybase_03;
OK
db_name comment location owner_name owner_type parameters
mybase_03 hdfs://node1:8020/user/hive/warehouse hadoop USER
Time taken: 0.053 seconds, Fetched: 1 row(s)
hive (default)> desc database extended mybase_03;
OK
db_name comment location owner_name owner_type parameters
mybase_03 hdfs://node1:8020/user/hive/warehouse hadoop USER
Time taken: 0.05 seconds, Fetched: 1 row(s)
2.2 删除数据库
- 如果待删除的数据库中存在表
hive (default)> drop database mybase_01 cascade;
drop database if exists mybase_02;
hive (default)> show databases;
OK
database_name
default
mybase_01
mybase_02
mybase_03
test_hive
Time taken: 0.046 seconds, Fetched: 5 row(s)
hive (default)> drop database mybase_01 cascade;
OK
Time taken: 0.124 seconds
hive (default)> show databases;
OK
database_name
default
mybase_02
mybase_03
test_hive
Time taken: 0.02 seconds, Fetched: 4 row(s)