Hive01

• Hive 启动

0. cp hive-env.sh.template hive-env.sh
1. vim hive-env.sh
2. export HADOOP_HOME=/data/module/hadoop-2.7.2
3. :wq
4. vim hive-site.xml
5. 
<configuration>

  <property>
    <name>javax.jdo.option.ConnectionURL</name>
    <value>jdbc:mysql://192.168.41.8:3306/hive?createDatabaseIfNotExist=true</value>
    <description>JDBC connect string for a JDBC metastore</description>
  </property>
  
  <property>
    <name>javax.jdo.option.ConnectionDriverName</name>
    <value>com.mysql.jdbc.Driver</value>
    <description>Driver class name for a JDBC metastore</description>
  </property>
  
  <property>
    <name>javax.jdo.option.ConnectionUserName</name>
    <value>root</value>
    <description>Username to use against metastore database</description>
  </property>
  
  <property>
    <name>javax.jdo.option.ConnectionPassword</name>
    <value>123456</value>
    <description>password to use against metastore database</description>
  </property>
  
  
</configuration>
6. :wq

• Hive 启动方式

方式一：
./bin/hive
方式二：
./bin/hiveserver2
注意方式二链接方式：
./bin/beeline
beeline> ! connect jdbc:hive2://hadoop01:10000
Enter username for jdbc:hive2://hadoop01:10000: root
Enter password for jdbc:hive2://hadoop01:10000: ***

• 建表语法【单分区】示例：

create table t_t3(id int,name string) partitioned by (type string) 
ROW FORMAT DELIMITED 
FIELDS TERMINATED BY ','
COLLECTION ITEMS TERMINATED BY '-'
MAP KEYS TERMINATED BY ':'; 

• 加载【单分区】数据示例：

LOAD DATA local INPATH '/data/module/apache-hive-1.2.2-bin/hivedata/2.txt' INTO TABLE t_t3 partition(type='china');

• 【多分区】示例：

create table t_t4 (id int, name string) partitioned by (dt string, hour string)ROW FORMAT DELIMITED FIELDS TERMINATED BY ',';

• 加载【多分区】数据示例：

LOAD DATA local INPATH '/data/module/apache-hive-1.2.2-bin/hivedata/2.txt' INTO TABLE t_t4 partition(dt='2020-07-08',hour='09');

• 效果展示：

  
  
  

• 指定开启分桶

set hive.enforce.bucketing = true;
#分桶个数
set mapreduce.job.reduces=4;

# 创建分桶表
create table t_t5 (id int, name string) 
clustered by(id)
into 4 buckets
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';

#创建临时表-数据导入
create table t_t6 (id int, name string) 
ROW FORMAT DELIMITED
FIELDS TERMINATED BY ',';

#先进行 mr 程序，在 插入到分桶表
insert overwrite table t_t5 select * from t_t6 cluster by(id);

• 效果展示：