Hive DML 数据操作

1. 语法

   load data [local] inpath '数据的路径' [overwrite] into table 
   table_name [partition (partcol1=val1,…)];
   

   1. load data：表示加载数据。
   2. local：表示从本地加载数据到Hive表；否则从HDFS中加载数据到Hive表。
   3. inpath：表示加载数据的路径。
   4. overwrite：表示覆盖表中已有的数据，否则表示追加。
   5. into table：表示加载到那张表。
   6. partition：表示上传到指定分区。

2. 例子

   # 创建一张表
   create table student(id string, name string) 
   row format delimited fields terminated by 't';
   
   # 加载本地文件到Hive
   load data local inpath '/opt/module/hive/datas/student.txt' into table default.student;
   
   # 加载HDFS文件到Hive
   dfs -put /opt/module/hive/datas/student.txt /user/root/
   load data inpath '/user/root/student.txt' into table default.student;
   
   # 加载数据覆盖表中的数据
   load data inpath 'user/root/student.txt' overwrite into table default.student;
   

create table student_par(id int, name string)
row format delimited fields terminated by 't';

insert into table student_par 
values(1,'zhangsan'),(2,'wangwu');

insert overwrite table student_par 
select id,name from student where month='202108'
# insert into：追加
# insert overwrite ：覆盖
# 注意insert不支持插入部分字段

# 多表（多分区）插入模式
from student
insert overwrite table student partition(month='201707')
select id, name where month='201709'
insert overwrite table student partition(month='201706')
select id, name where month='201709';

create table if not exists student0
as select id,name from student;

# 上传数据
dfs -mkdir /data/student;
dfs -put /opt/module/hive/datas/student.txt /data/student;

# 创建外部表，并指定数据位置
create external table if not exists student(
id int, name string)
row format delimited fields terminated by 't'
location '/data/student';

# 查询数据
select * from student;

# 注意先用export导出后，再将数据导入
import table student2 from '/user/hive/warehouse/export/student';

# 将查询的结果导出到本地
insert overwrite local directory '/opt/module/hive/datas/export/student'
select * from student;

# 将查询的结果格式化导出到本地
insert overwrite local directory '/opt/module/hive/datas/export/student1'
row format delimited fields terminated by 't'
select * from student;

# 将查询的结果导出到HDFS上，没有local
insert overwrite directory '/user/root/student'
row format delimited fields terminated by 't'
select * from student;

dfs -get /user/hive/warehouse/student/student.txt /opt/tool/data/export/student.txt;

hive -e 'select * from default.student;' > /opt/tool/data/export/student1.txt

export table default.student to '/user/hive/warehouse/export/student';

export和import主要用于两个Hadoop平台集群之间Hive表迁移

truncate table student;

truncate只能删除管理表，不能删除外部表的数据。