1.语法
hive> load data [local] inpath '/opt/module/datas/student.txt' [overwrite] | into table student [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加载数据到hive表,可选项
(3)inpath:表示加载数据的路径
(4)overwrite:表示覆盖表中已有数据,否则表示追加,可选项
(5)into table:表示加载到哪张表
(6)student:表示具体的表
(7)partition:表示上传到指定分区
2.实操案例
(1)创建一张表
hive (default)> create table student(id string, name string) row format delimited fields terminated by '\t';
(2)加载本地文件到hive表中
hive (default)> load data local inpath '/opt/module/datas/student.txt' into table default.student;
(3)加载HDFS文件到hive表中
#上传文件到HDFS
hive (default)> dfs -put /opt/module/datas/student.txt /user/atguigu/hive;
#加载HDFS上数据到hive表
hive (default)> load data inpath '/user/atguigu/hive/student.txt' into table default.student;
(4)加载数据覆盖表中已有的数据
#上传文件到HDFS
hive (default)> dfs -put /opt/module/datas/student.txt /user/atguigu/hive;
#加载数据覆盖表中已有的数据
hive (default)> load data inpath '/user/atguigu/hive/student.txt' overwrite into table default.student;
(1)创建一张分区表
hive (default)> create table student(id int, name string) partitioned by (month string) row format delimited fields terminated by '\t';
(2)基本插入数据
hive (default)> insert into table student partition(month='201709') values(1,'wangwu');
(3)基本模式插入(根据单张表查询结果)
hive (default)> insert overwrite table student partition(month='201708')
select id, name from student where month='201709';
4.多插入模式(根据多张表查询结果)
hive (default)> 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';
根据查询结果创建表(查询的结果会添加到新创建的表中)
create table if not exists student3 as select id, name from student;
(1)创建表,并指定在hdfs上的位置
hive (default)> create table if not exists student5(
id int, name string
)
row format delimited fields terminated by '\t'
location '/user/hive/warehouse/student5';
(2)上传数据到hdfs上
hive (default)> dfs -put /opt/module/datas/student.txt /user/hive/warehouse/student5;
(3)查询数据
hive (default)> select * from student5;
注意:先用export导出后,再将数据导入。
hive (default)> import table student2 partition(month='201709') from '/user/hive/warehouse/export/student';
(1)将查询的结果导出到本地
hive (default)> insert overwrite local directory '/opt/module/datas/export/student'
select * from student;
(2)将查询的结果格式化导出到本地
hive(default)>insert overwrite local directory '/opt/module/datas/export/student1'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t' select * from student;
(3)将查询的结果导出到HDFS上(没有local)
hive (default)> insert overwrite directory '/user/atguigu/student2'
ROW FORMAT DELIMITED FIELDS TERMINATED BY '\t'
select * from student;
hive (default)> dfs -get /user/hive/warehouse/student/month=201709/000000_0
/opt/module/datas/export/student3.txt;
基本语法:(hive -f/-e 执行语句或者脚本 > file)
[atguigu@hadoop102 hive]$ bin/hive -e 'select * from default.student;' > /opt/module/datas/export/student4.txt;
(defahiveult)> export table default.student to '/user/hive/warehouse/export/student';