Hive-DML操作

最新推荐文章于 2023-12-22 16:59:25 发布

丿沐染烟忱丶

最新推荐文章于 2023-12-22 16:59:25 发布

阅读量129

点赞数

分类专栏： Hive 文章标签： hive hadoop 大数据数据仓库

本文链接：https://blog.csdn.net/weixin_45607513/article/details/103930662

版权

Hive 专栏收录该内容

10 篇文章 0 订阅

订阅专栏

加载文件数据到表中

LOAD DATA [LOCAL] INPATH 'filepath' [OVERWRITE] INTO TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)]

load data local inpath "/root/baizhi/t_employee" overwrite into table t_employee partition(deptno=20);

查询结构插入表中

将查询结果加入表中

INSERT OVERWRITE TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...) [IF NOT EXISTS]]   
select_statement1 FROM from_statement; --覆盖

INSERT INTO TABLE tablename1 [PARTITION (partcol1=val1, partcol2=val2 ...)] 
select_statement1 FROM from_statement;--追加

{"EMPNO": 7369,"ENAME": "SMITH","JOB": "CLERK","MGR": 7902,"HIREDATE": "1980-12-17 00:00:00","SAL": 800.00,"COMM": null,"DEPTNO": 20}
{"EMPNO": 7499,"ENAME": "ALLEN","JOB": "SALESMAN","MGR": 7698,"HIREDATE": "1981-02-20 00:00:00","SAL": 1600.00,"COMM": 300.00,"DEPTNO": 30}
{"EMPNO": 7521,"ENAME": "WARD","JOB": "SALESMAN","MGR": 7698,"HIREDATE": "1981-02-22 00:00:00","SAL": 1250.00,"COMM": 500.00,"DEPTNO": 30}
{"EMPNO": 7566,"ENAME": "JONES","JOB": "MANAGER","MGR": 7839,"HIREDATE": "1981-04-02 00:00:00","SAL": 2975.00,"COMM": null,"DEPTNO": 20}
{"EMPNO": 7654,"ENAME": "MARTIN","JOB": "SALESMAN","MGR": 7698,"HIREDATE": "1981-09-28 00:00:00","SAL": 1250.00,"COMM": 1400.00,"DEPTNO": 30}
{"EMPNO": 7698,"ENAME": "BLAKE","JOB": "MANAGER","MGR": 7839,"HIREDATE": "1981-05-01 00:00:00","SAL": 2850.00,"COMM": null,"DEPTNO": 30}
{"EMPNO": 7782,"ENAME": "CLARK","JOB": "MANAGER","MGR": 7839,"HIREDATE": "1981-06-09 00:00:00","SAL": 2450.00,"COMM": null,"DEPTNO": 10}
{"EMPNO": 7788,"ENAME": "SCOTT","JOB": "ANALYST","MGR": 7566,"HIREDATE": "1987-04-19 00:00:00","SAL": 1500.00,"COMM": null,"DEPTNO": 20}
{"EMPNO": 7839,"ENAME": "KING","JOB": "PRESIDENT","MGR": null,"HIREDATE": "1981-11-17 00:00:00","SAL": 5000.00,"COMM": null,"DEPTNO": 10}
{"EMPNO": 7844,"ENAME": "TURNER","JOB": "SALESMAN","MGR": 7698,"HIREDATE": "1981-09-08 00:00:00","SAL": 1500.00,"COMM": 0.00,"DEPTNO": 30}
{"EMPNO": 7876,"ENAME": "ADAMS","JOB": "CLERK","MGR": 7788,"HIREDATE": "1987-05-23 00:00:00","SAL": 1100.00,"COMM": null,"DEPTNO": 20}
{"EMPNO": 7900,"ENAME": "JAMES","JOB": "CLERK","MGR": 7698,"HIREDATE": "1981-12-03 00:00:00","SAL": 950.00,"COMM": null,"DEPTNO": 30}
{"EMPNO": 7902,"ENAME": "FORD","JOB": "ANALYST","MGR": 7566,"HIREDATE": "1981-12-03 00:00:00","SAL": 3000.00,"COMM": null,"DEPTNO": 20}
{"EMPNO": 7934,"ENAME": "MILLER","JOB": "CLERK","MGR": 7782,"HIREDATE": "1982-01-23 00:00:00","SAL": 1300.00,"COMM": null,"DEPTNO": 10}

0: jdbc:hive2://CentOS:10000> add  jar /usr/apache-hive-1.2.2-bin/hcatalog/share/hcatalog/hive-hcatalog-core-1.2.2.jar

CREATE EXTERNAL TABLE t_emp_json(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2),
    deptno INT)
    ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe';
    
0: jdbc:hive2://CentOS:10000> select empno,ename,job,mgr,hiredate,sal,comm,deptno from t_emp_json;

+--------+---------+------------+-------+------------------------+-------+-------+---------+--+
| empno  |  ename  |    job     |  mgr  |        hiredate        |  sal  | comm  | deptno  |
+--------+---------+------------+-------+------------------------+-------+-------+---------+--+
| 7369   | SMITH   | CLERK      | 7902  | 1980-12-17 00:00:00.0  | 800   | NULL  | 20      |
| 7499   | ALLEN   | SALESMAN   | 7698  | 1981-02-20 00:00:00.0  | 1600  | 300   | 30      |
| 7521   | WARD    | SALESMAN   | 7698  | 1981-02-22 00:00:00.0  | 1250  | 500   | 30      |
| 7566   | JONES   | MANAGER    | 7839  | 1981-04-02 00:00:00.0  | 2975  | NULL  | 20      |
| 7654   | MARTIN  | SALESMAN   | 7698  | 1981-09-28 00:00:00.0  | 1250  | 1400  | 30      |
| 7698   | BLAKE   | MANAGER    | 7839  | 1981-05-01 00:00:00.0  | 2850  | NULL  | 30      |
| 7782   | CLARK   | MANAGER    | 7839  | 1981-06-09 00:00:00.0  | 2450  | NULL  | 10      |
| 7788   | SCOTT   | ANALYST    | 7566  | 1987-04-19 00:00:00.0  | 1500  | NULL  | 20      |
| 7839   | KING    | PRESIDENT  | NULL  | 1981-11-17 00:00:00.0  | 5000  | NULL  | 10      |
| 7844   | TURNER  | SALESMAN   | 7698  | 1981-09-08 00:00:00.0  | 1500  | 0     | 30      |
| 7876   | ADAMS   | CLERK      | 7788  | 1987-05-23 00:00:00.0  | 1100  | NULL  | 20      |
| 7900   | JAMES   | CLERK      | 7698  | 1981-12-03 00:00:00.0  | 950   | NULL  | 30      |
| 7902   | FORD    | ANALYST    | 7566  | 1981-12-03 00:00:00.0  | 3000  | NULL  | 20      |
| 7934   | MILLER  | CLERK      | 7782  | 1982-01-23 00:00:00.0  | 1300  | NULL  | 10      |
+--------+---------+------------+-------+------------------------+-------+-------+---------+--+

 CREATE TABLE t_employee(
    empno INT,
    ename STRING,
    job STRING,
    mgr INT,
    hiredate TIMESTAMP,
    sal DECIMAL(7,2),
    comm DECIMAL(7,2)
    )
    PARTITIONED BY (deptno INT)   
    ROW FORMAT DELIMITED FIELDS TERMINATED BY "\t";

0: jdbc:hive2://CentOS:10000> insert overwrite  table t_employee partition(deptno=10) select empno,ename,job,mgr,hiredate,sal,comm from t_emp_json where deptno=10;--覆盖
0: jdbc:hive2://CentOS:10000> insert into  table t_employee partition(deptno=20) select empno,ename,job,mgr,hiredate,sal,comm from t_emp_json where deptno=20;--追加

将查询结果插入多个表中

FROM from_statement
INSERT OVERWRITE TABLE tablename1 
[PARTITION (partcol1=val1, partcol2=val2 ...) [IF NOT EXISTS]] select_statement1
[INSERT OVERWRITE TABLE tablename2 [PARTITION ... [IF NOT EXISTS]] select_statement2]
[INSERT INTO TABLE tablename2 [PARTITION ...] select_statement2] ...;

from t_emp_json 
INSERT OVERWRITE TABLE t_employee partition(deptno=10) select empno,ename,job,mgr,hiredate,sal,comm  where deptno=10 
INSERT OVERWRITE TABLE t_employee partition(deptno=20) select empno,ename,job,mgr,hiredate,sal,comm  where deptno=20 
INSERT OVERWRITE TABLE t_employee partition(deptno=30) select empno,ename,job,mgr,hiredate,sal,comm  where deptno=30

动态插入

0: jdbc:hive2://CentOS:10000> set hive.exec.dynamic.partition.mode=nonstrict;#开启动态分区
No rows affected (0.004 seconds)
0: jdbc:hive2://CentOS:10000> INSERT OVERWRITE TABLE t_employee PARTITION (deptno)  SELECT empno,ename,job,mgr,hiredate,sal,comm,deptno FROM t_emp_json;

0: jdbc:hive2://CentOS:10000> show partitions t_employee;
+------------+--+
| partition  |
+------------+--+
| deptno=10  |
| deptno=20  |
| deptno=30  |
+------------+--+
3 rows selected (0.064 seconds)

结果写出到文件系统

INSERT OVERWRITE [LOCAL] DIRECTORY directory1
  [ROW FORMAT row_format] [STORED AS file_format] 
  SELECT ... FROM ...
[ROW FORMAT row_format]：不指定采用默认分隔符
[STORED AS file_format]：输出类型

0: jdbc:hive2://CentOS:10000> INSERT OVERWRITE  DIRECTORY '/employee' ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' STORED AS TEXTFILE select * from t_employee;

丿沐染烟忱丶

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Hive-DML操作

加载文件数据到表中LOAD DATA [LOCAL] INPATH 'filepath' [OVERWRITE] INTO TABLE tablename [PARTITION (partcol1=val1, partcol2=val2 ...)]load data local inpath "/root/baizhi/t_employee" overwrite into table t_e...
复制链接

扫一扫