hive表操做（轉）

轉載於：http://blog.csdn.net/lovelovelovelovelo/article/details/52234971

數據類型 
基本數據類型 
集合類型，array、map、struct 
文件格式，textfile、sequencefile、rcfile

建立表（內部表）

create table employee(
    name string comment 'name',
    salary float,
    subordinates array<string>,
    deductions map<string,float>,
    address struct<street:string,city:string,state:string,zip:int>
)
row format delimited fields termited by '\t' lines terminated by '\n' stored as textfile;

 

從文件加載數據，覆蓋源表

load data local infile 'path' overwrite into table 'table'

 

 

建立外部表

create external table employee(
    name string comment 'name',
    salary float,
    subordinates array<string>,
    deductions map<string,float>,
    address struct<street:string,city:string,state:string,zip:int>
)
row format delimited fields terminated by '\t' 
collection items terminated by ','
map keys terminated by ':'
lines terminated by '\n'
stored as textfile
location '/data/';

 

表中數據

lucy 11000 tom,jack,dave,kate  tom:1200,jack:1560 beijing,changanjie,xichengqu,10000
lily 13000 dave,kate  dave:1300,kate:1260 beijing,changanjie,xichengqu,10000

 

 

和咱們熟悉的關係型數據庫不同，Hive如今還不支持在insert語句裏面直接給出一組記錄的文字形式，也就是說，hive並不支持INSERT INTO …. VALUES形式的語句。

新建employee.txt，將數據存入文件中，注意字段間用tab，行間換行enter 
經過hive命令加載數據

hive> load data local inpath '/root/employee.txt' into table employee;
hive> select * from employee;                                         
OK
lucy    11000.0 ["tom","jack","dave","kate"]    {"tom":1200.0,"jack":1560.0}    {"street":"beijing","city":"changanjie","state":"xichengqu","zip":10000}
lily    13000.0 ["dave","kate"] {"dave":1300.0,"kate":1260.0}   {"street":"beijing","city":"changanjie","state":"xichengqu","zip":10000}
Time taken: 0.054 seconds, Fetched: 2 row(s)

select * from table不走mapreduce 

 

由一個表建立另外一個表

create table table2 like table1;

 

從其餘表查詢建立表

create table table2 as select name,age,add from table1;

 

 

hive不一樣文件讀取

stored as textfile:
    hadoop fs -text
stored as sequencefile:
    hadoop fs -text
stored as rcfile:
    hive -service rcfilecat path
stored as input format 'class':
    outformat 'class'

 

分區表操做

alter table employee add if not exists partition(country='')
alter table employee drop if exists partition(country='')

 

 

hive分桶

create table bucket_table(
    id int,
    name string
)
clustered by(id) sorted by(name) into 4 buckets
row format  delimited fields terminated by '\t' stored as textfile;
set hive.enforce.bucketing=true;

 

 

建立分區表

create table partitionTable(
    name string,
    age int
)
partitioned by(dt string)
row format delimited fields terminated by '\t' 
lines terminated by '\n'
stored as textfile;