• 使用HQL语句创建一个指向HBase的Hive表

CREATE TABLE hbase_table_1(key int, value string) //Hive中的表名hbase_table_1
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'  //指定存储处理器
WITH SERDEPROPERTIES ("hbase.columns.mapping" = ":key,cf1:val") //声明列族，列名
TBLPROPERTIES ("hbase.table.name" = "xyz", "hbase.mapred.output.outputtable" = "xyz");  
//hbase.table.name声明HBase表名，为可选属性默认与Hive的表名相同，
//hbase.mapred.output.outputtable指定插入数据时写入的表，如果以后需要往该表插入数据就需要指定该值

• 通过HBase shell可以查看刚刚创建的HBase表的属性

$ hbase shell
HBase Shell; enter 'help<RETURN>' for list of supported commands.
Version: 0.20.3, r902334, Mon Jan 25 13:13:08 PST 2010
hbase(main):001:0> list
xyz                                                                                                           
1 row(s) in 0.0530 seconds
hbase(main):002:0> describe "xyz"
DESCRIPTION                                                           ENABLED                               
  {NAME => 'xyz', FAMILIES => [{NAME => 'cf1', COMPRESSION => 'NONE', VE true                                  
  RSIONS => '3', TTL => '2147483647', BLOCKSIZE => '65536', IN_MEMORY =>                                       
  'false', BLOCKCACHE => 'true'}]}                                                                            
1 row(s) in 0.0220 seconds

hbase(main):003:0> scan "xyz"
ROW                          COLUMN+CELL                                                                      
0 row(s) in 0.0060 seconds

• 使用HQL向HBase表中插入数据

INSERT OVERWRITE TABLE hbase_table_1 SELECT * FROM pokes WHERE foo=98;

• 在HBase端查看插入的数据

hbase(main):009:0> scan "xyz"
ROW                          COLUMN+CELL                                                                      
 98                          column=cf1:val, timestamp=1267737987733, value=val_98                            
1 row(s) in 0.0110 seconds

• 创建一个指向已经存在的HBase表的Hive表

CREATE EXTERNAL TABLE hbase_table_2(key int, value string) 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES ("hbase.columns.mapping" = "cf1:val")
TBLPROPERTIES("hbase.table.name" = "some_existing_table", "hbase.mapred.output.outputtable" = "some_existing_table");

CREATE TABLE hbase_table_1(key int, value1 string, value2 int, value3 int) 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES (
"hbase.columns.mapping" = ":key,a:b,a:c,d:e"
);
INSERT OVERWRITE TABLE hbase_table_1 SELECT foo, bar, foo+1, foo+2 
FROM pokes WHERE foo=98 OR foo=100;

CREATE TABLE hbase_table_1(value map<string,int>, row_key int) 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES (
"hbase.columns.mapping" = "cf:,:key"
);
INSERT OVERWRITE TABLE hbase_table_1 SELECT map(bar, foo), foo FROM pokes 
WHERE foo=98 OR foo=100;

• 在HBase下查看数据

hbase(main):012:0> scan "hbase_table_1"
ROW                          COLUMN+CELL                                                                      
 100                         column=cf:val_100, timestamp=1267739509194, value=100                            
 98                          column=cf:val_98, timestamp=1267739509194, value=98                              
2 row(s) in 0.0080 seconds

• 在Hive下查看数据

hive> select * from hbase_table_1;
Total MapReduce jobs = 1
Launching Job 1 out of 1
...
OK
{"val_100":100}    100
{"val_98":98}    98
Time taken: 3.808 seconds

CREATE TABLE hbase_table_1(key int, value map<int,int>) 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES (
"hbase.columns.mapping" = ":key,cf:"
);

CREATE TABLE hbase_table_1(key int, value string) 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler'
WITH SERDEPROPERTIES (
"hbase.columns.mapping" = ":key,cf:"
);

CREATE EXTERNAL TABLE delimited_example(key struct<f1:string, f2:string>, value string) 
ROW FORMAT DELIMITED 
COLLECTION ITEMS TERMINATED BY '~' 
STORED BY 'org.apache.hadoop.hive.hbase.HBaseStorageHandler' 
WITH SERDEPROPERTIES (
  'hbase.columns.mapping'=':key,f:c1');