@Mehdi TAZI
Avro
CREATE EXTERNAL TABLE table_avro
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
TBLPROPERTIES ('avro.schema.url'='hdfs://user/schemas/table_avro.avsc')
STORED AS INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
LOCATION '/user/table/table_avro';
From Hive 0.14 and Up (Easier DDL)
CREATE TABLE kst (
string1 string,
string2 string,
int1 int,
boolean1 boolean,
long1 bigint,
float1 float,
double1 double,
inner_record1 struct,
enum1 string,
array1 array,
map1 map,
union1 uniontype,
fixed1 binary,
null1 void,
unionnullint int,
bytes1 binary)
PARTITIONED BY (ds string)
STORED AS AVRO;
See Apache Hive language Docs also here for more examples on Avro and Parquet However to get true performance benefits of Hive with Cost Base optimization and Vectorization you should consider having your Hive tables in the ORC format.
... View more
