[
https://issues.apache.org/jira/browse/TAJO-200?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jinho Kim updated TAJO-200:
---------------------------
Attachment: TAJO-200.patch
{code:title=Text Serialize/Deserialize |borderStyle=solid}
// Tajo
CREATE TABLE tablename (col1 type, col2 type)
USING RCFILE WITH
('rcfile.serde'='org.apache.tajo.storage.TextSerializeDeserialize')
//Hive 0.11 <=
CREATE TABLE tablename (col1 type, col2 type)
STORED AS RCFILE
{code}
{code:title=Binary Serialize/Deserialize |borderStyle=solid}
// Tajo
CREATE TABLE tablename (col1 type, col2 type)
USING RCFILE
//Hive
CREATE TABLE tablename (col1 type, col2 type)
ROW FORMAT SERDE
'org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe'
STORED AS RCFILE
{code}
{code:title=Lineitem example |borderStyle=solid}
CREATE TABLE lineitem (L_ORDERKEY bigint,
L_PARTKEY bigint,
L_SUPPKEY bigint,
L_LINENUMBER bigint,
L_QUANTITY double,
L_EXTENDEDPRICE double,
L_DISCOUNT double,
L_TAX double,
L_RETURNFLAG text,
L_LINESTATUS text,
L_SHIPDATE text,
L_COMMITDATE text,
L_RECEIPTDATE text,
L_SHIPINSTRUCT text,
L_SHIPMODE text,
L_COMMENT text)
USING RCFILE WITH
('rcfile.serde'='org.apache.tajo.storage.TextSerializeDeserialize',
'compression.codec'='org.apache.hadoop.io.compress.SnappyCodec',
'rcfile.null'='\\N')
{code}
> RCFile compatible to apache hive
> --------------------------------
>
> Key: TAJO-200
> URL: https://issues.apache.org/jira/browse/TAJO-200
> Project: Tajo
> Issue Type: New Feature
> Components: storage
> Reporter: Jinho Kim
> Assignee: Jinho Kim
> Fix For: 0.8-incubating
>
> Attachments: TAJO-200.patch
>
>
> * Support both the text and the binary serialization/deserialization.
> ** dafault : org.apache.tajo.storage.BinarySerializeDeserialize
> * use SequenceFile.metadata.
> ** key: rcfile.serde
> ** value: org.apache.tajo.storage.BinarySerializeDeserialize,
> org.apache.tajo.storage.TextSerializeDeserialize
> * improve memory efficiency
> * support tajo pushdown projection
> * support compression
--
This message was sent by Atlassian JIRA
(v6.1#6144)
