i5v7e7hK

1-- From CSV to Parquet in favor to Cloudera Impala
2CREATE EXTERNAL TABLE IF NOT EXISTS [from_table] (
3		schema DATA_TYPE,
4    ...
5	)
6	COMMENT 'A sample of vehicle infomation'
7	ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
8	WITH SERDEPROPERTIES (
9	   "separatorChar" = ",",
10	   "quoteChar"     = "\""
11	)  
12	LOCATION '/user/cloudera/path/to/source.csv'
13  tblproperties ("skip.header.line.count"="1");
14
15-- Conversion
16CREATE EXTERNAL TABLE IF NOT EXISTS [target_table] (
17		same_schema DATA_TYPE,
18    ...
19	)
20	STORED AS PARQUET
21  LOCATION '/user/cloudera/path/to/target';
22
23INSERT overwrite TABLE [target_table] SELECT * FROM [from_table];