Skip to content

Instantly share code, notes, and snippets.

@laughingman7743
Created April 21, 2016 14:19
Show Gist options
  • Save laughingman7743/e4085226aebd8bb72f78627042cbb8e6 to your computer and use it in GitHub Desktop.
Save laughingman7743/e4085226aebd8bb72f78627042cbb8e6 to your computer and use it in GitHub Desktop.
ADD JAR /usr/lib/hive-hcatalog/share/hcatalog/hive-hcatalog-core-1.0.0-amzn-3.jar;
CREATE EXTERNAL TABLE IF NOT EXISTS test_json_table
(
_id bigint,
column1 string,
column2 string,
column3 string,
column4 string,
column5 string
)
PARTITIONED BY(year string, month string, day string, hour string)
ROW FORMAT SERDE 'org.apache.hive.hcatalog.data.JsonSerDe' STORED AS TEXTFILE
LOCATION 's3://YOUR_BUCKET/path/to/json/';
SET hive.exec.dynamic.partition.mode=nonstrict;
SET hive.exec.compress.output=true;
SET io.seqfile.compression.type=BLOCK;
SET mapred.output.compression.codec = org.apache.hadoop.io.compress.GzipCodec;
ADD JAR /usr/lib/hive-hcatalog/share/hcatalog/hive-hcatalog-core-1.0.0-amzn-3.jar;
INSERT OVERWRITE TABLE test_json_table
PARTITION(year, month, day, hour)
SELECT
_id,
column1,
column2,
column3,
column4,
column5,
year,
month,
day,
hour
FROM test_table;
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment