gistfile1.txt

CREATE TABLE IF NOT EXISTS normalized (
 gram string,
 year int,
 occurrences bigint
);

INSERT OVERWRITE TABLE normalized 
SELECT
 lower(gram),
 year,
 occurrences
FROM
ngrams
WHERE
 year >= (${hiveconf:min_year} - 1) AND
 year <= ${hiveconf:max_year} AND
 gram REGEXP "^[A-Za-z+'-]{3,}$";