If we run the tileset script, it chokes and dies on 30 October - Hive doesn't return any data that meets the query. Wat?
Query:
SELECT style, zoom, scale, format, user_id, cache, COUNT(1) AS n
FROM (
SELECT
REGEXP_EXTRACT(uri_path, '^/([^/]+)/([0-9]{1,2})/(-?[0-9]+)/(-?[0-9]+)(@([0-9]\\.?[0-9]?)x)?\\.([a-z]+)$', 1) AS style,
REGEXP_EXTRACT(uri_path, '^/([^/]+)/([0-9]{1,2})/(-?[0-9]+)/(-?[0-9]+)(@([0-9]\\.?[0-9]?)x)?\\.([a-z]+)$', 2) AS zoom,
COALESCE(REGEXP_EXTRACT(uri_path, '^/([^/]+)/([0-9]{1,2})/(-?[0-9]+)/(-?[0-9]+)(@([0-9]\\.?[0-9]?)x)?\\.([a-z]+)$', 6), '1') AS scale,
REGEXP_EXTRACT(uri_path, '^/([^/]+)/([0-9]{1,2})/(-?[0-9]+)/(-?[0-9]+)(@([0-9]\\.?[0-9]?)x)?\\.([a-z]+)$', 7) AS format,
CONCAT(user_agent, client_ip) AS user_id,
cache_status AS cache
FROM wmf.webrequest
WHERE
year=2015 AND month=10 and day=30
AND webrequest_source = 'maps'
AND http_status IN('200','304')
AND uri_path RLIKE '^/([^/]+)/([0-9]{1,2})/(-?[0-9]+)/(-?[0-9]+)(@([0-9]\\.?[0-9]?)x)?\\.([a-z]+)$'
) prepared
GROUP BY style, zoom, scale, format, user_id, cache;