WITH q AS
(
SELECT (
SELECT MIN(start_date)
FROM mytable
) + level - 1 AS mydate
FROM dual
CONNECT BY
level <= (
SELECT MAX(end_date) - MIN(start_date)
FROM mytable
)
)
SELECT group, mydate,
(
SELECT COUNT(*)
FROM mytable mi
WHERE mi.group = mo.group
AND q BETWEEN mi.start_date AND mi.end_date
)
FROM q
CROSS JOIN
(
SELECT DISTINCT group
FROM mytable
) mo
Актуализация:
По-добра и по-бърза заявка, използваща аналитични функции.
Основната идея е, че броят на диапазоните, съдържащи всяка дата, е разликата преди броя на диапазоните, започнали преди тази дата, и броя на диапазоните, които са приключили преди нея.
SELECT cur_date,
grouper,
SUM(COALESCE(scnt, 0) - COALESCE(ecnt, 0)) OVER (PARTITION BY grouper ORDER BY cur_date) AS ranges
FROM (
SELECT (
SELECT MIN(start_date)
FROM t_range
) + level - 1 AS cur_date
FROM dual
CONNECT BY
level <=
(
SELECT MAX(end_date)
FROM t_range
) -
(
SELECT MIN(start_date)
FROM t_range
) + 1
) dates
CROSS JOIN
(
SELECT DISTINCT grouper AS grouper
FROM t_range
) groups
LEFT JOIN
(
SELECT grouper AS sgrp, start_date, COUNT(*) AS scnt
FROM t_range
GROUP BY
grouper, start_date
) starts
ON sgrp = grouper
AND start_date = cur_date
LEFT JOIN
(
SELECT grouper AS egrp, end_date, COUNT(*) AS ecnt
FROM t_range
GROUP BY
grouper, end_date
) ends
ON egrp = grouper
AND end_date = cur_date - 1
ORDER BY
grouper, cur_date
Тази заявка завършва за 1
второ на 1,000,000
редове.
Вижте този запис в моя блог за повече подробности: