This PR fixes a performance problem when reviewing a pull request in a
big instance which have many records in the `review` table.
Traditionally, we should add more indexes in that table. But since
dismissed reviews of 1 pull request will not be too many as expected in
a common repository. Filtering reviews in the memory should be more
quick .
---------
Co-authored-by: wxiaoguang <wxiaoguang@gmail.com>
// Get latest review of each reviewer, sorted in order they were made
// Get all reviews for the issue id
iferr:=db.GetEngine(ctx).SQL("SELECT * FROM review WHERE id IN (SELECT max(id) as id FROM review WHERE issue_id = ? AND reviewer_team_id = 0 AND type in (?, ?, ?) AND original_author_id <> 0 GROUP BY issue_id, original_author_id) ORDER BY review.updated_unix ASC",
// Get latest review of each reviewer, sorted in order they were made
individualReviews:=make([]*Review,0,10)
iferr:=sess.SQL("SELECT * FROM review WHERE id IN (SELECT max(id) as id FROM review WHERE issue_id = ? AND reviewer_team_id = 0 AND type in (?, ?, ?) AND dismissed = ? AND original_author_id = 0 GROUP BY issue_id, reviewer_id) ORDER BY review.updated_unix ASC",
iferr:=sess.SQL("SELECT * FROM review WHERE id IN (SELECT max(id) as id FROM review WHERE issue_id = ? AND reviewer_team_id <> 0 AND original_author_id = 0 GROUP BY issue_id, reviewer_team_id) ORDER BY review.updated_unix ASC",