中文
devexamples

Row Number Deduplication Keep Latest

Deduplicate rows keeping the newest per key with ROW_NUMBER, sweeping duplicates in one statement or blocking them upstream.

SqlData Integrity

Code

snippet
-- 每个邮箱保留 created_at 最新的一行，标记其余为重复
WITH ranked AS (
  SELECT
    id,
    email,
    created_at,
    ROW_NUMBER() OVER (
      PARTITION BY email
      ORDER BY created_at DESC, id DESC
    ) AS rn
  FROM subscribers
)
SELECT id, email, created_at, (rn = 1) AS is_primary
FROM ranked
ORDER BY email, rn;

-- 一次性清扫：删除全部非首行
WITH ranked AS (
  SELECT id,
         ROW_NUMBER() OVER (
           PARTITION BY email
           ORDER BY created_at DESC, id DESC
         ) AS rn
  FROM subscribers
)
DELETE FROM subscribers s
USING ranked r
WHERE s.id = r.id
  AND r.rn > 1;

-- 上游堵漏：唯一索引阻止重复再次写入
CREATE UNIQUE INDEX CONCURRENTLY idx_subscribers_email
  ON subscribers (email);

Related Examples