查询仅适用于某些情况

时间：2016-03-21 08:06:03

标签： mysql sql database date relational-database

我有一张类似于以下结构的表格：

City        start_date             end_date
Paris       1995-01-01 00:00:00    1997-10-01 23:59:59
Paris       1997-10-02 00:00:00    0001-01-01 00:00:00
Paris       2013-01-25 00:00:00    0001-01-01 00:00:00
Paris       2015-04-25 00:00:00    0001-01-01 00:00:00
Berlin      2014-11-01 00:00:00    0001-01-01 00:00:00
Berlin      2014-06-01 00:00:00    0001-01-01 00:00:00
Berlin      2015-09-11 00:00:00    0001-01-01 00:00:00
Berlin      2015-10-01 00:00:00    0001-01-01 00:00:00
Milan       2001-01-01 00:00:00    0001-01-01 00:00:00
Milan       2005-10-02 00:00:00    2006-10-02 23:59:59
Milan       2006-10-03 00:00:00    2015-04-24 23:59:59
Milan       2015-04-25 00:00:00    0001-01-01 00:00:00

数据包含基于城市的开始和结束日期的历史视图。城市的最新记录应该是具有最高开始日期和结束日期为＆＃0001; 0001-01-01 00：00：00＆＃39;，表示还没有结束日期。

我需要清理这些数据并确保每个城市的历史记录都有在下一个记录的开始日期前一秒，仅在设置了end_date的情况下到＃0001; 0001-01-01 00：00：00＆＃39;。因此，在end_date具有实际日期的情况下，将忽略该日期。此外，具有最近一个城市的start_date的记录不需要修改end_date。

结果表应如下所示：

City        start_date             end_date
Paris       1995-01-01 00:00:00    1997-10-01 23:59:59
Paris       1997-10-02 00:00:00    2013-01-24 23:59:59
Paris       2013-01-25 00:00:00    2015-04-24 23:59:59
Paris       2015-04-25 00:00:00    0001-01-01 00:00:00
Berlin      2014-11-01 00:00:00    2014-05-31 23:59:59
Berlin      2014-06-01 00:00:00    2015-09-10 23:59:59
Berlin      2015-09-11 00:00:00    2015-09-30 23:59:59
Berlin      2015-10-01 00:00:00    0001-01-01 23:59:59
Milan       2001-01-01 00:00:00    2005-10-01 23:59:59
Milan       2005-10-02 00:00:00    2006-10-02 23:59:59
Milan       2006-10-03 00:00:00    2015-04-24 23:59:59
Milan       2015-04-25 00:00:00    0001-01-01 00:00:00

我尝试了this question中用户建议的以下脚本。

update test join
       (select t.*,
               (select min(start_date)
                from test t2
                where t2.city = t.city and
                      t2.start_date > t.start_date
                order by t2.start_date
                limit 1
               ) as next_start_date
        from test t
       ) tt
       on tt.city = test.city and tt.start_date = test.start_date
    set test.end_date = date_sub(tt.next_start_date, interval 1 second)
where test.end_date = '0001-01-01' and
      next_start_date is not null;

不幸的是，从柏林记录开始，有些end_dates不符合预期（例如id号为5和6）。然而，其他人正如他们应该出现的那样。如下所示：

enter image description here

以下是能够复制的create和insert语句：

CREATE TABLE `test` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `city` varchar(50) DEFAULT NULL,
  `start_date` datetime DEFAULT NULL,
  `end_date` datetime DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=13 DEFAULT CHARSET=utf8;

INSERT INTO test (city, start_date, end_date) VALUES ('Paris','1995-01-01 00:00:00','1997-10-01 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','1997-10-02 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','2013-01-25 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','2015-04-25 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2014-11-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2014-06-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2015-09-11 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2015-10-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2001-01-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2005-10-02 00:00:00','2006-10-02 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2006-10-03 00:00:00','2015-04-24 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2015-04-25 00:00:00','0001-01-01 00:00:00');

1 个答案:

答案 0 :(得分：-1)

-- query wanted
UPDATE test t1 INNER JOIN
    (SELECT *, @id := @id + 1 AS new_id 
     FROM test CROSS JOIN (SELECT @id := 0) param
     ORDER BY city, start_date) t2
     ON t1.city = t2.city AND t1.start_date = t2.start_date
     INNER JOIN 
    (SELECT *, @id2 := @id2 + 1 AS new_id 
     FROM test CROSS JOIN (SELECT @id2 := 0) param
     ORDER BY city, start_date) t3 
     ON t2.new_id + 1 = t3.new_id AND t2.city = t3.city
SET t1.end_date = DATE_SUB(t3.start_date, INTERVAL 1 SECOND)
WHERE t1.end_date = '0001-01-01 00:00:00';

以下是完整演示。

SQL：

-- data
CREATE TABLE `test` (
  `id` int(11) NOT NULL AUTO_INCREMENT,
  `city` varchar(50) DEFAULT NULL,
  `start_date` datetime DEFAULT NULL,
  `end_date` datetime DEFAULT NULL,
  PRIMARY KEY (`id`)
) ENGINE=InnoDB AUTO_INCREMENT=13 DEFAULT CHARSET=utf8;

INSERT INTO test (city, start_date, end_date) VALUES ('Paris','1995-01-01 00:00:00','1997-10-01 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','1997-10-02 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','2013-01-25 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Paris','2015-04-25 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2014-11-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2014-06-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2015-09-11 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Berlin','2015-10-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2001-01-01 00:00:00','0001-01-01 00:00:00');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2005-10-02 00:00:00','2006-10-02 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2006-10-03 00:00:00','2015-04-24 23:59:59');
INSERT INTO test (city, start_date, end_date) VALUES ('Milan','2015-04-25 00:00:00','0001-01-01 00:00:00');
select * from test;

-- query wanted
UPDATE test t1 INNER JOIN
    (SELECT *, @id := @id + 1 AS new_id 
     FROM test CROSS JOIN (SELECT @id := 0) param
     ORDER BY city, start_date) t2
     ON t1.city = t2.city AND t1.start_date = t2.start_date
     INNER JOIN 
    (SELECT *, @id2 := @id2 + 1 AS new_id 
     FROM test CROSS JOIN (SELECT @id2 := 0) param
     ORDER BY city, start_date) t3 
     ON t2.new_id + 1 = t3.new_id AND t2.city = t3.city
SET t1.end_date = DATE_SUB(t3.start_date, INTERVAL 1 SECOND)
WHERE t1.end_date = '0001-01-01 00:00:00';

select * from test;

输出：

mysql> -- query wanted
mysql> UPDATE test t1 INNER JOIN
    -> (SELECT *, @id := @id + 1 AS new_id
    ->  FROM test CROSS JOIN (SELECT @id := 0) param
    ->  ORDER BY city, start_date) t2
    ->  ON t1.city = t2.city AND t1.start_date = t2.start_date
    ->  INNER JOIN
    -> (SELECT *, @id2 := @id2 + 1 AS new_id
    ->  FROM test CROSS JOIN (SELECT @id2 := 0) param
    ->  ORDER BY city, start_date) t3
    ->  ON t2.new_id + 1 = t3.new_id AND t2.city = t3.city
    -> SET t1.end_date = DATE_SUB(t3.start_date, INTERVAL 1 SECOND)
    -> WHERE t1.end_date = '0001-01-01 00:00:00';
rom tesQuery OK, 6 rows affected (0.00 sec)
Rows matched: 6  Changed: 6  Warnings: 0

mysql> select * from test;
+----+--------+---------------------+---------------------+
| id | city   | start_date          | end_date            |
+----+--------+---------------------+---------------------+
| 13 | Paris  | 1995-01-01 00:00:00 | 1997-10-01 23:59:59 |
| 14 | Paris  | 1997-10-02 00:00:00 | 2013-01-24 23:59:59 |
| 15 | Paris  | 2013-01-25 00:00:00 | 2015-04-24 23:59:59 |
| 16 | Paris  | 2015-04-25 00:00:00 | 0001-01-01 00:00:00 |
| 17 | Berlin | 2014-11-01 00:00:00 | 2014-05-31 23:59:59 |
| 18 | Berlin | 2014-06-01 00:00:00 | 2015-09-10 23:59:59 |
| 19 | Berlin | 2015-09-11 00:00:00 | 2015-09-30 23:59:59 |
| 20 | Berlin | 2015-10-01 00:00:00 | 0001-01-01 00:00:00 |
| 21 | Milan  | 2001-01-01 00:00:00 | 2005-10-01 23:59:59 |
| 22 | Milan  | 2005-10-02 00:00:00 | 2006-10-02 23:59:59 |
| 23 | Milan  | 2006-10-03 00:00:00 | 2015-04-24 23:59:59 |
| 24 | Milan  | 2015-04-25 00:00:00 | 0001-01-01 00:00:00 |
+----+--------+---------------------+---------------------+
12 rows in set (0.00 sec)
相关问题
最新问题