CREATE TABLE table1( uid VARCHAR(10) NOT NULL, name VARCHAR(10) NOT NULL, PRIMARY KEY(uid))ENGINE=INNODB DEFAULT CHARSET=UTF8; CREATE TABLE table2( oid INT NOT NULL auto_increment, uid VARCHAR(10), PRIMARY KEY(oid))ENGINE=INNODB DEFAULT CHARSET=UTF8;
3. 插入数据
INSERT INTO table1(uid,name) VALUES('aaa','mike'),('bbb','jack'),('ccc','mike'),('ddd','mike'); INSERT INTO table2(uid) VALUES('aaa'),('aaa'),('bbb'),('bbb'),('bbb'),('ccc'),(NULL);
4. 最后想要的结果
SELECT a.uid, count(b.oid) AS totalFROM table1 AS aLEFT JOIN table2 AS b ON a.uid = b.uidWHERE a. NAME = 'mike'GROUP BY a.uidHAVING count(b.oid) < 2ORDER BY total DESCLIMIT 1;
3.2 现在开始SQL解析之旅吧!
1. FROM
当涉及多个表的时候,左边表的输出会作为右边表的输入,之后会生成一个虚拟表 VT1。
(1-J1)笛卡尔积
计算两个相关联表的笛卡尔积 (CROSS JOIN) ,生成虚拟表 VT1-J1。
mysql> select * from table1,table2;+-----+------+-----+------+| uid | name | oid | uid |+-----+------+-----+------+| aaa | mike | 1 | aaa || bbb | jack | 1 | aaa || ccc | mike | 1 | aaa || ddd | mike | 1 | aaa || aaa | mike | 2 | aaa || bbb | jack | 2 | aaa || ccc | mike | 2 | aaa || ddd | mike | 2 | aaa || aaa | mike | 3 | bbb || bbb | jack | 3 | bbb || ccc | mike | 3 | bbb || ddd | mike | 3 | bbb || aaa | mike | 4 | bbb || bbb | jack | 4 | bbb || ccc | mike | 4 | bbb || ddd | mike | 4 | bbb || aaa | mike | 5 | bbb || bbb | jack | 5 | bbb || ccc | mike | 5 | bbb || ddd | mike | 5 | bbb || aaa | mike | 6 | ccc || bbb | jack | 6 | ccc || ccc | mike | 6 | ccc || ddd | mike | 6 | ccc || aaa | mike | 7 | NULL || bbb | jack | 7 | NULL || ccc | mike | 7 | NULL || ddd | mike | 7 | NULL |+-----+------+-----+------+28 rows in set (0.00 sec)
(1-J2) ON过滤
基于虚拟表 VT1-J1 这一个虚拟表进行过滤,过滤出所有满足 ON 谓词条件的列,生成虚拟表 VT1-J2。
注意:这里因为语法限制,使用了 'WHERE' 代替,从中读者也可以感受到两者之间微妙的关系。
mysql> SELECT -> * -> FROM -> table1, -> table2 -> WHERE -> table1.uid = table2.uid -> ;+-----+------+-----+------+| uid | name | oid | uid |+-----+------+-----+------+| aaa | mike | 1 | aaa || aaa | mike | 2 | aaa || bbb | jack | 3 | bbb || bbb | jack | 4 | bbb || bbb | jack | 5 | bbb || ccc | mike | 6 | ccc |+-----+------+-----+------+6 rows in set (0.00 sec)
mysql> SELECT -> * -> FROM -> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid;+-----+------+------+------+| uid | name | oid | uid |+-----+------+------+------+| aaa | mike | 1 | aaa || aaa | mike | 2 | aaa || bbb | jack | 3 | bbb || bbb | jack | 4 | bbb || bbb | jack | 5 | bbb || ccc | mike | 6 | ccc || ddd | mike | NULL | NULL |+-----+------+------+------+7 rows in set (0.00 sec)
mysql> SELECT -> * -> FROM
-> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike';+-----+------+------+------+| uid | name | oid | uid |+-----+------+------+------+| aaa | mike | 1 | aaa || aaa | mike | 2 | aaa || ccc | mike | 6 | ccc || ddd | mike | NULL | NULL |+-----+------+------+------+4 rows in set (0.00 sec)
3. GROUP BY
这个子句会把 VT2 中生成的表按照 GROUP BY 中的列进行分组,生成 VT3 表。
注意:其后处理过程的语句,如 SELECT、HAVING,所用到的列必须包含在 GROUP BY 中,对于没有出现的,得用聚合函数;
原因:GROUP BY 改变了对表的引用,将其转换为新的引用方式,能够对其进行下一级逻辑操作的列会减少。
mysql> SELECT -> * -> FROM -> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike' -> GROUP BY -> a.uid;+-----+------+------+------+| uid | name | oid | uid |+-----+------+------+------+| aaa | mike | 1 | aaa || ccc | mike | 6 | ccc || ddd | mike | NULL | NULL |+-----+------+------+------+3 rows in set (0.00 sec)
4. HAVING
这个子句对 VT3 表中的不同的组进行过滤,只作用于分组后的数据,满足 HAVING 条件的子句被加入到 VT4 表中。
mysql> SELECT -> * -> FROM -> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike' -> GROUP BY -> a.uid -> HAVING -> count(b.oid) < 2;+-----+------+------+------+| uid | name | oid | uid |+-----+------+------+------+| ccc | mike | 6 | ccc || ddd | mike | NULL | NULL |+-----+------+------+------+2 rows in set (0.00 sec)
mysql> SELECT -> a.uid, -> count(b.oid) AS total -> FROM -> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike' -> GROUP BY -> a.uid -> HAVING -> count(b.oid) < 2;+-----+-------+| uid | total |+-----+-------+| ccc | 1 || ddd | 0 |+-----+-------+2 rows in set (0.00 sec)
6. ORDER BY
从 VT5-J2 中的表中,根据 ORDER BY 子句的条件对结果进行排序,生成 VT6 表。
注意:唯一可使用 SELECT 中别名的地方。
mysql> SELECT -> a.uid, -> count(b.oid) AS total -> FROM -> table1 AS a -> LEFT OUTER JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike' -> GROUP BY -> a.uid -> HAVING -> count(b.oid) < 2 -> ORDER BY -> total DESC;+-----+-------+| uid | total |+-----+-------+| ccc | 1 || ddd | 0 |+-----+-------+2 rows in set (0.00 sec)
7. LIMIT
LIMIT 子句从上一步得到的 VT6 虚拟表中选出从指定位置开始的指定行数据。
注意:
offset 和 rows 的正负带来的影响;
当偏移量很大时效率是很低的,可以这么做;
采用子查询的方式优化,在子查询里先从索引获取到最大 id,然后倒序排,再取 N 行结果集;
采用 INNER JOIN 优化,JOIN 子句里也优先从索引获取 ID 列表,然后直接关联查询获得最终结果。
mysql> SELECT -> a.uid, -> count(b.oid) AS total -> FROM -> table1 AS a -> LEFT JOIN table2 AS b ON a.uid = b.uid -> WHERE -> a. NAME = 'mike' -> GROUP BY -> a.uid -> HAVING -> count(b.oid) < 2 -> ORDER BY -> total DESC -> LIMIT 1;+-----+-------+| uid | total |+-----+-------+| ccc | 1 |+-----+-------+1 row in set (0.00 sec)
至此 SQL 的解析之旅就结束了,上图总结一下:
《MySQL性能调优与架构实践》
《MySQL技术内幕:SQL编程》
尾声
嗯,到这里这一次的深入了解之旅就差不多真的结束了,虽然也不是很深入,只是一些东西将其东拼西凑在一起而已,参考了一些以前看过的书籍,大师之笔果然不一样。而且在这过程中也是 get 到了蛮多东西的,最重要的是更进一步意识到,计算机软件世界的宏大呀~