MySQL之单表查询

一 单表查询的语法：

SELECT 字段1,字段2... FROM 表名
                  WHERE 条件
                  GROUP BY field
                  HAVING 筛选
                  ORDER BY field
                  LIMIT 限制条数

二 单表查询关键字执行的优先级：

重点中的重点：关键字的执行优先级
from：from后面跟的是表，也就是说我们从哪个表中查询。
where：where后面加的是一些限制条件，比如大于多少，范围多少等。
group by:group by 后面跟的分组条件，也就是按照什么来分组。
having：having是在语法级别上跟where是一样的，唯一的区别是having实在分组之后进行限制，可以使用聚合函数，而where不行
select：select后面跟所要查询的字段信息。
distinct：distinct是用来去重的。
order by：限制显示的顺序，可以按照id，age等显示，最后还可以跟降序（desc）和升序（asc）。
limit：限制一次显示记录的数量，limit 5，name一次显示五条，同样可以limit 1,5表示从1开始显示5条。其中不包括1.

1.找到表:from

2.拿着where指定的约束条件，去文件/表中取出一条条记录

3.将取出的一条条记录进行分组group by，如果没有group by，则整体作为一组

4.将分组的结果进行having过滤

5.执行select

6.去重

7.将结果按条件排序：order by

8.限制结果的显示条数。

 

下面我们通过一个实例来演示这些关键字的功能：

company.employee
    员工id      id                  int             
    姓名        emp_name            varchar
    性别        sex                 enum
    年龄        age                 int
    入职日期     hire_date           date
    岗位        post                varchar
    职位描述     post_comment        varchar
    薪水        salary              double
    办公室       office              int
    部门编号     depart_id           int



#创建表
create table employee(
id int not null unique auto_increment,
name varchar(20) not null,
sex enum('male','female') not null default 'male', #大部分是男的
age int(3) unsigned not null default 28,
hire_date date not null,
post varchar(50),
post_comment varchar(100),
salary double(15,2),
office int, #一个部门一个屋子
depart_id int
);


#查看表结构
mysql> desc employee;
+--------------+-----------------------+------+-----+---------+----------------+
| Field        | Type                  | Null | Key | Default | Extra          |
+--------------+-----------------------+------+-----+---------+----------------+
| id           | int(11)               | NO   | PRI | NULL    | auto_increment |
| name         | varchar(20)           | NO   |     | NULL    |                |
| sex          | enum('male','female') | NO   |     | male    |                |
| age          | int(3) unsigned       | NO   |     | 28      |                |
| hire_date    | date                  | NO   |     | NULL    |                |
| post         | varchar(50)           | YES  |     | NULL    |                |
| post_comment | varchar(100)          | YES  |     | NULL    |                |
| salary       | double(15,2)          | YES  |     | NULL    |                |
| office       | int(11)               | YES  |     | NULL    |                |
| depart_id    | int(11)               | YES  |     | NULL    |                |
+--------------+-----------------------+------+-----+---------+----------------+

#插入记录
#三个部门：教学，销售，运营
insert into employee(name,sex,age,hire_date,post,salary,office,depart_id) values
('egon','male',18,'20170301','老男孩驻沙河办事处外交大使',7300.33,401,1), #以下是教学部
('alex','male',78,'20150302','teacher',1000000.31,401,1),
('wupeiqi','male',81,'20130305','teacher',8300,401,1),
('yuanhao','male',73,'20140701','teacher',3500,401,1),
('liwenzhou','male',28,'20121101','teacher',2100,401,1),
('jingliyang','female',18,'20110211','teacher',9000,401,1),
('jinxin','male',18,'19000301','teacher',30000,401,1),
('成龙','male',48,'20101111','teacher',10000,401,1),

('歪歪','female',48,'20150311','sale',3000.13,402,2),#以下是销售部门
('丫丫','female',38,'20101101','sale',2000.35,402,2),
('丁丁','female',18,'20110312','sale',1000.37,402,2),
('星星','female',18,'20160513','sale',3000.29,402,2),
('格格','female',28,'20170127','sale',4000.33,402,2),

('张野','male',28,'20160311','operation',10000.13,403,3), #以下是运营部门
('程咬金','male',18,'19970312','operation',20000,403,3),
('程咬银','female',18,'20130311','operation',19000,403,3),
('程咬铜','male',18,'20150411','operation',18000,403,3),
('程咬铁','female',18,'20140512','operation',17000,403,3)
;

#ps：如果在windows系统中，插入中文字符，select的结果为空白，可以将所有字符编码统一设置成gbk

准备表和记录

1  简单查询：

#简单查询
    SELECT id,name,sex,age,hire_date,post,post_comment,salary,office,depart_id 
    FROM employee;

    SELECT * FROM employee;

    SELECT name,salary FROM employee;

#避免重复DISTINCT
    SELECT DISTINCT post FROM employee;    

#通过四则运算查询
    SELECT name, salary*12 FROM employee;
    SELECT name, salary*12 AS Annual_salary FROM employee;
    SELECT name, salary*12 Annual_salary FROM employee;

#定义显示格式
   CONCAT() 函数用于连接字符串
   SELECT CONCAT('姓名: ',name,'  年薪: ', salary*12)  AS Annual_salary 
   FROM employee;
   
   CONCAT_WS() 第一个参数为分隔符
   SELECT CONCAT_WS(':',name,salary*12)  AS Annual_salary 
   FROM employee;

   结合CASE语句：
   SELECT
       (
           CASE
           WHEN NAME = 'egon' THEN
               NAME
           WHEN NAME = 'alex' THEN
               CONCAT(name,'_BIGSB')
           ELSE
               concat(NAME, 'SB')
           END
       ) as new_name
   FROM
       emp;

2  where：

where字句中可以使用：

1. 比较运算符：> < >= <= <> !=
2. between 80 and 100 值在80到100之间
3. in(80,90,100) 值是80或90或100
4. like 'egon%'
    pattern可以是%或_，
    %表示任意多字符
    _表示一个字符 
5. 逻辑运算符：在多个条件直接可以使用逻辑运算符 and or not

#1:单条件查询
    SELECT name FROM employee
        WHERE post='sale';
        
#2:多条件查询
    SELECT name,salary FROM employee
        WHERE post='teacher' AND salary>10000;

#3:关键字BETWEEN AND#between的用法就是后面加上两个数，两个数之间加一个and。
    SELECT name,salary FROM employee 
        WHERE salary BETWEEN 10000 AND 20000;

    SELECT name,salary FROM employee 
        WHERE salary NOT BETWEEN 10000 AND 20000;
    
#4:关键字IS NULL(判断某个字段是否为NULL不能用等号，需要用IS)
    SELECT name,post_comment FROM employee 
        WHERE post_comment IS NULL;

    SELECT name,post_comment FROM employee 
        WHERE post_comment IS NOT NULL;
        
    SELECT name,post_comment FROM employee 
        WHERE post_comment=''; 注意''是空字符串，不是null
    ps：
        执行
        update employee set post_comment='' where id=2;
        再用上条查看，就会有结果了

#5:关键字IN集合查询
    SELECT name,salary FROM employee 
        WHERE salary=3000 OR salary=3500 OR salary=4000 OR salary=9000 ;
    
    SELECT name,salary FROM employee 
        WHERE salary IN (3000,3500,4000,9000) ;

    SELECT name,salary FROM employee 
        WHERE salary NOT IN (3000,3500,4000,9000) ;

#6:关键字LIKE模糊查询
    通配符’%’
    SELECT * FROM employee 
            WHERE name LIKE 'eg%';

    通配符’_’
    SELECT * FROM employee 
            WHERE name LIKE 'al__';

三 分组查询：

#1、首先明确一点：分组发生在where之后，即分组是基于where之后得到的记录而进行的

#2、分组指的是：将所有记录按照某个相同字段进行归类，比如针对员工信息表的职位分组，或者按照性别进行分组等

#3、为何要分组呢？
    取每个部门的最高工资
    取每个部门的员工数
    取男人数和女人数

小窍门：‘每’这个字后面的字段，就是我们分组的依据，这是对于一般情况下而言的。

#4、大前提：
    可以按照任意字段分组，但是分组完毕后，比如group by post，只能查看post字段，如果想查看组内信息，需要借助于聚合函数

那么分组的时候有没有指定：set global sql_mode='ONLY_FULL_GROUP_BY';  是有区别的，没有设置的时候默认查到的是每一个组第一条信息。同样的分完组之后我们不能再直接通过select * from emp来查询组内的信息，

假如我们按照post来分组，那么我们查询的时候只能select post 聚合函数（max（），min（），avg（））from  emp group by post等。

mysql> select * from emp group by post; 
+----+------+--------+-----+------------+----------------------------+--------------+------------+--------+-----------+
| id | name | sex    | age | hire_date  | post                       | post_comment | salary     | office | depart_id |
+----+------+--------+-----+------------+----------------------------+--------------+------------+--------+-----------+
| 14 | 张野 | male   |  28 | 2016-03-11 | operation                  | NULL         |   10000.13 |    403 |         3 |
|  9 | 歪歪 | female |  48 | 2015-03-11 | sale                       | NULL         |    3000.13 |    402 |         2 |
|  2 | alex | male   |  78 | 2015-03-02 | teacher                    | NULL         | 1000000.31 |    401 |         1 |
|  1 | egon | male   |  18 | 2017-03-01 | 老男孩驻沙河办事处外交大使 | NULL         |    7300.33 |    401 |         1 |
+----+------+--------+-----+------------+----------------------------+--------------+------------+--------+-----------+
4 rows in set (0.00 sec)


#由于没有设置ONLY_FULL_GROUP_BY,于是也可以有结果，默认都是组内的第一条记录，但其实这是没有意义的

mysql> set global sql_mode='ONLY_FULL_GROUP_BY';
Query OK, 0 rows affected (0.00 sec)

mysql> quit #设置成功后，一定要退出，然后重新登录方可生效
Bye

mysql> use db1;
Database changed
mysql> select * from emp group by post; #报错
ERROR 1055 (42000): 'db1.emp.id' isn't in GROUP BY
mysql> select post,count(id) from emp group by post; #只能查看分组依据和使用聚合函数
+----------------------------+-----------+
| post                       | count(id) |
+----------------------------+-----------+
| operation                  |         5 |
| sale                       |         5 |
| teacher                    |         7 |
| 老男孩驻沙河办事处外交大使 |         1 |
+----------------------------+-----------+
4 rows in set (0.00 sec)

单独使用GROUP BY关键字分组
    SELECT post FROM employee GROUP BY post;
    注意：我们按照post字段分组，那么select查询的字段只能是post，想要获取组内的其他相关信息，需要借助函数

GROUP BY关键字和GROUP_CONCAT()函数一起使用
    SELECT post,GROUP_CONCAT(name) FROM employee GROUP BY post;#按照岗位分组，并查看组内成员名
    SELECT post,GROUP_CONCAT(name) as emp_members FROM employee GROUP BY post;

GROUP BY与聚合函数一起使用
    select post,count(id) as count from employee group by post;#按照岗位分组，并查看每个组有多少人

四  聚合函数：

#强调：聚合函数聚合的是组的内容，若是没有分组，则默认一组

示例：
    SELECT COUNT(*) FROM employee;
    SELECT COUNT(*) FROM employee WHERE depart_id=1;
    SELECT MAX(salary) FROM employee;
    SELECT MIN(salary) FROM employee;
    SELECT AVG(salary) FROM employee;
    SELECT SUM(salary) FROM employee;
    SELECT SUM(salary) FROM employee WHERE depart_id=3;

五 HAVING过滤：

#！！！执行优先级从高到低：where > group by > having 
#1. Where 发生在分组group by之前，因而Where中可以有任意字段，但是绝对不能使用聚合函数。

#2. Having发生在分组group by之后，因而Having中可以使用分组的字段，无法直接取到其他字段,可以使用聚合函数

六  order by排序：

按单列排序
    SELECT * FROM employee ORDER BY salary;
    SELECT * FROM employee ORDER BY salary ASC;
                                                      ASC是升序排序，而desc为降序排序。默认是按照升序排序的。
    SELECT * FROM employee ORDER BY salary DESC;      分别为ascend和descend

按多列排序:先按照age排序，如果年纪相同，则按照薪资排序，
    SELECT * from employee
        ORDER BY age,
        salary DESC;

七 limit限制查询的显示记录数：

示例：
    SELECT * FROM employee ORDER BY salary DESC 
        LIMIT 3;                    #默认初始位置为0 
    
    SELECT * FROM employee ORDER BY salary DESC
        LIMIT 0,5; #从第0开始，即先查询出第一条，然后包含这一条在内往后查5条

    SELECT * FROM employee ORDER BY salary DESC
        LIMIT 5,5; #从第5开始，即先查询出第6条，然后包含这一条在内往后查5条

八  使用正则表达式查询：

SELECT * FROM employee WHERE name REGEXP '^ale';

SELECT * FROM employee WHERE name REGEXP 'on$';

SELECT * FROM employee WHERE name REGEXP 'm{2}';


小结：对字符串匹配的方式
WHERE name = 'egon';
WHERE name LIKE 'yua%';
WHERE name REGEXP 'on$';

查看所有员工中名字是jin开头，n或者g结果的员工信息

select * from employee where name regexp '^jin.*[gn]$';

总结：

一 语法

   select distinct 查询字段1，查询字段2，。。。 from 表名
        where 分组之前的过滤条件
        group by 分组依据
        having 分组之后的过滤条件
        order by 排序字段
        limit 显示的条数;


def from(dir,file):
    open('%s\%s' %(dir,file),'r')
    return f

def where(f,pattern):
    for line in f:
        if pattern：
            yield line


def group():
    pass

def having():
    pass


def distinct():
    pass


def order():
    pass


def limit():
    pass



def select():
    res1=from()
    res2=where(res1,pattern)
    res3=group(res2,)
    res4=having(res3)
    res5=distinct(res4)
    res6=order(res5)
    limit(res6)


二 where过滤

    select id,name from db39.emp where id >= 3 and id <= 6
    select *  from db39.emp where id between 3 and 6;


    select * from emp where salary = 20000 or salary = 18000 or salary = 17000;
    select * from emp where salary in (20000,18000,17000);


    要求：查询员工姓名中包含i字母的员工姓名与其薪资
    select name,salary from db39.emp where name like '%i%'

    要求：查询员工姓名是由四个字符组成的的员工姓名与其薪资
    select name,salary from db39.emp where name like '____';
    select name,salary from db39.emp where char_length(name) = 4;



    select *  from db39.emp where id not between 3 and 6;
    select * from emp where salary not in (20000,18000,17000);

    要求：查询岗位描述为空的员工名与岗位名
    select name,post from db39.emp where post_comment is NULL;
    select name,post from db39.emp where post_comment is not NULL;


三 group by分组
    #设置sql_mode为only_full_group_by，意味着以后但凡分组，只能取到分组的依据
    mysql> set global sql_mode="strict_trans_tables,only_full_group_by";

    #每个部门的最高工资
    select post,max(salary) from emp group by post;
    select post,min(salary) from emp group by post;
    select post,avg(salary) from emp group by post;
    select post,sum(salary) from emp group by post;
    select post,count(id) from emp group by post;



    #group_concat（分组之后用）
    select post,group_concat(name) from emp group by post;
    select post,group_concat(name,"_SB") from emp group by post;
    select post,group_concat(name,": ",salary) from emp group by post;
    select post,group_concat(salary) from emp group by post;

    # 补充concat（不分组时用）
    select name as 姓名,salary as 薪资 from emp;

    select concat("NAME: ",name) as 姓名,concat("SAL: ",salary) as 薪资 from emp;

    # 补充as语法
    mysql> select emp.id,emp.name from emp as t1; # 报错，这里报错是因为你已经把表名emp改成t1了，所以再使用emp。id
                                                     这个时候没办法找到emp

    mysql> select t1.id,t1.name from emp as t1;


    # 查询四则运算
    select name,salary*12 as annual_salary from emp;


    分组练习

    1. 查询岗位名以及岗位包含的所有员工名字
        select post,group_concat(name) from emp group by post;


    2. 查询岗位名以及各岗位内包含的员工个数
        select post,count(id) from emp group by post;

    3. 查询公司内男员工和女员工的个数
        select sex,count(id) from emp group by sex;

    4. 查询岗位名以及各岗位的平均薪资
        select post,avg(salary) from emp group by post;
    5. 查询岗位名以及各岗位的最高薪资
    6. 查询岗位名以及各岗位的最低薪资
    7. 查询男员工与男员工的平均薪资，女员工与女员工的平均薪资
        select sex,avg(salary) from emp group by sex;

    8、统计各部门年龄在30岁以上的员工平均工资
       select post,avg(salary) from emp where age >= 30 group by post;


四 having过滤
    having的语法格式与where一模一样，只不过having是在分组之后进行的进一步过滤
    即where不能用聚合函数，而having是可以用聚合函数，这也是他们俩最大的区别

    1、统计各部门年龄在30岁以上的员工平均工资，并且保留平均工资大于10000的部门
    select post,avg(salary) from emp
            where age >= 30
            group by post
            having avg(salary) > 10000;

    #强调：having必须在group by后面使用
    select * from emp
            having avg(salary) > 10000;



五 distinct去重

select distinct post,avg(salary) from emp
            where age >= 30
            group by post
            having avg(salary) > 10000;


六 order by 排序
select * from emp order by salary asc; #默认升序排ascend
select * from emp order by salary desc; #降序排descend

select * from emp order by age desc; #降序排

select * from emp order by age desc,salary asc; #先按照age降序排，再按照薪资升序排



# 统计各部门年龄在10岁以上的员工平均工资，并且保留平均工资大于1000的部门，
然后对平均工资进行排序

select post,avg(salary) from emp
    where age > 10
    group by post
    having avg(salary) > 1000
    order by avg(salary)
    ;


七 limit 限制显示条数
select * from emp limit 3;

select * from emp order by salary desc limit 1;



# 分页显示
select * from emp limit 0,5;
select * from emp limit 5,5;



八 正则表达式

select * from emp where name regexp '^jin.*(n|g)$';