单表查询与多表查询

单表查询
    准备表
        #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
        );

        #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)
        ;


    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;

        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


        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
        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;

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

        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)$';

多表查询

    准备表
        #建表
        create table department(
        id int,
        name varchar(20)
        );

        create table employee(
        id int primary key auto_increment,
        name varchar(20),
        sex enum('male','female') not null default 'male',
        age int,
        dep_id int
        );

        #插入数据
        insert into department values
        (200,'技术'),
        (201,'人力资源'),
        (202,'销售'),
        (203,'运营');

        insert into employee(name,sex,age,dep_id) values
        ('egon','male',18,200),
        ('alex','female',48,201),
        ('wupeiqi','male',38,201),
        ('yuanhao','female',28,202),
        ('liwenzhou','male',18,200),
        ('jingliyang','female',18,204)
        ;

    一、内连接：把两张表有对应关系的记录连接成一张虚拟表
        select * from emp inner join dep on emp.dep_id = dep.id;

    #应用：
            select * from emp,dep where emp.dep_id = dep.id and dep.name = "技术"; # 不要用where做连表的活

            select * from emp inner join dep on emp.dep_id = dep.id
                where dep.name = "技术"
            ;

    二、左连接：在内连接的基础上，保留左边没有对应关系的记录
        select * from emp left join dep on emp.dep_id = dep.id;


    三、右连接：在内连接的基础上，保留右边没有对应关系的记录
        select * from emp right join dep on emp.dep_id = dep.id;


    四、全连接：在内连接的基础上，保留左、右边没有对应关系的记录
        select * from emp left join dep on emp.dep_id = dep.id
        union
        select * from emp right join dep on emp.dep_id = dep.id;



    #补充：多表连接可以不断地与虚拟表连接

    查找各部门最高工资人的信息
        select t1.* from emp as t1
        inner join
        (select post,max(salary) as ms from emp group by post) as t2
        on t1.post = t2.post
        where t1.salary = t2.ms
        ;