高级SQL基础查询

基础查询

-- distinct 过滤重复 (常用语检查一列数据是否有异常值)

select distinct sex from student;

-- count 统计

select count(distinct sex) from student;

-- top 取前N条记录

select top 3 * from student;

-- limit是mysql的语法
select * from table limit m,n

其中m是指记录开始的index，从0开始，表示第一条记录

n是指从第m+1条开始，取n条。

-- column 列运算

select (age + id) col from student;

select s.name + '-' + c.name from classes c, student s where s.cid = c.id;

-- having 分组过滤条件

-- 按照年龄分组，过滤年龄为空的数据，并且统计分组的条数和现实年龄信息

select count(*), age from student group by age having age is not null;

-- 按照年龄和cid组合分组，过滤条件是cid大于1的记录

select count(*), cid, sex from student group by cid, sex having cid > 1;

-- 按照年龄分组，过滤条件是分组后的记录条数大于等于2

select count(*), age from student group by age having count(age) >= 2; 

-- 按照cid和性别组合分组，过滤条件是cid大于1，cid的最大值大于2

select count(*), cid, sex from student group by cid, sex having cid > 1 and max(cid) > 2;

嵌套子查询

子查询是一个嵌套在select、insert、update 或 delete 语句或其他子查询中的查询。任何允许使用表达式的地方都可以使用子查询。子查询也称为内部查询或内部选择，而包含子查询的语句也成为外部查询或外部选择。

将一个 table 的查询结果当做一个新表进行查询

select * from（

    select id, name from student where sex = 1

) t where t.id > 2;

上面括号中的语句，就是子查询语句（内部查询）。在外面的是外部查询，其中外部查询可以包含以下语句：

 1、 包含常规选择列表组件的常规select查询

 2、 包含一个或多个表或视图名称的常规from语句

 3、 可选的where子句

 4、 可选的group by子句

 5、 可选的having子句

查询班级信息，统计班级学生人生

select *, (select count(*) from student where cid = classes.id) as num 

from classes order by num;

查询班级id大于小于X的这些班级的学生信息

select * from student where cid in (

    select id from classes where id > 2 and id < 4

);

– 查询不是X班的学生信息

select * from student where cid not in (

    select id from classes where name = '2班'

)

all,any,some

select * from student where cid = 5 and age > all (

    select age from student where cid = 3

);



select * from student where cid = 5 and age > any (

    select age from student where cid = 3

);



select * from student where cid = 5 and age > some (

    select age from student where cid = 3

);

聚合查询

1、 distinct去掉重复数据

select distinct sex from student;

select count(sex), count(distinct sex) from student;

2、 compute和compute by汇总查询

– 对年龄大于20的进行汇总

select age from student where age > 20 order by age compute sum(age) by age;

– 对年龄大于20的按照性别进行分组汇总年龄信息

select id, sex, age from student where age > 20 order by sex, age compute sum(age) by sex;

按照年龄分组汇总

select age from student where age > 20 order by age, id compute sum(age);

– 按照年龄分组，年龄汇总，id找最大值

select id, age from student where age > 20 order by age compute sum(age), max(id);

compute 进行汇总，前面是查询的结果，后面一条结果集就是汇总的信息。compute 子句中可以添加多个汇总表达式，可以添加的信息如下：

 a、 可选by关键字。它是每一列计算指定的行聚合

 b、 行聚合函数名称。包括sum、avg、min、max、count等

 c、 要对其执行聚合函数的列

 compute by适合做先分组后汇总的业务。compute by 后面的列一定要是 order by 中出现的列。

3、 cube 汇总

cube汇总和compute效果类似，但语法较简洁，而且返回的是一个结果集。

select count(*), sex from student group by sex with cube;

select count(*), age, sum(age) from student where age is not null group by age with cube;

cube要结合group by语句完成分组汇总

排序函数

排序在很多地方需要用到，需要对查询结果进行排序并且给出序号。比如：

1、 对某张表进行排序，序号需要递增不重复的

2、 对学生的成绩进行排序，得出名次，名次可以并列，但名次的序号是连续递增的

3、 在某些排序的情况下，需要跳空序号，虽然是并列

– 基本语法

– 排序函数 over([分组语句] 排序子句[desc][asc])

– 排序子句 order by 列名, 列名

– 分组子句 partition by 分组列, 分组列

– row_number 函数

– 根据排序子句给出递增连续序号,按照名称排序的顺序递增

select s.id, s.name, cid, c.name, row_number() over(order by c.name) as number

from student s, classes c where cid = c.id;

– rank 函数函数

– 根据排序子句给出递增的序号，但是存在并列并且跳空

– 顺序递增

select id, name, rank() over(order by cid) as rank from student;

– dense_rank 函数

– 根据排序子句给出递增的序号，但是存在并列不跳空

select s.id, s.name, cid, c.name, dense_rank() over(order by c.name) as dense

from student s, classes c where cid = c.id;

– partition by 分组子句

– 可以完成对分组的数据进行增加排序，partition by可以与以上三个函数联合使用。

select s.id, s.name, cid, c.name, row_number() over(partition by c.name order by s.id) as rank

from student s, classes c where cid = c.id;

select s.id, s.name, cid, c.name, rank() over(partition by c.name order by s.id) as rank

from student s, classes c where cid = c.id;

select s.id, s.name, cid, c.name, dense_rank() over(partition by c.name order by s.id) as rank

from student s, classes c where cid = c.id;

– ntile 平均排序函数

– 将要排序的数据进行平分，然后按照等分排序。ntile中的参数代表分成多少等分。

select s.id, s.name, cid, c.name, ntile(5) over(order by c.name) as ntile

from student s, classes c where cid = c.id;

? 集合运算

操作两组查询结果，进行交集、并集、减集运算

– union 并集、不重复

select id, name from student where name like 'ja%'

union select id, name from student where id = 4;

– union all 并集、重复

select * from student where name like 'ja%'

union all select * from student;

– 交集相同

select * from student where name like 'ja%'

intersect select * from student;

– 减集（除相同部分）

select * from student where name like 'ja%'

except select * from student where name like 'jas%';

公式表表达式

查询表的时候，有时候中间表需要重复使用，这些子查询被重复查询调用，不但效率低，而且可读性低，不利于理解。那么公式表表达式可以解决这个问题。

我们可以将公式表表达式（CET）视为临时结果集，在select、insert、update、delete或是create view语句的执行范围内进行定义。

with statNum(id, num) as

(

select cid, count(*) from student where id > 0 group by cid

)

select id, num from statNum order by id;

with statNum(id, num) as

(

select cid, count(*) from student where id > 0 group by cid

)

select max(id), avg(num) from statNum;

表的联合查询

-- 简化联接查询


select s.id, s.name, c.id, c.name from student s, classes c where s.cid = c.id;



-- 左连接 (左为基表)

select s.id, s.name, c.id, c.name from student s left join classes c on s.cid = c.id;



-- 右连接 (右为基表)

select s.id, s.name, c.id, c.name from student s right join classes c on s.cid = c.id;



-- 内连接 (等值联合)

select s.id, s.name, c.id, c.name from student s inner join classes c on s.cid = c.id;



-- 交叉联接查询，结果是一个笛卡儿乘积

select s.id, s.name, c.id, c.name from student s ,classes c



-- 自连接

select distinct s.* from student s, student s1 where s.id <> s1.id and s.sex = s1.sex;

函数

– 聚合函数 (max最大值、min最小值、count统计、avg平均值、sum求和、var求方差)

select

max(age) max_age, 

min(age) min_age, 

count(age) count_age, 

avg(age) avg_age, 

sum(age) sum_age, 

var(age) var_age 

from student;

– 日期时间函数

select dateAdd(day, 3, getDate());

select dateAdd(year, 3, getDate());

select dateAdd(hour, 3, getDate());

select dateDiff(day, ‘2011-06-20’, getDate());

select dateDiff(second, ‘2011-06-22 11:00:00’, getDate());

select dateDiff(hour, ‘2011-06-22 10:00:00’, getDate());

select dateName(month, getDate());

select dateName(minute, getDate());

select dateName(weekday, getDate());

select datePart(month, getDate());

select datePart(weekday, getDate());

select datePart(second, getDate());

select day(getDate());

select day(‘2011-06-30’);

select month(getDate());

select month(‘2011-11-10’);

select year(getDate());

select year(‘2010-11-10’);

select getDate();

select getUTCDate();

– 数学函数

select pi();

select rand(100), rand(50), rand();

select round(rand(), 3), round(rand(100), 5);

select round(123.456, 2), round(254.124, -2);

select round(123.4567, 1, 2);

– 元数据

select col_name(object_id(‘student’), 1); // 返回列名

select col_name(object_id(‘student’), 2);

– 该列数据类型长度

select col_length(‘student’, col_name(object_id(‘student’), 2));

– 该列数据类型长度

select col_length(‘student’, col_name(object_id(‘student’), 1));

– 返回类型名称、类型id

select type_name(type_id(‘varchar’)), type_id(‘varchar’);

– 返回列类型长度

select columnProperty(object_id(‘student’), ‘name’, ‘PRECISION’);

– 返回列所在索引位置

select columnProperty(object_id(‘student’), ‘sex’, ‘ColumnId’);

– 字符串函数

select ascii('a');

select ascii('A');

select char(97);

select char(65);

select nchar(65);

select nchar(45231);

select nchar(32993);

select unicode('A'), unicode('中');

select soundex('hello'), soundex('world'), soundex('word');

select patindex('%a', 'ta'), patindex('%ac%', 'jack'), patindex('dex%', 'dexjack');

select 'a' + space(2) + 'b', 'c' + space(5) + 'd';

select charIndex('o', 'hello world');

select charIndex('o', 'hello world', 6);

select quoteName('abc[]def'), quoteName('123]45');

select str(123.456, 2), str(123.456, 3), str(123.456, 4);

select str(123.456, 9, 2), str(123.456, 9, 3), str(123.456, 6, 1), str(123.456, 9, 6);

select difference('hello', 'helloWorld');

select difference('hello', 'world');

select difference('hello', 'llo');

select difference('hello', 'hel');

select difference('hello', 'hello');

select replace('abcedef', 'e', 'E');

select stuff('hello world', 3, 4, 'ABC');

select replicate('abc#', 3);

select subString('abc', 1, 1), subString('abc', 1, 2), subString('hello Wrold', 7, 5);

select len('abc');

select reverse('sqlServer'); 

select left('leftString', 4);

select left('leftString', 7);

select right('leftString', 6);

select right('leftString', 3);

select lower('aBc'), lower('ABC');

select upper('aBc'), upper('abc');

select ltrim(' abc'), ltrim('# abc#'), ltrim('  abc');

select rtrim(' abc    '), rtrim('# abc#   '), rtrim('abc');