mysql自定义函数

1. 提取字符串中所有数字

使用方法：

select GetNum(字段名) from atable

CREATE FUNCTION GetNum (Varstring varchar(50))
RETURNS varchar(30)
BEGIN
DECLARE v_length INT DEFAULT 0;
DECLARE v_Tmp varchar(50) default '';
set v_length=CHAR_LENGTH(Varstring);
WHILE v_length > 0 DO
IF (ASCII(mid(Varstring,v_length,1))>47 and ASCII(mid(Varstring,v_length,1))<58 ) THEN
set v_Tmp=concat(v_Tmp,mid(Varstring,v_length,1));
END IF;
SET v_length = v_length - 1;
END WHILE;
RETURN REVERSE(v_Tmp);
END;

2. 相似度计算

Levenshtein 距离，又称编辑距离，指的是两个字符串之间，由一个转换成另一个所需的最少编辑操作次数

使用方法:

levenshtein(str1,str2)

-- levenshtein 为主函数
 CREATE FUNCTION levenshtein( s1 VARCHAR(255), s2 VARCHAR(255) )
 RETURNS INT
 DETERMINISTIC
 BEGIN
 DECLARE s1_len, s2_len, i, j, c, c_temp, cost INT;
 DECLARE s1_char CHAR;
 -- max strlen=255
 DECLARE cv0, cv1 VARBINARY(256);
 SET s1_len = CHAR_LENGTH(s1), s2_len = CHAR_LENGTH(s2), cv1 = 0x00, j = 1, i = 1, c = 0;
 IF s1 = s2 THEN
 RETURN 0;
 ELSEIF s1_len = 0 THEN
 RETURN s2_len;
 ELSEIF s2_len = 0 THEN
 RETURN s1_len;
 ELSE
 WHILE j <= s2_len DO
 SET cv1 = CONCAT(cv1, UNHEX(HEX(j))), j = j + 1;
 END WHILE;
 WHILE i <= s1_len DO
 SET s1_char = SUBSTRING(s1, i, 1), c = i, cv0 = UNHEX(HEX(i)), j = 1;
 WHILE j <= s2_len DO
 SET c = c + 1;
 IF s1_char = SUBSTRING(s2, j, 1) THEN 
 SET cost = 0; ELSE SET cost = 1;
 END IF;
 SET c_temp = CONV(HEX(SUBSTRING(cv1, j, 1)), 16, 10) + cost;
 IF c > c_temp THEN SET c = c_temp; END IF;
 SET c_temp = CONV(HEX(SUBSTRING(cv1, j+1, 1)), 16, 10) + 1;
 IF c > c_temp THEN 
 SET c = c_temp; 
 END IF;
 SET cv0 = CONCAT(cv0, UNHEX(HEX(c))), j = j + 1;
 END WHILE;
 SET cv1 = cv0, i = i + 1;
 END WHILE;
 END IF;
 RETURN c;
 END;


 CREATE FUNCTION levenshtein_ratio( s1 VARCHAR(255), s2 VARCHAR(255) )
 RETURNS INT
 DETERMINISTIC
 BEGIN
 DECLARE s1_len, s2_len, max_len INT;
 SET s1_len = LENGTH(s1), s2_len = LENGTH(s2);
 IF s1_len > s2_len THEN 
 SET max_len = s1_len; 
 ELSE 
 SET max_len = s2_len; 
 END IF;
 RETURN ROUND((1 - LEVENSHTEIN(s1, s2) / max_len) * 100);
 END;

3. mysql 记录行号

 SELECT @rownum:=@rownum+1 rownum, tablename.* FROM (SELECT @rownum:=0) r, tablename;

4. 统计重复数据

SELECT COUNT(*) as repetitions, description, s_id FROM tablename GROUP BY s_id HAVING repetitions > 1;

5. 过滤重复数据

SELECT DISTINCT s_id, description FROM tablename ORDER BY s_id;

6. mysql 创建临时表，MySQL 临时表只在当前连接可见，只有在关闭客户端程序时才会销毁临时表，也可以手动销毁

 create temporary table aaa(product_name VARCHAR(50) NOT NULL, total_sales DECIMAL(12,2) NOT NULL DEFAULT 0.00, avg_unit_price DECIMAL(7,2) NOT NULL DEFAULT 0.00 , total_units_sold INT UNSIGNED NOT NULL DEFAULT 0);

当你使用 show tables 显示数据表时，无法看到临时表，如果你退出当前MySQL会话，再使用 SELECT命令来读取原先创建的临时表数据，那你会发现数据库中没有该表的存在，因为在你退出时该临时表已经被销毁了。

7. mysql 数据库复制

SELECT a.id,a.couponid,a.brand,a.website,a.is_root,a.root_domain,a.is_etsy,b.cat from coupon_etsy_url_source_likai a join cat_rmn b on(a.website=b.website)

8. mysql 数据表 导出以excel 形式；

mysql womanistmusings  -uroot -padmin -e "select 'womanist',comment_author,comment_author_email,comment_author_IP,comment_date,if(comment_approved=0,'pending','approved') status from wp_comments where comment_approved not in('trash','spam')" > aaatest.xls