字符串相似度处理函数

Posted 2021-02-20 5sdba-notes

oracle里面查比如存储过程里面与表SALES有关jobs:

SELECT * FROM (SELECT a.name,upper(b.what)AS what,SYS.UTL_MATCH.edit_distance_similarity
(a.name,upper(b.what)) AS similarity FROM dba_source a,dba_jobs b
WHERE  SYS.UTL_MATCH.edit_distance_similarity(a.name,upper(b.what))>80
AND upper(a.text)  LIKE ‘%SALES%‘
AND b.what NOT LIKE ‘%dbms_refresh%‘)
ORDER BY 3 DESC;

有自带相似度函数 SYS.UTL_MATCH.edit_distance_similarity 可以直接用。

mysql8里面我只查到了一个搜索相关的文档文档地址并不适合我自己用，找了一下大佬的文章，发现了一个能用的自定义函数，用于计算字符串相似度。

DELIMITER $$
CREATE DEFINER=`root`@`localhost` FUNCTION `COMPARE_STRING`( s1 text, s2 text) RETURNS int(11)
    DETERMINISTIC
BEGIN 
    DECLARE s1_len, s2_len, i, j, c, c_temp, cost INT; 
    DECLARE s1_char CHAR; 
    DECLARE cv0, cv1 text; 
    SET s1_len = CHAR_LENGTH(s1), s2_len = CHAR_LENGTH(s2), cv1 = 0x00, j = 1, i = 1, c = 0; 
    IF s1 = s2 THEN 
      RETURN 0;     
    ELSEIF s1_len = 0 THEN 
      RETURN s2_len; 
    ELSEIF s2_len = 0 THEN 
      RETURN s1_len; 
    ELSE 
      WHILE j <= s2_len DO 
        SET cv1 = CONCAT(cv1, UNHEX(HEX(j))), j = j + 1; 
      END WHILE; 
      WHILE i <= s1_len DO 
        SET s1_char = SUBSTRING(s1, i, 1), c = i, cv0 = UNHEX(HEX(i)), j = 1; 
        WHILE j <= s2_len DO 
          SET c = c + 1; 
          IF s1_char = SUBSTRING(s2, j, 1) THEN  
            SET cost = 0; ELSE SET cost = 1; 
          END IF; 
          SET c_temp = CONV(HEX(SUBSTRING(cv1, j, 1)), 16, 10) + cost; 
          IF c > c_temp THEN SET c = c_temp; END IF; 
            SET c_temp = CONV(HEX(SUBSTRING(cv1, j+1, 1)), 16, 10) + 1; 
            IF c > c_temp THEN  
              SET c = c_temp;  
            END IF; 
            SET cv0 = CONCAT(cv0, UNHEX(HEX(c))), j = j + 1; 
        END WHILE; 
        SET cv1 = cv0, i = i + 1; 
      END WHILE; 
    END IF; 
    RETURN c; 
  END$$
DELIMITER ;

DELIMITER $$
CREATE DEFINER=`root`@`localhost` FUNCTION `SIMILARITY_STRING`(a text, b text) RETURNS double
BEGIN
RETURN ABS(((COMPARE_STRING(a, b) / length(b)) * 100) - 100);
END$$
DELIMITER ;

试了一下还挺好用的，一些逻辑可以自己再适当的修改。

而在gp里面，我找了许久，发现一个 fuzzystrmatch  看起来比较高档的函数，这个函数需要安装：

[gpadmin@SZWPLDB1085 ~]$ psql -d postgres -f $GPHOME/share/postgresql/contrib/fuzzystrmatch.sql
SET
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION
CREATE FUNCTION

然后会在 postgres 库多出一些函数：

用法在文档地址