参考https://stackoverflow.com/questions/12617348/mysql-levenshtein
以及java版本的实现
部分修改
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。许可的编辑操作包括将一个字符替换成另一个字符,插入一个字符,删除一个字符。
1.莱温斯顿函数
CREATE DEFINER=`root`@`%` FUNCTION `levenshtein`(s1 VARCHAR(255), s2 VARCHAR(255)) RETURNS int(11)
DETERMINISTICBEGIN
DECLARE s1_len, s2_len, i, j, c, c_temp, cost INT;
DECLARE s1_char CHAR;
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
2.比率
CREATE DEFINER=`root`@`%` FUNCTION `levenshtein_ratio`(s1 VARCHAR(255), s2 VARCHAR(255)) RETURNS int(11)
DETERMINISTIC
BEGIN
DECLARE s1_len, s2_len, max_len INT;
SET s1_len = CHAR_LENGTH(s1), s2_len = CHAR_LENGTH(s2);
IF s1_len > s2_len THEN
SET max_len = s1_len;
ELSE
SET max_len = s2_len;
END IF;
IF max_len = 0 THEN
RETURN 100;
ELSE
RETURN ROUND((1 - LEVENSHTEIN(s1, s2) / max_len) * 100);
END IF;
END
3.用法levenshtein_ratio("str1","str2")