似乎当前的答案中没有一个实际上会从字符串的开头和结尾删除100%的空格。
如其他文章所述,默认值TRIM
仅删除空格-而不是制表符,换页符等TRIM
。指定其他空格字符的s 组合可能会提供有限的改进,例如TRIM(BOTH '\r' FROM TRIM(BOTH '\n' FROM TRIM(BOTH '\f' FROM TRIM(BOTH '\t' FROM TRIM(txt)))))
。但是这种方法的问题是只能为一个特定TRIM
的字符指定一个字符,而这些字符只能从开头和结尾删除。因此,如果要修剪的字符串类似\t \t \t \t
(例如,空格和制表符),则TRIM
需要更多s-在一般情况下,它可能会无限期地继续下去。
对于轻量级解决方案,应该有可能编写一个简单的用户定义函数(UDF),以通过遍历字符串开头和结尾的字符来完成这项工作。但是我不打算这样做...因为我已经写了一个重量更重的正则表达式替换器,它也可以完成这项工作-并且可能由于其他原因而有用,如本博客文章中所述。
演示版
Rextester在线演示。特别是,最后一行显示其他方法失败,而正则表达式方法成功。
功能:
-- ------------------------------------------------------------------------------------
-- USAGE
-- ------------------------------------------------------------------------------------
-- SELECT reg_replace(<subject>,
-- <pattern>,
-- <replacement>,
-- <greedy>,
-- <minMatchLen>,
-- <maxMatchLen>);
-- where:
-- <subject> is the string to look in for doing the replacements
-- <pattern> is the regular expression to match against
-- <replacement> is the replacement string
-- <greedy> is TRUE for greedy matching or FALSE for non-greedy matching
-- <minMatchLen> specifies the minimum match length
-- <maxMatchLen> specifies the maximum match length
-- (minMatchLen and maxMatchLen are used to improve efficiency but are
-- optional and can be set to 0 or NULL if not known/required)
-- Example:
-- SELECT reg_replace(txt, '^[Tt][^ ]* ', 'a', TRUE, 2, 0) FROM tbl;
DROP FUNCTION IF EXISTS reg_replace;
CREATE FUNCTION reg_replace(subject VARCHAR(21845), pattern VARCHAR(21845),
replacement VARCHAR(21845), greedy BOOLEAN, minMatchLen INT, maxMatchLen INT)
RETURNS VARCHAR(21845) DETERMINISTIC BEGIN
DECLARE result, subStr, usePattern VARCHAR(21845);
DECLARE startPos, prevStartPos, startInc, len, lenInc INT;
IF subject REGEXP pattern THEN
SET result = '';
-- Sanitize input parameter values
SET minMatchLen = IF(minMatchLen < 1, 1, minMatchLen);
SET maxMatchLen = IF(maxMatchLen < 1 OR maxMatchLen > CHAR_LENGTH(subject),
CHAR_LENGTH(subject), maxMatchLen);
-- Set the pattern to use to match an entire string rather than part of a string
SET usePattern = IF (LEFT(pattern, 1) = '^', pattern, CONCAT('^', pattern));
SET usePattern = IF (RIGHT(pattern, 1) = '$', usePattern, CONCAT(usePattern, '$'));
-- Set start position to 1 if pattern starts with ^ or doesn't end with $.
IF LEFT(pattern, 1) = '^' OR RIGHT(pattern, 1) <> '$' THEN
SET startPos = 1, startInc = 1;
-- Otherwise (i.e. pattern ends with $ but doesn't start with ^): Set start position
-- to the min or max match length from the end (depending on "greedy" flag).
ELSEIF greedy THEN
SET startPos = CHAR_LENGTH(subject) - maxMatchLen + 1, startInc = 1;
ELSE
SET startPos = CHAR_LENGTH(subject) - minMatchLen + 1, startInc = -1;
END IF;
WHILE startPos >= 1 AND startPos <= CHAR_LENGTH(subject)
AND startPos + minMatchLen - 1 <= CHAR_LENGTH(subject)
AND !(LEFT(pattern, 1) = '^' AND startPos <> 1)
AND !(RIGHT(pattern, 1) = '$'
AND startPos + maxMatchLen - 1 < CHAR_LENGTH(subject)) DO
-- Set start length to maximum if matching greedily or pattern ends with $.
-- Otherwise set starting length to the minimum match length.
IF greedy OR RIGHT(pattern, 1) = '$' THEN
SET len = LEAST(CHAR_LENGTH(subject) - startPos + 1, maxMatchLen), lenInc = -1;
ELSE
SET len = minMatchLen, lenInc = 1;
END IF;
SET prevStartPos = startPos;
lenLoop: WHILE len >= 1 AND len <= maxMatchLen
AND startPos + len - 1 <= CHAR_LENGTH(subject)
AND !(RIGHT(pattern, 1) = '$'
AND startPos + len - 1 <> CHAR_LENGTH(subject)) DO
SET subStr = SUBSTRING(subject, startPos, len);
IF subStr REGEXP usePattern THEN
SET result = IF(startInc = 1,
CONCAT(result, replacement), CONCAT(replacement, result));
SET startPos = startPos + startInc * len;
LEAVE lenLoop;
END IF;
SET len = len + lenInc;
END WHILE;
IF (startPos = prevStartPos) THEN
SET result = IF(startInc = 1, CONCAT(result, SUBSTRING(subject, startPos, 1)),
CONCAT(SUBSTRING(subject, startPos, 1), result));
SET startPos = startPos + startInc;
END IF;
END WHILE;
IF startInc = 1 AND startPos <= CHAR_LENGTH(subject) THEN
SET result = CONCAT(result, RIGHT(subject, CHAR_LENGTH(subject) + 1 - startPos));
ELSEIF startInc = -1 AND startPos >= 1 THEN
SET result = CONCAT(LEFT(subject, startPos), result);
END IF;
ELSE
SET result = subject;
END IF;
RETURN result;
END;
DROP FUNCTION IF EXISTS format_result;
CREATE FUNCTION format_result(result VARCHAR(21845))
RETURNS VARCHAR(21845) DETERMINISTIC BEGIN
RETURN CONCAT(CONCAT('|', REPLACE(REPLACE(REPLACE(REPLACE(result, '\t', '\\t'), CHAR(12), '\\f'), '\r', '\\r'), '\n', '\\n')), '|');
END;
DROP TABLE IF EXISTS tbl;
CREATE TABLE tbl
AS
SELECT 'Afghanistan' AS txt
UNION ALL
SELECT ' AF' AS txt
UNION ALL
SELECT ' Cayman Islands ' AS txt
UNION ALL
SELECT CONCAT(CONCAT(CONCAT('\t \t ', CHAR(12)), ' \r\n\t British Virgin Islands \t \t ', CHAR(12)), ' \r\n') AS txt;
SELECT format_result(txt) AS txt,
format_result(TRIM(txt)) AS trim,
format_result(TRIM(BOTH '\r' FROM TRIM(BOTH '\n' FROM TRIM(BOTH '\f' FROM TRIM(BOTH '\t' FROM TRIM(txt))))))
AS `trim spaces, tabs, formfeeds and line endings`,
format_result(reg_replace(reg_replace(txt, '^[[:space:]]+', '', TRUE, 1, 0), '[[:space:]]+$', '', TRUE, 1, 0))
AS `reg_replace`
FROM tbl;
用法:
SELECT reg_replace(
reg_replace(txt,
'^[[:space:]]+',
'',
TRUE,
1,
0),
'[[:space:]]+$',
'',
TRUE,
1,
0) AS `trimmed txt`
FROM tbl;