Trim specific character from a string
Update: Was curious around the performance of different solutions and so I've updated a basic benchmark here: https://www.measurethat.net/Benchmarks/Show/12738/0/trimming-leadingtrailing-characters
Some interesting and unexpected results running under Chrome. https://www.measurethat.net/Benchmarks/ShowResult/182877
+-----------------------------------+-----------------------+
| Test name | Executions per second |
+-----------------------------------+-----------------------+
| Index Version (Jason Larke) | 949979.7 Ops/sec |
| Substring Version (Pho3niX83) | 197548.9 Ops/sec |
| Regex Version (leaf) | 107357.2 Ops/sec |
| Boolean Filter Version (mbaer3000)| 94162.3 Ops/sec |
| Spread Version (Robin F.) | 4242.8 Ops/sec |
+-----------------------------------+-----------------------+
Please note; tests were carried out on only a single test string (with both leading and trailing characters that needed trimming). In addition, this benchmark only gives an indication of raw speed; other factors like memory usage are also important to consider.
If you're dealing with longer strings I believe this should outperform most of the other options by reducing the number of allocated strings to either zero or one:
function trim(str, ch) {
var start = 0,
end = str.length;
while(start < end && str[start] === ch)
++start;
while(end > start && str[end - 1] === ch)
--end;
return (start > 0 || end < str.length) ? str.substring(start, end) : str;
}
// Usage:
trim('|hello|world|', '|'); // => 'hello|world'
Or if you want to trim from a set of multiple characters:
function trimAny(str, chars) {
var start = 0,
end = str.length;
while(start < end && chars.indexOf(str[start]) >= 0)
++start;
while(end > start && chars.indexOf(str[end - 1]) >= 0)
--end;
return (start > 0 || end < str.length) ? str.substring(start, end) : str;
}
// Usage:
trimAny('|hello|world ', [ '|', ' ' ]); // => 'hello|world'
// because '.indexOf' is used, you could also pass a string for the 2nd parameter:
trimAny('|hello| world ', '| '); // => 'hello|world'
EDIT: For fun, trim words (rather than individual characters)
// Helper function to detect if a string contains another string
// at a specific position.
// Equivalent to using `str.indexOf(substr, pos) === pos` but *should* be more efficient on longer strings as it can exit early (needs benchmarks to back this up).
function hasSubstringAt(str, substr, pos) {
var idx = 0, len = substr.length;
for (var max = str.length; idx < len; ++idx) {
if ((pos + idx) >= max || str[pos + idx] != substr[idx])
break;
}
return idx === len;
}
function trimWord(str, word) {
var start = 0,
end = str.length,
len = word.length;
while (start < end && hasSubstringAt(str, word, start))
start += word.length;
while (end > start && hasSubstringAt(str, word, end - len))
end -= word.length
return (start > 0 || end < str.length) ? str.substring(start, end) : str;
}
// Usage:
trimWord('blahrealmessageblah', 'blah');
One line is enough:
var x = '|f|oo||';
var y = x.replace(/^\|+|\|+$/g, '');
document.write(x + '<br />' + y);
^ beginning of the string
\|+ pipe, one or more times
| or
\|+ pipe, one or more times
$ end of the string
A general solution:
function trim (s, c) {
if (c === "]") c = "\\]";
if (c === "^") c = "\\^";
if (c === "\\") c = "\\\\";
return s.replace(new RegExp(
"^[" + c + "]+|[" + c + "]+$", "g"
), "");
}
chars = ".|]\\^";
for (c of chars) {
s = c + "foo" + c + c + "oo" + c + c + c;
console.log(s, "->", trim(s, c));
}
Parameter c
is expected to be a character (a string of length 1).
As mentionned in the comments, it might be useful to support multiple characters, as it's quite common to trim multiple whitespace-like characters for example. To do this, MightyPork suggests to replace the if
s with the following line of code:
c = c.replace(/[-/\\^$*+?.()|[\]{}]/g, '\\$&');
This part [-/\\^$*+?.()|[\]{}]
is a set of special characters in regular expression syntax, and $&
is a placeholder which stands for the matching character, meaning that the replace
function escapes special characters. Try in your browser console:
> "{[hello]}".replace(/[-/\\^$*+?.()|[\]{}]/g, '\\$&')
"\{\[hello\]\}"
You can use a regular expression such as:
var x = "|f|oo||";
var y = x.replace(/^\|+|\|+$/g, "");
alert(y); // f|oo
UPDATE:
Should you wish to generalize this into a function, you can do the following:
var escapeRegExp = function(strToEscape) {
// Escape special characters for use in a regular expression
return strToEscape.replace(/[\-\[\]\/\{\}\(\)\*\+\?\.\\\^\$\|]/g, "\\$&");
};
var trimChar = function(origString, charToTrim) {
charToTrim = escapeRegExp(charToTrim);
var regEx = new RegExp("^[" + charToTrim + "]+|[" + charToTrim + "]+$", "g");
return origString.replace(regEx, "");
};
var x = "|f|oo||";
var y = trimChar(x, "|");
alert(y); // f|oo
If I understood well, you want to remove a specific character only if it is at the beginning or at the end of the string (ex: ||fo||oo||||
should become foo||oo
). You can create an ad hoc function as follows:
function trimChar(string, charToRemove) {
while(string.charAt(0)==charToRemove) {
string = string.substring(1);
}
while(string.charAt(string.length-1)==charToRemove) {
string = string.substring(0,string.length-1);
}
return string;
}
I tested this function with the code below:
var str = "|f|oo||";
$( "#original" ).html( "Original String: '" + str + "'" );
$( "#trimmed" ).html( "Trimmed: '" + trimChar(str, "|") + "'" );