I have the following code that uses a regex:
var mystring = "<<cool>> <<stuff>>"
var regexString = /<<([^\:]{0,})>>/gi
mystring.replace(regexString, "$1")
I would like to be able to replace the string based on the text I get back on the capture group. Something like:
var mystring = "<<cool>> <<stuff>>"
var regexString = /<<([^>]{1,})>>/gi
mystring.replace(regexString, function(var0) { //var0 being the text from the capture group
if(var0 == "cool") {
console.log("got cool")
} else {
console.log("didn't get cool")
}
})
Is there someway to do this?
Yes, you can definitely use a function as a second argument of .replace(). For example:
mystring.replace(regexString, function(match, group1) {
// do anything with group1 here
});
Reference: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/replace
Related
You can backreference like this in JavaScript:
var str = "123 $test 123";
str = str.replace(/(\$)([a-z]+)/gi, "$2");
This would (quite silly) replace "$test" with "test". But imagine I'd like to pass the resulting string of $2 into a function, which returns another value. I tried doing this, but instead of getting the string "test", I get "$2". Is there a way to achieve this?
// Instead of getting "$2" passed into somefunc, I want "test"
// (i.e. the result of the regex)
str = str.replace(/(\$)([a-z]+)/gi, somefunc("$2"));
Like this:
str.replace(regex, function(match, $1, $2, offset, original) { return someFunc($2); })
Pass a function as the second argument to replace:
str = str.replace(/(\$)([a-z]+)/gi, myReplace);
function myReplace(str, group1, group2) {
return "+" + group2 + "+";
}
This capability has been around since Javascript 1.3, according to mozilla.org.
Using ESNext, quite a dummy links replacer but just to show-case how it works :
let text = 'Visit http://lovecats.com/new-posts/ and https://lovedogs.com/best-dogs NOW !';
text = text.replace(/(https?:\/\/[^ ]+)/g, (match, link) => {
// remove ending slash if there is one
link = link.replace(/\/?$/, '');
return `${link.substr(link.lastIndexOf('/') +1)}`;
});
document.body.innerHTML = text;
Note: Previous answer was missing some code. It's now fixed + example.
I needed something a bit more flexible for a regex replace to decode the unicode in my incoming JSON data:
var text = "some string with an encoded 's' in it";
text.replace(/&#(\d+);/g, function() {
return String.fromCharCode(arguments[1]);
});
// "some string with an encoded 's' in it"
If you would have a variable amount of backreferences then the argument count (and places) are also variable. The MDN Web Docs describe the follwing syntax for sepcifing a function as replacement argument:
function replacer(match[, p1[, p2[, p...]]], offset, string)
For instance, take these regular expressions:
var searches = [
'test([1-3]){1,3}', // 1 backreference
'([Ss]ome) ([A-z]+) chars', // 2 backreferences
'([Mm][a#]ny) ([Mm][0o]r[3e]) ([Ww][0o]rd[5s])' // 3 backreferences
];
for (var i in searches) {
"Some string chars and many m0re w0rds in this test123".replace(
new RegExp(
searches[i]
function(...args) {
var match = args[0];
var backrefs = args.slice(1, args.length - 2);
// will be: ['Some', 'string'], ['many', 'm0re', 'w0rds'], ['123']
var offset = args[args.length - 2];
var string = args[args.length - 1];
}
)
);
}
You can't use 'arguments' variable here because it's of type Arguments and no of type Array so it doesn't have a slice() method.
I'm trying to clean strings which has been transformed from word text but I'm stuck on removing special character '…'
By click on button "clean", script removes all dots and only one special character, however I need to remove all of them
Where is my mistake?
Here is my code and plunker with struggles
$scope.string = "My transformed string ………….........…...."
$scope.removeDots = function () {
var em = document.getElementsByTagName('em');
var reg = /\./g;
var hellip = /…/g
angular.forEach(em, function (item) {
if(item.innerText.match(reg)){
item.innerText = process(item.innerText)
}
if (item.innerText.match(hellip)){
item.innerText = item.innerText.replace("…", "")
}
});
};
function process( str ) {
return str.replace( /^([^.]*\.)(.*)$/, function ( a, b, c ) {
return b + c.replace( /\./g, '' );
});
}
There's a few problems here, but they can all be resolved by simply reducing the code to a single regex replace within process that will handle both periods and … entities:
$scope.removeDots = function () {
var em = document.getElementsByTagName('em');
angular.forEach(em, function (item) {
item.innerText = process(item.innerText)
});
};
function process( str ) {
return str.replace( /\.|…/g, '');
}
});
Plunker demo
You replace every occurrence of . in process, but only replace … once.
I don't see why don't you just do something like .replace(/(\.|…)/g, ''); the g modifier makes sure every match is replaced.
You can do both replacements by first replacing the occurrences of … with one point (because it might be the only thing you find), and then replacing any sequence of points by one:
function process( str ) {
return str.replace(/…/g, '.').replace(/\.\.+/g, '.');
}
var test="My transformed string ………….........…....";
console.log(process(test));
One of the reasons your code did not replace everything, is that you used a string as find argument, which will result in one replacement only. By using the regular expression as find argument you can get the effect of the g modifier.
I want to remove the comma(,) from the the string if it occur at first position or last position in the string.
For Example :
var str = ",abcd,efg,last,";
The output should be
output = 'abcd,efg,last'
if input is
str = "abcdef,ghij,kl"
the output should be :
output = "abcdef,ghij,kl"
var str = ",abcd,efg,last,";
var res = str.replace(/^,|,$/g, '');
console.log(res);
do this
this will remove the comma if it is at the starting position or at the end of the string position
There must be some strip() function in Javascript that I don't know for lack of my knowledge. But here is how you can do it using regex:
output = ",abcd,efg,last,".replace(/^,|,$/g, "");
JavaScript doesn't include a native method for this. The closest is trim, but that doesn't take any args. I think it should, though. So you could write something like this
String.prototype.trim = (function (trim) {
if (!trim) // polyfill if not included in browser
trim = function () {
return this.replace(/^\s+|\s+$/g, '');
};
else if (trim.call('.', '.') === '') // already supports this
return trim;
return function (chars) {
if (!chars) return trim.call(this);
chars = chars.replace(/([\^\\\]-])/g, '\\$1');
return this.replace(new RegExp('^['+chars+']+|['+chars+']+$', 'g'), '');
}
}(String.prototype.trim));
Now we have
' foo '.trim(); // "foo"
',,,foo,,,'.trim(','); // "foo"
I have the following regex where I am trying to capture the Ids of each start comment. But for some reason I am only able to capture the first one. It won't grab the Id of the nested comment. It only prints 1000 to the console. I am trying to get it to capture both 1000 and 2000. Can anyone spot the error in my regex?
<script type="text/javascript">
function ExtractText() {
var regex = /\<!--Start([0-9]{4})-->([\s\S]*?)<!--End[0-9]{4}-->/gm;
var match;
while (match = regex.exec($("#myHtml").html())) {
console.log(match[1]);
}
}
</script>
<div id="myHtml">
<!--Start1000-->Text on<!--Start2000-->the left<!--End1000-->Text on the right<!--End2000-->
</div>
Based on Mike Samuel's answer I updated my JS to the following:
function GetAllIds() {
var regex = /<!--Start([0-9]{4})-->([\s\S]*?)<!--End\1-->/g;
var text = $("#myHtml").html();
var match;
while (regex.test(text)) {
text = text.replace(
regex,
function (_, id, content) {
console.log(id);
return content;
});
}
}
In
<!--Start1000-->Text on<!--Start2000-->the left<!--End1000-->Text on the right<!--End2000-->
the "1000" region overlaps the "2000" region, but the exec loop only finds non-overlapping matches since each call to exec with the same regex and string starts at the end of the last match. To solve this problem, try
var regex = /<!--Start([0-9]{4})-->([\s\S]*?)<!--End\1-->/g;
for (var s = $("#myHtml").html(), sWithoutComment;
// Keep going until we fail to replace a comment bracketed chunk
// with the chunk minus comments.
true;
s = sWithoutComment) {
// Replace one group of non-overlapping comment pairs.
sWithoutComment = s.replace(
regex,
function (_, id, content) {
console.log(id);
// Replace the whole thing with the body.
return content;
});
if (s === sWithoutComment) { break; }
}
You can use grouping and then another regexp:
var regex = /(<!--Start)([0-9]{4})/ig;
var str = document.getElementById('myHtml').innerHTML;
var matches = str.match(regex);
for(var i=0;i<matches.length;i++){
var m = matches[i];
var num = m.match(/(\d+)/)[1];
console.log(num);
}
You can backreference like this in JavaScript:
var str = "123 $test 123";
str = str.replace(/(\$)([a-z]+)/gi, "$2");
This would (quite silly) replace "$test" with "test". But imagine I'd like to pass the resulting string of $2 into a function, which returns another value. I tried doing this, but instead of getting the string "test", I get "$2". Is there a way to achieve this?
// Instead of getting "$2" passed into somefunc, I want "test"
// (i.e. the result of the regex)
str = str.replace(/(\$)([a-z]+)/gi, somefunc("$2"));
Like this:
str.replace(regex, function(match, $1, $2, offset, original) { return someFunc($2); })
Pass a function as the second argument to replace:
str = str.replace(/(\$)([a-z]+)/gi, myReplace);
function myReplace(str, group1, group2) {
return "+" + group2 + "+";
}
This capability has been around since Javascript 1.3, according to mozilla.org.
Using ESNext, quite a dummy links replacer but just to show-case how it works :
let text = 'Visit http://lovecats.com/new-posts/ and https://lovedogs.com/best-dogs NOW !';
text = text.replace(/(https?:\/\/[^ ]+)/g, (match, link) => {
// remove ending slash if there is one
link = link.replace(/\/?$/, '');
return `${link.substr(link.lastIndexOf('/') +1)}`;
});
document.body.innerHTML = text;
Note: Previous answer was missing some code. It's now fixed + example.
I needed something a bit more flexible for a regex replace to decode the unicode in my incoming JSON data:
var text = "some string with an encoded 's' in it";
text.replace(/&#(\d+);/g, function() {
return String.fromCharCode(arguments[1]);
});
// "some string with an encoded 's' in it"
If you would have a variable amount of backreferences then the argument count (and places) are also variable. The MDN Web Docs describe the follwing syntax for sepcifing a function as replacement argument:
function replacer(match[, p1[, p2[, p...]]], offset, string)
For instance, take these regular expressions:
var searches = [
'test([1-3]){1,3}', // 1 backreference
'([Ss]ome) ([A-z]+) chars', // 2 backreferences
'([Mm][a#]ny) ([Mm][0o]r[3e]) ([Ww][0o]rd[5s])' // 3 backreferences
];
for (var i in searches) {
"Some string chars and many m0re w0rds in this test123".replace(
new RegExp(
searches[i]
function(...args) {
var match = args[0];
var backrefs = args.slice(1, args.length - 2);
// will be: ['Some', 'string'], ['many', 'm0re', 'w0rds'], ['123']
var offset = args[args.length - 2];
var string = args[args.length - 1];
}
)
);
}
You can't use 'arguments' variable here because it's of type Arguments and no of type Array so it doesn't have a slice() method.