Is there a way to retrieve the (starting) character positions inside a string of the results of a regex match() in Javascript?
This question is related to
javascript
regex
match
string-matching
Here is a cool feature I discovered recently, I tried this on the console and it seems to work:
var text = "border-bottom-left-radius";
var newText = text.replace(/-/g,function(match, index){
return " " + index + " ";
});
Which returned: "border 6 bottom 13 left 18 radius"
So this seems to be what you are looking for.
In modern browsers, you can accomplish this with string.matchAll().
The benefit to this approach vs RegExp.exec()
is that it does not rely on the regex being stateful, as in @Gumbo's answer.
let regexp = /bar/g;
let str = 'foobarfoobar';
let matches = [...str.matchAll(regexp)];
matches.forEach((match) => {
console.log("match found at " + match.index);
});
_x000D_
From developer.mozilla.org docs on the String .match()
method:
The returned Array has an extra input property, which contains the original string that was parsed. In addition, it has an index property, which represents the zero-based index of the match in the string.
When dealing with a non-global regex (i.e., no g
flag on your regex), the value returned by .match()
has an index
property...all you have to do is access it.
var index = str.match(/regex/).index;
Here is an example showing it working as well:
var str = 'my string here';_x000D_
_x000D_
var index = str.match(/here/).index;_x000D_
_x000D_
alert(index); // <- 10
_x000D_
I have successfully tested this all the way back to IE5.
var str = 'my string here';
var index = str.match(/hre/).index;
alert(index); // <- 10
_x000D_
exec
returns an object with a index
property:
var match = /bar/.exec("foobar");_x000D_
if (match) {_x000D_
console.log("match found at " + match.index);_x000D_
}
_x000D_
And for multiple matches:
var re = /bar/g,_x000D_
str = "foobarfoobar";_x000D_
while ((match = re.exec(str)) != null) {_x000D_
console.log("match found at " + match.index);_x000D_
}
_x000D_
This member fn returns an array of 0-based positions, if any, of the input word inside the String object
String.prototype.matching_positions = function( _word, _case_sensitive, _whole_words, _multiline )
{
/*besides '_word' param, others are flags (0|1)*/
var _match_pattern = "g"+(_case_sensitive?"i":"")+(_multiline?"m":"") ;
var _bound = _whole_words ? "\\b" : "" ;
var _re = new RegExp( _bound+_word+_bound, _match_pattern );
var _pos = [], _chunk, _index = 0 ;
while( true )
{
_chunk = _re.exec( this ) ;
if ( _chunk == null ) break ;
_pos.push( _chunk['index'] ) ;
_re.lastIndex = _chunk['index']+1 ;
}
return _pos ;
}
Now try
var _sentence = "What do doers want ? What do doers need ?" ;
var _word = "do" ;
console.log( _sentence.matching_positions( _word, 1, 0, 0 ) );
console.log( _sentence.matching_positions( _word, 1, 1, 0 ) );
You can also input regular expressions:
var _second = "z^2+2z-1" ;
console.log( _second.matching_positions( "[0-9]\z+", 0, 0, 0 ) );
Here one gets the position index of linear term.
function trimRegex(str, regex){
return str.substr(str.match(regex).index).split('').reverse().join('').substr(str.match(regex).index).split('').reverse().join('');
}
let test = '||ab||cd||';
trimRegex(test, /[^|]/);
console.log(test); //output: ab||cd
or
function trimChar(str, trim, req){
let regex = new RegExp('[^'+trim+']');
return str.substr(str.match(regex).index).split('').reverse().join('').substr(str.match(regex).index).split('').reverse().join('');
}
let test = '||ab||cd||';
trimChar(test, '|');
console.log(test); //output: ab||cd
You can use the search
method of the String
object. This will only work for the first match, but will otherwise do what you describe. For example:
"How are you?".search(/are/);
// 4
var str = "The rain in SPAIN stays mainly in the plain";
function searchIndex(str, searchValue, isCaseSensitive) {
var modifiers = isCaseSensitive ? 'gi' : 'g';
var regExpValue = new RegExp(searchValue, modifiers);
var matches = [];
var startIndex = 0;
var arr = str.match(regExpValue);
[].forEach.call(arr, function(element) {
startIndex = str.indexOf(element, startIndex);
matches.push(startIndex++);
});
return matches;
}
console.log(searchIndex(str, 'ain', true));
Source: Stackoverflow.com