Is there a version of JavaScript's String.indexOf() that allows for regular expressions?
JavascriptRegexIndexofJavascript Problem Overview
In javascript, is there an equivalent of String.indexOf() that takes a regular expression instead of a string for the first first parameter while still allowing a second parameter ?
I need to do something like
str.indexOf(/[abc]/ , i);
and
str.lastIndexOf(/[abc]/ , i);
While String.search() takes a regexp as a parameter it does not allow me to specify a second argument!
Edit:
This turned out to be harder than I originally thought so I wrote a small test function to test all the provided solutions... it assumes regexIndexOf and regexLastIndexOf have been added to the String object.
function test (str) {
var i = str.length +2;
while (i--) {
if (str.indexOf('a',i) != str.regexIndexOf(/a/,i))
alert (['failed regexIndexOf ' , str,i , str.indexOf('a',i) , str.regexIndexOf(/a/,i)]) ;
if (str.lastIndexOf('a',i) != str.regexLastIndexOf(/a/,i) )
alert (['failed regexLastIndexOf ' , str,i,str.lastIndexOf('a',i) , str.regexLastIndexOf(/a/,i)]) ;
}
}
and I am testing as follow to make sure that at least for one character regexp, the result is the same as if we used indexOf
//Look for the a among the xes
test('xxx');
test('axx');
test('xax');
test('xxa');
test('axa');
test('xaa');
test('aax');
test('aaa');
Javascript Solutions
Solution 1 - Javascript
Instances of the String constructor have a .search() method which accepts a RegExp and returns the index of the first match.
To start the search from a particular position (faking the second parameter of .indexOf()) you can slice off the first i characters:
str.slice(i).search(/re/)
But this will get the index in the shorter string (after the first part was sliced off) so you'll want to then add the length of the chopped off part (i) to the returned index if it wasn't -1. This will give you the index in the original string:
function regexIndexOf(text, re, i) {
var indexInSuffix = text.slice(i).search(re);
return indexInSuffix < 0 ? indexInSuffix : indexInSuffix + i;
}
Solution 2 - Javascript
Combining a few of the approaches already mentioned (the indexOf is obviously rather simple), I think these are the functions that will do the trick:
function regexIndexOf(string, regex, startpos) {
var indexOf = string.substring(startpos || 0).search(regex);
return (indexOf >= 0) ? (indexOf + (startpos || 0)) : indexOf;
}
function regexLastIndexOf(string, regex, startpos) {
regex = (regex.global) ? regex : new RegExp(regex.source, "g" + (regex.ignoreCase ? "i" : "") + (regex.multiLine ? "m" : ""));
if(typeof (startpos) == "undefined") {
startpos = string.length;
} else if(startpos < 0) {
startpos = 0;
}
var stringToWorkWith = string.substring(0, startpos + 1);
var lastIndexOf = -1;
var nextStop = 0;
while((result = regex.exec(stringToWorkWith)) != null) {
lastIndexOf = result.index;
regex.lastIndex = ++nextStop;
}
return lastIndexOf;
}
UPDATE: Edited regexLastIndexOf() so that is seems to mimic lastIndexOf() now. Please let me know if it still fails and under what circumstances.
UPDATE: Passes all tests found on in comments on this page, and my own. Of course, that doesn't mean it's bulletproof. Any feedback appreciated.
Solution 3 - Javascript
I have a short version for you. It works well for me!
var match = str.match(/[abc]/gi);
var firstIndex = str.indexOf(match[0]);
var lastIndex = str.lastIndexOf(match[match.length-1]);
And if you want a prototype version:
String.prototype.indexOfRegex = function(regex){
var match = this.match(regex);
return match ? this.indexOf(match[0]) : -1;
}
String.prototype.lastIndexOfRegex = function(regex){
var match = this.match(regex);
return match ? this.lastIndexOf(match[match.length-1]) : -1;
}
EDIT : if you want to add support for fromIndex
String.prototype.indexOfRegex = function(regex, fromIndex){
var str = fromIndex ? this.substring(fromIndex) : this;
var match = str.match(regex);
return match ? str.indexOf(match[0]) + fromIndex : -1;
}
String.prototype.lastIndexOfRegex = function(regex, fromIndex){
var str = fromIndex ? this.substring(0, fromIndex) : this;
var match = str.match(regex);
return match ? str.lastIndexOf(match[match.length-1]) : -1;
}
To use it, as simple as this:
var firstIndex = str.indexOfRegex(/[abc]/gi);
var lastIndex = str.lastIndexOfRegex(/[abc]/gi);
Solution 4 - Javascript
Solution 5 - Javascript
You could use substr.
str.substr(i).match(/[abc]/);
Solution 6 - Javascript
Based on BaileyP's answer. The main difference is that these methods return -1 if the pattern can't be matched.
Edit: Thanks to Jason Bunting's answer I got an idea. Why not modify the .lastIndex property of the regex? Though this will only work for patterns with the global flag (/g).
Edit: Updated to pass the test-cases.
String.prototype.regexIndexOf = function(re, startPos) {
startPos = startPos || 0;
if (!re.global) {
var flags = "g" + (re.multiline?"m":"") + (re.ignoreCase?"i":"");
re = new RegExp(re.source, flags);
}
re.lastIndex = startPos;
var match = re.exec(this);
if (match) return match.index;
else return -1;
}
String.prototype.regexLastIndexOf = function(re, startPos) {
startPos = startPos === undefined ? this.length : startPos;
if (!re.global) {
var flags = "g" + (re.multiline?"m":"") + (re.ignoreCase?"i":"");
re = new RegExp(re.source, flags);
}
var lastSuccess = -1;
for (var pos = 0; pos <= startPos; pos++) {
re.lastIndex = pos;
var match = re.exec(this);
if (!match) break;
pos = match.index;
if (pos <= startPos) lastSuccess = pos;
}
return lastSuccess;
}
Solution 7 - Javascript
RexExp instances have a lastIndex property already (if they are global) and so what I'm doing is copying the regular expression, modifying it slightly to suit our purposes, exec-ing it on the string and looking at the lastIndex. This will inevitably be faster than looping on the string. (You have enough examples of how to put this onto the string prototype, right?)
function reIndexOf(reIn, str, startIndex) {
var re = new RegExp(reIn.source, 'g' + (reIn.ignoreCase ? 'i' : '') + (reIn.multiLine ? 'm' : ''));
re.lastIndex = startIndex || 0;
var res = re.exec(str);
if(!res) return -1;
return re.lastIndex - res[0].length;
};
function reLastIndexOf(reIn, str, startIndex) {
var src = /\$$/.test(reIn.source) && !/\\\$$/.test(reIn.source) ? reIn.source : reIn.source + '(?![\\S\\s]*' + reIn.source + ')';
var re = new RegExp(src, 'g' + (reIn.ignoreCase ? 'i' : '') + (reIn.multiLine ? 'm' : ''));
re.lastIndex = startIndex || 0;
var res = re.exec(str);
if(!res) return -1;
return re.lastIndex - res[0].length;
};
reIndexOf(/[abc]/, "tommy can eat"); // Returns 6
reIndexOf(/[abc]/, "tommy can eat", 8); // Returns 11
reLastIndexOf(/[abc]/, "tommy can eat"); // Returns 11
You could also prototype the functions onto the RegExp object:
RegExp.prototype.indexOf = function(str, startIndex) {
var re = new RegExp(this.source, 'g' + (this.ignoreCase ? 'i' : '') + (this.multiLine ? 'm' : ''));
re.lastIndex = startIndex || 0;
var res = re.exec(str);
if(!res) return -1;
return re.lastIndex - res[0].length;
};
RegExp.prototype.lastIndexOf = function(str, startIndex) {
var src = /\$$/.test(this.source) && !/\\\$$/.test(this.source) ? this.source : this.source + '(?![\\S\\s]*' + this.source + ')';
var re = new RegExp(src, 'g' + (this.ignoreCase ? 'i' : '') + (this.multiLine ? 'm' : ''));
re.lastIndex = startIndex || 0;
var res = re.exec(str);
if(!res) return -1;
return re.lastIndex - res[0].length;
};
/[abc]/.indexOf("tommy can eat"); // Returns 6
/[abc]/.indexOf("tommy can eat", 8); // Returns 11
/[abc]/.lastIndexOf("tommy can eat"); // Returns 11
A quick explanation of how I am modifying the RegExp: For indexOf I just have to ensure that the global flag is set. For lastIndexOf of I am using a negative look-ahead to find the last occurrence unless the RegExp was already matching at the end of the string.
Solution 8 - Javascript
It does not natively, but you certainly can add this functionality
<script type="text/javascript">
String.prototype.regexIndexOf = function( pattern, startIndex )
{
startIndex = startIndex || 0;
var searchResult = this.substr( startIndex ).search( pattern );
return ( -1 === searchResult ) ? -1 : searchResult + startIndex;
}
String.prototype.regexLastIndexOf = function( pattern, startIndex )
{
startIndex = startIndex === undefined ? this.length : startIndex;
var searchResult = this.substr( 0, startIndex ).reverse().regexIndexOf( pattern, 0 );
return ( -1 === searchResult ) ? -1 : this.length - ++searchResult;
}
String.prototype.reverse = function()
{
return this.split('').reverse().join('');
}
// Indexes 0123456789
var str = 'caabbccdda';
alert( [
str.regexIndexOf( /[cd]/, 4 )
, str.regexLastIndexOf( /[cd]/, 4 )
, str.regexIndexOf( /[yz]/, 4 )
, str.regexLastIndexOf( /[yz]/, 4 )
, str.lastIndexOf( 'd', 4 )
, str.regexLastIndexOf( /d/, 4 )
, str.lastIndexOf( 'd' )
, str.regexLastIndexOf( /d/ )
]
);
</script>
I didn't fully test these methods, but they seem to work so far.
Solution 9 - Javascript
I needed a regexIndexOf function also for an array, so I programed one myself. However I doubt, that it's optimized, but i guess it should work properly.
Array.prototype.regexIndexOf = function (regex, startpos = 0) {
len = this.length;
for(x = startpos; x < len; x++){
if(typeof this[x] != 'undefined' && (''+this[x]).match(regex)){
return x;
}
}
return -1;
}
arr = [];
arr.push(null);
arr.push(NaN);
arr[3] = 7;
arr.push('asdf');
arr.push('qwer');
arr.push(9);
arr.push('...');
console.log(arr);
arr.regexIndexOf(/\d/, 4);
Solution 10 - Javascript
After having all the proposed solutions fail my tests one way or the other, (edit: some were updated to pass the tests after I wrote this) I found the mozilla implementation for Array.indexOf and Array.lastIndexOf
I used those to implement my version of String.prototype.regexIndexOf and String.prototype.regexLastIndexOf as follows:
String.prototype.regexIndexOf = function(elt /*, from*/)
{
var arr = this.split('');
var len = arr.length;
var from = Number(arguments[1]) || 0;
from = (from < 0) ? Math.ceil(from) : Math.floor(from);
if (from < 0)
from += len;
for (; from < len; from++) {
if (from in arr && elt.exec(arr[from]) )
return from;
}
return -1;
};
String.prototype.regexLastIndexOf = function(elt /*, from*/)
{
var arr = this.split('');
var len = arr.length;
var from = Number(arguments[1]);
if (isNaN(from)) {
from = len - 1;
} else {
from = (from < 0) ? Math.ceil(from) : Math.floor(from);
if (from < 0)
from += len;
else if (from >= len)
from = len - 1;
}
for (; from > -1; from--) {
if (from in arr && elt.exec(arr[from]) )
return from;
}
return -1;
};
They seem to pass the test functions I provided in the question.
Obviously they only work if the regular expression matches one character but that is enough for my purpose since I will be using it for things like ( [abc] , \s , \W , \D )
I will keep monitoring the question in case someone provides a better/faster/cleaner/more generic implementation that works on any regular expression.
Solution 11 - Javascript
In certain simple cases, you can simplify your backwards search by using split.
function regexlast(string,re){
var tokens=string.split(re);
return (tokens.length>1)?(string.length-tokens[tokens.length-1].length):null;
}
This has a few serious problems:
- overlapping matches won't show up
- returned index is for the end of the match rather than the beginning (fine if your regex is a constant)
But on the bright side it's way less code. For a constant-length regex that can't overlap (like /\s\w/ for finding word boundaries) this is good enough.
Solution 12 - Javascript
For a solution that's more concise than most of the other answers posted, you may want to use the String.prototype.replace function which will run a function on every detected pattern. For example:
let firstIndex = -1;
"the 1st numb3r".replace(/\d/,(p,i) => { firstIndex = i; });
// firstIndex === 4
This is especially useful for the "last index" case:
let lastIndex = -1;
"the l4st numb3r".replace(/\d/g,(p,i) => { lastIndex = i; });
// lastIndex === 13
Here, it's important to include the "g" modifier so that all occurrences are evaluated. These versions will also result in -1 if the regular expression was not found.
Finally, here are the more general functions which include a start index:
function indexOfRegex(str,regex,start = 0) {
regex = regex.global ? regex : new RegExp(regex.source,regex.flags + "g");
let index = -1;
str.replace(regex,function() {
const pos = arguments[arguments.length - 2];
if(index < 0 && pos >= start)
index = pos;
});
return index;
}
function lastIndexOfRegex(str,regex,start = str.length - 1) {
regex = regex.global ? regex : new RegExp(regex.source,regex.flags + "g");
let index = -1;
str.replace(regex,function() {
const pos = arguments[arguments.length - 2];
if(pos <= start)
index = pos;
});
return index;
}
These functions specifically avoid splitting the string at the start index which I feel is risky in the age of Unicode. They don't modify the prototype of common Javascript classes (although you're free to do so yourself). They accept more RegExp flags, for example "u" or "s" and any flags that may be added in the future. And I find it easier to reason about callback functions than for/while loops.
Solution 13 - Javascript
For data with sparse matches, using string.search is the fastest across browsers. It re-slices a string each iteration to :
function lastIndexOfSearch(string, regex, index) {
if(index === 0 || index)
string = string.slice(0, Math.max(0,index));
var idx;
var offset = -1;
while ((idx = string.search(regex)) !== -1) {
offset += idx + 1;
string = string.slice(idx + 1);
}
return offset;
}
For dense data I made this. It's complex compared to the execute method, but for dense data, it's 2-10x faster than every other method I tried, and about 100x faster than the accepted solution. The main points are:
-
It calls exec on the regex passed in once to verify there is a match or quit early. I do this using (?= in a similar method, but on IE checking with exec is dramatically faster.
-
It constructs and caches a modified regex in the format '(r).(?!.?r)'
-
The new regex is executed and the results from either that exec, or the first exec, are returned;
function lastIndexOfGroupSimple(string, regex, index) { if (index === 0 || index) string = string.slice(0, Math.max(0, index + 1)); regex.lastIndex = 0; var lastRegex, index flags = 'g' + (regex.multiline ? 'm' : '') + (regex.ignoreCase ? 'i' : ''), key = regex.source + '$' + flags, match = regex.exec(string); if (!match) return -1; if (lastIndexOfGroupSimple.cache === undefined) lastIndexOfGroupSimple.cache = {}; lastRegex = lastIndexOfGroupSimple.cache[key]; if (!lastRegex) lastIndexOfGroupSimple.cache[key] = lastRegex = new RegExp('.*(' + regex.source + ')(?!.*?' + regex.source + ')', flags); index = match.index; lastRegex.lastIndex = match.index; return (match = lastRegex.exec(string)) ? lastRegex.lastIndex - match[1].length : index; };
I don't understand the purpose of the tests up top. Situations that require a regex are impossible to compare against a call to indexOf, which I think is the point of making the method in the first place. To get the test to pass, it makes more sense to use 'xxx+(?!x)', than adjust the way the regex iterates.
Solution 14 - Javascript
Jason Bunting's last index of does not work. Mine is not optimal, but it works.
//Jason Bunting's
String.prototype.regexIndexOf = function(regex, startpos) {
var indexOf = this.substring(startpos || 0).search(regex);
return (indexOf >= 0) ? (indexOf + (startpos || 0)) : indexOf;
}
String.prototype.regexLastIndexOf = function(regex, startpos) {
var lastIndex = -1;
var index = this.regexIndexOf( regex );
startpos = startpos === undefined ? this.length : startpos;
while ( index >= 0 && index < startpos )
{
lastIndex = index;
index = this.regexIndexOf( regex, index + 1 );
}
return lastIndex;
}
Solution 15 - Javascript
There are still no native methods that perform the requested task.
Here is the code that I am using. It mimics the behaviour of String.prototype.indexOf and String.prototype.lastIndexOf methods but they also accept a RegExp as the search argument in addition to a string representing the value to search for.
Yes it is quite long as an answer goes as it tries to follow current standards as close as possible and of course contains a reasonable amount of JSDOC comments. However, once minified, the code is only 2.27k and once gzipped for transmission it is only 1023 bytes.
The 2 methods that this adds to String.prototype (using Object.defineProperty where available) are:
searchOfsearchLastOf
It passes all the tests that the OP posted and additionally I have tested the routines quite thoroughly in my daily usage, and have attempted to be sure that they work across multiple environments, but feedback/issues are always welcome.
/*jslint maxlen:80, browser:true */
/*
* Properties used by searchOf and searchLastOf implementation.
*/
/*property
MAX_SAFE_INTEGER, abs, add, apply, call, configurable, defineProperty,
enumerable, exec, floor, global, hasOwnProperty, ignoreCase, index,
lastIndex, lastIndexOf, length, max, min, multiline, pow, prototype,
remove, replace, searchLastOf, searchOf, source, toString, value, writable
*/
/*
* Properties used in the testing of searchOf and searchLastOf implimentation.
*/
/*property
appendChild, createTextNode, getElementById, indexOf, lastIndexOf, length,
searchLastOf, searchOf, unshift
*/
(function () {
'use strict';
var MAX_SAFE_INTEGER = Number.MAX_SAFE_INTEGER || Math.pow(2, 53) - 1,
getNativeFlags = new RegExp('\\/([a-z]*)$', 'i'),
clipDups = new RegExp('([\\s\\S])(?=[\\s\\S]*\\1)', 'g'),
pToString = Object.prototype.toString,
pHasOwn = Object.prototype.hasOwnProperty,
stringTagRegExp;
/**
* Defines a new property directly on an object, or modifies an existing
* property on an object, and returns the object.
*
* @private
* @function
* @param {Object} object
* @param {string} property
* @param {Object} descriptor
* @returns {Object}
* @see https://goo.gl/CZnEqg
*/
function $defineProperty(object, property, descriptor) {
if (Object.defineProperty) {
Object.defineProperty(object, property, descriptor);
} else {
object[property] = descriptor.value;
}
return object;
}
/**
* Returns true if the operands are strictly equal with no type conversion.
*
* @private
* @function
* @param {*} a
* @param {*} b
* @returns {boolean}
* @see http://www.ecma-international.org/ecma-262/5.1/#sec-11.9.4
*/
function $strictEqual(a, b) {
return a === b;
}
/**
* Returns true if the operand inputArg is undefined.
*
* @private
* @function
* @param {*} inputArg
* @returns {boolean}
*/
function $isUndefined(inputArg) {
return $strictEqual(typeof inputArg, 'undefined');
}
/**
* Provides a string representation of the supplied object in the form
* "[object type]", where type is the object type.
*
* @private
* @function
* @param {*} inputArg The object for which a class string represntation
* is required.
* @returns {string} A string value of the form "[object type]".
* @see http://www.ecma-international.org/ecma-262/5.1/#sec-15.2.4.2
*/
function $toStringTag(inputArg) {
var val;
if (inputArg === null) {
val = '[object Null]';
} else if ($isUndefined(inputArg)) {
val = '[object Undefined]';
} else {
val = pToString.call(inputArg);
}
return val;
}
/**
* The string tag representation of a RegExp object.
*
* @private
* @type {string}
*/
stringTagRegExp = $toStringTag(getNativeFlags);
/**
* Returns true if the operand inputArg is a RegExp.
*
* @private
* @function
* @param {*} inputArg
* @returns {boolean}
*/
function $isRegExp(inputArg) {
return $toStringTag(inputArg) === stringTagRegExp &&
pHasOwn.call(inputArg, 'ignoreCase') &&
typeof inputArg.ignoreCase === 'boolean' &&
pHasOwn.call(inputArg, 'global') &&
typeof inputArg.global === 'boolean' &&
pHasOwn.call(inputArg, 'multiline') &&
typeof inputArg.multiline === 'boolean' &&
pHasOwn.call(inputArg, 'source') &&
typeof inputArg.source === 'string';
}
/**
* The abstract operation throws an error if its argument is a value that
* cannot be converted to an Object, otherwise returns the argument.
*
* @private
* @function
* @param {*} inputArg The object to be tested.
* @throws {TypeError} If inputArg is null or undefined.
* @returns {*} The inputArg if coercible.
* @see https://goo.gl/5GcmVq
*/
function $requireObjectCoercible(inputArg) {
var errStr;
if (inputArg === null || $isUndefined(inputArg)) {
errStr = 'Cannot convert argument to object: ' + inputArg;
throw new TypeError(errStr);
}
return inputArg;
}
/**
* The abstract operation converts its argument to a value of type string
*
* @private
* @function
* @param {*} inputArg
* @returns {string}
* @see https://people.mozilla.org/~jorendorff/es6-draft.html#sec-tostring
*/
function $toString(inputArg) {
var type,
val;
if (inputArg === null) {
val = 'null';
} else {
type = typeof inputArg;
if (type === 'string') {
val = inputArg;
} else if (type === 'undefined') {
val = type;
} else {
if (type === 'symbol') {
throw new TypeError('Cannot convert symbol to string');
}
val = String(inputArg);
}
}
return val;
}
/**
* Returns a string only if the arguments is coercible otherwise throws an
* error.
*
* @private
* @function
* @param {*} inputArg
* @throws {TypeError} If inputArg is null or undefined.
* @returns {string}
*/
function $onlyCoercibleToString(inputArg) {
return $toString($requireObjectCoercible(inputArg));
}
/**
* The function evaluates the passed value and converts it to an integer.
*
* @private
* @function
* @param {*} inputArg The object to be converted to an integer.
* @returns {number} If the target value is NaN, null or undefined, 0 is
* returned. If the target value is false, 0 is returned
* and if true, 1 is returned.
* @see http://www.ecma-international.org/ecma-262/5.1/#sec-9.4
*/
function $toInteger(inputArg) {
var number = +inputArg,
val = 0;
if ($strictEqual(number, number)) {
if (!number || number === Infinity || number === -Infinity) {
val = number;
} else {
val = (number > 0 || -1) * Math.floor(Math.abs(number));
}
}
return val;
}
/**
* Copies a regex object. Allows adding and removing native flags while
* copying the regex.
*
* @private
* @function
* @param {RegExp} regex Regex to copy.
* @param {Object} [options] Allows specifying native flags to add or
* remove while copying the regex.
* @returns {RegExp} Copy of the provided regex, possibly with modified
* flags.
*/
function $copyRegExp(regex, options) {
var flags,
opts,
rx;
if (options !== null && typeof options === 'object') {
opts = options;
} else {
opts = {};
}
// Get native flags in use
flags = getNativeFlags.exec($toString(regex))[1];
flags = $onlyCoercibleToString(flags);
if (opts.add) {
flags += opts.add;
flags = flags.replace(clipDups, '');
}
if (opts.remove) {
// Would need to escape `options.remove` if this was public
rx = new RegExp('[' + opts.remove + ']+', 'g');
flags = flags.replace(rx, '');
}
return new RegExp(regex.source, flags);
}
/**
* The abstract operation ToLength converts its argument to an integer
* suitable for use as the length of an array-like object.
*
* @private
* @function
* @param {*} inputArg The object to be converted to a length.
* @returns {number} If len <= +0 then +0 else if len is +INFINITY then
* 2^53-1 else min(len, 2^53-1).
* @see https://people.mozilla.org/~jorendorff/es6-draft.html#sec-tolength
*/
function $toLength(inputArg) {
return Math.min(Math.max($toInteger(inputArg), 0), MAX_SAFE_INTEGER);
}
/**
* Copies a regex object so that it is suitable for use with searchOf and
* searchLastOf methods.
*
* @private
* @function
* @param {RegExp} regex Regex to copy.
* @returns {RegExp}
*/
function $toSearchRegExp(regex) {
return $copyRegExp(regex, {
add: 'g',
remove: 'y'
});
}
/**
* Returns true if the operand inputArg is a member of one of the types
* Undefined, Null, Boolean, Number, Symbol, or String.
*
* @private
* @function
* @param {*} inputArg
* @returns {boolean}
* @see https://goo.gl/W68ywJ
* @see https://goo.gl/ev7881
*/
function $isPrimitive(inputArg) {
var type = typeof inputArg;
return type === 'undefined' ||
inputArg === null ||
type === 'boolean' ||
type === 'string' ||
type === 'number' ||
type === 'symbol';
}
/**
* The abstract operation converts its argument to a value of type Object
* but fixes some environment bugs.
*
* @private
* @function
* @param {*} inputArg The argument to be converted to an object.
* @throws {TypeError} If inputArg is not coercible to an object.
* @returns {Object} Value of inputArg as type Object.
* @see http://www.ecma-international.org/ecma-262/5.1/#sec-9.9
*/
function $toObject(inputArg) {
var object;
if ($isPrimitive($requireObjectCoercible(inputArg))) {
object = Object(inputArg);
} else {
object = inputArg;
}
return object;
}
/**
* Converts a single argument that is an array-like object or list (eg.
* arguments, NodeList, DOMTokenList (used by classList), NamedNodeMap
* (used by attributes property)) into a new Array() and returns it.
* This is a partial implementation of the ES6 Array.from
*
* @private
* @function
* @param {Object} arrayLike
* @returns {Array}
*/
function $toArray(arrayLike) {
var object = $toObject(arrayLike),
length = $toLength(object.length),
array = [],
index = 0;
array.length = length;
while (index < length) {
array[index] = object[index];
index += 1;
}
return array;
}
if (!String.prototype.searchOf) {
/**
* This method returns the index within the calling String object of
* the first occurrence of the specified value, starting the search at
* fromIndex. Returns -1 if the value is not found.
*
* @function
* @this {string}
* @param {RegExp|string} regex A regular expression object or a String.
* Anything else is implicitly converted to
* a String.
* @param {Number} [fromIndex] The location within the calling string
* to start the search from. It can be any
* integer. The default value is 0. If
* fromIndex < 0 the entire string is
* searched (same as passing 0). If
* fromIndex >= str.length, the method will
* return -1 unless searchValue is an empty
* string in which case str.length is
* returned.
* @returns {Number} If successful, returns the index of the first
* match of the regular expression inside the
* string. Otherwise, it returns -1.
*/
$defineProperty(String.prototype, 'searchOf', {
enumerable: false,
configurable: true,
writable: true,
value: function (regex) {
var str = $onlyCoercibleToString(this),
args = $toArray(arguments),
result = -1,
fromIndex,
match,
rx;
if (!$isRegExp(regex)) {
return String.prototype.indexOf.apply(str, args);
}
if ($toLength(args.length) > 1) {
fromIndex = +args[1];
if (fromIndex < 0) {
fromIndex = 0;
}
} else {
fromIndex = 0;
}
if (fromIndex >= $toLength(str.length)) {
return result;
}
rx = $toSearchRegExp(regex);
rx.lastIndex = fromIndex;
match = rx.exec(str);
if (match) {
result = +match.index;
}
return result;
}
});
}
if (!String.prototype.searchLastOf) {
/**
* This method returns the index within the calling String object of
* the last occurrence of the specified value, or -1 if not found.
* The calling string is searched backward, starting at fromIndex.
*
* @function
* @this {string}
* @param {RegExp|string} regex A regular expression object or a String.
* Anything else is implicitly converted to
* a String.
* @param {Number} [fromIndex] Optional. The location within the
* calling string to start the search at,
* indexed from left to right. It can be
* any integer. The default value is
* str.length. If it is negative, it is
* treated as 0. If fromIndex > str.length,
* fromIndex is treated as str.length.
* @returns {Number} If successful, returns the index of the first
* match of the regular expression inside the
* string. Otherwise, it returns -1.
*/
$defineProperty(String.prototype, 'searchLastOf', {
enumerable: false,
configurable: true,
writable: true,
value: function (regex) {
var str = $onlyCoercibleToString(this),
args = $toArray(arguments),
result = -1,
fromIndex,
length,
match,
pos,
rx;
if (!$isRegExp(regex)) {
return String.prototype.lastIndexOf.apply(str, args);
}
length = $toLength(str.length);
if (!$strictEqual(args[1], args[1])) {
fromIndex = length;
} else {
if ($toLength(args.length) > 1) {
fromIndex = $toInteger(args[1]);
} else {
fromIndex = length - 1;
}
}
if (fromIndex >= 0) {
fromIndex = Math.min(fromIndex, length - 1);
} else {
fromIndex = length - Math.abs(fromIndex);
}
pos = 0;
rx = $toSearchRegExp(regex);
while (pos <= fromIndex) {
rx.lastIndex = pos;
match = rx.exec(str);
if (!match) {
break;
}
pos = +match.index;
if (pos <= fromIndex) {
result = pos;
}
pos += 1;
}
return result;
}
});
}
}());
(function () {
'use strict';
/*
* testing as follow to make sure that at least for one character regexp,
* the result is the same as if we used indexOf
*/
var pre = document.getElementById('out');
function log(result) {
pre.appendChild(document.createTextNode(result + '\n'));
}
function test(str) {
var i = str.length + 2,
r,
a,
b;
while (i) {
a = str.indexOf('a', i);
b = str.searchOf(/a/, i);
r = ['Failed', 'searchOf', str, i, a, b];
if (a === b) {
r[0] = 'Passed';
}
log(r);
a = str.lastIndexOf('a', i);
b = str.searchLastOf(/a/, i);
r = ['Failed', 'searchLastOf', str, i, a, b];
if (a === b) {
r[0] = 'Passed';
}
log(r);
i -= 1;
}
}
/*
* Look for the a among the xes
*/
test('xxx');
test('axx');
test('xax');
test('xxa');
test('axa');
test('xaa');
test('aax');
test('aaa');
}());
<pre id="out"></pre>
Solution 16 - Javascript
If you are looking for a very simple lastIndex lookup with RegExp and don't care if it mimics lastIndexOf to the last detail, this may catch your attention.
I simply reverse the string, and subtract the first occurence index from length - 1. It happens to pass my test, but I think there could arise a performance issue with long strings.
interface String {
reverse(): string;
lastIndex(regex: RegExp): number;
}
String.prototype.reverse = function(this: string) {
return this.split("")
.reverse()
.join("");
};
String.prototype.lastIndex = function(this: string, regex: RegExp) {
const exec = regex.exec(this.reverse());
return exec === null ? -1 : this.length - 1 - exec.index;
};
Solution 17 - Javascript
I used String.prototype.match(regex) which returns a string array of all found matches of the given regex in the string (more info see here):
function getLastIndex(text, regex, limit = text.length) {
const matches = text.match(regex);
// no matches found
if (!matches) {
return -1;
}
// matches found but first index greater than limit
if (text.indexOf(matches[0] + matches[0].length) > limit) {
return -1;
}
// reduce index until smaller than limit
let i = matches.length - 1;
let index = text.lastIndexOf(matches[i]);
while (index > limit && i >= 0) {
i--;
index = text.lastIndexOf(matches[i]);
}
return index > limit ? -1 : index;
}
// expect -1 as first index === 14
console.log(getLastIndex('First Sentence. Last Sentence. Unfinished', /\. /g, 10));
// expect 29
console.log(getLastIndex('First Sentence. Last Sentence. Unfinished', /\. /g));
Solution 18 - Javascript
var mystring = "abc ab a";
var re = new RegExp("ab"); // any regex here
if ( re.exec(mystring) != null ){
alert("matches"); // true in this case
}
Use standard regular expressions:
var re = new RegExp("^ab"); // At front
var re = new RegExp("ab$"); // At end
var re = new RegExp("ab(c|d)"); // abc or abd
Solution 19 - Javascript
let regExp; // your RegExp here
arr.map(x => !!x.toString().match(regExp)).indexOf(true)
Solution 20 - Javascript
The regexIndexOf from Jason Bunting can be inverted more simply and still support UTF8 characters by doing this:
function regexLastIndexOf(string, regex, startpos=0) {
return text.length - regexIndexOf([...text].reverse().join(""), regex, startpos) - 1;
}
Solution 21 - Javascript
Well, as you are just looking to match the position of a character , regex is possibly overkill.
I presume all you want is, instead of "find first of these this character" , just find first of these characters.
This of course is the simple answer, but does what your question sets out to do, albeit without the regex part ( because you didn't clarify why specifically it had to be a regex )
function mIndexOf( str , chars, offset )
{
var first = -1;
for( var i = 0; i < chars.length; i++ )
{
var p = str.indexOf( chars[i] , offset );
if( p < first || first === -1 )
{
first = p;
}
}
return first;
}
String.prototype.mIndexOf = function( chars, offset )
{
return mIndexOf( this, chars, offset ); # I'm really averse to monkey patching.
};
mIndexOf( "hello world", ['a','o','w'], 0 );
>> 4
mIndexOf( "hello world", ['a'], 0 );
>> -1
mIndexOf( "hello world", ['a','o','w'], 4 );
>> 4
mIndexOf( "hello world", ['a','o','w'], 5 );
>> 6
mIndexOf( "hello world", ['a','o','w'], 7 );
>> -1
mIndexOf( "hello world", ['a','o','w','d'], 7 );
>> 10
mIndexOf( "hello world", ['a','o','w','d'], 10 );
>> 10
mIndexOf( "hello world", ['a','o','w','d'], 11 );
>> -1