I would like to split a very large string (let's say, 10,000 characters) into N-size chunks.
What would be the best way in terms of performance to do this?
For instance:
"1234567890" split by 2 would become ["12", "34", "56", "78", "90"].
Would something like this be possible using String.prototype.match and if so, would that be the best way to do it in terms of performance?
You can do something like this:
"1234567890".match(/.{1,2}/g);
// Results in:
["12", "34", "56", "78", "90"]
The method will still work with strings whose size is not an exact multiple of the chunk-size:
"123456789".match(/.{1,2}/g);
// Results in:
["12", "34", "56", "78", "9"]
In general, for any string out of which you want to extract at-most n-sized substrings, you would do:
str.match(/.{1,n}/g); // Replace n with the size of the substring
If your string can contain newlines or carriage returns, you would do:
str.match(/(.|[\r\n]){1,n}/g); // Replace n with the size of the substring
As far as performance, I tried this out with approximately 10k characters and it took a little over a second on Chrome. YMMV.
This can also be used in a reusable function:
function chunkString(str, length) {
return str.match(new RegExp('.{1,' + length + '}', 'g'));
}
. does not match newline at all. I will update the answer so that it takes \n and \r into account.var chunks = str.split("").reverse().join().match(/.{1, 4}/).map(function(s) { return s.split("").reverse().join(); });. This does it in chunks of 4. I am not sure what you mean by "less or more". Keep in mind this won't work in general, especially with strings that contain combining characters and can break Unicode strings as well.
[^]. With this your example would result in str.match(/[^]{1,n}/g)
I created several faster variants which you can see on jsPerf. My favorite one is this:
function chunkSubstr(str, size) {
const numChunks = Math.ceil(str.length / size)
const chunks = new Array(numChunks)
for (let i = 0, o = 0; i < numChunks; ++i, o += size) {
chunks[i] = str.substr(o, size)
}
return chunks
}
Math.ceil() to determine the correct number of chunks.
match, slice, substr and substringmatch and slice for different chunk sizesmatch and slice with small chunk sizeBottom line:
match is very inefficient, slice is better, on Firefox substr/substring is better stillmatch is even more inefficient for short strings (even with cached regex - probably due to regex parsing setup time)match is even more inefficient for large chunk size (probably due to inability to "jump")match outperforms slice on older IE but still loses on all other systems
This is a fast and straightforward solution -
function chunkString (str, len) {
const size = Math.ceil(str.length/len)
const r = Array(size)
let offset = 0
for (let i = 0; i < size; i++) {
r[i] = str.substr(offset, len)
offset += len
}
return r
}
console.log(chunkString("helloworld", 3))
// => [ "hel", "low", "orl", "d" ]
// 10,000 char string
const bigString = "helloworld".repeat(1000)
console.time("perf")
const result = chunkString(bigString, 3)
console.timeEnd("perf")
console.log(result)
// => perf: 0.385 ms
// => [ "hel", "low", "orl", "dhe", "llo", "wor", ... ]
substr() instead of substring().
substr() is now deprecated in favor of substring() developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/…Surprise! You can use split to split.
var parts = "1234567890 ".split(/(.{2})/).filter(O=>O)
Results in [ '12', '34', '56', '78', '90', ' ' ]
filter (o=>o) for?
filter(x=>x) is used to filter out those empty elements
You can definitely do something like
let pieces = "1234567890 ".split(/(.{2})/).filter(x => x.length == 2);
to get this:
[ '12', '34', '56', '78', '90' ]
If you want to dynamically input/adjust the chunk size so that the chunks are of size n, you can do this:
n = 2;
let pieces = "1234567890 ".split(new RegExp("(.{"+n.toString()+"})")).filter(x => x.length == n);
To find all possible size n chunks in the original string, try this:
let subs = new Set();
let n = 2;
let str = "1234567890 ";
let regex = new RegExp("(.{"+n.toString()+"})"); //set up regex expression dynamically encoded with n
for (let i = 0; i < n; i++){ //starting from all possible offsets from position 0 in the string
let pieces = str.split(regex).filter(x => x.length == n); //divide the string into chunks of size n...
for (let p of pieces) //...and add the chunks to the set
subs.add(p);
str = str.substr(1); //shift the string reading frame
}
You should end up with:
[ '12', '23', '34', '45', '56', '67', '78', '89', '90', '0 ' ]
var str = "123456789";
var chunks = [];
var chunkSize = 2;
while (str) {
if (str.length < chunkSize) {
chunks.push(str);
break;
}
else {
chunks.push(str.substr(0, chunkSize));
str = str.substr(chunkSize);
}
}
alert(chunks); // chunks == 12,34,56,78,9
Include both left and right version with pre-allocation. This is as fast as RegExp impl for small chunks but it goes faster as the chunk size grows. And it is memory efficent.
function chunkLeft (str, size = 3) {
if (typeof str === 'string') {
const length = str.length
const chunks = Array(Math.ceil(length / size))
for (let i = 0, index = 0; index < length; i++) {
chunks[i] = str.slice(index, index += size)
}
return chunks
}
}
function chunkRight (str, size = 3) {
if (typeof str === 'string') {
const length = str.length
const chunks = Array(Math.ceil(length / size))
if (length) {
chunks[0] = str.slice(0, length % size || size)
for (let i = 1, index = chunks[0].length; index < length; i++) {
chunks[i] = str.slice(index, index += size)
}
}
return chunks
}
}
console.log(chunkRight()) // undefined
console.log(chunkRight('')) // []
console.log(chunkRight('1')) // ["1"]
console.log(chunkRight('123')) // ["123"]
console.log(chunkRight('1234')) // ["1", "234"]
console.log(chunkRight('12345')) // ["12", "345"]
console.log(chunkRight('123456')) // ["123", "456"]
console.log(chunkRight('1234567')) // ["1", "234", "567"]
I have written an extended function, so the chunk length can also be an array of numbers, like [1,3]
String.prototype.chunkString = function(len) {
var _ret;
if (this.length < 1) {
return [];
}
if (typeof len === 'number' && len > 0) {
var _size = Math.ceil(this.length / len), _offset = 0;
_ret = new Array(_size);
for (var _i = 0; _i < _size; _i++) {
_ret[_i] = this.substring(_offset, _offset = _offset + len);
}
}
else if (typeof len === 'object' && len.length) {
var n = 0, l = this.length, chunk, that = this;
_ret = [];
do {
len.forEach(function(o) {
chunk = that.substring(n, n + o);
if (chunk !== '') {
_ret.push(chunk);
n += chunk.length;
}
});
if (n === 0) {
return undefined; // prevent an endless loop when len = [0]
}
} while (n < l);
}
return _ret;
};
The code
"1234567890123".chunkString([1,3])
will return:
[ '1', '234', '5', '678', '9', '012', '3' ]
const getChunksFromString = (str, chunkSize) => {
var regexChunk = new RegExp(`.{1,${chunkSize}}`, 'g') // '.' represents any character
return str.match(regexChunk)
}
Call it as needed
console.log(getChunksFromString("Hello world", 3)) // ["Hel", "lo ", "wor", "ld"]
getChunksFromString('1\n2\n3\n4', 2) does output [ "1", "2", "3", "4" ], without newline characters.new RegExp("...", "gs")it Split's large string in to Small strings of given words .
function chunkSubstr(str, words) {
var parts = str.split(" ") , values = [] , i = 0 , tmpVar = "";
$.each(parts, function(index, value) {
if(tmpVar.length < words){
tmpVar += " " + value;
}else{
values[i] = tmpVar.replace(/\s+/g, " ");
i++;
tmpVar = value;
}
});
if(values.length < 1 && parts.length > 0){
values[0] = tmpVar;
}
return values;
}
var l = str.length, lc = 0, chunks = [], c = 0, chunkSize = 2;
for (; lc < l; c++) {
chunks[c] = str.slice(lc, lc += chunkSize);
}
I would use a regex...
var chunkStr = function(str, chunkLength) {
return str.match(new RegExp('[\\s\\S]{1,' + +chunkLength + '}', 'g'));
}
Here's a solution I came up with for template strings after a little experimenting:
Usage:
chunkString(5)`testing123`
function chunkString(nSize) {
return (strToChunk) => {
let result = [];
let chars = String(strToChunk).split('');
for(let i = 0; i < (String(strToChunk).length / nSize); i++) {
result = result.concat(chars.slice(i*nSize,(i+1)*nSize).join(''));
}
return result
}
}
document.write(chunkString(5)`testing123`);
// returns: testi,ng123
document.write(chunkString(3)`testing123`);
// returns: tes,tin,g12,3What about this small piece of code:
function splitME(str, size) {
let subStr = new RegExp('.{1,' + size + '}', 'g');
return str.match(subStr);
};
You can use reduce() without any regex:
(str, n) => {
return str.split('').reduce(
(acc, rec, index) => {
return ((index % n) || !(index)) ? acc.concat(rec) : acc.concat(',', rec)
},
''
).split(',')
}
reduce method.Here is the code that I am using, it uses String.prototype.slice.
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 828 bytes and once gzipped for transmission it is only 497 bytes.
The 1 method that this adds to String.prototype (using Object.defineProperty where available) is:
A number of tests have been included to check the functionality.
Worried that the length of code will affect the performance? No need to worry, http://jsperf.com/chunk-string/3
Much of the extra code is there to be sure that the code will respond the same across multiple javascript environments.
/*jslint maxlen:80, browser:true, devel:true */
/*
* Properties used by toChunks.
*/
/*property
MAX_SAFE_INTEGER, abs, ceil, configurable, defineProperty, enumerable,
floor, length, max, min, pow, prototype, slice, toChunks, value,
writable
*/
/*
* Properties used in the testing of toChunks implimentation.
*/
/*property
appendChild, createTextNode, floor, fromCharCode, getElementById, length,
log, pow, push, random, toChunks
*/
(function () {
'use strict';
var MAX_SAFE_INTEGER = Number.MAX_SAFE_INTEGER || Math.pow(2, 53) - 1;
/**
* 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
* @return {Object}
* @see https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Object/defineProperty
*/
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
* @return {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
* @return {boolean}
*/
function $isUndefined(inputArg) {
return $strictEqual(typeof inputArg, 'undefined');
}
/**
* 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.
* @return {*} The inputArg if coercible.
* @see https://people.mozilla.org/~jorendorff/es6-draft.html#sec-requireobjectcoercible
*/
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
* @return {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.
* @return {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.
* @return {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;
}
/**
* 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.
* @return {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);
}
if (!String.prototype.toChunks) {
/**
* This method chunks a string into an array of strings of a specified
* chunk size.
*
* @function
* @this {string} The string to be chunked.
* @param {Number} chunkSize The size of the chunks that the string will
* be chunked into.
* @returns {Array} Returns an array of the chunked string.
*/
$defineProperty(String.prototype, 'toChunks', {
enumerable: false,
configurable: true,
writable: true,
value: function (chunkSize) {
var str = $onlyCoercibleToString(this),
chunkLength = $toInteger(chunkSize),
chunked = [],
numChunks,
length,
index,
start,
end;
if (chunkLength < 1) {
return chunked;
}
length = $toLength(str.length);
numChunks = Math.ceil(length / chunkLength);
index = 0;
start = 0;
end = chunkLength;
chunked.length = numChunks;
while (index < numChunks) {
chunked[index] = str.slice(start, end);
start = end;
end += chunkLength;
index += 1;
}
return chunked;
}
});
}
}());
/*
* Some tests
*/
(function () {
'use strict';
var pre = document.getElementById('out'),
chunkSizes = [],
maxChunkSize = 512,
testString = '',
maxTestString = 100000,
chunkSize = 0,
index = 1;
while (chunkSize < maxChunkSize) {
chunkSize = Math.pow(2, index);
chunkSizes.push(chunkSize);
index += 1;
}
index = 0;
while (index < maxTestString) {
testString += String.fromCharCode(Math.floor(Math.random() * 95) + 32);
index += 1;
}
function log(result) {
pre.appendChild(document.createTextNode(result + '\n'));
}
function test() {
var strLength = testString.length,
czLength = chunkSizes.length,
czIndex = 0,
czValue,
result,
numChunks,
pass;
while (czIndex < czLength) {
czValue = chunkSizes[czIndex];
numChunks = Math.ceil(strLength / czValue);
result = testString.toChunks(czValue);
czIndex += 1;
log('chunksize: ' + czValue);
log(' Number of chunks:');
log(' Calculated: ' + numChunks);
log(' Actual:' + result.length);
pass = result.length === numChunks;
log(' First chunk size: ' + result[0].length);
pass = pass && result[0].length === czValue;
log(' Passed: ' + pass);
log('');
}
}
test();
log('');
log('Simple test result');
log('abcdefghijklmnopqrstuvwxyz'.toChunks(3));
}());<pre id="out"></pre>
window.format = function(b, a) {
if (!b || isNaN(+a)) return a;
var a = b.charAt(0) == "-" ? -a : +a,
j = a < 0 ? a = -a : 0,
e = b.match(/[^\d\-\+#]/g),
h = e && e[e.length - 1] || ".",
e = e && e[1] && e[0] || ",",
b = b.split(h),
a = a.toFixed(b[1] && b[1].length),
a = +a + "",
d = b[1] && b[1].lastIndexOf("0"),
c = a.split(".");
if (!c[1] || c[1] && c[1].length <= d) a = (+a).toFixed(d + 1);
d = b[0].split(e);
b[0] = d.join("");
var f = b[0] && b[0].indexOf("0");
if (f > -1)
for (; c[0].length < b[0].length - f;) c[0] = "0" + c[0];
else +c[0] == 0 && (c[0] = "");
a = a.split(".");
a[0] = c[0];
if (c = d[1] && d[d.length -
1].length) {
for (var d = a[0], f = "", k = d.length % c, g = 0, i = d.length; g < i; g++) f += d.charAt(g), !((g - k + 1) % c) && g < i - c && (f += e);
a[0] = f
}
a[1] = b[1] && a[1] ? h + a[1] : "";
return (j ? "-" : "") + a[0] + a[1]
};
var str="1234567890";
var formatstr=format( "##,###.", str);
alert(formatstr);
This will split the string in reverse order with comma separated after 3 char's. If you want you can change the position.
Using slice() method:
function returnChunksArray(str, chunkSize) {
var arr = [];
while(str !== '') {
arr.push(str.slice(0, chunkSize));
str = str.slice(chunkSize);
}
return arr;
}
The same can be done using substring() method.
function returnChunksArray(str, chunkSize) {
var arr = [];
while(str !== '') {
arr.push(str.substring(0, chunkSize));
str = str.substring(chunkSize);
}
return arr;
}
My issue with the above solution is that it beark the string into formal size chunks regardless of the position in the sentences.
I think the following a better approach; although it needs some performance tweaking:
static chunkString(str, length, size,delimiter='\n' ) {
const result = [];
for (let i = 0; i < str.length; i++) {
const lastIndex = _.lastIndexOf(str, delimiter,size + i);
result.push(str.substr(i, lastIndex - i));
i = lastIndex;
}
return result;
}
Use this npm library "chkchars" but remember to make sure the length of the string given is perfectly divided by the "number" parameter.
const phrase = "1110010111010011100101110100010000011100101110100111001011101001011101001110010111010001000001110010111010011100101110100"
const number = 7
chkchars.splitToChunks(phrase, number)
// result => ['1110010', '1110100','1110010', '1110100','0100000', '1110010','1110100', '1110010','1110100', '1011101','0011100', '1011101','0001000','0011100','1011101', '0011100','1011101']
// perf => 0.287ms
function chunkString(str, length = 10) {
let result = [],
offset = 0;
if (str.length <= length) return result.push(str) && result;
while (offset < str.length) {
result.push(str.substr(offset, length));
offset += length;
}
return result;
}
