How do I split a string with multiple separators in javascript?

How do I split a string with multiple separators in JavaScript? I'm trying to split on both commas and spaces but, AFAIK, JS's split function only supports one separator.

Answers:

Answer

Pass in a regexp as the parameter:

js> "Hello awesome, world!".split(/[\s,]+/)
Hello,awesome,world!

Edited to add:

You can get the last element by selecting the length of the array minus 1:

>>> bits = "Hello awesome, world!".split(/[\s,]+/)
["Hello", "awesome", "world!"]
>>> bit = bits[bits.length - 1]
"world!"

... and if the pattern doesn't match:

>>> bits = "Hello awesome, world!".split(/foo/)
["Hello awesome, world!"]
>>> bits[bits.length - 1]
"Hello awesome, world!"
Answer

You can pass a regex into Javascript's split operator. For example:

"1,2 3".split(/,| /) 
["1", "2", "3"]

Or, if you want to allow multiple separators together to act as one only:

"1, 2, , 3".split(/(?:,| )+/) 
["1", "2", "3"]

(You have to use the non-capturing (?:) parens because otherwise it gets spliced back into the result. Or you can be smart like Aaron and use a character class.)

(Examples tested in Safari + FF)

Answer

Another simple but effective method is to use split + join repeatedly.

"a=b,c:d".split('=').join(',').split(':').join(',').split(',')

Essentially doing a split followed by a join is like a global replace so this replaces each separator with a comma then once all are replaced it does a final split on comma

The result of the above expression is:

['a', 'b', 'c', 'd']

Expanding on this you could also place it in a function:

function splitMulti(str, tokens){
        var tempChar = tokens[0]; // We can use the first token as a temporary join character
        for(var i = 1; i < tokens.length; i++){
            str = str.split(tokens[i]).join(tempChar);
        }
        str = str.split(tempChar);
        return str;
}

Usage:

splitMulti('a=b,c:d', ['=', ',', ':']) // ["a", "b", "c", "d"]

If you use this functionality a lot it might even be worth considering wrapping String.prototype.split for convenience (I think my function is fairly safe - the only consideration is the additional overhead of the conditionals (minor) and the fact that it lacks an implementation of the limit argument if an array is passed).

Be sure to include the splitMulti function if using this approach to the below simply wraps it :). Also worth noting that some people frown on extending built-ins (as many people do it wrong and conflicts can occur) so if in doubt speak to someone more senior before using this or ask on SO :)

    var splitOrig = String.prototype.split; // Maintain a reference to inbuilt fn
    String.prototype.split = function (){
        if(arguments[0].length > 0){
            if(Object.prototype.toString.call(arguments[0]) == "[object Array]" ) { // Check if our separator is an array
                return splitMulti(this, arguments[0]);  // Call splitMulti
            }
        }
        return splitOrig.apply(this, arguments); // Call original split maintaining context
    };

Usage:

var a = "a=b,c:d";
    a.split(['=', ',', ':']); // ["a", "b", "c", "d"]

// Test to check that the built-in split still works (although our wrapper wouldn't work if it didn't as it depends on it :P)
        a.split('='); // ["a", "b,c:d"] 

Enjoy!

Answer

Lets keep it simple: (add a "[ ]+" to your RegEx means "1 or more")

This means "+" and "{1,}" are the same.

var words = text.split(/[ .:;?!~,`"&|()<>{}\[\]\r\n/\\]+/); // note ' and - are kept
Answer

Tricky method:

var s = "dasdnk asd, (naks) :d skldma";
var a = s.replace('(',' ').replace(')',' ').replace(',',' ').split(' ');
console.log(a);//["dasdnk", "asd", "naks", ":d", "skldma"]
Answer

For those of you who want more customization in their splitting function, I wrote a recursive algorithm that splits a given string with a list of characters to split on. I wrote this before I saw the above post. I hope it helps some frustrated programmers.

splitString = function(string, splitters) {
    var list = [string];
    for(var i=0, len=splitters.length; i<len; i++) {
        traverseList(list, splitters[i], 0);
    }
    return flatten(list);
}

traverseList = function(list, splitter, index) {
    if(list[index]) {
        if((list.constructor !== String) && (list[index].constructor === String))
            (list[index] != list[index].split(splitter)) ? list[index] = list[index].split(splitter) : null;
        (list[index].constructor === Array) ? traverseList(list[index], splitter, 0) : null;
        (list.constructor === Array) ? traverseList(list, splitter, index+1) : null;    
    }
}

flatten = function(arr) {
    return arr.reduce(function(acc, val) {
        return acc.concat(val.constructor === Array ? flatten(val) : val);
    },[]);
}

var stringToSplit = "people and_other/things";
var splitList = [" ", "_", "/"];
splitString(stringToSplit, splitList);

Example above returns: ["people", "and", "other", "things"]

Note: flatten function was taken from Rosetta Code

Answer

You could just lump all the characters you want to use as separators either singularly or collectively into a regular expression and pass them to the split function. For instance you could write:

console.log( "dasdnk asd, (naks) :d skldma".split(/[ \(,\)]+/) );

And the output will be:

["dasdnk", "asd", "naks", ":d", "skldma"]
Answer

Perhaps you should do some sort of string replace to turn one separator into the other separator so you then only have one separator to deal with in your split.

Answer

Hi for example if you have split and replace in String 07:05:45PM

var hour = time.replace("PM", "").split(":");

Result

[ '07', '05', '45' ]
Answer
a = "a=b,c:d"

array = ['=',',',':'];

for(i=0; i< array.length; i++){ a= a.split(array[i]).join(); }

this will return the string without a special charecter.

Answer

Here is a new way to achieving same in ES6:

function SplitByString(source, splitBy) {
  var splitter = splitBy.split('');
  splitter.push([source]); //Push initial value

  return splitter.reduceRight(function(accumulator, curValue) {
    var k = [];
    accumulator.forEach(v => k = [...k, ...v.split(curValue)]);
    return k;
  });
}

var source = "abc,def#hijk*lmn,opq#rst*uvw,xyz";
var splitBy = ",*#";
console.log(SplitByString(source, splitBy));

Please note in this function:

  • No Regex involved
  • Returns splitted value in same order as it appears in source

Result of above code would be:

enter image description here

Answer

I think it's easier if you specify what you wanna leave, instead of what you wanna remove.

As if you wanna have only English words, you can use something like this:

text.match(/[a-z'\-]+/gi);

Examples (run snippet):

var R=[/[a-z'\-]+/gi,/[a-z'\-\s]+/gi];
var s=document.getElementById('s');
for(var i=0;i<R.length;i++)
 {
  var o=document.createElement('option');
  o.innerText=R[i]+'';
  o.value=i;
  s.appendChild(o);
 }
var t=document.getElementById('t');
var r=document.getElementById('r');

s.onchange=function()
 {
  r.innerHTML='';
  var x=s.value;
  if((x>=0)&&(x<R.length))
   x=t.value.match(R[x]);
  for(i=0;i<x.length;i++)
   {
    var li=document.createElement('li');
    li.innerText=x[i];
    r.appendChild(li);
   }
 }
<textarea id="t" style="width:70%;height:12em">even, test; spider-man

But saying o'er what I have said before:
My child is yet a stranger in the world;
She hath not seen the change of fourteen years,
Let two more summers wither in their pride,
Ere we may think her ripe to be a bride.

—Shakespeare, William. The Tragedy of Romeo and Juliet</textarea>

<p><select id="s">
 <option selected>Select a regular expression</option>
 <!-- option value="1">/[a-z'\-]+/gi</option>
 <option value="2">/[a-z'\-\s]+/gi</option -->
</select></p>
 <ol id="r" style="display:block;width:auto;border:1px inner;overflow:scroll;height:8em;max-height:10em;"></ol>
</div>

Answer

Starting from @stephen-sweriduk solution (that was the more interesting to me!), I have slightly modified it to make more generic and reusable:

/**
 * Adapted from: http://stackoverflow.com/questions/650022/how-do-i-split-a-string-with-multiple-separators-in-javascript
*/
var StringUtils = {

  /**
   * Flatten a list of strings
   * http://rosettacode.org/wiki/Flatten_a_list
   */
  flatten : function(arr) {
    var self=this;
    return arr.reduce(function(acc, val) {
        return acc.concat(val.constructor === Array ? self.flatten(val) : val);
    },[]);
  },

  /**
   * Recursively Traverse a list and apply a function to each item
   * @param list array
   * @param expression Expression to use in func
   * @param func function of (item,expression) to apply expression to item
   *
   */
  traverseListFunc : function(list, expression, index, func) {
    var self=this;
    if(list[index]) {
        if((list.constructor !== String) && (list[index].constructor === String))
            (list[index] != func(list[index], expression)) ? list[index] = func(list[index], expression) : null;
        (list[index].constructor === Array) ? self.traverseListFunc(list[index], expression, 0, func) : null;
        (list.constructor === Array) ? self.traverseListFunc(list, expression, index+1, func) : null;
    }
  },

  /**
   * Recursively map function to string
   * @param string
   * @param expression Expression to apply to func
   * @param function of (item, expressions[i])
   */
  mapFuncToString : function(string, expressions, func) {
    var self=this;
    var list = [string];
    for(var i=0, len=expressions.length; i<len; i++) {
        self.traverseListFunc(list, expressions[i], 0, func);
    }
    return self.flatten(list);
  },

  /**
   * Split a string
   * @param splitters Array of characters to apply the split
   */
  splitString : function(string, splitters) {
    return this.mapFuncToString(string, splitters, function(item, expression) {
      return item.split(expression);
    })
  },

}

and then

var stringToSplit = "people and_other/things";
var splitList = [" ", "_", "/"];
var splittedString=StringUtils.splitString(stringToSplit, splitList);
console.log(splitList, stringToSplit, splittedString);

that gives back as the original:

[ ' ', '_', '/' ] 'people and_other/things' [ 'people', 'and', 'other', 'things' ]
Answer

An easy way to do this is to process each character of the string with each delimiter and build an array of the splits:

splix = function ()
{
  u = [].slice.call(arguments); v = u.slice(1); u = u[0]; w = [u]; x = 0;

  for (i = 0; i < u.length; ++i)
  {
    for (j = 0; j < v.length; ++j)
    {
      if (u.slice(i, i + v[j].length) == v[j])
      {
        y = w[x].split(v[j]); w[x] = y[0]; w[++x] = y[1];
      };
    };
  };

  return w;
};

console.logg = function ()
{
  document.body.innerHTML += "<br>" + [].slice.call(arguments).join();
}

splix = function() {
  u = [].slice.call(arguments);
  v = u.slice(1);
  u = u[0];
  w = [u];
  x = 0;
  console.logg("Processing: <code>" + JSON.stringify(w) + "</code>");

  for (i = 0; i < u.length; ++i) {
    for (j = 0; j < v.length; ++j) {
      console.logg("Processing: <code>[\x22" + u.slice(i, i + v[j].length) + "\x22, \x22" + v[j] + "\x22]</code>");
      if (u.slice(i, i + v[j].length) == v[j]) {
        y = w[x].split(v[j]);
        w[x] = y[0];
        w[++x] = y[1];
        console.logg("Currently processed: " + JSON.stringify(w) + "\n");
      };
    };
  };

  console.logg("Return: <code>" + JSON.stringify(w) + "</code>");
};

setTimeout(function() {
  console.clear();
  splix("1.23--4", ".", "--");
}, 250);
@import url("http://fonts.googleapis.com/css?family=Roboto");

body {font: 20px Roboto;}

Usage: splix(string, delimiters...)

Example: splix("1.23--4", ".", "--")

Returns: ["1", "23", "4"]

Answer

I will provide a classic implementation for a such function. The code works in almost all versions of JavaScript and is somehow optimum.

  • It doesn't uses regex, which is hard to maintain
  • It doesn't uses new features of JavaScript
  • It doesn't uses multiple .split() .join() invocation which require more computer memory

Just pure code:

var text = "Create a function, that will return an array (of string), with the words inside the text";

println(getWords(text));

function getWords(text)
{
    let startWord = -1;
    let ar = [];

    for(let i = 0; i <= text.length; i++)
    {
        let c = i < text.length ? text[i] : " ";

        if (!isSeparator(c) && startWord < 0)
        {
            startWord = i;
        }

        if (isSeparator(c) && startWord >= 0)
        {
            let word = text.substring(startWord, i);
            ar.push(word);

            startWord = -1;
        }
    }

    return ar;
}

function isSeparator(c)
{
    var separators = [" ", "\t", "\n", "\r", ",", ";", ".", "!", "?", "(", ")"];
    return separators.includes(c);
}

You can see the code running in playground: https://codeguppy.com/code.html?IJI0E4OGnkyTZnoszAzf

Answer

I find that one of the main reasons I need this is to split file paths on both / and \. It's a bit of a tricky regex so I'll post it here for reference:

var splitFilePath = filePath.split(/[\/\\]/);
Answer

I don't know the performance of RegEx, but here is another alternative for RegEx leverages native HashSet and works in O( max(str.length, delimeter.length) ) complexity instead:

var multiSplit = function(str,delimiter){
    if (!(delimiter instanceof Array))
        return str.split(delimiter);
    if (!delimiter || delimiter.length == 0)
        return [str];
    var hashSet = new Set(delimiter);
    if (hashSet.has(""))
        return str.split("");
    var lastIndex = 0;
    var result = [];
    for(var i = 0;i<str.length;i++){
        if (hashSet.has(str[i])){
            result.push(str.substring(lastIndex,i));
            lastIndex = i+1;
        }
    }
    result.push(str.substring(lastIndex));
    return result;
}

multiSplit('1,2,3.4.5.6 7 8 9',[',','.',' ']);
// Output: ["1", "2", "3", "4", "5", "6", "7", "8", "9"]

multiSplit('1,2,3.4.5.6 7 8 9',' ');
// Output: ["1,2,3.4.5.6", "7", "8", "9"]
Answer

Not the best way but works to Split with Multiple and Different seperators/delimiters

html

<button onclick="myFunction()">Split with Multiple and Different seperators/delimiters</button>
<p id="demo"></p>

javascript

<script>
function myFunction() {

var str = "How : are | you doing : today?";
var res = str.split(' | ');

var str2 = '';
var i;
for (i = 0; i < res.length; i++) { 
    str2 += res[i];

    if (i != res.length-1) {
      str2 += ",";
    }
}
var res2 = str2.split(' : ');

//you can add countless options (with or without space)

document.getElementById("demo").innerHTML = res2;
</script>
Answer

My refactor of @Brian answer

var string = 'and this is some kind of information and another text and simple and some egample or red or text';
var separators = ['and', 'or'];

function splitMulti(str, separators){
            var tempChar = 't3mp'; //prevent short text separator in split down
            
            //split by regex e.g. \b(or|and)\b
            var re = new RegExp('\\b(' + separators.join('|') + ')\\b' , "g");
            str = str.replace(re, tempChar).split(tempChar);
            
            // trim & remove empty
            return str.map(el => el.trim()).filter(el => el.length > 0);
}

console.log(splitMulti(string, separators))

Answer

I use regexp:

str =  'Write a program that extracts from a given text all palindromes, e.g. "ABBA", "lamal", "exe".';

var strNew = str.match(/\w+/g);

// Output: ["Write", "a", "program", "that", "extracts", "from", "a", "given", "text", "all", "palindromes", "e", "g", "ABBA", "lamal", "exe"]

Tags

Recent Questions

Top Questions

Home Tags Terms of Service Privacy Policy DMCA Contact Us

©2020 All rights reserved.