Split a string by commas but ignore commas within double-quotes using Javascript

I'm looking for [a, b, c, "d, e, f", g, h]to turn into an array of 6 elements: a, b, c, "d,e,f", g, h. I'm a bit of a noob with RegEx so any help is great. I'm trying to do this through Javascript. This is what I have so far:

str = str.split(/,+|"[^"]+"/g); 

But right now it's splitting out everything that's in the double-quotes, which is incorrect. Thanks for any help.

Edit: Okay sorry I worded this question really poorly. I'm being given a string not an array.

var str = 'a, b, c, "d, e, f", g, h';

And I want to turn that into an array using something like the "split" function.

Answers:

Answer

Here's what I would do.

var str = 'a, b, c, "d, e, f", g, h';
var arr = str.match(/(".*?"|[^",\s]+)(?=\s*,|\s*$)/g);
/* will match:

    (
        ".*?"       double quotes + anything but double quotes + double quotes
        |           OR
        [^",\s]+    1 or more characters excl. double quotes, comma or spaces of any kind
    )
    (?=             FOLLOWED BY
        \s*,        0 or more empty spaces and a comma
        |           OR
        \s*$        0 or more empty spaces and nothing else (end of string)
    )

*/
arr = arr || [];
// this will prevent JS from throwing an error in
// the below loop when there are no matches
for (var i = 0; i < arr.length; i++) console.log('arr['+i+'] =',arr[i]);
Answer

Here is a JavaScript function to do it:

function splitCSVButIgnoreCommasInDoublequotes(str) {  
    //split the str first  
    //then merge the elments between two double quotes  
    var delimiter = ',';  
    var quotes = '"';  
    var elements = str.split(delimiter);  
    var newElements = [];  
    for (var i = 0; i < elements.length; ++i) {  
        if (elements[i].indexOf(quotes) >= 0) {//the left double quotes is found  
            var indexOfRightQuotes = -1;  
            var tmp = elements[i];  
            //find the right double quotes  
            for (var j = i + 1; j < elements.length; ++j) {  
                if (elements[j].indexOf(quotes) >= 0) {  
                    indexOfRightQuotes = j; 
                    break;
                }  
            }  
            //found the right double quotes  
            //merge all the elements between double quotes  
            if (-1 != indexOfRightQuotes) {   
                for (var j = i + 1; j <= indexOfRightQuotes; ++j) {  
                    tmp = tmp + delimiter + elements[j];  
                }  
                newElements.push(tmp);  
                i = indexOfRightQuotes;  
            }  
            else { //right double quotes is not found  
                newElements.push(elements[i]);  
            }  
        }  
        else {//no left double quotes is found  
            newElements.push(elements[i]);  
        }  
    }  

    return newElements;  
}  
Answer

This works well for me. (I used semicolons so the alert message would show the difference between commas added when turning the array into a string and the actual captured values.)

var str = 'a; b; c; "d; e; f"; g; h; "i"';
var array = str.match(/("[^"]*")|[^;]+/g); 
alert(array);
Answer

Here's a non-regex one that assumes doublequotes will come in pairs:

function splitCsv(str) {
  return str.split(',').reduce((accum,curr)=>{
    if(accum.isConcatting) {
      accum.soFar[accum.soFar.length-1] += ','+curr
    } else {
      accum.soFar.push(curr)
    }
    if(curr.split('"').length % 2 == 0) {
      accum.isConcatting= !accum.isConcatting
    }
    return accum;
  },{soFar:[],isConcatting:false}).soFar
}

console.log(splitCsv('asdf,"a,d",fdsa'),' should be ',['asdf','"a,d"','fdsa'])
console.log(splitCsv(',asdf,,fds,'),' should be ',['','asdf','','fds',''])
console.log(splitCsv('asdf,"a,,,d",fdsa'),' should be ',['asdf','"a,,,d"','fdsa'])

Answer

regex: /,(?=(?:(?:[^"]*"){2})*[^"]*$)/

const input_line = '"2C95699FFC68","201 S BOULEVARDRICHMOND, VA 23220","8299600062754882","2018-09-23"'

let my_split = input_line.split(/,(?=(?:(?:[^"]*"){2})*[^"]*$)/)[4]

Output: 
my_split[0]: "2C95699FFC68", 
my_split[1]: "201 S BOULEVARDRICHMOND, VA 23220", 
my_split[2]: "8299600062754882", 
my_split[3]: "2018-09-23"

Reference following link for an explanation: regexr.com/44u6o

Answer

Something like a stack should do the trick. Here I vaguely use marker boolean as stack (just getting my purpose served with it).

var str = "a,b,c,blah\"d,=,f\"blah,\"g,h,";
var getAttributes = function(str){
  var result = [];
  var strBuf = '';
  var start = 0 ;
  var marker = false;
  for (var i = 0; i< str.length; i++){

    if (str[i] === '"'){
      marker = !marker;
    }
    if (str[i] === ',' && !marker){
      result.push(str.substr(start, i - start));
      start = i+1;
    }
  }
  if (start <= str.length){
    result.push(str.substr(start, i - start));
  }
  return result;
};

console.log(getAttributes(str));
Answer

jsfiddle setting image code output image

The code works if your input string in the format of stringTocompare. Run the code on https://jsfiddle.net/ to see output for fiddlejs setting. Please refer to the screenshot. You can either use split function for the same for the code below it and tweak the code according to you need. Remove the bold or word with in ** from the code if you dont want to have comma after split attach=attach**+","**+actualString[t+1].

var stringTocompare='"Manufacturer","12345","6001","00",,"Calfe,eto,lin","Calfe,edin","4","20","10","07/01/2018","01/01/2006",,,,,,,,"03/31/2004"';

console.log(stringTocompare);

var actualString=stringTocompare.split(',');
console.log("Before");
for(var i=0;i<actualString.length;i++){
console.log(actualString[i]);
}
//var actualString=stringTocompare.split(/,(?=(?:(?:[^"]*"){2})*[^"]*$)/);
for(var i=0;i<actualString.length;i++){
var flag=0;
var x=actualString[i];
if(x!==null)
{
if(x[0]=='"' && x[x.length-1]!=='"'){
   var p=0;
   var t=i;
   var b=i;
   for(var k=i;k<actualString.length;k++){
   var y=actualString[k];
        if(y[y.length-1]!=='"'){        
        p++;
        }
        if(y[y.length-1]=='"'){

                flag=1;
        }
        if(flag==1)
        break;
   }
   var attach=actualString[t];
for(var s=p;s>0;s--){

  attach=attach+","+actualString[t+1];
  t++;
}
actualString[i]=attach;
actualString.splice(b+1,p);
}
}


}
console.log("After");
for(var i=0;i<actualString.length;i++){
console.log(actualString[i]);
}




  [1]: https://i.stack.imgur.com/3FcxM.png
Answer

This takes a csv file one line at a time and spits back an array with commas inside speech marks intact. if there are no speech marks detected it just .split(",")s as normal... could probs replace that second loop with something but it does the job as is

function parseCSVLine(str){
    if(str.indexOf("\"")>-1){
        var aInputSplit = str.split(",");
        var aOutput = [];
        var iMatch = 0;
        //var adding = 0;
        for(var i=0;i<aInputSplit.length;i++){
            if(aInputSplit[i].indexOf("\"")>-1){
                var sWithCommas = aInputSplit[i];
                for(var z=i;z<aInputSplit.length;z++){
                    if(z !== i && aInputSplit[z].indexOf("\"") === -1){
                        sWithCommas+= ","+aInputSplit[z];
                    }else if(z !== i && aInputSplit[z].indexOf("\"") > -1){
                        sWithCommas+= ","+aInputSplit[z];
                        sWithCommas.replace(new RegExp("\"", 'g'), "");
                        aOutput.push(sWithCommas);
                        i=z;
                        z=aInputSplit.length+1;
                        iMatch++;
                    }
                    if(z === aInputSplit.length-1){
                        if(iMatch === 0){
                            aOutput.push(aInputSplit[z]);
                        }                  
                        iMatch = 0;
                    }
                }
            }else{
                aOutput.push(aInputSplit[i]);
            }
        }
        return aOutput
    }else{
        return str.split(",")
    }
}
Answer

Assuming your string really looks like '[a, b, c, "d, e, f", g, h]', I believe this would be 'an acceptable use case for eval():

myString = 'var myArr ' + myString;
eval(myString);

console.log(myArr); // will now be an array of elements: a, b, c, "d, e, f", g, h

Edit: As Rocket pointed out, strict mode removes eval's ability to inject variables into the local scope, meaning you'd want to do this:

var myArr = eval(myString);
Answer

I've had similar issues with this, and I've found no good .net solution so went DIY. NOTE: This was also used to reply to

Splitting comma separated string, ignore commas in quotes, but allow strings with one double quotation

but seems more applicable here (but useful over there)

In my application I'm parsing a csv so my split credential is ",". this method I suppose only works for where you have a single char split argument.

So, I've written a function that ignores commas within double quotes. it does it by converting the input string into a character array and parsing char by char

public static string[] Splitter_IgnoreQuotes(string stringToSplit)
    {   
        char[] CharsOfData = stringToSplit.ToCharArray();
        //enter your expected array size here or alloc.
        string[] dataArray = new string[37];
        int arrayIndex = 0;
        bool DoubleQuotesJustSeen = false;          
        foreach (char theChar in CharsOfData)
        {
            //did we just see double quotes, and no command? dont split then. you could make ',' a variable for your split parameters I'm working with a csv.
            if ((theChar != ',' || DoubleQuotesJustSeen) && theChar != '"')
            {
                dataArray[arrayIndex] = dataArray[arrayIndex] + theChar;
            }
            else if (theChar == '"')
            {
                if (DoubleQuotesJustSeen)
                {
                    DoubleQuotesJustSeen = false;
                }
                else
                {
                    DoubleQuotesJustSeen = true;
                }
            }
            else if (theChar == ',' && !DoubleQuotesJustSeen)
            {
                arrayIndex++;
            }
        }
        return dataArray;
    }

This function, to my application taste also ignores ("") in any input as these are unneeded and present in my input.

Answer

Here's the regex we're using to extract valid arguments from a comma-separated argument list, supporting double-quoted arguments. It works for the outlined edge cases. E.g.

  • doesn't include quotes in the matches
  • works with white spaces in matches
  • works with empty fields

(?<=")[^"]+?(?="(?:\s*?,|\s*?$))|(?<=(?:^|,)\s*?)(?:[^,"\s][^,"]*[^,"\s])|(?:[^,"\s])(?![^"]*?"(?:\s*?,|\s*?$))(?=\s*?(?:,|$))

Proof: https://regex101.com/r/UL8kyy/3/tests

According to our guidelines it avoids non-capturing groups and greedy matching.

I'm sure it can be simplified, I'm open to suggestions / additional test cases.

For anyone interested, the first part matches double-quoted, comma-delimited arguments:

(?<=")[^"]+?(?="(?:\s*?,|\s*?$))

And the second part matches comma-delimited arguments by themselves:

(?<=(?:^|,)\s*?)(?:[^,"\s][^,"]*[^,"\s])|(?:[^,"\s])(?![^"]*?"(?:\s*?,|\s*?$))(?=\s*?(?:,|$))

Answer

I know it's a bit long, but here's my take:

var sample="[a, b, c, \"d, e, f\", g, h]";

var inQuotes = false, items = [], currentItem = '';

for(var i = 0; i < sample.length; i++) {
  if (sample[i] == '"') { 
    inQuotes = !inQuotes; 

    if (!inQuotes) {
      if (currentItem.length) items.push(currentItem);
      currentItem = '';
    }

    continue; 
  }

  if ((/^[\"\[\]\,\s]$/gi).test(sample[i]) && !inQuotes) {
    if (currentItem.length) items.push(currentItem);
    currentItem = '';
    continue;
  }

  currentItem += sample[i];
}

if (currentItem.length) items.push(currentItem);

console.log(items);

As a side note, it will work both with, and without the braces in the start and end.

Answer

I almost liked the accepted answer, but it didn't parse the space correctly, and/or it left the double quotes untrimmed, so here is my function:

    /**
     * Splits the given string into components, and returns the components array.
     * Each component must be separated by a comma.
     * If the component contains one or more comma(s), it must be wrapped with double quotes.
     * The double quote must not be used inside components (replace it with a special string like __double__quotes__ for instance, then transform it again into double quotes later...).
     *
     * https://stackoverflow.com/questions/11456850/split-a-string-by-commas-but-ignore-commas-within-double-quotes-using-javascript
     */
    function splitComponentsByComma(str){
        var ret = [];
        var arr = str.match(/(".*?"|[^",]+)(?=\s*,|\s*$)/g);
        for (let i in arr) {
            let element = arr[i];
            if ('"' === element[0]) {
                element = element.substr(1, element.length - 2);
            } else {
                element = arr[i].trim();
            }
            ret.push(element);
        }
        return ret;
    }
    console.log(splitComponentsByComma('Hello World, b, c, "d, e, f", c')); // [ 'Hello World', 'b', 'c', 'd, e, f', 'c' ]

Tags

Recent Questions

Top Questions

Home Tags Terms of Service Privacy Policy DMCA Contact Us

©2020 All rights reserved.