Split a string by commas but ignore commas within

Question

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.

Answer 1

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 2

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 3

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 4

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 5

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;  
                }  
            }  
            //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 6

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);