how to turn a Persian (Farsi) paragraph into its list of words in Javascript

Question

I am trying to make an object out of a paragraph that shows words with their frequencies.

var pattern = /\w+/g,
//the farsi paragraph
    string = "من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم",
    matchedWords = string.match( pattern );

/* The Array.prototype.reduce method assists us in producing a single value from an
   array. In this case, we're going to use it to output an object with results. */
var counts = matchedWords.reduce(function ( stats, word ) {

    /* `stats` is the object that we'll be building up over time.
       `word` is each individual entry in the `matchedWords` array */
    if ( stats.hasOwnProperty( word ) ) {
        /* `stats` already has an entry for the current `word`.
           As a result, let's increment the count for that `word`. */
        stats[ word ] = stats[ word ] + 1;
    } else {
        /* `stats` does not yet have an entry for the current `word`.
           As a result, let's add a new entry, and set count to 1. */
        stats[ word ] = 1;
    }

    /* Because we are building up `stats` over numerous iterations,
       we need to return it for the next pass to modify it. */
    return stats;

}, {})

var dict = []; // create an empty array
// this for loop makes a dictionary for you
for (i in counts){
dict.push({'text':i, "size": counts[i]});


};

/* lets print and see if you can solve your problem */

console.log( dict);

the code originally worked out for an English paragraph. However I need to use it for a Farsi one. I know that it should be something else instead of "/\w+/g" in:

var pattern = /\w+/g,

but I don't know what.

Answer 1

In your regex use the variable for "any character but whitespace" that is \S. Edit: whitespace is considered a newline, a tab and a space)

var pattern = /\S+/g,
//the farsi paragraph
    string = "من امروز در مورد مهر خروج مشمولین اطلاعات جدیدی از سفارت ایران در مالزی گرفتم",
    matchedWords = string.match( pattern );

/* The Array.prototype.reduce method assists us in producing a single value from an
   array. In this case, we're going to use it to output an object with results. */
var counts = matchedWords.reduce(function ( stats, word ) {

    /* `stats` is the object that we'll be building up over time.
       `word` is each individual entry in the `matchedWords` array */
    if ( stats.hasOwnProperty( word ) ) {
        /* `stats` already has an entry for the current `word`.
           As a result, let's increment the count for that `word`. */
        stats[ word ] = stats[ word ] + 1;
    } else {
        /* `stats` does not yet have an entry for the current `word`.
           As a result, let's add a new entry, and set count to 1. */
        stats[ word ] = 1;
    }

    /* Because we are building up `stats` over numerous iterations,
       we need to return it for the next pass to modify it. */
    return stats;

}, {})

var dict = []; // create an empty array
// this for loop makes a dictionary for you
for (i in counts){
dict.push({'text':i, "size": counts[i]});


};

/* lets print and see if you can solve your problem */

console.log( dict);