NodeJS - Parallel Tasking - reading multiple files at once and counting word totals

node_parallel_tasking.js

var fs = require('fs'),
	completedTasks = 0,
	tasks = [],
	wordCounts = {},
	filesDir = './text';

function checkIfComplete(){
	completedTasks++;
	if(completedTasks == tasks.length){
		for(var index in wordCounts){
			console.log(index + ': ' + wordCounts[index]);
		}
	}
};

function countWordsInText(text) {
	var words = text
	.toString()
	.toLowerCase()
	.split(/\W+/)
	.sort();
	for(var index in words) {
		var word = words[index];
		if (word) {
			wordCounts[word] = (wordCounts[word]) ? wordCounts[word] + 1 : 1;
		}
	}
};

fs.readdir(filesDir, function(err, files){
	if(err) throw err;

	for(var index in files){
		var task = (function(file){
			return function(){
				fs.readFile(file, function(err, text){
					if(err) throw err;

					countWordsInText(text);
					checkIfComplete();
				});
			};
		})(filesDir + '/' + files[index]);

		tasks.push(task);
	};

	for(var task in tasks){
		tasks[task]();
	}
});

Why did you use self-invoking function and then call it again within another for loop?

Precicely, why this:

fs.readdir(filesDir, function(err, files){
	if(err) throw err;

	for(var index in files){
		var task = (function(file){
			return function(){
				fs.readFile(file, function(err, text){
					if(err) throw err;

					countWordsInText(text);
					checkIfComplete();
				});
			};
		})(filesDir + '/' + files[index]);

		tasks.push(task);
	};

	for(var task in tasks){
		tasks[task]();
	}
});

and not this:

fs.readdir(filesDir, function(err, files) {
	if (err) throw err;
	for (var index in files) {
		tasksCount++; // tasks counter added
		fs.readFile(filesDir + '/' + files[index], function(err, text) {
			if (err) throw err;

			countWordsInText(text);
			checkIfComplete();
		});
	}
});