Parse output of spawned node.js child process line by line

Question

I have a PhantomJS/CasperJS script which I'm running from within a node.js script using process.spawn() . Since CasperJS doesn't support require() ing modules, I'm trying to print commands from CasperJS to stdout and then read them in from my node.js script using spawn.stdout.on('data', function(data) {}); in order to do things like add objects to redis/mongoose (convoluted, yes, but seems more straightforward than setting up a web service for this...) The CasperJS script executes a series of commands and creates, say, 20 screenshots which need to be added to my database.

However, I can't figure out how to break the data variable (a Buffer ?) into lines... I've tried converting it to a string and then doing a replace, I've tried doing spawn.stdout.setEncoding('utf8'); but nothing seems to work...

Here is what I have right now

var spawn = require('child_process').spawn;

var bin = "casperjs"
//googlelinks.js is the example given at http://casperjs.org/#quickstart
var args = ['scripts/googlelinks.js'];
var cspr = spawn(bin, args);

//cspr.stdout.setEncoding('utf8');
cspr.stdout.on('data', function (data) {
    var buff = new Buffer(data);
    console.log("foo: " + buff.toString('utf8'));
});

cspr.stderr.on('data', function (data) {
    data += '';
    console.log(data.replace("\n", "\nstderr: "));
});

cspr.on('exit', function (code) {
    console.log('child process exited with code ' + code);
    process.exit(code);
});

https://gist.github.com/2131204

Answer 1

Try this:

cspr.stdout.setEncoding('utf8');
cspr.stdout.on('data', function(data) {
  var str = data.toString(), lines = str.split(/(\r?\n)/g);
  for (var i=0; i<lines.length; i++) {
    // Process the line, noting it might be incomplete.
  }
});

Note that the "data" event might not necessarily break evenly between lines of output, so a single line might span multiple data events.

Answer 2

I've actually written a Node library for exactly this purpose, it's called stream-splitter and you can find it on Github: samcday/stream-splitter .

The library provides a special Stream you can pipe your casper stdout into, along with a delimiter (in your case, \\n), and it will emit neat token events, one for each line it has split out from the input Stream . The internal implementation for this is very simple, and delegates most of the magic to substack/node-buffers which means there's no unnecessary Buffer allocations/copies.

Answer 3

I found a nicer way to do this with just pure node, which seems to work well:

const childProcess = require('child_process');
const readline = require('readline');

const cspr = childProcess.spawn(bin, args);

const rl = readline.createInterface({ input: cspr.stdout });
rl.on('line', line => /* handle line here */)

Answer 4

Adding to maerics' answer, which does not deal properly with cases where only part of a line is fed in a data dump (theirs will give you the first part and the second part of the line individually, as two separate lines.)

var _breakOffFirstLine = /\r?\n/
function filterStdoutDataDumpsToTextLines(callback){ //returns a function that takes chunks of stdin data, aggregates it, and passes lines one by one through to callback, all as soon as it gets them.
    var acc = ''
    return function(data){
        var splitted = data.toString().split(_breakOffFirstLine)
        var inTactLines = splitted.slice(0, splitted.length-1)
        var inTactLines[0] = acc+inTactLines[0] //if there was a partial, unended line in the previous dump, it is completed by the first section.
        acc = splitted[splitted.length-1] //if there is a partial, unended line in this dump, store it to be completed by the next (we assume there will be a terminating newline at some point. This is, generally, a safe assumption.)
        for(var i=0; i<inTactLines.length; ++i){
            callback(inTactLines[i])
        }
    }
}

usage:

process.stdout.on('data', filterStdoutDataDumpsToTextLines(function(line){
    //each time this inner function is called, you will be getting a single, complete line of the stdout ^^
}) )

Answer 5

You can give this a try. It will ignore any empty lines or empty new line breaks.

cspr.stdout.on('data', (data) => {
    data = data.toString().split(/(\r?\n)/g);
    data.forEach((item, index) => {
        if (data[index] !== '\n' && data[index] !== '') {
            console.log(data[index]);
        }
    });
});

Answer 6

Old stuff but still useful...

I have made a custom stream Transform subclass for this purpose.

See https://stackoverflow.com/a/59400367/4861714