node.js - Create a zip file on S3 from files on S3 using Lambda Node

Question

I need to create a Zip file that consists of a selection of files (videos and images) located in my s3 bucket.

The problem at the moment using my code below is that I quickly hit the memory limit on Lambda.

async.eachLimit(files, 10, function(file, next) {
    var params = {
        Bucket: bucket, // bucket name
        Key: file.key
    };
    s3.getObject(params, function(err, data) {
        if (err) {
            console.log('file', file.key);
            console.log('get image files err',err, err.stack); // an error occurred
        } else {
            console.log('file', file.key);
            zip.file(file.key, data.Body);
            next();
        }
    });
}, 
function(err) {
    if (err) {
        console.log('err', err);
    } else {
        console.log('zip', zip);
        content = zip.generateNodeStream({
            type: 'nodebuffer',
            streamFiles:true
        });
        var params = {
            Bucket: bucket, // name of dest bucket
            Key: 'zipped/images.zip',
            Body: content
        };
        s3.upload(params, function(err, data) {
            if (err) {
                console.log('upload zip to s3 err',err, err.stack); // an error occurred
            } else {
                console.log(data); // successful response
            }
        });
    }
});

• Is this possible using Lambda, or should I look at a different approach?

• Is it possible to write to a compressed zip file on the fly, therefore eliminating the memory issue somewhat, or do I need to have the files collected before compression?

Any help would be much appreciated.

Answer 1

Okay, I got to do this today and it works. Direct Buffer to Stream, no disk involved. So memory or disk limitation won't be an issue here:

'use strict';

const AWS = require("aws-sdk");
AWS.config.update( { region: "eu-west-1" } );
const s3 = new AWS.S3( { apiVersion: '2006-03-01'} );

const   _archiver = require('archiver');

//This returns us a stream.. consider it as a real pipe sending fluid to S3 bucket.. Don't forget it
const streamTo = (_bucket, _key) => {
var stream = require('stream');
var _pass = new stream.PassThrough();
s3.upload( { Bucket: _bucket, Key: _key, Body: _pass }, (_err, _data) => { /*...Handle Errors Here*/ } );
return _pass;
};
      
exports.handler = async (_req, _ctx, _cb) => {
var _keys = ['list of your file keys in s3'];

    var _list = await Promise.all(_keys.map(_key => new Promise((_resolve, _reject) => {
            s3.getObject({Bucket:'bucket-name', Key:_key})
                .then(_data => _resolve( { data: _data.Body, name: `${_key.split('/').pop()}` } ));
        }
    ))).catch(_err => { throw new Error(_err) } );

    await new Promise((_resolve, _reject) => { 
        var _myStream = streamTo('bucket-name', 'fileName.zip');//Now we instantiate that pipe...
        var _archive = _archiver('zip');
        _archive.on('error', err => { throw new Error(err); } );
        
        //Your promise gets resolved when the fluid stops running... so that's when you get to close and resolve
        _myStream.on('close', _resolve);
        _myStream.on('end', _resolve);
        _myStream.on('error', _reject);
        
        _archive.pipe(_myStream);//Pass that pipe to _archive so it can push the fluid straigh down to S3 bucket
        _list.forEach(_itm => _archive.append(_itm.data, { name: _itm.name } ) );//And then we start adding files to it
        _archive.finalize();//Tell is, that's all we want to add. Then when it finishes, the promise will resolve in one of those events up there
    }).catch(_err => { throw new Error(_err) } );
    
    _cb(null, { } );//Handle response back to server
};