How can I use a cursor.forEach() in MongoDB using Node.js?

Question

I have a huge collection of documents in my DB and I\'m wondering how can I run through all the documents and update them, each document with a different value.

Answer 1

var MongoClient = require('mongodb').MongoClient,
    assert = require('assert');

MongoClient.connect('mongodb://localhost:27017/crunchbase', function(err, db) {

    assert.equal(err, null);
    console.log("Successfully connected to MongoDB.");

    var query = {
        "category_code": "biotech"
    };

    db.collection('companies').find(query).toArray(function(err, docs) {

        assert.equal(err, null);
        assert.notEqual(docs.length, 0);

        docs.forEach(function(doc) {
            console.log(doc.name + " is a " + doc.category_code + " company.");
        });

        db.close();

    });

});

Notice that the call .toArray is making the application to fetch the entire dataset.

var MongoClient = require('mongodb').MongoClient,
    assert = require('assert');

MongoClient.connect('mongodb://localhost:27017/crunchbase', function(err, db) {

    assert.equal(err, null);
    console.log("Successfully connected to MongoDB.");

    var query = {
        "category_code": "biotech"
    };

    var cursor = db.collection('companies').find(query);

    function(doc) {
        cursor.forEach(
                console.log(doc.name + " is a " + doc.category_code + " company.");
            },
            function(err) {
                assert.equal(err, null);
                return db.close();
            }
    );
});

Notice that the cursor returned by the find() is assigned to var cursor. With this approach, instead of fetching all data in memory and consuming data at once, we're streaming the data to our application. find() can create a cursor immediately because it doesn't actually make a request to the database until we try to use some of the documents it will provide. The point of cursor is to describe our query. The 2nd parameter to cursor.forEach shows what to do when the driver gets exhausted or an error occurs.

In the initial version of the above code, it was toArray() which forced the database call. It meant we needed ALL the documents and wanted them to be in an array.

Also, MongoDB returns data in batch format. The image below shows, requests from cursors (from application) to MongoDB

forEach is better than toArray because we can process documents as they come in until we reach the end. Contrast it with toArray - where we wait for ALL the documents to be retrieved and the entire array is built. This means we're not getting any advantage from the fact that the driver and the database system are working together to batch results to your application. Batching is meant to provide efficiency in terms of memory overhead and the execution time. Take advantage of it, if you can in your application.

Answer 2

Leonid's answer is great, but I want to reinforce the importance of using async/promises and to give a different solution with a promises example.

The simplest solution to this problem is to loop forEach document and call an update. Usually, you don't need close the db connection after each request, but if you do need to close the connection, be careful. You must just close it if you are sure that all updates have finished executing.

A common mistake here is to call db.close() after all updates are dispatched without knowing if they have completed. If you do that, you'll get errors.

Wrong implementation:

collection.find(query).each(function(err, doc) {
  if (err) throw err;

  if (doc) {
    collection.update(query, update, function(err, updated) {
      // handle
    });
  } 
  else {
    db.close(); // if there is any pending update, it will throw an error there
  }
});

However, as db.close() is also an async operation (its signature have a callback option) you may be lucky and this code can finish without errors. It may work only when you need to update just a few docs in a small collection (so, don't try).

Correct solution:

As a solution with async was already proposed by Leonid, below follows a solution using Q promises.

var Q = require('q');
var client = require('mongodb').MongoClient;

var url = 'mongodb://localhost:27017/test';

client.connect(url, function(err, db) {
  if (err) throw err;

  var promises = [];
  var query = {}; // select all docs
  var collection = db.collection('demo');
  var cursor = collection.find(query);

  // read all docs
  cursor.each(function(err, doc) {
    if (err) throw err;

    if (doc) {

      // create a promise to update the doc
      var query = doc;
      var update = { $set: {hi: 'there'} };

      var promise = 
        Q.npost(collection, 'update', [query, update])
        .then(function(updated){ 
          console.log('Updated: ' + updated); 
        });

      promises.push(promise);
    } else {

      // close the connection after executing all promises
      Q.all(promises)
      .then(function() {
        if (cursor.isClosed()) {
          console.log('all items have been processed');
          db.close();
        }
      })
      .fail(console.error);
    }
  });
});

Answer 3

You can now use (in an async function, of course):

for await (let doc of collection.find(query)) {
  await updateDoc(doc);
}

// all done

which nicely serializes all updates.

Answer 4

And here is an example of using a Mongoose cursor async with promises:

new Promise(function (resolve, reject) {
  collection.find(query).cursor()
    .on('data', function(doc) {
      // ...
    })
    .on('error', reject)
    .on('end', resolve);
})
.then(function () {
  // ...
});

Reference:

• Mongoose cursors
• Streams and promises