user3502786 user3502786 - 3 months ago 177
Node.js Question

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

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

The answer depends on the driver you're using. All MongoDB drivers I know have cursor.forEach() implemented one way or another.

Here are some examples:

node-mongodb-native

collection.find(query).each(function(err, doc) {
  // handle
});

mongojs

db.collection.find(query).forEach(function(err, doc) {
  // handle
});

monk

collection.find(query, { stream: true })
  .each(function(doc){
    // handle doc
  })
  .error(function(err){
    // handle error
  })
  .success(function(){
    // final callback
  });

mongoose

collection.find(query).stream()
  .on('data', function(doc){
    // handle doc
  })
  .on('error', function(err){
    // handle error
  })
  .on('end', function(){
    // final callback
  });

Updating documents inside of .forEach callback

The only problem with updating documents inside of .forEach callback is that you have no idea when all documents are updated.

To solve this problem you should use some asynchronous control flow solution. Here are some options:

Here is an example of using async, using its queue feature:

var q = async.queue(function (doc, callback) {
  // code for your update
  collection.update({
    _id: doc._id
  }, {
    $set: {hi: 'there'}
  }, {
    w: 1
  }, callback);
}, Infinity);

var cursor = collection.find(query);
cursor.each(function(err, doc) {
  if (err) throw err;
  if (doc) q.push(doc); // dispatching doc to async.queue
});

q.drain = function() {
  if (cursor.isClosed()) {
    console.log('all items have been processed');
    db.close();
  }
}
Comments