Node plus MongoDb build and execute query - node.js

I'm using nodejs and mongodb. I'm trying to build a query and execute it so that I can return a json object through this api. When I do the following I get the error:
TypeError: Cannot read property 'exec' of undefined
How should I be setting this up differently.
var mongodb = require('mongodb');
var db = new mongodb.Db('MyDD', new mongodb.Server('localhost', 27017, {}));
exports.findAll = function(req, res) {
const limit = parseInt(req.query.limit);
let query = GetTransactionList(limit)
query.exec(function(err,items){
if (err){
console.log(err);
} else {
res.json(items);
}
})
}
function GetTransactionList(limit){
console.log("GetTransactionList entered with limit: ", limit)
let query;
if (limit){
query = db.collection('transtest').find({},{limit:limit}).sort({postdate: -1})
} else {
query = db.collection('transtest').find()
}
return query
}

you should first import or create GetTransactionList scheme.
but in your example it is not a scheme and does not implement method exec.
its a plain function.

The exec is a helper method of Mongoose defined in mongoose not in mongodb, so in mongodb the find() method return a cursor to the selected documents and you can use toArray() method to returns an array of the documents from the cursor.
Simple Example
db.collection('restaurants').find().toArray(function(err, documents){
documents.forEach(function(doc){
console.log(doc.name);
});
});
In your case
query.toArray(function(err, items){
//assert.equal(err, null);
items.forEach(function(item){
console.log(item);
});
res.json(items);
})
I hope this could help you

Because the find() method returns a cursor, you may want to append the toArray() method of the cursor to return a Promise instead when no callback is passed.
Consider rewriting your code as follows:
exports.findAll = function(req, res) {
const query = GetTransactionList(parseInt(req.query.limit));
query.then(res.json).catch(console.log);
/* Above is equivalent to
query.then(function(items) {
res.json(items);
}).catch(function(err) {
console.log(err);
});
*/
}
function GetTransactionList(limit){
console.log("GetTransactionList entered with limit: ", limit);
const cursor = db.collection('transtest').find({});
return limit ? cursor.sort([['postdate', -1]]).limit(limit).toArray() : cursor.toArray();
}

Related

nodejs mongodb official node package - async function won't return data

I am trying to write a simple function to grab the id of a specific instance based on matching criteria from mongodb using the official node package 'mongodb'.
My function works as I can console log the data but I am unable to return the data to use it as I intended to do as you can see.
const mongo = require('mongodb').MongoClient;
const url = 'mongodb://localhost:27017';
// Function for finding database id of device based on deviceKey, The database is written into
// the code under the const 'db' as is the collection.
async function fetchId(deviceKey) {
const client = await mongo.connect(url, { useNewUrlParser: true });
const db = client.db('telcos');
const collection = db.collection('device');
try {
await collection.find({"deviceKey": deviceKey}).toArray((err, response) => {
if (err) throw err;
console.log(response[0]._id); // << works logs _id
return response[0]._id; // << does nothing... ?
})
} finally {
client.close();
}
}
// # fetchId() USAGE EXAMPLE
//
// fetchId(112233); < include deviceKey to extract id
//
// returns database id of device with deviceKey 112233
// Run test on fetchId() to see if it works
fetchId("112233")
.then(function(id) {
console.dir(id); // << undefined
})
.catch(function(error) {
console.log(error);
});
Why does my test return undefined but my console.log() inside the function works?
It looks like you're combining callback code with async/await code in an odd way. Your function fetchId isn't returning anything at all, which is why you don't see id after fetching.
try {
const response = await collection.find(...).toArray()
return response[0]._id
}...
If we weren't able to await collection.find(...).toArray() and needed to manually convert this from using callbacks to promises, we'd have to do something like:
function fetchId (id) {
// this function returns a promise
return new Promise((resolve, reject) => {
...
collection.find(...).toArray((err, response) => {
// within the callback, returning values doesn't do anything
if (err) return reject(err);
return resolve(response[0]._id);
})
});
}
You are returning a value but handled like a promise is being returned.Please try this code.I had not tested it.
const mongo = require('mongodb').MongoClient;
const url = 'mongodb://localhost:27017';
// Function for finding database id of device based on deviceKey, The database is written into
// the code under the const 'db' as is the collection.
async function fetchId(deviceKey) {
return new Promise((resolve,reject)=>{
const client = await mongo.connect(url, { useNewUrlParser: true });
const db = client.db('telcos');
const collection = db.collection('device');
try {
await collection.find({"deviceKey": deviceKey}).toArray((err, response) => {
if (err) throw err;
console.log(response[0]._id); // << works logs _id
return resolve(response[0]._id); // << does nothing... ?
})
}
catch(error){
return reject(error);
}
finally {
client.close();
}
});
}
// # fetchId() USAGE EXAMPLE
//
// fetchId(112233); < include deviceKey to extract id
//
// returns database id of device with deviceKey 112233
// Run test on fetchId() to see if it works
fetchId("112233")
.then(function(id) {
console.dir(id); // << undefined
})
.catch(function(error) {
console.log(error);
});

Retrieve data from MongoDB and save it to global object in Node.js and Express.js

I'm trying to get data from MongoDB collection and then save it to a global object.Later I need to parse it to HTML template.
Here is my code:
When user log onto his profile: then we need to get his projects and here we call findeprojects() function
usrRouter.route('/profile')
.all(function (req,res,next) {
if(!req.user){
res.redirect('/');
}
next();
})
.get(function (req,res,userObj) {
// var proj = findprojects();
userObj = req.user;
var pro = {};
pro = findprojects(userObj);
res.render('index',{name:userObj.username, email:userObj.email});
//res.sendFile('profile.html',{root:path.join(__dirname,'../public'),},{name:userObj.username});
});
Here is findeprojects function code:
var findprojects = function(obj) {
var usern = obj.username;
mongodb.connect(url,function(err, db){
if(err) throw err;
var collection = db.collection('projects');
//console.log(usern);
collection.find({'pusername':usern});
cursor =db.collection('projects').find({ 'pusername': usern }).toArray(function(err,items){
//console.log(items);
var i;
for(i=0; i<items.length;){
userProjects.createdBy = items[i].pusername;
userProjects.proName = items[i].projectName;
userProjects.proType = items[i].projectType;
userProjects.proDesc = items[i].projectDesc;
//return userProjects;
i = i+1;
}
});
console.log(userProjects);
});
};
I have declared global object at the top like:
userProjects = {
createdBy:'',
proName:'',
proType:'',
proDesc:''
};
But when I console userprojects object after calling the findeprojects() function it displays empty values.
why dont you use mongoose to model your stuff.
its more intuitive and you no need to declare the global object and do the mapping in the for loop that you are doing.
also your approach is a bit wrong in terms of when you iterate through for aren't you overwriting ?
say you have two documents where pusername is abdul.
so in your case you loose first object which will get overwritten by the second one.
i see that you commented out a return statement but even that wont work properly.
from a design point of view your approach is not efficient.
in mongoose you can do:
{
var userProjectSchema = new mongoose.Schema({
createdBy: { type: String }
, proName: String
, proType: String
, proDesc: String
});
// Find a single document by username.
userProjectSchema.findOne({ pusername : 'abdul' }, function(err, resDoc) {
if (err) return console.error(err);
// do your html stuff here
});
// Find all documents.
userProjectSchema.find(function(err, results) {
if (err) return console.error(err);
// do your html stuff here
});
}

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.
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).forEach(function(doc) {
// handle
}, function(err) {
// done or error
});
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:
async
promises (when.js, bluebird)
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();
}
}
Using the mongodb driver, and modern NodeJS with async/await, a good solution is to use next():
const collection = db.collection('things')
const cursor = collection.find({
bla: 42 // find all things where bla is 42
});
let document;
while ((document = await cursor.next())) {
await collection.findOneAndUpdate({
_id: document._id
}, {
$set: {
blu: 43
}
});
}
This results in only one document at a time being required in memory, as opposed to e.g. the accepted answer, where many documents get sucked into memory, before processing of the documents starts. In cases of "huge collections" (as per the question) this may be important.
If documents are large, this can be improved further by using a projection, so that only those fields of documents that are required are fetched from the database.
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.
None of the previous answers mentions batching the updates. That makes them extremely slow 🐌 - tens or hundreds of times slower than a solution using bulkWrite.
Let's say you want to double the value of a field in each document. Here's how to do that fast 💨 and with fixed memory consumption:
// Double the value of the 'foo' field in all documents
let bulkWrites = [];
const bulkDocumentsSize = 100; // how many documents to write at once
let i = 0;
db.collection.find({ ... }).forEach(doc => {
i++;
// Update the document...
doc.foo = doc.foo * 2;
// Add the update to an array of bulk operations to execute later
bulkWrites.push({
replaceOne: {
filter: { _id: doc._id },
replacement: doc,
},
});
// Update the documents and log progress every `bulkDocumentsSize` documents
if (i % bulkDocumentsSize === 0) {
db.collection.bulkWrite(bulkWrites);
bulkWrites = [];
print(`Updated ${i} documents`);
}
});
// Flush the last <100 bulk writes
db.collection.bulkWrite(bulkWrites);
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
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);
}
});
});
The node-mongodb-native now supports a endCallback parameter to cursor.forEach as for one to handle the event AFTER the whole iteration, refer to the official document for details http://mongodb.github.io/node-mongodb-native/2.2/api/Cursor.html#forEach.
Also note that .each is deprecated in the nodejs native driver now.
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.
let's assume that we have the below MongoDB data in place.
Database name: users
Collection name: jobs
===========================
Documents
{ "_id" : ObjectId("1"), "job" : "Security", "name" : "Jack", "age" : 35 }
{ "_id" : ObjectId("2"), "job" : "Development", "name" : "Tito" }
{ "_id" : ObjectId("3"), "job" : "Design", "name" : "Ben", "age" : 45}
{ "_id" : ObjectId("4"), "job" : "Programming", "name" : "John", "age" : 25 }
{ "_id" : ObjectId("5"), "job" : "IT", "name" : "ricko", "age" : 45 }
==========================
This code:
var MongoClient = require('mongodb').MongoClient;
var dbURL = 'mongodb://localhost/users';
MongoClient.connect(dbURL, (err, db) => {
if (err) {
throw err;
} else {
console.log('Connection successful');
var dataBase = db.db();
// loop forEach
dataBase.collection('jobs').find().forEach(function(myDoc){
console.log('There is a job called :'+ myDoc.job +'in Database')})
});
I looked for a solution with good performance and I end up creating a mix of what I found which I think works good:
/**
* This method will read the documents from the cursor in batches and invoke the callback
* for each batch in parallel.
* IT IS VERY RECOMMENDED TO CREATE THE CURSOR TO AN OPTION OF BATCH SIZE THAT WILL MATCH
* THE VALUE OF batchSize. This way the performance benefits are maxed out since
* the mongo instance will send into our process memory the same number of documents
* that we handle in concurrent each time, so no memory space is wasted
* and also the memory usage is limited.
*
* Example of usage:
* const cursor = await collection.aggregate([
{...}, ...],
{
cursor: {batchSize: BATCH_SIZE} // Limiting memory use
});
DbUtil.concurrentCursorBatchProcessing(cursor, BATCH_SIZE, async (doc) => ...)
* #param cursor - A cursor to batch process on.
* We can get this from our collection.js API by either using aggregateCursor/findCursor
* #param batchSize - The batch size, should match the batchSize of the cursor option.
* #param callback - Callback that should be async, will be called in parallel for each batch.
* #return {Promise<void>}
*/
static async concurrentCursorBatchProcessing(cursor, batchSize, callback) {
let doc;
const docsBatch = [];
while ((doc = await cursor.next())) {
docsBatch.push(doc);
if (docsBatch.length >= batchSize) {
await PromiseUtils.concurrentPromiseAll(docsBatch, async (currDoc) => {
return callback(currDoc);
});
// Emptying the batch array
docsBatch.splice(0, docsBatch.length);
}
}
// Checking if there is a last batch remaining since it was small than batchSize
if (docsBatch.length > 0) {
await PromiseUtils.concurrentPromiseAll(docsBatch, async (currDoc) => {
return callback(currDoc);
});
}
}
An example of usage for reading many big documents and updating them:
const cursor = await collection.aggregate([
{
...
}
], {
cursor: {batchSize: BATCH_SIZE}, // Limiting memory use
allowDiskUse: true
});
const bulkUpdates = [];
await DbUtil.concurrentCursorBatchProcessing(cursor, BATCH_SIZE, async (doc: any) => {
const update: any = {
updateOne: {
filter: {
...
},
update: {
...
}
}
};
bulkUpdates.push(update);
// Updating if we read too many docs to clear space in memory
await this.bulkWriteIfNeeded(bulkUpdates, collection);
});
// Making sure we updated everything
await this.bulkWriteIfNeeded(bulkUpdates, collection, true);
...
private async bulkWriteParametersIfNeeded(
bulkUpdates: any[], collection: any,
forceUpdate = false, flushBatchSize) {
if (bulkUpdates.length >= flushBatchSize || forceUpdate) {
// concurrentPromiseChunked is a method that loops over an array in a concurrent way using lodash.chunk and Promise.map
await PromiseUtils.concurrentPromiseChunked(bulkUpsertParameters, (upsertChunk: any) => {
return techniquesParametersCollection.bulkWrite(upsertChunk);
});
// Emptying the array
bulkUpsertParameters.splice(0, bulkUpsertParameters.length);
}
}

How to set a variable to a query? mongodb

How do I set a variable to a query? I am trying to use functions and callbacks in node.js to work through async, but I am not sure how to get a query to equal to a variable. What I am trying to do in this code is take a friend collection that belongs to a user and return the friends result(which I don't think I am doing correctly in the query insertAll) and then find the user's info for each of the query. And then return the results as a render. I am not sure how to call render either with this...
Here is my code:
exports.contactList = function(req, res) {
var insertFriend = function(data, callback) {
var friend = User.findById({_id: user.friendStatus.fuId}, function() {
callback(null, data);
}, friend);
};;
var insertAll = function(coll, callback) {
var queue = coll.slice(0),
friendX;
(function iterate(){
if(queue.length === 0) {
callback();
return;
}
friendX = queue.splice(0,1)[0];
insertFriend(friendX, function(err, friendX) {
if(err) {throw err;}
console.log(friendX + ' inserted');
process.nextTick(iterate);
});
})();
};
insertAll([Friend.findOne({userId: req.signedCookies.userid})], function(){
});
};
A Query object is returned if you do not pass a callback.
From http://mongoosejs.com/docs/queries.html:
When a callback function:
is passed, the operation will be executed immediately with the results passed to the
callback.
is not passed, an instance of Query is returned, which provides a special QueryBuilder
interface for you.

Mongoose (mongodb) batch insert?

Does Mongoose v3.6+ support batch inserts now? I've searched for a few minutes but anything matching this query is a couple of years old and the answer was an unequivocal no.
Edit:
For future reference, the answer is to use Model.create(). create() accepts an array as its first argument, so you can pass your documents to be inserted as an array.
See Model.create() documentation
Model.create() vs Model.collection.insert(): a faster approach
Model.create() is a bad way to do inserts if you are dealing with a very large bulk. It will be very slow. In that case you should use Model.collection.insert, which performs much better. Depending on the size of the bulk, Model.create() will even crash! Tried with a million documents, no luck. Using Model.collection.insert it took just a few seconds.
Model.collection.insert(docs, options, callback)
docs is the array of documents to be inserted;
options is an optional configuration object - see the docs
callback(err, docs) will be called after all documents get saved or an error occurs. On success, docs is the array of persisted documents.
As Mongoose's author points out here, this method will bypass any validation procedures and access the Mongo driver directly. It's a trade-off you have to make since you're handling a large amount of data, otherwise you wouldn't be able to insert it to your database at all (remember we're talking hundreds of thousands of documents here).
A simple example
var Potato = mongoose.model('Potato', PotatoSchema);
var potatoBag = [/* a humongous amount of potato objects */];
Potato.collection.insert(potatoBag, onInsert);
function onInsert(err, docs) {
if (err) {
// TODO: handle error
} else {
console.info('%d potatoes were successfully stored.', docs.length);
}
}
Update 2019-06-22: although insert() can still be used just fine, it's been deprecated in favor of insertMany(). The parameters are exactly the same, so you can just use it as a drop-in replacement and everything should work just fine (well, the return value is a bit different, but you're probably not using it anyway).
Reference
Mongo documentation
Aaron Heckman on Google Groups discussing bulk inserts
Mongoose 4.4.0 now supports bulk insert
Mongoose 4.4.0 introduces --true-- bulk insert with the model method .insertMany(). It is way faster than looping on .create() or providing it with an array.
Usage:
var rawDocuments = [/* ... */];
Book.insertMany(rawDocuments)
.then(function(mongooseDocuments) {
/* ... */
})
.catch(function(err) {
/* Error handling */
});
Or
Book.insertMany(rawDocuments, function (err, mongooseDocuments) { /* Your callback function... */ });
You can track it on:
https://github.com/Automattic/mongoose/issues/723
https://github.com/Automattic/mongoose/blob/1887e72694829b62f4e3547283783cebbe66b46b/lib/model.js#L1774
Indeed, you can use the "create" method of Mongoose, it can contain an array of documents, see this example:
Candy.create({ candy: 'jelly bean' }, { candy: 'snickers' }, function (err, jellybean, snickers) {
});
The callback function contains the inserted documents.
You do not always know how many items has to be inserted (fixed argument length like above) so you can loop through them:
var insertedDocs = [];
for (var i=1; i<arguments.length; ++i) {
insertedDocs.push(arguments[i]);
}
Update: A better solution
A better solution would to use Candy.collection.insert() instead of Candy.create() - used in the example above - because it's faster (create() is calling Model.save() on each item so it's slower).
See the Mongo documentation for more information:
http://docs.mongodb.org/manual/reference/method/db.collection.insert/
(thanks to arcseldon for pointing this out)
Here are both way of saving data with insertMany and save
1) Mongoose save array of documents with insertMany in bulk
/* write mongoose schema model and export this */
var Potato = mongoose.model('Potato', PotatoSchema);
/* write this api in routes directory */
router.post('/addDocuments', function (req, res) {
const data = [/* array of object which data need to save in db */];
Potato.insertMany(data)
.then((result) => {
console.log("result ", result);
res.status(200).json({'success': 'new documents added!', 'data': result});
})
.catch(err => {
console.error("error ", err);
res.status(400).json({err});
});
})
2) Mongoose save array of documents with .save()
These documents will save parallel.
/* write mongoose schema model and export this */
var Potato = mongoose.model('Potato', PotatoSchema);
/* write this api in routes directory */
router.post('/addDocuments', function (req, res) {
const saveData = []
const data = [/* array of object which data need to save in db */];
data.map((i) => {
console.log(i)
var potato = new Potato(data[i])
potato.save()
.then((result) => {
console.log(result)
saveData.push(result)
if (saveData.length === data.length) {
res.status(200).json({'success': 'new documents added!', 'data': saveData});
}
})
.catch((err) => {
console.error(err)
res.status(500).json({err});
})
})
})
You can perform bulk insert using mongoose, as the highest score answer.
But the example cannot work, it should be:
/* a humongous amount of potatos */
var potatoBag = [{name:'potato1'}, {name:'potato2'}];
var Potato = mongoose.model('Potato', PotatoSchema);
Potato.collection.insert(potatoBag, onInsert);
function onInsert(err, docs) {
if (err) {
// TODO: handle error
} else {
console.info('%d potatoes were successfully stored.', docs.length);
}
}
Don't use a schema instance for the bulk insert, you should use a plain map object.
It seems that using mongoose there is a limit of more than 1000 documents, when using
Potato.collection.insert(potatoBag, onInsert);
You can use:
var bulk = Model.collection.initializeOrderedBulkOp();
async.each(users, function (user, callback) {
bulk.insert(hash);
}, function (err) {
var bulkStart = Date.now();
bulk.execute(function(err, res){
if (err) console.log (" gameResult.js > err " , err);
console.log (" gameResult.js > BULK TIME " , Date.now() - bulkStart );
console.log (" gameResult.js > BULK INSERT " , res.nInserted)
});
});
But this is almost twice as fast when testing with 10000 documents:
function fastInsert(arrOfResults) {
var startTime = Date.now();
var count = 0;
var c = Math.round( arrOfResults.length / 990);
var fakeArr = [];
fakeArr.length = c;
var docsSaved = 0
async.each(fakeArr, function (item, callback) {
var sliced = arrOfResults.slice(count, count+999);
sliced.length)
count = count +999;
if(sliced.length != 0 ){
GameResultModel.collection.insert(sliced, function (err, docs) {
docsSaved += docs.ops.length
callback();
});
}else {
callback()
}
}, function (err) {
console.log (" gameResult.js > BULK INSERT AMOUNT: ", arrOfResults.length, "docsSaved " , docsSaved, " DIFF TIME:",Date.now() - startTime);
});
}
You can perform bulk insert using mongoDB shell using inserting the values in an array.
db.collection.insert([{values},{values},{values},{values}]);
Sharing working and relevant code from our project:
//documentsArray is the list of sampleCollection objects
sampleCollection.insertMany(documentsArray)
.then((res) => {
console.log("insert sampleCollection result ", res);
})
.catch(err => {
console.log("bulk insert sampleCollection error ", err);
});

Resources