We Keep Coding

Trying to write a recursive asynchronous search in JavaScript

I am trying to write some code that searches through a bunch of objects in a MongoDB database. I want to pull the objects from the database by ID, then those objects have ID references. The program should be searching for a specific ID through this process, first getting object from id, then ids from the object.
async function objectFinder(ID1, ID2, depth, previousList = []) {
let route = []
if (ID1 == ID2) {
return [ID2]
} else {
previousList.push(ID1)
let obj1 = await findObjectByID(ID1)
let connectedID = obj1.connections.concat(obj1.inclusions) //creates array of both references to object and references from object
let mapPromises = connectedID.map(async (id) => {
return findID(id) //async function
})
let fulfilled = await Promise.allSettled(mapPromises)
let list = fulfilled.map((object) => {
return object.value.main, object.value.included
})
list = list.filter(id => !previousList.includes(id))
for (id of list) {
await objectFinder(id, ID2, depth - 1, previousList).then(result => {
route = [ID1].concat(result)
if (route[route.length - 1] == ID2) {
return route
}})
}
}
if (route[route.length - 1] == ID2) {
return route
}
}
I am not sure how to make it so that my code works like a tree search, with each object and ID being a node.

I didn't look too much into your code as I strongly believe in letting your database do the work for you if possible.
In this case Mongo has the $graphLookup aggregation stage, which allows recursive lookups. here is a quick example on how to use it:
db.collection.aggregate([
{
$match: {
_id: 1,
}
},
{
"$graphLookup": {
"from": "collection",
"startWith": "$inclusions",
"connectFromField": "inclusions",
"connectToField": "_id",
"as": "matches",
}
},
{
//the rest of the pipeline is just to restore the original structure you don't need this
$addFields: {
matches: {
"$concatArrays": [
[
{
_id: "$_id",
inclusions: "$inclusions"
}
],
"$matches"
]
}
}
},
{
$unwind: "$matches"
},
{
"$replaceRoot": {
"newRoot": "$matches"
}
}
])
Mongo Playground
If for whatever reason you want to keep this in code then I would take a look at your for loop:
for (id of list) {
await objectFinder(id, ID2, depth - 1, previousList).then(result => {
route = [ID1].concat(result);
if (route[route.length - 1] == ID2) {
return route;
}
});
}
Just from a quick glance I can tell you're executing this:
route = [ID1].concat(result);
Many times at the same level. Additional I could not understand your bottom return statements, I feel like there might be an issue there.

MongoDB - Most Recent Item for Each ID in List

I have a list of content IDs and I’m trying to fetch the most recent comment (if one exists) for each of the content IDs in the list -
My query looks as follows:
const query = [
{
$match: {
content_id: { $in: myContentIds },
},
},
{ $sort: { ‘comment_created’: -1 } },
]
const results = await collection.find(query).toArray();
My understanding is this will fetch all of the comments related to the contentIds in the myContentIds array and sort them in descending order based on the date.
I could then limit my results using { $limit: 1} but this would return the most recent comment on any of the content items, rather than the most recent comment for each content.
How can I modify my query to return the most recent comment for each of my content items?

$group by content_id and get first recent document
$replaceRoot to replace that recent document in root (this is optional, you can use document by object recentComment)
const query = [
{ $match: { content_id: { $in: myContentIds } } },
{ $sort: { comment_created: -1 } },
{
$group: {
_id: "$content_id",
recentComment: { $first: "$$ROOT" }
}
},
{ $replaceRoot: { newRoot: "$recentComment" } }
];
const results = await collection.aggregate(query);
Playground

MongoDB Node.JS driver: create, append, and update documents with arrays in one go

Is this really the only way to create, append, and update documents with arrays in a database or could this be done in only ONE beautiful operation ? I am of course looking to optimise this bit of code into how it is supposed to be implemented in MongoDB operators, it would reduce the operations done to the database... What do you think?
const { MongoClient } = require('mongodb');
async function main() {
try {
// Make the appropriate DB calls
// Create a new document
await createDocument(client);
// Append new items to the items array
await appendNewItemsToArray(client);
// Update items in the items array
await updateItemsInArray(client);
} finally {
// Close the connection to the MongoDB cluster
await client.close();
}
}
main().catch(console.error);
async function createDocument(client) {
const result = await client.db("NameOfYourDb").collection("NameOfYourCollection").insertOne({
"_id": "UniqueId1",
"items": [
{
"item_name": "my_item_one",
"first_seen": 1000,
"last_seen": 1000,
"logic": true
}
]
});
console.log(`New document created with the following id: ${result.insertedId}`);
}
async function appendNewItemsToArray(client) {
const result = await client.db("NameOfYourDb").collection("NameOfYourCollection").updateOne(
{ "_id": "UniqueId1" },
{
$push: {
items: {
$each: [
{
"item_name": "my_item_two",
"first_seen": 2000,
"last_seen": 2000,
"logic": true
},
{
"item_name": "my_item_three",
"first_seen": 3000,
"last_seen": 3000,
"logic": true
}]
}
}
});
console.log(`${result.matchedCount} document(s) matched the query criteria.`);
console.log(`${result.modifiedCount} document(s) was/were updated.`);
}
async function updateItemsInArray(client) {
const result = await client.db("NameOfYourDb").collection("NameOfYourCollection").updateOne(
{ "_id": "UniqueId1", "items.item_name": "my_item_one" },
{ $set: { "items.$.logic": false, "items.$.last_seen": 4000 } }
);
console.log(`${result.matchedCount} document(s) matched the query criteria.`);
console.log(`${result.modifiedCount} document(s) was/were updated.`);
}
I have found this original piece of code here bellow:
MongoDB Node.JS driver: create, append, and update documents with arrays
Of course some modifications are required.

MongoDB select random 5 documents via find query

I need to find random 5 documents from mongoDB by using find function. I using LoopBack 4 framework. I already try to use sample (it is in comment)
const userParties: IndividualParty[] = (await find(
this.logger,
{
where: {
and: [
{ _id: { nin: ids.map(id => id) } },
{ gender: { inq: gender } },
],
},
//sample: { size: 5 },
//limit: 5,
} as Filter<IndividualParty>,
this.partyRepository,
)) as IndividualParty[];

I'm not familiar with Loopback, but using pure node and node MongoDB driver, here's the shortest example I can come up with:
var run = async function() {
const conn = await require('mongodb').MongoClient.connect('mongodb://localhost:27017', {useNewUrlParser: true})
let agg = [
{'$match': {'_id': {'$gte': 50}}},
{'$sample': {'size': 5}}
]
let res = await conn.db('test').collection('test').aggregate(agg).toArray()
console.log(res)
await conn.close()
}()
In a collection containing _id from 0 to 99, this will randomly output 5 documents having _id larger than 50. Example output:
[ { _id: 60 }, { _id: 77 }, { _id: 84 }, { _id: 96 }, { _id: 63 } ]
You would need to make the above example work with Loopback, but the basic idea is there.
Note:
You need aggregation instead of find().
Have a read through the $sample documentation and note especially its behavior:
$sample uses one of two methods to obtain N random documents, depending on the size of the collection, the size of N, and $sample’s position in the pipeline.
The position of $sample in the pipeline is important. If you need to select a subset of the collection to do $sample on via a $match stage (as with the example above), then you will need to ensure that the subset to be sampled is within 16 MB (the limit of MongoDB in-memory sort).

How count pages total number of pages? [duplicate]

I am interested in optimizing a "pagination" solution I'm working on with MongoDB. My problem is straight forward. I usually limit the number of documents returned using the limit() functionality. This forces me to issue a redundant query without the limit() function in order for me to also capture the total number of documents in the query so I can pass to that to the client letting them know they'll have to issue an additional request(s) to retrieve the rest of the documents.
Is there a way to condense this into 1 query? Get the total number of documents but at the same time only retrieve a subset using limit()? Is there a different way to think about this problem than I am approaching it?

Mongodb 3.4 has introduced $facet aggregation
which processes multiple aggregation pipelines within a single stage
on the same set of input documents.
Using $facet and $group you can find documents with $limit and can get total count.
You can use below aggregation in mongodb 3.4
db.collection.aggregate([
{ "$facet": {
"totalData": [
{ "$match": { }},
{ "$skip": 10 },
{ "$limit": 10 }
],
"totalCount": [
{ "$group": {
"_id": null,
"count": { "$sum": 1 }
}}
]
}}
])
Even you can use $count aggregation which has been introduced in mongodb 3.6.
You can use below aggregation in mongodb 3.6
db.collection.aggregate([
{ "$facet": {
"totalData": [
{ "$match": { }},
{ "$skip": 10 },
{ "$limit": 10 }
],
"totalCount": [
{ "$count": "count" }
]
}}
])

No, there is no other way. Two queries - one for count - one with limit. Or you have to use a different database. Apache Solr for instance works like you want. Every query there is limited and returns totalCount.

MongoDB allows you to use cursor.count() even when you pass limit() or skip().
Lets say you have a db.collection with 10 items.
You can do:
async function getQuery() {
let query = await db.collection.find({}).skip(5).limit(5); // returns last 5 items in db
let countTotal = await query.count() // returns 10-- will not take `skip` or `limit` into consideration
let countWithConstraints = await query.count(true) // returns 5 -- will take into consideration `skip` and `limit`
return { query, countTotal }
}

Here's how to do this with MongoDB 3.4+ (with Mongoose) using $facets. This examples returns a $count based on the documents after they have been matched.
const facetedPipeline = [{
"$match": { "dateCreated": { $gte: new Date('2021-01-01') } },
"$project": { 'exclude.some.field': 0 },
},
{
"$facet": {
"data": [
{ "$skip": 10 },
{ "$limit": 10 }
],
"pagination": [
{ "$count": "total" }
]
}
}
];
const results = await Model.aggregate(facetedPipeline);
This pattern is useful for getting pagination information to return from a REST API.
Reference: MongoDB $facet

Times have changed, and I believe you can achieve what the OP is asking by using aggregation with $sort, $group and $project. For my system, I needed to also grab some user info from my users collection. Hopefully this can answer any questions around that as well. Below is an aggregation pipe. The last three objects (sort, group and project) are what handle getting the total count, then providing pagination capabilities.
db.posts.aggregate([
{ $match: { public: true },
{ $lookup: {
from: 'users',
localField: 'userId',
foreignField: 'userId',
as: 'userInfo'
} },
{ $project: {
postId: 1,
title: 1,
description: 1
updated: 1,
userInfo: {
$let: {
vars: {
firstUser: {
$arrayElemAt: ['$userInfo', 0]
}
},
in: {
username: '$$firstUser.username'
}
}
}
} },
{ $sort: { updated: -1 } },
{ $group: {
_id: null,
postCount: { $sum: 1 },
posts: {
$push: '$$ROOT'
}
} },
{ $project: {
_id: 0,
postCount: 1,
posts: {
$slice: [
'$posts',
currentPage ? (currentPage - 1) * RESULTS_PER_PAGE : 0,
RESULTS_PER_PAGE
]
}
} }
])

there is a way in Mongodb 3.4: $facet
you can do
db.collection.aggregate([
{
$facet: {
data: [{ $match: {} }],
total: { $count: 'total' }
}
}
])
then you will be able to run two aggregate at the same time

By default, the count() method ignores the effects of the
cursor.skip() and cursor.limit() (MongoDB docs)
As the count method excludes the effects of limit and skip, you can use cursor.count() to get the total count
const cursor = await database.collection(collectionName).find(query).skip(offset).limit(limit)
return {
data: await cursor.toArray(),
count: await cursor.count() // this will give count of all the documents before .skip() and limit()
};

It all depends on the pagination experience you need as to whether or not you need to do two queries.
Do you need to list every single page or even a range of pages? Does anyone even go to page 1051 - conceptually what does that actually mean?
Theres been lots of UX on patterns of pagination - Avoid the pains of pagination covers various types of pagination and their scenarios and many don't need a count query to know if theres a next page. For example if you display 10 items on a page and you limit to 13 - you'll know if theres another page..

MongoDB has introduced a new method for getting only the count of the documents matching a given query and it goes as follows:
const result = await db.collection('foo').count({name: 'bar'});
console.log('result:', result) // prints the matching doc count
Recipe for usage in pagination:
const query = {name: 'bar'};
const skip = (pageNo - 1) * pageSize; // assuming pageNo starts from 1
const limit = pageSize;
const [listResult, countResult] = await Promise.all([
db.collection('foo')
.find(query)
.skip(skip)
.limit(limit),
db.collection('foo').count(query)
])
return {
totalCount: countResult,
list: listResult
}
For more details on db.collection.count visit this page

It is possible to get the total result size without the effect of limit() using count() as answered here:
Limiting results in MongoDB but still getting the full count?
According to the documentation you can even control whether limit/pagination is taken into account when calling count():
https://docs.mongodb.com/manual/reference/method/cursor.count/#cursor.count
Edit: in contrast to what is written elsewhere - the docs clearly state that "The operation does not perform the query but instead counts the results that would be returned by the query". Which - from my understanding - means that only one query is executed.
Example:
> db.createCollection("test")
{ "ok" : 1 }
> db.test.insert([{name: "first"}, {name: "second"}, {name: "third"},
{name: "forth"}, {name: "fifth"}])
BulkWriteResult({
"writeErrors" : [ ],
"writeConcernErrors" : [ ],
"nInserted" : 5,
"nUpserted" : 0,
"nMatched" : 0,
"nModified" : 0,
"nRemoved" : 0,
"upserted" : [ ]
})
> db.test.find()
{ "_id" : ObjectId("58ff00918f5e60ff211521c5"), "name" : "first" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c6"), "name" : "second" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c7"), "name" : "third" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c8"), "name" : "forth" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c9"), "name" : "fifth" }
> db.test.count()
5
> var result = db.test.find().limit(3)
> result
{ "_id" : ObjectId("58ff00918f5e60ff211521c5"), "name" : "first" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c6"), "name" : "second" }
{ "_id" : ObjectId("58ff00918f5e60ff211521c7"), "name" : "third" }
> result.count()
5 (total result size of the query without limit)
> result.count(1)
3 (result size with limit(3) taken into account)

Try as bellow:
cursor.count(false, function(err, total){ console.log("total", total) })
core.db.users.find(query, {}, {skip:0, limit:1}, function(err, cursor){
if(err)
return callback(err);
cursor.toArray(function(err, items){
if(err)
return callback(err);
cursor.count(false, function(err, total){
if(err)
return callback(err);
console.log("cursor", total)
callback(null, {items: items, total:total})
})
})
})

Thought of providing a caution while using the aggregate for the pagenation. Its better to use two queries for this if the API is used frequently to fetch data by the users. This is atleast 50 times faster than getting the data using aggregate on a production server when more users are accessing the system online. The aggregate and $facet are more suited for Dashboard , reports and cron jobs that are called less frequently.

We can do it using 2 query.
const limit = parseInt(req.query.limit || 50, 10);
let page = parseInt(req.query.page || 0, 10);
if (page > 0) { page = page - 1}
let doc = await req.db.collection('bookings').find().sort( { _id: -1 }).skip(page).limit(limit).toArray();
let count = await req.db.collection('bookings').find().count();
res.json({data: [...doc], count: count});

I took the two queries approach, and the following code has been taken straight out of a project I'm working on, using MongoDB Atlas and a full-text search index:
return new Promise( async (resolve, reject) => {
try {
const search = {
$search: {
index: 'assets',
compound: {
should: [{
text: {
query: args.phraseToSearch,
path: [
'title', 'note'
]
}
}]
}
}
}
const project = {
$project: {
_id: 0,
id: '$_id',
userId: 1,
title: 1,
note: 1,
score: {
$meta: 'searchScore'
}
}
}
const match = {
$match: {
userId: args.userId
}
}
const skip = {
$skip: args.skip
}
const limit = {
$limit: args.first
}
const group = {
$group: {
_id: null,
count: { $sum: 1 }
}
}
const searchAllAssets = await Models.Assets.schema.aggregate([
search, project, match, skip, limit
])
const [ totalNumberOfAssets ] = await Models.Assets.schema.aggregate([
search, project, match, group
])
return await resolve({
searchAllAssets: searchAllAssets,
totalNumberOfAssets: totalNumberOfAssets.count
})
} catch (exception) {
return reject(new Error(exception))
}
})

I had the same problem and came across this question. The correct solution to this problem is posted here.

You can do this in one query. First you run a count and within that run the limit() function.
In Node.js and Express.js, you will have to use it like this to be able to use the "count" function along with the toArray's "result".
var curFind = db.collection('tasks').find({query});
Then you can run two functions after it like this (one nested in the other)
curFind.count(function (e, count) {
// Use count here
curFind.skip(0).limit(10).toArray(function(err, result) {
// Use result here and count here
});
});