Conditionally count foreign fields in collection with Mongo aggregations [duplicate] - node.js

I have a mongoDB collection called "conference" with an array of participants as below :
[
{
"_id" : 5b894357a0c84d5a5d221f25,
"conferenceName" : "myFirstConference",
"startDate" : 1535722327,
"endDate" : 1535722420,
"participants" : [
{
"name" : "user1",
"origin" : "internal",
"ip" : "192.168.0.2"
},
{
"name" : "user2",
"origin" : "external",
"ip" : "172.20.0.3"
},
]
},
...
]
I would like to get the following result :
[
{
"conferenceName" : "myFirstConference",
"startDate" : 1535722327,
"endDate" : 1535722420,
"internalUsersCount" : 1
"externalUsersCount" : 1,
},
...
]
I tried the request below but it's not working :
db.getCollection("conference").aggregate([
{
$addFields: {
internalUsersCount : {
$size : { "$participants" : {$elemMatch : { origin : "internal" }}}
},
externalUsersCount : {
$size : { "$participants" : {$elemMatch : { origin : "external" }}}
}
}
}
])
How is it possible to count "participant" array elements that match {"origin" : "internal"} and {"origin" : "external"} ?

You need to use $filter aggregation to filter out the external origin and internal origin along with the $size aggregation to calculate the length of the arrays.
Something like this
db.collection.aggregate([
{ "$addFields": {
"internalUsersCount": {
"$size": {
"$filter": {
"input": "$participants",
"as": "part",
"cond": { "$eq": ["$$part.origin", "internal"]}
}
}
},
"externalUsersCount": {
"$size": {
"$filter": {
"input": "$participants",
"as": "part",
"cond": { "$eq": ["$$part.origin", "external"] }
}
}
}
}}
])
Output
[
{
"conferenceName": "myFirstConference",
"endDate": 1535722420,
"externalUsersCount": 1,
"internalUsersCount": 1,
"startDate": 1535722327
}
]

Related

Find with arrayFilters using Mongoose

I have to filter the object which contains only status C in comments(If atleast only comment have the status C then that object alone should be print) I tried using array Filters but I don't get exact result
{
"_id" : ObjectId("5b8f84379f432a42383a85bb"),
"projectID" : ObjectId("00000000e614c33390237ce3"),
"inspection_data" : [
{
"locationAspects" : [
{
"aspectname" : "Ground floor",
"comments" : [
{
"status" :"C",
"comment" : [
"good"
],
"_id" : ObjectId("5b8f84379f16400f884d9974")
}
],
"_id" : ObjectId("5b8f84379f16400f884d9975")
},
{
"aspectname" : "Second floor",
"comments" : [
{
"status" :"P",
"comment" : [
"nothing"
],
"_id" : ObjectId("5b8f84379f16400f884d9971")
}
],
"_id" : ObjectId("5b8f84379f16400f884d9972")
},
],
"published_date" : ISODate("2018-09-05T07:22:31.017Z"),
"_id" : ObjectId("5b8f84379f16400f884d9976")
},
{
"locationAspects" : [
{
"aspectname" : "Ground floor",
"comments" : [
{
"status" :"P",
"comment" : [
"good"
],
"_id" : ObjectId("5b8f84379f16400f884d9974")
}
],
"_id" : ObjectId("5b8f84379f16400f884d9975")
}
],
"published_date" : ISODate("2018-09-05T07:22:31.017Z"),
"_id" : ObjectId("5b8f84379f16400f884d9976")
}
]
Now the inspection data having two object but one object only containing comment status c, So That should be print
Expected Result
[ {
"locationAspects" : [
{
"aspectname" : "Ground floor",
"comments" : [
{
"status" :"C",
"comment" : [
"good"
],
"_id" : ObjectId("5b8f84379f16400f884d9974")
}
],
"_id" : ObjectId("5b8f84379f16400f884d9975")
},
{
"aspectname" : "Second floor",
"comments" : [
{
"status" :"P",
"comment" : [
"nothing"
],
"_id" : ObjectId("5b8f84379f16400f884d9971")
}
],
"_id" : ObjectId("5b8f84379f16400f884d9972")
},
],
"published_date" : ISODate("2018-09-05T07:22:31.017Z"),
"_id" : ObjectId("5b8f84379f16400f884d9976")
}]
Above object only having the status C if alteast one comment status is C that object alone have to display
You need $filter to process inspection_data. Things are getting complicated since you have multiple levels of nestings, so before you can apply $in condition you need to get an array of all statuses for single inspection_data. To achieve that you can use direct path like "$$data.locationAspects.comments.status" but it returns an array of arrays like this:
[ [ "C" ], [ "P" ] ], [ [ "P" ] ] ]
So you have to flatten that array and that can be achieved using $reduce and $concatArrays. Try:
db.col.aggregate([
{ $match: { projectID: ObjectId("00000000e614c33390237ce3") } },
{
$project: {
filtered_inspection_data: {
$filter: {
input: "$inspection_data",
as: "data",
cond: {
$let: {
vars: {
statuses: {
$reduce: {
input: "$$data.locationAspects.comments.status",
initialValue: [],
in: { $concatArrays: [ "$$this", "$$value" ] }
}
}
},
in: { $in: [ "C", "$$statuses" ] }
}
}
}
}
}
}
])
EDIT: to match "C" or "P" you can use replace { $in: [ "C", "$$statuses" ] } with following line
{ $or: [ { $in: [ "C", "$$statuses" ] }, { $in: [ "P", "$$statuses" ] } ] }

add fields where condition match to nested array

I have following users collection
[{
"_id" : ObjectId("5afadfdf08a7aa6f1a27d986"),
"firstName" : "bruce",
"friends" : [ ObjectId("5afd1c42af18d985a06ac306"),ObjectId("5afd257daf18d985a06ac6ac") ]
},
{
"_id" : ObjectId("5afbfe21daf4b13ddde07dbe"),
"firstName" : "clerk",
"friends" : [],
}]
and have friends collection
[{
"_id" : ObjectId("5afd1c42af18d985a06ac306"),
"recipient" : ObjectId("5afaab572c4ec049aeb0bcba"),
"requester" : ObjectId("5afadfdf08a7aa6f1a27d986"),
"status" : 2,
},
{
"_id" : ObjectId("5afd257daf18d985a06ac6ac"),
"recipient" : ObjectId("5afadfdf08a7aa6f1a27d986"),
"requester" : ObjectId("5afbfe21daf4b13ddde07dbe"),
"status" : 1,
}]
suppose I have an user logged in with _id: "5afaab572c4ec049aeb0bcba" and this _id matches the recipient of the friends
Now I have to add a field friendsStatus which contains the status from friends collection... And if does not matches the any recipient from the array then its status should be 0
So when I get all users then my output should be
[{
"_id" : ObjectId("5afadfdf08a7aa6f1a27d986"),
"firstName" : "bruce",
"friends" : [ ObjectId("5afd1c42af18d985a06ac306") ],
"friendStatus": 2
},
{
"_id" : ObjectId("5afbfe21daf4b13ddde07dbe"),
"firstName" : "clerk",
"friends" : [],
"friendStatus": 0
}]
Thanks in advance!!!
If you have MongoDB 3.6 then you can use $lookup with a "sub-pipeline"
User.aggregate([
{ "$lookup": {
"from": Friend.collection.name,
"let": { "friends": "$friends" },
"pipeline": [
{ "$match": {
"recipient": ObjectId("5afaab572c4ec049aeb0bcba"),
"$expr": { "$in": [ "$_id", "$$friends" ] }
}},
{ "$project": { "status": 1 } }
],
"as": "friends"
}},
{ "$addFields": {
"friends": {
"$map": {
"input": "$friends",
"in": "$$this._id"
}
},
"friendsStatus": {
"$ifNull": [ { "$min": "$friends.status" }, 0 ]
}
}}
])
For earlier versions, it's ideal to actually use $unwind in order to ensure you don't breach the BSON Limit:
User.aggregate([
{ "$lookup": {
"from": Friend.collection.name,
"localField": "friends",
"foreignField": "_id",
"as": "friends"
}},
{ "$unwind": { "path": "$friends", "preserveNullAndEmptyArrays": true } },
{ "$match": {
"$or": [
{ "friends.recipient": ObjectId("5afaab572c4ec049aeb0bcba") },
{ "friends": null }
]
}},
{ "$group": {
"_id": "$_id",
"firstName": { "$first": "$firstName" },
"friends": { "$push": "$friends._id" },
"friendsStatus": {
"$min": {
"$ifNull": ["$friends.status",0]
}
}
}}
])
There is "one difference" from the most optimal form here in that the pipeline optimization does not actually "roll-up" the $match condition into the $lookup itself:
{
"$lookup" : {
"from" : "friends",
"as" : "friends",
"localField" : "friends",
"foreignField" : "_id",
"unwinding" : {
"preserveNullAndEmptyArrays" : true
}
}
},
{
"$match" : { // <-- outside will preserved array
Because of the preserveNullAndEmptyArrays option being true then the "fully optimized" action where the condition would actually be applied to the foreign collection "before" results are returned does not happen.
So the only purpose of unwinding here is purely to avoid what would normally be a target "array" from the $lookup result causing the parent document to grow beyond the BSON Limit. Additional conditions of the $match are then applied "after" this stage. The default $unwind without the option presumes false for the preservation and a matching condition is added instead to do this. This of course would result in the documents with no foreign matches being excluded.
And not really advisable because of that BSON Limit, but there is also applying $filter to the resulting array of $lookup:
User.aggregate([
{ "$lookup": {
"from": Friend.collection.name,
"localField": "friends",
"foreignField": "_id",
"as": "friends"
}},
{ "$addFields": {
"friends": {
"$map": {
"input": {
"$filter": {
"input": "$friends",
"cond": {
"$eq": [
"$$this.recipient",
ObjectId("5afaab572c4ec049aeb0bcba")
]
}
}
},
"in": "$$this._id"
}
},
"friendsStatus": {
"$ifNull": [
{ "$min": {
"$map": {
"input": {
"$filter": {
"input": "$friends",
"cond": {
"$eq": [
"$$this.recipient",
ObjectId("5afaab572c4ec049aeb0bcba")
]
}
}
},
"in": "$$this.status"
}
}},
0
]
}
}}
])
In either case we're basically adding the "additional condition" to the join being not just on the directly related field but also with the additional constraint of the queried ObjectId value for "recipient".
Not really sure what you are expecting for "friendsStatus" since the result is an array and there can possibly be more than one ( as far as I know ) and therefore just applying $min here to extract one value from the array in either case.
The governing condition in each case is $ifNull which is applied where there isn't anything in the "friends" output array to extract from and then you simply return the result of 0 where that is the case.
All output the same thing:
{
"_id" : ObjectId("5afadfdf08a7aa6f1a27d986"),
"firstName" : "bruce",
"friends" : [
ObjectId("5afd1c42af18d985a06ac306")
],
"friendsStatus" : 2
}
{
"_id" : ObjectId("5afbfe21daf4b13ddde07dbe"),
"firstName" : "clerk",
"friends" : [ ],
"friendsStatus" : 0
}

Multiple $group in mongoDB

I have in mongodb differents records. I write down a little example:
{_id:"sad547er4w2v5x85b8", name:"Jhon", jobTime:600, floor:2, dept:5, age:25},
{_id:"xcz547wer4xcvcx1g2", name:"Alex", jobTime:841, floor:4, dept:1, age:55},
{_id:"xcnwep2321954ldfsl", name:"Alice", jobTime:100, floor:3, dept:3, age:55},
{_id:"23s3ih94h548jhfk2u", name:"Anne", jobTime:280, floor:2, dept:8, age:22},
{_id:"03dfsk9342hjwq1503", name:"Alexa", jobTime:355, floor:2, dept:6, age:25}
I tried to obtain this output, but I don't know how to group by twice to get that structure.
{[
{age:22, floors:[{floor:2,persons:[{name:"Anne",jobTime:280,dept:8}]}]},
{age:25, floors:[{floor:2,persons:[{name:"Jhon",jobTime:600,dept:5},{name:"Alexa",jobTime:355,dept:6}]}]},
{age:55, floors:[{floor:3,persons:[{name:"Alex",jobTime:841,dept:1}]},{floor:4,persons:[{name:"Alice",jobTime:100,dept:3}]}]}
]}
Exactly. Use "two" $group stages
collection.aggregate([
{ "$group": {
"_id": {
"age": "$age",
"floor": "$floor",
},
"persons": { "$push": {
"name": "$name",
"jobTime": "$jobTime",
"dept": "$dept"
}}
}},
{ "$group": {
"_id": "$_id.age",
"floors": { "$push": {
"floor": "$_id.floor",
"persons": "$persons"
}}
}}
],function(err,results) {
// deal with results here
})
Which produces:
{
"_id" : 25,
"floors" : [
{ "floor" : 2,
"persons" : [
{ "name" : "Jhon", "jobTime" : 600, "dept" : 5 },
{ "name" : "Alexa", "jobTime" : 355, "dept" : 6 }
]
}
]
},
{
"_id" : 55,
"floors" : [
{ "floor" : 3,
"persons" : [
{ "name" : "Alice", "jobTime" : 100, "dept" : 3 }
]
},
{ "floor" : 4,
"persons" : [
{ "name" : "Alex", "jobTime" : 841, "dept" : 1 }
]
}
]
},
{
"_id" : 22,
"floors" : [
{ "floor" : 2,
"persons" : [
{ "name" : "Anne", "jobTime" : 280, "dept" : 8 }
]
}
]
}
So the initial $group is on a compound key including the detail down to the items you want to add to the initial "array", for "persons". Then the second $group takes only part of the initial _id for it's key and again "pushes" the content into a new array.

slice in array not working?

This is my mongoose collection data:
{
"ShopId" : "439",
"productName" : "veg",
"productCategory" : "meals",
"mrp" : "38 "
},
{
"ShopId" : "439",
"productName" : "non-veg",
"productCategory" : "meals",
"mrp" : "380 "
},{....}
Query
db.getCollection('ProductDetails').aggregate(
[{ "$match": { "ShopId": "439" } },{"$group": {"_id": "$productCategory", "count": { "$sum": 1 },
"products": {"$push":{"productname": "$productName"}}}},
{"$group": {"_id": null, "productList": {"$push": {"categoryname": "$_id", "productcount": "$count",
"products": "$products"}}}},{$project:{products:{$slice:["$productList.products",2]}}}])
Output:
{
"_id" : null,
"productList" : [
{
"categoryname" : "meals",
"productcount" : 8.0,
"products" : [
{
"productname" : "non veg"
},
{
"productname" : "veg"
},
{
"productname" : "c"
},
{
"productname" : "d"
},
{
"productname" : "df"
},
{
"productname" : "dfr"
},
{
"productname" : "qe"
},
{
"productname" : "as"
}
]
}
]
}
expected output:
I want to limit the number of products to 2.But instead of that all products are displaying.
{
"_id" : null,
"productList" : [
{
"categoryname" : "meals",
"productcount" : 8.0,
"products" : [
{
"productname" : "non veg"
},
{
"productname" : "veg"
}
]
}
]
}
Replace your $project stage with below.
{$project:{products:{$slice:[{$arrayElemAt:["$productList.products", 0]},2]}}}
Your products is array of arrays.
"products": [
[{
"productname": "veg"
}, {
"productname": "non-veg"
}]
]
$arrayElemAt with 0 will pick the inner array and you can use $slice to limit the products.
I believe you are using the $slice function wrong: As I mentioned in this post:
Find a value in array
The slice function takes two parameters: The first is the initial index and the second is the number of elements after this index. Here's an example:
db.collection.find({},{_id:0,products:{$slice : [0,2]})
This will take two elements from the index [0] of the array. Hope my answer was helpful.

Mongo query not giving exact results for aggregate function

My mongo database contains a collection 'Shops' and the data is like below:
{
"_id" : ObjectId("XXXX1b83d2b227XXXX"),
"ShopId" : 435,
"products" : [
{
"productId" : "1234",
"productName" : "non veg",
"productCategory" : "meals",
"mrp" : "38",
},
{
"productId" : "5234",
"productName" : "non veg",
"productCategory" : "meals",
"mrp" : "38",
},
{
"productId" : "6234",
"productName" : "apple",
"productCategory" : "juice",
"mrp" : "38",
},
{
"productId" : "7234",
"productName" : "non veg",
"productCategory" : "biriyani",
"mrp" : "38",
},
{
"productId" : "8234",
"productName" : "non veg",
"productCategory" : "biriyani",
"mrp" : "38",
}
]
}
There will be several shops in the collection having a list of products.
Expected Output
{ "productList": [
{
"categoryname": "meals",
"productcount": "2",
"products": [
{
"productname": "Non-Veg"
},
{
"productname": "Veg"
}
]
},
{
"categoryname": "juice",
"productcount": "1",
"products": [
{
"productname": "apple"
}
]
},{......}
]
}
I tried it using 'async' method with 2 queries, but I didn't get the output correctly. I think it can be done in one query without using 'async'.
My code follows, I think it's the wrong approach:
model.Shops.aggregate([
{$match:{ShopId:435}},
{$unwind:"$products"},
{$limit:2},{$skip:0},
{$group:{_id:{"productCategory":"$products.productCategory"}}}
],function (err, doc) {
if (doc!=null){
var arr = [];
async.each(doc, function(item,callback){
model.Shops.aggregate([
{"$unwind":"$products"},
{$match:{"ShopId":435,"products.productCategory":item._id.productCategory}},
{$limit:2},
{
$group: {
_id:null,
"products": {
$push:{"productName":"$products.productName"}
}
}
}
], function (err,doc) {
arr.push({"categoryname":item._id.productCategory,"products":doc.products});
callback(null);
});
},function (err) {
res.json(arr);
});
}
});
You certainly do not need two queries for this, a single pipeline will suffice. Run the following aggregate operation to get the desired results:
model.Shops.aggregate([
{ "$match": { "ShopId": 435 } },
{ "$unwind": "$products" },
{
"$group": {
"_id": "$products.productCategory",
"count": { "$sum": 1 },
"products": {
"$push": {
"productName": "$products.productName"
}
}
}
},
{
"$group": {
"_id": null,
"productList": {
"$push": {
"categoryname": "$_id",
"productcount": "$count",
"products": "$products"
}
}
}
}
], function (err, results) {
res.json(results);
});
Explanations
The above pipeline uses the following pipeline steps (in the order given) and explained as:
Step 1) $match operator is there to filter documents that get into the pipeline. If you are coming from a SQL background, this pipeline is similar to the SQL's WHERE clause where e.g.
SELECT *
FROM Shops
WHERE ShopId = 435
If you run the pipeline at this stage only, it will return all the documents that match on the ShopId of 435
Step 2) $unwind - The products field is an array so you'll need to add an $unwind stage to your pipeline so that you can flatten the array as it needs to be processed further down as a denormalised field. For each input document, this outputs n documents where n is the number of array elements and can be zero for an empty array.
Running the aggregate pipeline up to this stage for the above sample will produce 5 documents i.e. in mongo shell
db.getCollection('shops').aggregate([
{ "$match": { "ShopId": 435 } }, // Step 1
{ "$unwind": "$products" } // Step 2
])
will yield
[
{
"_id" : ObjectId("58aadec0671a3794272f342f"),
"ShopId" : 435,
"products" : {
"productId" : "1234",
"productName" : "non veg",
"productCategory" : "meals",
"mrp" : "38"
}
},
{
"_id" : ObjectId("58aadec0671a3794272f342f"),
"ShopId" : 435,
"products" : {
"productId" : "5234",
"productName" : "non veg",
"productCategory" : "meals",
"mrp" : "38"
}
},
{
"_id" : ObjectId("58aadec0671a3794272f342f"),
"ShopId" : 435,
"products" : {
"productId" : "6234",
"productName" : "apple",
"productCategory" : "juice",
"mrp" : "38"
}
},
{
"_id" : ObjectId("58aadec0671a3794272f342f"),
"ShopId" : 435,
"products" : {
"productId" : "7234",
"productName" : "non veg",
"productCategory" : "biriyani",
"mrp" : "38"
}
},
{
"_id" : ObjectId("58aadec0671a3794272f342f"),
"ShopId" : 435,
"products" : {
"productId" : "8234",
"productName" : "non veg",
"productCategory" : "biriyani",
"mrp" : "38"
}
}
]
Step 3) $group pipeline step to group the documents in the pipeline by the productCategory field from the denormalised documents and creates an array products that has fields from the previous pipeline. The $group pipeline operator is similar to the SQL's GROUP BY clause.
In SQL, you can't use GROUP BY unless you use any of the aggregation functions. The same way, you have to use an aggregation function called accumulator in MongoDB as well. You can read more about the aggregation functions here.
The accumulator operator you would need to create the array is $push.
In the same $group operation, the logic to calculate the count aggregate i.e. the number of documents in each category group is done using the $sum accumulator operator. The expression { $sum : 1 } returns the sum of values of the number of documents in each group.
To understand the pipeline, run the operation at this stage and analyse the results. So, executing the equivalent mongo operation
db.getCollection('shops').aggregate([
{ "$match": { "ShopId": 435 } }, // Step 1
{ "$unwind": "$products" }, // Step 2
{ // Step 3
"$group": {
"_id": "$products.productCategory",
"count": { "$sum": 1 },
"products": {
"$push": {
"productName": "$products.productName"
}
}
}
}
])
yields the following documents
[
{
"_id" : "meals",
"count" : 2,
"products" : [
{
"productName" : "non veg"
},
{
"productName" : "non veg"
}
]
},
{
"_id" : "juice",
"count" : 1,
"products" : [
{
"productName" : "apple"
}
]
},
{
"_id" : "biriyani",
"count" : 2,
"products" : [
{
"productName" : "non veg"
},
{
"productName" : "non veg"
}
]
}
]
Step 4) The last $group pipeline will then produce the desired result when you specify an _id value of null to calculate accumulated values for all the input documents above as a whole. The desired structure has a productsList array that can be created using the $push operator.
Again, running the final aggregate pipeline at this stage will give you the desired result, i.e. executing this in mongo shell
db.getCollection('shops').aggregate([
{ "$match": { "ShopId": 435 } }, // Step 1
{ "$unwind": "$products" }, // Step 2
{ // Step 3
"$group": {
"_id": "$products.productCategory",
"count": { "$sum": 1 },
"products": {
"$push": {
"productName": "$products.productName"
}
}
}
},
{ // Step 4
"$group": {
"_id": null,
"productList": {
"$push": {
"categoryname": "$_id",
"productcount": "$count",
"products": "$products"
}
}
}
}
])
will yield
{
"_id" : null,
"productList" : [
{
"categoryname" : "meals",
"productcount" : 2,
"products" : [
{
"productName" : "non veg"
},
{
"productName" : "non veg"
}
]
},
{
"categoryname" : "juice",
"productcount" : 1,
"products" : [
{
"productName" : "apple"
}
]
},
{
"categoryname" : "biriyani",
"productcount" : 2,
"products" : [
{
"productName" : "non veg"
},
{
"productName" : "non veg"
}
]
}
]
}
One thing to note here is when executing a pipeline, MongoDB pipes operators into each other. "Pipe" here takes the Linux meaning: the output of an operator becomes the input of the following operator. The result of each operator is a new collection of documents. So Mongo executes the above pipeline as follows:
collection | $match | $unwind | $group | $group => result

Resources