We have three nested arrays:
principalCredits with 2 objects
credits with 2 objects each
awardNominations.edges with variable totals from 0 to 3
The task is to add a field to the third array of objects awardNominations.edges based on a lookup from eventsCollection.
Here's the data I have (simplified, can copy and paste into MongoDB Compass):
[{
"principalCredits": [
{
"category": {
"id": "director",
"text": "Directors"
},
"totalCredits": 2,
"credits": [
{
"name": {
"id": "nm11813828",
"nameText": {
"text": "Pippa Ehrlich"
},
"awardNominations": {
"total": 2,
"edges": [
{
"node": {
"id": "an1393007",
"isWinner": true,
"award": {
"id": "an1393007",
"year": 2020,
"text": "Green Warsaw Award",
"event": {
"id": "ev0003786",
"text": "Millennium Docs Against Gravity"
},
"category": {
"text": null
}
}
}
},
{
"node": {
"id": "an1428940",
"isWinner": false,
"award": {
"id": "an1428940",
"year": 2021,
"text": "IDA Award",
"event": {
"id": "ev0000351",
"text": "International Documentary Association"
},
"category": {
"text": "Best Writing"
}
}
}
},
]
}
},
"category": {
"id": "director",
"text": "Director"
}
},
{
"name": {
"id": "nm1624755",
"nameText": {
"text": "James Reed"
},
"awardNominations": {
"total": 3,
"edges": [
{
"node": {
"id": "an0694012",
"isWinner": true,
"award": {
"id": "an0694012",
"year": 2015,
"text": "Best of Festival",
"event": {
"id": "ev0001486",
"text": "Jackson Wild Media Awards"
},
"category": {
"text": "Best of Festival"
}
}
}
},
{
"node": {
"id": "an0975779",
"isWinner": true,
"award": {
"id": "an0975779",
"year": 2017,
"text": "RTS West Television Award",
"event": {
"id": "ev0000571",
"text": "Royal Television Society, UK"
},
"category": {
"text": "Documentary"
}
}
}
},
{
"node": {
"id": "an0975781",
"isWinner": true,
"award": {
"id": "an0975781",
"year": 2015,
"text": "Grand Teton Prize",
"event": {
"id": "ev0001356",
"text": "Jackson Hole Film Festival"
},
"category": {
"text": "Best in Festival"
}
}
}
}
]
}
},
"category": {
"id": "director",
"text": "Director"
}
}
]
},
{
"category": {
"id": "writer",
"text": "Writers"
},
"totalCredits": 2,
"credits": [
{
"name": {
"id": "nm11813828",
"nameText": {
"text": "Pippa Ehrlich"
},
"awardNominations": {
"total": 2,
"edges": [
{
"node": {
"id": "an1393007",
"isWinner": true,
"award": {
"id": "an1393007",
"year": 2020,
"text": "Green Warsaw Award",
"event": {
"id": "ev0003786",
"text": "Millennium Docs Against Gravity"
},
"category": {
"text": null
}
}
}
},
{
"node": {
"id": "an1428940",
"isWinner": false,
"award": {
"id": "an1428940",
"year": 2021,
"text": "IDA Award",
"event": {
"id": "ev0000351",
"text": "International Documentary Association"
},
"category": {
"text": "Best Writing"
}
}
}
}
]
}
},
"category": {
"id": "writer",
"text": "Writer"
},
},
{
"name": {
"id": "nm1624755",
"nameText": {
"text": "James Reed"
},
"awardNominations": {
"total": 0,
"edges": []
}
},
"category": {
"id": "writer",
"text": "Writer"
},
}
]
}
]
}]
An example scored award should look like this:
{
"id": "an0975781",
"isWinner": true,
"award": { ... },
"score": 1.5
}
Once all the manipulation is done, the data needs to be in exactly the same shape as it was initially and with no null values. So in the case of the last array awardsNominations.edges it should be [] as it was, and not { node: { score: null }} or anything else.
To achieve this I have created an aggregation pipeline:
[
{
'$unwind': {
'path': '$principalCredits',
'preserveNullAndEmptyArrays': true
}
}, {
'$unwind': {
'path': '$principalCredits.credits',
'preserveNullAndEmptyArrays': true
}
}, {
'$unwind': {
'path': '$principalCredits.credits.name.awardNominations.edges',
'preserveNullAndEmptyArrays': true
}
}, {
'$lookup': {
'from': 'eventsCollection',
'localField': 'principalCredits.credits.name.awardNominations.edges.node.award.event.id',
'foreignField': 'id',
'as': 'matchingEvent'
}
}, {
'$unwind': {
'path': '$matchingEvent',
'preserveNullAndEmptyArrays': true
}
}, {
'$addFields': {
'principalCredits.credits.name.awardNominations.edges.node.score': {
'$multiply': [
'$matchingEvent.importance', {
'$cond': {
'if': '$principalCredits.credits.name.awardNominations.edges.node.isWinner',
'then': 1.5,
'else': 1.2
}
}
]
}
}
}
]
The above pipeline assigns the score to each award. However, the null values are still there and I have absolutely no idea how to group it back together. I have tried to group with:
{
'$group': {
'_id': '$id',
'titleDoc': {
'$first': '$$ROOT'
},
'allPrincipalCredits': {
'$push': '$principalCredits'
}
}
}
To keep the root and then somehow sort all the records back into shape but could not get back to the orginal object structure.
Any help in putting it all together will be much appriciated!
I'm fairly good with simple aggregations, but this seems to be too much for me currently and would love to learn how to $group things back properly.
I've tried and put together all the knowledge I have so far from different sources and similar answers but can't seem to get it to work.
Lookup collection eventsCollection contains objects like this:
{
"_id": { "$oid": "62c57125d6943d92f83f6fff" },
"id": "ev0030197",
"text": "#AmLatino Film Festival",
"importance": 1
}
So the "rule" in restoring to original structure is that for each $unwind you did to "deconstruct" the document you now have to do a $group to restore it.
As you can imagine in such a pipeline this could be VERY cumbersome. but definitely doable.
However let me propose a different approach that is still very messy but much easier compared to the alternative, additionally it is more efficient from a performance perspective.
(just minor sidenot the reason your score is still null is because you have a syntax error in your $multiply function)
Anyways, The idea is to first gather all the unique event ids that exist in the in nested documents.
Then execute one lookup to fetch all the relevant events.
And finally adding the score field using $map and $mergeDocuments instead of $unwinding and $grouping, like so:
Mongo Playground
db.collection.aggregate([
{
$addFields: {
allEvents: {
$reduce: {
input: {
$map: {
input: "$principalCredits",
in: {
$map: {
input: "$$this.credits",
as: "credit",
in: {
$map: {
input: "$$credit.name.awardNominations.edges",
as: "edge",
in: "$$edge.node.award.event.id"
}
}
}
}
}
},
initialValue: [],
in: {
"$concatArrays": [
{
"$reduce": {
input: "$$this",
initialValue: [],
in: {
"$concatArrays": [
"$$this",
"$$value"
]
}
}
},
"$$value"
]
}
}
}
}
},
{
"$lookup": {
"from": "eventsCollection",
"localField": "allEvents",
"foreignField": "id",
"as": "matchingEvents"
}
},
{
$addFields: {
principalCredits: {
$map: {
input: "$principalCredits",
in: {
$mergeObjects: [
"$$this",
{
credits: {
$map: {
input: "$$this.credits",
as: "credit",
in: {
$mergeObjects: [
"$$credit",
{
name: {
"$mergeObjects": [
"$$credit.name",
{
"awardNominations": {
"$mergeObjects": [
"$$credit.name.awardNominations",
{
edges: {
$map: {
input: "$$credit.name.awardNominations.edges",
as: "edge",
in: {
node: {
$mergeObjects: [
"$$edge.node",
{
score: {
"$multiply": [
{
$cond: [
"$$edge.node.isWinner",
1.5,
1.2
]
},
{
$first: {
$map: {
input: {
$filter: {
input: "$matchingEvents",
as: "matchedEvent",
cond: {
$eq: [
"$$matchedEvent.id",
"$$edge.node.award.event.id"
]
}
}
},
as: "matched",
in: "$$matched.importance"
}
}
}
]
}
}
]
}
}
}
}
}
]
}
}
]
}
}
]
}
}
}
}
]
}
}
}
}
},
{
$unset: [
"allEvents",
"matchingEvents"
]
}
])
Mongo Playground
I will just mention that you can make this much much much cleaner by involving some code while keeping the same approach suggested. first getting unique eventid with distinct. then fetching the matching importance for each event. Finally execute a single query using arrayFilters you can construct with this information.
Final side not is that the provided pipeline did not deal with null or missing values. So if an array is missing an error will be thrown as $map expects input to be a valid array.
This can easily be solved by just wrapping each of these expressions with $ifNull, like so:
{
$map: {
input: {$ifNull: ["$$this.credits",[]]}
}
}
This will also replace null values with an empty []
The deep buried keys (...award.event.id) in arrays confounds an easy approach without 1) messing up the structure as the OP has noted 2) incurring potentially very expensive multiple $unwind calls.
Recommendation: Two pass approach. Get the necessary importance values for the principalCredits objects in question, then go back and manually iterate over the collection, diving into the structure and applying the logic score = importance * isWinner? 1.2 : 1.5
PASS 1: Get the ev data
c=db.foo.aggregate([
{$project: {
XX: {$reduce: {
// Rapidly get to things we need to lookup:
input: '$principalCredits.credits.name.awardNominations.edges.node.award.event.id',
// We end up with a mess incl. empty arrays...
// [ [[ev1,ev2], [ev3,ev4]], [], [[ev1,...], [] ... ] ]
// Need to collapse all those arrays of arrays of arrays into
// a single list of ev values, hence a reduce within a reduce:
initialValue: [],
in: {$concatArrays: [
'$$value',
{$reduce: {
input: '$$this',
initialValue: [],
in: {$concatArrays: [ '$$value', '$$this' ] }
}} ]}
}}
}}
// XX is now [ ev1,ev2,ev3,ev4,ev1 ... ]
// The empty arrays are ignored. Don't worry about dupes.
,{$lookup: {
from: "Xev",
let: { evids: "$XX" },
pipeline: [
{$match: {$expr: {$in: ["$id","$$evids"]} } }
],
as: 'XX' // overwrite XX...
}}
]);
evdict = {}
c.forEach(function(d) {
d['XX'].forEach(function(ww) {
evdict[ww['id']] = ww;
});
});
{
"ev0003786" : {
"_id" : ObjectId("62cd7f8138d0fbc0eacfb17f"),
"id" : "ev0003786",
"text" : "Millennium Docs Against Gravity",
"importance" : 1
},
"ev0000351" : {
"_id" : ObjectId("62cd7f8138d0fbc0eacfb180"),
"id" : "ev0000351",
"text" : "International Documentary Association",
"importance" : 2
},
"ev0000571" : {
"_id" : ObjectId("62cd7f8138d0fbc0eacfb181"),
"id" : "ev0000571",
"text" : "Royal Television Society, UK",
"importance" : 3
}
}
PASS 2: Iterate main collection
Left as exercise to reader.
Note that if
The number of events is small.
There is no need or value in performing $match on the initial principalCredits collection (i.e. before the fancy $project/$reduce) to significantly reduce the lookup set into events
then this whole thing is unnecessary. Simply slurp all events into evdict with a quick find and proceed to pass 2.
There is potentially a very cool solution that can do this in one pass
UPDATED
See Tom's answer below.
Note to MongoDB 5.0 users: The new $getField function allows you to pluck out fields by name instead of having to use the standard trick of using dot notation in the $in clause to access the field. This might be clearer to some:
{$getField: {
"field": "importance",
"input": {
$first: {
$filter: {
input: "$matchingEvents",
as: "matchedEvent",
cond: {
$eq: [
"$$matchedEvent.id",
"$$edge.node.award.event.id"
]
}
}
}
}
}
}
I have some date in mongo db
[
{
"_id": ObjectId("5a934e000102030405000000"),
"orgId": "606abce197dc265ac41ae82c",
"registrations": {
"id1": {
"status": "status",
"topStage": {
"id": "stage1",
"name": "stage1"
}
},
"id2": {
"status": "status",
"topStage": {
"id": "stage1",
"name": "stage1"
}
},
"id3": {
"status": "status",
"topStage": {
"id": "stage2",
"name": "stage2"
}
}
}
}
]
I am expecting to pass a stage id (at path registrations-> topStage -> id) and return all matching key values.
i have written following query
db.collection.aggregate([
{
$project: {
teams: {
$objectToArray: "$registrations"
},
original: "$$ROOT"
}
},
{
"$project": {
"teams": {
"$filter": {
"input": "$teams",
"as": "team",
"cond": {
"$eq": [
"$$team.v.topStage.id",
"stage1"
]
}
}
}
}
},
{
"$project": {
"registrations": {
"$arrayToObject": "$teams"
}
}
}
])
It does return me right values
for stage1 as stage id
[
{
"_id": ObjectId("5a934e000102030405000000"),
"registrations": {
"id1": {
"status": "status",
"topStage": {
"id": "stage1",
"name": "stage1"
}
},
"id2": {
"status": "status",
"topStage": {
"id": "stage1",
"name": "stage1"
}
}
}
}
]
and for stage2 as stage id, it returns
[
{
"_id": ObjectId("5a934e000102030405000000"),
"registrations": {
"id3": {
"status": "status",
"topStage": {
"id": "stage2",
"name": "stage2"
}
}
}
}
]
Can someone let me know if this is the best way to write this query or this can be simplified ??
It's the correct way to do it but there will be performance impact in the following cases.
If you don't have any other match condition against the indices
if you have a match condition and it matches few docs where registrations has more objects
Other best option you could do is that altering the schema.
you can keep registrations.id1 as registrations : { id:1, status_id: 2}
or you could alter the way such that it will not need to use objectToArray on larger set
if your data is huge, I would recommend to add an index on nested status Id field.
And mongo documentation itself suggests to evaluate multiple schemas for any data to get the best out of it.
Let's say I have two different arrays in two different documents, namely carPolicies[] and paPolicies[]. Evidently, there are policy objects containing a key of agent.
[
{
"_id": "_id",
"name": "qwe",
"password": "pw",
"carPolicies": [
{
"policy": {
"agent": "47"
}
},
],
"paPolicies": [
{
"policy": {
"agent": "47"
}
},
]
},
{
"_id": "_id",
"name": "rty",
"password": "wp",
"carPolicies": [
{
"policy": {
"agent": "47"
}
},
],
"paPolicies": [
{
"policy": {
"agent": "47"
}
},
{
"policy": {
"agent": "99"
}
}
]
}
]
If I do a query such as I have below, it will return me the policies only from carPolicies[] where agent: 47.
db.collection('users').aggregate([
// get just the documents that contain an agent key where agent is === 47
{ $match: { 'carPolicies.policy.agent': req.params.name } },
{
$project: {
policy: {
$filter: {
input: '$carPolicies.policy',
as: 'police',
cond: { $eq: ['$$police.agent', req.params.name ]}
}
}
}
}
])
However, I would like to modify the same query to check paPolicies[] where agent: 47 also. How would I add an $or to be able to check both arrays in one query where agent is 47? Or is there another operator that fits my use case more?
My expected outcome should output:
[
{
"policy": [
{
"agent": "47"
}
]
},
{
"policy": [
{
"agent": "47"
}
]
},
{
"policy": [
{
"agent": "47"
}
]
},
{
"policy": [
{
"agent": "47"
}
]
}
]
There should be 4 policies in the output since in my example, only 4 policies have agent = 47 where one of the policies have an agent = 99 which should not be retrieved.
You can try,
add condition in $match using $or
add paPolicies.policy as input in filter using and $concatArrays
$unwind deconstruct policy array
$project to convert policy as array
db.collection.aggregate([
{
$match: {
$or: [
{ "carPolicies.policy.agent": req.params.name },
{ "paPolicies.policy.agent": req.params.name }
]
}
},
{
$project: {
policy: {
$filter: {
input: {
$concatArrays: ["$carPolicies.policy", "$paPolicies.policy"]
},
as: "police",
cond: { $eq: ["$$police.agent", req.params.name] }
}
}
}
},
{ $unwind: "$policy" },
{
$project: {
_id: 0,
policy: ["$policy"]
}
}
])
Playground
I have a collection which has documents like;
{
"name": "Subject1",
"attributes": [{
"_id": "security_level1",
"level": {
"value": "100",
"valueKey": "ABC"
}
}, {
"_id": "security_score1",
"level": {
"value": "1000",
"valueKey": "CDE"
}
}
]
},
{
"name": "Subject2",
"attributes": [{
"_id": "security_level1",
"level": {
"value": "99",
"valueKey": "XYZ"
}
}, {
"_id": "security_score1",
"level": {
"value": "2000",
"valueKey": "EDF"
}
}
]
},
......
Each document will have so many attributes generated dynamically, can be different in size.
Is it possible to sort records based on level.value of security_level1? (security_level1 is _id field value)
As per above example, the second document ("name": "Subject2") should come first as the value ('level.value') of _id:security_level1 is 99, which is less than of Subject1's security_level1 value (100) - (Ascending order)
Use $filter and $arrayElemAt to get security_level1 item. Then you can use $toInt to convert that value to an integer so that $sort can be applied:
db.collection.aggregate([
{
$addFields: {
level: {
$let: {
vars: {
level_1: { $arrayElemAt: [ { $filter: { input: "$attributes", cond: { $eq: [ "$$this._id", "security_level1" ] } } } ,0] }
},
in: {
$toInt: "$$level_1.level.value"
}
}
}
}
},
{
$sort: {
level: 1
}
}
])
Mongo Playground
I'm trying to make a query to mongodb. I want to get an array containing [location, status] of every document.
This is how my collection looks like
{
"_id": 1,
"status": "OPEN",
"location": "Costa Rica",
"type": "virtual store"
},
{
"_id": 2,
"status": "CLOSED",
"location": "El Salvador"
"type": "virtual store"
},
{
"_id": 3,
"status": "OPEN",
"location": "Mexico",
"type": "physical store"
},
{
"_id": 4,
"status": "CLOSED",
"location": "Nicaragua",
"type": "physical store"
}
I made a query, using the aggregate framework, trying to get all documents that match that specific type of store.
{
{'$match': {
'type': { '$eq': "physical store"}
}
}
What I want is something like this:
{
{
'stores': [
["Mexico", "OPEN"],
["Nicaragua", "CLOSED"]
]
},
}
I tried with the $push but couldn't make it.
Could someone please guide me on how to do it.
Since { $push: ["$location", "$status"] } would give you the error The $push accumulator is a unary operator. You would have to work around it a bit by passing to it a single object that output your desired array. One way to do it would be:
[
{
"$match": {
"type": {
"$eq": "physical store"
}
}
},
{
"$group": {
"_id": null,
"stores": {
"$push": {
"$slice": [["$location", "$status"], 2]
}
}
}
}
]
If the given documents are not sub-documents, then below is the approach:
db.collection.find({
type: {
$eq: "physical store"
}
},
{
location: 1,
status: 1
})
MongoPlayGround link for the above
If, they are the part of a field (means they are sub-documents), then below is the approach:
db.collection.aggregate([
{
$project: {
stores: {
$filter: {
input: "$stores",
as: "store",
cond: {
$eq: [
"$$store.type",
"physical store"
]
}
}
}
}
},
{
$unwind: "$stores"
},
{
$project: {
location: "$stores.location",
status: "$stores.status",
_id: "$stores._id"
}
}
])
MongoPlayGround link for the above