mongodb aggregation multiple lookup with conditions - mongodb

I have 3 collection.
db.a.insert([
{ "_id" : ObjectId("5b56989172ebcb11105e8f41"), "db_type":b, "number" : 1},
{ "_id" : ObjectId("5b56989172ebcb11105e8f42"), "db_type":c, "number" : 2},
])
db.b.insert([
{ "_id" : ObjectId("5b56989172ebcb11105e8f43"), "number" : 1, "value" : "111"},
])
db.c.insert([
{ "_id" : ObjectId("5b56989172ebcb11105e8f44"), "number" : 2, "value" : "222"},
])
I want to make a lookup query that gets values from each collection according to db_type.
What should I do in this case?
result :
{ "_id" : ObjectId("5b56989172ebcb11105e8f41"), "db_type" : b, "number" : 1, "value" : "111"}
{ "_id" : ObjectId("5b56989172ebcb11105e8f42"), "db_type" : c, "number" : 2, "value" : "222"}
clogged part...
db.getCollection('a').aggregate([
{
"$lookup":{
"from": "b" or "c", // I want to give condition here.
"localField": "number",
"foreignField": "number",
"as": "result"
}
},
])

For your case, as you have only 2 cases b and c to lookup from. You can simply do 2 separate lookups and use $setUnion to group the results together.
db.a.aggregate([
{
"$lookup": {
"from": "b",
"let": {
db_type: "$db_type",
number: "$number"
},
"pipeline": [
{
$match: {
$expr: {
$and: [
{
$eq: [
"$$db_type",
"b"
]
},
{
$eq: [
"$$number",
"$number"
]
}
]
}
}
}
],
"as": "bLookup"
}
},
{
"$lookup": {
"from": "c",
"let": {
db_type: "$db_type",
number: "$number"
},
"pipeline": [
{
$match: {
$expr: {
$and: [
{
$eq: [
"$$db_type",
"c"
]
},
{
$eq: [
"$$number",
"$number"
]
}
]
}
}
}
],
"as": "cLookup"
}
},
{
"$addFields": {
"allLookup": {
"$setUnion": [
"$bLookup",
"$cLookup"
]
}
}
}
])
Here is the Mongo playground for your reference.

Related

Mongo DB aggregation with $project and $filter: $add and $subtract return null

So I'm running a pretty big aggregation query in mongo shell (just for testing purpose)
in my last $project step, i use $filter to select a range of elements.
$filter: {
"input": "$users",
"as": "users",
"cond": {
$and: [
{
$lte: [
"$$users.ranking",
{$add: ["$myUser[0].ranking", 5]}
]
},
{
$gte: [
"$$users.ranking",
{$subtract: ["$myUser[0].ranking", 5]}
]
}
]
}
}
$subtract and $add both return null, any idea how i get it correct?
MongoVersion: 3.6.3, running in a docker container using the mongo 3.6.3 image.
Correct output should be:
"users" : [
{
"_id" : ObjectId("5ba3c2089a3a3e26a859f11b"),
"sgId" : ObjectId("5b76c1040c3aa5000559e6b3"),
"score" : 30,
"ranking" : NumberLong("0")
},
{
"_id" : ObjectId("5ba3c1d89a3a3e26a859f11a"),
"sgId" : ObjectId("5b76c1000c3aa500060e0fd2"),
"score" : 20,
"ranking" : NumberLong("1")
},
{
"_id" : ObjectId("5ba4fa3b71936b33e46569b9"),
"sgId" : ObjectId("5b76c8a3f7d606000566b652"),
"score" : 10,
"ranking" : NumberLong("2")
},
{
"_id" : ObjectId("5ba4fa4c71936b33e46569ba"),
"sgId" : ObjectId("5b76cafbf7d6060006270c90"),
"score" : 9,
"ranking" : NumberLong("3")
},
{
"_id" : ObjectId("5ba4fe6e71936b33e46569bb"),
"sgId" : ObjectId("5b7a4e69f7d606000566b65f"),
"score" : 8,
"ranking" : NumberLong("4")
},
{
"_id" : ObjectId("5ba4fe7471936b33e46569bc"),
"sgId" : ObjectId("5b7a4f47f7d6060006270cc4"),
"score" : 7,
"ranking" : NumberLong("5")
},
{
"_id" : ObjectId("5ba4fe8871936b33e46569bd"),
"sgId" : ObjectId("5b7a5265f7d606000566b67e"),
"score" : 6,
"ranking" : NumberLong("6")
}
]
Complete Query:
db.highscore.aggregate([
{
$sort: {score: -1}
},
{
$group: {
"_id": false,
"users": {
$push: {
"_id": "$_id",
"sgId": "$sgId",
"score": "$score",
}
}
}
},
{
$unwind: {
"path": "$users",
"includeArrayIndex": "ranking"
}
},
{
$group: {
"_id": false,
"users": {
$push: {
"_id": "$users._id",
"sgId": "$users.sgId",
"score": "$users.score",
"ranking": "$ranking"
}
}
}
},
{
$project: {
"users": "$users",
"myUser": {
$filter: {
"input": "$users",
"as": "user",
"cond": {
$eq: ["$$user.sgId", ObjectId("5b76c1000c3aa500060e0fd2")]
}
}
}
}
},
{
$project: {
"myUser": "$myUser",
"users" : {
$filter: {
"input": "$users",
"as": "users",
"cond": {
$and: [
{
$lte: [
"$$users.ranking",
{$add: ["$myUser[0].ranking", NumberLong("5")]}
]
},
{
$gte: [
"$$users.ranking",
{$subtract: ["$myUser[0].ranking", NumberLong("5")]}
]
}
]
}
}
}
}
},
])
Used Documents:
{
"_id" : ObjectId("5ba3c1d89a3a3e26a859f11a"),
"sgId" : ObjectId("5b76c1000c3aa500060e0fd2"),
"type" : "a",
"score" : 20,
"created" : ISODate("2018-09-20T17:50:48.024+02:00")
},
{
"_id" : ObjectId("5ba3c2089a3a3e26a859f11b"),
"sgId" : ObjectId("5b76c1040c3aa5000559e6b3"),
"type" : "a",
"score" : 30,
"created" : ISODate("2018-09-20T17:51:36.258+02:00")
},
{
"_id" : ObjectId("5ba4fa3b71936b33e46569b9"),
"sgId" : ObjectId("5b76c8a3f7d606000566b652"),
"type" : "a",
"score" : 10,
"created" : ISODate("2018-09-20T17:50:48.024+02:00")
},
{
"_id" : ObjectId("5ba4fa4c71936b33e46569ba"),
"sgId" : ObjectId("5b76cafbf7d6060006270c90"),
"type" : "a",
"score" : 9,
"created" : ISODate("2018-09-20T17:50:48.024+02:00")
}
Found it,
i just needed to add an $unwind before the last $project to convert the myUser Array into an object - then i was able to reach it for the add.
So full pipeline to get rankings of a highscore list and a range with your given user as source.
db.highscore.aggregate([
{
$sort: {score: -1}
},
{
$group: {
"_id": false,
"users": {
$push: {
"_id": "$_id",
"sgId": "$sgId",
"score": "$score",
}
}
}
},
{
$unwind: {
"path": "$users",
"includeArrayIndex": "ranking"
}
},
{
$group: {
"_id": false,
"users": {
$push: {
"_id": "$users._id",
"sgId": "$users.sgId",
"score": "$users.score",
"ranking": "$ranking"
}
}
}
},
{
$project: {
"users": "$users",
"myUser": {
$filter: {
"input": "$users",
"as": "user",
"cond": {
$eq: ["$$user.sgId", ObjectId("5b76c1000c3aa500060e0fd2")]
}
}
}
}
},
{
$unwind: {
path: '$myUser'
}
},
{
$project: {
"myUser": "$myUser",
"users" : {
$filter: {
"input": "$users",
"as": "users",
"cond": {
$and: [
{
$lte: [
"$$users.ranking",
{$add: ["$myUser.ranking", NumberLong("2")]}
]
},
{
$gte: [
"$$users.ranking",
{$subtract: ["$myUser.ranking", NumberLong("2")]}
]
}
]
}
}
}
}
},
], {'allowDiskUse': true})

exclude fields in $lookup aggregation

I am querying between 3 collections I want to exclude _id everywhere in output
My output is:
{
"_id" : ObjectId("5b6aed5f9bcdb5d4ae64aef5"),
"userID" : "1",
"skills" : [
{
"_id" : ObjectId("5b766b5f1365a4940bb6050f"),
"skillID" : "javaid",
"skillname" : "जावा",
"languageID" : "hindiid"
},
{
"_id" : ObjectId("5b766b8c1365a4940bb60535"),
"skillID" : "pythonid",
"skillname" : "पायथन",
"languageID" : "hindiid"
}
],
"gender" : {
"_id" : ObjectId("5b7687cd2a2329043e2383d5"),
"genderID" : "femaleid",
"gendername" : "महिला",
"languageID" : "hindiid"
}
}
Query:
db.User.aggregate([
{ "$match": { "userID":"1" }},
{ "$lookup":{
"from": "Skill",
"pipeline": [
{ "$match": { "languageID": "hindiid", "skillID": { "$in": [ "javaid","pythonid" ] }}},
],
"as": "skills"
}},
{ "$lookup": {
"from": "Gender",
"pipeline": [
{ "$match": { "languageID": "hindiid", "genderID" : "femaleid" }},
],
"as": "gender"
}},
{ "$unwind": { "path": "$gender", "preserveNullAndEmptyArrays": true }},
{ "$project": { "userID": 1, "skills": 1, "gender": 1 }}
])
In output for every object has _id.Example for skill list every object has _id i want exclude _id field every where. How I can exclude?
In mongodb 3.6 you can use projection ($project) inside $lookup pipeline... Something like this
db.User.aggregate([
{ "$match": { "userID":"1" }},
{ "$lookup":{
"from": "Skill",
"pipeline": [
{ "$match": { "languageID": "hindiid", "skillID": { "$in": [ "javaid","pythonid" ] }}},
{ "$project": { "_id": 0 }}
],
"as": "skills"
}}
])

MongoDB: How to get add filter main collection by second collection using $lookup [duplicate]

How can I add a filter after an $lookup or is there any other method to do this?
My data collection test is:
{ "_id" : ObjectId("570557d4094a4514fc1291d6"), "id" : 100, "value" : "0", "contain" : [ ] }
{ "_id" : ObjectId("570557d4094a4514fc1291d7"), "id" : 110, "value" : "1", "contain" : [ 100 ] }
{ "_id" : ObjectId("570557d4094a4514fc1291d8"), "id" : 120, "value" : "1", "contain" : [ 100 ] }
{ "_id" : ObjectId("570557d4094a4514fc1291d9"), "id" : 121, "value" : "2", "contain" : [ 100, 120 ] }
I select id 100 and aggregate the childs:
db.test.aggregate([ {
$match : {
id: 100
}
}, {
$lookup : {
from : "test",
localField : "id",
foreignField : "contain",
as : "childs"
}
}]);
I get back:
{
"_id":ObjectId("570557d4094a4514fc1291d6"),
"id":100,
"value":"0",
"contain":[ ],
"childs":[ {
"_id":ObjectId("570557d4094a4514fc1291d7"),
"id":110,
"value":"1",
"contain":[ 100 ]
},
{
"_id":ObjectId("570557d4094a4514fc1291d8"),
"id":120,
"value":"1",
"contain":[ 100 ]
},
{
"_id":ObjectId("570557d4094a4514fc1291d9"),
"id":121,
"value":"2",
"contain":[ 100, 120 ]
}
]
}
But I want only childs that match with "value: 1"
At the end I expect this result:
{
"_id":ObjectId("570557d4094a4514fc1291d6"),
"id":100,
"value":"0",
"contain":[ ],
"childs":[ {
"_id":ObjectId("570557d4094a4514fc1291d7"),
"id":110,
"value":"1",
"contain":[ 100 ]
},
{
"_id":ObjectId("570557d4094a4514fc1291d8"),
"id":120,
"value":"1",
"contain":[ 100 ]
}
]
}
The question here is actually about something different and does not need $lookup at all. But for anyone arriving here purely from the title of "filtering after $lookup" then these are the techniques for you:
MongoDB 3.6 - Sub-pipeline
db.test.aggregate([
{ "$match": { "id": 100 } },
{ "$lookup": {
"from": "test",
"let": { "id": "$id" },
"pipeline": [
{ "$match": {
"value": "1",
"$expr": { "$in": [ "$$id", "$contain" ] }
}}
],
"as": "childs"
}}
])
Earlier - $lookup + $unwind + $match coalescence
db.test.aggregate([
{ "$match": { "id": 100 } },
{ "$lookup": {
"from": "test",
"localField": "id",
"foreignField": "contain",
"as": "childs"
}},
{ "$unwind": "$childs" },
{ "$match": { "childs.value": "1" } },
{ "$group": {
"_id": "$_id",
"id": { "$first": "$id" },
"value": { "$first": "$value" },
"contain": { "$first": "$contain" },
"childs": { "$push": "$childs" }
}}
])
If you question why would you $unwind as opposed to using $filter on the array, then read Aggregate $lookup Total size of documents in matching pipeline exceeds maximum document size for all the detail on why this is generally necessary and far more optimal.
For releases of MongoDB 3.6 and onwards, then the more expressive "sub-pipeline" is generally what you want to "filter" the results of the foreign collection before anything gets returned into the array at all.
Back to the answer though which actually describes why the question asked needs "no join" at all....
Original
Using $lookup like this is not the most "efficient" way to do what you want here. But more on this later.
As a basic concept, just use $filter on the resulting array:
db.test.aggregate([
{ "$match": { "id": 100 } },
{ "$lookup": {
"from": "test",
"localField": "id",
"foreignField": "contain",
"as": "childs"
}},
{ "$project": {
"id": 1,
"value": 1,
"contain": 1,
"childs": {
"$filter": {
"input": "$childs",
"as": "child",
"cond": { "$eq": [ "$$child.value", "1" ] }
}
}
}}
]);
Or use $redact instead:
db.test.aggregate([
{ "$match": { "id": 100 } },
{ "$lookup": {
"from": "test",
"localField": "id",
"foreignField": "contain",
"as": "childs"
}},
{ "$redact": {
"$cond": {
"if": {
"$or": [
{ "$eq": [ "$value", "0" ] },
{ "$eq": [ "$value", "1" ] }
]
},
"then": "$$DESCEND",
"else": "$$PRUNE"
}
}}
]);
Both get the same result:
{
"_id":ObjectId("570557d4094a4514fc1291d6"),
"id":100,
"value":"0",
"contain":[ ],
"childs":[ {
"_id":ObjectId("570557d4094a4514fc1291d7"),
"id":110,
"value":"1",
"contain":[ 100 ]
},
{
"_id":ObjectId("570557d4094a4514fc1291d8"),
"id":120,
"value":"1",
"contain":[ 100 ]
}
]
}
Bottom line is that $lookup itself cannot "yet" query to only select certain data. So all "filtering" needs to happen after the $lookup
But really for this type of "self join" you are better off not using $lookup at all and avoiding the overhead of an additional read and "hash-merge" entirely. Just fetch the related items and $group instead:
db.test.aggregate([
{ "$match": {
"$or": [
{ "id": 100 },
{ "contain.0": 100, "value": "1" }
]
}},
{ "$group": {
"_id": {
"$cond": {
"if": { "$eq": [ "$value", "0" ] },
"then": "$id",
"else": { "$arrayElemAt": [ "$contain", 0 ] }
}
},
"value": { "$first": { "$literal": "0"} },
"childs": {
"$push": {
"$cond": {
"if": { "$ne": [ "$value", "0" ] },
"then": "$$ROOT",
"else": null
}
}
}
}},
{ "$project": {
"value": 1,
"childs": {
"$filter": {
"input": "$childs",
"as": "child",
"cond": { "$ne": [ "$$child", null ] }
}
}
}}
])
Which only comes out a little different because I deliberately removed the extraneous fields. Add them in yourself if you really want to:
{
"_id" : 100,
"value" : "0",
"childs" : [
{
"_id" : ObjectId("570557d4094a4514fc1291d7"),
"id" : 110,
"value" : "1",
"contain" : [ 100 ]
},
{
"_id" : ObjectId("570557d4094a4514fc1291d8"),
"id" : 120,
"value" : "1",
"contain" : [ 100 ]
}
]
}
So the only real issue here is "filtering" any null result from the array, created when the current document was the parent in processing items to $push.
What you also seem to be missing here is that the result you are looking for does not need aggregation or "sub-queries" at all. The structure that you have concluded or possibly found elsewhere is "designed" so that you can get a "node" and all of it's "children" in a single query request.
That means just the "query" is all that is really needed, and the data collection ( which is all that is happening since no content is really being "reduced" ) is just a function of iterating the cursor result:
var result = {};
db.test.find({
"$or": [
{ "id": 100 },
{ "contain.0": 100, "value": "1" }
]
}).sort({ "contain.0": 1 }).forEach(function(doc) {
if ( doc.id == 100 ) {
result = doc;
result.childs = []
} else {
result.childs.push(doc)
}
})
printjson(result);
This does exactly the same thing:
{
"_id" : ObjectId("570557d4094a4514fc1291d6"),
"id" : 100,
"value" : "0",
"contain" : [ ],
"childs" : [
{
"_id" : ObjectId("570557d4094a4514fc1291d7"),
"id" : 110,
"value" : "1",
"contain" : [
100
]
},
{
"_id" : ObjectId("570557d4094a4514fc1291d8"),
"id" : 120,
"value" : "1",
"contain" : [
100
]
}
]
}
And serves as proof that all you really need to do here is issue the "single" query to select both the parent and children. The returned data is just the same, and all you are doing on either server or client is "massaging" into another collected format.
This is one of those cases where you can get "caught up" in thinking of how you did things in a "relational" database, and not realize that since the way the data is stored has "changed", you no longer need to use the same approach.
That is exactly what the point of the documentation example "Model Tree Structures with Child References" in it's structure, where it makes it easy to select parents and children within one query.

MongoDB join data inside an array of objects

I have document like this in a collection called diagnoses :
{
"_id" : ObjectId("582d43d18ec3f432f3260682"),
"patientid" : ObjectId("582aacff3894c3afd7ad4677"),
"doctorid" : ObjectId("582a80c93894c3afd7ad4675"),
"medicalcondition" : "high fever, cough, runny nose.",
"diagnosis" : "Viral Flu",
"addmissiondate" : "2016-01-12",
"dischargedate" : "2016-01-16",
"bhtno" : "125",
"prescription" : [
{
"drug" : ObjectId("58345e0e996d340bd8126149"),
"instructions" : "Take 2 daily, after meals."
},
{
"drug" : ObjectId("5836bc0b291918eb42966320"),
"instructions" : "Take 1 daily, after meals."
}
]
}
The drug id inside the prescription object array is from a separate collection called drugs, see sample document below :
{
"_id" : ObjectId("58345e0e996d340bd8126149"),
"genericname" : "Paracetamol Tab 500mg",
"type" : "X",
"isbrand" : false
}
I am trying to create a mongodb query using the native node.js driver to get a result like this:
{
"_id" : ObjectId("582d43d18ec3f432f3260682"),
"patientid" : ObjectId("582aacff3894c3afd7ad4677"),
"doctorid" : ObjectId("582a80c93894c3afd7ad4675"),
"medicalcondition" : "high fever, cough, runny nose.",
"diagnosis" : "Viral Flu",
"addmissiondate" : "2016-01-12",
"dischargedate" : "2016-01-16",
"bhtno" : "125",
"prescription" : [
{
"drug" :
{
"_id" : ObjectId("58345e0e996d340bd8126149"),
"genericname" : "Paracetamol Tab 500mg",
"type" : "X",
"isbrand" : false
},
"instructions" : "Take 2 daily, after meals."
},
...
]
}
Any advice on how to approach a similar result like this is much appreciated, thanks.
Using MongoDB 3.4.4 and newer
With the aggregation framework, the $lookup operators supports arrays
db.diagnoses.aggregate([
{ "$addFields": {
"prescription": { "$ifNull" : [ "$prescription", [ ] ] }
} },
{ "$lookup": {
"from": "drugs",
"localField": "prescription.drug",
"foreignField": "_id",
"as": "drugs"
} },
{ "$addFields": {
"prescription": {
"$map": {
"input": "$prescription",
"in": {
"$mergeObjects": [
"$$this",
{ "drug": {
"$arrayElemAt": [
"$drugs",
{
"$indexOfArray": [
"$drugs._id",
"$$this.drug"
]
}
]
} }
]
}
}
}
} },
{ "$project": { "drugs": 0 } }
])
For older MongoDB versions:
You can create a pipeline that first flattens the prescription array using the $unwind operator and a $lookup subsequent pipeline step to do a "left outer join" on the "drugs" collection. Apply another $unwind operation on the created array from the "joined" field. $group the previously flattened documents from the first pipeline where there $unwind operator outputs a document for each element in the prescription array.
Assembling the above pipeline, run the following aggregate operation:
db.diagnoses.aggregate([
{
"$project": {
"patientid": 1,
"doctorid": 1,
"medicalcondition": 1,
"diagnosis": 1,
"addmissiondate": 1,
"dischargedate": 1,
"bhtno": 1,
"prescription": { "$ifNull" : [ "$prescription", [ ] ] }
}
},
{
"$unwind": {
"path": "$prescription",
"preserveNullAndEmptyArrays": true
}
},
{
"$lookup": {
"from": "drugs",
"localField": "prescription.drug",
"foreignField": "_id",
"as": "prescription.drug"
}
},
{ "$unwind": "$prescription.drug" },
{
"$group": {
"_id": "$_id",
"patientid" : { "$first": "$patientid" },
"doctorid" : { "$first": "$doctorid" },
"medicalcondition" : { "$first": "$medicalcondition" },
"diagnosis" : { "$first": "$diagnosis" },
"addmissiondate" : { "$first": "$addmissiondate" },
"dischargedate" : { "$first": "$dischargedate" },
"bhtno" : { "$first": "$bhtno" },
"prescription" : { "$push": "$prescription" }
}
}
])
Sample Output
{
"_id" : ObjectId("582d43d18ec3f432f3260682"),
"patientid" : ObjectId("582aacff3894c3afd7ad4677"),
"doctorid" : ObjectId("582a80c93894c3afd7ad4675"),
"medicalcondition" : "high fever, cough, runny nose.",
"diagnosis" : "Viral Flu",
"addmissiondate" : "2016-01-12",
"dischargedate" : "2016-01-16",
"bhtno" : "125",
"prescription" : [
{
"drug" : {
"_id" : ObjectId("58345e0e996d340bd8126149"),
"genericname" : "Paracetamol Tab 500mg",
"type" : "X",
"isbrand" : false
},
"instructions" : "Take 2 daily, after meals."
},
{
"drug" : {
"_id" : ObjectId("5836bc0b291918eb42966320"),
"genericname" : "Paracetamol Tab 100mg",
"type" : "Y",
"isbrand" : false
},
"instructions" : "Take 1 daily, after meals."
}
]
}
In MongoDB 3.6 or later versions
It seems that
$lookup will overwrite the original array instead of merging it.
A working solution (a workaround, if you prefer) is to create a different field,
and then merge two fields, as shown below:
db.diagnoses.aggregate([
{ "$lookup": {
"from": "drugs",
"localField": "prescription.drug",
"foreignField": "_id",
"as": "prescription_drug_info"
} },
{ "$addFields": {
"merged_drug_info": {
"$map": {
"input": "$prescription",
"in": {
"$mergeObjects": [
"$$this",
{ "$arrayElemAt": [
"$prescription_drug_info._id",
"$$this._id"
] }
]
}
}
}
} }
])
This would add two more fields and the name of the desired field
will be merged_drug_info. We can then add $project stage to filter
out excessive fields and $set stage to rename the field:
...
{ "$set": { "prescription": "$merged_drug_info" } },
{ "$project": { "prescription_drug_info": 0, "merged_drug_info": 0 } }
...

Nested filters: $filter array, then $filter child array

Essentially I'm trying to filter OUT subdocuments and sub-subdocuments that have been "trashed". Here's a stripped-down version of my schema:
permitSchema = {
_id,
name,
...
feeClassifications: [
new Schema({
_id,
_trashed,
name,
fees: [
new Schema({
_id,
_trashed,
name,
amount
})
]
})
],
...
}
So I'm able to get the effect I want with feeClassifications. But I'm struggling to find a way to have the same effect for feeClassifications.fees as well.
So, this works as desired:
Permit.aggregate([
{ $match: { _id: mongoose.Types.ObjectId(req.params.id) }},
{ $project: {
_id: 1,
_name: 1,
feeClassifications: {
$filter: {
input: '$feeClassifications',
as: 'item',
cond: { $not: {$gt: ['$$item._trashed', null] } }
}
}
}}
])
But I also want to filter the nested array fees. I've tried a few things including:
Permit.aggregate([
{ $match: { _id: mongoose.Types.ObjectId(req.params.id) }},
{ $project: {
_id: 1,
_name: 1,
feeClassifications: {
$filter: {
input: '$feeClassifications',
as: 'item',
cond: { $not: {$gt: ['$$item._trashed', null] } }
},
fees: {
$filter: {
input: '$fees',
as: 'fee',
cond: { $not: {$gt: ['$$fee._trashed', null] } }
}
}
}
}}
])
Which seems to follow the mongodb docs the closest. But I get the error:
this object is already an operator expression, and can't be used as a document expression (at 'fees')
Update: -----------
As requested, here's a sample document:
{
"_id" : ObjectId("57803fcd982971e403e3e879"),
"_updated" : ISODate("2016-07-11T19:24:27.204Z"),
"_created" : ISODate("2016-07-09T00:05:33.274Z"),
"name" : "Single Event",
"feeClassifications" : [
{
"_updated" : ISODate("2016-07-11T19:05:52.418Z"),
"_created" : ISODate("2016-07-11T17:49:12.247Z"),
"name" : "Event Type 1",
"_id" : ObjectId("5783dc18e09be99840fad29f"),
"fees" : [
{
"_updated" : ISODate("2016-07-11T18:51:10.259Z"),
"_created" : ISODate("2016-07-11T18:41:16.110Z"),
"name" : "Basic Fee",
"amount" : 156.5,
"_id" : ObjectId("5783e84cc46a883349bb2339")
},
{
"_updated" : ISODate("2016-07-11T19:05:52.419Z"),
"_created" : ISODate("2016-07-11T19:05:47.340Z"),
"name" : "Secondary Fee",
"amount" : 50,
"_id" : ObjectId("5783ee0bad7bf8774f6f9b5f"),
"_trashed" : ISODate("2016-07-11T19:05:52.410Z")
}
]
},
{
"_updated" : ISODate("2016-07-11T18:22:21.567Z"),
"_created" : ISODate("2016-07-11T18:22:21.567Z"),
"name" : "Event Type 2",
"_id" : ObjectId("5783e3dd540078de45bbbfaf"),
"_trashed" : ISODate("2016-07-11T19:24:27.203Z")
}
]
}
And here's the desired output ("trashed" subdocuments are excluded from BOTH feeClassifications AND fees):
{
"_id" : ObjectId("57803fcd982971e403e3e879"),
"_updated" : ISODate("2016-07-11T19:24:27.204Z"),
"_created" : ISODate("2016-07-09T00:05:33.274Z"),
"name" : "Single Event",
"feeClassifications" : [
{
"_updated" : ISODate("2016-07-11T19:05:52.418Z"),
"_created" : ISODate("2016-07-11T17:49:12.247Z"),
"name" : "Event Type 1",
"_id" : ObjectId("5783dc18e09be99840fad29f"),
"fees" : [
{
"_updated" : ISODate("2016-07-11T18:51:10.259Z"),
"_created" : ISODate("2016-07-11T18:41:16.110Z"),
"name" : "Basic Fee",
"amount" : 156.5,
"_id" : ObjectId("5783e84cc46a883349bb2339")
}
]
}
]
}
Since we want to filter both the outer and inner array fields, we can use the $map variable operator which return an array with the "values" we want.
In the $map expression, we provide a logical $conditional $filter to remove the non matching documents from both the document and subdocument array field.
The conditions are $lt which return true when the field "_trashed" is absent in the sub-document and or in the sub-document array field.
Note that in the $cond expression we also return false for the <false case>. Of course we need to apply filter to the $map result to remove all false.
Permit.aggregate(
[
{ "$match": { "_id": mongoose.Types.ObjectId(req.params.id) } },
{ "$project": {
"_updated": 1,
"_created": 1,
"name": 1,
"feeClassifications": {
"$filter": {
"input": {
"$map": {
"input": "$feeClassifications",
"as": "fclass",
"in": {
"$cond": [
{ "$lt": [ "$$fclass._trashed", 0 ] },
{
"_updated": "$$fclass._updated",
"_created": "$$fclass._created",
"name": "$$fclass.name",
"_id": "$$fclass._id",
"fees": {
"$filter": {
"input": "$$fclass.fees",
"as": "fees",
"cond": { "$lt": [ "$$fees._trashed", 0 ] }
}
}
},
false
]
}
}
},
"as": "cls",
"cond": "$$cls"
}
}
}}
]
)
In the upcoming MongoDB release (as of this writing and since MongoDB 3.3.5), You can replace the $cond expression in the the $map expression with a $switch expression:
Permit.aggregate(
[
{ "$match": { "_id": mongoose.Types.ObjectId(req.params.id) } },
{ "$project": {
"_updated": 1,
"_created": 1,
"name": 1,
"feeClassifications": {
"$filter": {
"input": {
"$map": {
"input": "$feeClassifications",
"as": "fclass",
"in": {
"$switch": {
"branches": [
{
"case": { "$lt": [ "$$fclass._trashed", 0 ] },
"then": {
"_updated": "$$fclass._updated",
"_created": "$$fclass._created",
"name": "$$fclass.name",
"_id": "$$fclass._id",
"fees": {
"$filter": {
"input": "$$fclass.fees",
"as": "fees",
"cond": { "$lt": [ "$$fees._trashed", 0 ] }
}
}
}
}
],
"default": false
}
}
}
},
"as": "cls",
"cond": "$$cls"
}
}
}}
]
)
For more complicated bigdats, it would be unnecessarily difficult.
Just edit it in $filter input by adding a dotted annotation field.You can search the document to any depth of JSON by dotted annotation without further complicated $filter mapping.
"$filter":{
"input": "$feeClassifications._trashed",
"as": "trashed",
"cond": { "$lt": [ "$$trashed._trashed", 0 ] }
}