Related
Colleges
/* 1 createdAt:5/9/2019, 7:00:04 PM*/
{
"_id" : ObjectId("5cd42b5c65b41027845938ae"),
"clgID" : "100",
"name" : "Anna University"
},
/* 2 createdAt:5/9/2019, 7:00:04 PM*/
{
"_id" : ObjectId("5cd42b5c65b41027845938ad"),
"clgID" : "200",
"name" : "National"
}
Subjects:
/* 1 createdAt:5/9/2019, 7:03:24 PM*/
{
"_id" : ObjectId("5cd42c2465b41027845938b0"),
"name" : "Hindi",
"members" : {
"student" : [
"123"
]
},
"college" : {
"collegeID" : "100"
}
},
/* 2 createdAt:5/9/2019, 7:03:24 PM*/
{
"_id" : ObjectId("5cd42c2465b41027845938af"),
"name" : "English",
"members" : {
"student" : [
"456",
"789"
]
},
"college" : {
"collegeID" : "100"
}
}
Here i am having two collection and i want to join Colleges table is clgID and Subjects table iscollege.collegeID , then i want to take members.student values and push into single array based on college.collegeID.
My Expected Output
{
"GroupDetails" : [ ],
"clgName" : "National"
},
{
"GroupDetails" : [
"123",
"456",
"789"
],
"clgName" : "Anna University"
}
My Code
db.Colleges.aggregate([
{ $match : { "clgID" : { $in : ["100", "200"] } } },
{ $lookup: { from: "Subjects", localField: "clgID", foreignField: "college.collegeID", as: "GroupDetails" } },
//{ $unwind: "$GroupDetails" },
{ $project: { '_id' : false, 'clgName' : '$name', 'GroupDetails.members.student' : true } }
])
I am getting like this
/* 1 */
{
"GroupDetails" : [ ],
"clgName" : "National"
},
/* 2 */
{
"GroupDetails" : [
{
"members" : {
"student" : [
"456"
]
}
},
{
"members" : {
"student" : [
"123"
]
}
}
],
"clgName" : "Anna University"
}
You can use below aggregation with mongodb 3.6 and above
db.Colleges.aggregate([
{ "$match": { "clgID": { "$in": ["100", "200"] } } },
{ "$lookup": {
"from": "Subjects",
"let": { "clgId": "$clgID" },
"pipeline": [
{ "$match": { "$expr": { "$eq": ["$$clgId", "$college.collegeID"] } } },
{ "$group": {
"_id": "$college.collegeID",
"groupDetails": { "$push": "$members.student" }
}},
{ "$project": {
"groupDetails": {
"$reduce": {
"input": "$groupDetails",
"initialValue": [],
"in": { "$concatArrays": ["$$this", "$$value"] }
}
}
}}
],
"as": "clg"
}},
{ "$unwind": { "path": "$clg", "preserveNullAndEmptyArrays": true } },
{ "$project": {
"clgName": "$name",
"groupDetails": { "$ifNull": ["$clg.groupDetails", []] }
}}
])
MongoPlayground
Or with the mongodb 3.4 and below
db.Colleges.aggregate([
{ "$match": { "clgID": { "$in": ["100", "200"] }}},
{ "$lookup": {
"from": "Subjects",
"localField": "clgID",
"foreignField": "college.collegeID",
"as": "clg"
}},
{ "$unwind": { "path": "$clg", "preserveNullAndEmptyArrays": true }},
{ "$group": {
"_id": { "clgId": "$clg.college.collegeID", "_id": "$_id" },
"groupDetails": { "$push": "$clg.members.student" },
"clgName": { "$first": "$name" }
}},
{ "$project": {
"_id": "$_id._id",
"clgName": 1,
"groupDetails": {
"$reduce": {
"input": "$groupDetails",
"initialValue": [],
"in": { "$concatArrays": ["$$this", "$$value"] }
}
}
}}
])
MongoPlayground
Mongo query generated out of java code:
{
"pipeline": [{
"$match": {
"Id": "09cd9a5a-85c5-4948-808b-20a52d92381a"
}
},
{
"$group": {
"_id": "$result",
"id": {
"$first": "$result"
},
"labelKey": {
"$first": {
"$ifNull": ["$result",
"$result"]
}
},
"value": {
"$sum": 1
}
}
}]
}
Field 'result' can have values like Approved, Rejected, null and "" (empty string). What I am trying to achieve is combining the count of both null and empty together.
So that the empty string Id will have the count of both null and "", which is equal to 4
I'm sure theres a more "proper" way but this is what i could quickly come up with:
[
{
"$group" : {
"_id" : "$result",
"id" : {
"$first" : "$result"
},
"labelKey" : {
"$first" : {
"$ifNull" : [
"$result",
"$result"
]
}
},
"value" : {
"$sum" : 1.0
}
}
},
{
"$group" : {
"_id" : {
"$cond" : [{
$or: [
{"$eq": ["$_id", "Approved"]},
{"$eq": ["$_id", "Rejected"]},
]}},
"$_id",
""
]
},
"temp" : {
"$push" : {
"_id" : "$_id",
"labelKey" : "$labelKey"
}
},
"count" : {
"$sum" : "$value"
}
}
},
{
"$unwind" : "$temp"
},
{
"$project" : {
"_id" : "$temp._id",
"labelKey": "$temp.labelKey",
"count" : "$count"
}
}
],
);
Due to the fact the second group is only on 4 documents tops i don't feel too bad about doing this.
I have used $facet.
The MongoDB stage $facet lets you run several independent pipelines within the stage of a pipeline, all using the same data. This means that you can run several aggregations with the same preliminary stages, and successive stages.
var queries = [{
"$match": {
"Id": "09cd9a5a-85c5-4948-808b-20a52d92381a"
}
},{
$facet: {//
"empty": [
{
$match : {
result : { $in : ['',null]}
}
},{
"$group" : {
"_id" : null,
value : { $sum : 1}
}
}
],
"non_empty": [
{
$match : {
result : { $nin : ['',null]}
}
},{
"$group" : {
"_id" : '$result',
value : { $sum : 1}
}
}
]
}
},
{
$project: {
results: {
$concatArrays: [ "$empty", "$non_empty" ]
}
}
}];
Output :
{
"results": [{
"_id": null,
"value": 52 // count of both '' and null.
}, {
"_id": "Approved",
"value": 83
}, {
"_id": "Rejected",
"value": 3661
}]
}
Changing the group by like below solved the problem
{
"$group": {
"_id": {
"$ifNull": ["$result", ""]
},
"id": {
"$first": "$result"
},
"labelKey": {
"$first": {
"$ifNull": ["$result",
"$result"]
}
},
"value": {
"$sum": 1
}
}
}
Given this function, I have a data set that I am querying. The data looks like this:
db.activity.insert(
{
"_id" : ObjectId("5908e64e3b03ca372dc945d5"),
"startDate" : ISODate("2017-05-06T00:00:00Z"),
"details" : [
{
"code" : "2",
"_id" : ObjectId("5908ebf96ae5003a4471c9b2"),
"walkDistance" : "03",
"jogDistance" : "01",
"runDistance" : "08",
"sprintDistance" : "01"
}
]
}
)
db.activity.insert(
{
"_id" : ObjectId("58f79163bebac50d5b2ae760"),
"startDate" : ISODate("2017-05-07T00:00:00Z"),
"details" : [
{
"code" : "2",
"_id" : ObjectId("58f7948fbebac50d5b2ae7f2"),
"walkDistance" : "01",
"jogDistance" : "02",
"runDistance" : "09",
"sprintDistance" : ""
}
]
}
)
Using this function, thanks to Neil Lunn, I am able to get my desired output:
db.activity.aggregate([
{ "$project": {
"_id": 0,
"unique": {
"$filter": {
"input": {
"$setDifference": [
{ "$concatArrays": [
"$details.walkDistance",
"$details.jogDistance",
"$details.runDistance",
"$details.sprintDistance"
]},
[]
]
},
"cond": { "$ne": [ "$$this", "" ] }
}
}
}},
{ "$unwind": "$unique" },
{ "$group": {
"_id": null,
"uniqueArray": { "$addToSet": "$unique" }
}}
])
However, I cannot add a match statement to the beginning.
db.activity.aggregate([
{$match: {"startDate" : ISODate("2017-05-06T00:00:00Z"), "details.code": "2" },
{$unwind: '$details'},
{$match: {"startDate" : ISODate("2017-05-06T00:00:00Z"), "details.code": "2" },
{ "$project": {
"_id": 0,
"unique": {
"$filter": {
"input": {
"$setDifference": [
{ "$concatArrays": [
"$details.walkDistance",
"$details.jogDistance",
"$details.runDistance",
"$details.sprintDistance"
]},
[]
]
},
"cond": { "$ne": [ "$$this", "" ] }
}
}
}},
{ "$unwind": "$unique" },
{ "$group": {
"_id": null,
"uniqueArray": { "$addToSet": "$unique" }
}}
])
Because it gives an error message of:
> $concatArrays only supports arrays, not string
How can I modify this query so that a $match statement can be added?
Don't $unwind the array you are feeding to $concatArrays. Instead apply $filter to only extract the matching values. And as stated, we can just use $setUnion for the 'unique concatenation' instead:
db.activity.aggregate([
{ "$match": { "startDate" : ISODate("2017-05-06T00:00:00Z"), "details.code": "2" } },
{ "$project": {
"_id": 0,
"unique": {
"$let": {
"vars": {
"filtered": {
"$filter": {
"input": "$details",
"cond": { "$eq": [ "$$this.code", "2" ] }
}
}
},
"in": {
"$setDifference": [
{ "$setUnion": [
"$$filtered.walkDistance",
"$$filtered.jogDistance",
"$$filtered.runDistance",
"$$filtered.sprintDistance"
]},
[""]
]
}
}
}
}},
{ "$unwind": "$unique" },
{ "$group": {
"_id": null,
"uniqueArray": { "$addToSet": "$unique" }
}}
])
Using $let makes things a bit cleaner syntax wise since you don't need to specify multiple $map and $filter statements "inline" as the source for $setUnion
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 ] }
}
{
"_id" : ObjectId("56fb04fd2e6bb8bc059287c9"),
"BillNo" : "Bill_001",
"DateP" : "12-12-2015",
"Type" : "Cash",
"Items" : [
{
"id" : NumberInt(1),
"ItemName" : "cement",
"Qty" : "100",
"Rate" : "10",
"Total" : "1000"
},
{
"id" : NumberInt(2),
"ItemName" : "steel",
"Qty" : "10",
"Rate" : "50",
"Total" : "500"
},
{
"id" : NumberInt(3),
"ItemName" : "sand",
"Qty" : "1",
"Rate" : "1500",
"Total" : "1500"
}
]
}
{
"_id" : ObjectId("56fb05382e6bb8bc059287ca"),
"BillNo" : "Bill_002",
"DateP" : "12-10-2015",
"Type" : "Cash",
"Items" : [
{
"id" : NumberInt(1),
"ItemName" : "Paint",
"Qty" : "50",
"Rate" : "100",
"Total" : "5000"
},
{
"id" : NumberInt(2),
"ItemName" : "Brush",
"Qty" : "5",
"Rate" : "10",
"Total" : "50"
}
]
}
In the above collection stores all the purchase details in main document and its Items details storing as inner array of main item.I need to get the result like following by using mongodb; How to find total from inner array in mongodb.
Bill_001 1500
Bill_002 5050
Ideally in MongoDB you can use $map with $sum as both an $group accumulator and it's new role in adding the members of the provided array:
db.collection.aggregate({
{ "$group": {
"_id": "$BillNo",
"Total": {
"$sum": {
"$sum": {
"$map": {
"input": "$Items",
"as": "item",
"in": "$$item.Total"
}
}
}
}
}}
})
Or just per document:
db.collection.aggregate({
{ "$group": {
"_id": "$_id",
"BillNo": { "$first": "$BillNo" },
"DateP": { "$first" "$DateP" },
"Type": { "$first": "$Type" }
"Total": {
"$sum": {
"$sum": {
"$map": {
"input": "$Items",
"as": "item",
"in": "$$item.Total"
}
}
}
}
}}
})
Using the other accumulator of $first. Of course you could really just $project With MongoDB 3.2:
db.collection.aggregate({
{ "$project": {
"BillNo": 1,
"DateP": 1,
"Type": 1,
"Total": {
"$sum": {
"$map": {
"input": "$Items",
"as": "item",
"in": "$$item.Total"
}
}
}
}}
})
In older versions you still need $unwind on the array first:
db.collection.aggregate([
{ "$unwind": "$Items" },
{ "$group": {
"_id": "$BillNo",
"Total": {
"$sum": "$Items.Total"
}
}}
])
Or if you are only adding per document:
db.collection.aggregate([
{ "$unwind": "$Items" },
{ "$group": {
"_id": "_id",
"BillNo": { "$first": "$BillNo" },
"DateP": { "$first": "$DateP" },
"Type": { "$first": "$Type" },
"Total": {
"$sum": "$Items.Total"
}
}}
])
But only of course once you actually fix the strings to be numeric values.
Ideally you can fix it like this:
var ops = [];
db.collection.find().forEach(function(doc) {
doc.Items.forEach(function(item) {
ops.push({
"updateOne": {
"filter": { "_id": doc._id, "Items.id": item.id },
"update": {
"$set": {
"Items.$.Qty": parseInt(item.Qty),
"Items.$.Rate": parseInt(item.Rate),
"Items.$Total": parseInt(item.Total)
}
}
}
});
// Send batch of updates
if ( ops.length == 1000 ) {
db.collection.bulkWrite(ops);
ops = [];
}
})
});
// Clear any unprocessed updates
if ( ops.length > 0 ) {
db.collection.bulkWrite(ops);
}