MongoDB avoid duplicates using $addToSet in aggregation pipeline - mongodb

Question

there is aggregation pipeline:
db.getCollection('yourCollection').aggregate(
{
$unwind: {
path: "$dates",
includeArrayIndex: "idx"
}
},
{
$project: {
_id: 0,
dates: 1,
numbers: { $arrayElemAt: ["$numbers", "$idx"] },
goals: { $arrayElemAt: ["$goals", "$idx"] },
durations: { $arrayElemAt: ["$durations", "$idx"] }
}
}
)
which perform on the following data (sample documents):
{
"_id" : ObjectId("52d017d4b60fb046cdaf4851"),
"dates" : [
1399518702000,
1399126333000,
1399209192000,
1399027545000
],
"dress_number" : "4",
"name" : "J. Evans",
"numbers" : [
"5982",
"5983",
"5984",
"5985"
],
"goals": [
"1",
"0",
"4",
"2"
],
"durations": [
"78",
"45",
"90",
"90"
]
}
{
"_id" : ObjectId("57e250c1b60fb0213d06737c"),
"dates" : [
"1399027545000",
"1399101432000",
"1399026850000",
"1399904504000"
],
"dress_number" : "6",
"name" : K. Mitnick,
"numbers" : [
"0982",
"0981",
"0958",
"0982"
],
"durations" : [
98,
110,
66,
92
],
"goals" : [
"2",
"3",
"0",
"1"
]
}
The query works good, but there are duplicate records so I'm trying to use $addToSet operator to avoid duplicates:
db.getCollection('yourCollection').aggregate(
{
$match: {
"number": number
}
},
{
$unwind: {
path: "$dates",
includeArrayIndex: "idx"
}
},
$group: {
_id: '$_id',
dates: { $addToSet: '$dates' }
},
{
$project: {
_id: 0,
dates: 1,
numbers: { $arrayElemAt: ["$numbers", "$idx"] },
goals: { $arrayElemAt: ["$goals", "$idx"] },
durations: { $arrayElemAt: ["$durations", "$idx"] }
}
}
)
but I got only dates (other field are null)
{ dates:
[ '1399026850000',
'1399101432000',
'1399027545000',
'1399904504000',
'1399024474000',
'1399126333000' ],
numbers: null,
goals: null,
durations: null },
{ dates:
[ '1399027545000',
'1399024474000',
'1399518702000',
'1399126333000',
'1399209192000',
'1399356651000' ],
numbers: null,
goals: null,
conversation_durations: null },
{ dates:
[ '1399026850000',
'1399101432000',
'1399027545000',
'1399904504000',
'1399024474000' ],
numbers: null,
goals: null,
durations: null }
Does anybody know where is the problem?

Answer 1

You need to include the fields within the $group pipeline using the $first operator as follows:
db.getCollection('yourCollection').aggregate([
{ "$unwind": "$dates" },
{
"$group": {
"_id": "$_id",
"dates": { "$addToSet": "$dates" },
"numbers": { "$first": "$numbers" },
"goals": { "$first": "$goals" },
"durations": { "$first": "$durations" }
}
},
{ "$unwind": {
"path": "$dates",
"includeArrayIndex": "idx"
} },
{
"$project": {
"_id": 0,
"dates": 1,
"numbers": { "$arrayElemAt": ["$numbers", "$idx"] },
"goals": { "$arrayElemAt": ["$goals", "$idx"] },
"durations": { "$arrayElemAt": ["$durations", "$idx"] }
}
}
])
or using $setUnion to eliminate duplicates as:
db.getCollection('yourCollection').aggregate([
{
"$project": {
"_id": 0,
"dates": { "$setUnion": ["$dates", "$dates"] },
"numbers": 1,
"goals": 1,
"durations": 1
}
}
{ "$unwind": {
"path": "$dates",
"includeArrayIndex": "idx"
} },
{
"$project": {
"_id": 0,
"dates": 1,
"dateIndex": "$idx",
"numbers": { "$arrayElemAt": ["$numbers", "$idx"] },
"goals": { "$arrayElemAt": ["$goals", "$idx"] },
"durations": { "$arrayElemAt": ["$durations", "$idx"] }
}
}
])