Hello I tried to querying json data with mongo db with aggregate framework but get stuck, here's the data :
[{
"_id" : ObjectId("5adf2294bc832359aa9bc710"),
"kabupaten" : "Badung",
"jenis_wisata" : [
{
"jenis" : "resto",
"list" : [
{
"nama_resto" : "Warung Nasi Ayam Bu Oki",
"alamat" : "Bukit Jimbaran"
},
{
"nama_resto" : "Warung Pojok Segitiga Emas",
"alamat" : "Bukit Jimbaran"
}
]
},
{
"jenis" : "gunung",
"list" : [
{
"nama_gunung" : "gunung_1",
"alamat" : "alamat_1"
},
{
"nama_gunung" : "gunung_1",
"alamat" : "alamat_1"
}
]
}
]
},{
"_id" : ObjectId("5adf2294bc832359aa9bc711"),
"kabupaten" : "Denpasar",
"jenis_wisata" : [
{
"jenis" : "resto",
"list" : [
{
"nama_resto" : "Warung Nasi Ayam Bu Oki",
"alamat" : "Bukit Jimbaran"
},
{
"nama_resto" : "Warung Pojok Segitiga Emas",
"alamat" : "Bukit Jimbaran"
}
]
},
{
"jenis" : "gunung",
"list" : [
{
"nama_gunung" : "gunung_1",
"alamat" : "alamat_1"
},
{
"nama_gunung" : "gunung_1",
"alamat" : "alamat_1"
}
]
}
]
}]
what I want to achieve is to display the total amount of array "list" inside each element in array "jenis_wisata", here's the expected result that I want to achieve:
[{
"kabupaten" : "Badung",
"jenis_wisata" : [
{
"jenis" : "resto",
"total" : 2
},
{
"jenis" : "gunung",
"total" : 2
}
]
},{
"kabupaten" : "Denpasar",
"jenis_wisata" : [
{
"jenis" : "resto",
"total" : 2
},
{
"jenis" : "gunung",
"total" : 2
}
]
}]
Really appreciate your help here, Thanks
You need $map to transform your inner array and $size to get the length of an array.
db.collection.aggregate([
{
$project: {
kabupaten: 1,
jenis_wisata: {
$map: {
input: "$jenis_wisata",
as: "element",
in: {
jenis: "$$element.jenis",
total: { $size: "$$element.list" }
}
}
}
}
}
])
Related
I am trying to update data of "array1.array2._id": ObjectId("627a6fab60dc3c523b396af1") and Set Name to John But it's updating in all array2's first element's name to John.
db.getCollection('tests')
.updateOne({ "array1.array2._id": ObjectId("627a6fab60dc3c523b396af1") },{ $set: { "array1.$[].array2.$.name" : "John" } })
{
"_id" : ObjectId("627a6fab60dc3c523b396aec"),
"array1" : [
{
"array2" : [
{
"_id" : ObjectId("627a6fab60dc3c523b396af1"),
"name" : "test"
},
{
"_id" : ObjectId("627a6fab60dc3c523b396af2"),
"name" : "ABC"
}
],
"_id" : ObjectId("627a6fab60dc3c523b396aed")
},
{
"array2" : [
{
"_id" : ObjectId("627a6fab60dc3c523b396af3"),
"name" : "XYZ"
},
{
"_id" : ObjectId("627a6fab60dc3c523b396af4"),
"name" : "Testing"
}
],
"_id" : ObjectId("627a6fab60dc3c523b396aee")
}
]
}
Based on this great answer by #R2D2, you can do:
db.collection.update({
"array1.array2._id": ObjectId("627a6fab60dc3c523b396af1")
},
{
$set: {
"array1.$[].array2.$[y].name": "John"
}
},
{
arrayFilters: [
{
"y._id": ObjectId("627a6fab60dc3c523b396af1")
}
]
})
As you can see on this playground example
I have am trying to perform an aggregate function on my collection but I can't seem to fit the right query for the job.
My goal is to display the top 2 fastest laps on all maps and show the associated user first name and last name.
Here is my stats collections:
{
"_id" : ObjectId("5c86674d87e8cd468c850c86"),
"lapTime" : "1:32:29",
"map" : "France",
"driver" : [
ObjectId("5c7c499b555fa13f50c9c248")
],
"date" : ISODate("2019-03-11T13:49:01.472Z"),
"__v" : 0
}
{
"_id" : ObjectId("5c8667ec87e8cd468c850c87"),
"lapTime" : "2:32:34",
"map" : "France",
"driver" : [
ObjectId("5c7c499b555fa13f50c9c248")
],
"date" : ISODate("2019-03-11T13:51:40.895Z"),
"__v" : 0
}
{
"_id" : ObjectId("5c86674x87e8Sd567c120c86"),
"lapTime" : "1:12:29",
"map" : "France",
"driver" : [
ObjectId("5c7c499b555fa13f50c9c248")
],
"date" : ISODate("2019-03-11T10:49:01.472Z"),
"__v" : 0
}
{
"_id" : ObjectId("5c8667f887e8cd468c850c88"),
"lapTime" : "1:88:29",
"map" : "Italy",
"driver" : [
ObjectId("5c7c499b555fa13f50c9c248")
],
"date" : ISODate("2019-03-11T13:51:52.727Z"),
"__v" : 0
}
{
"_id" : ObjectId("5c866970c65910291c6f2000"),
"lapTime" : "1:34:29",
"map" : "Italy",
"driver" : [
ObjectId("5c80f78ca0ecdf26c83dfc8a")
],
"date" : ISODate("2019-03-11T13:58:08.135Z"),
"__v" : 0
}
{
"_id" : ObjectId("5c868532b5c50c17b0917f9e"),
"lapTime" : "1:43:33",
"map" : "Italy",
"driver" : [
ObjectId("5c80f78ca0ecdf26c83dfc8a")
],
"date" : ISODate("2019-03-11T15:56:34.869Z"),
"__v" : 0
}
Since I am passing the driver ID by reference here:
"driver":[ObjectId("5c7c499b555fa13f50c9c248")] , I want to display the driver's attributes from my users collection.
Here is one of my user objects:
{
"_id" : ObjectId("5c7c499b555fa13f50c9c248"),
"password" : "$2a$10$L..Pf44/R7yJfNPdikIObe04aiJaY/e94VSKlFscjgYOe49Y7iwJK",
"email" : "john.smith#yahoo.com",
"firstName" : "John",
"lastName" : "Smith",
"laps" : [],
"__v" : 0,
}
Here is what I tried so far:
db.getCollection('stats').aggregate([
{ $group: {
_id: { map: "$map" }, // replace `name` here twice
laps: { $addToSet: "$lapTime" },
driver:{$addToSet: "$driver"},
count: { $sum: 1 }
} },
{$lookup:
{
from: "users",
localField: "firstName",
foreignField: "lastName",
as: "driver"
}},
{ $match: {
count: { $gte: 2 }
} },
{ $sort : { count : -1} },
{ $limit : 10 }
]);
As a result, I am getting drivers as a empty array.
What I am actually trying to achieve is something like this:
{
"_id" : {
"map" : "France"
},
"laps" : [
"Jonathan Smith":"2:32:34",
"Someone Else":"1:32:29"
],
"count" : 2.0
}
I think this should work:-
db.getCollection('stats').aggregate([
{ $unwind: "$driver" },
{$lookup:
{
from: "users",
localField: "driver",
foreignField: "_id",
as: "driver"
}},
{ $group: {
_id: { map: "$map" }, // replace `name` here twice
laps: { $addToSet:
{
lapTime: "$lapTime",
driverName: "$driver.firstName" + "$driver.lastName"
}
},
count: { $sum: 1 }
} },
{ $match: {
count: { $gte: 2 }
} },
{ $sort : { count : -1} },
{ $limit : 10 }
]);
{
"_id" : NumberLong(107),
"cnic" : NumberLong(098765),
"recordsOFGt" : [
{
"records" : [
{
"_id" : NumberLong(1),
"contactIds" : [
NumberLong(303)
],
},
{
"_id" : NumberLong(2),
"contactIds" : [
NumberLong(303),
NumberLong(304)
],
},
{
"_id" : NumberLong(3),
"contactIds" : [
NumberLong(309),
NumberLong(304)
],
},
{
"_id" : NumberLong(4),
"contactIds" : [
NumberLong(303),
NumberLong(304)
],
},
{
"_id" : NumberLong(5),
"contactIds" : [
NumberLong(303),
NumberLong(304)
],
},
]
},
"records2" : {
...
...
}
]
}
I want only record element that will be matched via _id I have tried this
db.getCollection('tempCollection').findOne(
{ 'recordsOFGt': {$elemMatch: {'records._id': 1} }},
{'recordsOFGt.$': 1}
)
this returns all elements of records array need just matching element.
this is what I want as output :
{
"records" :
{
"_id" : NumberLong(1),
"contactIds" : [
NumberLong(303)
],
}
}
My collection coll is
/* 1 */
{
"_id" : ObjectId("566121aa4b88d840eb7d1c50"),
"batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"),
"array" : [
{
"id" : 1
},
{
"id" : 2
},
{
"id" : 3
},
{
"id" : 4
}
]
}
/* 2 */
{
"_id" : ObjectId("5661224a4b88d840eb7d1c51"),
"batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"),
"array" : [
{
"id" : 1
},
{
"id" : 7
},
{
"id" : 3
},
{
"id" : 5
}
]
}
what i need is to pull objects in array 'array' where
batchCourseId = ObjectId("566122ab94b792fbdf81bcf3")
and 2<array.id<=5
expected output is
/* 1 */
{
"_id" : ObjectId("566121aa4b88d840eb7d1c50"),
"array" : [
{
"id" : 3
},
{
"id" : 4
}
]
}
/* 2 */
{
"_id" : ObjectId("5661224a4b88d840eb7d1c51"),
"array" : [
{
"id" : 3
},
{
"id" : 5
}
]
}
already tried
db.coll.find({"batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3")},
{ array: { $elemMatch: { id: { $gt: 2,$lte: 5} } } })
the output is like
/* 1 */
{
"_id" : ObjectId("566121aa4b88d840eb7d1c50"),
"array" : [
{
"id" : 3
}
]
}
/* 2 */
{
"_id" : ObjectId("5661224a4b88d840eb7d1c51"),
"array" : [
{
"id" : 3
}
]
}
close but only the first matching object in array is in result
FYI this only a sample set of data the original data is more complex and big in count
so pls let me know the best practice to do this, performance is also important
thanks in advance
You can use aggregation for achieving the same. A sample is shown below:
db.coll.aggregate(
{$match: {"batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3")}},
{$unwind: '$array'},
{$match: {'array.id': { $gt: 2,$lte: 5}}},
{$group: {_id: '$_id', array: {$push : '$array'}}}
)
Result:
{ "_id" : ObjectId("5661224a4b88d840eb7d1c51"), "array" : [ { "id" : 3 }, { "id" : 5 } ] }
{ "_id" : ObjectId("566121aa4b88d840eb7d1c50"), "array" : [ { "id" : 3 }, { "id" : 4 } ] }
In MongoDB aggregation $unwind creates Cartesian_product problem so in large data set is good way to avoid $unwind.
Let's check with your example if you use $unwind in aggregation then result looks like this
db.collectionName.aggregate([
{ "$match": { "batchCourseId": ObjectId("566122ab94b792fbdf81bcf3") }},
{ "$unwind": "$array" }
])
so result of above query is :
{ "_id" : ObjectId("566121aa4b88d840eb7d1c50"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 1 } }
{ "_id" : ObjectId("566121aa4b88d840eb7d1c50"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 2 } }
{ "_id" : ObjectId("566121aa4b88d840eb7d1c50"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 3 } }
{ "_id" : ObjectId("566121aa4b88d840eb7d1c50"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 4 } }
{ "_id" : ObjectId("5661224a4b88d840eb7d1c51"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 1 } }
{ "_id" : ObjectId("5661224a4b88d840eb7d1c51"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 7 } }
{ "_id" : ObjectId("5661224a4b88d840eb7d1c51"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 3 } }
{ "_id" : ObjectId("5661224a4b88d840eb7d1c51"), "batchCourseId" : ObjectId("566122ab94b792fbdf81bcf3"), "array" : { "id" : 5 } }
this create multiple documents and in large documents in collections it slow the performance and increase processing time.
Instead of $unwind use $map in aggregation with aggregation-set operator and the query is as below :
db.collection.aggregate([{
"$match": {
"batchCourseId": ObjectId("566122ab94b792fbdf81bcf3")
}
}, {
"$project": {
"array": {
"$setDifference": [{
"$map": {
"input": "$array",
"as": "el",
"in": {
"$cond": {
"if": {
"$and": [{
"$gt": ["$$el.id", 2]
}, {
"$lte": ["$$el.id", 5]
}]
},
"then": "$$el",
"else": false
}
}
}
},
[false]
]
}
}
}])
docs:
order1.filter = ['tag1','tag2']
order2.filter = ['tag1','tag2','tag3']
want to get:
query ['tag1','tag2'] -> (only order1)
query ['tag1','tag2','tag3'] -> (order1 and order2)
query ['tag1','tag2','tag3','tag4', etc ] -> (order1 and order2)
and
query ['tag1','tag3'] -> (null)
query ['tag2','tag3'] -> (null)
All values order.filter should be necessarily in the query array
How to do it? Tried directives $all, $in :(
You can do this with aggregation framework (there is no way to do this with regular find that I know of).
I think this is basically a duplicate so adjusting that code for your fields you get something like:
//sample documents:
> db.docs.find({},{_id:0})
{ "order" : 1, "filter" : [ "t1", "t2" ] }
{ "order" : 2, "filter" : [ "t1", "t2", "t3" ] }
var tagArray = [ "t1", "t2" ]; // array to "match"
db.docs.aggregate( [
{
"$project" : {
"order" : 1,
"filter" : 1,
"killFlag" : {
"$const" : [
true,
false
]
}
}
},
{
"$unwind" : "$filter"
},
{
"$unwind" : "$killFlag"
},
{
"$match" : {
"$nor" : [
{
"filter" : {
"$in" : tagArray
},
"killFlag" : true
}
]
}
},
{
"$group" : {
"_id" : "$order",
"filter" : {
"$addToSet" : "$filter"
},
"killFlag" : {
"$max" : "$killFlag"
}
}
},
{
"$match" : {
"killFlag" : false
}
},
{
"$project" : {
"_id" : 1,
"filter" : 1
}
}
]);