MongoDB Aggregation Error Returning wrong result - mongodb

I have my json object like this
{
"_id": "5c2e811154855c0012308f00",
"__pclass": "QXRzXFByb2plY3RcTW9kZWxcUHJvamVjdA==",
"id": 44328,
"name": "Test project via postman2//2",
"address": "some random address",
"area": null,
"bidDate": null,
"building": {
"name": "Health Care Facilities",
"type": "Dental Clinic"
},
"collaborators": [],
"createdBy": {
"user": {
"id": 7662036,
"name": "Someone Here"
},
"firm": {
"id": 2520967,
"type": "ATS"
}
},
"createdDate": "2019-01-03T21:39:29Z",
"customers": [],
"doneBy": null,
"file": null,
"firm": {
"id": 1,
"name": "MyFirm"
},
"leadSource": {
"name": "dontknow",
"number": "93794497"
},
"location": {
"id": null,
"city": {
"id": 567,
"name": "Bahamas"
},
"country": {
"id": 38,
"name": "Canada"
},
"province": {
"id": 7,
"name": "British Columbia"
}
},
"modifiedBy": null,
"modifiedDate": null,
"projectPhase": {
"id": 1,
"name": "pre-design"
},
"quotes": [{
"id": 19,
"opportunityValues": {
"Key1": 100,
"Key2 Key2": 100,
"Key3 Key3 Key3": 200,
}
}],
"specForecast": [],
"specIds": [],
"tags": [],
"valuation": "something"
}
I am trying to aggregate using this query in MongoDB. My aggregation key is 4 level deep and also contains spaces. On all online examples shows me the aggregation at the first level. Looking to the online codes, I tried to re-iterate the same with my 4th level deep key.
db.mydata.aggregate([
{$match: {"id": 44328 } } ,
{$group: { _id: "$quotes.id",
totalKey2:{ $sum: "$quotes.opportunityValues.Key2 Key2"},
totalKey3:{ $sum: "$quotes.opportunityValues.Key3 Key3 Key3"}
}
}
]);
This should return
_id totalKey2 totalKey3
0 19 100 300
But it is returning
_id totalKey2 totalKey3
0 19 0 0
What am I doing Wrong?

Although it's not recommended to use space in field names in Mongo, it works as expected.
The problem with your query is that "quotes" is an array and you should first unwind it before grouping it.
This works as expected:
db.mydata.aggregate([
{ $match: { "id": 44328 } } ,
{ $unwind: "$quotes" },
{ $group: { _id: "$quotes.id",
totalKey2:{ $sum: "$quotes.opportunityValues.Key2 Key2" },
totalKey3:{ $sum: "$quotes.opportunityValues.Key3 Key3 Key3" } }
}
]);

Related

MongoDB Select By Group along with that Count Unique match exclude array and object fields Get data sort by latest objects

I have a collection where from the backend user can input multiple same name bikes but with different registration number but in front-End I want them to be grouped by matching the same name but as user updates separately display image changes but I want only one display image as it is 1 vehicle
provided there is a node created I will implement it we can sort it by the latest and take the price and image of it
Activa -2 Count
KTM -1 Count
but there is a catch.
Activa 2 bikes but I want only count 2 and the price as it is the same in an array I want only 1 and the same applies to displayimage here display image file path is different but I want the latest one only Sharing data below
Data:
[
{
"price": [
{
"Description": "Hourly",
"Price": "1"
},
{
"Description": "Daily",
"Price": "11"
},
{
"Description": "Monthly",
"Price": "111"
}
],
"_id": "62e69ee3edfe4d0f3cb4994a",
"bikename": "KTM",
"bikenumber": "KA05HM2034",
"bikebrand": {
"id": 1,
"label": "Honda"
},
"freekm": 234,
"displayimage": {
"file": "bike-2020-honda-city-exterior-8-1659281111883.jpg",
"file_path": "https://www.example.com/images/upload/bike-2020-honda-city-exterior-8-1659281111883.jpg",
"idx": 1
}
},
{
"price": [
{
"Description": "Hourly",
"Price": "1"
},
{
"Description": "Daily",
"Price": "11"
},
{
"Description": "Monthly",
"Price": "111"
}
],
"_id": "62dba8418ef8f51f454ed757",
"bikename": "Activa",
"bikenumber": "KA05HM2033",
"bikebrand": {
"id": 1,
"label": "Honda"
},
"freekm": 234,
"displayimage": {
"file": "bike-v_activa-i-deluxe-1658562557459.jpg",
"file_path": "https://www.example.com/images/upload/bike-v_activa-i-deluxe-1658562557459.jpg",
"idx": 0
}
},
{
"price": [
{
"Description": "Hourly",
"Price": "1"
},
{
"Description": "Daily",
"Price": "11"
},
{
"Description": "Monthly",
"Price": "111"
}
],
"_id": "62d7ff7e70b9ab38c6ab0cb1",
"bikename": "Activa",
"bikenumber": "KA05HM2223",
"bikebrand": {
"id": 1,
"label": "Honda"
},
"freekm": 234,
"afterfreekmprice": 22,
"descreption": "Activa",
"displayimage": {
"file": "bike-v_activa-i-deluxe-1658322798414.jpg",
"file_path": "https://www.example.com/images/upload/bike-v_activa-i-deluxe-1658322798414.jpg",
"idx": 0
}
}
]
Expected:
[
{
"_id":{
"price": [
{
"Description": "Hourly",
"Price": "1"
},
{
"Description": "Daily",
"Price": "11"
},
{
"Description": "Monthly",
"Price": "111"
}
],
"_id": "62dba8418ef8f51f454ed757",
"bikename": "Activa",
"bikebrand": {
"id": 1,
"label": "Honda"
},
"freekm": 234,
"displayimage": {
"file": "bike-v_activa-i-deluxe-1658562557459.jpg",
"file_path": "https://www.example.com/images/upload/bike-v_activa-i-deluxe-1658562557459.jpg",
"idx": 0
}
},
"count": 2
},
{
"_id":{
"price": [
{
"Description": "Hourly",
"Price": "1"
},
{
"Description": "Daily",
"Price": "11"
},
{
"Description": "Monthly",
"Price": "111"
}
],
"_id": "62e69ee3edfe4d0f3cb4994a",
"bikename": "KTM",
"bikebrand": {
"id": 1,
"label": "Honda"
},
"freekm": 234,
"displayimage": {
"file": "bike-2020-honda-city-exterior-8-1659281111883.jpg",
"file_path": "https://www.example.com/images/upload/bike-2020-honda-city-exterior-8-1659281111883.jpg",
"idx": 1
}
}
"count": 1
}
]
You can use the aggregation pipeline,
$sort by _id in descending order
$group by bikename and get the first root document that is latest one in root and count total documents in count
$project to show required documents
db.collection.aggregate([
{ $sort: { _id: -1 } },
{
$group: {
_id: "$bikename",
root: { $first: "$$ROOT" },
count: { $sum: 1 }
}
},
{
$project: {
_id: "$root",
count: 1
}
}
])
Playground
You can use $group for this:
db.collection.aggregate([
{$group: {
_id: "$bikename",
count: {$sum: 1},
data: {$first: "$$ROOT"}
}
},
{$set: {"data.count": "$count"}},
{$replaceRoot: {newRoot: "$data"}}
])
See how it works on the playground example

MongoDb extract array

I have a mongodb which I want to extract some specific data.
Here is my json:
{
"jobs" : [
{
"id": 554523,
"code": "1256-554523",
"name": "Banco de Talentos",
"status": "published",
"type": "vacancy_type_effective",
"publicationType": "external",
"numVacancies": 1,
"departmentId": 108141,
"departmentName": "FUTURAS OPORTUNIDADES",
"roleId": 169970,
"roleName": "BANCO DE TALENTOS",
"createdAt": "2020-10-30T12:23:48.572Z",
"updatedAt": "2020-12-30T23:21:30.403Z",
"branchId": null,
"branchName": null
},
{
"id": 616834,
"code": "1256-616834",
"name": "YYYYYY (o) YYYYY",
"status": "frozen",
"type": "vacancy_type_effective",
"publicationType": "external",
"numVacancies": 1,
"departmentId": 109190,
"departmentName": "TESTE TESTE",
"roleId": 165712,
"roleName": "SL - TESTE PL",
"createdAt": "2020-12-16T14:17:36.187Z",
"updatedAt": "2021-01-29T17:08:43.613Z",
"branchId": 120448,
"branchName": "TESTE TESTE1"
}
],
"application": [
{
"id": 50707344,
"score": 40.251965332031254,
"partnerName": "indeed",
"endedAt": null,
"createdAt": "2020-12-21T11:21:30.587Z",
"updatedAt": "2021-02-18T22:02:35.866Z",
"tags": {},
"candidate": {
"birthdate": "1986-04-04",
"id": 578615,
"name": "TESTE",
"lastName": "TESTE TESTE",
"email": "teste#teste.com.br",
"identificationDocument": "34356792807",
"countryOfOrigin": "BR",
"linkedinProfileUrl": "teste",
"gender": "female",
"mobileNumber": "+5511972319799",
"phoneNumber": "(11)2463-2039"
},
"job": {
"id": 619713,
"name": "XXXXde XXXX Pleno"
},
"manualCandidate": null,
"currentStep": {
"id": 3527370,
"name": "Cadastro",
"status": "done"
}
},
{
"id": 50707915,
"score": 3.75547943115234E+1,
"partnerName": "indeed",
"endedAt": null,
"createdAt": "2020-12-21T11:31:31.877Z",
"updatedAt": "2021-02-18T14:07:06.605Z",
"tags": {},
"candidate": {
"birthdate": "1971-10-02",
"id": 919358,
"name": "TESTE TESTE",
"lastName": "SILVA",
"email": "teste.teste#teste.com",
"identificationDocument": "3232323232",
"countryOfOrigin": "BR",
"linkedinProfileUrl": "teste/",
"gender": "female",
"mobileNumber": "11 94021- 5521",
"phoneNumber": "+5511995685247"
},
"job": {
"id": 619713,
"name": "Analista de XXXXX Pleno"
},
"manualCandidate": null,
"currentStep": {
"id": 3527370,
"name": "Cadastro",
"status": "done"
}
}
]
}
My question is: How can I extract only the array objects in jobs and application separately? Anyone knows the code in Mongodb for do this?
I need do this task for after I can insert the extract separated data in different collections.
Thanks a lot.
Unfortunately there is no real "good" way of doing this. Here is an example of how I would do it by using $facet and other operators to manipulate the structure
db.collection.aggregate([
{
$match: {
/** your query*/
}
},
{
$facet: {
jobs: [
{
$unwind: "$jobs"
},
{
$replaceRoot: {
newRoot: "$jobs"
}
}
],
applications: [
{
$unwind: "$application"
},
{
$replaceRoot: {
newRoot: "$application"
}
}
]
}
},
{
$addFields: {
"merged": {
"$concatArrays": [
"$jobs",
"$applications"
]
}
}
},
{
$unwind: "$merged"
},
{
"$replaceRoot": {
"newRoot": "$merged"
}
}
])
Mongo Playground
I would personally just do it in code after you fetched the document.

Mongo Aggregation using $Max

I have a collection that stores history, i.e. a new document is created every time a change is made to the data, I need to extract fields based on the max value of a date field, however my query keeps returning either all of the dates or requires me to push the fields into an array which make the data hard to analyze for an end-user.
Expected output as CSV:
MAX(DATE), docID, url, type
1579719200216, 12371, www.foodnetwork.com, food
1579719200216, 12371, www.cnn.com, news,
1579719200216, 12371, www.wikipedia.com, info
Sample Doc:
{
"document": {
"revenueGroup": "fn",
"metaDescription": "",
"metaData": {
"audit": {
"lastModified": 1312414124,
"clientId": ""
},
"entities": [],
"docId": 1313943,
"url": ""
},
"rootUrl": "",
"taggedImages": {
"totalSize": 1,
"list": [
{
"image": {
"objectId": "woman-reaching-for-basket",
"caption": "",
"url": "",
"height": 3840,
"width": 5760,
"owner": "Facebook",
"alt": "Woman reaching for basket"
},
"tags": {
"totalSize": 4,
"list": []
}
}
]
},
"title": "The 8 Best Food Items of 2020",
"socialTitle": "The 8 Best Food Items of 2020",
"primaryImage": {
"objectId": "woman-reaching-for-basket.jpg",
"caption": "",
"url": "",
"height": 3840,
"width": 5760,
"owner": "Hero Images / Getty Images",
"alt": "Woman reaching for basket in laundry room"
},
"subheading": "Reduce your footprint with these top-performing diets",
"citations": {
"list": []
},
"docId": 1313943,
"revisionId": "1313943_1579719200216",
"templateType": "LIST",
"documentState": {
"activeDate": 579719200166,
"state": "ACTIVE"
}
},
"url": "",
"items": {
"totalSize": "",
"list": [
{
"type": "recipe",
"data": {
"comInfo": {
"list": [
{
"type": "food",
"id": "https://www.foodnetwork.com"
}
]
},
"type": ""
},
"id": 4,
"uuid": "1313ida-qdad3-42c3-b41d-223q2eq2j"
},
{
"type": "recipe",
"data": {
"comInfo": {
"list": [
{
"type": "news",
"id": "https://www.cnn.com"
},
{
"type": "info",
"id": "https://www.wikipedia.com"
}
]
},
"type": "PRODUCT"
},
"id": 11,
"uuid": "318231jc-da12-4475-8994-283u130d32"
}
]
},
"vertical": "food"
}
Below query:
db.collection.aggregate([
{
$match: {
vertical: "food",
"document.documentState.state": "ACTIVE",
"document.templateType": "LIST"
}
},
{
$unwind: "$document.items"
},
{
$unwind: "$document.items.list"
},
{
$unwind: "$document.items.list.contents"
},
{
$unwind: "$document.items.list.contents.list"
},
{
$match: {
"document.items.list.contents.list.type": "recipe",
"document.revenueGroup": "fn"
}
},
{
$sort: {
"document.revisionId": -1
}
},
{
$group: {
_id: {
_id: {
docId: "$document.docId",
date: {$max: "$document.revisionId"}
},
url: "$document.items.list.contents.list.data.comInfo.list.id",
type: "$document.items.list.contents.list.data.comInfo.list.type"
}
}
},
{
$project: {
_id: 1
}
},
{
$sort: {
"document.items.list.contents.list.id": 1, "document.revisionId": -1
}
}
], {
allowDiskUse: true
})
First of all, you need to go through the documentation of the $group aggregation here.
you should be doing this instead:
{
$group: {
"_id": "$document.docId"
"date": {
$max: "$document.revisionId"
},
"url": {
$first: "$document.items.list.contents.list.data.comInfo.list.id"
},
"type": {
$first:"$document.items.list.contents.list.data.comInfo.list.type"
}
}
}
This will give you the required output.

Mongo Aggs and total count

I experiencing some trouble in mongodb to do a query on collection to get all documents filtered, paginate(with skip and limit) and get the total count like that
The chat document look like that:
{
"_id": "c603db3e75ec76f5a4dff559bc525e29",
"members": [{
"user": "5b2b0d5135cfd60185034bf6",
"status": "creator"
}, {
"user": "5b31dc3f88284a009fa847e5",
"status": "member"
}],
"messages": [{
"_id": 2,
"from": "5b2b0d5135cfd60185034bf6",
"parse_mode": "none",
"text": "fffasdfsa",
"attachment": null,
"time": 1529995684119,
"type": "text"
},
{...},
{...}
]}
And i would like to get result like that
{
total_count: 3,
chats: [{
"_id": "c603db3e75ec76f5a4dff559bc525e29",
"members": [{
"user": "5b2b0d5135cfd60185034bf6",
"status": "creator"
}, {
"user": "5b31dc3f88284a009fa847e5",
"status": "member"
}],
"creator": {
"user": "5b2b0d5135cfd60185034bf6",
"status": "creator"
},
"lastMessage": {
"_id": 4,
"from": "5b2b0d5135cfd60185034bf6",
"parse_mode": "none",
"text": "aasdas",
"attachment": null,
"time": 1529995698736,
"type": "text"
},
"messages": [{
"_id": 2,
"from": "5b2b0d5135cfd60185034bf6",
"parse_mode": "none",
"text": "fffasdfsa",
"attachment": null,
"time": 1529995684119,
"type": "text"
}, {
"_id": 3,
"from": "5b2b0d5135cfd60185034bf6",
"parse_mode": "none",
"text": "weqw",
"attachment": null,
"time": 1529995690015,
"type": "text"
}, {
"_id": 4,
"from": "5b2b0d5135cfd60185034bf6",
"parse_mode": "none",
"text": "aasdas",
"attachment": null,
"time": 1529995698736,
"type": "text"
}]
},
{...},
{...}
]
}
My query is
collection<DbChat>('chats').aggregate([
{
$match: {
messages: { $exists: true }
}
},
{ $unwind: '$messages' },
{ $unwind: '$members' },
{ $group: {_id: '$_id', members: { $push: '$members' }, member: { $last: '$members' }, creator: { $first: '$members' }, messages: {$push: '$messages' } , lastMessage: {$last: '$messages'}}},
{ $sort: this.sort},
]}.skip(skip).limit(size)
with this query i dont get the total_count I tried lot of things but i didnt found a way to get the result and the count in the same query.
Thanks

Elasticsearch nested query

I'm new to elasticsearch, managed to set it up and import recordset from my mongodb collection using the river plugin. For a start, I want to query against the "desc" field but just can't manage to get the query .. not sure if the problem is driven by the way index was defined.. can anyone help please?
Sample recordset in elastic search looks like this
{
"took": 2,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"failed": 0
},
"hits": {
"total": 107209,
"max_score": 1,
"hits": [
{
"_index": "shiv",
"_type": "shiv",
"_id": "iG1eIzN7RGO7hFfxTlnLuA",
"_score": 1,
"_source": {
"_id": {
"$oid": "50901d7f485bf7bd1c000021"
},
"brand": "",
"category": {
"$ref": "categories",
"$id": {
"$oid": "4fbd2221758cb11d14000174"
}
},
"comments": [],
"count_comment": 0,
"count_fav": 2,
"count_hotness": 1.46,
"count_rekick": 0,
"count_share": 0,
"country": {
"$ref": "countries",
"$id": {
"$oid": "4fec98f7758cb18c6e0002c9"
}
},
"currency": "pound",
"desc": "A men's automatic watch, this Seamaster Bond model features a Co-Axial escapement and date function. Its blue dial is teamed with a stainless steel case and bracelet for a look that's sporty and refined.",
"gender": "male",
"ident": "omega-seamaster-diver-bond-men-s-automatic-watch---ernest-jones-1351622015",
"img_url": "http://s7ondemand4.scene7.com/is/image/Signet/5735793?$detail$",
"lifestyles": [
{
"$ref": "lifestyles",
"$id": {
"$oid": "508ff6ca485bf73112000060"
}
}
],
"location": "United Kingdom",
"owner": {
"$ref": "accounts",
"$id": {
"$oid": "50742fd8485bf74b7a00213f"
}
},
"price": 2400,
"store": "ernestjones.co.uk",
"tags": [
"ernest-jones",
"bond"
],
"timestamp_creation": 1351622015,
"timestamp_exp": 1356825600,
"timestamp_update": 1351622015,
"title": "Omega Seamaster Diver Bond men's automatic watch - Ernest Jones",
"url": "http%3A%2F%2Fwww.ernestjones.co.uk%2Fwebstore%2Fd%2F5735793%2Fomega%20seamaster%20diver%20bond%20men%27s%20automatic%20watch%2F%3Futm_source%3Dgooglebase%26utm_medium%3Dfeedmanager%26cm_mmc%3DFroogle-_-CKB-_-nurses_fobs-_-watches%26cm_mmca1%3Domega%26cm_mmca2%3Dmale%26cm_mmca3%3Dadult"
}
}
]
}
}
The mapping of the index "shiv" looks like
{
"shiv": {
"properties": {
"$oid": {
"type": "string"
}
}
}
}
Thanks again
There are lots of ways to query, have you tried a match query?
Using curl or a rest client of your choice...
http://[host]:9200/[index_name]/[doc_type]/_search
{
"query" : {
"match" : {
"desc" : "some value you want to find in desc"
}
}
}