I need to batch update cdi_tags with md5 collection(push item to cdi_tags) as follows:
db.getCollection("event").update({
"_id": {
$in: [ObjectId("6368f03e21b1ad246c84d67b"), ObjectId("6368f03f21b1ad246c84d982")]
},
"meta": {
$elemMatch: {
"key": "bags",
"value"
}
}
}, {
$addToSet: {
"meta.$.value.$[t].cdi_tags: "test_tag"
}
}, {
arrayFilters: [{
"t": {
$in: ["cc09ab29db36f85e154d2c1ae9517f57", "b6b9c266f584191b6eb2d2659948a7a9"]
}
}],
multi: true
})
but not work, my doc as follows
{
"_id": ObjectId("6368f03f21b1ad246c84d982"),
"event_key": "PLAA7-194710",
"data_source": "EAP",
"name": "EP33L-AA94710",
"production": "CP",
"meta":
[
{
"key": "auto_note",
"value":
[]
},
{
"key": "bags",
"value":
{
"cc09ab29db36f85e154d2c1ae9517f57":
{
"name": "PLAA63952_event_ftp_pcar_event_20221107-194709_0.bag",
"profile": "msquare-prediction-ro",
"md5": "cc09ab29db36f85e154d2c1ae9517f57",
"cdi_tags":
[
"FDI_V1_0_0",
"from_dpp",
"epl-no-sensor",
"with_f100",
"epl-fix_video",
"epl-fix_horizon"
]
},
"361f5160cca3c3dec90cbbf93e3d7ae3":
{
"name": "PLAA63952_event_ftp_pcar_event_20221107-194709_0.bag",
"profile": "msquare-prediction-ro",
"md5": "361f5160cca3c3dec90cbbf93e3d7ae3",
"cdi_tags":
[
"FDI_V1_0_0",
"china",
"ftp_epcar_rawdata",
"from_dpp",
"trigger_type:system"
]
}
}
}
]
}
thinks
how to batch update nested doc in mongo
Related
I have the following data, which describes who is going to do what work.
Basically I want to replace the "workId" and "userId" with objects that contain all the data from their respective documents and retain the "when" data.
I am starting with this data:
{
"schedule": {
"WorkId": "4e51dc1069c27c015ede4e3e",
"daily": [
{
"when": 1,
"U_W": [
{
"workId": "3a60dc1069c27c015ede1111",
"userId": "5f60c3b7f93d8e00a1cdf414"
},
{
"workId": "3a60dc1069c27c015ede1122",
"userId": "5f60c3b7f93d8e00a1cdf415"
}
]
}
]
}
}
Here is the user table
"userSchema": [
{
_id: "5f60c3b7f93d8e00a1cdf414",
Name: "Bob"
},
{
_id: "5f60c3b7f93d8e00a1cdf415",
Name: "Joe"
}
],
Here is the work table
"workSchema": [
{
_id: "3a60dc1069c27c015ede1111",
Name: "shovel"
},
{
_id: "3a60dc1069c27c015ede1122",
Name: "hammer"
}
]
what I want to end up with is this
{
"schedule": {
"WorkId": "4e51dc1069c27c015ede4e3e",
"daily": [
{
"when": 1,
"U_W": [
{
"work": {
"id": "3a60dc1069c27c015ede1111",
"name": "shovel"
},
"user": {
"id": "5f60c3b7f93d8e00a1cdf414",
"name": "bob"
}
},
{
"work": {
"id": "3a60dc1069c27c015ede1122",
"name": "hammer"
},
"user": {
"id": "5f60c3b7f93d8e00a1cdf415",
"name": "joe"
}
}
]
}
]
}
}
Here is my first attempt:
I have it joining the the two documents
How can I get rid of the duplicates ( bob:hammer and joe:shovel ) ?
and how do I include the "when" ?
Here is the playground that provides the following :
[
{
"_id": ObjectId("5a934e000102030405000000"),
"user_info": {
"Name": "Bob",
"_id": "5f60c3b7f93d8e00a1cdf414"
},
"work_role": {
"Name": "shovel",
"_id": "3a60dc1069c27c015ede1111"
}
},
{
"_id": ObjectId("5a934e000102030405000000"),
"user_info": {
"Name": "Bob",
"_id": "5f60c3b7f93d8e00a1cdf414"
},
"work_role": {
"Name": "hammer",
"_id": "3a60dc1069c27c015ede1122"
}
},
{
"_id": ObjectId("5a934e000102030405000000"),
"user_info": {
"Name": "Joe",
"_id": "5f60c3b7f93d8e00a1cdf415"
},
"work_role": {
"Name": "shovel",
"_id": "3a60dc1069c27c015ede1111"
}
},
{
"_id": ObjectId("5a934e000102030405000000"),
"user_info": {
"Name": "Joe",
"_id": "5f60c3b7f93d8e00a1cdf415"
},
"work_role": {
"Name": "hammer",
"_id": "3a60dc1069c27c015ede1122"
}
}
]
After beating my head against the wall for some time...
I found a pretty cool feature of mongo "references"
eg:
REF_work: { type: Schema.Types.ObjectId, required: true, ref: 'work' },
REF_person: { type: Schema.Types.ObjectId, required: true, ref: 'users' },
then when I call it from my get function I add a populate to the find
assignments.find(query).populate('daily.cp.REF_person').populate('daily.cp.REF_work');
I get exactly what I want:
[
{
"_id": ObjectId("5a934e000102030405000000"),
"REF_person": {
"Name": "Bob",
"_id": "5f60c3b7f93d8e00a1cdf414"
},
"REF_work": {
"Name": "shovel",
"_id": "3a60dc1069c27c015ede1111"
}
},
{
"_id": ObjectId("5a934e000102030405000000"),
"REF_person": {
"Name": "Joe",
"_id": "5f60c3b7f93d8e00a1cdf415"
},
"REF_work": {
"Name": "hammer",
"_id": "3a60dc1069c27c015ede1122"
}
}
]
Record is database:
[
{
"title": "title1",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
},
{
"title": "title2",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
},
{
"title": "title3",
"author": [
{
"name": "user1",
"register": true
},
{
"name": "user2",
"register": true
}
],
"tags": [
"tag1",
"tag2",
"tag3"
]
}
]
expected output:
{"tag":"tag1", "titles":["title1","title2","title3"], "size":3}
{"tag":"tag2", "titles":["title2","title4"], "size":2}
Can someone help with aggregate query?
You can use group
$unwind to deconstruct the array
$group to regroup the based on tags
$project to show the desired output
Here is the code,
db.collection.aggregate([
{ "$unwind": "$tags" },
{
"$group": {
"_id": "$tags",
"titles": { "$push": "$title" }
}
},
{
$project: {
tag: "$_id",
titles: 1,
size: { $size: "$titles" },
_id: "$$REMOVE"
}
}
])
Working Mongo playground
OBS! Noob question probably :)
Given the following data, how can I query and return a summary for each index?
[
{
"title": "test",
"indexes":[
{ "id":1, "value": 0.5764860139860139860139860140 },
{ "id":2, "value": 0.3083479020979020979020979020 },
{ "id":3, "value": 0.1151660839160839160839160838 }
]
},
{
"title": "test",
"indexes":[
{ "id":1, "value": 0.5764860139860139860139860140 },
{ "id":2, "value": 0.3083479020979020979020979020 },
{ "id":3, "value": 0.1151660839160839160839160838 }
]
},
{
"title": "test",
"indexes":[
{ "id":1, "value": 0.5764860139860139860139860140 },
{ "id":2, "value": 0.3083479020979020979020979020 },
{ "id":3, "value": 0.1151660839160839160839160838 }
]
},
{
"title": "test",
"indexes":[
{ "id":1, "value": 0.5764860139860139860139860140 },
{ "id":2, "value": 0.3083479020979020979020979020 },
{ "id":3, "value": 0.1151660839160839160839160838 }
]
}
]
I.e. I want to produce something like this:
index.id:1, total: 2.305...
index.id:2, total: 1.233...
etc
db.collection.aggregate([
{
"$unwind": "$indexes"
},
{
$group: {
_id: "$indexes.id",
total: {
$sum: "$indexes.value"
}
}
}
])
try this query
you will get like this
[
{
"_id": 2,
"total": 1.2333916083916083
},
{
"_id": 1,
"total": 2.305944055944056
},
{
"_id": 3,
"total": 0.4606643356643357
}
]
db.collection.aggregate([
{
$unwind: "$indexes"
},
{
$group: {
_id: "$indexes.id",
total: {
$sum: "$indexes.value"
}
}
}
])
Working Mongo playground
I have collections with following values:
reports
{
"_id": { "$oid": "5f05e1d13e0f6637739e215b" },
"testReport": [
{
"name": "Calcium",
"value": "87",
"slug": "ca",
"details": {
"description": "description....",
"recommendation": "recommendation....",
"isNormal": false
}
},
{
"name": "Magnesium",
"value": "-98",
"slug": "mg",
"details": {
"description": "description....",
"recommendation": "recommendation....",
"isNormal": false
}
}
],
"patientName": "Patient Name",
"clinicName": "Clinic",
"gender": "Male",
"bloodGroup": "A",
"createdAt": { "$date": "2020-07-08T15:10:09.612Z" },
"updatedAt": { "$date": "2020-07-08T15:10:09.612Z" }
},
setups
{
"_id": { "$oid": "5efcba7503f4693d164e651d" },
"code": "Ca",
"codeLower": "ca",
"name": "Calcium",
"valueFrom": -75,
"valueTo": -51,
"treatmentDescription": "description...",
"isNormal": false,
"gender": "",
"recommendation": "recommendation...",
"createdAt": { "$date": "2020-07-01T16:31:50.205Z" },
"updatedAt": { "$date": "2020-07-01T16:31:50.205Z" }
},
{
"_id": { "$oid": "5efcba7503f4693d164e651e" }, // <=== should find this for Calcium
"code": "Ca",
"codeLower": "ca",
"name": "Calcium",
"valueFrom": 76,
"valueTo": 100,
"treatmentDescription": "description...",
"isNormal": false,
"gender": "",
"recommendation": "recommendation...",
"createdAt": { "$date": "2020-07-01T16:31:50.205Z" },
"updatedAt": { "$date": "2020-07-01T16:31:50.205Z" }
},
{
"_id": { "$oid": "5efcba7603f4693d164e65bb" }, // <=== should find this for Magnesium
"code": "Mg",
"codeLower": "mg",
"name": "Magnesium",
"valueFrom": -100,
"valueTo": -76,
"treatmentDescription": "description...",
"isNormal": false,
"gender": "",
"recommendation": "recommendation...",
"createdAt": { "$date": "2020-07-01T16:31:50.205Z" },
"updatedAt": { "$date": "2020-07-01T16:31:50.205Z" }
},
{
"_id": { "$oid": "5efcba7503f4693d164e6550" },
"code": "Mg",
"codeLower": "mg",
"name": "Magnesium",
"valueFrom": 76,
"valueTo": 100,
"treatmentDescription": "description...",
"isNormal": false,
"gender": "",
"recommendation": "recommendation...",
"createdAt": { "$date": "2020-07-01T16:31:50.205Z" },
"updatedAt": { "$date": "2020-07-01T16:31:50.205Z" }
}
I want to search the value from reports collection and check whether the value is in range from the setups collection and return the _id and add the returned _ids in setupIds field on reports collection.
I tried with the following aggregation framework:
db.reports.aggegrate([
{
'$match': {
'_id': new ObjectId('5f05e1d13e0f6637739e215b')
}
}, {
'$lookup': {
'from': 'setups',
'let': {
'testValue': '$testReport.value',
'testName': '$testReport.name'
},
'pipeline': [
{
'$match': {
'$expr': {
{
'$and': [
{
'$eq': [
'$name', '$$testName'
]
}, {
'$gte': [
'$valueTo', '$$testValue'
]
}, {
'$lte': [
'$valueFrom', '$$testValue'
]
}
]
}
}
}
}
],
'as': 'setupIds'
}
}
])
This query didn't find the expected results.
This is the updated reports collection I want:
{
"_id": { "$oid": "5f05e1d13e0f6637739e215b" },
"setupIds": [{ "$oid": "5efcba7503f4693d164e651e" }, { "$oid": "5efcba7603f4693d164e65bb" }], // <=== Here, array of the ObjectId (ref: "Setups")
"patientName": "Patient Name",
"clinicName": "Clinic",
"gender": "Male",
"bloodGroup": "A",
"createdAt": { "$date": "2020-07-08T15:10:09.612Z" },
"updatedAt": { "$date": "2020-07-08T15:10:09.612Z" }
},
You can try like following
[{
$match: {
_id: ObjectId('5f05e1d13e0f6637739e215b')
}
}, {
$unwind: {
path: "$testReport"
}
}, {
$lookup: {
from: 'setup',
'let': {
testValue: {
$toInt: '$testReport.value'
},
testName: '$testReport.name'
},
pipeline: [{
$match: {
$expr: {
$and: [{
"$eq": [
"$name",
"$$testName"
]
},
{
"$gte": [
"$valueTo",
"$$testValue"
]
},
{
"$lte": [
"$valueFrom",
"$$testValue"
]
}
]
}
}
}],
as: 'setupIds'
}
}, {
$group: {
_id: "$_id",
patientName: {
$first: "$patientName"
},
clinicName: {
$first: "$clinicName"
},
gender: {
$first: "$gender"
},
bloodGroup: {
$first: "$bloodGroup"
},
createdAt: {
$first: "$createdAt"
},
updatedAt: {
$first: "$updatedAt"
},
setupIds: {
$addToSet: "$setupIds._id"
}
}
}, {
$addFields: {
setupIds: {
$reduce: {
input: "$setupIds",
initialValue: [],
in: {
$setUnion: ["$$this", "$$value"]
}
}
}
}
}]
Working Mongo playground
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.