mongoDB read performance difference between one to many models and normalized models - mongodb

here are 2 possibilities for a note taking database that will have multiple notes for multiple users to keep track of
1.
[
{
"_id": "abcd",
"userInfo": {
"userID": "1",
"notes": [
{
"noteID": "1",
"text": "123"
},
{
"noteID": "2",
"text": "456"
},
{
"noteID": "3",
"text": "789"
}
]
}
},
{
"_id": "efgh",
"userInfo": {
"userID": "2",
"notes": [
{
"noteID": "1",
"text": "123"
},
{
"noteID": "2",
"text": "456"
}
]
}
}
]
And the 2nd option:
[
{
"_id": "abcd",
"userID": "1",
"noteID": "1",
"text": "123"
},
{
"_id": "efgh",
"userID": "1",
"noteID": "2",
"text": "456"
},
{
"_id": "ijkl",
"userID": "1",
"noteID": "3",
"text": "789"
},
{
"_id": "mnop",
"userID": "2",
"noteID": "1",
"text": "123"
},
{
"_id": "wxyz",
"userID": "2",
"noteID": "2",
"text": "123"
}
]
I'd expect 1 to have a much better performance when it comes to loading notes for a single user(if the user has a ton of notes). However, 2nd option is much better when modifying and adding individual notes.

Related

MongoDB lookup with multiple nested levels

In my application, I have a section of comments and replies under some documents.
Here's how my database schema looks like
db.updates.insertOne({
"_id": "62347813d28412ffd82b551d",
"documentID": "17987e64-f848-40f3-817e-98adfd9f4ecd",
"stream": [
{
"id": "623478134c449b218b68f636",
"type": "comment",
"text": "Hey #john, we got a problem",
"authorID": "843df3dbbdfc62ba2d902326",
"taggedUsers": [
"623209d2ab26cfdbbd3fd348"
],
"replies": [
{
"id": "623478284c449b218b68f637",
"type": "reply",
"text": "Not sure, let's involve #jim here",
"authorID": "623209d2ab26cfdbbd3fd348",
"taggedUsers": [
"26cfdbbd3fd349623209d2ab"
]
}
]
}
]
})
db.users.insertMany([
{
"_id": "843df3dbbdfc62ba2d902326",
"name": "Manager"
},
{
"_id": "623209d2ab26cfdbbd3fd348",
"name": "John"
},
{
"_id": "26cfdbbd3fd349623209d2ab",
"name": "Jim"
},
])
I want to join those two collections, and replace user ids with complete user information on all levels. So the final JSON should look like this
{
"_id": "62347813d28412ffd82b551d",
"documentID": "17987e64-f848-40f3-817e-98adfd9f4ecd",
"stream": [
{
"id": "623478134c449b218b68f636",
"type": "comment",
"text": "Hey #john, we got a problem",
"author": {
"_id": "843df3dbbdfc62ba2d902326",
"name": "Manager"
},
"taggedUsers": [
{
"_id": "623209d2ab26cfdbbd3fd348",
"name": "John"
}
],
"replies": [
{
"id": "623478284c449b218b68f637",
"type": "reply",
"text": "Not sure, let's involve #jim here",
"author": {
"_id": "623209d2ab26cfdbbd3fd348",
"name": "John"
},
"taggedUsers": [
{
"_id": "26cfdbbd3fd349623209d2ab",
"name": "Jim"
}
]
}
]
}
]
}
I know how to do the $lookup on the top-level fields, including pipelines, but how can I do with the nested ones?

mongodb - filter collection by string array contains ""

For the below document, I want to write mongodb query to get the result.
[{
"id": "1",
"class": "class1",
"value": "xyz"
}, {
"id": "2",
"class": "class2",
"value": "abc"
}, {
"id": "3",
"class": "class3",
"value": "123"
}, {
"id": "4",
"class": "class4"
}, {
"id": "5",
"class": "class5",
"value": ""
}
]
The search parameter is an array of values - ["abc", "xyz", ""] and this is
going to look attribute "value"
The output should be below and in this case, the third item in the search array "" is pointing to collection that has "id" - 4 and 5 :
[{
"id": "1",
"class": "class1",
"value": "xyz"
}, {
"id": "2",
"class": "class2",
"value": "abc"
}, {
"id": "4",
"class": "class4"
}, {
"id": "5",
"class": "class5",
"value": ""
}
]
Please assist to provide the mongodb query to get the result like this

Whenever you have blank string you can add null in array, like this,
db.collection.find({
value: {
$in: ["abc", "xyz", "", null]
}
})

check if a field of type array contains an array

Im using mongoose, I have the following data of user collection:
[{
"_id": "1",
"notes": [
{
"value": "A90",
"text": "math"
},
{
"value": "A80",
"text": "english"
},
{
"value": "A70",
"text": "art"
}
]
},
{
"_id": "2",
"notes": [
{
"value": "A90",
"text": "math"
},
{
"value": "A80",
"text": "english"
}
]
},
{
"_id": "3",
"notes": [
{
"value": "A80",
"text": "art"
}
]
}]
and I have as a parameters the following array: [ "A90", "A80" ]
so I want to make a query to use this array to return only the records that have all the array items in the notes (value) table.
So for the example above it will return:
[{
"_id": "1",
"notes": [
{
"value": "A90",
"text": "math"
},
{
"value": "A80",
"text": "english"
},
{
"value": "A70",
"text": "art"
}
]
},
{
"_id": "2",
"notes": [
{
"value": "A90",
"text": "math"
},
{
"value": "A80",
"text": "english"
}
]
}]
I tried the following find query:
{ "notes": { $elemMatch: { value: { $in: valuesArray } } }}
but it returns a record even if just one element in valuesArray exist.

it turned out to be quite easy:
find({ "notes.value": { $all: arrayValues } })

How to check $exists in one to many relationship mongodb sails js?

Is there any way to find records that collection is empty?
For example please find below array. I want only that records with index "companydata" is empty. and also how can i get data that does not have empty "companydata" data.
Thanks in advance.
[
{
"company_id": {
"company_name": "C2",
"slug": "c2",
"is_organized": 1,
"status": "1",
"id": "5adf158f547f7f0314ca8b56",
"companydata": []
},
"user_id": "5ab889aee74a151b50d04ec1",
"status": "0",
"id": "5ae014e7432e85298081be0b"
},
{
"company_id": {
"company_name": "My Compnay",
"slug": "my-compnay",
"is_organized": 1,
"status": "1",
"id": "5ad442d98a0e0c1358ca93df",
"companydata": [
{
"name": "Bhavesh Amin",
"company_id": "5ad442d98a0e0c1358ca93df",
"status": "0",
"id": "5ad442da8a0e0c1358ca93e0"
}
]
},
"user_id": "5ab889aee74a151b50d04ec1",
"status": "0",
"id": "5ae01388432e85298081bdf8"
},
{
"company_id": {
"company_name": "Organization Name",
"slug": "organization-name",
"is_organized": 1,
"status": "1",
"id": "5ad08f9b938d1131eceea624",
"companydata": [
{
"name": "Helen H. Langley",
"company_id": "5ad08f9b938d1131eceea624",
"status": "1",
"id": "5ad08f9b938d1131eceea625"
}
]
},
"user_id": "5ab889aee74a151b50d04ec1",
"status": "0",
"id": "5ad42a5f52851a2b1449db2d"
},
]

Nested grouping of array

There are 3 master collection of category , subcategory and criteria each, i will be building framework with any possible combination of category , subcategory and criteria which will be stored as below-
framework document is added below having list of criteriaconfig as embedded object which further have single object of category , subcategory and criteria. you can refer criteriaconfig as link table that u call in mysql.
[
{
"id": "592bc3059f3ad715002b2331",
"name": "Framework1",
"description": "framework 1 for testing",
"criteriaConfigs": [
{
"id": "592bc3059f3ad715002b232f",
"category": {
"id": "591c2f5faa187956b2d0fb39",
"name": "category1",
"description": "category1",
"deleted": false,
"createdDate": 1495019359558
},
"subCategory": {
"id": "591c2f5faa187956b2d0fb83",
"name": "subCat1",
"description": "subCat1"
},
"criteria": {
"id": "591c2f5faa187956b2d0fbad",
"name": "criteria1",
"measure": "Action"
}
},
{
"id": "592bc3059f3ad715002b232e",
"category": {
"id": "591c2f5faa187956b2d0fb37",
"name": "Process",
"description": "Enagagement"
},
"subCategory": {
"id": "591c2f5faa187956b2d0fb81",
"name": "COMM / BRANDING",
"description": "COMM / BRANDING"
},
"criteria": {
"id": "591c2f5faa187956b2d0fba9",
"name": "Company representative forgets about customer on hold",
"measure": ""
}
} ]
},
{
"id": "592bc3059f3ad715002b2332",
"name": "Framework2",
"description": "framework 2 for testing",
"criteriaConfigs": [
{
"id": "592bc3059f3ad715002b232f",
"category": {
"id": "591c2f5faa187956b2d0fb39",
"name": "category1",
"description": "category1"
},
"subCategory": {
"id": "591c2f5faa187956b2d0fb83",
"name": "subCat1",
"description": "subCat1"
},
"criteria": {
"id": "591c2f5faa187956b2d0fbad",
"name": "criteria1",
"measure": "Action"
}
}
]
}
]
i need a view containing framework that will contain all list of category and inside category there will be list of added subcategory and inside subcategory will have list of criteria for single framework.
expected result -
[
{
"id": "f1",
"name": "Framework1",
"description": "framework 1 for testing",
"categories": [
{
"id": "c2",
"name": "category2",
"description": "category2",
"subCategories": [
{
"id": "sb1",
"name": "subCat1",
"description": "subCat1",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr2",
"name": "criteria2",
"measure": "Action"
},
{
"id": "cr3",
"name": "criteria3",
"measure": "Action"
}]
},
{
"id": "sb2",
"name": "subCat2",
"description": "subCat2",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr4",
"name": "criteria4",
"measure": "Action"
}]
}]
},
{
"id": "c1",
"name": "category1",
"description": "category1",
"subCategories": [
{
"id": "sb3",
"name": "subCat3",
"description": "subCat3",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr2",
"name": "criteria2",
"measure": "Action"
}
]},
{
"id": "sb2",
"name": "subCat2",
"description": "subCat2",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr4",
"name": "criteria4",
"measure": "Action"
}]
}
]
}]
},
{
"id": "f2",
"name": "Framework2",
"description": "framework 2 for testing",
"categories": [
{
"id": "c2",
"name": "category2",
"description": "category2",
"subCategories": [
{
"id": "sb4",
"name": "subCat5",
"description": "subCat5",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr3",
"name": "criteria3",
"measure": "Action"
}]
},
{
"id": "sb2",
"name": "subCat2",
"description": "subCat2",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr4",
"name": "criteria4",
"measure": "Action"
}]
}]
},
{
"id": "c1",
"name": "category1",
"description": "category1",
"subCategories": [
{
"id": "sb3",
"name": "subCat3",
"description": "subCat3",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr2",
"name": "criteria2",
"measure": "Action"
}
]},
{
"id": "sb2",
"name": "subCat2",
"description": "subCat2",
"criterias": [
{
"id": "cr1",
"name": "criteria1",
"measure": "Action"
},
{
"id": "cr4",
"name": "criteria4",
"measure": "Action"
}]
}
]
}]
}
]
Note - Category document doesn't have any reference to subcategory and same way subcategory doesn't have any reference to criteria object currently as they are master data and are generic , framework is created with their combination dynamically.

If you want to try to do all the work in the aggregation, you could group first by subcategory, then by category like:
db.collection.aggregate([
{$unwind:"$criteriaConfigs"},
{$project:{
_id:0,
category:"$criteriaConfigs.category",
subCategory:"$criteriaConfigs.subCategory",
criteria:"$criteriaConfigs.criteria"
}},
{$group:{
_id:{"category":"$category","subCategory":"$subCategory"},
criteria:{$addToSet:"$criteria"}
}},
{$group:{
_id:{"category":"$_id.category"},
subCategories:{$addToSet:{subCategory:"$_id.subCategory",
criteria:"$criteria"}}
}},
{$project:{
_id:0,category:"$_id.category",
subCategories:"$subCategories"
}}
])
Depending on how you plan to us the return data, it may be more efficient to return each unique combination:
db.collection.aggregate([
{$unwind:"$criteriaConfigs"},
{$group:{
_id:{
category:"$criteriaConfigs.category.name",
subCategory:"$criteriaConfigs.subCategory.name",
criteria:"$criteriaConfigs.criteria.name"
}
}},
{$project:{
_id:0,
category:"$_id.category",
subCategory:"$_id.subCategory",
criteria:"$_id.criteria"
}}
])
I'm not sure from your question what shape you are expecting the return data to have, so you may need to adjust for that.