Develop Reference

MongoDB - How to aggregate data for each record

I have some stored data like this:
{
"_id" : 1,
"serverAddresses" : {
"name" : "0.0.0.0:8000",
"name2": "0.0.0.0:8001"
}
}
I need aggregated data to this:
[
{
"gameId": "1",
"name": "name1",
"url": "0.0.0.0:8000"
},
{
"gameId": "1",
"name": "name2",
"url": "0.0.0.0:8001"
}
]
What is the solution without using for loop?

$project - Add addresses field by converting $serverAddress to (key-value) array.
$unwind - Descontruct addresses field to multiple documents.
$replaceRoot - Decorate the output document based on (2).
db.collection.aggregate([
{
"$project": {
"addresses": {
"$objectToArray": "$serverAddresses"
}
}
},
{
$unwind: "$addresses"
},
{
"$replaceRoot": {
"newRoot": {
gameId: "$_id",
name: "$addresses.k",
address: "$addresses.v"
}
}
}
])
Sample Mongo Playground

How do i remove a item in a object if i did not know the key name in MongoDB?

Please refer this image
Please refer the image, Here i want to delete bearing_accelerometer_sensor field but i dont know this key name but i know the value here (i.e ObjectId("618e3fc8fccb88b50f2d9317")), I'm aware we can use this query db.getCollection('algorithm_association_collection').update({},{"$unset":{"sensor.bearing_accelerometer_sensor":""}}) to delete the field but in my case i dont know the key name "bearing_accelerometer_sensor". Pls help thanks in advance

You can use this one:
db.collection.aggregate([
{
$set: {
sensor: {
$filter: {
input: { $objectToArray: "$sensor" },
cond: { $ne: [ "$$this.v", ObjectId("618e3fc8fccb88b50f2d9317") ] }
}
}
}
},
{ $set: { sensor: { $arrayToObject: "$sensor" } } }
])
Mongo Playground
If you like to update existing collection, you can use the pipeline in an update statement:
db.collection.updateMany({}, [
{
$set: {
sensor: {
$filter: {
input: { $objectToArray: "$sensor" },
cond: { $ne: [ "$$this.v", ObjectId("618e3fc8fccb88b50f2d9317") ] }
}
}
}
},
{ $set: { sensor: { $arrayToObject: "$sensor" } } }
])

Basic request to mongodb with pymongo

I need to get all objects inside "posts" that have "published: true"
with pymongo. I've tried already so many variants but all I can do:
for elt in db[collection].find({}, {"posts"}):
print(elt)
And it'll show all "posts". I've tried smth like this:
for elt in db[collection].find({}, {"posts", {"published": {"$eq": True}}}):
print(elt)
But it doesn't work. Help, I'm trying for 3 days already =\

What you want to be doing is to use the aggregate $filter like so:
db[collection].aggregate([
{
"$match": { // only fetch documents with such posts
"posts.published": {"$eq": True}
}
},
{
"$project": {
"posts": {
"$filter": {
"input": "$posts",
"as": "post",
"cond": {"$eq": ["$$post.published", True]}
}
}
}
}
])
Note that the currenct structure returned will be:
[
{posts: [post1, post2]},
{posts: [post3, post4]}
]
If you want to retrieve it as a list of posts you'll need to add an $unwind stage to flatten the array.
The query options are quite limited you can do it with $elemMatch (projection) or with the $ operator but both of these return only the first post that matches the condition which is not what you want.
------- EDIT --------
Realizing posts is actually an object and not an array, you'll have to turn the object to an array, iterate over to filter and then restore the structure like so:
db.collection.aggregate([
{
$project: {
"posts": {
"$arrayToObject": {
$filter: {
input: {
"$objectToArray": "$posts"
},
as: "post",
cond: {
$eq: [
"$$post.v.published",
true
]
}
}
}
}
}
}
])
Mongo Playground

What I assumed that your document looks like this,
{
"_id" : ObjectId("5f8570f8afdefd2cfe7473a7"),
"posts" : {
"a" : {
"p" : false,
"name" : "abhishek"
},
"k" : {
"p" : true,
"name" : "jack"
},
"c" : {
"p" : true,
"name" : "abhinav"
}
}}
You can try the following query but the result format will be a bit different, adding that for clarification,
db.getCollection('temp2').aggregate([
{
$project: {
subPost: { $objectToArray: "$posts" }
}
},
{
'$unwind' : '$subPost'
},
{
'$match' : {'subPost.v.p':true}
},
{
'$group': {_id:'$_id', subPosts: { $push: { subPost: "$subPost"} }}
}
])
result format,
{
"_id" : ObjectId("5f8570f8afdefd2cfe7473a7"),
"subPosts" : [
{
"subPost" : {
"k" : "k",
"v" : {
"p" : true,
"name" : "jack"
}
}
},
{
"subPost" : {
"k" : "c",
"v" : {
"p" : true,
"name" : "abhinav"
}
}
}
]
}

mongoDB - Get newest date from document in array

I want to retrieve the array object with the newest dates for a particular document.
But I sadly can't solve it, I always end up with errors.
Dateformat 2020-06-10T13:25:25.645+00:00 datetime.now()
Sample data
collection.insert_one(
{
"document_name": "My Document",
"status": [
{
"status_time": datetimeobject, # 2020-01-02T13:25:25.645+00:00
"status_title": "Sample Title 1"
},
{
"status_time": datetimeobject, # 2020-06-10T13:25:25.645+00:00
"status_title": "Sample Title"
}
]
})
What I've tried
result = collection.find_one({"document_name": "My Document"}, {"status": 1}).sort({"status.status_time": -1}).limit(1)
result = collection.find_one({"document_name": "My Document"}, {"$max": {"status.status_time": -1})
result = collection_projects.find_one({"document_name": "Document"}, {"status": {"$elemMatch": {"$max": "$´status_time"}}})
result = list(collection.find({"document_name": "Document"}, {"_id": 0, "status": 1}).limit(1))
result = collection_projects.find_one(
{"document_name": "My Document"},
{"status.status_time": {"$arrayElemAt": -1}})
Result I'm looking for
{
"status_time": datetimeobject, # 2020-06-10T13:25:25.645+00:00
"status_title": "Sample Title 2"
}

You need to use aggregation to achieve this :
Query 1 :
db.collection.aggregate([
/** Re-create `status` field with what is needed */
{
$addFields: {
status: {
$reduce: {
input: "$status", // Iterate on array
initialValue: { initialDate: ISODate("1970-06-09T17:56:34.350Z"), doc: {} }, // Create initial values
in: { // If condition is met push current value to accumulator or return acummulator as is
initialValue: { $cond: [ { $gt: [ "$$this.status_time", "$$value.initialDate" ] }, "$$this.status_time", "$$value.initialDate" ] },
doc: { $cond: [ { $gt: [ "$$this.status_time", "$$value.initialDate" ] }, "$$this", "$$value" ] }
}
}
}
}
},
/**
* re-create `status` field from `$status.doc`
* Since it will always be having only on object you can make `status` as an object ratherthan an array
* Just in case if `status` need to be an array you need do { status: [ "$status.doc" ] }
*/
{
$addFields: { status: "$status.doc" }
}
])
Test : mongoplayground
Ref : $reduce , pymongo
Query 2 :
db.collection.aggregate([
/** unwind on `status` array */
{
$unwind: {
path: "$status",
preserveNullAndEmptyArrays: true // preserves doc where `status` field is `[]` or null or missing (Optional)
}
},
/** sort on descending order */
{
$sort: { "status.status_time": -1 }
},
/** group on `_id` & pick first found doc */
{
$group: { _id: "$_id", doc: { $first: "$$ROOT" } }
},
/** make `doc` field as new root */
{
$replaceRoot: { newRoot: "$doc" }
}
])
Test : mongoplayground
Test both queries, I believe on a huge dataset $unwind & $sort might be a bit slow, similar to iteration on a huge array.

You will have to use aggregate with $reduce, this solution is similar to #whoami's except there is no nested document when using $reduce
db.collection.aggregate([
{
$match: {
document_name: "My Document"
}
},
{
$project: { // use $project if you only want the status, use $addFields if you want other fields as well
status: {
$reduce: {
input: "$status",
initialValue: null,
in: {
$cond: [
{
$gte: [
"$$this.status_time",
"$$value.status_time"
]
},
"$$this",
"$$value"
]
}
}
}
}
}
])
mongoplayground

Multiple queries in one ElasticSearch Query

Here an example of an item indexed in ES :
{
"_id" : ..,
"class": "A",
"name": "item1"
}
I want a single query where I can get all items of the same class of the item with name "item1". So basically, I want all indexed items with class A, with only having the name.
I can do it with 2 queries :
Query 1 :
SEARCH
{
"query": {
"query_string": {
"default_field": "name",
"query": "item1"
}
}
Then from this I get the class and I write this query :
SEARCH
{
"query": {
"query_string": {
"default_field": "class",
"query": "A"
}
}
Any idea ? I know there's an easy way but I can't find it...

You can combine multiple queries with clauses using a bool query. In this case, two criteria must be satisified, so both queries should be must clauses
{
"query": {
"bool": {
"must": [
{
"query_string": {
"query": "item1",
"fields": [
"name"
]
}
},
{
"query_string": {
"query": "A",
"fields": [
"class"
]
}
}
]
}
}
}
If you don't need relevancy scores, which it doesn't appear that you do in this case, both queries could be filter clauses instead of must clauses.
If name and class are mapped as keyword datatypes, you may want to use a term-level query as opposed to a full-text query like query_string query. Here's what that would look like, using filter clauses
{
"query": {
"bool": {
"filter": [
{
"term": {
"name": {
"value": "item1"
}
}
},
{
"term": {
"class": {
"value": "A"
}
}
}
]
}
}
}