Related
I have created a pipeline between 3 collections and the final result must be in count based on their respective field. Hope someone gives some assistance.
INPUT
{
"_id" : "josh_7#user.com",
"users" : [
{
"_id" : ObjectId("612f60cb5dce270014648294"),
"userType" : "Admin",
"userPlan" : "GROWTH",
"username" : "josh_7#user.com",
"company" : "josh_7#user.com",
"accounts" : [
{
"_id" : {
"username" : "josh_7#user.com"
}
},
{
"_id" : {
"username" : "josh_7#user.com",
"status" : "ERROR"
}
},
{
"_id" : {
"username" : "josh_7#user.com",
"status" : "SENT"
}
},
{
"_id" : {
"username" : "josh_7#user.com",
"status" : "REMOVED_FROM_QUEUE"
}
},
{
"_id" : {
"username" : "josh_7#user.com",
"status" : "REMOVED_FOR_PUBLISH"
}
},
{
"_id" : {
"username" : "josh_7#user.com",
"status" : "UNSCHEDULED"
}
}
]
},
]
}
EXPECTED OUTPUT
{
"_id": "josh_7#user.com",
"users": [
{
"username": "josh_7#user.com",
"userType": "Admin",
"userPlan": "GROWTH",
"company": "josh_7#user.com",
"accounts": [ // This section is where i got stuck
{
"_id": "josh_7#user.com,
"READY_TO_GO_count": 0,
"SENT": 36,
"UNSCHEDULED": 0,
"AWAITING_APPROVAL": 0,
"REMOVED_FROM_QUEUE": 16,
"FLAGGED": 1,
"ERROR": 1
}
]
},
I tried using the below line
{$group:{_id:"$status",count:{$sum:1}}}
The output was :
"accounts" : [
{
"_id" : "SENT",
"count" : 4.0
},
{
"_id" : "REMOVED_FROM_QUEUE",
"count" : 8.0
}
]
I Figured something for the above question, If it's not the best way, Please do correct me.
{$group:{_id:"$username","SENT":{$sum:{$cond:[{$eq:["$status","SENT"]},1,0]}},"AWAITING_APPROVAL":{$sum:{$cond:[{$eq:["$status","AWAITING_APPROVAL"]},1,0]}},"FLAGGED":{$sum:{$cond:[{$eq:["$status","FLAGGED"]},1,0]}},}}
Result
{
"_id" : ObjectId("5ed7abc5986c050012d4aa4a"),
"userType" : "Regular",
"userPlan" : "GRANDE",
"username" : "shan2#psk3n.com",
"company" : "tariyi8792#psk3n.com",
"accounts" : [
{
"_id" : "shan2#psk3n.com",
"SENT" : 1.0,
"AWAITING_APPROVAL" : 0.0,
"FLAGGED" : 0.0
}
]
}
I have datas of following format collection(projects) inside my database:
{ "_id" : ObjectId("5981a80f223e491a58230e5d"), "id" : 2, "name" : "gbqplhlqxzwl", "managerId" : 65151, "startDate" : "03.11.1999", "finishDate" : "02.01.2003", "projectStatus" : "POSTPONED", "participants" : [ ], "estimatedBudget" : 6017891.811079914 }
{ "_id" : ObjectId("5981a80f223e491a58230e5e"), "id" : 3, "name" : "erfekfsdgryu", "managerId" : 83749, "startDate" : "07.07.2007", "finishDate" : "26.12.2027", "projectStatus" : "POSTPONED", "participants" : [ 19229, 81856, 79270, 5509, 70344, 39424 ], "estimatedBudget" : 3086213.8981674756 }
{ "_id" : ObjectId("5981a80f223e491a58230e5f"), "id" : 1, "name" : "jvbzobhppntd", "managerId" : 18925, "startDate" : "29.04.1999", "finishDate" : "13.10.2008", "projectStatus" : "OPEN", "participants" : [ 46100, 96968, 6676, 56121, 4716, 68901, 43990, 48587, 62547, 30292, 65153, 17551, 27083, 20261, 27097, 50036, 86585, 69890, 18790, 22592, 60774, 93709, 78471, 27157, 4328, 36501, 47296, 16831 ], "estimatedBudget" : 3581496.7068344904 }
{ "_id" : ObjectId("5981a80f223e491a58230e60"), "id" : 4, "name" : "cdspkkqwvwld", "managerId" : 62042, "startDate" : "13.03.1998", "finishDate" : "20.06.2007", "projectStatus" : "OPEN", "participants" : [ 53480, 60897, 23677, 22064, 60807, 66637, 84609, 28378, 87143, 27675, 79283, 94992, 20429, 48769, 91671, 41747, 21651, 91134, 41684, 57228, 51949, 18756, 45679, 87781, 67287, 6902, 27526 ], "estimatedBudget" : 2126283.953787842 }
....
I need to find the busiest employee and list all his projects.
participants array contains employee ids who participate in the project.
I use the following query to find the busiest employee:
db.projects.aggregate(
{
$unwind: '$participants'
},
{
$addFields: {
count: 1
}
},
{
$group: {
_id : '$participants',
participation_count : {
'$sum':'$count'
}
}
},
{
$sort:{participation_count:-1}
},
{
$limit:1
}
)
and this work correctly. But I have no ideas how to list all his projects.
any ideas?
db.projects.aggregate(
[
{
$unwind: '$participants'
},
{
$addFields: {
count: 1
}
},
{
$group: {
_id : '$participants',
participation_count : {'$sum':'$count'},
projectId : {$push: '$id'}
}
},
{
$sort:{participation_count:-1}
},
{
$limit:1
}
],
{
allowDiskUse:true
}
)
I am trying to port an existing SQL schema into Mongo.
We have document tables, with sometimes several times the same document, with a different revision but the same reference. I want to get only the latest revisions of the documents.
A sample input data:
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC305",
"code" : "305-D",
"title" : "Document 305",
"creationdate" : ISODate("2011-11-24T15:13:28.887Z"),
"creator" : "X"
},
{
"Uid" : "xxx",
"status" : "COMMENTED",
"reference" : "DOC306",
"code" : "306-A",
"title" : "Document 306",
"creationdate" : ISODate("2011-11-28T07:23:18.807Z"),
"creator" : "X"
},
{
"Uid" : "xxx",
"status" : "COMMENTED",
"reference" : "DOC306",
"code" : "306-B",
"title" : "Document 306",
"creationdate" : ISODate("2011-11-28T07:26:49.447Z"),
"creator" : "X"
},
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC501",
"code" : "501-A",
"title" : "Document 501",
"creationdate" : ISODate("2011-11-19T06:30:35.757Z"),
"creator" : "X"
},
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC501",
"code" : "501-B",
"title" : "Document 501",
"creationdate" : ISODate("2011-11-19T06:40:32.957Z"),
"creator" : "X"
}
Given this data, I want this result set (sometimes I want only the last revision, sometimes I want all revisions with an attribute telling me whether it's the latest):
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC305",
"code" : "305-D",
"title" : "Document 305",
"creationdate" : ISODate("2011-11-24T15:13:28.887Z"),
"creator" : "X",
"lastrev" : true
},
{
"Uid" : "xxx",
"status" : "COMMENTED",
"reference" : "DOC306",
"code" : "306-B",
"title" : "Document 306",
"creationdate" : ISODate("2011-11-28T07:26:49.447Z"),
"creator" : "X",
"lastrev" : true
},
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC501",
"code" : "501-B",
"title" : "Document 501",
"creationdate" : ISODate("2011-11-19T06:40:32.957Z"),
"creator" : "X",
"lastrev" : true
}
I already have a bunch of filters, sorting, and skip/limit (for pagination of data), so the final result set should be mindful of these constraints.
The current "find" query (built with the .Net driver), which filters fine but gives me all revisions of each document:
coll.find(
{ "$and" : [
{ "$or" : [
{ "deletedid" : { "$exists" : false } },
{ "deletedid" : null }
] },
{ "$or" : [
{ "taskid" : { "$exists" : false } },
{ "taskid" : null }
] },
{ "objecttypeuid" : { "$in" : ["xxxxx"] } }
] },
{ "_id" : 0, "Uid" : 1, "lastrev" : 1, "title" : 1, "code" : 1, "creator" : 1, "owner" : 1, "modificator" : 1, "status" : 1, "reference": 1, "creationdate": 1 }
).sort({ "creationdate" : 1 }).skip(0).limit(10);
Using another question, I have been able to build this aggregation, which gives me the latest revision of each document, but with not enough attributes in the result:
coll.aggregate([
{ $sort: { "creationdate": 1 } },
{
$group: {
"_id": "$reference",
result: { $last: "$creationdate" },
creationdate: { $last: "$creationdate" }
}
}
]);
I would like to integrating the aggregate with the find query.
I have found the way to mix aggregation and filtering:
coll.aggregate(
[
{ $match: {
"$and" : [
{ "$or" : [
{ "deletedid" : { "$exists" : false } },
{ "deletedid" : null }
] },
{ "$or" : [
{ "taskid" : { "$exists" : false } },
{ "taskid" : null }
] },
{ "objecttypeuid" : { "$in" : ["xxx"] } }
]
}
},
{ $sort: { "creationdate": 1 } },
{ $group: {
"_id": "$reference",
"doc": { "$last": "$$ROOT" }
}
},
{ $sort: { "doc.creationdate": 1 } },
{ $skip: skip },
{ $limit: limit }
],
{ allowDiskUse: true }
);
For each result node, this gives me a "doc" node with the document data. It has too much data still (it's missing projections), but it's a start.
Translated in .Net:
FilterDefinitionBuilder<BsonDocument> filterBuilder = Builders<BsonDocument>.Filter;
FilterDefinition<BsonDocument> filters = filterBuilder.Empty;
filters = filters & (filterBuilder.Not(filterBuilder.Exists("deletedid")) | filterBuilder.Eq("deletedid", BsonNull.Value));
filters = filters & (filterBuilder.Not(filterBuilder.Exists("taskid")) | filterBuilder.Eq("taskid", BsonNull.Value));
foreach (var f in fieldFilters) {
filters = filters & filterBuilder.In(f.Key, f.Value);
}
var sort = Builders<BsonDocument>.Sort.Ascending(orderby);
var group = new BsonDocument {
{ "_id", "$reference" },
{ "doc", new BsonDocument("$last", "$$ROOT") }
};
var aggregate = coll.Aggregate(new AggregateOptions { AllowDiskUse = true })
.Match(filters)
.Sort(sort)
.Group(group)
.Sort(sort)
.Skip(skip)
.Limit(rows);
return aggregate.ToList();
I'm pretty sure there are better ways to do this, though.
You answer is pretty close. Instead of $last, $max is better.
About $last operator:
Returns the value that results from applying an expression to the last document in a group of documents that share the same group by a field. Only meaningful when documents are in a defined order.
Get the last revision in each group, see code below in mongo shell:
db.collection.aggregate([
{
$group: {
_id: '$reference',
doc: {
$max: {
"creationdate" : "$creationdate",
"code" : "$code",
"Uid" : "$Uid",
"status" : "$status",
"title" : "$title",
"creator" : "$creator"
}
}
}
},
{
$project: {
_id: 0,
Uid: "$doc.Uid",
status: "$doc.status",
reference: "$_id",
code: "$doc.code",
title: "$doc.title",
creationdate: "$doc.creationdate",
creator: "$doc.creator"
}
}
]).pretty()
The output as your expect:
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC501",
"code" : "501-B",
"title" : "Document 501",
"creationdate" : ISODate("2011-11-19T06:40:32.957Z"),
"creator" : "X"
}
{
"Uid" : "xxx",
"status" : "COMMENTED",
"reference" : "DOC306",
"code" : "306-B",
"title" : "Document 306",
"creationdate" : ISODate("2011-11-28T07:26:49.447Z"),
"creator" : "X"
}
{
"Uid" : "xxx",
"status" : "ACCEPTED",
"reference" : "DOC305",
"code" : "305-D",
"title" : "Document 305",
"creationdate" : ISODate("2011-11-24T15:13:28.887Z"),
"creator" : "X"
}
I have data with multiple documents :
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e486"),
"empId" : "1"
"type" : "WebUser",
"city" : "Pune"
}
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e487"),
"empId" : "2"
"type" : "Admin",
"city" : "Mumbai"
}
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e488"),
"empId" : "3"
"type" : "Admin",
"city" : "Pune"
}
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e489"),
"empId" : "4"
"type" : "User",
"city" : "Mumbai"
}
I want to get data according to my multiple conditions :
condition 1:- {"type" : "WebUser", "city" : "Pune"}
condition 2:- {"type" : "WebUser", "city" : "Pune"} & {"type" : "User", "city" : "Mumbai"}
I want below result when run condition 1 :
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e486"),
"empId" : "1"
"type" : "WebUser",
"city" : "Pune"
}
When I run second condition :
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e486"),
"empId" : "1"
"type" : "WebUser",
"city" : "Pune"
}
{
"_id" : ObjectId("57b68dbbc19c0bd86d62e489"),
"empId" : "4"
"type" : "User",
"city" : "Mumbai"
}
I want above result by one query,
Currently I am using below aggregate query,
db.emp.aggregate([
{ $match: { '$and': [
{"type" : "WebUser", "city" : "Pune"},
{"type" : "User", "city" : "Mumbai"}
] } },
{ $group: { _id: 1, ids: { $push: "$empId" } } }
])
Above query work for first condition & fails for other. Please help me.
For the second condition, you can use the $in operator in your query as:
db.emp.find({
"type" : { "$in": ["WebUser", "User"] },
"city" : { "$in": ["Pune", "Mumbai"] }
})
If you want to use in aggregation:
db.emp.aggregate([
{
"$match": {
"type" : { "$in": ["WebUser", "User"] },
"city" : { "$in": ["Pune", "Mumbai"] }
}
},
{ "$group": { "_id": null, "ids": { "$push": "$empId" } } }
])
or simply use the distinct() method to return an array of distinct empIds that match the above query as:
var employeeIds = db.emp.distinct("empId", {
"type" : { "$in": ["WebUser", "User"] },
"city" : { "$in": ["Pune", "Mumbai"] }
});
If you are looking for the AND operator
This example checks if a field exists AND is null
db.getCollection('TheCollection').find({
$and: [
{'the_key': { $exists: true }},
{'the_key': null}
]
})
This example checks if a field has 'value1' OR 'value2'
db.getCollection('TheCollection').find({
$or: [
{'the_key': 'value1'},
{`the_key': 'value2'}
]
})
When just checking for null, the return contains non-existing fields plus fields with value null
db.getCollection('TheCollection').find({'the_key': null})
You can use mongo db $or operator.
db.emp.find({ $or: [
{ "type": "WebUser", "city": "Pune" },
{ "type": "user", "city": "Mumbai"}
]})
You can pass conditions in the array.
For more reference see mongo docs
Display the document where in the “StudName” has value “Ajay Rathod”.
db.Student.find({name:"ajay rathod"})
{ "_id" : ObjectId("5fdd895cd2d5a20ee8cea0de"), "
Retrieve only Student Name and Grade.
db.Student.find({},{name:1,grade:1,_id:0})
{ "name" : "dhruv", "grade" : "A" }
{ "name" : "jay", "grade" : "B" }
{ "name" : "abhi", "grade" : "C" }
{ "name" : "aayush", "grade" : "A" }
{ "name" : "sukhdev", "grade" : "B" }
{ "name" : "dhruval", "grade" : "B" }
{ "name" : "ajay rathod", "grade" : "D" }
i have the following document in my collection:
"_id" : "12345",
"name" : "test",
"users" : [
{
"name" : "spiderman",
"email" : "spiderman#spiderman.com",
"accepted" : true
},
{
"name" : "superman",
"email" : "superman#superman.com",
"accepted" : true
}
]
I would like to remove the user superman.
This is what i would like my final result to look like:
"_id" : "12345",
"name" : "test",
"users" : [
{
"name" : "spiderman",
"email" : "spiderman#spiderman.com",
"accepted" : true
}
]
Ive tried a few things but nothing worked so far. Any help is appreciated.
Thank you
You can use $pull
db.collection.update(
{ "users.name": "superman" },
{ $pull: { "users": {"name" : "superman"} } },
{ multi: false}
)