How do I forEach on runCommand result - mongodb

I got E QUERY TypeError: Object [object Object] has no method 'forEach'
How could I for each the result ?
cur = db[source_collection].runCommand('aggregate',
pipeline: pipeline
allowDiskUse: true)
cur.forEach (customer) ->
db[output_collection].update({'_id': customer._id},{
'$pull': {
'$records.items': {
$regex: /\s+/
}
}
})

Use the aggregate() helper instead since in 2.6 and later, the aggregate() helper always returns a cursor:
cur = db[source_collection].aggregate pipeline
cur.forEach (customer) ->
db[output_collection].update('_id': customer._id,
'$pull':
'records.$.items':
'$regex': /\s+/
)

As per mongo aggregation runCommand documentation
Using the aggregate command to return a cursor is a low-level operation, intended for authors of drivers.
and
runCommand returns a document that contains results
so you write cur.result.forEach

It is old but even though I will right this:
For the first case I think it will help:
cur.result.forEach(
function(doc)
{
...
...
})
I have more one that can I add more for future questions around it:
db.runCommand(
{ aggregate: "MyCollectionName",
pipeline: [
{ $group :
{
_id : "$GroupColumnName"
,"count": { "$sum": 1 }
, AllDocs: { $push: "$$ROOT" }
}
},
{ "$match": {"_id" :{ "$ne" : null } , "count" : {"$gt": 1} } }
],
allowDiskUse: true
}
).result.forEach(
function(doc)
{
doc.AllDocs.forEach(
function(docInternal)
{
print(docInternal._id);
}
);
})

Related

Query nested doc's field with dot in the name

Consider such a collection:
> db.test.find({})
{ "_id" : ObjectId("5f969419d40c1580f2d4aa31"), "users" : { "foo#bar.com" : "baz" } }
{ "_id" : ObjectId("5f9694d4d40c1580f2d4aa33"), "users" : { "baz#test.com" : "foo" } }
I want to find documents where users contains field foo#bar.com.
Firstly I tried
> db.test.find({"users.foo#bar.com": { $exists: true } })
But it returned nothing. Because of the dot (.) in field's name it was looking for a such a field: users > foo#bar > com which does not exist.
I learned that the dot in key's name can be escaped with \u002e so I tried
> db.test.find({"users.foo#bar\u002ecom": { $exists: true } })
But it also returns nothing. I guess that I am not escaping properly. How should I do this?
You can do it using aggregation. Try this query.
db.test.aggregate([
{
"$project": {
"users": {
"$objectToArray": "$users"
}
}
},
{
"$match": {
"users.k": "foo#bar.com"
}
},
{
"$project": {
"users": {
"$arrayToObject": "$users"
}
}
}
])
Here is Mongo Playground
Try this one:
db.test.find({$expr:{$literal:{"users.foo#bar.com":{$exists:true}}}})
Explanation
$expr allows us to use aggregation operators in MQL
$literal returns "users.foo#bar.com" as a field (no parsing)
$literal does not touch the inner level $exists still works.

Pymongo find() with "$toString" projection operator

I want to query a mongo object getting the _id as a string instead of an ObjectId.
def get_obj():
query = {}
contents = {
'UniqueId' : True,
'Name' : True,
'Address1' : True,
'id' : {
"$toString": "$_id"
}
}
return db.get_db().collection.find(query,contents)
When I run it this way I get this output:
pymongo.errors.OperationFailure: Unsupported projection option: id: { $toString: "$_id" }
I believe that your issue is that your are using an aggregate function ($toString) without doing an aggregation.
There are at least 2 options:
Just use the python str() method.
cursor = list(get_obj())
print([str(doc['_id']) for doc in cursor])
Use aggregation
def get_obj():
contents = [
{'$project': {
'_id': {'$toString': '$_id'},
# other desired fields
}}
]
return db.get_db().collection.aggregate(contents)
result = list(get_obj())
print([doc for doc in result])

Run MongoDB Function for all documents [duplicate]

In MongoDB, is it possible to update the value of a field using the value from another field? The equivalent SQL would be something like:
UPDATE Person SET Name = FirstName + ' ' + LastName
And the MongoDB pseudo-code would be:
db.person.update( {}, { $set : { name : firstName + ' ' + lastName } );
The best way to do this is in version 4.2+ which allows using the aggregation pipeline in the update document and the updateOne, updateMany, or update(deprecated in most if not all languages drivers) collection methods.
MongoDB 4.2+
Version 4.2 also introduced the $set pipeline stage operator, which is an alias for $addFields. I will use $set here as it maps with what we are trying to achieve.
db.collection.<update method>(
{},
[
{"$set": {"name": { "$concat": ["$firstName", " ", "$lastName"]}}}
]
)
Note that square brackets in the second argument to the method specify an aggregation pipeline instead of a plain update document because using a simple document will not work correctly.
MongoDB 3.4+
In 3.4+, you can use $addFields and the $out aggregation pipeline operators.
db.collection.aggregate(
[
{ "$addFields": {
"name": { "$concat": [ "$firstName", " ", "$lastName" ] }
}},
{ "$out": <output collection name> }
]
)
Note that this does not update your collection but instead replaces the existing collection or creates a new one. Also, for update operations that require "typecasting", you will need client-side processing, and depending on the operation, you may need to use the find() method instead of the .aggreate() method.
MongoDB 3.2 and 3.0
The way we do this is by $projecting our documents and using the $concat string aggregation operator to return the concatenated string.
You then iterate the cursor and use the $set update operator to add the new field to your documents using bulk operations for maximum efficiency.
Aggregation query:
var cursor = db.collection.aggregate([
{ "$project": {
"name": { "$concat": [ "$firstName", " ", "$lastName" ] }
}}
])
MongoDB 3.2 or newer
You need to use the bulkWrite method.
var requests = [];
cursor.forEach(document => {
requests.push( {
'updateOne': {
'filter': { '_id': document._id },
'update': { '$set': { 'name': document.name } }
}
});
if (requests.length === 500) {
//Execute per 500 operations and re-init
db.collection.bulkWrite(requests);
requests = [];
}
});
if(requests.length > 0) {
db.collection.bulkWrite(requests);
}
MongoDB 2.6 and 3.0
From this version, you need to use the now deprecated Bulk API and its associated methods.
var bulk = db.collection.initializeUnorderedBulkOp();
var count = 0;
cursor.snapshot().forEach(function(document) {
bulk.find({ '_id': document._id }).updateOne( {
'$set': { 'name': document.name }
});
count++;
if(count%500 === 0) {
// Excecute per 500 operations and re-init
bulk.execute();
bulk = db.collection.initializeUnorderedBulkOp();
}
})
// clean up queues
if(count > 0) {
bulk.execute();
}
MongoDB 2.4
cursor["result"].forEach(function(document) {
db.collection.update(
{ "_id": document._id },
{ "$set": { "name": document.name } }
);
})
You should iterate through. For your specific case:
db.person.find().snapshot().forEach(
function (elem) {
db.person.update(
{
_id: elem._id
},
{
$set: {
name: elem.firstname + ' ' + elem.lastname
}
}
);
}
);
Apparently there is a way to do this efficiently since MongoDB 3.4, see styvane's answer.
Obsolete answer below
You cannot refer to the document itself in an update (yet). You'll need to iterate through the documents and update each document using a function. See this answer for an example, or this one for server-side eval().
For a database with high activity, you may run into issues where your updates affect actively changing records and for this reason I recommend using snapshot()
db.person.find().snapshot().forEach( function (hombre) {
hombre.name = hombre.firstName + ' ' + hombre.lastName;
db.person.save(hombre);
});
http://docs.mongodb.org/manual/reference/method/cursor.snapshot/
Starting Mongo 4.2, db.collection.update() can accept an aggregation pipeline, finally allowing the update/creation of a field based on another field:
// { firstName: "Hello", lastName: "World" }
db.collection.updateMany(
{},
[{ $set: { name: { $concat: [ "$firstName", " ", "$lastName" ] } } }]
)
// { "firstName" : "Hello", "lastName" : "World", "name" : "Hello World" }
The first part {} is the match query, filtering which documents to update (in our case all documents).
The second part [{ $set: { name: { ... } }] is the update aggregation pipeline (note the squared brackets signifying the use of an aggregation pipeline). $set is a new aggregation operator and an alias of $addFields.
Regarding this answer, the snapshot function is deprecated in version 3.6, according to this update. So, on version 3.6 and above, it is possible to perform the operation this way:
db.person.find().forEach(
function (elem) {
db.person.update(
{
_id: elem._id
},
{
$set: {
name: elem.firstname + ' ' + elem.lastname
}
}
);
}
);
I tried the above solution but I found it unsuitable for large amounts of data. I then discovered the stream feature:
MongoClient.connect("...", function(err, db){
var c = db.collection('yourCollection');
var s = c.find({/* your query */}).stream();
s.on('data', function(doc){
c.update({_id: doc._id}, {$set: {name : doc.firstName + ' ' + doc.lastName}}, function(err, result) { /* result == true? */} }
});
s.on('end', function(){
// stream can end before all your updates do if you have a lot
})
})
update() method takes aggregation pipeline as parameter like
db.collection_name.update(
{
// Query
},
[
// Aggregation pipeline
{ "$set": { "id": "$_id" } }
],
{
// Options
"multi": true // false when a single doc has to be updated
}
)
The field can be set or unset with existing values using the aggregation pipeline.
Note: use $ with field name to specify the field which has to be read.
Here's what we came up with for copying one field to another for ~150_000 records. It took about 6 minutes, but is still significantly less resource intensive than it would have been to instantiate and iterate over the same number of ruby objects.
js_query = %({
$or : [
{
'settings.mobile_notifications' : { $exists : false },
'settings.mobile_admin_notifications' : { $exists : false }
}
]
})
js_for_each = %(function(user) {
if (!user.settings.hasOwnProperty('mobile_notifications')) {
user.settings.mobile_notifications = user.settings.email_notifications;
}
if (!user.settings.hasOwnProperty('mobile_admin_notifications')) {
user.settings.mobile_admin_notifications = user.settings.email_admin_notifications;
}
db.users.save(user);
})
js = "db.users.find(#{js_query}).forEach(#{js_for_each});"
Mongoid::Sessions.default.command('$eval' => js)
With MongoDB version 4.2+, updates are more flexible as it allows the use of aggregation pipeline in its update, updateOne and updateMany. You can now transform your documents using the aggregation operators then update without the need to explicity state the $set command (instead we use $replaceRoot: {newRoot: "$$ROOT"})
Here we use the aggregate query to extract the timestamp from MongoDB's ObjectID "_id" field and update the documents (I am not an expert in SQL but I think SQL does not provide any auto generated ObjectID that has timestamp to it, you would have to automatically create that date)
var collection = "person"
agg_query = [
{
"$addFields" : {
"_last_updated" : {
"$toDate" : "$_id"
}
}
},
{
$replaceRoot: {
newRoot: "$$ROOT"
}
}
]
db.getCollection(collection).updateMany({}, agg_query, {upsert: true})
(I would have posted this as a comment, but couldn't)
For anyone who lands here trying to update one field using another in the document with the c# driver...
I could not figure out how to use any of the UpdateXXX methods and their associated overloads since they take an UpdateDefinition as an argument.
// we want to set Prop1 to Prop2
class Foo { public string Prop1 { get; set; } public string Prop2 { get; set;} }
void Test()
{
var update = new UpdateDefinitionBuilder<Foo>();
update.Set(x => x.Prop1, <new value; no way to get a hold of the object that I can find>)
}
As a workaround, I found that you can use the RunCommand method on an IMongoDatabase (https://docs.mongodb.com/manual/reference/command/update/#dbcmd.update).
var command = new BsonDocument
{
{ "update", "CollectionToUpdate" },
{ "updates", new BsonArray
{
new BsonDocument
{
// Any filter; here the check is if Prop1 does not exist
{ "q", new BsonDocument{ ["Prop1"] = new BsonDocument("$exists", false) }},
// set it to the value of Prop2
{ "u", new BsonArray { new BsonDocument { ["$set"] = new BsonDocument("Prop1", "$Prop2") }}},
{ "multi", true }
}
}
}
};
database.RunCommand<BsonDocument>(command);
MongoDB 4.2+ Golang
result, err := collection.UpdateMany(ctx, bson.M{},
mongo.Pipeline{
bson.D{{"$set",
bson.M{"name": bson.M{"$concat": []string{"$lastName", " ", "$firstName"}}}
}},
)

mongodb: $substr inside $group

I am a bit new to mongodb, and I have a situation.
The entries in my mongodb collection is around 300k, I used mongodb aggregate to migrate all the old entries to new and my code looks like
collection.aggregate([
{ $group: {
_id: "$_id",
"new_id" : {$substr : [{$first: "$old_id"}, 2,-1]}, //error exists here
"new_roles": {$push: "$old_role"},
}
},
{ $out: newCollection}
], {allowDiskUse:true}, function (updateError, updateResult) {
if (!updateError) {
return cb(false, true);
} else {
return cb(true, false);
}
})
What I want to achieve it that I want to take substring of old_id and put it in new_id. The old_id of old collection looks like a-112 a-34311. I want to remove a- from these old ids and put it into new id.
I tried using the above code but it shows error that The $substr accumulator is a unary operator. I tried searching for the error but no luck
You can't use $substr in the $group stage as it is not an accumulator operator. You need to do this in a $project stage like this:
collection.aggregate([
{ $group: {
_id: "$_id",
"new_id" : {$first: "$old_id"},
"new_roles": {$push: "$old_role"},
}
},
{$project: {
"new_id": {$substr: ["$new_id", 2, -1]},
"new_roles": 1
}
},
{ $out: newCollection}
], {allowDiskUse:true}, function (updateError, updateResult) {
if (!updateError) {
return cb(false, true);
} else {
return cb(true, false);
}
})

MongoDB concatenate strings from two fields into a third field

How do I concatenate values from two string fields and put it into a third one?
I've tried this:
db.collection.update(
{ "_id": { $exists: true } },
{ $set: { column_2: { $add: ['$column_4', '$column_3'] } } },
false, true
)
which doesn't seem to work though, and throws not ok for storage.
I've also tried this:
db.collection.update(
{ "_id": { $exists : true } },
{ $set: { column_2: { $add: ['a', 'b'] } } },
false, true
)
but even this shows the same error not ok for storage.
I want to concatenate only on the mongo server and not in my application.
You can use aggregation operators $project and $concat:
db.collection.aggregate([
{ $project: { newfield: { $concat: [ "$field1", " - ", "$field2" ] } } }
])
Unfortunately, MongoDB currently does not allow you to reference the existing value of any field when performing an update(). There is an existing Jira ticket to add this functionality: see SERVER-1765 for details.
At present, you must do an initial query in order to determine the existing values, and do the string manipulation in the client. I wish I had a better answer for you.
You could use $set like this in 4.2 which supports aggregation pipeline in update.
db.collection.update(
{"_id" :{"$exists":true}},
[{"$set":{"column_2":{"$concat":["$column_4","$column_3"]}}}]
)
Building on the answer from #rebe100x, as suggested by #Jamby ...
You can use $project, $concat and $out (or $merge) in an aggregation pipeline.
https://docs.mongodb.org/v3.0/reference/operator/aggregation/project/
https://docs.mongodb.org/manual/reference/operator/aggregation/concat/
https://docs.mongodb.com/manual/reference/operator/aggregation/out/
For example:
db.collection.aggregate(
[
{ $project: { newfield: { $concat: [ "$field1", " - ", "$field2" ] } } },
{ $out: "collection" }
]
)
With MongoDB 4.2 . . .
MongoDB 4.2 adds the $merge pipeline stage which offers selective replacement of documents within the collection, while $out would replace the entire collection. You also have the option of merging instead of replacing the target document.
db.collection.aggregate(
[
{ $project: { newfield: { $concat: [ "$field1", " - ", "$field2" ] } } },
{ $merge: { into: "collection", on: "_id", whenMatched: "merge", whenNotMatched: "discard" }
]
)
You should consider the trade-offs between performance, concurrency and consistency, when choosing between $merge and $out, since $out will atomically perform the collection replacement via a temporary collection and renaming.
https://docs.mongodb.com/manual/reference/operator/aggregation/merge/
https://docs.mongodb.com/manual/reference/operator/aggregation/merge/#merge-out-comparison
**
in my case this $concat worked for me ...
**
db.collection.update( { "_id" : {"$exists":true} },
[ {
"$set" : {
"column_2" : { "$concat" : ["$column_4","$column_3"] }
}
}
]
let suppose that you have a collection name is "myData" where you have data like this
{
"_id":"xvradt5gtg",
"first_name":"nizam",
"last_name":"khan",
"address":"H-148, Near Hero Show Room, Shahjahanpur",
}
and you want concatenate fields (first_name+ last_name +address) and save it into "address" field like this
{
"_id":"xvradt5gtg",
"first_name":"nizam",
"last_name":"khan",
"address":"nizam khan,H-148, Near Hero Show Room, Shahjahanpur",
}
now write query will be
{
var x=db.myData.find({_id:"xvradt5gtg"});
x.forEach(function(d)
{
var first_name=d.first_name;
var last_name=d.last_name;
var _add=d.address;
var fullAddress=first_name+","+last_name+","+_add;
//you can print also
print(fullAddress);
//update
db.myData.update({_id:d._id},{$set:{address:fullAddress}});
})
}
You can also follow the below.
db.collectionName.find({}).forEach(function(row) {
row.newField = row.field1 + "-" + row.field2
db.collectionName.save(row);
});
Find and Update Each Using For Loop
Try This:
db.getCollection('users').find({ }).forEach( function(user) {
user.full_name = user.first_name + " " + user.last_name;
db.getCollection('users').save(user);
});
Or Try This:
db.getCollection('users').find({ }).forEach( function(user) {
db.getCollection('users').update(
{ _id: user._id },
{ $set: { "full_name": user.first_name + " " + user.last_name } }
)
});