I am new to MongoDB. I was wondering how MongoDB implements "variable Interpolation" ?
I have following code
for (i=0;i<3;i++){
db.test2.insert({i:i+1});
}
Which insert
{ "_id" : ObjectId("564a1bd0987fe676b9cad025"), "i" : 1 }
{ "_id" : ObjectId("564a1bd0987fe676b9cad026"), "i" : 2 }
{ "_id" : ObjectId("564a1bd0987fe676b9cad027"), "i" : 3 }
But I want
{ "_id" : ObjectId("564a1bd0987fe676b9cad025"), "0" : 1 }
{ "_id" : ObjectId("564a1bd0987fe676b9cad026"), "1" : 2 }
{ "_id" : ObjectId("564a1bd0987fe676b9cad027"), "2" : 3 }
Mongo does not changes value in key part. How to fit it?
You will need to build your query dynamically.
var documents = [];
for(var i=0; i<3; i++) {
var doc = {};
doc[i] = i;
documents.push(doc);
}
db.collection.insert(documents)
Then db.collection.find() yields:
{ "_id" : ObjectId("564a2296c68c7068c12fb206"), "0" : 0 }
{ "_id" : ObjectId("564a2296c68c7068c12fb207"), "1" : 1 }
{ "_id" : ObjectId("564a2296c68c7068c12fb208"), "2" : 2 }
Note that it's not a good practice to have string of integer as field's name
Related
Hi I have a collection that has a complex structure, and the documents in this structures are different in the structure. I want to update all the keys V to have value 0 in this collection.
Example:
{
"_id" : ObjectId("5805dfa519f972b200ea2955"),
"s" : {
"id" : NumberLong(36435)
},
"a" : [
{
"XX-(random value)" : {
"V" : 4
},
"V" : 4,
"u" : {
"YY-(random value)" : {
"V" : 4,
"ZZ-(random value)" : {
"V" : 4,
"WW-(random value)" : {
"V" : 4
}
}
}
}
}
]
}
You can do this with a short javascript. You need to iterate through each property of each document, checking the name of the property. If it matches the name "V" then update it with the value 0. This can be done recursively using a loop. The following javascript code should do the needful:
function checkProperties(doc) {
for (var propertyName in doc) {
if (typeof doc[propertyName] == "object") {
checkProperties(doc[propertyName]);
} else {
if (propertyName == "V") {
doc[propertyName] = 0;
print(doc[propertyName]);
}
}
}
}
db.<your_collection_name>.find({}).forEach(function(doc) {
checkProperties(doc);
db.<your_collection_name>.save(doc);
});
If you save this code in a .js file you can then run it against your mongo database:
> mongo --host <host> --port <port> <script_name>.js
We have a basic enquiry management tool that we're using to track some website enquiries in our administration suite, and we're using the ObjectId of each document in our enquiries collection to sort the enquiries by the date they were added.
{
"_id" : ObjectId("53a007db144ff47be1000003"),
"comments" : "This is a test enquiry. Please ignore. We'll delete it shortly.",
"customer" : {
"name" : "Test Enquiry",
"email" : "test#test.com",
"telephone" : "07890123456",
"mobile" : "07890123456",
"quote" : false,
"valuation" : false
},
"site" : [],
"test" : true,
"updates" : [
{
"_id" : ObjectId("53a007db144ff47be1000001"),
"status" : "New",
"status_id" : ObjectId("537de7c3a5e6e668ffc2335c"),
"status_index" : 100,
"substatus" : "New Web Enquiry",
"substatus_id" : ObjectId("5396bb9fa5e6e668ffc23388"),
"notes" : "New enquiry received from website.",
},
{
"_id" : ObjectId("53a80c977d299cfe91bacf81"),
"status" : "New",
"status_id" : ObjectId("537de7c3a5e6e668ffc2335c"),
"status_index" : 100,
"substatus" : "Attempted Contact",
"substatus_id" : ObjectId("53a80e06a5e6e668ffc2339e"),
"notes" : "In this test, we pretend that we've not managed to get hold of the customer on the first attempt.",
},
{
"_id" : ObjectId("53a80e539b966b8da5c40c36"),
"status" : "Approved",
"status_id" : ObjectId("52e77a49d85e95f00ebf6c72"),
"status_index" : 200,
"substatus" : "Enquiry Confirmed",
"substatus_id" : ObjectId("53901f1ba5e6e668ffc23372"),
"notes" : "In this test, we pretend that we've got hold of the customer after failing to contact them on the first attempt.",
}
]
}
Within each enquiry is an updates array of objects which also have an ObjectId as their main identity field. We're using an $unwind and $group aggregation to pull the first and latest updates, as well as the count of updates, making sure we only take enquiries where there have been more than one update (as one is automatically inserted when the enquiry is made):
db.enquiries.aggregate([
{
$match: {
"test": true
}
},
{
$unwind: "$updates"
},
{
$group: {
"_id": "$_id",
"latest_update_id": {
$last: "$updates._id"
},
"first_update_id": {
$first: "$updates._id"
},
"update_count": {
$sum: 1
}
}
},
{
$match: {
"update_count": {
$gt: 1
}
}
}
])
This results in the following output:
{
"result" : [
{
"_id" : ObjectId("53a295ad122ea80200000005"),
"latest_update_id" : ObjectId("53a80bdc7d299cfe91bacf7e"),
"first_update_id" : ObjectId("53a295ad122ea80200000003"),
"update_count" : 2
},
{
"_id" : ObjectId("53a007db144ff47be1000003"),
"latest_update_id" : ObjectId("53a80e539b966b8da5c40c36"),
"first_update_id" : ObjectId("53a007db144ff47be1000001"),
"update_count" : 3
}
],
"ok" : 1
}
This is then passed through to our code (node.js, in this case) where we perform a few operations on it and then present some information on our dashboard.
Ideally, I'd like to add another $group pipeline aggregation to the query which would subtract the timestamp of first_update_id from the timestamp of latest_update_id to give us a timespan, which we could then use $avg on.
Can anyone tell me if this is possible? (Thank you!)
As Neil already pointed out, you can't get to the timestamp from the ObjectId in the aggregation framework.
You said that speed is not important, so using MapReduce you can get what you want:
var map = function() {
if (this.updates.length > 1) {
var first = this.updates[0];
var last = this.updates[this.updates.length - 1];
var diff = last._id.getTimestamp() - first._id.getTimestamp();
var val = {
latest_update_id : last._id,
first_update_id : first._id,
update_count : this.updates.length,
diff: diff
}
emit(this._id, val);
}
};
var reduce = function() { };
db.runCommand(
{
mapReduce: "enquiries",
map: map,
reduce: reduce,
out: "mrresults",
query: { test : true}
}
);
This are the results:
{
"_id" : ObjectId("53a007db144ff47be1000003"),
"value" : {
"latest_update_id" : ObjectId("53a80e539b966b8da5c40c36"),
"first_update_id" : ObjectId("53a007db144ff47be1000001"),
"update_count" : 3,
"diff" : 525944000
}
}
Edit:
If you want to get the average diff for all documents you can do it like this:
var map = function() {
if (this.updates.length > 1) {
var first = this.updates[0];
var last = this.updates[this.updates.length - 1];
var diff = last._id.getTimestamp() - first._id.getTimestamp();
emit("1", {diff : diff});
}
};
var reduce = function(key, values) {
var reducedVal = { count: 0, sum: 0 };
for (var idx = 0; idx < values.length; idx++) {
reducedVal.count += 1;
reducedVal.sum += values[idx].diff;
}
return reducedVal;
};
var finalize = function (key, reducedVal) {
reducedVal.avg = reducedVal.sum/reducedVal.count;
return reducedVal;
};
db.runCommand(
{
mapReduce: "y",
map: map,
reduce: reduce,
finalize : finalize,
out: "mrtest",
query: { test : true}
}
);
And the example output:
> db.mrtest.find().pretty()
{
"_id" : "1",
"value" : {
"count" : 2,
"sum" : 1051888000,
"avg" : 525944000
}
}
I am trying to find in a collection all of the documents that have the given key equal to one of the strings in an array.
Heres an example of the collection.
{
roomId = 'room1',
name = 'first'
},
{
roomId = 'room2',
name = 'second'
},
{
roomId = 'room3',
name = 'third'
}
And heres an example of the array to look through.
[ 'room2', 'room3' ]
What i thought would work is...
collection.find({ roomId : { $in : [ 'room2', 'room3' ]}}, function( e, r )
{
// r should return the second and third room
});
How can i achieve this?
One way this could be solve would be to do a for loop...
var roomIds = [ 'room2', 'room3' ];
for ( var i=0; i < roomIds.length; i++ )
{
collection.find({ id : roomIds[ i ]})
}
But this is not ideal....
What you posted should work - no looping required. The $in operator does the job:
> db.Room.insert({ "_id" : 1, name: 'first'});
> db.Room.insert({ "_id" : 2, name: 'second'});
> db.Room.insert({ "_id" : 3, name: 'third'});
> // test w/ int
> db.Room.find({ "_id" : { $in : [1, 2] }});
{ "_id" : 1, "name" : "first" }
{ "_id" : 2, "name" : "second" }
> // test w/ strings
> db.Room.find({ "name" : { $in : ['first', 'third'] }});
{ "_id" : 1, "name" : "first" }
{ "_id" : 3, "name" : "third" }
Isn't that what you expect?
Tested w/ MongoDB 2.1.1
I am trying to run a map/reduce function in mongodb where I group by 3 different fields contained in objects in my collection. I can get the map/reduce function to run, but all the emitted fields run together in the output collection. I'm not sure this is normal or not, but outputting the data for analysis takes more work to clean up. Is there a way to separate them, then use mongoexport?
Let me show you what I mean:
The fields I am trying to group by are the day, user ID (or uid) and destination.
I run these functions:
map = function() {
day = (this.created_at.getFullYear() + "-" + (this.created_at.getMonth()+1) + "-" + this.created_at.getDate());
emit({day: day, uid: this.uid, destination: this.destination}, {count:1});
}
/* Reduce Function */
reduce = function(key, values) {
var count = 0;
values.forEach(function(v) {
count += v['count'];
}
);
return {count: count};
}
/* Output Function */
db.events.mapReduce(map, reduce, {query: {destination: {$ne:null}}, out: "TMP"});
The output looks like this:
{ "_id" : { "day" : "2012-4-9", "uid" : "1234456", "destination" : "Home" }, "value" : { "count" : 1 } }
{ "_id" : { "day" : "2012-4-9", "uid" : "2345678", "destination" : "Home" }, "value" : { "count" : 1 } }
{ "_id" : { "day" : "2012-4-9", "uid" : "3456789", "destination" : "Login" }, "value" : { "count" : 1 } }
{ "_id" : { "day" : "2012-4-9", "uid" : "4567890", "destination" : "Contact" }, "value" : { "count" : 1 } }
{ "_id" : { "day" : "2012-4-9", "uid" : "5678901", "destination" : "Help" }, "value" : { "count" : 1 } }
When I attempt to use mongoexport, I can not separate day, uid, or destination by columns because the map combines the fields together.
What I would like to have would look like this:
{ { "day" : "2012-4-9" }, { "uid" : "1234456" }, { "destination" : "Home"}, { "count" : 1 } }
Is this even possible?
As an aside - I was able to make the output work by applying sed to the file and cleaning up the CSV. More work, but it worked. It would be ideal if I could get it out of mongodb in the correct format.
MapReduce only returns documents of the form {_id:some_id, value:some_value}
see: How to change the structure of MongoDB's map-reduce results?
In MySQL
select a,b,count(1) as cnt from list group by a, b having cnt > 2;
I have to execute the group by function using having condition in mongodb.
But i am getting following error. Please share your input.
In MongoDB
> res = db.list.group({key:{a:true,b:true},
... reduce: function(obj,prev) {prev.count++;},
... initial: {count:0}}).limit(10);
Sat Jan 7 16:36:30 uncaught exception: group command failed: {
"errmsg" : "exception: group() can't handle more than 20000 unique keys",
"code" : 10043,
"ok" : 0
Once it will be executed, we need to run the following file on next.
for (i in res) {if (res[i].count>2) printjson(res[i])};
Regards,
Kumaran
MongoDB group by is very limited in most cases, for instance
- the result set must be lesser than 10000 keys.
- it will not work in sharded environments
So its better to use map reduce. so the query would be like this
map = function() { emit({a:true,b:true},{count:1}); }
reduce = function(k, values) {
var result = {count: 0};
values.forEach(function(value) {
result.count += value.count;
});
return result;
}
and then
db.list.mapReduce(map,reduce,{out: { inline : 1}})
Its a untested version. let me know if it works
EDIT:
The earlier map function was faulty. Thats why you are not getting the results. it should have been
map = function () {
emit({a:this.a, b:this.b}, {count:1});
}
Test data:
> db.multi_group.insert({a:1,b:2})
> db.multi_group.insert({a:2,b:2})
> db.multi_group.insert({a:3,b:2})
> db.multi_group.insert({a:1,b:2})
> db.multi_group.insert({a:3,b:2})
> db.multi_group.insert({a:7,b:2})
> db.multi_group.mapReduce(map,reduce,{out: { inline : 1}})
{
"results" : [
{
"_id" : {
"a" : 1,
"b" : 2
},
"value" : {
"count" : 2
}
},
{
"_id" : {
"a" : 2,
"b" : 2
},
"value" : {
"count" : 1
}
},
{
"_id" : {
"a" : 3,
"b" : 2
},
"value" : {
"count" : 2
}
},
{
"_id" : {
"a" : 7,
"b" : 2
},
"value" : {
"count" : 1
}
}
],
"timeMillis" : 1,
"counts" : {
"input" : 6,
"emit" : 6,
"reduce" : 2,
"output" : 4
},
"ok" : 1,
}
EDIT2:
Complete solution including applying having count >= 2
map = function () {
emit({a:this.a, b:this.b}, {count:1,_id:this._id});
}
reduce = function(k, values) {
var result = {count: 0,_id:[]};
values.forEach(function(value) {
result.count += value.count;
result._id.push(value._id);
});
return result;
}
>db.multi_group.mapReduce(map,reduce,{out: { replace : "multi_result"}})
> db.multi_result.find({'value.count' : {$gte : 2}})
{ "_id" : { "a" : 1, "b" : 2 }, "value" : { "_id" : [ ObjectId("4f0adf2884025491024f994c"), ObjectId("4f0adf3284025491024f994f") ], "count" : 2 } }
{ "_id" : { "a" : 3, "b" : 2 }, "value" : { "_id" : [ ObjectId("4f0adf3084025491024f994e"), ObjectId("4f0adf3584025491024f9950") ], "count" : 2 } }
You should use MapReduce instead. Group has its limitations.
In future you'll be able to use the Aggregation Framework. But for now, use map/reduce.
Depends on the number of your groups, you might find a simpler and faster solution than group or MapReduce by using distinct:
var res = [];
for( var cur_a = db.list.distinct('a'); cur_a.hasNext(); ) {
var a = cur_a.next();
for( var cur_b = db.list.distinct('b'); cur_b.hasNext(); ) {
var b = cur_b.next();
var cnt = db.list.count({'a':a,'b':b})
if (cnt > 2)
res.push({ 'a': a, 'b' : b 'cnt': cnt}
}
}
It will be faster if you have indexes on a and b
db.list.ensureIndex({'a':1,'b':1})