This question already has answers here:
Find in Double Nested Array MongoDB
(2 answers)
Closed 5 years ago.
My document contains nearly seven levels of the document in MongoDB, now I need to write a query to check all conditions like, subject=java, topic=oops, level=l1, complexity=easy, questionType=mcq based on this requirement display all questions in the collection.
Any one please help me out, Thanks in advance.
{
"_id" : ObjectId("59f71b4d0bec333e1707a8d3"),
"_class" : "com.wipro.domain.QuestionBank",
"subjectLists" : [
{
"subject" : "java",
"topicList" : [
{
"topic" : "oops",
"levelList" : [
{
"level" : "l1",
"complexityList" : [
{
"complexity" : "easy",
"questionTypeList" : [
{
"questionType" : "mcq",
"questionList" : [
{
"_id" : "2",
"question" : "2st question",
"options" : [
{
"a" : "1",
"b" : "2",
"c" : "3",
"d" : "4"
}
],
"correctAnswer" : "b",
"marksAlloted" : "1"
}
]
}
]
}
]
}
]
}
]
}
]
}
{
"_id" : ObjectId("59f71b700bec333e1707a8d4"),
"_class" : "com.wipro.domain.QuestionBank",
"subjectLists" : [
{
"subject" : "java",
"topicList" : [
{
"topic" : "threds",
"levelList" : [
{
"level" : "l3",
"complexityList" : [
{
"complexity" : "hard",
"questionTypeList" : [
{
"questionType" : "mcq",
"questionList" : [
{
"_id" : "3",
"question" : "3rd question",
"options" : [
{
"a" : "1",
"b" : "2",
"c" : "3",
"d" : "4"
}
],
"correctAnswer" : "b",
"marksAlloted" : "1"
}
]
}
]
}
]
}
]
}
]
}
]
}
You can try this script.
db.getCollection('document').aggregate([
{
$match:{
$and: [
{"subjectLists.subject": "java"}
,{"subjectLists.topicList.topic": "oops"}
,{"subjectLists.topicList.levelList.level": "l1"}
,{"subjectLists.topicList.levelList.complexityList.complexity": "easy"}
,{"subjectLists.topicList.levelList.complexityList.questionTypeList.questionType": "mcq"}
]
}
},
{
$unwind: "$subjectLists"
}
,{
$unwind: "$subjectLists.topicList"
}
,{
$unwind: "$subjectLists.topicList.levelList"
}
,{
$unwind: "$subjectLists.topicList.levelList.complexityList"
}
,{
$unwind: "$subjectLists.topicList.levelList.complexityList.questionTypeList"
}
,{
$unwind: "$subjectLists.topicList.levelList.complexityList.questionTypeList.questionList"
},
{
$project: {
"questionList": "$subjectLists.topicList.levelList.complexityList.questionTypeList.questionList"
}
}
,
{
$replaceRoot: { newRoot: "$questionList" }
}
])
Result:
{
"_id" : "2",
"question" : "2st question",
"options" : [
{
"a" : "1",
"b" : "2",
"c" : "3",
"d" : "4"
}
],
"correctAnswer" : "b",
"marksAlloted" : "1"
}
Note: $replaceRoot came with version 3.4 of mongo.
Following query with projection lists only questions:
Note: Pass your query below:
db.questions.findOne({}, {'subjectLists.topicList.levelList.complexityList.questionTypeList.questionList':1})
Related
Lets say I have this kind of collection
{
"_id" :"A",
"title" : "TITLE1",
"brand" : [
{
"brand_id" : "B",
"varients" : [
{
"name" : "RED ",
"price" : 5.0
}
]
},
{
"brand_id" : "C",
"varients" : [
{
"name" : "GREEN",
"price" : 5.0
}
]
},
{
"brand_id" : "D",
"varients" : [
{
"name" : "Others",
"price" : 0.0
}
]
}
],
}
I then want to select one and ONLY the nested data of variants. Have tried with the following statement without any success.
db.testing.findOne( {_id: "A", "brand.brand_id" : 'D'} )
Expected output
"varients" : [
{
"name" : "Others",
"price" : 0.0
}
]
Using findOne you can't get the subset or nest content of the document in the response, but yes using aggregation you can get it in a way you want it
Check out this aggregation pipeline:
[
{
'$match': {
'_id': 'A'
}
}, {
'$unwind': {
'path': '$brand'
}
}, {
'$match': {
'brand.brand_id': 'D'
}
}, {
'$project': {
'varients': '$brand.varients',
'_id': 0
}
}
]
I am struggling around with the aggregation pipeline feature from MongoDB.
So far the output for one result looks like this:
{
"type": "inbound",
"sender": "postAG",
"receiver": "maxMusterMan",
"datetime": "20191125",
"info": [
{
"q": "A",
"value": "5",
"name": null,
"plz": 1234
},
{
"q": "B",
"value": "AS",
"name": "ABS",
"plz": null
},
{
"q": "A",
"value": "5",
"name": "aa",
"plz": null
},
... more objects
]
}
The final result should look like:
{
"type": "inbound",
"sender": "postAG",
"receiver": "maxMusterMan",
"datetime": "20191125",
"info": [
{
"q": "A",
"value": "0",
"name": "aa",
"plz": 1234
},
{
"q": "B",
"value": "AS",
"name": "ABS"
}
]
}
So in a nutshell, I want to group the values from the array field info by the "q" field and merge the objects (newer one overwrites the old value).
Further I would like to remove all the values with value "" or null;
There are more fields in the real payload, so I would like to avoid to add a $cond for each field of the object.
Some approaches so far from my side:
for the cleanup, use a UDF, but this is not possible in the pipeline.
use map-reduce for the group and merge, not available in the pipeline.
Please consider that the input file is the output from the several pipeline steps.
So I can not just use map-reduce alone, first I need the pipeline too.
My idea was to create two views, first will do the pipeline stuff and second map-reduce, is this a good solution?
Thx
Andreas
I didn't really understand from your explanation if you can or cannot use map-reduce.
However assuming you can't and you have to 'concat' the pipelines there is no 'generic' workaround for multiple fields - you have to create a condition for each in the pipeline.
With that said here is a working pipeline:
db.collection.aggregate(
[
{
"$unwind" : "$info"
},
{
"$group" : {
"_id" : "$info.q",
"type" : {
"$first" : "$type"
},
"sender" : {
"$first" : "$sender"
},
"receiver" : {
"$first" : "$receiver"
},
"datetime" : {
"$first" : "$datetime"
},
"values" : {
"$push" : "$info.value"
},
"names" : {
"$push" : "$info.name"
},
"plz" : {
"$push" : "$info.plz"
}
}
},
{
"$project" : {
"_id" : 1.0,
"type" : 1.0,
"sender" : 1.0,
"receiver" : 1.0,
"datetime" : 1.0,
"values" : {
"$filter" : {
"input" : "$values",
"as" : "curr",
"cond" : {
"$or" : [
{
"$ne" : [
"$$curr",
null
]
},
{
"$ne" : [
"$$curr",
""
]
}
]
}
}
},
"names" : {
"$filter" : {
"input" : "$names",
"as" : "curr",
"cond" : {
"$or" : [
{
"$ne" : [
"$$curr",
null
]
},
{
"$ne" : [
"$$curr",
""
]
}
]
}
}
},
"plz" : {
"$filter" : {
"input" : "$plz",
"as" : "curr",
"cond" : {
"$or" : [
{
"$ne" : [
"$$curr",
null
]
},
{
"$ne" : [
"$$curr",
""
]
}
]
}
}
}
}
},
{
"$project" : {
"sender" : 1.0,
"receiver" : 1.0,
"datetime" : 1.0,
"type" : 1.0,
"_id" : 1.0,
"value" : {
"$cond" : {
"if" : {
"$gt" : [
{
"$size" : "$values"
},
0.0
]
},
"then" : {
"$arrayElemAt" : [
"$values",
-1.0
]
},
"else" : null
}
},
"name" : {
"$cond" : {
"if" : {
"$gt" : [
{
"$size" : "$names"
},
0.0
]
},
"then" : {
"$arrayElemAt" : [
"$names",
-1.0
]
},
"else" : null
}
},
"plz" : {
"$cond" : {
"if" : {
"$gt" : [
{
"$size" : "$plz"
},
0.0
]
},
"then" : {
"$arrayElemAt" : [
"$plz",
-1.0
]
},
"else" : null
}
}
}
},
{
"$addFields" : {
"infoArray" : [
{
"k" : "type",
"v" : "$_id"
},
{
"k" : "value",
"v" : "$value"
},
{
"k" : "name",
"v" : "$name"
},
{
"k" : "plz",
"v" : "$plz"
}
]
}
},
{
"$addFields" : {
"info" : {
"$arrayToObject" : {
"$filter" : {
"input" : "$infoArray",
"as" : "curr",
"cond" : {
"$ne" : [
"$$curr.v",
null
]
}
}
}
}
}
},
{
"$group" : {
"_id" : null,
"type" : {
"$first" : "$type"
},
"sender" : {
"$first" : "$sender"
},
"receiver" : {
"$first" : "$receiver"
},
"datetime" : {
"$first" : "$datetime"
},
"info" : {
"$push" : "$info"
}
}
}
]
)
I have something like below:
{
"_id" : "1",
"firstArray" : [
{
"_id" : "11",
"secondArray" : [ ]
},
{
"_id" : "12",
"secondArray" : [ ]
},
{
"_id" : "13",
"secondArray" : [ { "type" : "somthing" } ]
}
]
},
{
"_id" : "2",
"firstArray" : [
{
"_id" : "21",
"secondArray" : [ ]
},
{
"_id" : "22",
"secondArray" : [ ]
}
]
}
I need a mongodb query to find documents which ALL of the nested secondArrays are empty? the query should return second document and not the first one.
to solve that, we need to check size of arr2, but to enable that we need first to unwind arr1.
Please find below aggregation framework snippet which solves this problem,
db.pmoubed.aggregate([{
$unwind : "$firstArray"
}, {
$project : {
_id : 1,
firstArray : 1,
isNotEmpty : {
$size : "$firstArray.secondArray"
}
}
}, {
$group : {
_id : "$_id",
isNotEmpty : {
$sum : "$isNotEmpty"
},
firstArray : {
$push : "$firstArray"
}
}
}, {
$match : {
"isNotEmpty" : 0
}
}
])
Any comments welcome
I am trying to use Mongo Aggregation Framework to find out intersection between an array inside my document AND another user defined array.
I don't get a correct result and my guess is its because of the fact that I have array inside of an array.
Here is my data set.
My documents:
{
"_id" : 1,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65f"),
"tags" : [
{
"tagKey" : "owner",
"tagValue" : "john"
},
{
"tagKey" : "ErrorCode",
"tagValue" : "7001"
},
{
"tagKey" : "ErrorDescription",
"tagValue" : "error123"
}
],
"entryTime" : ISODate("2016-04-04T00:26:43.167Z")
}
]
},
/* 1 */
{
"_id" : 2,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65d"),
"tags" : [
{
"tagKey" : "owner",
"tagValue" : "peter"
},
{
"tagKey" : "ErrorCode",
"tagValue" : "6001"
},
{
"tagKey" : "JIRA",
"tagValue" : "Oabc-123"
}
],
"entryTime" : ISODate("2016-04-04T00:26:43.167Z")
}
]
},
/* 2 */
{
"_id" : 3,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65c"),
"tags" : [
{
"tagKey" : "owner",
"tagValue" : "abc"
},
{
"tagKey" : "ErrorCode",
"tagValue" : "6001"
},
{
"tagKey" : "JIRA",
"tagValue" : "abc-123"
}
],
"entryTime" : ISODate("2016-04-04T00:26:43.167Z")
}
]
}
My Query:
db.entrylike.aggregate(
[
{ $project: { "pendingEntries.entryID": 1, "common": { $setIntersection: [ "$pendingEntries.tags", [{ "tagKey" : "ErrorCode", "tagValue" : "7001" }] ] } } }
]
)
Result:
{
"result" : [
{
"_id" : 1,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65f")
}
],
"common" : []
},
{
"_id" : 2,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65d")
}
],
"common" : []
},
{
"_id" : 3,
"pendingEntries" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65c")
}
],
"common" : []
}
],
"ok" : 1
}
I am not expecting first common field to be empty. Can someone let me know what is it that I am doing wrong? Or any work arounds that I can take.
I am using mongodb 3.0.8. I am aware of the fact that Mongodb 3.2 can offer some features which will fulfill my needs but 3.2 upgrade is not in our pipeline soon and I am looking to resolve this using Mongo3.0 if possible.
My goal is to either replace tags array with the common elements from the user defined list or add a new field with common elements. My am trying to to the later in my example.
The reason you the common field is empty is because your "pendingEntries" array and your user defined array have not element in common. What you really want is to return an array that contains the elements that appear in your "tags" array and your user defined array. To do that you can simply use the $map operator and apply the $setIntersection operator to each subdocument "tags" in the "pendingEntries" array.
db.entrylike.aggregate([
{ "$project": {
"common": {
"$map": {
"input": "$pendingEntries",
"as": "p",
"in": {
"entryID": "$$p.entryID",
"tags": {
"$setIntersection": [
"$$p.tags",
{ "$literal": [
{
"tagKey" : "ErrorCode",
"tagValue" : "7001"
}
]}
]
}
}
}
}
}}
])
Which returns:
{
"_id" : 1,
"common" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65f"),
"tags" : [
{
"tagKey" : "ErrorCode",
"tagValue" : "7001"
}
]
}
]
}
{
"_id" : 2,
"common" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65d"),
"tags" : [ ]
}
]
}
{
"_id" : 3,
"common" : [
{
"entryID" : ObjectId("5701b4c3c6b126083332e65c"),
"tags" : [ ]
}
]
}
i have a document like this :
{
"ExtraFields" : [
{
"value" : "print",
"fieldID" : ObjectId("5535627631efa0843554b0ea")
},
{
"value" : "14",
"fieldID" : ObjectId("5535627631efa0843554b0eb")
},
{
"value" : "POLYE",
"fieldID" : ObjectId("5535627631efa0843554b0ec")
},
{
"value" : "30",
"fieldID" : ObjectId("5535627631efa0843554b0ed")
},
{
"value" : "0",
"fieldID" : ObjectId("5535627631efa0843554b0ee")
},
{
"value" : "0",
"fieldID" : ObjectId("5535627731efa0843554b0ef")
},
{
"value" : "0",
"fieldID" : ObjectId("5535627831efa0843554b0f0")
},
{
"value" : "42",
"fieldID" : ObjectId("5535627831efa0843554b0f1")
},
{
"value" : "30",
"fieldID" : ObjectId("5535627831efa0843554b0f2")
},
{
"value" : "14",
"fieldID" : ObjectId("5535627831efa0843554b0f3")
},
{
"value" : "19",
"fieldID" : ObjectId("5535627831efa0843554b0f4")
}
],
"id" : ObjectId("55369e60733e4914550832d0"), "title" : "A product"
}
what i want is to match one or more sets from the ExtraFields array. For example, all the products that contain the values print and 30. Since a value may be found in more than one fieldID (like 0 or true) we need to create a set like
WHERE (fieldID : ObjectId("5535627631efa0843554b0ea"), value : "print")
Where i'm having problems is when querying more than one fields. The pipeline i came up with is :
db.products.aggregate([
{'$unwind': '$ExtraFields'},
{
'$match': {
'$and': [{
'$and': [{'ExtraFields.value': {'$in': ["A52A2A"]}}, {
'ExtraFields.fieldID': ObjectId("5535627631efa0843554b0ea")
}]
}
,
{
'$and': [{'ExtraFields.value': '14'}, {'ExtraFields.fieldID': ObjectId("5535627631efa0843554b0eb")}]
}
]
}
},
]);
This returns zero results, but this is what i want to do in theory. Match all items that contain set 1 AND all that contain set 2.
The end result should look like a faceted search output :
[
{
"_id" : {
"values" : "18",
"fieldID" : ObjectId("5535627831efa0843554b0f3")
},
"count" : 2
},
{
"_id" : {
"values" : "33",
"fieldID" : ObjectId("5535627831efa0843554b0f2")
},
"count" : 1
}
]
Any ideas?
You could try the following aggregation pipeline
db.products.aggregate([
{
"$match": {
"ExtraFields.value": { "$in": ["A52A2A", "14"] },
"ExtraFields.fieldID": {
"$in": [
ObjectId("5535627631efa0843554b0ea"),
ObjectId("5535627631efa0843554b0eb")
]
}
}
},
{
"$unwind": "$ExtraFields"
},
{
"$match": {
"ExtraFields.value": { "$in": ["A52A2A", "14"] },
"ExtraFields.fieldID": {
"$in": [
ObjectId("5535627631efa0843554b0ea"),
ObjectId("5535627631efa0843554b0eb")
]
}
}
},
{
"$group": {
"_id": {
"value": "$ExtraFields.value",
"fieldID": "$ExtraFields.fieldID"
},
"count": {
"$sum": 1
}
}
}
])
With the sample document provided, this gives the output:
/* 1 */
{
"result" : [
{
"_id" : {
"value" : "14",
"fieldID" : ObjectId("5535627631efa0843554b0eb")
},
"count" : 1
}
],
"ok" : 1
}