Get names of all keys in the collection

Question

I'd like to get the names of all the keys in a MongoDB collection.

For example, from this:

db.things.insert( { type : ['dog', 'cat'] } );
db.things.insert( { egg : ['cat'] } );
db.things.insert( { type : [] } );
db.things.insert( { hello : []  } );

I'd like to get the unique keys:

type, egg, hello

Answer 1

Using python. Returns the set of all top-level keys in the collection:

#Using pymongo and connection named 'db'

reduce(
    lambda all_keys, rec_keys: all_keys | set(rec_keys), 
    map(lambda d: d.keys(), db.things.find()), 
    set()
)

Answer 2

To get a list of all the keys minus _id, consider running the following aggregate pipeline:

var keys = db.collection.aggregate([
    { "$project": {
       "hashmaps": { "$objectToArray": "$$ROOT" } 
    } }, 
    { "$project": {
       "fields": "$hashmaps.k"
    } },
    { "$group": {
        "_id": null,
        "fields": { "$addToSet": "$fields" }
    } },
    { "$project": {
            "keys": {
                "$setDifference": [
                    {
                        "$reduce": {
                            "input": "$fields",
                            "initialValue": [],
                            "in": { "$setUnion" : ["$$value", "$$this"] }
                        }
                    },
                    ["_id"]
                ]
            }
        }
    }
]).toArray()[0]["keys"];

Answer 3

I think the best way do this as mentioned here is in mongod 3.4.4+ but without using the $unwind operator and using only two stages in the pipeline. Instead we can use the $mergeObjects and $objectToArray operators.

In the $group stage, we use the $mergeObjects operator to return a single document where key/value are from all documents in the collection.

Then comes the $project where we use $map and $objectToArray to return the keys.

let allTopLevelKeys =  [
    {
        "$group": {
            "_id": null,
            "array": {
                "$mergeObjects": "$$ROOT"
            }
        }
    },
    {
        "$project": {
            "keys": {
                "$map": {
                    "input": { "$objectToArray": "$array" },
                    "in": "$$this.k"
                }
            }
        }
    }
];

---

Now if we have a nested documents and want to get the keys as well, this is doable. For simplicity, let consider a document with simple embedded document that look like this:

{field1: {field2: "abc"}, field3: "def"}
{field1: {field3: "abc"}, field4: "def"}

The following pipeline yield all keys (field1, field2, field3, field4).

let allFistSecondLevelKeys = [
    {
        "$group": {
            "_id": null,
            "array": {
                "$mergeObjects": "$$ROOT"
            }
        }
    },
    {
        "$project": {
            "keys": {
                "$setUnion": [
                    {
                        "$map": {
                            "input": {
                                "$reduce": {
                                    "input": {
                                        "$map": {
                                            "input": {
                                                "$objectToArray": "$array"
                                            },
                                            "in": {
                                                "$cond": [
                                                    {
                                                        "$eq": [
                                                            {
                                                                "$type": "$$this.v"
                                                            },
                                                            "object"
                                                        ]
                                                    },
                                                    {
                                                        "$objectToArray": "$$this.v"
                                                    },
                                                    [
                                                        "$$this"
                                                    ]
                                                ]
                                            }
                                        }
                                    },
                                    "initialValue": [

                                    ],
                                    "in": {
                                        "$concatArrays": [
                                            "$$this",
                                            "$$value"
                                        ]
                                    }
                                }
                            },
                            "in": "$$this.k"
                        }
                    }
                ]
            }
        }
    }
]

---

With a little effort, we can get the key for all subdocument in an array field where the elements are object as well.

Answer 4

Here is the sample worked in Python: This sample returns the results inline.

from pymongo import MongoClient
from bson.code import Code

mapper = Code("""
    function() {
                  for (var key in this) { emit(key, null); }
               }
""")
reducer = Code("""
    function(key, stuff) { return null; }
""")

distinctThingFields = db.things.map_reduce(mapper, reducer
    , out = {'inline' : 1}
    , full_response = True)
## do something with distinctThingFields['results']

Answer 5

I was trying to write in nodejs and finally came up with this:

db.collection('collectionName').mapReduce(
function() {
    for (var key in this) {
        emit(key, null);
    }
},
function(key, stuff) {
    return null;
}, {
    "out": "allFieldNames"
},
function(err, results) {
    var fields = db.collection('allFieldNames').distinct('_id');
    fields
        .then(function(data) {
            var finalData = {
                "status": "success",
                "fields": data
            };
            res.send(finalData);
            delteCollection(db, 'allFieldNames');
        })
        .catch(function(err) {
            res.send(err);
            delteCollection(db, 'allFieldNames');
        });
 });

After reading the newly created collection "allFieldNames", delete it.

db.collection("allFieldNames").remove({}, function (err,result) {
     db.close();
     return; 
});

Answer 6

A cleaned up and reusable solution using pymongo:

from pymongo import MongoClient
from bson import Code

def get_keys(db, collection):
    client = MongoClient()
    db = client[db]
    map = Code("function() { for (var key in this) { emit(key, null); } }")
    reduce = Code("function(key, stuff) { return null; }")
    result = db[collection].map_reduce(map, reduce, "myresults")
    return result.distinct('_id')

Usage:

get_keys('dbname', 'collection')
>> ['key1', 'key2', ... ]