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

var schematodo = db.[collection].findOne();
for (var key in schematodo) { print (key) ; }

Answer 2

Try this:

doc=db.thinks.findOne();
for (key in doc) print(key);

Answer 3

I extended Carlos LM's solution a bit so it's more detailed.

Example of a schema:

var schema = {
    _id: 123,
    id: 12,
    t: 'title',
    p: 4.5,
    ls: [{
            l: 'lemma',
            p: {
                pp: 8.9
            }
        },
         {
            l: 'lemma2',
            p: {
               pp: 8.3
           }
        }
    ]
};

Type into the console:

var schemafy = function(schema, i, limit) {
    var i = (typeof i !== 'undefined') ? i : 1;
    var limit = (typeof limit !== 'undefined') ? limit : false;
    var type = '';
    var array = false;

    for (key in schema) {
        type = typeof schema[key];
        array = (schema[key] instanceof Array) ? true : false;

        if (type === 'object') {
            print(Array(i).join('    ') + key+' <'+((array) ? 'array' : type)+'>:');
            schemafy(schema[key], i+1, array);
        } else {
            print(Array(i).join('    ') + key+' <'+type+'>');
        }

        if (limit) {
            break;
        }
    }
}

Run:

schemafy(db.collection.findOne());

Output

_id <number>
id <number>
t <string>
p <number>
ls <object>:
    0 <object>:
    l <string>
    p <object>:
        pp <number> 

Answer 4

You could do this with MapReduce:

mr = db.runCommand({
  "mapreduce" : "my_collection",
  "map" : function() {
    for (var key in this) { emit(key, null); }
  },
  "reduce" : function(key, stuff) { return null; }, 
  "out": "my_collection" + "_keys"
})

Then run distinct on the resulting collection so as to find all the keys:

db[mr.result].distinct("_id")
["foo", "bar", "baz", "_id", ...]

Answer 5

If your target collection is not too large, you can try this under mongo shell client:

var allKeys = {};

db.YOURCOLLECTION.find().forEach(function(doc){Object.keys(doc).forEach(function(key){allKeys[key]=1})});

allKeys;

Answer 6

As per the mongoldb documentation, a combination of distinct

Finds the distinct values for a specified field across a single collection or view and returns the results in an array.

and indexes collection operations are what would return all possible values for a given key, or index:

Returns an array that holds a list of documents that identify and describe the existing indexes on the collection

So in a given method one could do use a method like the following one, in order to query a collection for all it's registered indexes, and return, say an object with the indexes for keys (this example uses async/await for NodeJS, but obviously you could use any other asynchronous approach):

async function GetFor(collection, index) {

    let currentIndexes;
    let indexNames = [];
    let final = {};
    let vals = [];

    try {
        currentIndexes = await collection.indexes();
        await ParseIndexes();
        //Check if a specific index was queried, otherwise, iterate for all existing indexes
        if (index && typeof index === "string") return await ParseFor(index, indexNames);
        await ParseDoc(indexNames);
        await Promise.all(vals);
        return final;
    } catch (e) {
        throw e;
    }

    function ParseIndexes() {
        return new Promise(function (result) {
            let err;
            for (let ind in currentIndexes) {
                let index = currentIndexes[ind];
                if (!index) {
                    err = "No Key For Index "+index; break;
                }
                let Name = Object.keys(index.key);
                if (Name.length === 0) {
                    err = "No Name For Index"; break;
                }
                indexNames.push(Name[0]);
            }
            return result(err ? Promise.reject(err) : Promise.resolve());
        })
    }

    async function ParseFor(index, inDoc) {
        if (inDoc.indexOf(index) === -1) throw "No Such Index In Collection";
        try {
            await DistinctFor(index);
            return final;
        } catch (e) {
            throw e
        }
    }
    function ParseDoc(doc) {
        return new Promise(function (result) {
            let err;
            for (let index in doc) {
                let key = doc[index];
                if (!key) {
                    err = "No Key For Index "+index; break;
                }
                vals.push(new Promise(function (pushed) {
                    DistinctFor(key)
                        .then(pushed)
                        .catch(function (err) {
                            return pushed(Promise.resolve());
                        })
                }))
            }
            return result(err ? Promise.reject(err) : Promise.resolve());
        })
    }

    async function DistinctFor(key) {
        if (!key) throw "Key Is Undefined";
        try {
            final[key] = await collection.distinct(key);
        } catch (e) {
            final[key] = 'failed';
            throw e;
        }
    }
}

So querying a collection with the basic _id index, would return the following (test collection only has one document at the time of the test):

Mongo.MongoClient.connect(url, function (err, client) {
    assert.equal(null, err);

    let collection = client.db('my db').collection('the targeted collection');

    GetFor(collection, '_id')
        .then(function () {
            //returns
            // { _id: [ 5ae901e77e322342de1fb701 ] }
        })
        .catch(function (err) {
            //manage your error..
        })
});

Mind you, this uses methods native to the NodeJS Driver. As some other answers have suggested, there are other approaches, such as the aggregate framework. I personally find this approach more flexible, as you can easily create and fine-tune how to return the results. Obviously, this only addresses top-level attributes, not nested ones. Also, to guarantee that all documents are represented should there be secondary indexes (other than the main _id one), those indexes should be set as required.