Get names of all keys in the collection
https://stackoverflow.com/questions/2298870
-
21-09-2019 - |
italiano
english
français
española
中国
日本の
العربية
Deutsch
한국어
Português
RussianQuestion
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
Solution
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", ...]
OTHER TIPS
With Kristina's answer as inspiration, I created an open source tool called Variety which does exactly this: https://github.com/variety/variety
You can use aggregation with new $objectToArrray in 3.4.4 version to convert all top key & value pair into document arrays followed by $unwind & $group with $addToSet to get distinct keys across entire collection.
$$ROOT for referencing the top level document.
db.things.aggregate([
{"$project":{"arrayofkeyvalue":{"$objectToArray":"$$ROOT"}}},
{"$unwind":"$arrayofkeyvalue"},
{"$group":{"_id":null,"allkeys":{"$addToSet":"$arrayofkeyvalue.k"}}}
])
You can use below query for getting keys in a single document.
db.things.aggregate([
{"$project":{"arrayofkeyvalue":{"$objectToArray":"$$ROOT"}}},
{"$project":{"keys":"$arrayofkeyvalue.k"}}
])
Try this:
doc=db.thinks.findOne();
for (key in doc) print(key);
If your target collection is not too large, you can try this under mongo shell client:
var allKeys = {};
db.YOURCOLLECTION.find().forEach(function(doc){Object.keys(doc).forEach(function(key){allKeys[key]=1})});
allKeys;
Using python. Returns the set of all top-level keys in the collection:
#Using pymongo and connection named 'db'
reduce(
lambda all_keys, rec_keys: all_keys | set(rec_keys),
map(lambda d: d.keys(), db.things.find()),
set()
)
Here is the sample worked in Python: This sample returns the results inline.
from pymongo import MongoClient
from bson.code import Code
mapper = Code("""
function() {
for (var key in this) { emit(key, null); }
}
""")
reducer = Code("""
function(key, stuff) { return null; }
""")
distinctThingFields = db.things.map_reduce(mapper, reducer
, out = {'inline' : 1}
, full_response = True)
## do something with distinctThingFields['results']
A cleaned up and reusable solution using pymongo:
from pymongo import MongoClient
from bson import Code
def get_keys(db, collection):
client = MongoClient()
db = client[db]
map = Code("function() { for (var key in this) { emit(key, null); } }")
reduce = Code("function(key, stuff) { return null; }")
result = db[collection].map_reduce(map, reduce, "myresults")
return result.distinct('_id')
Usage:
get_keys('dbname', 'collection')
>> ['key1', 'key2', ... ]
If you are using mongodb 3.4.4 and above then you can use below aggregation using $objectToArray and $group aggregation
db.collection.aggregate([
{ "$project": {
"data": { "$objectToArray": "$$ROOT" }
}},
{ "$project": { "data": "$data.k" }},
{ "$unwind": "$data" },
{ "$group": {
"_id": null,
"keys": { "$addToSet": "$data" }
}}
])
Here is the working example
This works fine for me:
var arrayOfFieldNames = [];
var items = db.NAMECOLLECTION.find();
while(items.hasNext()) {
var item = items.next();
for(var index in item) {
arrayOfFieldNames[index] = index;
}
}
for (var index in arrayOfFieldNames) {
print(index);
}
I am surprise, no one here has ans by using simple javascript and Set logic to automatically filter the duplicates values, simple example on mongo shellas below:
var allKeys = new Set()
db.collectionName.find().forEach( function (o) {for (key in o ) allKeys.add(key)})
for(let key of allKeys) print(key)
This will print all possible unique keys in the collection name: collectionName.
To get a list of all the keys minus _id, consider running the following aggregate pipeline:
var keys = db.collection.aggregate([
{ "$project": {
"hashmaps": { "$objectToArray": "$$ROOT" }
} },
{ "$project": {
"fields": "$hashmaps.k"
} },
{ "$group": {
"_id": null,
"fields": { "$addToSet": "$fields" }
} },
{ "$project": {
"keys": {
"$setDifference": [
{
"$reduce": {
"input": "$fields",
"initialValue": [],
"in": { "$setUnion" : ["$$value", "$$this"] }
}
},
["_id"]
]
}
}
}
]).toArray()[0]["keys"];
I think the best way do this as mentioned here is in mongod 3.4.4+ but without using the $unwind operator and using only two stages in the pipeline. Instead we can use the $mergeObjects and $objectToArray operators.
In the $group stage, we use the $mergeObjects operator to return a single document where key/value are from all documents in the collection.
Then comes the $project where we use $map and $objectToArray to return the keys.
let allTopLevelKeys = [
{
"$group": {
"_id": null,
"array": {
"$mergeObjects": "$$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.
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;
});
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.
Maybe slightly off-topic, but you can recursively pretty-print all keys/fields of an object:
function _printFields(item, level) {
if ((typeof item) != "object") {
return
}
for (var index in item) {
print(" ".repeat(level * 4) + index)
if ((typeof item[index]) == "object") {
_printFields(item[index], level + 1)
}
}
}
function printFields(item) {
_printFields(item, 0)
}
Useful when all objects in a collection has the same structure.
We can achieve this by Using mongo js file. Add below code in your getCollectionName.js file and run js file in the console of Linux as given below :
mongo --host 192.168.1.135 getCollectionName.js
db_set = connect("192.168.1.135:27017/database_set_name"); // for Local testing
// db_set.auth("username_of_db", "password_of_db"); // if required
db_set.getMongo().setSlaveOk();
var collectionArray = db_set.getCollectionNames();
collectionArray.forEach(function(collectionName){
if ( collectionName == 'system.indexes' || collectionName == 'system.profile' || collectionName == 'system.users' ) {
return;
}
print("\nCollection Name = "+collectionName);
print("All Fields :\n");
var arrayOfFieldNames = [];
var items = db_set[collectionName].find();
// var items = db_set[collectionName].find().sort({'_id':-1}).limit(100); // if you want fast & scan only last 100 records of each collection
while(items.hasNext()) {
var item = items.next();
for(var index in item) {
arrayOfFieldNames[index] = index;
}
}
for (var index in arrayOfFieldNames) {
print(index);
}
});
quit();
Thanks @ackuser
Following the thread from @James Cropcho's answer, I landed on the following which I found to be super easy to use. It is a binary tool, which is exactly what I was looking for: mongoeye.
Using this tool it took about 2 minutes to get my schema exported from command line.
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>
I have 1 simpler work around...
What you can do is while inserting data/document into your main collection "things" you must insert the attributes in 1 separate collection lets say "things_attributes".
so every time you insert in "things", you do get from "things_attributes" compare values of that document with your new document keys if any new key present append it in that document and again re-insert it.
So things_attributes will have only 1 document of unique keys which you can easily get when ever you require by using findOne()
