我想获得MongoDB集合中所有键的名称。

例如,从这个:

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

我想获得唯一的键:

type, egg, hello

当前回答

可能有点偏离主题,但你可以递归地漂亮打印对象的所有键/字段:

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)
}

当集合中的所有对象都具有相同的结构时非常有用。

其他回答

你可以用MapReduce来做:

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"
})

然后在结果集合上单独运行,以便找到所有的键:

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

要获得所有键减去_id的列表,可以考虑运行以下聚合管道:

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

基于@Wolkenarchitekt的回答:https://stackoverflow.com/a/48117846/8808983,我写了一个脚本,可以在db中找到所有键的模式,我认为它可以帮助其他人阅读这个线程:

"""
Python 3
This script get list of patterns and print the collections that contains fields with this patterns.
"""

import argparse

import pymongo
from bson import Code


# initialize mongo connection:
def get_db():
    client = pymongo.MongoClient("172.17.0.2")
    db = client["Data"]
    return db


def get_commandline_options():
    description = "To run use: python db_fields_pattern_finder.py -p <list_of_patterns>"
    parser = argparse.ArgumentParser(description=description)
    parser.add_argument('-p', '--patterns', nargs="+", help='List of patterns to look for in the db.', required=True)
    return parser.parse_args()


def report_matching_fields(relevant_fields_by_collection):
    print("Matches:")

    for collection_name in relevant_fields_by_collection:
        if relevant_fields_by_collection[collection_name]:
            print(f"{collection_name}: {relevant_fields_by_collection[collection_name]}")

    # pprint(relevant_fields_by_collection)


def get_collections_names(db):
    """
    :param pymongo.database.Database db:
    :return list: collections names
    """
    return db.list_collection_names()


def get_keys(db, collection):
    """
    See: https://stackoverflow.com/a/48117846/8808983
    :param db:
    :param collection:
    :return:
    """
    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')


def get_fields(db, collection_names):
    fields_by_collections = {}
    for collection_name in collection_names:
        fields_by_collections[collection_name] = get_keys(db, collection_name)
    return fields_by_collections


def get_matches_fields(fields_by_collections, patterns):
    relevant_fields_by_collection = {}
    for collection_name in fields_by_collections:
        relevant_fields = [field for field in fields_by_collections[collection_name] if
                           [pattern for pattern in patterns if
                            pattern in field]]
        relevant_fields_by_collection[collection_name] = relevant_fields

    return relevant_fields_by_collection


def main(patterns):
    """
    :param list patterns: List of strings to look for in the db.
    """
    db = get_db()

    collection_names = get_collections_names(db)
    fields_by_collections = get_fields(db, collection_names)
    relevant_fields_by_collection = get_matches_fields(fields_by_collections, patterns)

    report_matching_fields(relevant_fields_by_collection)


if __name__ == '__main__':
    args = get_commandline_options()
    main(args.patterns)

我试着用nodejs写,最后想到了这个:

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');
        });
 });

读取新创建的集合“allFieldNames”后,删除它。

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

这对我来说很有效:

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);
}