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
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
我认为这里提到的最好的方法是在mongod 3.4.4+中,但不使用$unwind操作符,只使用管道中的两个阶段。相反,我们可以使用$mergeObjects和$objectToArray操作符。
在$group阶段,我们使用$mergeObjects操作符返回一个文档,其中键/值来自集合中的所有文档。
然后是$project,我们使用$map和$objectToArray返回键。
let allTopLevelKeys = [
{
"$group": {
"_id": null,
"array": {
"$mergeObjects": "$$ROOT"
}
}
},
{
"$project": {
"keys": {
"$map": {
"input": { "$objectToArray": "$array" },
"in": "$$this.k"
}
}
}
}
];
现在,如果我们有一个嵌套的文档,想要获得键,这是可行的。为了简单起见,让我们考虑一个包含简单嵌入式文档的文档,它看起来像这样:
{field1: {field2: "abc"}, field3: "def"}
{field1: {field3: "abc"}, field4: "def"}
下面的管道会生成所有的键(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"
}
}
]
}
}
}
]
只需稍加努力,我们就可以获得数组字段中所有子文档的键,其中元素也是object。
其他回答
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)
我们可以通过使用mongo js文件来实现这一点。在getCollectionName.js文件中添加以下代码,并在Linux控制台中运行js文件,如下所示:
mongodb——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();
由于@ackuser
我知道我来晚了,但如果你想在python中快速找到所有键(甚至嵌套的键),你可以用递归函数来做:
def get_keys(dl, keys=None):
keys = keys or []
if isinstance(dl, dict):
keys += dl.keys()
list(map(lambda x: get_keys(x, keys), dl.values()))
elif isinstance(dl, list):
list(map(lambda x: get_keys(x, keys), dl))
return list(set(keys))
像这样使用它:
dl = db.things.find_one({})
get_keys(dl)
如果你的文件没有相同的密钥,你可以这样做:
dl = db.things.find({})
list(set(list(map(get_keys, dl))[0]))
但是这个解决方案肯定是可以优化的。
一般来说,这个解决方案基本上是解决在嵌套字典中查找键,所以这不是mongodb特定的。
使用python。返回集合中所有顶级键的集合:
#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()
)
我知道这个问题已经10年了,但是c#没有解决方案,我花了好几个小时才弄清楚。我正在使用。net驱动程序和系统。Linq返回键的列表。
var map = new BsonJavaScript("function() { for (var key in this) { emit(key, null); } }");
var reduce = new BsonJavaScript("function(key, stuff) { return null; }");
var options = new MapReduceOptions<BsonDocument, BsonDocument>();
var result = await collection.MapReduceAsync(map, reduce, options);
var list = result.ToEnumerable().Select(item => item["_id"].ToString());