从 mongo db 集合中删除重复记录

Question

下面是我的收藏，你能告诉我如何编写代码从下面的收藏中删除重复记录，收藏中有重复记录，请解释我如何从收藏中删除重复记录。

   /* 1 */
{
    "_id" : ObjectId("5e84200bdf949c00404ed5ff"),
    "area" : "573",
    "bc" : "GER",
    "bd" : "52001450",
    "bg" : "52001450",
    "borg" : "cde5642",
    "bsg" : "51585929",
    "bsgname" : "INFO TECHNOLOGY",
    "consulting" : null,
    "mobilePhoneNumber" : null,
    "cfax" : null,
    "l" : "BERL",
    "cpgr" : null,
    "o" : "S",
    "friendlyCountryName" : "Germ",
    "ctel" : "+49",
    "mail" : "tl2625@ge.at.com",
    "exch" : "204",
    "ext" : "5408",
    "facsimileTelephoneNumber" : null,
    "givenName" : "POMAS",
    "employeeNumber" : "0249527",
    "jt" : "MC",
    "jtname" : "FLEX FORCE ENGINEER IV",
    "sn" : "LEMP",
  
}

/* 2*/

{
    "_id" : ObjectId("5e84200bdf949c00404ed601"),
    "area" : "573",
    "bc" : "GER",
    "bd" : "52001450",
    "bg" : "52001450",
    "borg" : "cde5642",
    "bsg" : "51585929",
    "bsgname" : "INFO TECHNOLOGY",
    "consulting" : null,
    "mobilePhoneNumber" : null,
    "cfax" : null,
    "l" : "BERL",
    "cpgr" : null,
    "o" : "S",
    "friendlyCountryName" : "Germ",
    "ctel" : "+49",
    "mail" : "tl2625@ge.at.com",
    "exch" : "204",
    "ext" : "5408",
    "facsimileTelephoneNumber" : null,
    "givenName" : "POMAS",
    "employeeNumber" : "0249527",
    "jt" : "MC",
    "jtname" : "FLEX FORCE ENGINEER IV",
    "sn" : "LEMP",

Answer 1

通过下一段代码，您可以找到重复的记录。 （提示：将 ..., 更改为其他字段。）

var cursor = db.collection.aggregate(
[
        {
            "$group": {
                '_id': {
                    "area":"$area",
                    ..., # fill here by other fields
                    "sn": "$sn"
            },
            "count": {
                    "$sum": 1
                }
            },
            "assets":{
                  "$push": {"assets_id":"$_id"}
        },
        {
            "$match": {
                "count": {
                    "$gt": 1
                }
            }

        }, 
    {
            "$project": {
                "assets": "assets"
            }

        }
    }

]
)

然后通过过滤_id删除结果：

cursor.forEach(function (doc){
...     db.collection.remove({"_id": doc.assets[0].assets_id});
... });

现在你只需要用其他字段填写...，例如我填写的area 和sn。