Mongodb 聚合以获取数组中键值对的总数，并根据类似名称的字段值进行分组

我有如下结构的文档，其中每个数组元素都包含“n”和“v”作为不同类型数据的键和值。我需要按“ipaddress”的“n”值对其进行分组，并计算集合中的全部不同组合。但是，值相似但不相同。（例如：ip、ip地址和ip地址）

查询选择条件如下：

如果“loc”为“NW”且“logtype”为“1”，则“ipaddress”=“ip”

如果“loc”为“NW”且“logtype”为“2”，则“ipaddress”=“ip地址”

如果“loc”为“NW”且“logtype”为“3”，则“ipaddress”=“ipaddress”

港口是“53”

pro是“udp”或“tcp”

按“IP地址”分组

我想要这样的结果

{"ipaddress" : "2.2.2.2" , count : 1}
{"ipaddress" : "1.1.1.1" , count : 2}

这就是我到目前为止所做的：

db.final.aggregate([
    { "$match": {
        "$and": [
            {"props" : {"$elemMatch": { "n": "port", "v": "53" }}},
            {"props" : {"$elemMatch": { "n": "pro", "v": {"$in" : [/udp/, /tcp/]} }}}
        ]
    }},
    { "$unwind": "$props" },
        {
        "$project": {
            "_ipaddress": {
                "$cond": {
                    "if": { "$eq": [ "$props.n", "ip" ] },
                    "then": "$props.v",
                    "else": {
                        "$cond": {
                            "if": { "$eq": [ "$props.n", "ip_addr" ] },
                            "then": "$props.v",
                            "else": {
                                "$cond" : {
                                    "if": { "$eq": [ "$props.n", "ipaddr" ] },
                                    "then": "$props.v",
                                    "else" : 0
                                }
                            }
                        }
                    }
                }
            },
            "_id": 1,
            "props" : 1
        }
    },
    { "$group": {
        "_id": "$_id",
        "_ipaddress": {
            "$min": {
                "$cond": [ { "$ne": [ "$_ipaddress", 0 ] }, "$_ipaddress", false ]
            }
        },
        "pro": {
            "$min": {
                "$cond": [ { "$eq": [ "$props.n", "pro" ] }, "$props.v", false ]
            }
        },
        "logtype": {
            "$min": {
                "$cond": [ { "$eq": [ "$props.n", "logtype" ] }, "$props.v", false ]
            }
        },
        "port": {
            "$min": {
                "$cond": [ { "$eq": [ "$props.n", "port" ] }, "$props.v", false ]
            }
        }
    } },
        { "$group": {
        "_id": {
            "_ipaddress": "$_ipaddress",
        },
        "count": { "$sum": 1 }
    }}
])

---

但是我不知道如何组合“loc”和“logtype”条件。

这里每个文档都有一个数组，用于集中存储相关信息。这种设计不适合您尝试的查询。 据我所知，$unwind在这里帮不了什么忙，因为它会分割数组元素

我发现的解决方案是将数组元素设置为键：值对，并成功地扩展

> db.final.aggregate([
 ... {"$project" : {"pro" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "pro" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1}},
 ... {"$project" : {"loc" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "loc" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1}},
 ... {"$project" : {"port" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "port" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1}},
 ... {"$project" : {"ip" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ip" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1,port:1}},
 ... {"$project" : {"ip_addr" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ip_addr" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1,port:1,ip:1}},
 ... {"$project" : {"ipaddr" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ipaddr" ] }, "$$array_elem.v", null]}}}, [null] ] },pro:1,loc:1,port:1,ip:1,ip_addr:1}}
 ... ])

//Result(I have used data given in your question):
{ "_id" : 2, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "13438" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }
{ "_id" : 5, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }
{ "_id" : 1, "pro" : [ "udp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ "2.2.2.2" ], "ipaddr" : [ ] }
{ "_id" : 3, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ ], "ipaddr" : [ "1.1.1.1" ] }
{ "_id" : 4, "pro" : [ "udp" ], "loc" : [ "LA" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ ], "ipaddr" : [ "1.1.1.1" ] }
{ "_id" : 6, "pro" : [ "udp" ], "loc" : [ "LA" ], "port" : [ "53" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }

在这里，数组中的每个元素都是键和值。您可以在此文档上应用条件并获得所需的结果。我不会在这里给出完整的答案，因为您已经做了部分

注:

MongoDB不允许在aggregation（）中使用$elemMatch，而用于此的解决方法是增加聚合管道的大小

若数组中元素的位置是可靠的，那个么可以简单地将数组元素转换为键：值对

> db.final.aggregate([
 ... {"$project" : {"pro" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "pro" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1}},
 ... {"$project" : {"loc" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "loc" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1}},
 ... {"$project" : {"port" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "port" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1}},
 ... {"$project" : {"ip" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ip" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1,port:1}},
 ... {"$project" : {"ip_addr" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ip_addr" ] }, "$$array_elem.v", null]}}}, [null] ] },props:1,pro:1,loc:1,port:1,ip:1}},
 ... {"$project" : {"ipaddr" : { "$setDifference" :[{"$map" : {"input" : "$props","as" : "array_elem", "in" : { "$cond" : [ { "$eq" : [ "$$array_elem.n", "ipaddr" ] }, "$$array_elem.v", null]}}}, [null] ] },pro:1,loc:1,port:1,ip:1,ip_addr:1}}
 ... ])

//Result(I have used data given in your question):
{ "_id" : 2, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "13438" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }
{ "_id" : 5, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }
{ "_id" : 1, "pro" : [ "udp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ "2.2.2.2" ], "ipaddr" : [ ] }
{ "_id" : 3, "pro" : [ "tcp" ], "loc" : [ "NW" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ ], "ipaddr" : [ "1.1.1.1" ] }
{ "_id" : 4, "pro" : [ "udp" ], "loc" : [ "LA" ], "port" : [ "53" ], "ip" : [ ], "ip_addr" : [ ], "ipaddr" : [ "1.1.1.1" ] }
{ "_id" : 6, "pro" : [ "udp" ], "loc" : [ "LA" ], "port" : [ "53" ], "ip" : [ "1.1.1.1" ], "ip_addr" : [ ], "ipaddr" : [ ] }