mongodb - 聚合 $lookup 不返回元素原始数组顺序

Question

查询返回元素在其集合中的放置顺序，忽略初始数组的顺序。这会影响我们系统的功能。是否有任何额外的命令可以将其按正确的顺序排列？是否有可用的解决方法？

下面是一个简单的例子:

Collection1 文档

{
  "_id":ObjectId("5c781752176c512f180048e3"),
  "Name":"Pedro",
  "Classes":[
    {"ID": ObjectId("5c7af2b2f6f6e47c9060d7ce") },
    {"ID": ObjectId("5c7af2bcf6f6e47c9060d7cf") },
    {"ID": ObjectId("5c7af2aaf6f6e47c9060d7cd") }
  ]
}

Collection2 文档

{
  "_id":ObjectId("5c7af2aaf6f6e47c9060d7cd"),
  "variable1":"A"
},

{
  "_id": ObjectId("5c7af2b2f6f6e47c9060d7ce"),
  "variable1":"B"
},

{
  "_id": ObjectId("5c7af2bcf6f6e47c9060d7cf"),
  "variable1":"C"
}

查询:

aggregate(
  pipeline = '[
  {"$match": {"_id": {"$oid": "5c781752176c512f180048e3"}}},
  {"$lookup": {"from": "collection2", "localField": "Classes.ID", "foreignField": "_id", "as": "Collection2_doc"}}
  ]'
)

返回:

结果顺序:

[
    {
      "_id":ObjectId("5c7af2aaf6f6e47c9060d7cd"),
      "variable1":"A"
    },
    {
      "_id": ObjectId("5c7af2b2f6f6e47c9060d7ce"),
      "variable1":"B"
    },
    {
      "_id": ObjectId("5c7af2bcf6f6e47c9060d7cf"),
      "variable1":"C"
    }
]

预期顺序(第一个文档数组顺序):

[
    {
      "_id": ObjectId("5c7af2b2f6f6e47c9060d7ce"),
      "variable1":"B"
    },
    {
      "_id": ObjectId("5c7af2bcf6f6e47c9060d7cf"),
      "variable1":"C"
    },
    {
      "_id":ObjectId("5c7af2aaf6f6e47c9060d7cd"),
      "variable1":"A"
    }
]

有没有额外的命令ex。 $sort 可用于根据原始数组顺序返回它？

Answer 1

这是 $lookup 的“设计”执行。 实际上发生的“幕后”是MongoDB 内部转换$lookup中的参数使用 $expr 转换为新的表现力 格式和 $in .即使在实现这种富有表现力的形式之前的版本中，“值数组”的内部机制也几乎相同。

这里的解决方案是维护原始数组的副本作为重新排序“已加入” 项目的引用:

collection.aggregate([
  {"$match": {"_id": ObjectId("5c781752176c512f180048e3") }},
  {"$lookup": {
    "from": "collection2",
    "let": { "classIds": "$Classes.ID" },
    "pipeline": [
      { "$match": {
        "$expr": { "$in": [ "$_id", "$$classIds" ] }
      }},
      { "$addFields": {
        "sort": {
          "$indexOfArray": [ "$$classIds", "$_id" ]
        }
      }},
      { "$sort": { "sort": 1 } },
      { "$addFields": { "sort": "$$REMOVE" }}
    ],
    "as": "results"
  }}
])

或由遗产$lookup用法:

collection.aggregate([
  {"$match": {"_id": ObjectId("5c781752176c512f180048e3") }},
  {"$lookup": {
    "from": "collection2",
    "localField": "Classes.ID",
    "foreignField": "_id",
    "as": "results"
  }},
  { "$unwind": "$results" },
  { "$addFields": {
    "sort": {
      "$indexOfArray": [ "$Classes.ID", "$results._id" ]
    }
  }},
  { "$sort": { "_id": 1, "sort": 1 } },
  { "$group": {
    "_id": "$_id",
    "Name": { "$first": "$Name" },
    "Classes": { "$first": "$Classes" },
    "results": { "$push": "$results" }
  }}
])

两种变体产生相同的输出:

{
        "_id" : ObjectId("5c781752176c512f180048e3"),
        "Name" : "Pedro",
        "Classes" : [
                {
                        "ID" : ObjectId("5c7af2b2f6f6e47c9060d7ce")
                },
                {
                        "ID" : ObjectId("5c7af2bcf6f6e47c9060d7cf")
                },
                {
                        "ID" : ObjectId("5c7af2aaf6f6e47c9060d7cd")
                }
        ],
        "results" : [
                {
                        "_id" : ObjectId("5c7af2b2f6f6e47c9060d7ce"),
                        "variable1" : "B"
                },
                {
                        "_id" : ObjectId("5c7af2bcf6f6e47c9060d7cf"),
                        "variable1" : "C"
                },
                {
                        "_id" : ObjectId("5c7af2aaf6f6e47c9060d7cd"),
                        "variable1" : "A"
                }
        ]
}

一般概念是使用 $indexOfArray与 “加入” 内容中的 _id 值进行比较，以找到它在 中的原始源数组中的 “索引” 位置$Classes.ID”。不同的$lookup语法变体对于您如何访问此副本以及您如何基本重构有不同的方法。

$sort当然设置了实际文档的顺序，要么在表达形式的流水线处理中，要么通过$unwind 的公开文档。 .你在哪里使用$unwind然后你会$group回到原来的文档形式。

NOTE: The usage examples here depend on MongoDB 3.4 for the $indexOfArray at least and the $$REMOVE aligns with MongoDB 3.6 as would the expressive $lookup.

There are other approaches to re-ordering the array for prior releases, but these are demonstrated in more detail on Does MongoDB's $in clause guarantee order. Realistically the bare minimum you should presently be running as a production MongoDB version is the 3.4 release.

See Support Policy under MongoDB Server for the full details of supported releases and end dates.