我如何从数组中删除重复的项目（复杂对象）

newBike 发表于 Dev

新自行车

在每个文件中

的records是包含许多重复的对象的阵列。

并且buy_items其中还包含许多重复项。

如何清除重复的物品？

原始文件：

{
  "_id": "0005d116qwwewdq82a1b84f148fa6027d429f3e",
  "records": [
    {
      "DATE": new Date("1996-02-08T08:00:00+0800"),
      "buy_items": [
        "5210 ",
        "5210 ",
        "5210 "
      ]
    },
    {
      "DATE": new Date("1996-02-08T08:00:00+0800"),
      "buy_items": [
        "5210 ",
        "5210 ",
        "5210 "
      ]
    }
    {
      "DATE": new Date("2012-12-08T08:00:00+0800"),
      "buy_items": [
        "5210 ",
        "1234 ",
        " "
      ]
    }        
    ]
}

预期产量：

{
  "_id": "0005d116qwwewdq82a1b84f148fa6027d429f3e",
  "records": [
    {
      "DATE": new Date("1996-02-08T08:00:00+0800"),
      "buy_items": [
        "5210 "
      ]
    },
    {
      "DATE": new Date("2012-12-08T08:00:00+0800"),
      "buy_items": [
        "5210 ",
        "1234 ",
        " "
      ]
    }    
    ]
}

使用Michaels解决方案时，输出可能如下所示

{
  "_id": "0005d116qwwewdq82a1b84f148fa6027d429f3e",
  "records": [
    "date": new Date("1996-02-08T08:00:00+0800"),
      "buy_items": [
        "5210 "
        "1234 ",
        " "
      ]
    ]
}

苯乙烯

您可以使用聚合框架删除重复的对象

db.collection.aggregate(
    [
        { $unwind: "$records" }, 
        { $unwind: "$records.buy_items" }, 
        { $group: { "_id": {id: "$_id", date: "$records.DATE" }, buy_items: { $addToSet: "$records.buy_items" }}}, 
        { $group: {"_id": "$_id.id", records: { $push: {"date": "$_id.date", "buy_items": "$buy_items" }}}}, { $sort: { "records.0.date": 1 }} ,
        { $out: "collection" }
    ]
)

该$out运营商让你写你的聚合结果在指定的集合或替换你现有的集合。

使用“批量”操作甚至更好

var bulk = bulk = db.collection.initializeOrderedBulkOp(),
    count = 0;

db.collection.aggregate([
    { "$unwind": "$records" }, 
    { "$project": { 
        "date": "$records.DATE", 
        "buy_items": { "$setIntersection": "$records.buy_items" }
    }}, 
    { "$unwind": "$buy_items" }, 
    { "$group": { 
        "_id": { "id": "$_id", "date": "$date" }, 
        "buy_items": { "$addToSet": "$buy_items" }
    }},
    { "$group": { 
        "_id": "$_id.id", 
        "records": { "$push": { 
            "date": "$_id.date", 
            "buy_items": "$buy_items" 
        }}
    }}
]).forEach(function(doc) { 
       bulk.find({"_id": doc._id}).updateOne({
       "$set": { "records": doc.records }
       }); 
       count++; 
       if (count % 500 == 0) {   
           bulk.execute();    
           bulk = db.collection.initializeOrderedBulkOp(); 
       } 
})

if (count % 500 != 0)
    bulk.execute();

结果：

{
    "_id" : "0005d116qwwewdq82a1b84f148fa6027d429f3e",
    "records" : [
            {
                    "date" : ISODate("2012-12-08T00:00:00Z"),
                    "buy_items" : [
                            " ",
                            "1234 ",
                            "5210 "
                    ]
            },
            {
                    "date" : ISODate("1996-02-08T00:00:00Z"),
                    "buy_items" : [
                            "5210 "
                    ]
            }
    ]
}