$添加 ToSet

$addToSet聚合运算符从每个组的指定表达式中返回一个由唯一值组成的数组。它在$group阶段内用于累积不同的值，自动消除重复值。

参数

• expression：要为组中每个文档计算的表达式。

示例（MongoDB Shell）

以下示例演示如何使用$addToSet运营商收集为每位客户下单的独特城市。

创建示例文档

db.orders.insertMany([
  { _id: 1, customer: "Alice", city: "Seattle", amount: 100 },
  { _id: 2, customer: "Alice", city: "Portland", amount: 150 },
  { _id: 3, customer: "Bob", city: "Seattle", amount: 200 },
  { _id: 4, customer: "Alice", city: "Seattle", amount: 75 },
  { _id: 5, customer: "Bob", city: "Boston", amount: 300 }
]);

查询示例

db.orders.aggregate([
  {
    $group: {
      _id: "$customer",
      cities: { $addToSet: "$city" }
    }
  }
]);

输出

[
  { _id: 'Bob', cities: [ 'Seattle', 'Boston' ] },
  { _id: 'Alice', cities: [ 'Seattle', 'Portland' ] }
]

窗口运算符用法示例（MongoDB Shell）

8.0.2 版中的新内容。

该$addToSet操作员还可以在$setWindowFields舞台中用作窗口操作员。在此上下文中，它返回每个窗口中文档的指定表达式的唯一值的数组。您可以在output字段下指定运算符，也可以选择使用window文档定义窗口边界。

注意

在中用作窗口运算符时$setWindowFields，中间数据限制$addToSet为 100 MB。超过此限制的操作会返回错误。

创建示例文档

db.visits.insertMany([
  { _id: 1, customer: "Alice", day: 1, city: "Seattle" },
  { _id: 2, customer: "Alice", day: 2, city: "Portland" },
  { _id: 3, customer: "Alice", day: 3, city: "Seattle" },
  { _id: 4, customer: "Bob", day: 1, city: "Boston" },
  { _id: 5, customer: "Bob", day: 2, city: "Boston" }
]);

查询示例

以下示例对文档进行分区customer，按分区排序day，并返回从分区开始到当前文档的一组唯一city值。

db.visits.aggregate([
  {
    $setWindowFields: {
      partitionBy: "$customer",
      sortBy: { day: 1 },
      output: {
        citiesSoFar: {
          $addToSet: "$city",
          window: { documents: ["unbounded", "current"] }
        }
      }
    }
  }
]);

输出

[
  { "_id": 1, "customer": "Alice", "day": 1, "city": "Seattle", "citiesSoFar": [ "Seattle" ] },
  { "_id": 2, "customer": "Alice", "day": 2, "city": "Portland", "citiesSoFar": [ "Portland", "Seattle" ] },
  { "_id": 3, "customer": "Alice", "day": 3, "city": "Seattle", "citiesSoFar": [ "Portland", "Seattle" ] },
  { "_id": 4, "customer": "Bob", "day": 1, "city": "Boston", "citiesSoFar": [ "Boston" ] },
  { "_id": 5, "customer": "Bob", "day": 2, "city": "Boston", "citiesSoFar": [ "Boston" ] }
]

每个文档都添加citiesSoFar了从开始到当前文档的分区内的一组唯一city值。与累加器形式一样，不能保证返回数组中值的顺序。

代码示例

要查看使用$addToSet运算符的代码示例，请选择要使用的语言的选项卡。以下示例显示了累加器的用法（输入$group）和窗口运算符的用法（输入$setWindowFields）：

Node.js

const { MongoClient } = require('mongodb');

async function example() {
  const client = await MongoClient.connect('mongodb://<username>:<password>@<cluster-endpoint>:27017/?tls=true&tlsCAFile=global-bundle.pem&replicaSet=rs0&readPreference=secondaryPreferred&retryWrites=false');
  const db = client.db('test');

  // Accumulator usage: collect unique values per group
  const orders = db.collection('orders');
  await orders.insertMany([
    { _id: 1, customer: "Alice", city: "Seattle", amount: 100 },
    { _id: 2, customer: "Alice", city: "Portland", amount: 150 },
    { _id: 3, customer: "Bob", city: "Seattle", amount: 200 },
    { _id: 4, customer: "Alice", city: "Seattle", amount: 75 },
    { _id: 5, customer: "Bob", city: "Boston", amount: 300 }
  ]);
  const accumulatorResult = await orders.aggregate([
    {
      $group: {
        _id: "$customer",
        cities: { $addToSet: "$city" }
      }
    }
  ]).toArray();
  console.log('Accumulator result:', accumulatorResult);

  // Window operator usage: running set of unique values within each partition
  const visits = db.collection('visits');
  await visits.insertMany([
    { _id: 1, customer: "Alice", day: 1, city: "Seattle" },
    { _id: 2, customer: "Alice", day: 2, city: "Portland" },
    { _id: 3, customer: "Alice", day: 3, city: "Seattle" },
    { _id: 4, customer: "Bob", day: 1, city: "Boston" },
    { _id: 5, customer: "Bob", day: 2, city: "Boston" }
  ]);
  const windowResult = await visits.aggregate([
    {
      $setWindowFields: {
        partitionBy: "$customer",
        sortBy: { day: 1 },
        output: {
          citiesSoFar: {
            $addToSet: "$city",
            window: { documents: ["unbounded", "current"] }
          }
        }
      }
    }
  ]).toArray();
  console.log('Window result:', windowResult);

  await client.close();
}

example();

Python

from pymongo import MongoClient

def example():
    client = MongoClient('mongodb://<username>:<password>@<cluster-endpoint>:27017/?tls=true&tlsCAFile=global-bundle.pem&replicaSet=rs0&readPreference=secondaryPreferred&retryWrites=false')
    db = client['test']

    # Accumulator usage: collect unique values per group
    orders = db['orders']
    orders.insert_many([
        { '_id': 1, 'customer': 'Alice', 'city': 'Seattle', 'amount': 100 },
        { '_id': 2, 'customer': 'Alice', 'city': 'Portland', 'amount': 150 },
        { '_id': 3, 'customer': 'Bob', 'city': 'Seattle', 'amount': 200 },
        { '_id': 4, 'customer': 'Alice', 'city': 'Seattle', 'amount': 75 },
        { '_id': 5, 'customer': 'Bob', 'city': 'Boston', 'amount': 300 }
    ])
    accumulator_result = list(orders.aggregate([
        {
            '$group': {
                '_id': '$customer',
                'cities': { '$addToSet': '$city' }
            }
        }
    ]))
    print('Accumulator result:', accumulator_result)

    # Window operator usage: running set of unique values within each partition
    visits = db['visits']
    visits.insert_many([
        { '_id': 1, 'customer': 'Alice', 'day': 1, 'city': 'Seattle' },
        { '_id': 2, 'customer': 'Alice', 'day': 2, 'city': 'Portland' },
        { '_id': 3, 'customer': 'Alice', 'day': 3, 'city': 'Seattle' },
        { '_id': 4, 'customer': 'Bob', 'day': 1, 'city': 'Boston' },
        { '_id': 5, 'customer': 'Bob', 'day': 2, 'city': 'Boston' }
    ])
    window_result = list(visits.aggregate([
        {
            '$setWindowFields': {
                'partitionBy': '$customer',
                'sortBy': { 'day': 1 },
                'output': {
                    'citiesSoFar': {
                        '$addToSet': '$city',
                        'window': { 'documents': ['unbounded', 'current'] }
                    }
                }
            }
        }
    ]))
    print('Window result:', window_result)

    client.close()

example()