mongodb组由多个字段组成

时间:2014-04-08 09:03:59

标签: mongodb aggregation-framework

例如,我有这些文件:

{
  "addr": "address1",
  "book": "book1"
},
{
  "addr": "address2",
  "book": "book1"
},
{
  "addr": "address1",
  "book": "book5"
},
{
  "addr": "address3",
  "book": "book9"
},
{
  "addr": "address2",
  "book": "book5"
},
{
  "addr": "address2",
  "book": "book1"
},
{
  "addr": "address1",
  "book": "book1"
},
{
  "addr": "address15",
  "book": "book1"
},
{
  "addr": "address9",
  "book": "book99"
},
{
  "addr": "address90",
  "book": "book33"
},
{
  "addr": "address4",
  "book": "book3"
},
{
  "addr": "address5",
  "book": "book1"
},
{
  "addr": "address77",
  "book": "book11"
},
{
  "addr": "address1",
  "book": "book1"
}

等等。

如何提出一个请求,它将描述每个地址的前N个地址和前M个书籍?
例子预期结果:

地址1 | book_1:5
| book_2:10
| book_3:50
|总计:65
______________________
地址2 | book_1:10
| book_2:10
| | ...
| book_M:10
|总计:M * 10
... ...
______________________
地址N | book_1:20
| book_2:20
| | ...
| book_M:20
|总计:M * 20

3 个答案:

答案 0 :(得分:151)

TLDR摘要

在现代MongoDB版本中,您可以在基本聚合结果之外使用$slice强制执行此操作。对于“大”结果,请为每个分组运行并行查询(演示列表位于答案的末尾),或等待SERVER-9377解析,这将允许对项目数量的“限制” $push到数组。

db.books.aggregate([
    { "$group": {
        "_id": {
            "addr": "$addr",
            "book": "$book"
        },
        "bookCount": { "$sum": 1 }
    }},
    { "$group": {
        "_id": "$_id.addr",
        "books": { 
            "$push": { 
                "book": "$_id.book",
                "count": "$bookCount"
            },
        },
        "count": { "$sum": "$bookCount" }
    }},
    { "$sort": { "count": -1 } },
    { "$limit": 2 },
    { "$project": {
        "books": { "$slice": [ "$books", 2 ] },
        "count": 1
    }}
])

MongoDB 3.6预览

仍未解析SERVER-9377,但在此版本$lookup中允许使用"pipeline"表达式作为参数而不是"localFields"的新“非关联”选项和"foreignFields"选项。然后,这允许与另一个管道表达式“自联接”,我们可以在其中应用$limit以返回“top-n”结果。

db.books.aggregate([
  { "$group": {
    "_id": "$addr",
    "count": { "$sum": 1 }
  }},
  { "$sort": { "count": -1 } },
  { "$limit": 2 },
  { "$lookup": {
    "from": "books",
    "let": {
      "addr": "$_id"
    },
    "pipeline": [
      { "$match": { 
        "$expr": { "$eq": [ "$addr", "$$addr"] }
      }},
      { "$group": {
        "_id": "$book",
        "count": { "$sum": 1 }
      }},
      { "$sort": { "count": -1  } },
      { "$limit": 2 }
    ],
    "as": "books"
  }}
])

此处的另一个补充当然是能够通过$expr使用$match插入变量以选择“join”中的匹配项,但一般前提是“管道内的管道” “内部内容可以通过来自父级的匹配进行过滤。由于它们本身都是“管道”,我们可以分别$limit每个结果。

这将是运行并行查询的下一个最佳选择,如果$match被允许并且能够在“子管道”处理中使用索引,实际上会更好。因此,当引用的问题没有使用“限制$push”时,它实际上提供了应该更好的东西。


原创内容

你似乎偶然发现了顶级的“N”问题。在某种程度上,你的问题很容易解决,但不是你要求的确切限制:

db.books.aggregate([
    { "$group": {
        "_id": {
            "addr": "$addr",
            "book": "$book"
        },
        "bookCount": { "$sum": 1 }
    }},
    { "$group": {
        "_id": "$_id.addr",
        "books": { 
            "$push": { 
                "book": "$_id.book",
                "count": "$bookCount"
            },
        },
        "count": { "$sum": "$bookCount" }
    }},
    { "$sort": { "count": -1 } },
    { "$limit": 2 }
])

现在,这会给你一个这样的结果:

{
    "result" : [
            {
                    "_id" : "address1",
                    "books" : [
                            {
                                    "book" : "book4",
                                    "count" : 1
                            },
                            {
                                    "book" : "book5",
                                    "count" : 1
                            },
                            {
                                    "book" : "book1",
                                    "count" : 3
                            }
                    ],
                    "count" : 5
            },
            {
                    "_id" : "address2",
                    "books" : [
                            {
                                    "book" : "book5",
                                    "count" : 1
                            },
                            {
                                    "book" : "book1",
                                    "count" : 2
                            }
                    ],
                    "count" : 3
            }
    ],
    "ok" : 1
}

因此,这与您提出的要求不同,虽然我们确实得到了地址值的最高结果,但基础“书籍”选择并不仅限于所需的结果数量。

事实证明这很难做到,但是可以做到这一点虽然复杂性随着你需要匹配的项目数量的增加而增加。为了简单起见,我们最多可以保持2个匹配:

db.books.aggregate([
    { "$group": {
        "_id": {
            "addr": "$addr",
            "book": "$book"
        },
        "bookCount": { "$sum": 1 }
    }},
    { "$group": {
        "_id": "$_id.addr",
        "books": { 
            "$push": { 
                "book": "$_id.book",
                "count": "$bookCount"
            },
        },
        "count": { "$sum": "$bookCount" }
    }},
    { "$sort": { "count": -1 } },
    { "$limit": 2 },
    { "$unwind": "$books" },
    { "$sort": { "count": 1, "books.count": -1 } },
    { "$group": {
        "_id": "$_id",
        "books": { "$push": "$books" },
        "count": { "$first": "$count" }
    }},
    { "$project": {
        "_id": {
            "_id": "$_id",
            "books": "$books",
            "count": "$count"
        },
        "newBooks": "$books"
    }},
    { "$unwind": "$newBooks" },
    { "$group": {
      "_id": "$_id",
      "num1": { "$first": "$newBooks" }
    }},
    { "$project": {
        "_id": "$_id",
        "newBooks": "$_id.books",
        "num1": 1
    }},
    { "$unwind": "$newBooks" },
    { "$project": {
        "_id": "$_id",
        "num1": 1,
        "newBooks": 1,
        "seen": { "$eq": [
            "$num1",
            "$newBooks"
        ]}
    }},
    { "$match": { "seen": false } },
    { "$group":{
        "_id": "$_id._id",
        "num1": { "$first": "$num1" },
        "num2": { "$first": "$newBooks" },
        "count": { "$first": "$_id.count" }
    }},
    { "$project": {
        "num1": 1,
        "num2": 1,
        "count": 1,
        "type": { "$cond": [ 1, [true,false],0 ] }
    }},
    { "$unwind": "$type" },
    { "$project": {
        "books": { "$cond": [
            "$type",
            "$num1",
            "$num2"
        ]},
        "count": 1
    }},
    { "$group": {
        "_id": "$_id",
        "count": { "$first": "$count" },
        "books": { "$push": "$books" }
    }},
    { "$sort": { "count": -1 } }
])

这样,实际上会从前两个“地址”条目中为您提供前两本“书籍”。

但是对于我的钱,请保留第一个表单然后简单地“切片”返回的数组元素以获取第一个“N”元素。


演示代码

演示代码适用于v8.x和v10.x版本的当前LTS版本的NodeJS。这主要是针对async/await语法,但是在一般流程中没有任何内容存在任何此类限制,并且只需对简单的承诺进行少量修改,甚至回到简单的回调实现。

<强> index.js

const { MongoClient } = require('mongodb');
const fs = require('mz/fs');

const uri = 'mongodb://localhost:27017';

const log = data => console.log(JSON.stringify(data, undefined, 2));

(async function() {

  try {
    const client = await MongoClient.connect(uri);

    const db = client.db('bookDemo');
    const books = db.collection('books');

    let { version } = await db.command({ buildInfo: 1 });
    version = parseFloat(version.match(new RegExp(/(?:(?!-).)*/))[0]);

    // Clear and load books
    await books.deleteMany({});

    await books.insertMany(
      (await fs.readFile('books.json'))
        .toString()
        .replace(/\n$/,"")
        .split("\n")
        .map(JSON.parse)
    );

    if ( version >= 3.6 ) {

    // Non-correlated pipeline with limits
      let result = await books.aggregate([
        { "$group": {
          "_id": "$addr",
          "count": { "$sum": 1 }
        }},
        { "$sort": { "count": -1 } },
        { "$limit": 2 },
        { "$lookup": {
          "from": "books",
          "as": "books",
          "let": { "addr": "$_id" },
          "pipeline": [
            { "$match": {
              "$expr": { "$eq": [ "$addr", "$$addr" ] }
            }},
            { "$group": {
              "_id": "$book",
              "count": { "$sum": 1 },
            }},
            { "$sort": { "count": -1 } },
            { "$limit": 2 }
          ]
        }}
      ]).toArray();

      log({ result });
    }

    // Serial result procesing with parallel fetch

    // First get top addr items
    let topaddr = await books.aggregate([
      { "$group": {
        "_id": "$addr",
        "count": { "$sum": 1 }
      }},
      { "$sort": { "count": -1 } },
      { "$limit": 2 }
    ]).toArray();

    // Run parallel top books for each addr
    let topbooks = await Promise.all(
      topaddr.map(({ _id: addr }) =>
        books.aggregate([
          { "$match": { addr } },
          { "$group": {
            "_id": "$book",
            "count": { "$sum": 1 }
          }},
          { "$sort": { "count": -1 } },
          { "$limit": 2 }
        ]).toArray()
      )
    );

    // Merge output
    topaddr = topaddr.map((d,i) => ({ ...d, books: topbooks[i] }));
    log({ topaddr });

    client.close();

  } catch(e) {
    console.error(e)
  } finally {
    process.exit()
  }

})()

<强> books.json

{ "addr": "address1",  "book": "book1"  }
{ "addr": "address2",  "book": "book1"  }
{ "addr": "address1",  "book": "book5"  }
{ "addr": "address3",  "book": "book9"  }
{ "addr": "address2",  "book": "book5"  }
{ "addr": "address2",  "book": "book1"  }
{ "addr": "address1",  "book": "book1"  }
{ "addr": "address15", "book": "book1"  }
{ "addr": "address9",  "book": "book99" }
{ "addr": "address90", "book": "book33" }
{ "addr": "address4",  "book": "book3"  }
{ "addr": "address5",  "book": "book1"  }
{ "addr": "address77", "book": "book11" }
{ "addr": "address1",  "book": "book1"  }

答案 1 :(得分:33)

使用如下聚合函数:

[
{$group: {_id : {book : '$book',address:'$addr'}, total:{$sum :1}}},
{$project : {book : '$_id.book', address : '$_id.address', total : '$total', _id : 0}}
]

它会给你如下结果:

        {
            "total" : 1,
            "book" : "book33",
            "address" : "address90"
        }, 
        {
            "total" : 1,
            "book" : "book5",
            "address" : "address1"
        }, 
        {
            "total" : 1,
            "book" : "book99",
            "address" : "address9"
        }, 
        {
            "total" : 1,
            "book" : "book1",
            "address" : "address5"
        }, 
        {
            "total" : 1,
            "book" : "book5",
            "address" : "address2"
        }, 
        {
            "total" : 1,
            "book" : "book3",
            "address" : "address4"
        }, 
        {
            "total" : 1,
            "book" : "book11",
            "address" : "address77"
        }, 
        {
            "total" : 1,
            "book" : "book9",
            "address" : "address3"
        }, 
        {
            "total" : 1,
            "book" : "book1",
            "address" : "address15"
        }, 
        {
            "total" : 2,
            "book" : "book1",
            "address" : "address2"
        }, 
        {
            "total" : 3,
            "book" : "book1",
            "address" : "address1"
        }

我没有完全得到您期望的结果格式,因此请随意将其修改为您需要的格式。

答案 2 :(得分:1)

以下查询将提供与所需响应完全相同的结果:

db.books.aggregate([
    {
        $group: {
            _id: { addresses: "$addr", books: "$book" },
            num: { $sum :1 }
        }
    },
    {
        $group: {
            _id: "$_id.addresses",
            bookCounts: { $push: { bookName: "$_id.books",count: "$num" } }
        }
    },
    {
        $project: {
            _id: 1,
            bookCounts:1,
            "totalBookAtAddress": {
                "$sum": "$bookCounts.count"
            }
        }
    }

]) 

响应如下所示:

/* 1 */
{
    "_id" : "address4",
    "bookCounts" : [
        {
            "bookName" : "book3",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 2 */
{
    "_id" : "address90",
    "bookCounts" : [
        {
            "bookName" : "book33",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 3 */
{
    "_id" : "address15",
    "bookCounts" : [
        {
            "bookName" : "book1",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 4 */
{
    "_id" : "address3",
    "bookCounts" : [
        {
            "bookName" : "book9",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 5 */
{
    "_id" : "address5",
    "bookCounts" : [
        {
            "bookName" : "book1",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 6 */
{
    "_id" : "address1",
    "bookCounts" : [
        {
            "bookName" : "book1",
            "count" : 3
        },
        {
            "bookName" : "book5",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 4
},

/* 7 */
{
    "_id" : "address2",
    "bookCounts" : [
        {
            "bookName" : "book1",
            "count" : 2
        },
        {
            "bookName" : "book5",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 3
},

/* 8 */
{
    "_id" : "address77",
    "bookCounts" : [
        {
            "bookName" : "book11",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
},

/* 9 */
{
    "_id" : "address9",
    "bookCounts" : [
        {
            "bookName" : "book99",
            "count" : 1
        }
    ],
    "totalBookAtAddress" : 1
}