MongoDB 新手入门 - Aggregation

db.collection.aggregate( [ { <stage> }, ... ] )

db.orders.insertMany( [
   { _id: 0, name: "Pepperoni", size: "small", price: 19,
     quantity: 10, date: ISODate( "2021-03-13T08:14:30Z" ) },
   { _id: 1, name: "Pepperoni", size: "medium", price: 20,
     quantity: 20, date : ISODate( "2021-03-13T09:13:24Z" ) },
   { _id: 2, name: "Pepperoni", size: "large", price: 21,
     quantity: 30, date : ISODate( "2021-03-17T09:22:12Z" ) },
   { _id: 3, name: "Cheese", size: "small", price: 12,
     quantity: 15, date : ISODate( "2021-03-13T11:21:39.736Z" ) },
   { _id: 4, name: "Cheese", size: "medium", price: 13,
     quantity:50, date : ISODate( "2022-01-12T21:23:13.331Z" ) },
   { _id: 5, name: "Cheese", size: "large", price: 14,
     quantity: 10, date : ISODate( "2022-01-12T05:08:13Z" ) },
   { _id: 6, name: "Vegan", size: "small", price: 17,
     quantity: 10, date : ISODate( "2021-01-13T05:08:13Z" ) },
   { _id: 7, name: "Vegan", size: "medium", price: 18,
     quantity: 10, date : ISODate( "2021-01-13T05:10:13Z" ) }
] )

// SQL：SELECT 
// 				DATE_FORMAT(date, '%Y-%m-%d') AS _id, 
//        SUM(price * quantity) AS totalOrderValue,
//        AVG(quantity) AS averageOrderQuantity
//      FROM orders
//      WHERE date >= '2020-01-30' AND date < '2022-01-30'
//      GROUP BY DATE_FORMAT(date, '%Y-%m-%d')
//      ORDER BY SUM(price * quantity) DESC
db.orders.aggregate( [
   // Stage 1: 通过时间范围过滤披萨订单
   {
      $match:
      {
         "date": { $gte: new ISODate( "2020-01-30" ), $lt: new ISODate( "2022-01-30" ) }
      }
   },
   // Stage 2: 对匹配的订单进行分组，并且计算总价值和平均数量
   {
      $group:
      {
         _id: { $dateToString: { format: "%Y-%m-%d", date: "$date" } },
         totalOrderValue: { $sum: { $multiply: [ "$price", "$quantity" ] } },
         averageOrderQuantity: { $avg: "$quantity" }
      }
   },
   // Stage 3: 按照 totalOrderValue 对文档进行反向排序
   {
      $sort: { totalOrderValue: -1 }
   }
 ] )

[
   { _id: '2022-01-12', totalOrderValue: 790, averageOrderQuantity: 30 },
   { _id: '2021-03-13', totalOrderValue: 770, averageOrderQuantity: 15 },
   { _id: '2021-03-17', totalOrderValue: 630, averageOrderQuantity: 30 },
   { _id: '2021-01-13', totalOrderValue: 350, averageOrderQuantity: 10 }
]

db.books.aggregate( [
   {
      $project: {
         title: 1,
         "author.first": 1,
         "author.last" : 1,
         "author.middle": {
            // 这里判断 $author.middle 是否为空，为空则将该字段移除，否则返回该字段
            $cond: {
               if: { $eq: [ "", "$author.middle" ] },
               then: "$$REMOVE",
               else: "$author.middle"
            }
         }
      }
   }
] )

{ $match: { <query> } }

{ "_id" : ObjectId("512bc95fe835e68f199c8686"), "author" : "dave", "score" : 80, "views" : 100 }
{ "_id" : ObjectId("512bc962e835e68f199c8687"), "author" : "dave", "score" : 85, "views" : 521 }
{ "_id" : ObjectId("55f5a192d4bede9ac365b257"), "author" : "ahn", "score" : 60, "views" : 1000 }
{ "_id" : ObjectId("55f5a192d4bede9ac365b258"), "author" : "li", "score" : 55, "views" : 5000 }
{ "_id" : ObjectId("55f5a1d3d4bede9ac365b259"), "author" : "annT", "score" : 60, "views" : 50 }
{ "_id" : ObjectId("55f5a1d3d4bede9ac365b25a"), "author" : "li", "score" : 94, "views" : 999 }
{ "_id" : ObjectId("55f5a1d3d4bede9ac365b25b"), "author" : "ty", "score" : 95, "views" : 1000 }

// SQL：SELECT * FROM articles WHERE author = "dave"
db.articles.aggregate(
    [ { $match : { author : "dave" } } ]
);

{ "_id" : ObjectId("512bc95fe835e68f199c8686"), "author" : "dave", "score" : 80, "views" : 100 }
{ "_id" : ObjectId("512bc962e835e68f199c8687"), "author" : "dave", "score" : 85, "views" : 521 }

{ $count: <string> }

db.getCollection("orders").aggregate([
    { $match: {price: {$gt: 15}} },
    { $count: "price_gt_15_count" }
])

{"price_gt_15_count" : NumberInt(5) }

{ $limit: <positive 64-bit integer> }

db.getCollection("orders").aggregate([{$limit: 2}])

{ $project: { <specification(s)> } }

// SQL：SELECT name, size FROM orders WHERE quantity > 20
db.orders.aggregate([
    { $match: { quantity: { $gt: 20 } } },
    { $project: { name: true, size: 1, _id: false } }
])

{ "name" : "Pepperoni", "size" : "large" }
{ "name" : "Cheese", "size" : "medium" }

{
   $lookup:
     {
       from: <collection to join>,
       localField: <field from the input documents>,
       foreignField: <field from the documents of the "from" collection>,
       as: <output array field>
     }
}

SELECT *, <output array field>
FROM collection
WHERE <output array field> IN (
   SELECT *
   FROM <collection to join>
   WHERE <foreignField> = <collection.localField>
);

db.orders.insertMany( [
   { "_id" : 1, "item" : "almonds", "price" : 12, "quantity" : 2 },
   { "_id" : 2, "item" : "pecans", "price" : 20, "quantity" : 1 },
   { "_id" : 3  }
] )

db.inventory.insertMany( [
   { "_id" : 1, "sku" : "almonds", "description": "product 1", "instock" : 120 },
   { "_id" : 2, "sku" : "bread", "description": "product 2", "instock" : 80 },
   { "_id" : 3, "sku" : "cashews", "description": "product 3", "instock" : 60 },
   { "_id" : 4, "sku" : "pecans", "description": "product 4", "instock" : 70 },
   { "_id" : 5, "sku": null, "description": "Incomplete" },
   { "_id" : 6 }
] )

// SQL：SELECT *, inventory_docs
//      FROM orders
//      WHERE inventory_docs IN (
//         SELECT *
//         FROM inventory
//         WHERE sku = orders.item
//      );
db.orders.aggregate( [
   {
     $lookup:
       {
         from: "inventory",
         localField: "item",
         foreignField: "sku",
         as: "inventory_docs"
       }
  }
] )

{
   "_id" : 1,
   "item" : "almonds",
   "price" : 12,
   "quantity" : 2,
   "inventory_docs" : [
      { "_id" : 1, "sku" : "almonds", "description" : "product 1", "instock" : 120 }
   ]
}
{
   "_id" : 2,
   "item" : "pecans",
   "price" : 20,
   "quantity" : 1,
   "inventory_docs" : [
      { "_id" : 4, "sku" : "pecans", "description" : "product 4", "instock" : 70 }
   ]
}
{
   "_id" : 3,
   "inventory_docs" : [
      { "_id" : 5, "sku" : null, "description" : "Incomplete" },
      { "_id" : 6 }
   ]
}

{
   $lookup:
      {
         from: <joined collection>,
         let: { <var_1>: <expression>, …, <var_n>: <expression> },
         pipeline: [ <pipeline to run on joined collection> ],
         as: <output array field>
      }
}

SELECT *, <output array field>
FROM collection
WHERE <output array field> IN (
   SELECT <documents as determined from the pipeline>
   FROM <collection to join>
   WHERE <pipeline>
);

db.orders.insertMany( [
  { "_id" : 1, "item" : "almonds", "price" : 12, "ordered" : 2 },
  { "_id" : 2, "item" : "pecans", "price" : 20, "ordered" : 1 },
  { "_id" : 3, "item" : "cookies", "price" : 10, "ordered" : 60 }
] )
 
db.warehouses.insertMany( [
  { "_id" : 1, "stock_item" : "almonds", warehouse: "A", "instock" : 120 },
  { "_id" : 2, "stock_item" : "pecans", warehouse: "A", "instock" : 80 },
  { "_id" : 3, "stock_item" : "almonds", warehouse: "B", "instock" : 60 },
  { "_id" : 4, "stock_item" : "cookies", warehouse: "B", "instock" : 40 },
  { "_id" : 5, "stock_item" : "cookies", warehouse: "A", "instock" : 80 }
] )

// SQL: SELECT *, stockdata
//      FROM orders
//      WHERE stockdata IN (
//         SELECT warehouse, instock
//         FROM warehouses
//         WHERE stock_item = orders.item
//         AND instock >= orders.ordered
//      );
db.orders.aggregate( [
   {
      $lookup:
         {
           from: "warehouses",
           let: { order_item: "$item", order_qty: "$ordered" },
           pipeline: [
              { $match:
                 { $expr:
                    { $and:
                       [
                         { $eq: [ "$stock_item",  "$$order_item" ] },
                         { $gte: [ "$instock", "$$order_qty" ] }
                       ]
                    }
                 }
              },
              { $project: { stock_item: 0, _id: 0 } }
           ],
           as: "stockdata"
         }
    }
] )

{
  _id: 1,
  item: 'almonds',
  price: 12,
  ordered: 2,
  stockdata: [
    { warehouse: 'A', instock: 120 },
    { warehouse: 'B', instock: 60 }
  ]
},
{
  _id: 2,
  item: 'pecans',
  price: 20,
  ordered: 1,
  stockdata: [ { warehouse: 'A', instock: 80 } ]
},
{
  _id: 3,
  item: 'cookies',
  price: 10,
  ordered: 60,
  stockdata: [ { warehouse: 'A', instock: 80 } ]
}

{
   $lookup:
      {
         from: <foreign collection>,
         localField: <field from local collection's documents>,
         foreignField: <field from foreign collection's documents>,
         let: { <var_1>: <expression>, …, <var_n>: <expression> },
         pipeline: [ <pipeline to run> ],
         as: <output array field>
      }
}

SELECT *, <output array field>
FROM localCollection
WHERE <output array field> IN (
   SELECT <documents as determined from the pipeline>
   FROM <foreignCollection>
   WHERE <foreignCollection.foreignField> = <localCollection.localField>
   AND <pipeline match condition>
);

{
  $group:
    {
      _id: <expression>, // Group By Expression
      <field1>: { <accumulator1> : <expression1> },
      ...
    }
 }

db.getCollection("orders").aggregate(
    [
        { 
            $group : { 
                _id : "$size", 
                count : { $sum : 1 }
            }
        }
    ], 
    { 
        "allowDiskUse" : true
    }
);

{ "_id" : "medium", "count" : 3.0 }
{ "_id" : "small", "count" : 3.0 }
{ "_id" : "large", "count" : 2.0 }

db.getCollection("orders").aggregate([
    { 
        $group: {_id: "$size"}
    }
]);

{ "_id" : "medium" }
{ "_id" : "large" }
{ "_id" : "small" }

// SQL： SELECT size as _id, count(*) as count FROM orders GROUP BY size HAVING COUNT(*) >= 3 
db.getCollection("orders").aggregate(
    [
        { 
            $group : { 
                _id : "$size", 
                count : { $sum : 1 }
            }
        },
        {
            $match: { count: { $gte: 3} }
        }
    ]
);

{ "_id" : "medium", "count" : 3.0 }
{ "_id" : "small", "count" : 3.0 }

db.getCollection("orders").aggregate([
    { 
        $group: {
            _id: "$size", 
            names: { $push: "$name" } 
        }
    }
])

{ "_id" : "large", "names" : [ "Pepperoni", "Cheese" ] }
{ "_id" : "small", "names" : [ "Pepperoni", "Cheese", "Vegan" ] }
{ "_id" : "medium", "names" : [ "Pepperoni", "Cheese", "Vegan" ] }

db.getCollection("orders").aggregate([
    { $group: { _id: "$size", orders: { $push: "$$ROOT" } } },
    {
        $addFields: {
            totalQuantity: { $sum: "$orders.quantity" }
        }
    }
])

{ $facet:
   {
      <outputField1>: [ <stage1>, <stage2>, ... ],
      <outputField2>: [ <stage1>, <stage2>, ... ],
      ...
   }
}

{ "_id" : 1, "title" : "The Pillars of Society", "artist" : "Grosz", "year" : 1926,
  "price" : NumberDecimal("199.99"),
  "tags" : [ "painting", "satire", "Expressionism", "caricature" ] }
{ "_id" : 2, "title" : "Melancholy III", "artist" : "Munch", "year" : 1902,
  "price" : NumberDecimal("280.00"),
  "tags" : [ "woodcut", "Expressionism" ] }
{ "_id" : 3, "title" : "Dancer", "artist" : "Miro", "year" : 1925,
  "price" : NumberDecimal("76.04"),
  "tags" : [ "oil", "Surrealism", "painting" ] }
{ "_id" : 4, "title" : "The Great Wave off Kanagawa", "artist" : "Hokusai",
  "price" : NumberDecimal("167.30"),
  "tags" : [ "woodblock", "ukiyo-e" ] }
{ "_id" : 5, "title" : "The Persistence of Memory", "artist" : "Dali", "year" : 1931,
  "price" : NumberDecimal("483.00"),
  "tags" : [ "Surrealism", "painting", "oil" ] }
{ "_id" : 6, "title" : "Composition VII", "artist" : "Kandinsky", "year" : 1913,
  "price" : NumberDecimal("385.00"),
  "tags" : [ "oil", "painting", "abstract" ] }
{ "_id" : 7, "title" : "The Scream", "artist" : "Munch", "year" : 1893,
  "tags" : [ "Expressionism", "painting", "oil" ] }
{ "_id" : 8, "title" : "Blue Flower", "artist" : "O'Keefe", "year" : 1918,
  "price" : NumberDecimal("118.42"),
  "tags" : [ "abstract", "painting" ] }

db.artwork.aggregate( [
  {
    $facet: {
      "categorizedByTags": [
        { $unwind: "$tags" },
        { $sortByCount: "$tags" }
      ],
      "categorizedByPrice": [
        // Filter out documents without a price e.g., _id: 7
        { $match: { price: { $exists: 1 } } },
        {
          $bucket: {
            groupBy: "$price",
            boundaries: [  0, 150, 200, 300, 400 ],
            default: "Other",
            output: {
              "count": { $sum: 1 },
              "titles": { $push: "$title" }
            }
          }
        }
      ],
      "categorizedByYears(Auto)": [
        {
          $bucketAuto: {
            groupBy: "$year",
            buckets: 4
          }
        }
      ]
    }
  }
])

{
  "categorizedByYears(Auto)" : [
    // First bucket includes the document without a year, e.g., _id: 4
    { "_id" : { "min" : null, "max" : 1902 }, "count" : 2 },
    { "_id" : { "min" : 1902, "max" : 1918 }, "count" : 2 },
    { "_id" : { "min" : 1918, "max" : 1926 }, "count" : 2 },
    { "_id" : { "min" : 1926, "max" : 1931 }, "count" : 2 }
  ],
  "categorizedByPrice" : [
    {
      "_id" : 0,
      "count" : 2,
      "titles" : [
        "Dancer",
        "Blue Flower"
      ]
    },
    {
      "_id" : 150,
      "count" : 2,
      "titles" : [
        "The Pillars of Society",
        "The Great Wave off Kanagawa"
      ]
    },
    {
      "_id" : 200,
      "count" : 1,
      "titles" : [
        "Melancholy III"
      ]
    },
    {
      "_id" : 300,
      "count" : 1,
      "titles" : [
        "Composition VII"
      ]
    },
    {
      // Includes document price outside of bucket boundaries, e.g., _id: 5
      "_id" : "Other",
      "count" : 1,
      "titles" : [
        "The Persistence of Memory"
      ]
    }
  ],
  "categorizedByTags" : [
    { "_id" : "painting", "count" : 6 },
    { "_id" : "oil", "count" : 4 },
    { "_id" : "Expressionism", "count" : 3 },
    { "_id" : "Surrealism", "count" : 2 },
    { "_id" : "abstract", "count" : 2 },
    { "_id" : "woodblock", "count" : 1 },
    { "_id" : "woodcut", "count" : 1 },
    { "_id" : "ukiyo-e", "count" : 1 },
    { "_id" : "satire", "count" : 1 },
    { "_id" : "caricature", "count" : 1 }
  ]
}

{
  $unwind:
    {
      path: <field path>,
      includeArrayIndex: <string>,
      preserveNullAndEmptyArrays: <boolean>
    }
}

db.inventory.insertOne({ "_id" : 1, "item" : "ABC1", sizes: [ "S", "M", "L"] })

db.inventory.aggregate([ { $unwind: "$sizes" } ])

{ "_id" : 1, "item" : "ABC1", "sizes" : "S" }
{ "_id" : 1, "item" : "ABC1", "sizes" : "M" }
{ "_id" : 1, "item" : "ABC1", "sizes" : "L" }

{
  $bucket: {
      groupBy: <expression>,
      boundaries: [ <lowerbound1>, <lowerbound2>, ... ],
      default: <literal>,
      output: {
         <output1>: { <$accumulator expression> },
         ...
         <outputN>: { <$accumulator expression> }
      }
   }
}

db.artists.insertMany([
  { "_id" : 1, "last_name" : "Bernard", "first_name" : "Emil", "year_born" : 1868, "year_died" : 1941, "nationality" : "France" },
  { "_id" : 2, "last_name" : "Rippl-Ronai", "first_name" : "Joszef", "year_born" : 1861, "year_died" : 1927, "nationality" : "Hungary" },
  { "_id" : 3, "last_name" : "Ostroumova", "first_name" : "Anna", "year_born" : 1871, "year_died" : 1955, "nationality" : "Russia" },
  { "_id" : 4, "last_name" : "Van Gogh", "first_name" : "Vincent", "year_born" : 1853, "year_died" : 1890, "nationality" : "Holland" },
  { "_id" : 5, "last_name" : "Maurer", "first_name" : "Alfred", "year_born" : 1868, "year_died" : 1932, "nationality" : "USA" },
  { "_id" : 6, "last_name" : "Munch", "first_name" : "Edvard", "year_born" : 1863, "year_died" : 1944, "nationality" : "Norway" },
  { "_id" : 7, "last_name" : "Redon", "first_name" : "Odilon", "year_born" : 1840, "year_died" : 1916, "nationality" : "France" },
  { "_id" : 8, "last_name" : "Diriks", "first_name" : "Edvard", "year_born" : 1855, "year_died" : 1930, "nationality" : "Norway" }
])

db.artists.aggregate( [
  // First Stage
  {
    $bucket: {
      groupBy: "$year_born",                        // Field to group by
      boundaries: [ 1840, 1850, 1860, 1870, 1880 ], // Boundaries for the buckets
      default: "Other",                             // Bucket id for documents which do not fall into a bucket
      output: {                                     // Output for each bucket
        "count": { $sum: 1 },
        "artists" :
          {
            $push: {
              "name": { $concat: [ "$first_name", " ", "$last_name"] },
              "year_born": "$year_born"
            }
          }
      }
    }
  },
  // Second Stage
  {
    $match: { count: {$gt: 3} }
  }
] )

{ "_id" : 1860, "count" : 4, "artists" :
  [
    { "name" : "Emil Bernard", "year_born" : 1868 },
    { "name" : "Joszef Rippl-Ronai", "year_born" : 1861 },
    { "name" : "Alfred Maurer", "year_born" : 1868 },
    { "name" : "Edvard Munch", "year_born" : 1863 }
  ]
}

{
  $bucketAuto: {
      groupBy: <expression>,
      buckets: <number>,
      output: {
         <output1>: { <$accumulator expression> },
         ...
      }
      granularity: <string>
  }
}

db.artists.aggregate([
    { $bucketAuto: { groupBy: "$year_died", buckets: 4} }
])

{ "_id" : { "min" : 1890.0, "max" : 1927.0 }, "count" : 2 }
{ "_id" : { "min" : 1927.0, "max" : 1932.0 }, "count" : 2 }
{ "_id" : { "min" : 1932.0, "max" : 1944.0 }, "count" : 2 }
{ "_id" : { "min" : 1944.0, "max" : 1955.0 }, "count" : 2 }