我如何(在MongoDB)结合数据从多个集合到一个集合?
我可以使用地图减少，如果是，然后如何?
我非常感谢一些例子，因为我是一个新手。
当前回答
Mongorestore有这样一个特性，即在数据库中已经存在的数据之上追加数据，所以这个行为可以用于组合两个集合:
mongodump文物 collection2.rename(文物) mongorestore
还没有尝试过，但它可能比map/reduce方法执行得更快。
其他回答
代码片段。礼貌-关于堆栈溢出的多个帖子，包括这一篇。
db.cust.drop();
db.zip.drop();
db.cust.insert({cust_id:1, zip_id: 101});
db.cust.insert({cust_id:2, zip_id: 101});
db.cust.insert({cust_id:3, zip_id: 101});
db.cust.insert({cust_id:4, zip_id: 102});
db.cust.insert({cust_id:5, zip_id: 102});
db.zip.insert({zip_id:101, zip_cd:'AAA'});
db.zip.insert({zip_id:102, zip_cd:'BBB'});
db.zip.insert({zip_id:103, zip_cd:'CCC'});
mapCust = function() {
var values = {
cust_id: this.cust_id
};
emit(this.zip_id, values);
};
mapZip = function() {
var values = {
zip_cd: this.zip_cd
};
emit(this.zip_id, values);
};
reduceCustZip = function(k, values) {
var result = {};
values.forEach(function(value) {
var field;
if ("cust_id" in value) {
if (!("cust_ids" in result)) {
result.cust_ids = [];
}
result.cust_ids.push(value);
} else {
for (field in value) {
if (value.hasOwnProperty(field) ) {
result[field] = value[field];
}
};
}
});
return result;
};
db.cust_zip.drop();
db.cust.mapReduce(mapCust, reduceCustZip, {"out": {"reduce": "cust_zip"}});
db.zip.mapReduce(mapZip, reduceCustZip, {"out": {"reduce": "cust_zip"}});
db.cust_zip.find();
mapCZ = function() {
var that = this;
if ("cust_ids" in this.value) {
this.value.cust_ids.forEach(function(value) {
emit(value.cust_id, {
zip_id: that._id,
zip_cd: that.value.zip_cd
});
});
}
};
reduceCZ = function(k, values) {
var result = {};
values.forEach(function(value) {
var field;
for (field in value) {
if (value.hasOwnProperty(field)) {
result[field] = value[field];
}
}
});
return result;
};
db.cust_zip_joined.drop();
db.cust_zip.mapReduce(mapCZ, reduceCZ, {"out": "cust_zip_joined"});
db.cust_zip_joined.find().pretty();
var flattenMRCollection=function(dbName,collectionName) {
var collection=db.getSiblingDB(dbName)[collectionName];
var i=0;
var bulk=collection.initializeUnorderedBulkOp();
collection.find({ value: { $exists: true } }).addOption(16).forEach(function(result) {
print((++i));
//collection.update({_id: result._id},result.value);
bulk.find({_id: result._id}).replaceOne(result.value);
if(i%1000==0)
{
print("Executing bulk...");
bulk.execute();
bulk=collection.initializeUnorderedBulkOp();
}
});
bulk.execute();
};
flattenMRCollection("mydb","cust_zip_joined");
db.cust_zip_joined.find().pretty();
对聚合中的多个集合使用多个$查找
查询:
db.getCollection('servicelocations').aggregate([
{
$match: {
serviceLocationId: {
$in: ["36728"]
}
}
},
{
$lookup: {
from: "orders",
localField: "serviceLocationId",
foreignField: "serviceLocationId",
as: "orders"
}
},
{
$lookup: {
from: "timewindowtypes",
localField: "timeWindow.timeWindowTypeId",
foreignField: "timeWindowTypeId",
as: "timeWindow"
}
},
{
$lookup: {
from: "servicetimetypes",
localField: "serviceTimeTypeId",
foreignField: "serviceTimeTypeId",
as: "serviceTime"
}
},
{
$unwind: "$orders"
},
{
$unwind: "$serviceTime"
},
{
$limit: 14
}
])
结果:
{
"_id" : ObjectId("59c3ac4bb7799c90ebb3279b"),
"serviceLocationId" : "36728",
"regionId" : 1.0,
"zoneId" : "DXBZONE1",
"description" : "AL HALLAB REST EMIRATES MALL",
"locationPriority" : 1.0,
"accountTypeId" : 1.0,
"locationType" : "SERVICELOCATION",
"location" : {
"makani" : "",
"lat" : 25.119035,
"lng" : 55.198694
},
"deliveryDays" : "MTWRFSU",
"timeWindow" : [
{
"_id" : ObjectId("59c3b0a3b7799c90ebb32cde"),
"timeWindowTypeId" : "1",
"Description" : "MORNING",
"timeWindow" : {
"openTime" : "06:00",
"closeTime" : "08:00"
},
"accountId" : 1.0
},
{
"_id" : ObjectId("59c3b0a3b7799c90ebb32cdf"),
"timeWindowTypeId" : "1",
"Description" : "MORNING",
"timeWindow" : {
"openTime" : "09:00",
"closeTime" : "10:00"
},
"accountId" : 1.0
},
{
"_id" : ObjectId("59c3b0a3b7799c90ebb32ce0"),
"timeWindowTypeId" : "1",
"Description" : "MORNING",
"timeWindow" : {
"openTime" : "10:30",
"closeTime" : "11:30"
},
"accountId" : 1.0
}
],
"address1" : "",
"address2" : "",
"phone" : "",
"city" : "",
"county" : "",
"state" : "",
"country" : "",
"zipcode" : "",
"imageUrl" : "",
"contact" : {
"name" : "",
"email" : ""
},
"status" : "ACTIVE",
"createdBy" : "",
"updatedBy" : "",
"updateDate" : "",
"accountId" : 1.0,
"serviceTimeTypeId" : "1",
"orders" : [
{
"_id" : ObjectId("59c3b291f251c77f15790f92"),
"orderId" : "AQ18O1704264",
"serviceLocationId" : "36728",
"orderNo" : "AQ18O1704264",
"orderDate" : "18-Sep-17",
"description" : "AQ18O1704264",
"serviceType" : "Delivery",
"orderSource" : "Import",
"takenBy" : "KARIM",
"plannedDeliveryDate" : ISODate("2017-08-26T00:00:00.000Z"),
"plannedDeliveryTime" : "",
"actualDeliveryDate" : "",
"actualDeliveryTime" : "",
"deliveredBy" : "",
"size1" : 296.0,
"size2" : 3573.355,
"size3" : 240.811,
"jobPriority" : 1.0,
"cancelReason" : "",
"cancelDate" : "",
"cancelBy" : "",
"reasonCode" : "",
"reasonText" : "",
"status" : "",
"lineItems" : [
{
"ItemId" : "BNWB020",
"size1" : 15.0,
"size2" : 78.6,
"size3" : 6.0
},
{
"ItemId" : "BNWB021",
"size1" : 20.0,
"size2" : 252.0,
"size3" : 11.538
},
{
"ItemId" : "BNWB023",
"size1" : 15.0,
"size2" : 285.0,
"size3" : 16.071
},
{
"ItemId" : "CPMW112",
"size1" : 3.0,
"size2" : 25.38,
"size3" : 1.731
},
{
"ItemId" : "MMGW001",
"size1" : 25.0,
"size2" : 464.375,
"size3" : 46.875
},
{
"ItemId" : "MMNB218",
"size1" : 50.0,
"size2" : 920.0,
"size3" : 60.0
},
{
"ItemId" : "MMNB219",
"size1" : 50.0,
"size2" : 630.0,
"size3" : 40.0
},
{
"ItemId" : "MMNB220",
"size1" : 50.0,
"size2" : 416.0,
"size3" : 28.846
},
{
"ItemId" : "MMNB270",
"size1" : 50.0,
"size2" : 262.0,
"size3" : 20.0
},
{
"ItemId" : "MMNB302",
"size1" : 15.0,
"size2" : 195.0,
"size3" : 6.0
},
{
"ItemId" : "MMNB373",
"size1" : 3.0,
"size2" : 45.0,
"size3" : 3.75
}
],
"accountId" : 1.0
},
{
"_id" : ObjectId("59c3b291f251c77f15790f9d"),
"orderId" : "AQ137O1701240",
"serviceLocationId" : "36728",
"orderNo" : "AQ137O1701240",
"orderDate" : "18-Sep-17",
"description" : "AQ137O1701240",
"serviceType" : "Delivery",
"orderSource" : "Import",
"takenBy" : "KARIM",
"plannedDeliveryDate" : ISODate("2017-08-26T00:00:00.000Z"),
"plannedDeliveryTime" : "",
"actualDeliveryDate" : "",
"actualDeliveryTime" : "",
"deliveredBy" : "",
"size1" : 28.0,
"size2" : 520.11,
"size3" : 52.5,
"jobPriority" : 1.0,
"cancelReason" : "",
"cancelDate" : "",
"cancelBy" : "",
"reasonCode" : "",
"reasonText" : "",
"status" : "",
"lineItems" : [
{
"ItemId" : "MMGW001",
"size1" : 25.0,
"size2" : 464.38,
"size3" : 46.875
},
{
"ItemId" : "MMGW001-F1",
"size1" : 3.0,
"size2" : 55.73,
"size3" : 5.625
}
],
"accountId" : 1.0
},
{
"_id" : ObjectId("59c3b291f251c77f15790fd8"),
"orderId" : "AQ110O1705036",
"serviceLocationId" : "36728",
"orderNo" : "AQ110O1705036",
"orderDate" : "18-Sep-17",
"description" : "AQ110O1705036",
"serviceType" : "Delivery",
"orderSource" : "Import",
"takenBy" : "KARIM",
"plannedDeliveryDate" : ISODate("2017-08-26T00:00:00.000Z"),
"plannedDeliveryTime" : "",
"actualDeliveryDate" : "",
"actualDeliveryTime" : "",
"deliveredBy" : "",
"size1" : 60.0,
"size2" : 1046.0,
"size3" : 68.0,
"jobPriority" : 1.0,
"cancelReason" : "",
"cancelDate" : "",
"cancelBy" : "",
"reasonCode" : "",
"reasonText" : "",
"status" : "",
"lineItems" : [
{
"ItemId" : "MMNB218",
"size1" : 50.0,
"size2" : 920.0,
"size3" : 60.0
},
{
"ItemId" : "MMNB219",
"size1" : 10.0,
"size2" : 126.0,
"size3" : 8.0
}
],
"accountId" : 1.0
}
],
"serviceTime" : {
"_id" : ObjectId("59c3b07cb7799c90ebb32cdc"),
"serviceTimeTypeId" : "1",
"serviceTimeType" : "nohelper",
"description" : "",
"fixedTime" : 30.0,
"variableTime" : 0.0,
"accountId" : 1.0
}
}
Mongorestore有这样一个特性，即在数据库中已经存在的数据之上追加数据，所以这个行为可以用于组合两个集合:
mongodump文物 collection2.rename(文物) mongorestore
还没有尝试过，但它可能比map/reduce方法执行得更快。
从Mongo 4.4开始，我们可以通过将新的$unionWith聚合阶段与$group的新的$accumulator操作符耦合在聚合管道中实现这种连接:
// > db.users.find()
// [{ user: 1, name: "x" }, { user: 2, name: "y" }]
// > db.books.find()
// [{ user: 1, book: "a" }, { user: 1, book: "b" }, { user: 2, book: "c" }]
// > db.movies.find()
// [{ user: 1, movie: "g" }, { user: 2, movie: "h" }, { user: 2, movie: "i" }]
db.users.aggregate([
{ $unionWith: "books" },
{ $unionWith: "movies" },
{ $group: {
_id: "$user",
user: {
$accumulator: {
accumulateArgs: ["$name", "$book", "$movie"],
init: function() { return { books: [], movies: [] } },
accumulate: function(user, name, book, movie) {
if (name) user.name = name;
if (book) user.books.push(book);
if (movie) user.movies.push(movie);
return user;
},
merge: function(userV1, userV2) {
if (userV2.name) userV1.name = userV2.name;
userV1.books.concat(userV2.books);
userV1.movies.concat(userV2.movies);
return userV1;
},
lang: "js"
}
}
}}
])
// { _id: 1, user: { books: ["a", "b"], movies: ["g"], name: "x" } }
// { _id: 2, user: { books: ["c"], movies: ["h", "i"], name: "y" } }
$unionWith combines records from the given collection within documents already in the aggregation pipeline. After the 2 union stages, we thus have all users, books and movies records within the pipeline. We then $group records by $user and accumulate items using the $accumulator operator allowing custom accumulations of documents as they get grouped: the fields we're interested in accumulating are defined with accumulateArgs. init defines the state that will be accumulated as we group elements. the accumulate function allows performing a custom action with a record being grouped in order to build the accumulated state. For instance, if the item being grouped has the book field defined, then we update the books part of the state. merge is used to merge two internal states. It's only used for aggregations running on sharded clusters or when the operation exceeds memory limits.
在MongoDB中以“SQL UNION”的方式进行联合，可以在单个查询中使用聚合和查找。下面是我测试过的MongoDB 4.0的一个例子:
// Create employees data for testing the union.
db.getCollection('employees').insert({ name: "John", type: "employee", department: "sales" });
db.getCollection('employees').insert({ name: "Martha", type: "employee", department: "accounting" });
db.getCollection('employees').insert({ name: "Amy", type: "employee", department: "warehouse" });
db.getCollection('employees').insert({ name: "Mike", type: "employee", department: "warehouse" });
// Create freelancers data for testing the union.
db.getCollection('freelancers').insert({ name: "Stephany", type: "freelancer", department: "accounting" });
db.getCollection('freelancers').insert({ name: "Martin", type: "freelancer", department: "sales" });
db.getCollection('freelancers').insert({ name: "Doug", type: "freelancer", department: "warehouse" });
db.getCollection('freelancers').insert({ name: "Brenda", type: "freelancer", department: "sales" });
// Here we do a union of the employees and freelancers using a single aggregation query.
db.getCollection('freelancers').aggregate( // 1. Use any collection containing at least one document.
[
{ $limit: 1 }, // 2. Keep only one document of the collection.
{ $project: { _id: '$$REMOVE' } }, // 3. Remove everything from the document.
// 4. Lookup collections to union together.
{ $lookup: { from: 'employees', pipeline: [{ $match: { department: 'sales' } }], as: 'employees' } },
{ $lookup: { from: 'freelancers', pipeline: [{ $match: { department: 'sales' } }], as: 'freelancers' } },
// 5. Union the collections together with a projection.
{ $project: { union: { $concatArrays: ["$employees", "$freelancers"] } } },
// 6. Unwind and replace root so you end up with a result set.
{ $unwind: '$union' },
{ $replaceRoot: { newRoot: '$union' } }
]);
下面是它的工作原理:
Instantiate an aggregate out of any collection of your database that has at least one document in it. If you can't guarantee any collection of your database will not be empty, you can workaround this issue by creating in your database some sort of 'dummy' collection containing a single empty document in it that will be there specifically for doing union queries. Make the first stage of your pipeline to be { $limit: 1 }. This will strip all the documents of the collection except the first one. Strip all the fields of the remaining document by using a $project stage: { $project: { _id: '$$REMOVE' } } Your aggregate now contains a single, empty document. It's time to add lookups for each collection you want to union together. You may use the pipeline field to do some specific filtering, or leave localField and foreignField as null to match the whole collection. { $lookup: { from: 'collectionToUnion1', pipeline: [...], as: 'Collection1' } }, { $lookup: { from: 'collectionToUnion2', pipeline: [...], as: 'Collection2' } }, { $lookup: { from: 'collectionToUnion3', pipeline: [...], as: 'Collection3' } } You now have an aggregate containing a single document that contains 3 arrays like this: { Collection1: [...], Collection2: [...], Collection3: [...] } You can then merge them together into a single array using a $project stage along with the $concatArrays aggregation operator: { "$project" : { "Union" : { $concatArrays: ["$Collection1", "$Collection2", "$Collection3"] } } } You now have an aggregate containing a single document, into which is located an array that contains your union of collections. What remains to be done is to add an $unwind and a $replaceRoot stage to split your array into separate documents: { $unwind: "$Union" }, { $replaceRoot: { newRoot: "$Union" } } Voilà. You now have a result set containing the collections you wanted to union together. You can then add more stages to filter it further, sort it, apply skip() and limit(). Pretty much anything you want.
推荐文章
- MongoDB:如何找到安装的MongoDB的确切版本
- 如何使用mongoimport导入CSV文件?
- 在mongodb中存储日期/时间的最佳方法
- 如何排序mongodb与pymongo
- 如何在mongodb上导入。bson文件格式
- JSON文件的蒙古导入
- 如何删除mongodb中的数组元素?
- 修改MongoDB数据存储目录
- 在MongoDB中查找重复的记录
- 为什么MongoDB Java驱动在条件中使用随机数生成器?
- 在猫鼬，我如何排序的日期?(node . js)
- 将映像存储在MongoDB数据库中
- 重复Mongo ObjectId的可能性在两个不同的集合中生成?
- Redis比mongoDB快多少?
- 无法连接到服务器127.0.0.1:27017
