MongoDB Samples

// MongoDB CRUD Operations
const { MongoClient, ObjectId } = require('mongodb');

class DatabaseService {
    constructor(uri = 'mongodb://localhost:27017') {
        this.client = new MongoClient(uri);
        this.dbName = 'myapp';
    }

    async connect() {
        await this.client.connect();
        this.db = this.client.db(this.dbName);
    }

    async disconnect() {
        await this.client.close();
    }

    // CREATE operations
    async insertOne(collection, document) {
        const result = await this.db.collection(collection).insertOne(document);
        return result.insertedId;
    }

    async insertMany(collection, documents) {
        const result = await this.db.collection(collection).insertMany(documents);
        return result.insertedIds;
    }

    // READ operations
    async findOne(collection, query = {}) {
        return await this.db.collection(collection).findOne(query);
    }

    async find(collection, query = {}, options = {}) {
        const cursor = this.db.collection(collection).find(query, options);
        return await cursor.toArray();
    }

    async findById(collection, id) {
        return await this.db.collection(collection).findOne({
            _id: new ObjectId(id)
        });
    }

    // UPDATE operations
    async updateOne(collection, query, update) {
        return await this.db.collection(collection).updateOne(query, update);
    }

    async updateMany(collection, query, update) {
        return await this.db.collection(collection).updateMany(query, update);
    }

    async replaceOne(collection, query, replacement) {
        return await this.db.collection(collection).replaceOne(query, replacement);
    }

    // DELETE operations
    async deleteOne(collection, query) {
        return await this.db.collection(collection).deleteOne(query);
    }

    async deleteMany(collection, query) {
        return await this.db.collection(collection).deleteMany(query);
    }

    // Aggregation
    async aggregate(collection, pipeline) {
        const cursor = this.db.collection(collection).aggregate(pipeline);
        return await cursor.toArray();
    }
}

// Example usage
async function example() {
    const db = new DatabaseService();
    await db.connect();

    // Insert a document
    const userId = await db.insertOne('users', {
        name: 'John Doe',
        email: '[email protected]',
        age: 30,
        createdAt: new Date()
    });

    // Find user
    const user = await db.findById('users', userId);

    // Update user
    await db.updateOne('users',
        { _id: userId },
        { $set: { age: 31 } }
    );

    await db.disconnect();
}

// MongoDB Aggregation Framework
class AnalyticsService {
    constructor(db) {
        this.db = db;
    }

    // Sales analytics example
    async getSalesAnalytics(startDate, endDate) {
        const pipeline = [
            {
                $match: {
                    createdAt: {
                        $gte: startDate,
                        $lte: endDate
                    }
                }
            },
            {
                $group: {
                    _id: {
                        year: { $year: '$createdAt' },
                        month: { $month: '$createdAt' },
                        day: { $dayOfMonth: '$createdAt' }
                    },
                    totalSales: { $sum: '$amount' },
                    orderCount: { $sum: 1 },
                    averageOrderValue: { $avg: '$amount' }
                }
            },
            {
                $sort: { '_id.year': 1, '_id.month': 1, '_id.day': 1 }
            }
        ];

        return await this.db.collection('orders').aggregate(pipeline).toArray();
    }

    // Customer segmentation
    async getCustomerSegments() {
        const pipeline = [
            {
                $lookup: {
                    from: 'orders',
                    localField: '_id',
                    foreignField: 'customerId',
                    as: 'orders'
                }
            },
            {
                $addFields: {
                    totalSpent: { $sum: '$orders.amount' },
                    orderCount: { $size: '$orders' },
                    lastOrderDate: { $max: '$orders.createdAt' }
                }
            },
            {
                $addFields: {
                    segment: {
                        $switch: {
                            branches: [
                                {
                                    case: { $gte: ['$totalSpent', 1000] },
                                    then: 'VIP'
                                },
                                {
                                    case: { $gte: ['$totalSpent', 500] },
                                    then: 'Premium'
                                },
                                {
                                    case: { $gte: ['$totalSpent', 100] },
                                    then: 'Regular'
                                }
                            ],
                            default: 'Basic'
                        }
                    }
                }
            },
            {
                $group: {
                    _id: '$segment',
                    customers: { $sum: 1 },
                    totalRevenue: { $sum: '$totalSpent' },
                    avgCustomerValue: { $avg: '$totalSpent' }
                }
            }
        ];

        return await this.db.collection('customers').aggregate(pipeline).toArray();
    }

    // Product performance analytics
    async getProductPerformance() {
        const pipeline = [
            { $unwind: '$items' },
            {
                $group: {
                    _id: '$items.productId',
                    totalSold: { $sum: '$items.quantity' },
                    revenue: { $sum: { $multiply: ['$items.quantity', '$items.price'] } },
                    orderCount: { $sum: 1 }
                }
            },
            {
                $lookup: {
                    from: 'products',
                    localField: '_id',
                    foreignField: '_id',
                    as: 'product'
                }
            },
            { $unwind: '$product' },
            {
                $addFields: {
                    profitMargin: {
                        $multiply: [
                            { $divide: [{ $subtract: ['$revenue', '$product.cost'] }, '$revenue'] },
                            100
                        ]
                    }
                }
            },
            {
                $sort: { revenue: -1 }
            }
        ];

        return await this.db.collection('orders').aggregate(pipeline).toArray();
    }

    // Time series analysis
    async getTimeSeriesAnalysis(collection, dateField, interval = 'day') {
        const intervalFormats = {
            day: { $dateToString: { format: '%Y-%m-%d', date: dateField } },
            month: { $dateToString: { format: '%Y-%m', date: dateField } },
            year: { $dateToString: { format: '%Y', date: dateField } }
        };

        const pipeline = [
            {
                $group: {
                    _id: intervalFormats[interval],
                    count: { $sum: 1 },
                    avgValue: { $avg: '$value' },
                    totalValue: { $sum: '$value' }
                }
            },
            { $sort: { _id: 1 } }
        ];

        return await this.db.collection(collection).aggregate(pipeline).toArray();
    }
}

// MongoDB Indexing Strategies
class IndexingService {
    constructor(db) {
        this.db = db;
    }

    async createIndexes() {
        const collections = ['users', 'products', 'orders', 'reviews'];

        // Single field indexes
        await this.db.collection('users').createIndex({ email: 1 }, { unique: true });
        await this.db.collection('users').createIndex({ username: 1 }, { unique: true });

        // Compound indexes
        await this.db.collection('products').createIndex(
            { category: 1, price: 1, rating: -1 }
        );
        await this.db.collection('orders').createIndex(
            { customerId: 1, createdAt: -1 }
        );

        // Text indexes for search functionality
        await this.db.collection('products').createIndex(
            { name: 'text', description: 'text' },
            {
                weights: { name: 10, description: 1 },
                name: 'product_search_index'
            }
        );

        // Geospatial indexes
        await this.db.collection('users').createIndex(
            { location: '2dsphere' }
        );

        // TTL (Time To Live) indexes for automatic data expiration
        await this.db.collection('sessions').createIndex(
            { expiresAt: 1 },
            { expireAfterSeconds: 0 }
        );

        // Partial indexes (only index documents that meet criteria)
        await this.db.collection('users').createIndex(
            { emailVerificationToken: 1 },
            {
                partialFilterExpression: {
                    emailVerificationToken: { $exists: true }
                }
            }
        );

        // Sparse indexes (only index documents with the field)
        await this.db.collection('reviews').createIndex(
            { helpfulVotes: 1 },
            { sparse: true }
        );
    }

    async analyzeIndexUsage(collectionName) {
        const stats = await this.db.collection(collectionName).aggregate([
            { $indexStats: {} },
            {
                $project: {
                    name: 1,
                    usageCount: '$ops.accesses.ops',
                    lastUsed: '$ops.accesses.last'
                }
            }
        ]).toArray();

        return stats;
    }

    async explainQuery(collectionName, query) {
        return await this.db.collection(collectionName)
            .find(query)
            .explain('executionStats');
    }

    async createOptimizedIndexes() {
        // Covering index example (includes all fields needed for query)
        await this.db.collection('products').createIndex(
            { category: 1, price: 1 },
            {
                name: 'category_price_covering',
                background: true
            }
        );

        // Index with collation for case-insensitive search
        await this.db.collection('users').createIndex(
            { name: 1 },
            {
                collation: { locale: 'en', strength: 2 },
                name: 'name_case_insensitive'
            }
        );

        // Wildcard index (indexes all fields except _id)
        await this.db.collection('logs').createIndex(
            { '$**': 1 },
            { name: 'all_fields_wildcard' }
        );
    }

    async dropUnusedIndexes() {
        const collections = await this.db.listCollections().toArray();

        for (const collection of collections) {
            const indexes = await this.db.collection(collection.name)
                .listIndexes()
                .toArray();

            const indexStats = await this.analyzeIndexUsage(collection.name);
            const usedIndexes = new Set(indexStats.map(stat => stat.name));

            for (const index of indexes) {
                if (index.name !== '_id_' && !usedIndexes.has(index.name)) {
                    console.log('Dropping unused index: ' + index.name);
                    await this.db.collection(collection.name).dropIndex(index.name);
                }
            }
        }
    }
}

// MongoDB Schema Design Patterns

// 1. Embedding Pattern - One-to-One Relationship
const userSchema = {
    _id: ObjectId,
    name: String,
    email: String,
    profile: {
        firstName: String,
        lastName: String,
        avatar: String,
        bio: String,
        preferences: {
            theme: String,
            notifications: Boolean,
            language: String
        }
    },
    createdAt: Date,
    updatedAt: Date
};

// 2. Embedding Pattern - One-to-Few Relationship
const productSchema = {
    _id: ObjectId,
    name: String,
    description: String,
    price: Number,
    category: String,
    images: [
        {
            url: String,
            alt: String,
            isPrimary: Boolean
        }
    ],
    tags: [String],
    variants: [
        {
            name: String,
            sku: String,
            price: Number,
            inventory: Number
        }
    ],
    createdAt: Date
};

// 3. Referencing Pattern - One-to-Many Relationship
const orderSchema = {
    _id: ObjectId,
    customerId: ObjectId, // Reference to users collection
    orderNumber: String,
    status: String,
    items: [
        {
            productId: ObjectId, // Reference to products collection
            quantity: Number,
            price: Number,
            customizations: Object
        }
    ],
    shippingAddress: {
        street: String,
        city: String,
        state: String,
        zipCode: String,
        country: String
    },
    totalAmount: Number,
    createdAt: Date
};

// 4. Extended Reference Pattern
const userOrderSchema = {
    _id: ObjectId,
    customerId: ObjectId,
    orderNumber: String,
    status: String,
    items: [
        {
            productId: ObjectId,
            quantity: Number,
            price: Number,
            // Embedded frequently accessed product data
            productInfo: {
                name: String,
                imageUrl: String,
                category: String
            }
        }
    ],
    totalAmount: Number,
    createdAt: Date
};

// 5. Bucket Pattern - Time Series Data
const sensorDataSchema = {
    _id: ObjectId,
    sensorId: ObjectId,
    startDate: Date,
    endDate: Date,
    count: Number,
    measurements: {
        min: Number,
        max: Number,
        sum: Number,
        avg: Number
    },
    data: [
        {
            timestamp: Date,
            value: Number,
            quality: String
        }
    ]
};

// 6. Computed Pattern
const productStatsSchema = {
    _id: ObjectId,
    productId: ObjectId,
    totalViews: Number,
    totalPurchases: Number,
    averageRating: Number,
    reviewCount: Number,
    conversionRate: Number,
    lastUpdated: Date
};

// 7. Subset Pattern - Frequently accessed data subset
const userDashboardSchema = {
    _id: ObjectId,
    userId: ObjectId,
    recentOrders: [
        {
            orderId: ObjectId,
            orderNumber: String,
            totalAmount: Number,
            status: String,
            createdAt: Date
        }
    ],
    favoriteProducts: [
        {
            productId: ObjectId,
            name: String,
            imageUrl: String,
            price: Number
        }
    ],
    notifications: [
        {
            type: String,
            message: String,
            isRead: Boolean,
            createdAt: Date
        }
    ],
    lastUpdated: Date
};

// Schema validation rules
const createValidationRules = () => {
    return {
        $jsonSchema: {
            bsonType: 'object',
            required: ['name', 'email', 'createdAt'],
            properties: {
                name: {
                    bsonType: 'string',
                    description: 'must be a string and is required',
                    minLength: 2,
                    maxLength: 50
                },
                email: {
                    bsonType: 'string',
                    pattern: '^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$',
                    description: 'must be a valid email address'
                },
                age: {
                    bsonType: 'int',
                    minimum: 0,
                    maximum: 150,
                    description: 'must be an integer in [0, 150]'
                },
                status: {
                    enum: ['active', 'inactive', 'suspended'],
                    description: 'can only be one of the enum values'
                }
            }
        }
    };
};

# MongoDB Sharded Cluster Configuration

version: '3.8'

services:
  # Config servers (replica set)
  config-server-1:
    image: mongo:6.0
    command: mongod --configsvr --replSet config-replica-set --bind_ip_all
    ports:
      - "27019:27019"
    volumes:
      - config-server-1-data:/data/db

  config-server-2:
    image: mongo:6.0
    command: mongod --configsvr --replSet config-replica-set --bind_ip_all
    ports:
      - "27020:27019"
    volumes:
      - config-server-2-data:/data/db

  config-server-3:
    image: mongo:6.0
    command: mongod --configsvr --replSet config-replica-set --bind_ip_all
    ports:
      - "27021:27019"
    volumes:
      - config-server-3-data:/data/db

  # Shard servers (replica sets)
  shard1-server-1:
    image: mongo:6.0
    command: mongod --shardsvr --replSet shard1-replica-set --bind_ip_all
    ports:
      - "27022:27017"
    volumes:
      - shard1-server-1-data:/data/db

  shard1-server-2:
    image: mongo:6.0
    command: mongod --shardsvr --replSet shard1-replica-set --bind_ip_all
    ports:
      - "27023:27017"
    volumes:
      - shard1-server-2-data:/data/db

  shard2-server-1:
    image: mongo:6.0
    command: mongod --shardsvr --replSet shard2-replica-set --bind_ip_all
    ports:
      - "27024:27017"
    volumes:
      - shard2-server-1-data:/data/db

  shard2-server-2:
    image: mongo:6.0
    command: mongod --shardsvr --replSet shard2-replica-set --bind_ip_all
    ports:
      - "27025:27017"
    volumes:
      - shard2-server-2-data:/data/db

  # Mongos router
  mongos:
    image: mongo:6.0
    command: mongos --configdb config-replica-set/config-server-1:27019,config-server-2:27019,config-server-3:27019 --bind_ip_all --port 27017
    ports:
      - "27017:27017"
    depends_on:
      - config-server-1
      - config-server-2
      - config-server-3
      - shard1-server-1
      - shard1-server-2
      - shard2-server-1
      - shard2-server-2

  # Cluster initialization
  cluster-setup:
    image: mongo:6.0
    depends_on:
      - mongos
    command: |
      sh -c "
      sleep 30

      # Initialize config server replica set
      mongo --host config-server-1:27019 --eval '
      rs.initiate({
        _id: "config-replica-set",
        configsvr: true,
        members: [
          { _id: 0, host: "config-server-1:27019" },
          { _id: 1, host: "config-server-2:27019" },
          { _id: 2, host: "config-server-3:27019" }
        ]
      })'

      sleep 10

      # Initialize shard1 replica set
      mongo --host shard1-server-1:27022 --eval '
      rs.initiate({
        _id: "shard1-replica-set",
        members: [
          { _id: 0, host: "shard1-server-1:27022" },
          { _id: 1, host: "shard1-server-2:27023" }
        ]
      })'

      # Initialize shard2 replica set
      mongo --host shard2-server-1:27024 --eval '
      rs.initiate({
        _id: "shard2-replica-set",
        members: [
          { _id: 0, host: "shard2-server-1:27024" },
          { _id: 1, host: "shard2-server-2:27025" }
        ]
      })'

      sleep 20

      # Add shards to cluster
      mongo --host mongos:27017 --eval '
      sh.addShard("shard1-replica-set/shard1-server-1:27022,shard1-server-2:27023")
      sh.addShard("shard2-replica-set/shard2-server-1:27024,shard2-server-2:27025")

      # Enable sharding for database
      sh.enableSharding("myapp")

      # Shard collections
      sh.shardCollection("myapp.users", { "_id": "hashed" })
      sh.shardCollection("myapp.orders", { "customerId": 1, "createdAt": 1 })
      sh.shardCollection("myapp.products", { "category": 1 })
      '"

volumes:
  config-server-1-data:
  config-server-2-data:
  config-server-3-data:
  shard1-server-1-data:
  shard1-server-2-data:
  shard2-server-1-data:
  shard2-server-2-data: