feat: support mongo connector

coco.yml

@@ -319,6 +319,11 @@ connector:
     interval: 10s
     queue:
       name: indexing_documents
+  mongodb:  
+    enabled: true  
+    interval: 30s  
+    queue:  
+      name: indexing_documents 
   notion:
     enabled: true
     interval: 10s

config/setup/en-US/connector.tpl

@@ -229,4 +229,59 @@ POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/n
     }
   },
   "builtin": true
-}
+}
+POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/postgresql
+{
+  "id" : "postgresql",
+  "created" : "2025-08-14T00:00:00.000000+08:00",
+  "updated" : "2025-08-14T00:00:00.000000+08:00",
+  "name" : "PostgreSQL Connector",
+  "description" : "Fetch data from PostgreSQL database.",
+  "category" : "database",
+  "icon" : "/assets/icons/connector/postgresql/icon.png",
+  "tags" : [
+    "sql",
+    "storage",
+    "database"
+  ],
+  "url" : "http://coco.rs/connectors/postgresql",
+  "assets" : {
+    "icons" : {
+      "default" : "/assets/icons/connector/postgresql/icon.png"
+    }
+  },
+  "builtin": true
+}
+POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/mongodb
+{
+  "id" : "mongodb",
+  "created" : "2025-01-12T00:00:00.000000+08:00",
+  "updated" : "2025-01-12T00:00:00.000000+08:00",
+  "name" : "MongoDB Connector",
+  "description" : "Powerful MongoDB database connector supporting incremental/full sync, field mapping, pagination, cluster type optimization, authentication database configuration, projection pushdown, index hints, and other advanced features. Supports standalone, replica set, and sharded cluster deployments.",
+  "category" : "database",
+  "icon" : "/assets/icons/connector/mongodb/icon.png",
+  "tags" : [
+    "nosql",
+    "storage",
+    "database",
+    "document",
+    "mongodb",
+    "incremental_sync",
+    "field_mapping",
+    "pagination",
+    "cluster_optimization",
+    "authentication",
+    "performance"
+  ],
+  "url" : "http://coco.rs/connectors/mongodb",
+  "assets" : {
+    "icons" : {
+      "default" : "/assets/icons/connector/mongodb/icon.png",
+      "collection" : "/assets/icons/connector/mongodb/collection.png",
+      "document" : "/assets/icons/connector/mongodb/document.png",
+      "replica_set" : "/assets/icons/connector/mongodb/replica_set.png",
+      "sharded" : "/assets/icons/connector/mongodb/sharded.png"
+  },
+  "builtin": true
+}

config/setup/zh-CN/connector.tpl

@@ -229,4 +229,60 @@ POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/n
     }
   },
   "builtin": true
-}
+}
+POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/postgresql
+{
+  "id" : "postgresql",
+  "created" : "2025-08-14T00:00:00.000000+08:00",
+  "updated" : "2025-08-14T00:00:00.000000+08:00",
+  "name" : "PostgreSQL 连接器",
+  "description" : "提取 PostgreSQL 数据库数据。",
+  "category" : "database",
+  "icon" : "/assets/icons/connector/postgresql/icon.png",
+  "tags" : [
+    "sql",
+    "storage",
+    "database"
+  ],
+  "url" : "http://coco.rs/connectors/postgresql",
+  "assets" : {
+     "icons" : {
+       "default" : "/assets/icons/connector/postgresql/icon.png"
+     }
+  },
+  "builtin": true
+}
+POST $[[SETUP_INDEX_PREFIX]]connector$[[SETUP_SCHEMA_VER]]/$[[SETUP_DOC_TYPE]]/mongodb
+{
+  "id" : "mongodb",
+  "created" : "2025-01-12T00:00:00.000000+08:00",
+  "updated" : "2025-01-12T00:00:00.000000+08:00",
+  "name" : "MongoDB 连接器",
+  "description" : "强大的MongoDB数据库连接器，支持增量/全量同步、字段映射、分页处理、集群类型优化、认证数据库配置、投影下推、索引提示等高级功能。支持单机、复制集、分片集群部署。",
+  "category" : "database",
+  "icon" : "/assets/icons/connector/mongodb/icon.png",
+  "tags" : [
+    "nosql",
+    "storage",
+    "database",
+    "document",
+    "mongodb",
+    "incremental_sync",
+    "field_mapping",
+    "pagination",
+    "cluster_optimization",
+    "authentication",
+    "performance"
+  ],
+  "url" : "http://coco.rs/connectors/mongodb",
+  "assets" : {
+    "icons" : {
+      "default" : "/assets/icons/connector/mongodb/icon.png",
+      "collection" : "/assets/icons/connector/mongodb/collection.png",
+      "document" : "/assets/icons/connector/mongodb/document.png",
+      "replica_set" : "/assets/icons/connector/mongodb/replica_set.png",
+      "sharded" : "/assets/icons/connector/mongodb/sharded.png"
+    }
+  },
+  "builtin": true
+} 

docker/init-mongo.js

@@ -0,0 +1,41 @@
+// MongoDB initialization script for testing  
+db = db.getSiblingDB('coco_test');  
+
+// Create test user  
+db.createUser({  
+  user: 'coco_test',  
+  pwd: 'test_password',  
+  roles: [  
+    {  
+      role: 'readWrite',  
+      db: 'coco_test'  
+    }  
+  ]  
+});  
+
+// Create test collections with sample data  
+db.articles.insertMany([  
+  {  
+    title: "Sample Article 1",  
+    content: "This is sample content for testing",  
+    category: "Technology",  
+    tags: ["mongodb", "database"],  
+    url: "https://example.com/article1",  
+    updated_at: new Date(),  
+    status: "published"  
+  },  
+  {  
+    title: "Sample Article 2",   
+    content: "Another sample content for testing",  
+    category: "Programming",  
+    tags: ["go", "backend"],  
+    url: "https://example.com/article2",  
+    updated_at: new Date(),  
+    status: "draft"  
+  }  
+]);  
+
+// Create indexes for better performance  
+db.articles.createIndex({ "updated_at": 1 });  
+db.articles.createIndex({ "status": 1 });  
+db.articles.createIndex({ "category": 1 });

docker/mongodb-test.yml

@@ -0,0 +1,36 @@
+version: '3.8'  
+
+services:  
+  mongodb:  
+    image: mongo:7.0  
+    container_name: coco-mongodb-test  
+    ports:  
+      - "27017:27017"  
+    environment:  
+      MONGO_INITDB_ROOT_USERNAME: admin  
+      MONGO_INITDB_ROOT_PASSWORD: password  
+      MONGO_INITDB_DATABASE: coco_test  
+    volumes:  
+      - mongodb_data:/data/db  
+      - ./init-mongo.js:/docker-entrypoint-initdb.d/init-mongo.js:ro  
+    networks:  
+      - coco-test  
+
+  mongodb-replica:  
+    image: mongo:7.0  
+    container_name: coco-mongodb-replica-test  
+    ports:  
+      - "27018:27017"  
+    command: mongod --replSet rs0 --bind_ip_all  
+    volumes:  
+      - mongodb_replica_data:/data/db  
+    networks:  
+      - coco-test  
+
+volumes:  
+  mongodb_data:  
+  mongodb_replica_data:  
+
+networks:  
+  coco-test:  
+    driver: bridge

examples/mongodb.yml

@@ -0,0 +1,22 @@
+# MongoDB Connector Default Configuration  
+mongodb:  
+  # Default connection settings  
+  default_timeout: "30s"  
+  default_batch_size: 1000  
+  default_max_pool_size: 10  
+
+  # Default sync settings  
+  default_sync_strategy: "full"  
+
+  # Performance tuning  
+  max_concurrent_collections: 5  
+  memory_gc_interval: 10000  
+
+  # Retry settings  
+  connection_retry_attempts: 3  
+  connection_retry_delay: "30s"  
+
+  # Logging  
+  log_level: "info"  
+  log_slow_queries: true  
+  slow_query_threshold: "5s"

plugins/connectors/mongodb/config.go

@@ -0,0 +1,141 @@
+/* Copyright © INFINI LTD. All rights reserved.
+ * Web: https://infinilabs.com
+ * Email: hello#infini.ltd */
+
+package mongodb
+
+import (
+	"fmt"
+	"time"
+)
+
+// Config defines the configuration for the MongoDB connector
+type Config struct {
+	// Connection configuration
+	ConnectionURI string `config:"connection_uri"`
+	Database      string `config:"database"`
+	AuthDatabase  string `config:"auth_database"` // Authentication database (e.g., "admin")
+	ClusterType   string `config:"cluster_type"`   // Cluster type: "standalone", "replica_set", "sharded"
+
+	// Collections configuration
+	Collections []CollectionConfig `config:"collections"`
+
+	// Pagination configuration
+	Pagination bool `config:"pagination"`
+	PageSize   int  `config:"page_size"`
+
+	// Last modified field for incremental sync
+	LastModifiedField string `config:"last_modified_field"`
+
+	// Performance optimization configuration
+	BatchSize   int    `config:"batch_size"`
+	Timeout     string `config:"timeout"`
+	MaxPoolSize int    `config:"max_pool_size"`
+
+	// Sync strategy
+	SyncStrategy string `config:"sync_strategy"`
+
+	// Field mapping configuration
+	FieldMapping *FieldMappingConfig `config:"field_mapping"`
+
+	// Advanced query optimization
+	EnableProjection bool `config:"enable_projection"` // Enable projection pushdown
+	EnableIndexHint  bool `config:"enable_index_hint"` // Enable index hints for better performance
+}
+
+type CollectionConfig struct {
+	Name           string                 `config:"name"`
+	Filter         map[string]interface{} `config:"filter"`
+	TitleField     string                 `config:"title_field"`
+	ContentField   string                 `config:"content_field"`
+	CategoryField  string                 `config:"category_field"`
+	TagsField      string                 `config:"tags_field"`
+	URLField       string                 `config:"url_field"`
+	TimestampField string                 `config:"timestamp_field"`
+}
+
+// FieldMappingConfig defines the field mapping configuration
+type FieldMappingConfig struct {
+	Enabled bool                    `config:"enabled"`
+	Mapping map[string]interface{} `config:"mapping"`
+}
+
+func (p *Plugin) setDefaultConfig(config *Config) {
+	if config.BatchSize <= 0 {
+		config.BatchSize = 1000
+	}
+	if config.MaxPoolSize <= 0 {
+		config.MaxPoolSize = 10
+	}
+	if config.Timeout == "" {
+		config.Timeout = "30s"
+	}
+	if config.SyncStrategy == "" {
+		config.SyncStrategy = "full"
+	}
+	if config.PageSize <= 0 {
+		config.PageSize = 500
+	}
+	if config.AuthDatabase == "" {
+		config.AuthDatabase = "admin" // Default to admin database for authentication
+	}
+	if config.ClusterType == "" {
+		config.ClusterType = "standalone" // Default to standalone MongoDB instance
+	}
+	if config.FieldMapping == nil {
+		config.FieldMapping = &FieldMappingConfig{
+			Enabled: false,
+			Mapping: make(map[string]interface{}),
+		}
+	}
+
+	// Enable advanced optimizations by default for better performance
+	if !config.EnableProjection {
+		config.EnableProjection = true
+	}
+	if !config.EnableIndexHint {
+		config.EnableIndexHint = true
+	}
+}
+
+func (p *Plugin) validateConfig(config *Config) error {
+	if config.ConnectionURI == "" {
+		return fmt.Errorf("connection_uri must be specified")
+	}
+
+	if config.Database == "" {
+		return fmt.Errorf("database must be specified")
+	}
+
+	if len(config.Collections) == 0 {
+		return fmt.Errorf("at least one collection must be configured")
+	}
+
+	for i, coll := range config.Collections {
+		if coll.Name == "" {
+			return fmt.Errorf("collection[%d].name is required", i)
+		}
+	}
+
+	if config.BatchSize < 0 {
+		return fmt.Errorf("batch_size must be positive")
+	}
+
+	if config.MaxPoolSize < 0 {
+		return fmt.Errorf("max_pool_size must be positive")
+	}
+
+	if config.PageSize < 0 {
+		return fmt.Errorf("page_size must be positive")
+	}
+
+	if config.SyncStrategy != "" && config.SyncStrategy != "full" && config.SyncStrategy != "incremental" {
+		return fmt.Errorf("sync_strategy must be 'full' or 'incremental'")
+	}
+
+	if config.ClusterType != "" && config.ClusterType != "standalone" && config.ClusterType != "replica_set" && config.ClusterType != "sharded" {
+		return fmt.Errorf("cluster_type must be 'standalone', 'replica_set', or 'sharded'")
+	}
+
+	return nil
+}