feat(backend): 更新核心模块和文件处理

- 更新配置模块 (config.py)
- 更新数据库连接 (database.py)
- 更新主应用入口 (main.py)
- 更新数据模型 (models.py)
- 更新基础 Schema (base.py)
- 更新文件处理器 (docx, excel, pdf)
- 更新 Dockerfile

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

backend/app/core/config.py

@@ -4,7 +4,7 @@ Application Configuration
 
 from functools import lru_cache
 from pydantic_settings import BaseSettings
-from pydantic import Field
+from pydantic import Field, field_validator
 
 
 class Settings(BaseSettings):
@@ -15,12 +15,16 @@ class Settings(BaseSettings):
     DEBUG: bool = True
     HOST: str = "0.0.0.0"
     PORT: int = 8000
+    ALLOWED_ORIGINS: str = Field(
+        default="*",
+        description="Comma-separated list of allowed CORS origins"
+    )
 
     # Database - 使用 SQLite 进行开发/测试
     # 生产环境可切换为 PostgreSQL
     DATABASE_URL: str = Field(
-        default="sqlite:///./ygdataset.db",
-        description="Database connection URL (sqlite:// or postgresql+asyncpg://)"
+        default="sqlite+aiosqlite:///./ygdataset.db",
+        description="Database connection URL (sqlite+aiosqlite:// or postgresql+asyncpg://)"
     )
     DATABASE_URL_SYNC: str = Field(
         default="sqlite:///./ygdataset.db",
@@ -38,8 +42,31 @@ class Settings(BaseSettings):
     DEFAULT_MODEL_PROVIDER: str = "openai"
     DEFAULT_MODEL_NAME: str = "gpt-4o-mini"
 
+    # Security
+    SECRET_KEY: str = Field(
+        default="your-secret-key-change-in-production",
+        description="Secret key for JWT and other security operations"
+    )
+    API_KEY_HEADER: str = "X-API-Key"
+
+    # Pagination
+    DEFAULT_PAGE_SIZE: int = 20
+    MAX_PAGE_SIZE: int = 100
+
+    # Logging
+    LOG_LEVEL: str = "INFO"
+
+    @field_validator("MAX_FILE_SIZE")
+    @classmethod
+    def validate_max_file_size(cls, v: int) -> int:
+        """Validate max file size (max 500MB)"""
+        if v > 500 * 1024 * 1024:
+            return 500 * 1024 * 1024
+        return v
+
     class Config:
         env_file = ".env"
+        env_file_encoding = "utf-8"
         extra = "allow"
 
 
@@ -47,3 +74,7 @@ class Settings(BaseSettings):
 def get_settings() -> Settings:
     """Get cached settings"""
     return Settings()
+
+
+# Create global settings instance
+settings = get_settings()

backend/app/core/database.py

@@ -2,25 +2,32 @@
 Database Configuration and Session Management
 支持 SQLite 和 PostgreSQL
 """
-
+import logging
+from contextlib import asynccontextmanager
+from typing import AsyncGenerator
 from sqlalchemy.ext.asyncio import AsyncSession, create_async_engine, async_sessionmaker
 from sqlalchemy.orm import DeclarativeBase
-from sqlalchemy import create_engine
+from sqlalchemy import create_engine, event
+from sqlalchemy.pool import NullPool
+
 from app.core.config import get_settings
 
+logger = logging.getLogger(__name__)
 settings = get_settings()
 
 
 def get_engine_config():
     """根据数据库类型返回引擎配置"""
     if settings.DATABASE_URL.startswith("sqlite"):
-        return {"echo": settings.DEBUG}
+        return {"echo": settings.DEBUG, "poolclass": NullPool}
     else:
         return {
             "echo": settings.DEBUG,
             "pool_pre_ping": True,
             "pool_size": 10,
             "max_overflow": 20,
+            "pool_recycle": 3600,
+            "pool_timeout": 30,
         }
 
 
@@ -30,14 +37,14 @@ async_engine = create_async_engine(
     **get_engine_config()
 )
 
-# Sync engine for migrations
+# Sync engine for migrations (use NullPool for SQLite)
 sync_engine = create_engine(
     settings.DATABASE_URL_SYNC,
     echo=settings.DEBUG,
     pool_pre_ping=True,
+    poolclass=NullPool if settings.DATABASE_URL_SYNC.startswith("sqlite") else None,
 )
 
-
 # Async session factory
 AsyncSessionLocal = async_sessionmaker(
     async_engine,
@@ -55,8 +62,31 @@ class Base(DeclarativeBase):
 
 async def init_db():
     """Initialize database tables"""
+    logger.info("Initializing database...")
     async with async_engine.begin() as conn:
         await conn.run_sync(Base.metadata.create_all)
+    logger.info("Database initialized successfully")
+
+
+async def close_db():
+    """Close database connections"""
+    logger.info("Closing database connections...")
+    await async_engine.dispose()
+    logger.info("Database connections closed")
+
+
+@asynccontextmanager
+async def get_db_session() -> AsyncGenerator[AsyncSession, None]:
+    """Context manager for database sessions with automatic cleanup"""
+    session = AsyncSessionLocal()
+    try:
+        yield session
+    except Exception as e:
+        logger.error(f"Database session error: {str(e)}")
+        await session.rollback()
+        raise
+    finally:
+        await session.close()
 
 
 async def get_db() -> AsyncSession:
@@ -64,5 +94,9 @@ async def get_db() -> AsyncSession:
     async with AsyncSessionLocal() as session:
         try:
             yield session
+        except Exception as e:
+            logger.error(f"Database error in dependency: {str(e)}")
+            await session.rollback()
+            raise
         finally:
             await session.close()