完善后端日志

backend/app/services/excel_storage_service.py

@@ -23,6 +23,8 @@ from sqlalchemy.ext.asyncio import AsyncSession
 from app.core.database.mysql import Base, mysql_db
 
 logger = logging.getLogger(__name__)
+# 设置该模块的日志级别
+logger.setLevel(logging.DEBUG)
 
 
 class ExcelStorageService:
@@ -174,12 +176,15 @@ class ExcelStorageService:
         }
 
         try:
+            logger.info(f"开始读取Excel文件: {file_path}")
             # 读取 Excel
             if sheet_name:
                 df = pd.read_excel(file_path, sheet_name=sheet_name, header=header_row)
             else:
                 df = pd.read_excel(file_path, header=header_row)
 
+            logger.info(f"Excel读取完成，行数: {len(df)}, 列数: {len(df.columns)}")
+
             if df.empty:
                 return {"success": False, "error": "Excel 文件为空"}
 
@@ -202,8 +207,10 @@ class ExcelStorageService:
             model_class = self._create_table_model(table_name, df.columns, column_types)
 
             # 创建表结构
+            logger.info(f"正在创建MySQL表: {table_name}")
             async with self.mysql_db.get_session() as session:
                 model_class.__table__.create(session.bind, checkfirst=True)
+            logger.info(f"MySQL表创建完成: {table_name}")
 
             # 插入数据
             records = []
@@ -231,11 +238,13 @@ class ExcelStorageService:
 
                 records.append(record)
 
+            logger.info(f"正在插入 {len(records)} 条数据到 MySQL...")
             # 批量插入
             async with self.mysql_db.get_session() as session:
                 for record in records:
                     session.add(model_class(**record))
                 await session.commit()
+            logger.info(f"数据插入完成: {len(records)} 条")
 
             results["row_count"] = len(records)
             logger.info(f"Excel 数据已存储到 MySQL 表 {table_name}，共 {len(records)} 行")
@@ -243,7 +252,7 @@ class ExcelStorageService:
             return results
 
         except Exception as e:
-            logger.error(f"存储 Excel 到 MySQL 失败: {str(e)}")
+            logger.error(f"存储 Excel 到 MySQL 失败: {str(e)}", exc_info=True)
             return {"success": False, "error": str(e)}
 
     async def store_structured_data(

backend/app/services/file_service.py

@@ -3,6 +3,7 @@
 """
 import os
 import shutil
+import logging
 from pathlib import Path
 from datetime import datetime
 from typing import Optional
@@ -10,6 +11,8 @@ import uuid
 
 from app.config import settings
 
+logger = logging.getLogger(__name__)
+
 
 class FileService:
     """文件服务类，负责文件的存储、读取和管理"""
@@ -17,6 +20,7 @@ class FileService:
     def __init__(self):
         self.upload_dir = Path(settings.UPLOAD_DIR)
         self._ensure_upload_dir()
+        logger.info(f"FileService 初始化，上传目录: {self.upload_dir}")
 
     def _ensure_upload_dir(self):
         """确保上传目录存在"""
@@ -56,6 +60,8 @@ class FileService:
         with open(file_path, 'wb') as f:
             f.write(file_content)
 
+        file_size = len(file_content)
+        logger.info(f"文件已保存: {filename} -> {file_path} ({file_size} bytes)")
         return str(file_path)
 
     def read_file(self, file_path: str) -> bytes:

backend/app/services/table_rag_service.py

@@ -126,26 +126,45 @@ class TableRAGService:
         }
 
         try:
-            # 1. 读取 Excel
+            # 1. 先检查 Excel 文件是否有效
+            logger.info(f"正在检查Excel文件: {file_path}")
+            try:
+                xls_file = pd.ExcelFile(file_path)
+                sheet_names = xls_file.sheet_names
+                logger.info(f"Excel文件工作表: {sheet_names}")
+                if not sheet_names:
+                    return {"success": False, "error": "Excel 文件没有工作表"}
+            except Exception as e:
+                logger.error(f"读取Excel文件失败: {file_path}, error: {e}")
+                return {"success": False, "error": f"无法读取Excel文件: {str(e)}"}
+
+            # 2. 读取 Excel
             if sheet_name:
+                # 验证指定的sheet_name是否存在
+                if sheet_name not in sheet_names:
+                    logger.warning(f"指定的工作表 '{sheet_name}' 不存在，使用第一个工作表: {sheet_names[0]}")
+                    sheet_name = sheet_names[0]
                 df = pd.read_excel(file_path, sheet_name=sheet_name, header=header_row)
             else:
                 df = pd.read_excel(file_path, header=header_row)
 
+            logger.info(f"读取到数据: {len(df)} 行, {len(df.columns)} 列")
+
             if df.empty:
                 return {"success": False, "error": "Excel 文件为空"}
 
             # 清理列名
             df.columns = [str(c) for c in df.columns]
-            table_name = excel_storage._sanitize_table_name(filename)
+            table_name = self.excel_storage._sanitize_table_name(filename)
             results["table_name"] = table_name
             results["field_count"] = len(df.columns)
+            logger.info(f"表名: {table_name}, 字段数: {len(df.columns)}")
 
-            # 2. 初始化 RAG (如果需要)
+            # 3. 初始化 RAG (如果需要)
             if not self.rag._initialized:
                 self.rag._init_vector_store()
 
-            # 3. 为每个字段生成描述并索引
+            # 4. 为每个字段生成描述并索引
             all_fields_data = {}
             for col in df.columns:
                 # 采样示例值
@@ -187,7 +206,8 @@ class TableRAGService:
                     logger.error(error_msg)
                     results["errors"].append(error_msg)
 
-            # 4. 存储到 MySQL
+            # 5. 存储到 MySQL
+            logger.info(f"开始存储到MySQL: {filename}")
             store_result = await self.excel_storage.store_excel(
                 file_path=file_path,
                 filename=filename,