feat(backend): 完善日志系统，支持按日期分目录存储

- 实现 logs/YYYY-MM-DD/ 日期文件夹结构
- 添加 success.log 和 failure.log 专用日志
- 使用 TimedRotatingFileHandler 实现按天切割
- 添加 log_success 和 log_failure 便捷函数
- 集成 markitdown 进行文件转换
- 优化文件存储路径，按项目ID分类存储

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

backend/app/core/logging.py

@@ -4,8 +4,9 @@ Logging Configuration
 """
 import logging
 import sys
+from datetime import datetime
 from typing import Any
-from logging.handlers import RotatingFileHandler
+from logging.handlers import RotatingFileHandler, TimedRotatingFileHandler
 from pathlib import Path
 from app.core.config import get_settings
 
@@ -15,6 +16,18 @@ settings = get_settings()
 LOG_DIR = Path("./logs")
 LOG_DIR.mkdir(exist_ok=True)
 
+# 日期格式
+LOG_DATE = datetime.now().strftime("%Y-%m-%d")
+
+# 当天的日志目录
+CURRENT_LOG_DIR = LOG_DIR / LOG_DATE
+CURRENT_LOG_DIR.mkdir(exist_ok=True)
+
+
+def get_log_path(filename: str) -> Path:
+    """获取当天的日志文件路径"""
+    return CURRENT_LOG_DIR / filename
+
 
 def setup_logging(name: str = "yg_dataset") -> logging.Logger:
     """Setup application logging"""
@@ -35,20 +48,21 @@ def setup_logging(name: str = "yg_dataset") -> logging.Logger:
     console_handler.setFormatter(console_formatter)
     logger.addHandler(console_handler)
 
-    # File handler
-    file_handler = RotatingFileHandler(
-        LOG_DIR / f"{name}.log",
-        maxBytes=10 * 1024 * 1024,  # 10MB
-        backupCount=5,
+    # Main log file handler - app.log
+    main_file_handler = TimedRotatingFileHandler(
+        get_log_path("app.log"),
+        when="midnight",
+        interval=1,
+        backupCount=30,
         encoding="utf-8"
     )
-    file_handler.setLevel(logging.INFO)
-    file_formatter = logging.Formatter(
+    main_file_handler.setLevel(logging.INFO)
+    main_file_formatter = logging.Formatter(
         fmt="%(asctime)s | %(levelname)-8s | %(name)s:%(funcName)s:%(lineno)d | %(message)s",
         datefmt="%Y-%m-%d %H:%M:%S"
     )
-    file_handler.setFormatter(file_formatter)
-    logger.addHandler(file_handler)
+    main_file_handler.setFormatter(main_file_formatter)
+    logger.addHandler(main_file_handler)
 
     return logger
 
@@ -57,6 +71,65 @@ def setup_logging(name: str = "yg_dataset") -> logging.Logger:
 logger = setup_logging()
 
 
+# ============== Success Logger ==============
+def get_success_logger() -> logging.Logger:
+    """获取成功日志记录器"""
+    success_logger = logging.getLogger("yg_dataset.success")
+    if not success_logger.handlers:
+        handler = RotatingFileHandler(
+            get_log_path("success.log"),
+            maxBytes=10 * 1024 * 1024,
+            backupCount=30,
+            encoding="utf-8"
+        )
+        handler.setLevel(logging.INFO)
+        formatter = logging.Formatter(
+            fmt="%(asctime)s | %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S"
+        )
+        handler.setFormatter(formatter)
+        success_logger.addHandler(handler)
+        success_logger.setLevel(logging.INFO)
+    return success_logger
+
+
+# ============== Failure Logger ==============
+def get_failure_logger() -> logging.Logger:
+    """获取失败日志记录器"""
+    failure_logger = logging.getLogger("yg_dataset.failure")
+    if not failure_logger.handlers:
+        handler = RotatingFileHandler(
+            get_log_path("failure.log"),
+            maxBytes=10 * 1024 * 1024,
+            backupCount=30,
+            encoding="utf-8"
+        )
+        handler.setLevel(logging.WARNING)
+        formatter = logging.Formatter(
+            fmt="%(asctime)s | %(levelname)-8s | %(name)s:%(funcName)s:%(lineno)d | %(message)s",
+            datefmt="%Y-%m-%d %H:%M:%S"
+        )
+        handler.setFormatter(formatter)
+        failure_logger.addHandler(handler)
+        failure_logger.setLevel(logging.WARNING)
+    return failure_logger
+
+
+# ============== Convenience functions ==============
+def log_success(message: str, **kwargs):
+    """记录成功日志"""
+    extra_info = " | ".join([f"{k}={v}" for k, v in kwargs.items()]) if kwargs else ""
+    full_message = f"{message} | {extra_info}" if extra_info else message
+    get_success_logger().info(full_message)
+
+
+def log_failure(message: str, **kwargs):
+    """记录失败日志"""
+    extra_info = " | ".join([f"{k}={v}" for k, v in kwargs.items()]) if kwargs else ""
+    full_message = f"{message} | {extra_info}" if extra_info else message
+    get_failure_logger().warning(full_message)
+
+
 class LoggerMixin:
     """Mixin to add logging capability to classes"""