修改用户设置的新增用户的权限点击操作

backend/app/core/logging.py

@@ -8,7 +8,7 @@ from logging import Handler, LogRecord
 from pathlib import Path
 import re
 import time
-from typing import Any
+from typing import Any, Callable, Optional
 from uuid import uuid4
 
 from fastapi import FastAPI, Request
@@ -17,6 +17,74 @@ from app.core.config import Settings, get_settings
 
 request_id_var: ContextVar[str] = ContextVar("request_id", default="-")
 
+# ==================== 敏感数据脱敏规则 ====================
+
+SENSITIVE_PATTERNS: dict[str, Callable | str] = {
+    "token": "***",
+    "password": "***",
+    "access_token": "***",
+    "refresh_token": "***",
+    "secret_key": "***",
+    "authorization": "***",
+    "bearer": "***",
+    "api_key": "***",
+    "private_key": "***",
+}
+
+def mask_value(key: str, value: Any) -> str:
+    """对单个值进行脱敏处理"""
+    if value is None:
+        return ""
+    str_val = str(value)
+    
+    handler = SENSITIVE_PATTERNS.get(key)
+    if callable(handler):
+        return handler(str_val)
+    elif isinstance(handler, str):
+        # 支持正则替换模式，如 r"1\d{3}\d{4}"
+        try:
+            return re.sub(handler, "***", str_val)
+        except re.error:
+            return "***"
+    return handler
+
+
+def mask_sensitive_dict(data: dict) -> dict:
+    """递归脱敏字典中的敏感字段"""
+    if not data or not isinstance(data, dict):
+        return data
+    
+    result = {}
+    for key, value in data.items():
+        result[key] = mask_value(key, value)
+    return result
+
+
+def mask_sensitive_string(text: str) -> str:
+    """从文本中脱敏常见敏感信息"""
+    if not text:
+        return text
+    
+    patterns = [
+        (r'Bearer\s+[A-Za-z0-9\-._]+', '***'),
+        (r'token\s*[:=]\s*', '***'),
+        (r'password\s*[:=]\s*', '***'),
+        (r'secret[_-]?key\s*[:=]', '***'),
+        (r'api[-_]?key\s*[:=]', '***'),
+        (r'private[_-]?key\s*[:=]', '***'),
+        (r'\d{11}', r'\d{3}\*\d{4}'),  # 手机号/身份证
+        (r'1[3-9]\d{9}', r'1\*{3}\*{4}'),  # 手机号
+    ]
+    
+    for pattern, replacement in patterns:
+        try:
+            text = re.sub(pattern, replacement, text, flags=re.IGNORECASE)
+        except re.error:
+            pass
+    return text
+
+
+# ==================== RequestId Filter ====================
 
 class RequestIdFilter(logging.Filter):
     def filter(self, record: LogRecord) -> bool:
@@ -24,8 +92,30 @@ class RequestIdFilter(logging.Filter):
         return True
 
 
+# ==================== Enhanced JSON Formatter ====================
+
 class JsonLogFormatter(logging.Formatter):
-    """Format one JSON object per line for ELK/Filebeat collection."""
+    """
+    增强的 JSON 日志格式化器，支持结构化字段输出。
+    
+    输出示例：
+    {
+      "@timestamp": "2026-08-17T18:30:00.123Z",
+      "level": "INFO",
+      "logger": "dataset.router",
+      "message": "数据集创建成功",
+      "module": "dataset.router",
+      "function": "create_dataset",
+      "file": "dataset/router.py",
+      "line": 45,
+      "process": 12345,
+      "thread": "MainThread",
+      "request_id": "req-abc123",
+      "user_id": "u_admin",
+      "client_ip": "192.168.1.100",
+      "extra": {...}
+    }
+    """
 
     def format(self, record: LogRecord) -> str:
         payload: dict[str, Any] = {
@@ -44,13 +134,26 @@ class JsonLogFormatter(logging.Formatter):
             "thread_name": record.threadName,
             "request_id": getattr(record, "request_id", "-"),
         }
+        
+        # 从 record 中提取额外字段（通过 extra 参数传入）
+        for attr in ("user_id", "client_ip", "target_type", "target_id", 
+                    "duration_ms", "status_code", "error"):
+            val = getattr(record, attr, None)
+            if val is not None:
+                payload[attr] = val
+        
+        # 处理异常信息
         if record.exc_info:
             payload["exception"] = self.formatException(record.exc_info)
         if record.stack_info:
             payload["stack"] = self.formatStack(record.stack_info)
+            
         return json.dumps(payload, ensure_ascii=False, separators=(",", ":"))
 
 
+# ==================== DateSizeRotatingFileHandler ====================
+# （保持不变，已有实现）
+
 class DateSizeRotatingFileHandler(Handler):
     """Rotate log files by date and size while keeping date in every file name."""
 
@@ -160,6 +263,114 @@ class DateSizeRotatingFileHandler(Handler):
                 path.unlink(missing_ok=True)
 
 
+# ==================== Structured Logger 封装 ====================
+
+class StructuredLogger:
+    """
+    结构化日志记录器，提供统一的日志接口。
+    
+    使用方式：
+        logger = get_structured_logger('dataset.router')
+        logger.info('创建数据集', dataset_id='ds_123')
+    """
+    
+    def __init__(self, name: str, module: str = ""):
+        self.logger = logging.getLogger(name)
+        self.name = name
+        self.module = module
+        
+    @property
+    def trace_id(self) -> str:
+        return request_id_var.get("-")
+    
+    def info(self, message: str, **extra: Any) -> None:
+        self._log("INFO", message, **extra)
+
+    def warning(self, message: str, **extra: Any) -> None:
+        self._log("WARNING", message, **extra)
+
+    def error(self, message: str, **extra: Any) -> None:
+        self._log("ERROR", message, **extra)
+
+    def debug(self, message: str, **extra: Any) -> None:
+        self._log("DEBUG", message, **extra)
+
+    def _log(self, level: str, message: str, **extra: Any) -> None:
+        """统一日志记录方法"""
+        log_entry: dict[str, Any] = {
+            "timestamp": datetime.utcnow().isoformat(),
+            "level": level,
+            "logger": self.name,
+            "module": self.module,
+            "message": message,
+            "trace_id": self.trace_id,
+            "extra": extra,
+        }
+        self.logger.log(getattr(logging, level, logging.INFO), json.dumps(log_entry, ensure_ascii=False, default=str))
+
+
+def get_structured_logger(name: str, module: str = "") -> StructuredLogger:
+    """获取结构化日志记录器"""
+    return StructuredLogger(name, module)
+
+
+# ==================== 快捷函数 ====================
+
+def get_logger(name: str) -> logging.Logger:
+    """获取标准 Python logger"""
+    return logging.getLogger(name)
+
+
+def set_request_id(request_id: str) -> None:
+    """设置当前请求的追踪 ID"""
+    request_id_var.set(request_id)
+
+
+def setup_request_logging(app: FastAPI) -> None:
+    """配置 FastAPI 请求日志中间件"""
+    logger = get_logger("app.access")
+
+    @app.middleware("http")
+    async def request_logging_middleware(request: Request, call_next):  # type: ignore[no-untyped-def]
+        request_id = request.headers.get("X-Request-ID") or str(uuid4())
+        token = request_id_var.set(request_id)
+        started_at = time.perf_counter()
+        try:
+            response = await call_next(request)
+            elapsed_ms = (time.perf_counter() - started_at) * 1000
+            
+            noisy_paths = ("/health", "/system-info", "/compute/jobs/", "/model-eval/", "/model-compare/")
+            log_method = logger.debug if request.method == "GET" and response.status_code < 400 else logger.info
+            if any(request.url.path.endswith(path) or path in request.url.path for path in noisy_paths) and response.status_code < 400:
+                log_method = logger.debug
+            if response.status_code >= 400:
+                log_method = logger.warning
+            log_method(
+                "request completed method=%s path=%s status_code=%s duration_ms=%.2f client=%s",
+                request.method,
+                request.url.path,
+                response.status_code,
+                elapsed_ms,
+                request.client.host if request.client else "-",
+            )
+            response.headers["X-Request-ID"] = request_id
+            return response
+        except Exception:
+            elapsed_ms = (time.perf_counter() - started_at) * 1000
+            logger.exception(
+                "request failed method=%s path=%s duration_ms=%.2f client=%s",
+                request.method,
+                request.url.path,
+                elapsed_ms,
+                request.client.host if request.client else "-",
+            )
+            raise
+        finally:
+            request_id_var.reset(token)
+
+
+# ==================== 配置函数 ====================
+
 def configure_logging(settings: Settings | None = None) -> None:
     settings = settings or get_settings()
 
@@ -209,57 +420,5 @@ def configure_logging(settings: Settings | None = None) -> None:
         logger.handlers.clear()
         logger.propagate = True
 
-
-logging.getLogger("uvicorn.access").setLevel(logging.WARNING)
-logging.getLogger("psycopg.pool").setLevel(logging.ERROR)
-
-
-def get_logger(name: str) -> logging.Logger:
-    return logging.getLogger(name)
-
-
-def set_request_id(request_id: str) -> None:
-    request_id_var.set(request_id)
-
-
-def setup_request_logging(app: FastAPI) -> None:
-    logger = get_logger("app.access")
-
-    @app.middleware("http")
-    async def request_logging_middleware(request: Request, call_next):  # type: ignore[no-untyped-def]
-        request_id = request.headers.get("X-Request-ID") or str(uuid4())
-        token = request_id_var.set(request_id)
-        started_at = time.perf_counter()
-        try:
-            response = await call_next(request)
-            elapsed_ms = (time.perf_counter() - started_at) * 1000
-            # Docker/frontend probes and polling endpoints are intentionally
-            # quiet at INFO; failures remain visible at WARNING/ERROR.
-            noisy_paths = ("/health", "/system-info", "/compute/jobs/", "/model-eval/", "/model-compare/")
-            log_method = logger.debug if request.method == "GET" and response.status_code < 400 else logger.info
-            if any(request.url.path.endswith(path) or path in request.url.path for path in noisy_paths) and response.status_code < 400:
-                log_method = logger.debug
-            if response.status_code >= 400:
-                log_method = logger.warning
-            log_method(
-                "request completed method=%s path=%s status_code=%s duration_ms=%.2f client=%s",
-                request.method,
-                request.url.path,
-                response.status_code,
-                elapsed_ms,
-                request.client.host if request.client else "-",
-            )
-            response.headers["X-Request-ID"] = request_id
-            return response
-        except Exception:
-            elapsed_ms = (time.perf_counter() - started_at) * 1000
-            logger.exception(
-                "request failed method=%s path=%s duration_ms=%.2f client=%s",
-                request.method,
-                request.url.path,
-                elapsed_ms,
-                request.client.host if request.client else "-",
-            )
-            raise
-        finally:
-            request_id_var.reset(token)
+    logging.getLogger("uvicorn.access").setLevel(logging.WARNING)
+    logging.getLogger("psycopg.pool").setLevel(logging.ERROR)