mdbq 3.9.4__py3-none-any.whl → 3.9.6__py3-none-any.whl

mdbq/__version__.py

@@ -1 +1 @@
-VERSION = '3.9.4'
+VERSION = '3.9.6'

mdbq/log/mylogger.py

@@ -0,0 +1,556 @@
+import logging
+import logging.handlers
+import datetime
+import json
+import os
+import sys
+import time
+import threading
+import queue
+from typing import Optional, Dict, Any, List, Callable, Union
+import atexit
+
+try:
+    import psutil
+
+    HAS_PSUTIL = True
+except ImportError:
+    HAS_PSUTIL = False
+
+
+class MyLogger:
+    """
+    增强版结构化日志记录器，支持多种高级功能
+
+    功能增强：
+    - 异步日志记录（减少I/O阻塞）
+    - 上下文管理器支持
+    - 自定义日志过滤器
+    - 更丰富的系统指标采集
+    - 日志采样控制
+    - 动态日志级别调整
+    - 请求跟踪ID
+    - 多线程安全
+    - 日志缓冲和批量写入
+    - 自定义异常处理
+
+    使用示例：
+    logger = MyLogger(
+        name='app_logger',
+        logging_mode='both',
+        log_level='INFO',
+        log_file='app.log',
+        max_log_size=50,
+        backup_count=5,
+        enable_async=True
+    )
+
+    with logger.context(request_id='12345'):
+        logger.info("处理请求", extra={'user': 'admin'})
+    """
+
+    def __init__(
+            self,
+            name: str = 'mylogger.log',
+            logging_mode: str = 'console',  # 'both', 'console', 'file', 'none'
+            log_level: str = 'INFO',  # 'DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL'
+            log_file: str = 'm_app.log',
+            log_format: str = 'json',  # 默认json格式，可选'simple'
+            max_log_size: int = 50,  # MB
+            backup_count: int = 5,
+            sensitive_fields: Optional[List[str]] = None,
+            enable_async: bool = False,
+            buffer_size: int = 1000,
+            sample_rate: float = 1.0,
+            filters: Optional[List[Callable]] = None,
+            enable_metrics: bool = False,
+            metrics_interval: int = 300,
+            message_limited: int = 1000
+    ):
+        """
+        初始化日志记录器
+
+        :param name: 日志记录器名称
+        :param logging_mode: 日志输出模式
+        :param log_level: 日志级别
+        :param log_file: 日志文件路径
+        :param max_log_size: 单个日志文件最大大小(MB)
+        :param backup_count: 保留的日志文件数量
+        :param sensitive_fields: 敏感字段列表(会被过滤)
+        :param enable_async: 是否启用异步日志
+        :param buffer_size: 日志缓冲大小(仅异步模式有效)
+        :param sample_rate: 控制日志的采样率(0.0-1.0)，使用消息内容的哈希值来决定是否记录，减少日志量，防止日志过于冗长
+        :param filters: 自定义日志过滤器列表
+        :param enable_metrics: 是否启用系统指标采集
+        :param metrics_interval: 指标采集间隔(秒)
+        :param message_limited: 简化日志内容，避免过长
+        """
+        log_path = os.path.join(os.path.expanduser("~"), 'logfile')
+        if not os.path.isdir(log_path):
+            os.makedirs(log_path)
+
+        self.name = name
+        self.logging_mode = logging_mode.lower()
+        self.log_level = log_level.upper()
+        self.log_file = os.path.join(log_path, log_file)
+        self.log_format = log_format
+        self.max_log_size = max_log_size
+        self.backup_count = backup_count
+        self.sensitive_fields = sensitive_fields or []
+        self.enable_async = enable_async
+        self.buffer_size = buffer_size
+        self.sample_rate = max(0.0, min(1.0, sample_rate))
+        self.filters = filters or []
+        self.enable_metrics = enable_metrics and HAS_PSUTIL
+        self.metrics_interval = metrics_interval
+        self.message_limited = message_limited
+
+        # 上下文相关
+        self._context = threading.local()
+        self._context.data = {}
+
+        # 系统指标相关
+        self._last_metrics_time = 0
+        self._metrics_cache = {}
+
+        # 异步日志相关
+        self._log_queue = queue.Queue(maxsize=buffer_size)
+        self._async_thread = None
+        self._stop_event = threading.Event()
+
+        # 创建日志记录器
+        self.logger = logging.getLogger(name)
+        self._init_logging()
+
+        if self.enable_async:
+            self._start_async_logging()
+
+        atexit.register(self.shutdown)
+
+    def __enter__(self):
+        """上下文管理器入口"""
+        return self
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        """上下文管理器退出"""
+        self.shutdown()
+        if exc_type is not None:
+            self.error(f"上下文内异常: {exc_val}",
+                       extra={'类型': str(exc_type)})
+        return False
+
+    def context(self, **kwargs):
+        """返回一个上下文管理器，可以设置临时上下文变量"""
+        return self._ContextManager(self, kwargs)
+
+    class _ContextManager:
+        def __init__(self, logger, context_vars):
+            self.logger = logger
+            self.context_vars = context_vars
+            self.old_context = {}
+
+        def __enter__(self):
+            # 保存旧上下文并设置新上下文
+            self.old_context = getattr(self.logger._context, 'data', {}).copy()
+            self.logger._context.data.update(self.context_vars)
+            return self.logger
+
+        def __exit__(self, exc_type, exc_val, exc_tb):
+            # 恢复旧上下文
+            self.logger._context.data = self.old_context
+            if exc_type is not None:
+                self.logger.error(f"上下文内异常2: {exc_val}",
+                                  extra={'类型': str(exc_type)})
+            return False
+
+    def _init_logging(self):
+        """初始化日志配置"""
+        valid_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
+        if self.log_level not in valid_levels:
+            self.log_level = 'INFO'
+
+        self.logger.setLevel(self.log_level)
+
+        # 防止重复添加handler
+        if self.logger.handlers:
+            for handler in self.logger.handlers[:]:
+                self.logger.removeHandler(handler)
+
+        # 定义日志格式
+        if self.log_format.lower() == 'simple':
+            # 简单文本格式
+            class SimpleFormatter(logging.Formatter):
+                def format(self, record):
+                    # 基础日志信息
+                    msg = super().format(record)
+
+                    # 添加上下文信息
+                    if hasattr(record, 'extra_data') and record.extra_data:
+                        context_data = record.extra_data.get('context_data', {})
+                        if context_data:
+                            msg += f" | Context: {context_data}"
+
+                        # 添加性能指标
+                        metrics = record.extra_data.get('性能指标', {})
+                        if metrics:
+                            msg += f" | Metrics: {metrics}"
+
+                        # 添加其他额外数据
+                        extra = {k: v for k, v in record.extra_data.items()
+                                 if k not in ('context_data', '性能指标')}
+                        if extra:
+                            msg += f" | Extra: {extra}"
+
+                    return msg
+
+            formatter = SimpleFormatter('%(asctime)s - %(levelname)s - %(message)s')
+            formatter.datefmt = '%Y-%m-%d %H:%M:%S'
+        else:
+            # 结构化JSON格式
+            class StructuredFormatter(logging.Formatter):
+                def format(self, record):
+                    log_data = {
+                        'timestamp': datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),
+                        'level': record.levelname,
+                        'message': record.getMessage(),
+                        # 'module': record.module,
+                        'function': record.funcName,
+                        # 'line': record.lineno,
+                        # 'thread': record.threadName,
+                        # 'process': record.processName,
+                        'name': record.name,
+                    }
+
+                    # 添加额外字段
+                    if hasattr(record, 'extra_data'):
+                        log_data.update(record.extra_data)
+
+                    # 添加上下文信息
+                    if hasattr(record, 'context_data'):
+                        log_data.update(record.context_data)
+
+                    # 添加异常信息
+                    if record.exc_info:
+                        log_data['异常'] = self.formatException(record.exc_info)
+
+                    # 过滤敏感信息
+                    if hasattr(record, '过滤'):
+                        for field in record.sensitive_fields:
+                            if field in log_data:
+                                log_data[field] = '***'
+                            if isinstance(log_data.get('message'), str):
+                                log_data['message'] = log_data['message'].replace(field, '***')
+
+                    return json.dumps(log_data, ensure_ascii=False)
+
+            formatter = StructuredFormatter()
+
+        # 根据模式添加相应的handler
+        if self.logging_mode in ('both', 'console'):
+            console_handler = logging.StreamHandler()
+            console_handler.setFormatter(formatter)
+            self.logger.addHandler(console_handler)
+
+        if self.logging_mode in ('both', 'file'):
+            # 确保日志目录存在
+            log_dir = os.path.dirname(self.log_file)
+            if log_dir and not os.path.exists(log_dir):
+                os.makedirs(log_dir)
+
+            file_handler = logging.handlers.RotatingFileHandler(
+                filename=self.log_file,
+                maxBytes=self.max_log_size * 1024 * 1024,
+                backupCount=self.backup_count,
+                encoding='utf-8',
+                delay=False
+            )
+            file_handler.setFormatter(formatter)
+            self.logger.addHandler(file_handler)
+
+    def _get_system_metrics(self) -> Dict[str, Any]:
+        """获取系统资源使用指标"""
+        if not self.enable_metrics:
+            return {}
+
+        try:
+            return {
+                '内存': {
+                    '使用率': psutil.virtual_memory().percent,
+                    '已使用': psutil.virtual_memory().used,
+                    '可用': psutil.virtual_memory().available,
+                },
+                'CPU': {
+                    '使用率': psutil.cpu_percent(),
+                    '核心数': psutil.cpu_count(),
+                },
+                '磁盘': {
+                    '使用率': psutil.disk_usage('/').percent,
+                    '已使用': psutil.disk_usage('/').used,
+                    '剩余': psutil.disk_usage('/').free,
+                },
+                '网络': {
+                    '发送字节数': psutil.net_io_counters().bytes_sent,
+                    '接收字节数': psutil.net_io_counters().bytes_recv,
+                },
+                '进程': {
+                    'PID': os.getpid(),
+                    '线程数': threading.active_count(),
+                }
+            }
+        except Exception as e:
+            self.logger.warning(f"无法采集系统性能指标: {e}",
+                                extra={'extra_data': {'metrics_error': str(e)}})
+            return {}
+
+    def _apply_filters(self, level: str, message: str, extra: Dict) -> bool:
+        """应用自定义过滤器"""
+        for filter_func in self.filters:
+            try:
+                if not filter_func(level, message, extra):
+                    return False  # 如果过滤器返回 False，则丢弃该日志
+            except Exception as e:
+                self.logger.warning(f"过滤失败: {e}",
+                                    extra={'extra_data': {'filter_error': str(e)}})
+        return True  # 所有过滤器都返回 True，则记录该日志
+
+    def _async_log_worker(self):
+        """异步日志工作线程"""
+        while not self._stop_event.is_set() or not self._log_queue.empty():
+            try:
+                log_args = self._log_queue.get(timeout=0.1)
+                if log_args:
+                    level, message, extra = log_args
+                    self._sync_log(level, message, extra)
+            except queue.Empty:
+                continue
+            except Exception as e:
+                # 防止日志线程崩溃
+                try:
+                    self.logger.error(f"日志线程崩溃: {e}",
+                                      extra={'extra_data': {'async_error': str(e)}})
+                except:
+                    pass
+
+    def _start_async_logging(self):
+        """启动异步日志线程"""
+        self._stop_event.clear()
+        self._async_thread = threading.Thread(
+            target=self._async_log_worker,
+            name=f"{self.name}_async_logger",
+            daemon=True
+        )
+        self._async_thread.start()
+
+    def _sync_log(self, level: str, message: str, extra: Optional[Dict] = None):
+        """同步日志记录"""
+        if not hasattr(self.logger, level.lower()):
+            return
+
+        # 简化日志内容，避免过长
+        if len(message) > self.message_limited:
+            message = message[:self.message_limited] + '...'
+
+        # 定期收集系统指标
+        if self.enable_metrics:
+            now = time.time()
+            if now - self._last_metrics_time > self.metrics_interval:
+                self._metrics_cache = self._get_system_metrics()
+                self._last_metrics_time = now
+
+        # 准备日志额外数据
+        log_extra = {}
+        if self.enable_metrics:
+            log_extra['性能指标'] = self._metrics_cache
+        if extra:
+            log_extra.update(extra)
+
+        # 添加上下文信息
+        if hasattr(self._context, 'data') and self._context.data:
+            log_extra['context_data'] = self._context.data.copy()
+
+        # 添加敏感字段过滤
+        log_extra['过滤'] = self.sensitive_fields
+
+        # 应用日志采样
+        if self.sample_rate < 1.0 and level.lower() in ('debug', 'info'):
+            if hash(message) % 100 >= self.sample_rate * 100:
+                return
+
+        # 应用过滤器
+        if not self._apply_filters(level, message, log_extra):
+            return
+
+        # 记录日志
+        getattr(self.logger, level.lower())(message, extra={'extra_data': log_extra})
+
+    def log(self, level: str, message: str, extra: Optional[Dict] = None):
+        """
+        记录日志
+
+        :param level: 日志级别 ('debug', 'info', 'warning', 'error', 'critical')
+        :param message: 日志消息
+        :param extra: 额外数据字典
+        """
+        if not hasattr(self.logger, level.lower()):
+            return
+
+        if self.enable_async:
+            try:
+                self._log_queue.put((level, message, extra), timeout=0.1)
+            except queue.Full:
+                # 队列满时降级为同步日志
+                self._sync_log(level, f"[ASYNC QUEUE FULL] {message}", extra)
+        else:
+            self._sync_log(level, message, extra)
+
+    def set_level(self, level: str):
+        """动态设置日志级别"""
+        valid_levels = ['DEBUG', 'INFO', 'WARNING', 'ERROR', 'CRITICAL']
+        level = level.upper()
+        if level in valid_levels:
+            self.log_level = level
+            self.logger.setLevel(level)
+            for handler in self.logger.handlers:
+                handler.setLevel(level)
+
+    def add_filter(self, filter_func: Callable):
+        """添加日志过滤器"""
+        if callable(filter_func):
+            self.filters.append(filter_func)
+
+    def set_context(self, **kwargs):
+        """设置上下文变量"""
+        if not hasattr(self._context, 'data'):
+            self._context.data = {}
+        self._context.data.update(kwargs)
+
+    def get_context(self, key: str, default=None):
+        """获取上下文变量"""
+        if hasattr(self._context, 'data'):
+            return self._context.data.get(key, default)
+        return default
+
+    def clear_context(self):
+        """清除所有上下文变量"""
+        if hasattr(self._context, 'data'):
+            self._context.data.clear()
+
+    def shutdown(self):
+        """关闭日志记录器，确保所有日志被刷新"""
+        if self.enable_async:
+            self._stop_event.set()
+            if self._async_thread and self._async_thread.is_alive():
+                self._async_thread.join(timeout=5)
+
+        # 确保所有handler被刷新
+        for handler in self.logger.handlers:
+            handler.flush()
+            handler.close()
+
+    def debug(self, message: str, extra: Optional[Dict] = None):
+        """记录调试信息"""
+        self.log('debug', message, extra)
+
+    def info(self, message: str, extra: Optional[Dict] = None):
+        """记录一般信息"""
+        self.log('info', message, extra)
+
+    def warning(self, message: str, extra: Optional[Dict] = None):
+        """记录警告信息"""
+        self.log('warning', message, extra)
+
+    def error(self, message: str, extra: Optional[Dict] = None):
+        """记录错误信息"""
+        self.log('error', message, extra)
+
+    def critical(self, message: str, extra: Optional[Dict] = None):
+        """记录严重错误信息"""
+        self.log('critical', message, extra)
+
+    def exception(self, message: str, exc_info: Exception, extra: Optional[Dict] = None):
+        """记录异常信息"""
+        if not extra:
+            extra = {}
+        # # 获取异常发生的实际位置
+        # tb = exc_info.__traceback__
+        #
+        # if tb:
+        #     extra.update({
+        #         'module': tb.tb_frame.f_globals.get('__name__', ''),
+        #         'function': tb.tb_frame.f_code.co_name,
+        #         'line': tb.tb_lineno,
+        #         'file': tb.tb_frame.f_code.co_filename
+        #     })
+        # extra['异常'] = str(exc_info)
+        # extra['类型'] = exc_info.__class__.__name__
+        # self.log('error', message, extra)
+
+        # 获取完整的异常堆栈
+        tb = exc_info.__traceback__
+        while tb.tb_next:
+            tb = tb.tb_next  # 获取最内层的堆栈帧
+
+        extra.update({
+            'module': tb.tb_frame.f_globals.get('__name__', ''),
+            'function': tb.tb_frame.f_code.co_name,
+            'line': tb.tb_lineno,
+            'file': tb.tb_frame.f_code.co_filename,
+            '异常': str(exc_info),
+            '类型': exc_info.__class__.__name__,
+            '堆栈': self._format_traceback(exc_info)
+        })
+
+        # 直接使用logger的error方法记录，保留原始调用栈
+        self.log('error', message, extra)
+
+    def _format_traceback(self, exc_info):
+        """格式化异常堆栈"""
+        import traceback
+        return ''.join(traceback.format_exception(type(exc_info), exc_info, exc_info.__traceback__))
+
+    def timeit(self, message: str = "Execution time"):
+        """返回一个计时器上下文管理器"""
+        return self._Timer(self, message)
+
+    class _Timer:
+        def __init__(self, logger, message):
+            self.logger = logger
+            self.message = message
+            self.start_time = None
+
+        def __enter__(self):
+            self.start_time = time.time()
+            return self
+
+        def __exit__(self, exc_type, exc_val, exc_tb):
+            elapsed = time.time() - self.start_time
+            self.logger.info(f"{self.message}: {elapsed:.3f}s",
+                             extra={'elapsed_seconds': elapsed})
+            return False
+
+
+def main():
+    # 创建日志记录器
+    logger = MyLogger(
+        name='my_app',
+        logging_mode='both',
+        log_level='DEBUG',
+        log_file='/Users/xigua/Downloads/my_app.log',
+        log_format='json',
+        max_log_size=50,
+        backup_count=5,
+        enable_async=True,  # 是否启用异步日志
+        sample_rate=1,  # 采样50%的DEBUG/INFO日志
+        sensitive_fields=[],  #  敏感字段列表
+        enable_metrics=False,  # 是否启用性能指标
+    )
+
+    logger.info('123')
+
+    # 确保所有日志被刷新
+    logger.shutdown()
+
+
+if __name__ == '__main__':
+    pass
+    main()

mdbq/mysql/mysql.py

@@ -3004,7 +3004,7 @@ class MySQLDeduplicator:
 def main():
     uploader = MySQLUploader(
         username='root',
-        password='1',
+        password='188988yang188',
         host='localhost',
         port=3306,
         logging_mode='console',

{mdbq-3.9.4.dist-info → mdbq-3.9.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: mdbq
-Version: 3.9.4
+Version: 3.9.6
 Home-page: https://pypi.org/project/mdbq
 Author: xigua, 
 Author-email: 2587125111@qq.com

{mdbq-3.9.4.dist-info → mdbq-3.9.6.dist-info}/RECORD

@@ -1,14 +1,15 @@
 mdbq/__init__.py,sha256=Il5Q9ATdX8yXqVxtP_nYqUhExzxPC_qk_WXQ_4h0exg,16
-mdbq/__version__.py,sha256=44Qvc6l4hjIIQuGixaBICZNZB9jeL2ztNkT4fkONEBc,17
+mdbq/__version__.py,sha256=rCARLRw4aYsH5Ac1n95qGJBlNNqAlv-EapPM3bcYkto,17
 mdbq/aggregation/__init__.py,sha256=EeDqX2Aml6SPx8363J-v1lz0EcZtgwIBYyCJV6CcEDU,40
 mdbq/aggregation/optimize.py,sha256=2oalzD9weZhDclUC22OLxYa8Zj7KnmsGUoUau_Jlyc4,19796
 mdbq/aggregation/query_data.py,sha256=5_OzjGR5Sq00q-EgAYmSE5V9i4Solw9y4hkldl4mvt8,179808
 mdbq/config/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/config/config.py,sha256=eaTfrfXQ65xLqjr5I8-HkZd_jEY1JkGinEgv3TSLeoQ,3170
 mdbq/log/__init__.py,sha256=Mpbrav0s0ifLL7lVDAuePEi1hJKiSHhxcv1byBKDl5E,15
+mdbq/log/mylogger.py,sha256=CeQf8RcVITm9bVr-hHYdx6QtIbA--YkmWBAaPcMcXnY,20724
 mdbq/log/spider_logging.py,sha256=-ozWWEGm3HVv604ozs_OOvVwumjokmUPwbaodesUrPY,1664
 mdbq/mysql/__init__.py,sha256=A_DPJyAoEvTSFojiI2e94zP0FKtCkkwKP1kYUCSyQzo,11
-mdbq/mysql/mysql.py,sha256=ylGvSzFE2B78y77wG266tf_RaEuETnngqDKUTqjQCjs,132378
+mdbq/mysql/mysql.py,sha256=WFkv2flWuYRJqTzCOvxyiPeJgyJvVQzSG24jH_x5oEg,132390
 mdbq/mysql/s_query.py,sha256=X055aLRAgxVvueXx4NbfNjp6MyBI02_XBb1pTKw09L0,8660
 mdbq/other/__init__.py,sha256=jso1oHcy6cJEfa7udS_9uO5X6kZLoPBF8l3wCYmr5dM,18
 mdbq/other/download_sku_picture.py,sha256=YU8DxKMXbdeE1OOKEA848WVp62jYHw5O4tXTjUdq9H0,44832
@@ -22,7 +23,7 @@ mdbq/redis/__init__.py,sha256=YtgBlVSMDphtpwYX248wGge1x-Ex_mMufz4-8W0XRmA,12
 mdbq/redis/getredis.py,sha256=Uk8-cOWT0JU1qRyIVqdbYokSLvkDIAfcokmYj1ebw8k,24104
 mdbq/spider/__init__.py,sha256=RBMFXGy_jd1HXZhngB2T2XTvJqki8P_Fr-pBcwijnew,18
 mdbq/spider/aikucun.py,sha256=OhyEv1VyAKTOHjLDM37iNDQeRg5OnrNoKODoG2VxHes,19806
-mdbq-3.9.4.dist-info/METADATA,sha256=1FQB3vRRNlxontQEXd6gE-RhnHbjAPOZcnc_Xh9I4B0,363
-mdbq-3.9.4.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
-mdbq-3.9.4.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
-mdbq-3.9.4.dist-info/RECORD,,
+mdbq-3.9.6.dist-info/METADATA,sha256=RyMeBh6UL0QDEClon62yAzpowavd-5sUZKjniEex-hs,363
+mdbq-3.9.6.dist-info/WHEEL,sha256=jB7zZ3N9hIM9adW7qlTAyycLYW9npaWKLRzaoVcLKcM,91
+mdbq-3.9.6.dist-info/top_level.txt,sha256=2FQ-uLnCSB-OwFiWntzmwosW3X2Xqsg0ewh1axsaylA,5
+mdbq-3.9.6.dist-info/RECORD,,