crawlo 1.1.9__py3-none-any.whl → 1.2.1__py3-none-any.whl

tests/error_handling_example.py

@@ -1,172 +1,172 @@
-#!/usr/bin/python
-# -*- coding:UTF-8 -*-
-"""
-错误处理使用示例
-展示如何在实际项目中使用增强版错误处理工具
-"""
-import sys
-import os
-import asyncio
-import time
-from typing import Optional
-
-# 添加项目根目录到 Python 路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.utils.enhanced_error_handler import (
-    EnhancedErrorHandler, 
-    ErrorContext, 
-    DetailedException, 
-    handle_exception
-)
-
-
-# 创建错误处理器实例
-error_handler = EnhancedErrorHandler("example_module")
-
-
-class DatabaseConnectionError(DetailedException):
-    """数据库连接错误"""
-    pass
-
-
-class NetworkTimeoutError(DetailedException):
-    """网络超时错误"""
-    pass
-
-
-@handle_exception(context="数据库连接", module="database", function="connect_to_db", error_code="DB001")
-def connect_to_db(host: str, port: int) -> bool:
-    """模拟数据库连接"""
-    print(f"正在连接数据库 {host}:{port}...")
-    
-    # 模拟连接失败
-    if host == "invalid.host":
-        raise DatabaseConnectionError(
-            "无法连接到数据库服务器",
-            context=ErrorContext(context="数据库连接失败", module="database", function="connect_to_db"),
-            error_code="DB001",
-            host=host,
-            port=port
-        )
-    
-    # 模拟连接成功
-    print("✅ 数据库连接成功")
-    return True
-
-
-@error_handler.retry_on_failure(max_retries=3, delay=0.5, backoff_factor=2.0)
-async def fetch_data_from_api(url: str) -> dict:
-    """模拟从API获取数据（带重试机制）"""
-    print(f"正在从 {url} 获取数据...")
-    
-    # 模拟网络问题
-    if url == "https://slow.api.com/data":
-        time.sleep(2)  # 模拟慢速响应
-        raise NetworkTimeoutError(
-            "API响应超时",
-            context=ErrorContext(context="API调用超时", module="api", function="fetch_data_from_api"),
-            error_code="API001",
-            url=url,
-            timeout=1
-        )
-    
-    if url == "https://error.api.com/data":
-        raise NetworkTimeoutError(
-            "API服务器错误",
-            context=ErrorContext(context="API服务器错误", module="api", function="fetch_data_from_api"),
-            error_code="API002",
-            url=url,
-            status_code=500
-        )
-    
-    # 模拟成功响应
-    print("✅ API数据获取成功")
-    return {"data": "sample data", "status": "success"}
-
-
-def process_data(data: dict) -> Optional[str]:
-    """处理数据"""
-    try:
-        print("正在处理数据...")
-        
-        # 模拟处理错误
-        if not data:
-            raise ValueError("数据为空")
-        
-        if "error" in data:
-            raise RuntimeError(f"数据处理失败: {data['error']}")
-        
-        # 模拟处理成功
-        result = f"处理完成: {data.get('data', 'no data')}"
-        print(f"✅ {result}")
-        return result
-        
-    except Exception as e:
-        # 使用错误处理器处理异常
-        context = ErrorContext(context="数据处理", module="data_processor", function="process_data")
-        error_handler.handle_error(e, context=context, raise_error=False)
-        return None
-
-
-async def main():
-    """主函数"""
-    print("🚀 错误处理使用示例")
-    print("=" * 50)
-    
-    # 1. 测试数据库连接（成功情况）
-    print("1. 测试数据库连接（成功情况）")
-    try:
-        connect_to_db("localhost", 5432)
-    except Exception as e:
-        print(f"❌ 意外错误: {e}")
-    print()
-    
-    # 2. 测试数据库连接（失败情况）
-    print("2. 测试数据库连接（失败情况）")
-    try:
-        connect_to_db("invalid.host", 5432)
-    except Exception as e:
-        print(f"❌ 预期的数据库连接错误: {e}")
-    print()
-    
-    # 3. 测试API调用（成功情况）
-    print("3. 测试API调用（成功情况）")
-    try:
-        data = await fetch_data_from_api("https://api.com/data")
-        process_data(data)
-    except Exception as e:
-        print(f"❌ API调用错误: {e}")
-    print()
-    
-    # 4. 测试API调用（失败情况，带重试）
-    print("4. 测试API调用（失败情况，带重试）")
-    try:
-        data = await fetch_data_from_api("https://error.api.com/data")
-        process_data(data)
-    except Exception as e:
-        print(f"❌ API调用错误（重试后仍然失败）: {e}")
-    print()
-    
-    # 5. 测试数据处理（失败情况）
-    print("5. 测试数据处理（失败情况）")
-    process_data(None)  # 空数据
-    process_data({"error": "invalid format"})  # 错误数据
-    print()
-    
-    # 6. 查看错误历史
-    print("6. 错误历史记录")
-    history = error_handler.get_error_history()
-    print(f"共记录 {len(history)} 个错误:")
-    for i, record in enumerate(history, 1):
-        print(f"  {i}. {record['exception_type']}: {record['message']}")
-        if record['context']:
-            print(f"     上下文: {record['context']}")
-    print()
-    
-    print("=" * 50)
-    print("🎉 示例运行完成")
-
-
-if __name__ == "__main__":
+#!/usr/bin/python
+# -*- coding:UTF-8 -*-
+"""
+错误处理使用示例
+展示如何在实际项目中使用增强版错误处理工具
+"""
+import sys
+import os
+import asyncio
+import time
+from typing import Optional
+
+# 添加项目根目录到 Python 路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.utils.enhanced_error_handler import (
+    EnhancedErrorHandler, 
+    ErrorContext, 
+    DetailedException, 
+    handle_exception
+)
+
+
+# 创建错误处理器实例
+error_handler = EnhancedErrorHandler("example_module")
+
+
+class DatabaseConnectionError(DetailedException):
+    """数据库连接错误"""
+    pass
+
+
+class NetworkTimeoutError(DetailedException):
+    """网络超时错误"""
+    pass
+
+
+@handle_exception(context="数据库连接", module="database", function="connect_to_db", error_code="DB001")
+def connect_to_db(host: str, port: int) -> bool:
+    """模拟数据库连接"""
+    print(f"正在连接数据库 {host}:{port}...")
+    
+    # 模拟连接失败
+    if host == "invalid.host":
+        raise DatabaseConnectionError(
+            "无法连接到数据库服务器",
+            context=ErrorContext(context="数据库连接失败", module="database", function="connect_to_db"),
+            error_code="DB001",
+            host=host,
+            port=port
+        )
+    
+    # 模拟连接成功
+    print("✅ 数据库连接成功")
+    return True
+
+
+@error_handler.retry_on_failure(max_retries=3, delay=0.5, backoff_factor=2.0)
+async def fetch_data_from_api(url: str) -> dict:
+    """模拟从API获取数据（带重试机制）"""
+    print(f"正在从 {url} 获取数据...")
+    
+    # 模拟网络问题
+    if url == "https://slow.api.com/data":
+        time.sleep(2)  # 模拟慢速响应
+        raise NetworkTimeoutError(
+            "API响应超时",
+            context=ErrorContext(context="API调用超时", module="api", function="fetch_data_from_api"),
+            error_code="API001",
+            url=url,
+            timeout=1
+        )
+    
+    if url == "https://error.api.com/data":
+        raise NetworkTimeoutError(
+            "API服务器错误",
+            context=ErrorContext(context="API服务器错误", module="api", function="fetch_data_from_api"),
+            error_code="API002",
+            url=url,
+            status_code=500
+        )
+    
+    # 模拟成功响应
+    print("✅ API数据获取成功")
+    return {"data": "sample data", "status": "success"}
+
+
+def process_data(data: dict) -> Optional[str]:
+    """处理数据"""
+    try:
+        print("正在处理数据...")
+        
+        # 模拟处理错误
+        if not data:
+            raise ValueError("数据为空")
+        
+        if "error" in data:
+            raise RuntimeError(f"数据处理失败: {data['error']}")
+        
+        # 模拟处理成功
+        result = f"处理完成: {data.get('data', 'no data')}"
+        print(f"✅ {result}")
+        return result
+        
+    except Exception as e:
+        # 使用错误处理器处理异常
+        context = ErrorContext(context="数据处理", module="data_processor", function="process_data")
+        error_handler.handle_error(e, context=context, raise_error=False)
+        return None
+
+
+async def main():
+    """主函数"""
+    print("🚀 错误处理使用示例")
+    print("=" * 50)
+    
+    # 1. 测试数据库连接（成功情况）
+    print("1. 测试数据库连接（成功情况）")
+    try:
+        connect_to_db("localhost", 5432)
+    except Exception as e:
+        print(f"❌ 意外错误: {e}")
+    print()
+    
+    # 2. 测试数据库连接（失败情况）
+    print("2. 测试数据库连接（失败情况）")
+    try:
+        connect_to_db("invalid.host", 5432)
+    except Exception as e:
+        print(f"❌ 预期的数据库连接错误: {e}")
+    print()
+    
+    # 3. 测试API调用（成功情况）
+    print("3. 测试API调用（成功情况）")
+    try:
+        data = await fetch_data_from_api("https://api.com/data")
+        process_data(data)
+    except Exception as e:
+        print(f"❌ API调用错误: {e}")
+    print()
+    
+    # 4. 测试API调用（失败情况，带重试）
+    print("4. 测试API调用（失败情况，带重试）")
+    try:
+        data = await fetch_data_from_api("https://error.api.com/data")
+        process_data(data)
+    except Exception as e:
+        print(f"❌ API调用错误（重试后仍然失败）: {e}")
+    print()
+    
+    # 5. 测试数据处理（失败情况）
+    print("5. 测试数据处理（失败情况）")
+    process_data(None)  # 空数据
+    process_data({"error": "invalid format"})  # 错误数据
+    print()
+    
+    # 6. 查看错误历史
+    print("6. 错误历史记录")
+    history = error_handler.get_error_history()
+    print(f"共记录 {len(history)} 个错误:")
+    for i, record in enumerate(history, 1):
+        print(f"  {i}. {record['exception_type']}: {record['message']}")
+        if record['context']:
+            print(f"     上下文: {record['context']}")
+    print()
+    
+    print("=" * 50)
+    print("🎉 示例运行完成")
+
+
+if __name__ == "__main__":
     asyncio.run(main())

tests/redis_key_validation_demo.py

@@ -1,131 +1,131 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Redis Key 验证演示脚本
-演示如何使用Redis Key验证工具
-"""
-import sys
-import os
-
-# 添加项目根目录到路径
-sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
-
-from crawlo.utils.redis_key_validator import (
-    RedisKeyValidator, 
-    validate_redis_key_naming, 
-    validate_multiple_redis_keys,
-    get_redis_key_info,
-    print_validation_report
-)
-
-
-def demonstrate_redis_key_validation():
-    """演示Redis Key验证功能"""
-    print("=== Redis Key 验证功能演示 ===\n")
-    
-    # 1. 验证单个有效的Redis Key
-    print("1. 验证单个有效的Redis Key:")
-    valid_keys = [
-        "crawlo:books_distributed:filter:fingerprint",
-        "crawlo:books_distributed:queue:requests",
-        "crawlo:books_distributed:queue:processing",
-        "crawlo:books_distributed:queue:failed",
-        "crawlo:books_distributed:item:fingerprint"
-    ]
-    
-    for key in valid_keys:
-        is_valid = validate_redis_key_naming(key, "books_distributed")
-        print(f"  ✅ {key} - {'通过' if is_valid else '失败'}")
-    
-    print()
-    
-    # 2. 验证无效的Redis Key
-    print("2. 验证无效的Redis Key:")
-    invalid_keys = [
-        "invalid_format",  # 不以crawlo开头
-        "crawlo:books_distributed",  # 部分缺失
-        "crawlo:books_distributed:invalid_component:fingerprint",  # 无效组件
-        "crawlo:books_distributed:queue:invalid_subcomponent",  # 无效子组件
-        "crawlo:wrong_project:filter:fingerprint"  # 项目名称不匹配
-    ]
-    
-    for key in invalid_keys:
-        is_valid = validate_redis_key_naming(key, "books_distributed")
-        print(f"  ❌ {key} - {'通过' if is_valid else '失败'}")
-    
-    print()
-    
-    # 3. 批量验证Redis Key
-    print("3. 批量验证Redis Key:")
-    all_keys = valid_keys + invalid_keys
-    is_valid, invalid_keys_list = validate_multiple_redis_keys(all_keys, "books_distributed")
-    
-    print(f"  批量验证结果: {'全部通过' if is_valid else '存在无效Key'}")
-    if not is_valid:
-        print("  无效的Key:")
-        for key in invalid_keys_list:
-            print(f"    - {key}")
-    
-    print()
-    
-    # 4. 获取Redis Key信息
-    print("4. 获取Redis Key信息:")
-    sample_keys = [
-        "crawlo:api_data_collection:filter:fingerprint",
-        "crawlo:api_data_collection:queue:requests",
-        "crawlo:api_data_collection:item:fingerprint"
-    ]
-    
-    for key in sample_keys:
-        info = get_redis_key_info(key)
-        print(f"  Key: {key}")
-        if info['valid']:
-            print(f"    框架: {info['framework']}")
-            print(f"    项目: {info['project']}")
-            print(f"    组件: {info['component']}")
-            if 'sub_component' in info:
-                print(f"    子组件: {info['sub_component']}")
-        else:
-            print(f"    错误: {info.get('error', '无效')}")
-        print()
-    
-    # 5. 打印验证报告
-    print("5. 打印验证报告:")
-    print_validation_report(all_keys, "books_distributed")
-
-
-def demonstrate_advanced_validation():
-    """演示高级验证功能"""
-    print("\n=== 高级验证功能演示 ===\n")
-    
-    validator = RedisKeyValidator()
-    
-    # 1. 不指定项目名称的验证
-    print("1. 不指定项目名称的验证:")
-    key = "crawlo:any_project:filter:fingerprint"
-    is_valid = validator.validate_key_naming(key)  # 不指定项目名称
-    print(f"  {key} - {'通过' if is_valid else '失败'}")
-    
-    # 2. 验证不同项目的Key
-    print("\n2. 验证不同项目的Key:")
-    project_keys = {
-        "books_distributed": [
-            "crawlo:books_distributed:filter:fingerprint",
-            "crawlo:books_distributed:queue:requests"
-        ],
-        "api_data_collection": [
-            "crawlo:api_data_collection:filter:fingerprint",
-            "crawlo:api_data_collection:queue:requests"
-        ]
-    }
-    
-    for project_name, keys in project_keys.items():
-        print(f"  项目: {project_name}")
-        for key in keys:
-            is_valid = validator.validate_key_naming(key, project_name)
-            print(f"    {key} - {'通过' if is_valid else '失败'}")
-
-
-if __name__ == "__main__":
-    demonstrate_redis_key_validation()
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Redis Key 验证演示脚本
+演示如何使用Redis Key验证工具
+"""
+import sys
+import os
+
+# 添加项目根目录到路径
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..'))
+
+from crawlo.utils.redis_key_validator import (
+    RedisKeyValidator, 
+    validate_redis_key_naming, 
+    validate_multiple_redis_keys,
+    get_redis_key_info,
+    print_validation_report
+)
+
+
+def demonstrate_redis_key_validation():
+    """演示Redis Key验证功能"""
+    print("=== Redis Key 验证功能演示 ===\n")
+    
+    # 1. 验证单个有效的Redis Key
+    print("1. 验证单个有效的Redis Key:")
+    valid_keys = [
+        "crawlo:books_distributed:filter:fingerprint",
+        "crawlo:books_distributed:queue:requests",
+        "crawlo:books_distributed:queue:processing",
+        "crawlo:books_distributed:queue:failed",
+        "crawlo:books_distributed:item:fingerprint"
+    ]
+    
+    for key in valid_keys:
+        is_valid = validate_redis_key_naming(key, "books_distributed")
+        print(f"  ✅ {key} - {'通过' if is_valid else '失败'}")
+    
+    print()
+    
+    # 2. 验证无效的Redis Key
+    print("2. 验证无效的Redis Key:")
+    invalid_keys = [
+        "invalid_format",  # 不以crawlo开头
+        "crawlo:books_distributed",  # 部分缺失
+        "crawlo:books_distributed:invalid_component:fingerprint",  # 无效组件
+        "crawlo:books_distributed:queue:invalid_subcomponent",  # 无效子组件
+        "crawlo:wrong_project:filter:fingerprint"  # 项目名称不匹配
+    ]
+    
+    for key in invalid_keys:
+        is_valid = validate_redis_key_naming(key, "books_distributed")
+        print(f"  ❌ {key} - {'通过' if is_valid else '失败'}")
+    
+    print()
+    
+    # 3. 批量验证Redis Key
+    print("3. 批量验证Redis Key:")
+    all_keys = valid_keys + invalid_keys
+    is_valid, invalid_keys_list = validate_multiple_redis_keys(all_keys, "books_distributed")
+    
+    print(f"  批量验证结果: {'全部通过' if is_valid else '存在无效Key'}")
+    if not is_valid:
+        print("  无效的Key:")
+        for key in invalid_keys_list:
+            print(f"    - {key}")
+    
+    print()
+    
+    # 4. 获取Redis Key信息
+    print("4. 获取Redis Key信息:")
+    sample_keys = [
+        "crawlo:api_data_collection:filter:fingerprint",
+        "crawlo:api_data_collection:queue:requests",
+        "crawlo:api_data_collection:item:fingerprint"
+    ]
+    
+    for key in sample_keys:
+        info = get_redis_key_info(key)
+        print(f"  Key: {key}")
+        if info['valid']:
+            print(f"    框架: {info['framework']}")
+            print(f"    项目: {info['project']}")
+            print(f"    组件: {info['component']}")
+            if 'sub_component' in info:
+                print(f"    子组件: {info['sub_component']}")
+        else:
+            print(f"    错误: {info.get('error', '无效')}")
+        print()
+    
+    # 5. 打印验证报告
+    print("5. 打印验证报告:")
+    print_validation_report(all_keys, "books_distributed")
+
+
+def demonstrate_advanced_validation():
+    """演示高级验证功能"""
+    print("\n=== 高级验证功能演示 ===\n")
+    
+    validator = RedisKeyValidator()
+    
+    # 1. 不指定项目名称的验证
+    print("1. 不指定项目名称的验证:")
+    key = "crawlo:any_project:filter:fingerprint"
+    is_valid = validator.validate_key_naming(key)  # 不指定项目名称
+    print(f"  {key} - {'通过' if is_valid else '失败'}")
+    
+    # 2. 验证不同项目的Key
+    print("\n2. 验证不同项目的Key:")
+    project_keys = {
+        "books_distributed": [
+            "crawlo:books_distributed:filter:fingerprint",
+            "crawlo:books_distributed:queue:requests"
+        ],
+        "api_data_collection": [
+            "crawlo:api_data_collection:filter:fingerprint",
+            "crawlo:api_data_collection:queue:requests"
+        ]
+    }
+    
+    for project_name, keys in project_keys.items():
+        print(f"  项目: {project_name}")
+        for key in keys:
+            is_valid = validator.validate_key_naming(key, project_name)
+            print(f"    {key} - {'通过' if is_valid else '失败'}")
+
+
+if __name__ == "__main__":
+    demonstrate_redis_key_validation()
     demonstrate_advanced_validation()