diff --git a/.ipynb_checkpoints/readme-checkpoint.MD b/.ipynb_checkpoints/readme-checkpoint.MD deleted file mode 100644 index ba82ebe..0000000 --- a/.ipynb_checkpoints/readme-checkpoint.MD +++ /dev/null @@ -1,14 +0,0 @@ - -## 代码为啥要这样写，我要这样写代码 - -A 代码模式 -用一个简单任务，展示各种软件工程需求（完成任务简单、可读性强、可复用高、维护成本低等）下的代码写法 - -B 面向对象设计模式 -用一个业务场景复现面向对象的经典设计模式 - -C 高性能模式 -考虑执行时间快，资源占用少的一些思路、办法和结论 - -D 制造工业级代码 -问题同 A ，以构建工业级的代码为目标，用多种方式做了优化提升演示 \ No newline at end of file diff --git a/A 代码模式/10 跑起来了/.ipynb_checkpoints/3 Hacker-checkpoint.py b/A 动机与模式/10 跑起来了/.ipynb_checkpoints/3 Hacker-checkpoint.py similarity index 100% rename from A 代码模式/10 跑起来了/.ipynb_checkpoints/3 Hacker-checkpoint.py rename to A 动机与模式/10 跑起来了/.ipynb_checkpoints/3 Hacker-checkpoint.py diff --git a/A 代码模式/10 跑起来了/1 最基础的写法.py b/A 动机与模式/10 跑起来了/1 最基础的写法.py similarity index 100% rename from A 代码模式/10 跑起来了/1 最基础的写法.py rename to A 动机与模式/10 跑起来了/1 最基础的写法.py diff --git a/A 代码模式/10 跑起来了/2 使用一些函数.py b/A 动机与模式/10 跑起来了/2 使用一些函数.py similarity index 100% rename from A 代码模式/10 跑起来了/2 使用一些函数.py rename to A 动机与模式/10 跑起来了/2 使用一些函数.py diff --git a/A 代码模式/10 跑起来了/3 Hacker.py b/A 动机与模式/10 跑起来了/3 Hacker.py similarity index 100% rename from A 代码模式/10 跑起来了/3 Hacker.py rename to A 动机与模式/10 跑起来了/3 Hacker.py diff --git a/A 代码模式/11 封装/函数封装/1 全局变量.py b/A 动机与模式/11 封装/函数封装/1 全局变量.py similarity index 100% rename from A 代码模式/11 封装/函数封装/1 全局变量.py rename to A 动机与模式/11 封装/函数封装/1 全局变量.py diff --git a/A 代码模式/11 封装/函数封装/2 临时变量传递.py b/A 动机与模式/11 封装/函数封装/2 临时变量传递.py similarity index 100% rename from A 代码模式/11 封装/函数封装/2 临时变量传递.py rename to A 动机与模式/11 封装/函数封装/2 临时变量传递.py diff --git a/A 代码模式/11 封装/函数封装/3 常见风格.py b/A 动机与模式/11 封装/函数封装/3 常见风格.py similarity index 100% rename from A 代码模式/11 封装/函数封装/3 常见风格.py rename to A 动机与模式/11 封装/函数封装/3 常见风格.py diff --git a/A 代码模式/11 封装/函数封装/4 递归.py b/A 动机与模式/11 封装/函数封装/4 递归.py similarity index 100% rename from A 代码模式/11 封装/函数封装/4 递归.py rename to A 动机与模式/11 封装/函数封装/4 递归.py diff --git a/A 代码模式/11 封装/对象封装/1 类对象.py b/A 动机与模式/11 封装/对象封装/1 类对象.py similarity index 100% rename from A 代码模式/11 封装/对象封装/1 类对象.py rename to A 动机与模式/11 封装/对象封装/1 类对象.py diff --git a/A 代码模式/11 封装/对象封装/2 字典对象.py b/A 动机与模式/11 封装/对象封装/2 字典对象.py similarity index 100% rename from A 代码模式/11 封装/对象封装/2 字典对象.py rename to A 动机与模式/11 封装/对象封装/2 字典对象.py diff --git a/A 代码模式/11 封装/流式调用/1 嵌套调用.py b/A 动机与模式/11 封装/流式调用/1 嵌套调用.py similarity index 100% rename from A 代码模式/11 封装/流式调用/1 嵌套调用.py rename to A 动机与模式/11 封装/流式调用/1 嵌套调用.py diff --git a/A 代码模式/11 封装/流式调用/2 方法bind.py b/A 动机与模式/11 封装/流式调用/2 方法bind.py similarity index 100% rename from A 代码模式/11 封装/流式调用/2 方法bind.py rename to A 动机与模式/11 封装/流式调用/2 方法bind.py diff --git a/A 代码模式/11 封装/流式调用/3 重载管道.py b/A 动机与模式/11 封装/流式调用/3 重载管道.py similarity index 100% rename from A 代码模式/11 封装/流式调用/3 重载管道.py rename to A 动机与模式/11 封装/流式调用/3 重载管道.py diff --git a/A 代码模式/11 封装/流式调用/4 类方法.py b/A 动机与模式/11 封装/流式调用/4 类方法.py similarity index 100% rename from A 代码模式/11 封装/流式调用/4 类方法.py rename to A 动机与模式/11 封装/流式调用/4 类方法.py diff --git a/A 代码模式/11 封装/流式调用/5 类方法.py b/A 动机与模式/11 封装/流式调用/5 类方法.py similarity index 100% rename from A 代码模式/11 封装/流式调用/5 类方法.py rename to A 动机与模式/11 封装/流式调用/5 类方法.py diff --git a/A 代码模式/12 语言特性/1 动态定制类/元类.py b/A 动机与模式/12 语言特性/1 动态定制类/元类.py similarity index 100% rename from A 代码模式/12 语言特性/1 动态定制类/元类.py rename to A 动机与模式/12 语言特性/1 动态定制类/元类.py diff --git a/A 代码模式/12 语言特性/2 暂停执行/1 生成器.py b/A 动机与模式/12 语言特性/2 暂停执行/1 生成器.py similarity index 100% rename from A 代码模式/12 语言特性/2 暂停执行/1 生成器.py rename to A 动机与模式/12 语言特性/2 暂停执行/1 生成器.py diff --git a/A 代码模式/12 语言特性/2 暂停执行/2 异步.py b/A 动机与模式/12 语言特性/2 暂停执行/2 异步.py similarity index 100% rename from A 代码模式/12 语言特性/2 暂停执行/2 异步.py rename to A 动机与模式/12 语言特性/2 暂停执行/2 异步.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/1 内省/1 内省.py b/A 动机与模式/12 语言特性/3 运行期符号表/1 内省/1 内省.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/1 内省/1 内省.py rename to A 动机与模式/12 语言特性/3 运行期符号表/1 内省/1 内省.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/2 装饰/1 反射装饰.py b/A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/1 反射装饰.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/2 装饰/1 反射装饰.py rename to A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/1 反射装饰.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/2 装饰/2 装饰器.py b/A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/2 装饰器.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/2 装饰/2 装饰器.py rename to A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/2 装饰器.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/2 装饰/3 参数类型检查.py b/A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/3 参数类型检查.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/2 装饰/3 参数类型检查.py rename to A 动机与模式/12 语言特性/3 运行期符号表/2 装饰/3 参数类型检查.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/3 反射/反射_函数.py b/A 动机与模式/12 语言特性/3 运行期符号表/3 反射/反射_函数.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/3 反射/反射_函数.py rename to A 动机与模式/12 语言特性/3 运行期符号表/3 反射/反射_函数.py diff --git a/A 代码模式/12 语言特性/3 运行期符号表/3 反射/反射_类.py b/A 动机与模式/12 语言特性/3 运行期符号表/3 反射/反射_类.py similarity index 100% rename from A 代码模式/12 语言特性/3 运行期符号表/3 反射/反射_类.py rename to A 动机与模式/12 语言特性/3 运行期符号表/3 反射/反射_类.py diff --git a/A 代码模式/13 多计算单元/数据共享/1 内存/1 队列.py b/A 动机与模式/13 多计算单元/数据共享/1 内存/1 队列.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/1 内存/1 队列.py rename to A 动机与模式/13 多计算单元/数据共享/1 内存/1 队列.py diff --git a/A 代码模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_不合并.py b/A 动机与模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_不合并.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_不合并.py rename to A 动机与模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_不合并.py diff --git a/A 代码模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_分包.py b/A 动机与模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_分包.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_分包.py rename to A 动机与模式/13 多计算单元/数据共享/2 本地服务/2 服务进程_分包.py diff --git a/A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/DataQuery.py b/A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/DataQuery.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/DataQuery.py rename to A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/DataQuery.py diff --git a/A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/createDb.py b/A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/createDb.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/createDb.py rename to A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/createDb.py diff --git a/A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/processData.py b/A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/processData.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/3 数据库/ORM/processData.py rename to A 动机与模式/13 多计算单元/数据共享/3 数据库/ORM/processData.py diff --git a/A 代码模式/13 多计算单元/数据共享/3 数据库/tf.db b/A 动机与模式/13 多计算单元/数据共享/3 数据库/tf.db similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/3 数据库/tf.db rename to A 动机与模式/13 多计算单元/数据共享/3 数据库/tf.db diff --git a/A 代码模式/13 多计算单元/数据共享/3 数据库/数据库.py b/A 动机与模式/13 多计算单元/数据共享/3 数据库/数据库.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/3 数据库/数据库.py rename to A 动机与模式/13 多计算单元/数据共享/3 数据库/数据库.py diff --git a/A 代码模式/13 多计算单元/数据共享/4 网络/restful/app.py b/A 动机与模式/13 多计算单元/数据共享/4 网络/restful/app.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/4 网络/restful/app.py rename to A 动机与模式/13 多计算单元/数据共享/4 网络/restful/app.py diff --git a/A 代码模式/13 多计算单元/数据共享/4 网络/restful/client.py b/A 动机与模式/13 多计算单元/数据共享/4 网络/restful/client.py similarity index 100% rename from A 代码模式/13 多计算单元/数据共享/4 网络/restful/client.py rename to A 动机与模式/13 多计算单元/数据共享/4 网络/restful/client.py diff --git a/A 代码模式/13 多计算单元/数据分包/1 mapreduce.py b/A 动机与模式/13 多计算单元/数据分包/1 mapreduce.py similarity index 100% rename from A 代码模式/13 多计算单元/数据分包/1 mapreduce.py rename to A 动机与模式/13 多计算单元/数据分包/1 mapreduce.py diff --git a/A 代码模式/13 多计算单元/数据分包/2 多线程.py b/A 动机与模式/13 多计算单元/数据分包/2 多线程.py similarity index 100% rename from A 代码模式/13 多计算单元/数据分包/2 多线程.py rename to A 动机与模式/13 多计算单元/数据分包/2 多线程.py diff --git a/A 代码模式/13 多计算单元/数据分包/3 多进程.py b/A 动机与模式/13 多计算单元/数据分包/3 多进程.py similarity index 100% rename from A 代码模式/13 多计算单元/数据分包/3 多进程.py rename to A 动机与模式/13 多计算单元/数据分包/3 多进程.py diff --git a/A 代码模式/13 多计算单元/数据分包/4 抽象并发.py b/A 动机与模式/13 多计算单元/数据分包/4 抽象并发.py similarity index 100% rename from A 代码模式/13 多计算单元/数据分包/4 抽象并发.py rename to A 动机与模式/13 多计算单元/数据分包/4 抽象并发.py diff --git a/A 代码模式/14 人机交互/1 终端/终端命令行/command_line_1.py b/A 动机与模式/14 人机交互/1 终端/终端命令行/command_line_1.py similarity index 100% rename from A 代码模式/14 人机交互/1 终端/终端命令行/command_line_1.py rename to A 动机与模式/14 人机交互/1 终端/终端命令行/command_line_1.py diff --git a/A 代码模式/14 人机交互/1 终端/终端命令行/command_line_2.py b/A 动机与模式/14 人机交互/1 终端/终端命令行/command_line_2.py similarity index 100% rename from A 代码模式/14 人机交互/1 终端/终端命令行/command_line_2.py rename to A 动机与模式/14 人机交互/1 终端/终端命令行/command_line_2.py diff --git a/A 代码模式/14 人机交互/1 终端/终端菜单/terminal_menu.py b/A 动机与模式/14 人机交互/1 终端/终端菜单/terminal_menu.py similarity index 100% rename from A 代码模式/14 人机交互/1 终端/终端菜单/terminal_menu.py rename to A 动机与模式/14 人机交互/1 终端/终端菜单/terminal_menu.py diff --git a/A 代码模式/14 人机交互/1 终端/终端菜单/test.txt b/A 动机与模式/14 人机交互/1 终端/终端菜单/test.txt similarity index 100% rename from A 代码模式/14 人机交互/1 终端/终端菜单/test.txt rename to A 动机与模式/14 人机交互/1 终端/终端菜单/test.txt diff --git a/A 代码模式/14 人机交互/2 视窗/PyQT.py b/A 动机与模式/14 人机交互/2 视窗/PyQT.py similarity index 100% rename from A 代码模式/14 人机交互/2 视窗/PyQT.py rename to A 动机与模式/14 人机交互/2 视窗/PyQT.py diff --git a/A 代码模式/14 人机交互/2 视窗/test.txt b/A 动机与模式/14 人机交互/2 视窗/test.txt similarity index 100% rename from A 代码模式/14 人机交互/2 视窗/test.txt rename to A 动机与模式/14 人机交互/2 视窗/test.txt diff --git a/A 代码模式/14 人机交互/3 Web/MVC/app.py b/A 动机与模式/14 人机交互/3 Web/MVC/app.py similarity index 100% rename from A 代码模式/14 人机交互/3 Web/MVC/app.py rename to A 动机与模式/14 人机交互/3 Web/MVC/app.py diff --git a/A 代码模式/14 人机交互/3 Web/MVC/models.py b/A 动机与模式/14 人机交互/3 Web/MVC/models.py similarity index 100% rename from A 代码模式/14 人机交互/3 Web/MVC/models.py rename to A 动机与模式/14 人机交互/3 Web/MVC/models.py diff --git a/A 代码模式/14 人机交互/3 Web/MVC/templates/index.html b/A 动机与模式/14 人机交互/3 Web/MVC/templates/index.html similarity index 100% rename from A 代码模式/14 人机交互/3 Web/MVC/templates/index.html rename to A 动机与模式/14 人机交互/3 Web/MVC/templates/index.html diff --git a/A 代码模式/14 人机交互/3 Web/simpleWeb/app.py b/A 动机与模式/14 人机交互/3 Web/simpleWeb/app.py similarity index 100% rename from A 代码模式/14 人机交互/3 Web/simpleWeb/app.py rename to A 动机与模式/14 人机交互/3 Web/simpleWeb/app.py diff --git a/A 代码模式/14 人机交互/3 Web/simpleWeb/templates/index.html b/A 动机与模式/14 人机交互/3 Web/simpleWeb/templates/index.html similarity index 100% rename from A 代码模式/14 人机交互/3 Web/simpleWeb/templates/index.html rename to A 动机与模式/14 人机交互/3 Web/simpleWeb/templates/index.html diff --git a/A 代码模式/14 人机交互/3 Web/simpleWeb/templates/result.html b/A 动机与模式/14 人机交互/3 Web/simpleWeb/templates/result.html similarity index 100% rename from A 代码模式/14 人机交互/3 Web/simpleWeb/templates/result.html rename to A 动机与模式/14 人机交互/3 Web/simpleWeb/templates/result.html diff --git a/A 代码模式/15 工程化考虑/1 复用/函数调用复用.py b/A 动机与模式/15 工程化考虑/1 复用/函数调用复用.py similarity index 100% rename from A 代码模式/15 工程化考虑/1 复用/函数调用复用.py rename to A 动机与模式/15 工程化考虑/1 复用/函数调用复用.py diff --git a/A 代码模式/15 工程化考虑/1 复用/对象复用.py b/A 动机与模式/15 工程化考虑/1 复用/对象复用.py similarity index 100% rename from A 代码模式/15 工程化考虑/1 复用/对象复用.py rename to A 动机与模式/15 工程化考虑/1 复用/对象复用.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/1 观察者/1 观察者.py b/A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/1 观察者.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/1 观察者/1 观察者.py rename to A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/1 观察者.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/1 观察者/2 观察者.py b/A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/2 观察者.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/1 观察者/2 观察者.py rename to A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/2 观察者.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/1 观察者/3 注册回调.py b/A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/3 注册回调.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/1 观察者/3 注册回调.py rename to A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/3 注册回调.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/1 观察者/4 订阅发布.py b/A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/4 订阅发布.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/1 观察者/4 订阅发布.py rename to A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/4 订阅发布.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/1 观察者/readme.MD b/A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/readme.MD similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/1 观察者/readme.MD rename to A 动机与模式/15 工程化考虑/2 松耦合/1 观察者/readme.MD diff --git a/A 代码模式/15 工程化考虑/2 松耦合/2 消息链/1 只有消息接口.py b/A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/1 只有消息接口.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/2 消息链/1 只有消息接口.py rename to A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/1 只有消息接口.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/2 消息链/2 调用链.py b/A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/2 调用链.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/2 消息链/2 调用链.py rename to A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/2 调用链.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/2 消息链/3 消息链.py b/A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/3 消息链.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/2 消息链/3 消息链.py rename to A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/3 消息链.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/2 消息链/4 消息队列.py b/A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/4 消息队列.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/2 消息链/4 消息队列.py rename to A 动机与模式/15 工程化考虑/2 松耦合/2 消息链/4 消息队列.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/3 微服务/client_app.py b/A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/client_app.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/3 微服务/client_app.py rename to A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/client_app.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/3 微服务/counter_service.py b/A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/counter_service.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/3 微服务/counter_service.py rename to A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/counter_service.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/3 微服务/sorter_service.py b/A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/sorter_service.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/3 微服务/sorter_service.py rename to A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/sorter_service.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/3 微服务/tokenizer_service.py b/A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/tokenizer_service.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/3 微服务/tokenizer_service.py rename to A 动机与模式/15 工程化考虑/2 松耦合/3 微服务/tokenizer_service.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/config.ini b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/config.ini similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/config.ini rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/config.ini diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugin.py b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugin.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugin.py rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugin.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/buildingPyc.py b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/buildingPyc.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/buildingPyc.py rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/buildingPyc.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f1.py b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f1.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f1.py rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f1.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f2.py b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f2.py similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f2.py rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins-src/f2.py diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins/f1.pyc b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins/f1.pyc similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins/f1.pyc rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins/f1.pyc diff --git a/A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins/f2.pyc b/A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins/f2.pyc similarity index 100% rename from A 代码模式/15 工程化考虑/2 松耦合/4 插件/plugins/f2.pyc rename to A 动机与模式/15 工程化考虑/2 松耦合/4 插件/plugins/f2.pyc diff --git a/A 代码模式/15 工程化考虑/3 类型申明/参数类型申明.py b/A 动机与模式/15 工程化考虑/3 类型申明/参数类型申明.py similarity index 100% rename from A 代码模式/15 工程化考虑/3 类型申明/参数类型申明.py rename to A 动机与模式/15 工程化考虑/3 类型申明/参数类型申明.py diff --git a/A 代码模式/15 工程化考虑/4 对象接口/tf-14A.py b/A 动机与模式/15 工程化考虑/4 对象接口/tf-14A.py similarity index 100% rename from A 代码模式/15 工程化考虑/4 对象接口/tf-14A.py rename to A 动机与模式/15 工程化考虑/4 对象接口/tf-14A.py diff --git a/A 代码模式/15 工程化考虑/4 对象接口/tf-14B.py b/A 动机与模式/15 工程化考虑/4 对象接口/tf-14B.py similarity index 100% rename from A 代码模式/15 工程化考虑/4 对象接口/tf-14B.py rename to A 动机与模式/15 工程化考虑/4 对象接口/tf-14B.py diff --git a/A 代码模式/15 工程化考虑/5 对象属性 .py b/A 动机与模式/15 工程化考虑/5 对象属性 .py similarity index 100% rename from A 代码模式/15 工程化考虑/5 对象属性 .py rename to A 动机与模式/15 工程化考虑/5 对象属性 .py diff --git a/A 代码模式/16 其它/2 异常/1 软件不能挂掉.py b/A 动机与模式/16 其它/2 异常/1 软件不能挂掉.py similarity index 100% rename from A 代码模式/16 其它/2 异常/1 软件不能挂掉.py rename to A 动机与模式/16 其它/2 异常/1 软件不能挂掉.py diff --git a/A 代码模式/16 其它/2 异常/2 时间停止在那一刻.py b/A 动机与模式/16 其它/2 异常/2 时间停止在那一刻.py similarity index 100% rename from A 代码模式/16 其它/2 异常/2 时间停止在那一刻.py rename to A 动机与模式/16 其它/2 异常/2 时间停止在那一刻.py diff --git a/A 代码模式/16 其它/2 异常/3 所有错误的应对.py b/A 动机与模式/16 其它/2 异常/3 所有错误的应对.py similarity index 100% rename from A 代码模式/16 其它/2 异常/3 所有错误的应对.py rename to A 动机与模式/16 其它/2 异常/3 所有错误的应对.py diff --git a/A 代码模式/16 其它/3 状态机/81A.py b/A 动机与模式/16 其它/3 状态机/81A.py similarity index 100% rename from A 代码模式/16 其它/3 状态机/81A.py rename to A 动机与模式/16 其它/3 状态机/81A.py diff --git a/A 代码模式/cppy/cp_util.py b/A 动机与模式/cppy/cp_util.py similarity index 100% rename from A 代码模式/cppy/cp_util.py rename to A 动机与模式/cppy/cp_util.py diff --git a/A 代码模式/cppy/data/Prey.txt b/A 动机与模式/cppy/data/Prey.txt similarity index 100% rename from A 代码模式/cppy/data/Prey.txt rename to A 动机与模式/cppy/data/Prey.txt diff --git a/A 代码模式/cppy/data/pride-and-prejudice.txt b/A 动机与模式/cppy/data/pride-and-prejudice.txt similarity index 100% rename from A 代码模式/cppy/data/pride-and-prejudice.txt rename to A 动机与模式/cppy/data/pride-and-prejudice.txt diff --git a/A 代码模式/cppy/data/stop_words.txt b/A 动机与模式/cppy/data/stop_words.txt similarity index 100% rename from A 代码模式/cppy/data/stop_words.txt rename to A 动机与模式/cppy/data/stop_words.txt diff --git a/A 代码模式/cppy/data/test.txt b/A 动机与模式/cppy/data/test.txt similarity index 100% rename from A 代码模式/cppy/data/test.txt rename to A 动机与模式/cppy/data/test.txt diff --git a/A 代码模式/readme.MD b/A 动机与模式/readme.MD similarity index 100% rename from A 代码模式/readme.MD rename to A 动机与模式/readme.MD diff --git a/C 高性能模式/readme.md b/C 高性能编程/.ipynb_checkpoints/readme-checkpoint.md similarity index 100% rename from C 高性能模式/readme.md rename to C 高性能编程/.ipynb_checkpoints/readme-checkpoint.md diff --git a/C 高性能模式/02 操作系统相关知识.md b/C 高性能编程/02 操作系统相关知识.md similarity index 100% rename from C 高性能模式/02 操作系统相关知识.md rename to C 高性能编程/02 操作系统相关知识.md diff --git a/C 高性能模式/03 多线程的应用场景.md b/C 高性能编程/03 多线程的应用场景.md similarity index 100% rename from C 高性能模式/03 多线程的应用场景.md rename to C 高性能编程/03 多线程的应用场景.md diff --git a/C 高性能模式/04 其它知识.md b/C 高性能编程/04 其它知识.md similarity index 100% rename from C 高性能模式/04 其它知识.md rename to C 高性能编程/04 其它知识.md diff --git a/C 高性能模式/case_股票分析.md b/C 高性能编程/case_股票分析.md similarity index 100% rename from C 高性能模式/case_股票分析.md rename to C 高性能编程/case_股票分析.md diff --git a/C 高性能模式/case_股票分析.py b/C 高性能编程/case_股票分析.py similarity index 100% rename from C 高性能模式/case_股票分析.py rename to C 高性能编程/case_股票分析.py diff --git a/C 高性能编程/readme.md b/C 高性能编程/readme.md new file mode 100644 index 0000000..ef89afe --- /dev/null +++ b/C 高性能编程/readme.md @@ -0,0 +1,44 @@ + +从计算机系统结构的角度，提高 Python 任务执行速度的核心在于：减少解释器开销（编译/JIT）、提升并行性（多核/GPU）、优化内存访问（缓存友好）、降低 I/O 瓶颈以及适配硬件特性等。当前主要办法如下： + + +### 计算单元层面利用多核并行计算 +对于 CPU 密集型任务，使用多进程，每个进程拥有独立的 Python 解释器和内存空间，运行在独立的内核上，实现并行计算。 + + +### I/O 层面减少等待时间 +- 异步编程：针对I/O请求等待，手工实现任务切换，完成并发执行. +- 多线程：解释器自动完成I/O请求的线程切换 。 +- 批量处理，减少I/O请求数量 。 + + +### 编译层面减少解释器开销 +- 使用 JIT 编译器：Just-In-Time（JIT）编译可以在运行时将Python代码编译成机器码，从而提升执行速度 。PyPy 是一种替代 CPython 的实现，PyPy 的 JIT 引擎可以分析代码执行路径，优化频繁调用的函数，充分利用处理器架构。 +- **Cython 编译**：Cython 允许开发者为 Python 代码添加 C 类型注解，并编译为 C 代码，再由 C 编译器生成机器码。Cython 特别适合静态类型优化场景。 + + +### 利用Python的解释器特性 +- **使用内置数据类型和函数**：内置的数据类型（如列表、字典、集合等）和函数通常经过高度优化。 +- **选择合适的数据结构**：例如，一些类型执行一些操作更快，一些类型更省空间。 +- **减少全局变量的使用**：访问全局变量通常比局部变量慢，因为它们需要在更大的作用域中查找。 +- **减少函数调用**，可降低堆栈操作开销。 +- 使用列表推导式替代循环，降低频繁创建和销毁临时对象的开销。 +- 使用生成器而不是列表来处理大数据集，以减少内存占用。 +- 使用XX池或预分配资源。 + + +### 使用第三方高性能库 +- NumPy/Pandas 用 C/C++ 编写并经过优化,使用连续内存块存储数据，向量化操作比显式的Python循环更高效。 +- SIMD 指令加速，NumPy、Numba、Pandas/SciPy 都使用了 SIMD。Cython 可以直接用 C 代码使用 SIMD 。 +- `gzip` 模块可压缩数据，减少网络传输的数据量，提高网络传输速度。 +- `mmap` 模块实现内存映射文件，在处理超大文件、优化I/O性能以及进程间通信方面具有显著优势。 +- `functools.lru_cache` 缓存计算结果，避免重复计算 。 + + +### 使用性能分析工具 +如 cProfile 、Py-Spy、timeit 或 line_profiler + +## 总结 +具体实施时，应结合性能分析工具定位瓶颈，并根据任务特点选择合适的策略 。 +当然计算设备方面也可以简单提升：多机、更快的 CPU、更多核的CPU、更多的内存、更快的存储、增加 GPU/FPGA/TPU 。 +此外，随着Python社区的发展，新的技术和工具不断涌现，开发者应持续关注最新进展，以便更好地优化自己的代码 。 \ No newline at end of file diff --git a/D Plus/.ipynb_checkpoints/01 特殊执行方式的语言特性.ipynb-checkpoint.ipynb b/D Plus/.ipynb_checkpoints/01 特殊执行方式的语言特性.ipynb-checkpoint.ipynb deleted file mode 100644 index 65b84ab..0000000 --- a/D Plus/.ipynb_checkpoints/01 特殊执行方式的语言特性.ipynb-checkpoint.ipynb +++ /dev/null @@ -1,312 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "id": "86405617-889a-40c2-a895-7b51fb14b65d", - "metadata": {}, - "source": [ - "# 教学目标\n", - "\n", - "- 在词频统计案例中引入装饰器和函数式编程 。\n", - "- 分析这些特性和模式如何进一步优化代码质量（可读性、可维护性、可扩展性、复用性）。\n", - "- 探讨高级特性在案例中的适用性与局限性。" - ] - }, - { - "cell_type": "markdown", - "id": "e6a6a633-d3af-4778-815c-4490dff5f624", - "metadata": {}, - "source": [ - "## 第一部分：引入装饰器\n", - "\n", - "装饰器可用于在不修改函数代码的情况下添加功能。适合日志记录、性能分析、错误处理等场景。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "3a5c7d69-d445-4a9c-bb48-7fde0a36c646", - "metadata": {}, - "outputs": [], - "source": [ - "# 为 TextAnalyzer 类添加一个装饰器，用于记录方法执行时间。\n", - "\n", - "import os\n", - "import jieba\n", - "from collections import Counter\n", - "import yaml\n", - "import time\n", - "import functools\n", - "\n", - "def timing_decorator(func):\n", - " \"\"\"装饰器：记录函数执行时间\"\"\"\n", - " @functools.wraps(func)\n", - " def wrapper(*args, **kwargs):\n", - " start_time = time.time()\n", - " result = func(*args, **kwargs)\n", - " end_time = time.time()\n", - " print(f\"{func.__name__} took {end_time - start_time:.4f} seconds\")\n", - " return result\n", - " return wrapper\n", - "\n", - "class TextAnalyzer:\n", - " def __init__(self, config_path='config.yaml'):\n", - " with open(config_path, 'r', encoding='utf-8') as f:\n", - " config = yaml.safe_load(f)\n", - " self.data_dir = config['data_dir']\n", - " self.top_n = config['top_n']\n", - " self.stop_words_file = config['stop_words_file']\n", - " self.output_file = config['output_file']\n", - " self.word_count = Counter()\n", - " self.stop_words = self.load_stop_words()\n", - "\n", - " def load_stop_words(self):\n", - " \"\"\"加载停用词\"\"\"\n", - " try:\n", - " with open(self.stop_words_file, 'r', encoding='utf-8') as f:\n", - " return set(line.strip() for line in f if line.strip())\n", - " except Exception as e:\n", - " print(f\"Error loading stop words: {e}\")\n", - " return set()\n", - "\n", - " @timing_decorator\n", - " def read_file(self, file_path):\n", - " \"\"\"读取文件内容\"\"\"\n", - " try:\n", - " with open(file_path, 'r', encoding='utf-8') as f:\n", - " return f.read()\n", - " except Exception as e:\n", - " print(f\"Error reading {file_path}: {e}\")\n", - " return \"\"\n", - "\n", - " @timing_decorator\n", - " def tokenize(self, text):\n", - " \"\"\"中文分词并过滤停用词\"\"\"\n", - " words = jieba.lcut(text)\n", - " return [word for word in words if word not in self.stop_words]\n", - "\n", - " def process_file(self, file_path):\n", - " \"\"\"处理单个文件\"\"\"\n", - " if file_path.endswith('.txt'):\n", - " text = self.read_file(file_path)\n", - " words = self.tokenize(text)\n", - " self.word_count.update(words)\n", - "\n", - " def process_directory(self):\n", - " \"\"\"处理目录下所有文件\"\"\"\n", - " for file in os.listdir(self.data_dir):\n", - " file_path = os.path.join(self.data_dir, file)\n", - " self.process_file(file_path)\n", - "\n", - " def get_top_words(self):\n", - " \"\"\"获取前 N 高频词\"\"\"\n", - " return self.word_count.most_common(self.top_n)\n", - "\n", - " def save_results(self, top_words):\n", - " \"\"\"保存结果到文件\"\"\"\n", - " with open(self.output_file, 'w', encoding='utf-8') as f:\n", - " for word, count in top_words:\n", - " f.write(f\"{word}: {count}\\n\")\n", - "\n", - " def run(self):\n", - " \"\"\"执行词频统计并保存结果\"\"\"\n", - " self.process_directory()\n", - " top_words = self.get_top_words()\n", - " self.save_results(top_words)\n", - " for word, count in top_words:\n", - " print(f\"{word}: {count}\")" - ] - }, - { - "cell_type": "markdown", - "id": "4dcabfd9-b8f9-4796-a060-9d9f6689e92f", - "metadata": {}, - "source": [ - "### 装饰器分析\n", - "\n", - "功能：timing_decorator 记录 read_file 和 tokenize 方法的执行时间，帮助分析性能瓶颈（如分词耗时较长）。\n", - "\n", - "工程质量提升：\n", - " - 可维护性：无需修改原方法代码即可添加性能监控，符合开闭原则,维护更方便。\n", - " - 可读性：装饰器将性能监控逻辑与业务逻辑分离，代码更清晰。\n", - " - 复用性：timing_decorator 可复用于其他方法或项目。\n", - "\n", - "局限性：装饰器增加少量性能开销，需谨慎用于高频调用的函数。" - ] - }, - { - "cell_type": "markdown", - "id": "8fcbe48d-de8f-4387-9be3-f05f88553029", - "metadata": {}, - "source": [ - "## 第二部分：引入函数式编程\n", - "\n", - "函数式编程（如高阶函数、lambda、map/reduce）强调无变量污染、数据转换简洁性。在词频统计案例中，函数式编程可用于：\n", - "- 数据处理：使用 map 和 filter 处理文件和单词。\n", - "- 词频统计：使用 reduce 合并词频。\n", - "- 管道式处理：通过函数组合实现数据流处理。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "1a6970b2-7488-43e3-ae9f-0174ff9b4b57", - "metadata": {}, - "outputs": [], - "source": [ - "# 函数式处理文件和词频\n", - "\n", - "import os\n", - "import jieba\n", - "from collections import Counter\n", - "import yaml\n", - "from functools import reduce\n", - "from typing import List, Tuple\n", - "\n", - "def timing_decorator(func):\n", - " \"\"\"装饰器：记录函数执行时间\"\"\"\n", - " import time\n", - " import functools\n", - " @functools.wraps(func)\n", - " def wrapper(*args, **kwargs):\n", - " start_time = time.time()\n", - " result = func(*args, **kwargs)\n", - " end_time = time.time()\n", - " print(f\"{func.__name__} took {end_time - start_time:.4f} seconds\")\n", - " return result\n", - " return wrapper\n", - "\n", - "class TextAnalyzer:\n", - " def __init__(self, config_path='config.yaml'):\n", - " with open(config_path, 'r', encoding='utf-8') as f:\n", - " config = yaml.safe_load(f)\n", - " self.data_dir = config['data_dir']\n", - " self.top_n = config['top_n']\n", - " self.stop_words_file = config['stop_words_file']\n", - " self.output_file = config['output_file']\n", - " self.stop_words = self.load_stop_words()\n", - "\n", - " def load_stop_words(self) -> set:\n", - " \"\"\"加载停用词\"\"\"\n", - " try:\n", - " with open(self.stop_words_file, 'r', encoding='utf-8') as f:\n", - " return set(line.strip() for line in f if line.strip())\n", - " except Exception as e:\n", - " print(f\"Error loading stop words: {e}\")\n", - " return set()\n", - "\n", - " @timing_decorator\n", - " def read_file(self, file_path: str) -> str:\n", - " \"\"\"读取文件内容\"\"\"\n", - " try:\n", - " with open(file_path, 'r', encoding='utf-8') as f:\n", - " return f.read()\n", - " except Exception as e:\n", - " print(f\"Error reading {file_path}: {e}\")\n", - " return \"\"\n", - "\n", - " def tokenize(self, text: str) -> List[str]:\n", - " \"\"\"中文分词并过滤停用词（函数式）\"\"\"\n", - " return list(filter(lambda w: w not in self.stop_words, jieba.lcut(text)))\n", - "\n", - " def process_file(self, file_path: str) -> Counter:\n", - " \"\"\"处理单个文件，返回词频 Counter\"\"\"\n", - " if file_path.endswith('.txt'):\n", - " text = self.read_file(file Couple(path)\n", - " words = self.tokenize(text)\n", - " return Counter(words)\n", - " return Counter()\n", - "\n", - " def process_directory(self) -> Counter:\n", - " \"\"\"处理目录下所有文件（函数式）\"\"\"\n", - " file_paths = (os.path.join(self.data_dir, f) for f in os.listdir(self.data_dir))\n", - " counters = map(self.process_file, file_paths)\n", - " return reduce(lambda c1, c2: c1 + c2, counters, Counter())\n", - "\n", - " def get_top_words(self, word_count: Counter) -> List[Tuple[str, int]]:\n", - " \"\"\"获取前 N 高频词\"\"\"\n", - " return word_count.most_common(self.top_n)\n", - "\n", - " def save_results(self, top_words: List[Tuple[str, int]]):\n", - " \"\"\"保存结果到文件\"\"\"\n", - " with open(self.output_file, 'w', encoding='utf-8') as f:\n", - " for word, count in top_words:\n", - " f.write(f\"{word}: {count}\\n\")\n", - "\n", - " def run(self):\n", - " \"\"\"执行词频统计并保存结果\"\"\"\n", - " word_count = self.process_directory()\n", - " top_words = self.get_top_words(word_count)\n", - " self.save_results(top_words)\n", - " for word, count in top_words:\n", - " print(f\"{word}: {count}\")" - ] - }, - { - "cell_type": "markdown", - "id": "6ce3b7c3-f099-4e2c-b415-18b0e3ab492a", - "metadata": {}, - "source": [ - "### 函数式编程分析\n", - "\n", - "改进：\n", - "- map：在 process_directory 中，使用 map(self.process_file, file_paths) 并行处理文件路径，生成词频 Counter 列表。\n", - "- reduce：使用 reduce(lambda c1, c2: c1 + c2, counters, Counter()) 合并所有文件的词频，简洁且无副作用。\n", - "- filter：在 tokenize 中，使用 filter(lambda w: w not in self.stop_words, ...) 过滤停用词，替代列表推导式。\n", - "- 生成器：file_paths 使用生成器表达式，减少内存占用。\n", - "\n", - "工程质量提升：\n", - "- 可读性：函数式编程使数据处理逻辑更简洁，管道式处理清晰表达数据流（文件路径 -> 词频 -> 合并）。\n", - "- 性能：生成器和 map 优化内存使用，适合处理大量文件。\n", - "- 可维护性：函数式代码无副作用，易于测试和调试。\n", - "- 适用场景：适合数据转换和批量处理（如文件读取、词频合并）。\n", - "- 简洁性：map、reduce 等使数据处理逻辑更紧凑。\n", - "- 内存效率：生成器和惰性求值优化内存使用。\n", - "- 结合并发可显著提升效率。\n", - "\n", - "适用场景：数据流处理（如文件处理、词频合并）、无状态操作。\n", - "\n", - "局限性：\n", - "- 函数式代码对初学者可能不够直观，需熟悉 map、reduce 等概念。\n", - "- 对于复杂逻辑，函数式编程可能增加调试难度。" - ] - }, - { - "cell_type": "markdown", - "id": "458e18ec-b536-4860-9e12-d0bf5ed9d876", - "metadata": {}, - "source": [ - "# 练习\n", - "\n", - "实践练习：\n", - "- 添加日志装饰器，记录每次文件处理的详细信息。\n", - "- 使用 functools.reduce 重写 get_top_words，尝试不同排序逻辑。\n", - "\n", - "扩展任务：\n", - "- 添加缓存装饰器，避免重复分词相同文件。\n", - "- 实现函数式管道，将文件读取、分词、统计串联为单一流。" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.12.7" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/D Plus/.ipynb_checkpoints/99 工业级代码-checkpoint.ipynb b/D Plus/.ipynb_checkpoints/99 工业级代码-checkpoint.ipynb deleted file mode 100644 index b88eaf7..0000000 --- a/D Plus/.ipynb_checkpoints/99 工业级代码-checkpoint.ipynb +++ /dev/null @@ -1,665 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": null, - "id": "b6bc2a3c-3b15-4bc5-83a2-adeae3b7b4d0", - "metadata": {}, - "outputs": [], - "source": [ - "## 项目结构\n", - "\n", - "word_frequency_project/\n", - "│\n", - "├── data/ # 小说文本存放目录\n", - "│ ├── novel1.txt\n", - "│ ├── novel2.txt\n", - "│ └── ...\n", - "├── src/ # 源代码目录\n", - "│ ├── __init__.py\n", - "│ ├── config.py # 配置文件\n", - "│ ├── data_loader.py # 数据加载模块\n", - "│ ├── preprocessor.py # 文本预处理模块\n", - "│ ├── word_counter.py # 词频统计模块\n", - "│ ├── output_formatter.py # 输出格式化模块\n", - "│ └── main.py # 主程序入口\n", - "├── tests/ # 单元测试目录\n", - "│ ├── __init__.py\n", - "│ ├── test_data_loader.py\n", - "│ ├── test_preprocessor.py\n", - "│ ├── test_word_counter.py\n", - "│ └── test_output_formatter.py\n", - "├── requirements.txt # 依赖文件\n", - "└── README.md # 项目说明" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "d0b55f2e-24ba-49da-8d11-f0f5eea611b0", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/config.py\n", - "定义配置项，便于扩展和修改。\n", - "'''\n", - "\n", - "import os\n", - "\n", - "class Config:\n", - " DATA_DIR = \"data\"\n", - " TOP_N_WORDS = 10\n", - " STOP_WORDS = {\"的\", \"了\", \"是\", \"在\", \"和\", \"我\", \"你\", \"他\", \"她\"} # 示例停用词\n", - " ENCODING = \"utf-8\"\n", - " LOG_LEVEL = \"INFO\"\n", - "\n", - " @classmethod\n", - " def get_data_dir(cls):\n", - " return os.path.join(os.path.dirname(__file__), \"..\", cls.DATA_DIR)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "e5bdcdf0-16a2-4dda-85f1-d018c6370aee", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/data_loader.py\n", - "负责加载小说文本，支持目录扫描和文件读取，提供扩展点以支持不同格式。\n", - "'''\n", - "\n", - "import os\n", - "import logging\n", - "from src.config import Config\n", - "\n", - "class DataLoader:\n", - " def __init__(self):\n", - " self.data_dir = Config.get_data_dir()\n", - " logging.basicConfig(level=Config.LOG_LEVEL)\n", - " self.logger = logging.getLogger(__name__)\n", - "\n", - " def load_texts(self):\n", - " \"\"\"加载 data 目录下的所有文本文件\"\"\"\n", - " texts = []\n", - " try:\n", - " for filename in os.listdir(self.data_dir):\n", - " if filename.endswith(\".txt\"):\n", - " file_path = os.path.join(self.data_dir, filename)\n", - " with open(file_path, \"r\", encoding=Config.ENCODING) as f:\n", - " texts.append(f.read())\n", - " self.logger.info(f\"Loaded file: {filename}\")\n", - " if not texts:\n", - " self.logger.warning(\"No text files found in data directory\")\n", - " return texts\n", - " except Exception as e:\n", - " self.logger.error(f\"Error loading files: {str(e)}\")\n", - " raise" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "786e7ffa-82bc-46b9-8ffc-444d6796b87b", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/preprocessor.py\n", - "文本预处理模块，负责分词和清理，支持扩展以添加更多预处理逻辑。\n", - "'''\n", - "\n", - "import jieba\n", - "import re\n", - "from src.config import Config\n", - "\n", - "def timing_decorator(func):\n", - " \"\"\"装饰器：记录方法执行时间\"\"\"\n", - " import time\n", - " def wrapper(*args, **kwargs):\n", - " start = time.time()\n", - " result = func(*args, **kwargs)\n", - " end = time.time()\n", - " print(f\"{func.__name__} took {end - start:.2f} seconds\")\n", - " return result\n", - " return wrapper\n", - "\n", - "class TextPreprocessor:\n", - " def __init__(self):\n", - " self.stop_words = Config.STOP_WORDS\n", - "\n", - " @timing_decorator\n", - " def preprocess(self, text):\n", - " \"\"\"预处理：分词、去除停用词和非中文字符\"\"\"\n", - " # 移除非中文字符\n", - " text = re.sub(r\"[^\\u4e00-\\u9fff]\", \" \", text)\n", - " # 分词\n", - " words = jieba.cut(text)\n", - " # 过滤停用词和空字符\n", - " return [word for word in words if word.strip() and word not in self.stop_words]" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "4edd5ca7-4ba7-4446-b93e-2cfd83efca2e", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/word_counter.py\n", - "词频统计模块，使用单例模式确保全局唯一计数器。\n", - "'''\n", - "\n", - "from collections import Counter\n", - "from typing import List, Dict\n", - "\n", - "class Singleton: 为啥需要单例？\n", - " \"\"\"单例模式装饰器\"\"\"\n", - " def __init__(self, cls):\n", - " self._cls = cls\n", - " self._instance = None\n", - "\n", - " def __call__(self, *args, **kwargs):\n", - " if self._instance is None:\n", - " self._instance = self._cls(*args, **kwargs)\n", - " return self._instance\n", - "\n", - "@Singleton\n", - "class WordCounter:\n", - " def __init__(self):\n", - " self.counter = Counter()\n", - "\n", - " def count_words(self, words: List[str]) -> None:\n", - " \"\"\"更新词频统计\"\"\"\n", - " self.counter.update(words)\n", - "\n", - " def get_top_n(self, n: int = 10) -> Dict[str, int]:\n", - " \"\"\"获取前 N 个高频词\"\"\"\n", - " return dict(self.counter.most_common(n))\n", - "\n", - " def reset(self):\n", - " \"\"\"重置计数器\"\"\"\n", - " self.counter.clear()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "41af3e0e-3153-4d23-9a9f-65b566b384e8", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/output_formatter.py\n", - "输出格式化模块，支持多种输出格式，便于扩展。\n", - "'''\n", - "\n", - "from typing import Dict\n", - "\n", - "class OutputFormatter:\n", - " @staticmethod\n", - " def format_json(data: Dict[str, int]) -> str:\n", - " import json\n", - " return json.dumps(data, ensure_ascii=False, indent=2)\n", - "\n", - " @staticmethod\n", - " def format_text(data: Dict[str, int]) -> str:\n", - " return \"\\n\".join(f\"{word}: {count}\" for word, count in data.items())" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "6596162c-fd42-4b32-b328-9987568b3846", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "src/main.py\n", - "主程序入口，协调各模块工作。\n", - "'''\n", - "\n", - "from src.data_loader import DataLoader\n", - "from src.preprocessor import TextPreprocessor\n", - "from src.word_counter import WordCounter\n", - "from src.output_formatter import OutputFormatter\n", - "from src.config import Config\n", - "\n", - "def main():\n", - " # 初始化模块\n", - " loader = DataLoader()\n", - " preprocessor = TextPreprocessor()\n", - " counter = WordCounter()\n", - " formatter = OutputFormatter()\n", - "\n", - " # 加载文本\n", - " texts = loader.load_texts()\n", - "\n", - " # 预处理并统计词频\n", - " for text in texts:\n", - " words = preprocessor.preprocess(text)\n", - " counter.count_words(words)\n", - "\n", - " # 获取结果\n", - " top_words = counter.get_top_n(Config.TOP_N_WORDS)\n", - "\n", - " # 输出结果\n", - " print(\"=== Top 10 Words (Text Format) ===\")\n", - " print(formatter.format_text(top_words))\n", - " print(\"\\n=== Top 10 Words (JSON Format) ===\")\n", - " print(formatter.format_json(top_words))\n", - "\n", - "if __name__ == \"__main__\":\n", - " main()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "36a32f17-5ce3-46e2-a563-f151454f6342", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "tests/test_data_loader.py\n", - "单元测试示例，确保数据加载模块的正确性。\n", - "'''\n", - "\n", - "import unittest\n", - "import os\n", - "from src.data_loader import DataLoader\n", - "from src.config import Config\n", - "\n", - "class TestDataLoader(unittest.TestCase):\n", - " def setUp(self):\n", - " self.loader = DataLoader()\n", - " # 创建临时测试文件\n", - " self.test_file = os.path.join(Config.get_data_dir(), \"test_novel.txt\")\n", - " with open(self.test_file, \"w\", encoding=Config.ENCODING) as f:\n", - " f.write(\"这是一个测试文本\")\n", - "\n", - " def test_load_texts(self):\n", - " texts = self.loader.load_texts()\n", - " self.assertGreater(len(texts), 0)\n", - " self.assertIn(\"这是一个测试文本\", texts)\n", - "\n", - " def tearDown(self):\n", - " if os.path.exists(self.test_file):\n", - " os.remove(self.test_file)\n", - "\n", - "if __name__ == \"__main__\":\n", - " unittest.main()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "1f550544-f0f4-4f0c-bdb7-9928b6820bdf", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "tests/test_preprocessor.py\n", - "测试文本预处理模块。\n", - "'''\n", - "\n", - "import unittest\n", - "from src.preprocessor import TextPreprocessor\n", - "\n", - "class TestTextPreprocessor(unittest.TestCase):\n", - " def setUp(self):\n", - " self.preprocessor = TextPreprocessor()\n", - "\n", - " def test_preprocess(self):\n", - " text = \"这是一个测试文本，包含了123和一些符号！\"\n", - " words = self.preprocessor.preprocess(text)\n", - " expected = [\"测试\", \"文本\", \"包含\", \"一些\", \"符号\"]\n", - " self.assertEqual(words, expected)\n", - "\n", - "if __name__ == \"__main__\":\n", - " unittest.main()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "8fb8b4cd-0b27-426a-9556-8f21227c5374", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "tests/test_word_counter.py\n", - "测试词频统计模块。\n", - "'''\n", - "import unittest\n", - "from src.word_counter import WordCounter\n", - "\n", - "class TestWordCounter(unittest.TestCase):\n", - " def setUp(self):\n", - " self.counter = WordCounter()\n", - "\n", - " def test_count_words(self):\n", - " self.counter.count_words([\"测试\", \"文本\", \"测试\"])\n", - " result = self.counter.get_top_n(2)\n", - " expected = {\"测试\": 2, \"文本\": 1}\n", - " self.assertEqual(result, expected)\n", - "\n", - " def test_reset(self):\n", - " self.counter.count_words([\"测试\"])\n", - " self.counter.reset()\n", - " self.assertEqual(self.counter.get_top_n(1), {})\n", - "\n", - "if __name__ == \"__main__\":\n", - " unittest.main()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "4b7507dc-b693-4dbf-9a21-5f2833d13d0e", - "metadata": {}, - "outputs": [], - "source": [ - "'''\n", - "requirements.txt\n", - "列出项目依赖。\n", - "''''\n", - "jieba==0.42.1" - ] - }, - { - "cell_type": "markdown", - "id": "573c4ddd-800e-4b59-9e20-a87d6a2b14cd", - "metadata": {}, - "source": [ - "'''\n", - "README.md\n", - "提供项目说明和使用方法。\n", - "'''\n", - "# Word Frequency Analysis Project\n", - "\n", - "## Overview\n", - "This project processes 100 novels in the `data` directory, counts word frequencies, and outputs the top 10 words. It demonstrates software engineering principles like modularity, design patterns, and unit testing.\n", - "\n", - "## Setup\n", - "1. Install dependencies: `pip install -r requirements.txt`\n", - "2. Place novel files (.txt) in the `data` directory.\n", - "3. Run the program: `python src/main.py`\n", - "\n", - "## Testing\n", - "Run tests: `python -m unittest discover tests`\n", - "\n", - "## Extensibility\n", - "- Add new preprocessors in `preprocessor.py`.\n", - "- Support new output formats in `output_formatter.py`.\n", - "- Modify configurations in `config.py`." - ] - }, - { - "cell_type": "markdown", - "id": "4bd74972-f9c4-4ac9-a557-de4198889047", - "metadata": {}, - "source": [ - "## 使用方法\n", - "\n", - "准备环境：\n", - "pip install -r requirements.txt\n", - "\n", - "准备数据：\n", - "- 在 data 目录下放入 100 个 .txt 小说文件（需为 UTF-8 编码）。\n", - "- 确保安装 jieba 分词库。\n", - "\n", - "运行程序：\n", - "python src/main.py\n", - "\n", - "运行测试：\n", - "python -m unittest discover tests" - ] - }, - { - "cell_type": "markdown", - "id": "16f7a973-7c49-4d11-ab3f-457d4622e5e6", - "metadata": {}, - "source": [ - "## 扩展建议\n", - "\n", - "- 支持多语言：在 TextPreprocessor 中添加英文分词（如使用 nltk 或 spacy）。\n", - "- 数据库存储：将词频结果保存到数据库（如 SQLite），在 WordCounter 中添加存储方法。\n", - "- 并行处理：使用 multiprocessing 加速大文件处理。\n", - "- 可视化：在 OutputFormatter 中添加图表输出（如使用 matplotlib）。\n", - "- 配置文件：将 Config 改为从外部 JSON/YAML 文件加载。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "b2ad0efb-4c7c-4f98-a809-ce6cdcefdb34", - "metadata": {}, - "outputs": [], - "source": [ - "## 设计说明\n", - "\n", - "模块化设计：\n", - "- 各模块（DataLoader, TextPreprocessor, WordCounter, OutputFormatter）职责单一，符合单一职责原则（SRP）。\n", - "- 模块间通过明确接口交互，易于替换或扩展。\n", - "\n", - "设计模式：\n", - "- 单例模式：WordCounter 使用单例模式，确保全局唯一计数器。\n", - "- 策略模式：OutputFormatter 支持多种输出格式（JSON、Text），易于添加新格式。\n", - "- 装饰器模式：timing_decorator 用于性能监控，便于扩展其他功能（如日志记录）。\n", - "\n", - "可扩展性：\n", - "- Config 类集中管理配置，便于调整参数（如停用词、输出数量）。\n", - "- DataLoader 支持动态扫描目录，新增文件无需改动代码。\n", - "- TextPreprocessor 可扩展以支持其他分词工具或预处理规则。\n", - "\n", - "单元测试：\n", - "- 每个模块都有对应的测试用例，确保功能正确性。\n", - "- 使用 unittest 框架，支持持续集成。\n", - "\n", - "语言特性利用：\n", - "- 使用 Python 的装饰器（timing_decorator）记录方法执行时间。\n", - "- 利用类型注解（typing 模块）提高代码可读性。\n", - "- 异常处理和日志记录（logging）增强鲁棒性。\n", - "\n", - "教学用途：\n", - "- 包含常见工程化实践：模块化、测试驱动开发、配置管理。\n", - "- 提供扩展点（如支持英文分词、数据库存储），便于学生实践。" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "b1aac488-3a98-418c-8201-e7f77c392a1f", - "metadata": {}, - "outputs": [], - "source": [ - "# text_analyzer.py\n", - "\n", - "import os\n", - "import jieba\n", - "from collections import Counter\n", - "import yaml\n", - "from contextlib import contextmanager\n", - "from typing import List, Tuple\n", - "from abc import ABC, abstractmethod\n", - "\n", - "@contextmanager\n", - "def file_reader(file_path: str):\n", - " try:\n", - " with open(file_path, 'r', encoding='utf-8') as f:\n", - " yield f.read()\n", - " except Exception as e:\n", - " print(f\"Error reading {file_path}: {e}\")\n", - " yield \"\"\n", - "\n", - "class Tokenizer(ABC):\n", - " @abstractmethod\n", - " def tokenize(self, text: str, stop_words: set) -> List[str]:\n", - " pass\n", - "\n", - "class JiebaTokenizer(Tokenizer):\n", - " def tokenize(self, text: str, stop_words: set) -> List[str]:\n", - " for word in jieba.lcut(text):\n", - " if word not in stop_words:\n", - " yield word\n", - "\n", - "class SimpleTokenizer(Tokenizer):\n", - " def tokenize(self, text: str, stop_words: set) -> List[str]:\n", - " for word in text.split():\n", - " if word not in stop_words:\n", - " yield word\n", - "\n", - "class TokenizerFactory:\n", - " @staticmethod\n", - " def create_tokenizer(name: str) -> Tokenizer:\n", - " return {'jieba': JiebaTokenizer(), 'simple': SimpleTokenizer()}.get(name, JiebaTokenizer())\n", - "\n", - "class OutputObserver(ABC):\n", - " @abstractmethod\n", - " def update(self, top_words: List[Tuple[str, int]]):\n", - " pass\n", - "\n", - "class ConsoleOutput(OutputObserver):\n", - " def update(self, top_words: List[Tuple[str, int]]):\n", - " for word, count in top_words:\n", - " print(f\"{word}: {count}\")\n", - "\n", - "class FileOutput(OutputObserver):\n", - " def __init__(self, output_file: str):\n", - " self.output_file = output_file\n", - " def update(self, top_words: List[Tuple[str, int]]):\n", - " with open(self.output_file, 'w', encoding='utf-8') as f:\n", - " for word, count in top_words:\n", - " f.write(f\"{word}: {count}\\n\")\n", - "\n", - "class TextAnalyzer:\n", - " def __init__(self, config_path='config.yaml'):\n", - " with open(config_path, 'r', encoding='utf-8') as f:\n", - " config = yaml.safe_load(f)\n", - " self.data_dir = config['data_dir']\n", - " self.top_n = config['top_n']\n", - " self.stop_words_file = config['stop_words_file']\n", - " self.output_file = config['output_file']\n", - " self.stop_words = self.load_stop_words()\n", - " self.word_count = Counter()\n", - " self.tokenizer = TokenizerFactory.create_tokenizer(config.get('tokenizer', 'jieba'))\n", - " self.observers = [ConsoleOutput(), FileOutput(self.output_file)]\n", - "\n", - " def load_stop_words(self) -> set:\n", - " with file_reader(self.stop_words_file) as content:\n", - " return set(line.strip() for line in content.splitlines() if line.strip())\n", - "\n", - " def process_file(self, file_path: str):\n", - " if file_path.endswith('.txt'):\n", - " with file_reader(file_path) as text:\n", - " words = self.tokenizer.tokenize(text, self.stop_words)\n", - " self.word_count.update(words)\n", - "\n", - " def process_directory(self):\n", - " for file in os.listdir(self.data_dir):\n", - " file_path = os.path.join(self.data_dir, file)\n", - " self.process_file(file_path)\n", - "\n", - " def get_top_words(self) -> List[Tuple[str, int]]:\n", - " return self.word_count.most_common(self.top_n)\n", - "\n", - " def notify_observers(self, top_words: List[Tuple[str, int]]):\n", - " for observer in self.observers:\n", - " observer.update(top_words)\n", - "\n", - " def run(self):\n", - " self.process_directory()\n", - " top_words = self.get_top_words()\n", - " self.notify_observers(top_words)" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "d5c689f4-e363-4327-9dc4-15c7157d4288", - "metadata": {}, - "outputs": [], - "source": [ - "# main.py\n", - "\n", - "from text_analyzer import TextAnalyzer\n", - "\n", - "def main():\n", - " analyzer = TextAnalyzer()\n", - " analyzer.run()\n", - "\n", - "if __name__ == '__main__':\n", - " main()" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "cc1d9fb1-3bb5-4f71-aeb3-e304511f4785", - "metadata": {}, - "outputs": [], - "source": [ - "## 结论\n", - "\n", - "通过引入上下文管理器、生成器、元编程、策略模式、观察者模式和工厂模式，词频统计代码在可扩展性、可维护性和复用性上进一步提升。\n", - "这些特性和模式使代码更模块化、灵活，适合大型项目，同时保持清晰的工程结构。结合之前的装饰器和函数式编程，代码已达到工程化水平。\n", - "\n", - "若需深入，可以进一步考虑其它性能特性." - ] - }, - { - "cell_type": "code", - "execution_count": null, - "id": "7244afd0-4405-402a-b9be-75f5d7ff883c", - "metadata": {}, - "outputs": [], - "source": [ - "## 进一步练习\n", - "\n", - "实践练习：\n", - "- 实现新分词器（如 thulac）并通过策略模式或工厂模式集成。\n", - "- 添加新观察者（如 JSON 输出）。\n", - "\n", - "使用生成器实现流式词频统计，比较内存占用。\n", - "实现缓存机制，缓存已处理文件的分词结果。\n", - "\n", - "添加命令行接口（argparse），动态配置 top_n 和 tokenizer。" - ] - }, - { - "cell_type": "markdown", - "id": "09c10307-f162-4b36-85b6-6bc01d0001e0", - "metadata": {}, - "source": [ - "## 综合实现（整合特性与模式）\n", - "\n", - "整合上下文管理器、生成器、策略模式和观察者模式的最终实现（部分代码展示）。" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.12.7" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} diff --git a/D Plus/01 封装.ipynb b/D 走向工业级代码/01 封装.ipynb similarity index 100% rename from D Plus/01 封装.ipynb rename to D 走向工业级代码/01 封装.ipynb diff --git a/D Plus/02 利用语言特性.ipynb b/D 走向工业级代码/02 利用语言特性.ipynb similarity index 100% rename from D Plus/02 利用语言特性.ipynb rename to D 走向工业级代码/02 利用语言特性.ipynb diff --git a/D Plus/03 设计模式.ipynb b/D 走向工业级代码/03 设计模式.ipynb similarity index 100% rename from D Plus/03 设计模式.ipynb rename to D 走向工业级代码/03 设计模式.ipynb diff --git a/D Plus/99 工业级代码.ipynb b/D 走向工业级代码/99 工业级代码.ipynb similarity index 100% rename from D Plus/99 工业级代码.ipynb rename to D 走向工业级代码/99 工业级代码.ipynb diff --git a/D Plus/readme.MD b/D 走向工业级代码/readme.MD similarity index 100% rename from D Plus/readme.MD rename to D 走向工业级代码/readme.MD diff --git a/D Plus/测试驱动开发.ipynb b/D 走向工业级代码/测试驱动开发.ipynb similarity index 100% rename from D Plus/测试驱动开发.ipynb rename to D 走向工业级代码/测试驱动开发.ipynb diff --git a/readme.MD b/readme.MD index ba82ebe..8cd1afb 100644 --- a/readme.MD +++ b/readme.MD @@ -7,7 +7,7 @@ A 代码模式 B 面向对象设计模式 用一个业务场景复现面向对象的经典设计模式 -C 高性能模式 +C 高性能编程 考虑执行时间快，资源占用少的一些思路、办法和结论 D 制造工业级代码