Merge pull request microsoft#154 from john0isaac/improve-workflow

Improve workflow

.github/markdown_checker.py

@@ -22,7 +22,9 @@ def main() -> None:
             file_path = os.path.join(
                 in_arg.dir,
                 lesson_folder_name,
-                lesson_file_name )
+                lesson_file_name)
+            if in_arg.dir == lesson_folder_name:
+                file_path = os.path.join(lesson_folder_name, lesson_file_name)
             if "check_broken_paths" in in_arg.func:
                 formatted_output = check_broken_links(file_path, "path" , "broken")
                 if formatted_output:
@@ -50,29 +52,36 @@ def get_lessons_paths(root_path: str) -> dict:
     Return: formatted dictionary with directories as key and an array of files as values
     """
     lessons = {}
-
+    # add root path to the dictionary
+    lessons[root_path] = []
+    pass_list = ['CODE_OF_CONDUCT.md', 'CONTRIBUTING.md', 'SECURITY.md']
     # get lessons folders
     for item in os.listdir(root_path):
         if os.path.isdir(os.path.join(root_path, item)):
             lessons[item] = []
 
     # get lesson exercises (md, ipynb files)
     for lesson, _ in lessons.items():
-        for item in os.listdir(os.path.join(root_path, lesson)):
-            # check for translations directories
-            if os.path.isdir(os.path.join(root_path, lesson, item)):
-                for sub_item in os.listdir(os.path.join(root_path, lesson, item)):
-                    if os.path.isdir(os.path.join(root_path, lesson, item, sub_item)):
-                        for sub_item2 in os.listdir(os.path.join(root_path, lesson, item, sub_item)):
-                            # check for .md and .ipynb files and store them
-                            if sub_item2.lower().endswith(('.md', '.ipynb')):
-                                lessons[lesson].append(os.path.join(item, sub_item, sub_item2))
-                    # check for .md and .ipynb files and store them
-                    elif sub_item.lower().endswith(('.md', '.ipynb')):
-                        lessons[lesson].append(os.path.join(item, sub_item))
-            # check for .md and .ipynb files and store them
-            elif item.lower().endswith(('.md', '.ipynb')):
-                lessons[lesson].append(item)
+        if lesson != root_path:
+            for item in os.listdir(os.path.join(root_path, lesson)):
+                # check for translations directories
+                if os.path.isdir(os.path.join(root_path, lesson, item)):
+                    for sub_item in os.listdir(os.path.join(root_path, lesson, item)):
+                        if os.path.isdir(os.path.join(root_path, lesson, item, sub_item)):
+                            for sub_item2 in os.listdir(os.path.join(root_path, lesson, item, sub_item)):
+                                # check for .md and .ipynb files and store them
+                                if sub_item2.lower().endswith(('.md', '.ipynb')) and sub_item2 not in pass_list:
+                                    lessons[lesson].append(os.path.join(item, sub_item, sub_item2))
+                        # check for .md and .ipynb files and store them
+                        elif sub_item.lower().endswith(('.md', '.ipynb')) and sub_item not in pass_list:
+                            lessons[lesson].append(os.path.join(item, sub_item))
+                # check for .md and .ipynb files and store them
+                elif item.lower().endswith(('.md', '.ipynb')) and item not in pass_list:
+                    lessons[lesson].append(item)
+    # get .md and .ipynb in root directory
+    for item in os.listdir(root_path):
+        if item.lower().endswith(('.md', '.ipynb')) and item not in pass_list:
+            lessons[root_path].append(item)
 
     # check to remove folders that don't have .md files in them
     lessons = {key: values for key, values in lessons.items() if len(values) > 0}
@@ -95,24 +104,24 @@ def check_broken_links(file_path : str, link_type : str , check_type: str) -> st
         formatted_output = f"    FILE '{file_path}'\n"
         if link_type == "path":
             paths = get_paths_from_links(all_links)
-            if check_type == "broken":
+            if check_type == "broken" and len(paths) > 0:
                 broken_path = check_paths_exists(file_path, paths)
                 if len (broken_path) > 0:
                     formatted_output += f'    has the following broken relative paths {broken_path}\n'
                     return formatted_output
-            elif check_type == "tracking":
+            elif check_type == "tracking" and len(paths) > 0:
                 tracking_id_paths = check_url_tracking(paths)
                 if len(tracking_id_paths) > 0:
                     formatted_output += f'    has the following paths with no tracking id {tracking_id_paths}\n'
                     return formatted_output
         elif link_type == "url":
             urls = get_urls_from_links(all_links)
-            if check_type == "tracking":
+            if check_type == "tracking" and len(urls) > 0:
                 tracking_id_urls = check_url_tracking(urls)
                 if len(tracking_id_urls) > 0:
                     formatted_output += f'    has the following links with no tracking id {tracking_id_urls}\n'
                     return formatted_output
-            elif check_type == "locale":
+            elif check_type == "locale" and len(urls) > 0:
                 country_locale_urls = check_url_locale(urls)
                 if len(country_locale_urls) > 0:
                     formatted_output += f'    has the following links with country locale {country_locale_urls}\n'
@@ -125,20 +134,22 @@ def get_links_from_file(file_path: str) -> list:
     all_links = []
     with open(file_path, 'r',  encoding="utf-8") as file:
         data = file.read()
-        link_pattern = re.compile(r'\[.*\]\((.*?)\)')
+        link_pattern = re.compile(r'\]\((.*?)\)| \)')
         matches = re.finditer(link_pattern, data)
         for matched_group in matches:
-            all_links.append(matched_group.group(1))
+            if matched_group.group(1):
+                all_links.append(matched_group.group(1))
     return all_links
 
 def get_urls_from_links(all_links: list) -> list:
     """function to get an array of urls from a list"""
     urls = []
     url_pattern = re.compile(r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9]{1,6}\b([-a-zA-Z0-9@:%_\+.~#?&\/\/=]*)')
-
+    allowed_list = ['github.com', 'microsoft.com', 'visualstudio.com', 'aka.ms', 'azure.com']
     for link in all_links:
         matches = re.findall(url_pattern, link)
-        if matches:
+
+        if matches and any(allowed in link.lower() for allowed in allowed_list):
             urls.append(link)
     return urls
 

00-course-setup/translations/cn/README.md

@@ -10,7 +10,7 @@
 
 ### 1. Fork this Repo
 
-[Fork 这个完整的 repo](https://github.com/microsoft/generative-ai-for-beginners/fork) 到你自己的 GitHub 账号下以便您能完成代码的修改和完成相关的挑战. 您也可以 [给该 repo star (🌟)](https://docs.github.com/en/get-started/exploring-projects-on-github/saving-repositories-with-stars?WT.mc_id=academic-105485-koreyst) 让您更容易找到它和相关的 Repo.
+[Fork 这个完整的 repo](https://github.com/microsoft/generative-ai-for-beginners/fork?WT.mc_id=academic-105485-koreyst) 到你自己的 GitHub 账号下以便您能完成代码的修改和完成相关的挑战. 您也可以 [给该 repo star (🌟)](https://docs.github.com/en/get-started/exploring-projects-on-github/saving-repositories-with-stars?WT.mc_id=academic-105485-koreyst) 让您更容易找到它和相关的 Repo.
 
 ### 2. 创建 GitHub Codespaces
 
@@ -88,7 +88,7 @@ jupyterhub
 
 ## 贡献该内容
 
-本课程是一项开源计划。 如果您发现需要改进的地方或问题，请创建 [Pull Request](https://github.com/microsoft/generative-ai-for-beginners/pulls) 或记录 [Github 问题](https://github.com/microsoft/generative-ai-for-beginners/issues?WT.mc_id=academic-105485-koreyst)。
+本课程是一项开源计划。 如果您发现需要改进的地方或问题，请创建 [Pull Request](https://github.com/microsoft/generative-ai-for-beginners/pulls?WT.mc_id=academic-105485-koreyst) 或记录 [Github 问题](https://github.com/microsoft/generative-ai-for-beginners/issues?WT.mc_id=academic-105485-koreyst)。
 
 课程项目团队将跟踪所有贡献，为开源做出贡献是在生成人工智能领域建立职业生涯的绝佳方式。
 

translation/cn/README.md

@@ -23,7 +23,7 @@
 
 ## 🌱 如何开始
 
-首先，将 [整个repo fork ](https://github.com/microsoft/generative-ai-for-beginners/fork) 到您自己的 GitHub 帐户，以便能够更改任何代码并完成相关学习。 您还可以[(🌟)该 Fork](https://docs.github.com/en/get-started/exploring-projects-on-github/saving-repositories-with-stars?WT.mc_id=academic-105485-koreyst)以便稍后更容易地找到它！
+首先，将 [整个repo fork ](https://github.com/microsoft/generative-ai-for-beginners/fork?WT.mc_id=academic-105485-koreyst) 到您自己的 GitHub 帐户，以便能够更改任何代码并完成相关学习。 您还可以[(🌟)该 Fork](https://docs.github.com/en/get-started/exploring-projects-on-github/saving-repositories-with-stars?WT.mc_id=academic-105485-koreyst)以便稍后更容易地找到它！
 
 前往[课程学习环境设置](../../00-course-setup/translations/cn/README.md?WT.mc_id=academic-105485-koreyst) 找到最适合您的设置指南！
 
@@ -48,7 +48,7 @@
 |       |              课程链接             |                       相关教学内容                     |                     学习目标                 |                             
 | :---: | :------------------------------------: | :---------------------------------------------------------: | ----------------------------------------------------------- |
 | 00 | [课程介绍和学习环境设置](../../00-course-setup/translations/cn/README.md?WT.mc_id=academic-105485-koreyst) | 学习环境配置和课程结构 | 在学习本课程的同时帮助您取得成功 | 
-| 01 | [生成式人工智能和 LLMs 介绍](../../01-introduction-to-genai//translations/cn/README.md?WT.mc_id=academic-105485-koreyst) | **知识点**: 生成式人工智能以及我们如何适应当前的技术格局 | 了解什么是生成式人工智能 以及 LLMs 的工作原理。                 |
+| 01 | [生成式人工智能和 LLMs 介绍](../../01-introduction-to-genai/translations/cn/README.md?WT.mc_id=academic-105485-koreyst) | **知识点**: 生成式人工智能以及我们如何适应当前的技术格局 | 了解什么是生成式人工智能 以及 LLMs 的工作原理。                 |
 | 02 | [探索和比较不同的 LLMs](../../02-exploring-and-comparing-different-llms/translations/cn/README.md?WT.mc_id=academic-105485-koreyst) | **知识点**: 测试、迭代和比较不同的 LLMs 模型 | 为您的应用场景选择正确的模型 |
 | 03 | [负责任地使用生成式人工智能](../../03-using-generative-ai-responsibly/translations/cn/README.md?WT.mc_id=academic-105485-koreyst)| **知识点:** 了解基础模型的局限性和人工智能背后的风险 | 了解如何负责任地构建生成式人工智能应用程序
 | 04 | [提示工程基础](../../04-prompt-engineering-fundamentals/translations/cn/README.md?WT.mc_id=academic-105485-koreyst) | **代码/知识点:** 提示工程最佳实践| 了解提示结构和用法|