Markdown-Checker 0.0.5__tar.gz → 0.0.8__tar.gz

markdown-checker-0.0.8/MANIFEST.in

@@ -0,0 +1,6 @@
+include README.md
+include markdown_checker/inputs/*
+include markdown_checker/paths/*
+include markdown_checker/links/*
+include markdown_checker/generators/*
+include setup.cfg

{markdown-checker-0.0.5/markdown_checker.egg-info → markdown-checker-0.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown-checker
-Version: 0.0.5
+Version: 0.0.8
 Summary: A markdown validation reporting tool
 Home-page: https://github.com/john0isaac/markdown-checker
 Author: John Aziz
@@ -30,9 +30,11 @@ License-File: LICENSE
 markdown-checker is a markdown validation reporting tool.
 
 # How To
+
 1. Run `pip install markdown-checker`.
-2. Run `markdown-checker -d {src} -f {func}`. Replace `{src}` with the directory you want to analyse and {func} with the available functions like check_broken_paths.
-3. The output will be displayed in the terminal.
+2. Run `markdown-checker -d {src} -f {func} -gu {url}`. Replace `{src}` with the directory you want to analyze, {func} with the available functions like check_broken_paths, {gu} with your contribution guidance full URL.
+3. The output will be displayed in the terminal and in a `comments.md` file.
 
 # Using markdown-checker in GitHub Actions
-The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/action-check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.
+
+The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.

{markdown-checker-0.0.5 → markdown-checker-0.0.8}/README.md

@@ -7,9 +7,11 @@
 markdown-checker is a markdown validation reporting tool.
 
 # How To
+
 1. Run `pip install markdown-checker`.
-2. Run `markdown-checker -d {src} -f {func}`. Replace `{src}` with the directory you want to analyse and {func} with the available functions like check_broken_paths.
-3. The output will be displayed in the terminal.
+2. Run `markdown-checker -d {src} -f {func} -gu {url}`. Replace `{src}` with the directory you want to analyze, {func} with the available functions like check_broken_paths, {gu} with your contribution guidance full URL.
+3. The output will be displayed in the terminal and in a `comments.md` file.
 
 # Using markdown-checker in GitHub Actions
-The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/action-check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.
+
+The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.

markdown-checker-0.0.8/markdown_checker/check_markdown.py

@@ -0,0 +1,52 @@
+"""
+Module providing automatic checks functionality to markdown files 
+following some Guidelines
+"""
+from markdown_checker.links.link_operations import (
+    get_links_from_file,
+    get_paths_from_links,
+    get_urls_from_links,
+    check_paths_exists,
+    check_url_locale,
+    check_url_tracking
+)
+
+
+def check_broken_links(file_path : str, link_type : str , check_type: str) -> str:
+    """function that checks if urls and hyperlinks are broken
+    
+    Keyword arguments:
+    file_path -- a path to text file to check
+    link_type -- path or url
+    check_type -- broken or tracking or locale
+    Return: broken links and associated file path
+    """
+    all_links = get_links_from_file(file_path)
+
+    # check if file has links
+    if len(all_links) > 0:
+        formatted_output = f"|<code>{file_path}</code>|"
+        if link_type == "path":
+            paths = get_paths_from_links(all_links)
+            if check_type == "broken" and len(paths) > 0:
+                broken_path = check_paths_exists(file_path, paths)
+                if len (broken_path) > 0:
+                    formatted_output += f'<code>{broken_path}</code>|\n'
+                    return formatted_output
+            elif check_type == "tracking" and len(paths) > 0:
+                tracking_id_paths = check_url_tracking(paths)
+                if len(tracking_id_paths) > 0:
+                    formatted_output += f'<code>{tracking_id_paths}</code>|\n'
+                    return formatted_output
+        elif link_type == "url":
+            urls = get_urls_from_links(all_links)
+            if check_type == "tracking" and len(urls) > 0:
+                tracking_id_urls = check_url_tracking(urls)
+                if len(tracking_id_urls) > 0:
+                    formatted_output += f'<code>{tracking_id_urls}</code>|\n'
+                    return formatted_output
+            elif check_type == "locale" and len(urls) > 0:
+                country_locale_urls = check_url_locale(urls)
+                if len(country_locale_urls) > 0:
+                    formatted_output += f'<code>{country_locale_urls}</code>|\n'
+                    return formatted_output

markdown-checker-0.0.8/markdown_checker/generators/md_generator.py

@@ -0,0 +1,51 @@
+CHECK_BROKEN_PATHS = """# Check Broken Paths
+
+We have automatically detected the following broken relative paths in your lessons. Review and fix the paths to resolve this issue.
+
+Check the file paths and associated broken paths inside them."""
+CHECK_PATHS_TRACKING = """# Check Missing Tracking from Paths
+
+We have automatically detected missing tracking id from the following relative paths in your lessons. Review and add tracking to paths to resolve this issue.
+
+Check the file paths and associated paths inside them."""
+CHECK_URLS_TRACKING = """# Check Missing Tracking from URLs
+
+We have automatically detected missing tracking id from the following URLs in your lessons. Review and add tracking to URLs to resolve this issue.
+
+Check the file paths and associated URLs inside them."""
+CHECK_URLS_LOCALE = """# Check Country Locale in URLs
+
+We have automatically detected added country locale to URLs in your lessons. Review and remove country specific locale from URLs to resolve this issue.
+
+Check the file paths and associated URLs inside them."""
+
+def write_md_file(generated_md: str) -> None:
+    """Write the formatted output to a markdown file"""
+    with open("comment.md", "w", encoding="utf-8") as file:
+        file.write(generated_md)
+
+def generate_md(formatted_output: str, function_name: str, contributing_guide_url: str) -> None:
+    """Generate markdown file based on the formatted output, function name, and contributing guide URL.
+
+    Args:
+        formatted_output (str): The formatted output to be written to the markdown file.
+        function_name (str): The name of the function to determine the header for the markdown file.
+        contributing_guide_url (str): The URL of the contributing guide to be included in the markdown file.
+
+    Raises:
+        ValueError: If an invalid function name is provided.
+
+    """
+    contributing_guide_line = f" For more details, check our [Contributing Guide]({contributing_guide_url}).\n\n"
+    if function_name == "check_broken_paths":
+        formatted_output = CHECK_BROKEN_PATHS + contributing_guide_line + formatted_output
+    elif function_name == "check_paths_tracking":
+        formatted_output = CHECK_PATHS_TRACKING + contributing_guide_line + formatted_output
+    elif function_name == "check_urls_tracking":
+        formatted_output = CHECK_URLS_TRACKING + contributing_guide_line + formatted_output
+    elif function_name == "check_urls_locale":
+        formatted_output = CHECK_URLS_LOCALE + contributing_guide_line + formatted_output
+    else:
+        raise ValueError("Invalid function name")
+
+    write_md_file(formatted_output)

markdown-checker-0.0.5/markdown_checker/get_input_args/get_input_args.py → markdown-checker-0.0.8/markdown_checker/inputs/input_arguments.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 """
 Module providing automatic checks functionality to markdown files 
 following some Guidelines
@@ -34,4 +33,7 @@ def get_input_args() -> None:
                                  'check_urls_tracking',
                                  'check_urls_locale'])
 
-    return parser.parse_args()
+    parser.add_argument('-gu', '--guide-url', type = str, default = 'https://github.com/john0isaac/markdown-checker/blob/main/CONTRIBUTING.md',
+                    help = 'full url of your contributing guide', required=True)
+
+    return parser.parse_args()

markdown-checker-0.0.8/markdown_checker/links/link_operations.py

@@ -0,0 +1,100 @@
+import re
+import os
+
+def get_links_from_file(file_path: str) -> list:
+    """function to get an array of markdown links from a file
+    flags markdown links captures the part inside () that comes right after []
+    """
+    all_links = []
+    with open(file_path, 'r',  encoding="utf-8") as file:
+        data = file.read()
+        link_pattern = re.compile(r'\]\((.*?)\)| \)')
+        matches = re.finditer(link_pattern, data)
+        for matched_group in matches:
+            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 and any(allowed in link.lower() for allowed in allowed_list):
+            urls.append(link)
+    return urls
+
+def get_paths_from_links(all_links: list) -> list:
+    """function to get relative paths from a list
+    flags paths that start with ./ or ../
+    """
+    paths = []
+    path_pattern = re.compile(r'(\.{1,2}\/)+([A-Za-z0-9-]+\/)*(.+\.[A-Za-z]+)')
+
+    for link in all_links:
+        link = link.split(" ")[0]
+        matches = re.findall(path_pattern, link)
+        if matches:
+            paths.append(link)
+    return paths
+
+def check_paths_exists(file_path : str, paths : list) -> list:
+    """function checks if a path exist if not return non existent paths
+    flags any relative path that can't be accessed
+    """
+    broken_path = []
+    for path in paths:
+        path = re.sub(r'(\?|\&)(WT|wt)\.mc_id=.*', '', path)
+        if not os.path.exists(os.path.normpath(os.path.join(os.path.dirname(file_path), path))):
+            broken_path.append(path)
+    return broken_path
+
+def check_url_locale(urls : list) -> list:
+    """function checks if a url has country locale
+    flags urls that have ==> /en-us/
+    """
+    country_locale = []
+    for url in urls:
+        locale_pattern = re.compile(r'\/[a-z]{2}-[a-z]{2}\/')
+        matches = re.findall(locale_pattern, url)
+        if matches:
+            country_locale.append(url)
+    return country_locale
+
+def check_url_tracking(urls : list) -> list:
+    """function checks if a url has tracking id
+    flags urls missing ==> (? or &) plus WT.mc_id= or wt.mc_id=
+    """
+    tracking_id = []
+    for url in urls:
+        tracking_pattern = re.compile(r'(\?|\&)(WT|wt)\.mc_id=')
+        matches = re.findall(tracking_pattern, url)
+        if not matches:
+            tracking_id.append(url)
+    return tracking_id
+
+# DEPRECATED
+def get_urls_from_file(file_path: str) -> list:
+    """function to get an array of urls from a file"""
+    urls = []
+    with open(file_path, 'r',  encoding="utf-8") as file:
+        data = file.read()
+        url_pattern = re.compile(r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9]{1,6}\b([-a-zA-Z0-9@:%_\+.~#?&\/\/=]*)')
+        matches = re.finditer(url_pattern, data)
+        for matched_group in matches:
+            urls.append(matched_group.group())
+    return urls
+
+def get_paths_from_file(file_path: str) -> list:
+    """function to get relative paths from a file"""
+    paths = []
+    with open(file_path, 'r',  encoding="utf-8") as file:
+        data = file.read()
+        path_pattern = re.compile(r'(\.{1,2}\/)+([A-Za-z0-9-]+\/)*([A-Za-z0-9]+\.[A-Za-z]+)')
+        matches = re.finditer(path_pattern, data)
+        for matched_group in matches:
+            paths.append(matched_group.group())
+    return paths

markdown-checker-0.0.8/markdown_checker/paths/files_paths_reader.py

@@ -0,0 +1,42 @@
+"""
+This module contains a function to get a list of file paths from a root directory and
+its subdirectories, filtered by file extension.
+
+The main function in this module is `get_files_paths_list`.
+
+Functions:
+- get_files_paths_list(root_path: str, extension: list = None) -> list
+"""
+
+import os
+
+def get_files_paths_list(root_path: str, extensions: list = None) -> list:
+    """
+    function returns a list of files in a directory and its subdirectories,
+    filtered by file extensions.
+
+    Keyword arguments:
+    root_path (str): The root directory from which to start the search.
+    extensions (list, optional): A list of file extensions to filter by.
+    Defaults to [".md", ".ipynb"].
+
+    Returns:
+    list: A list of file paths that match the given file extensions.
+    """
+    if extensions is None:
+        extensions = [".md", ".ipynb"]
+
+    sub_folders, files_paths = [], []
+
+    for f in os.scandir(root_path):
+        if f.is_dir():
+            sub_folders.append(f.path)
+        if f.is_file():
+            if os.path.splitext(f.name)[1].lower() in extensions:
+                files_paths.append(f.path)
+
+    for directory in list(sub_folders):
+        sf, f = get_files_paths_list(directory, extensions)
+        sub_folders.extend(sf)
+        files_paths.extend(f)
+    return sub_folders, files_paths

markdown-checker-0.0.8/markdown_checker/validate_markdown.py

@@ -0,0 +1,48 @@
+#!/usr/bin/env python3
+"""
+Module providing automatic checks functionality to markdown files 
+following some Guidelines
+"""
+from markdown_checker.inputs.input_arguments import get_input_args
+from markdown_checker.check_markdown import check_broken_links
+from markdown_checker.paths.files_paths_reader import get_files_paths_list
+from markdown_checker.generators.md_generator import generate_md
+
+def main() -> None:
+    """Main program get inputs and run checks"""
+
+    # get input arguments directory, function to run
+    in_arg = get_input_args()
+
+    _, files_paths = get_files_paths_list(in_arg.dir)
+
+    pass_list = ['./CODE_OF_CONDUCT.md', './CONTRIBUTING.md', './SECURITY.md', '.\CODE_OF_CONDUCT.md', '.\CONTRIBUTING.md', '.\SECURITY.md']
+    files_paths = [file_path for file_path in files_paths if file_path not in pass_list]
+
+    formatted_output = ""
+
+    # iterate over the files to validate the content
+    for file_path in files_paths:
+        if "check_broken_paths" in in_arg.func:
+            broken_paths = check_broken_links(file_path, "path" , "broken")
+            if broken_paths:
+                formatted_output += broken_paths
+        if "check_paths_tracking" in in_arg.func:
+            paths_tracking = check_broken_links(file_path, "path" , "tracking")
+            if paths_tracking:
+                formatted_output += paths_tracking
+        if "check_urls_tracking" in in_arg.func:
+            urls_tracking = check_broken_links(file_path, "url" , "tracking")
+            if urls_tracking:
+                formatted_output += urls_tracking
+        if "check_urls_locale" in in_arg.func:
+            urls_locale = check_broken_links(file_path, "url" , "locale")
+            if urls_locale:
+                formatted_output += urls_locale
+    if formatted_output != "":
+        formatted_output = "| File Full Path | Issues |\n|--------|--------|\n" + formatted_output
+        print(formatted_output)
+        generate_md(formatted_output, in_arg.func, in_arg.guide_url)
+
+if __name__ == "__main__":
+    main()

{markdown-checker-0.0.5 → markdown-checker-0.0.8/markdown_checker.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: markdown-checker
-Version: 0.0.5
+Version: 0.0.8
 Summary: A markdown validation reporting tool
 Home-page: https://github.com/john0isaac/markdown-checker
 Author: John Aziz
@@ -30,9 +30,11 @@ License-File: LICENSE
 markdown-checker is a markdown validation reporting tool.
 
 # How To
+
 1. Run `pip install markdown-checker`.
-2. Run `markdown-checker -d {src} -f {func}`. Replace `{src}` with the directory you want to analyse and {func} with the available functions like check_broken_paths.
-3. The output will be displayed in the terminal.
+2. Run `markdown-checker -d {src} -f {func} -gu {url}`. Replace `{src}` with the directory you want to analyze, {func} with the available functions like check_broken_paths, {gu} with your contribution guidance full URL.
+3. The output will be displayed in the terminal and in a `comments.md` file.
 
 # Using markdown-checker in GitHub Actions
-The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/action-check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.
+
+The tool has been designed to be run within a GitHub workflow using the [action-check-markdown](https://github.com/marketplace/actions/check-markdown) GitHub action. The action will automatically post the output of the tool to your GitHub pull request as a comment.

markdown-checker-0.0.8/markdown_checker.egg-info/SOURCES.txt

@@ -0,0 +1,23 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+setup.cfg
+setup.py
+markdown_checker/__init__.py
+markdown_checker/check_markdown.py
+markdown_checker/validate_markdown.py
+markdown_checker.egg-info/PKG-INFO
+markdown_checker.egg-info/SOURCES.txt
+markdown_checker.egg-info/dependency_links.txt
+markdown_checker.egg-info/entry_points.txt
+markdown_checker.egg-info/top_level.txt
+markdown_checker/generators/__init__.py
+markdown_checker/generators/md_generator.py
+markdown_checker/inputs/__init__.py
+markdown_checker/inputs/input_arguments.py
+markdown_checker/links/__init__.py
+markdown_checker/links/link_operations.py
+markdown_checker/paths/__init__.py
+markdown_checker/paths/files_paths_reader.py
+tests/test_markdown_checker.py

{markdown-checker-0.0.5 → markdown-checker-0.0.8}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = markdown-checker
-version = 0.0.5
+version = 0.0.8
 author = John Aziz
 author_email = johnaziz269@gmail.com
 maintainer = John Aziz

markdown-checker-0.0.8/tests/test_markdown_checker.py

@@ -0,0 +1,46 @@
+"""
+Module to check paths in markdown files.
+"""
+
+import subprocess
+
+def check_broken_paths():
+    """
+    Function to check for broken paths.
+    """
+    print("check_broken_paths was called")
+    subprocess.run(["markdown-checker", "-d", "./tests/resources/", "-f", "check_broken_paths", "-gu", "https://github.com/john0isaac/markdown-checker/blob/main/CONTRIBUTING.md"], check=False)
+
+def check_paths_tracking():
+    """
+    Function to check paths tracking.
+    """
+    print("check_paths_tracking was called")
+    subprocess.run(["markdown-checker", "-d", "./tests/resources/", "-f", "check_paths_tracking", "-gu", "https://github.com/john0isaac/markdown-checker/blob/main/CONTRIBUTING.md"], check=False)
+
+def check_urls_tracking():
+    """
+    Function to check URLs tracking.
+    """
+    print("check_urls_tracking was called")
+    subprocess.run(["markdown-checker", "-d", "./tests/resources/", "-f", "check_urls_tracking", "-gu", "https://github.com/john0isaac/markdown-checker/blob/main/CONTRIBUTING.md"], check=False)
+
+def check_urls_locale():
+    """
+    Function to check URLs locale.
+    """
+    print("check_urls_locale was called")
+    subprocess.run(["markdown-checker", "-d", "./tests/resources/", "-f", "check_urls_locale", "-gu", "https://github.com/john0isaac/markdown-checker/blob/main/CONTRIBUTING.md"], check=False)
+
+mydict = {1:check_broken_paths, 2:check_paths_tracking, 3:check_urls_tracking, 4:check_urls_locale}
+
+try:
+    choices = list(map(int,input("Do you want to: \n(1) Run check_broken_paths \n(2) Run check_paths_tracking \n(3) Run check_urls_tracking \n(4) Run check_urls_locale \n").split()))
+except ValueError:
+    print("Please input number")
+
+for choice in choices:
+    if 0 < choice and choice < 5:
+        mydict[choice]()
+    else:
+        print("That is not between 1 and 4! Try again:")

markdown-checker-0.0.5/MANIFEST.in

@@ -1,3 +0,0 @@
-include README.md
-include markdown_checker/get_input_args/*
-include setup.cfg

markdown-checker-0.0.5/markdown_checker/markdown_checker.py

@@ -1,190 +0,0 @@
-#!/usr/bin/env python3
-"""
-Module providing automatic checks functionality to markdown files 
-following some Guidelines
-"""
-import os
-import re
-
-# Helper Functions
-
-def get_lessons_paths(root_path: str) -> dict:
-    """function to compile a dictionary of directories
-    
-    Keyword arguments:
-    root_path -- directory to go through looking for md files
-    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():
-        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}
-
-    return lessons
-
-def check_broken_links(file_path : str, link_type : str , check_type: str) -> str:
-    """function that checks if urls and hyperlinks are broken
-    
-    Keyword arguments:
-    file_path -- a path to text file to check
-    link_type -- path or url
-    check_type -- broken or tracking or locale
-    Return: broken links and associated file path
-    """
-    all_links = get_links_from_file(file_path)
-
-    # check if file has links
-    if len(all_links) > 0:
-        formatted_output = f"    FILE '{file_path}'\n"
-        if link_type == "path":
-            paths = get_paths_from_links(all_links)
-            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" 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" 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" 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'
-                    return formatted_output
-
-def get_links_from_file(file_path: str) -> list:
-    """function to get an array of markdown links from a file
-    flags markdown links captures the part inside () that comes right after []
-    """
-    all_links = []
-    with open(file_path, 'r',  encoding="utf-8") as file:
-        data = file.read()
-        link_pattern = re.compile(r'\]\((.*?)\)| \)')
-        matches = re.finditer(link_pattern, data)
-        for matched_group in matches:
-            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 and any(allowed in link.lower() for allowed in allowed_list):
-            urls.append(link)
-    return urls
-
-def get_paths_from_links(all_links: list) -> list:
-    """function to get relative paths from a list
-    flags paths that start with ./ or ../
-    """
-    paths = []
-    path_pattern = re.compile(r'(\.{1,2}\/)+([A-Za-z0-9-]+\/)*(.+\.[A-Za-z]+)')
-
-    for link in all_links:
-        link = link.split(" ")[0]
-        matches = re.findall(path_pattern, link)
-        if matches:
-            paths.append(link)
-    return paths
-
-def check_paths_exists(file_path : str, paths : list) -> list:
-    """function checks if a path exist if not return non existent paths
-    flags any relative path that can't be accessed
-    """
-    broken_path = []
-    for path in paths:
-        path = re.sub(r'(\?|\&)(WT|wt)\.mc_id=.*', '', path)
-        if not os.path.exists(os.path.normpath(os.path.join(os.path.dirname(file_path), path))):
-            broken_path.append(path)
-    return broken_path
-
-def check_url_locale(urls : list) -> list:
-    """function checks if a url has country locale
-    flags urls that have ==> /en-us/
-    """
-    country_locale = []
-    for url in urls:
-        locale_pattern = re.compile(r'\/[a-z]{2}-[a-z]{2}\/')
-        matches = re.findall(locale_pattern, url)
-        if matches:
-            country_locale.append(url)
-    return country_locale
-
-def check_url_tracking(urls : list) -> list:
-    """function checks if a url has tracking id
-    flags urls missing ==> (? or &) plus WT.mc_id= or wt.mc_id=
-    """
-    tracking_id = []
-    for url in urls:
-        tracking_pattern = re.compile(r'(\?|\&)(WT|wt)\.mc_id=')
-        matches = re.findall(tracking_pattern, url)
-        if not matches:
-            tracking_id.append(url)
-    return tracking_id
-
-# DEPRECATED
-def get_urls_from_file(file_path: str) -> list:
-    """function to get an array of urls from a file"""
-    urls = []
-    with open(file_path, 'r',  encoding="utf-8") as file:
-        data = file.read()
-        url_pattern = re.compile(r'https?:\/\/(www\.)?[-a-zA-Z0-9@:%._\+~#=]{1,256}\.[a-zA-Z0-9]{1,6}\b([-a-zA-Z0-9@:%_\+.~#?&\/\/=]*)')
-        matches = re.finditer(url_pattern, data)
-        for matched_group in matches:
-            urls.append(matched_group.group())
-    return urls
-
-def get_paths_from_file(file_path: str) -> list:
-    """function to get relative paths from a file"""
-    paths = []
-    with open(file_path, 'r',  encoding="utf-8") as file:
-        data = file.read()
-        path_pattern = re.compile(r'(\.{1,2}\/)+([A-Za-z0-9-]+\/)*([A-Za-z0-9]+\.[A-Za-z]+)')
-        matches = re.finditer(path_pattern, data)
-        for matched_group in matches:
-            paths.append(matched_group.group())
-    return paths

markdown-checker-0.0.5/markdown_checker/validate_markdown.py

@@ -1,45 +0,0 @@
-#!/usr/bin/env python3
-"""
-Module providing automatic checks functionality to markdown files 
-following some Guidelines
-"""
-import os
-from markdown_checker.get_input_args.get_input_args import get_input_args
-from markdown_checker.markdown_checker import get_lessons_paths, check_broken_links
-
-def main() -> None:
-    """Main program get inputs and run checks"""
-
-    # get input arguments directory, function to run
-    in_arg = get_input_args()
-
-    lessons = get_lessons_paths(in_arg.dir)
-
-    # iterate over the files to validate the content
-    for lesson_folder_name, lessons_array in lessons.items():
-        for lesson_file_name in lessons_array:
-            file_path = os.path.join(
-                in_arg.dir,
-                lesson_folder_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:
-                    print(formatted_output)
-            if "check_paths_tracking" in in_arg.func:
-                formatted_output = check_broken_links(file_path, "path" , "tracking")
-                if formatted_output:
-                    print(formatted_output)
-            if "check_urls_tracking" in in_arg.func:
-                formatted_output = check_broken_links(file_path, "url" , "tracking")
-                if formatted_output:
-                    print(formatted_output)
-            if "check_urls_locale" in in_arg.func:
-                formatted_output = check_broken_links(file_path, "url" , "locale")
-                if formatted_output:
-                    print(formatted_output)
-
-if __name__ == "__main__":
-    main()

markdown-checker-0.0.5/markdown_checker.egg-info/SOURCES.txt

@@ -1,16 +0,0 @@
-LICENSE
-MANIFEST.in
-README.md
-pyproject.toml
-setup.cfg
-setup.py
-markdown_checker/__init__.py
-markdown_checker/markdown_checker.py
-markdown_checker/validate_markdown.py
-markdown_checker.egg-info/PKG-INFO
-markdown_checker.egg-info/SOURCES.txt
-markdown_checker.egg-info/dependency_links.txt
-markdown_checker.egg-info/entry_points.txt
-markdown_checker.egg-info/top_level.txt
-markdown_checker/get_input_args/__init__.py
-markdown_checker/get_input_args/get_input_args.py