From 747a50bb7e9e4d9806b0f79ae7d0e89d5b13f4b0 Mon Sep 17 00:00:00 2001
From: Lukas Krupcik <lukas.krupcik@vsb.cz>
Date: Mon, 3 Mar 2025 14:22:02 +0100
Subject: [PATCH] fix

---
 ...rl-interni-test.py => url_interni_test.py} | 24 +++++++++++++++----
 scripts/{url-test.py => url_test.py}          |  5 +++-
 2 files changed, 24 insertions(+), 5 deletions(-)
 rename scripts/{url-interni-test.py => url_interni_test.py} (75%)
 rename scripts/{url-test.py => url_test.py} (83%)

diff --git a/scripts/url-interni-test.py b/scripts/url_interni_test.py
similarity index 75%
rename from scripts/url-interni-test.py
rename to scripts/url_interni_test.py
index 40a2a6aa..998a8789 100644
--- a/scripts/url-interni-test.py
+++ b/scripts/url_interni_test.py
@@ -8,25 +8,41 @@ import re
 from pathlib import Path
 
 def extract_links(content):
-    """Extract all internal links from the file."""
+    """
+    Extract all internal links from the file.
+
+    :param content: The content of the MDX file.
+    :return: A list of internal links.
+    """
     link_pattern = re.compile(r'\[.*?\]\((?!http)(.*?)\)')  # Everything except http/https
     return link_pattern.findall(content)
 
 def extract_headers(content):
-    """Extract all H1-H6 headers for hash reference checks."""
+    """
+    Extract all H1-H6 headers for hash reference checks.
+
+    :param content: The content of the MDX file.
+    :return: A set of headers formatted as hash links.
+    """
     header_pattern = re.compile(r'^(#+)\s*(.*)', re.MULTILINE)
     return {f"#{match[1].lower().replace(' ', '-')}" for match in header_pattern.findall(content)}
 
 def check_internal_links(directory):
-    """Check the existence of files and hash sections for internal links."""
+    """
+    Check the existence of files and hash sections for internal links.
+
+    :param directory: The directory containing MDX files.
+    """
     mdx_files = {f.relative_to(directory): f for f in Path(directory).rglob("*.mdx")}
     file_headers = {}
 
+    # Extract headers from each file
     for mdx_file, path in mdx_files.items():
         with open(path, "r", encoding="utf-8") as file:
             content = file.read()
             file_headers[mdx_file] = extract_headers(content)
 
+    # Check internal links
     for mdx_file, path in mdx_files.items():
         with open(path, "r", encoding="utf-8") as file:
             content = file.read()
@@ -44,7 +60,7 @@ def check_internal_links(directory):
                     print(f"❌ Broken file link in {mdx_file}: {link}")
 
                 # Check if the section exists
-                elif hash_part and hash_part not in file_headers.get(file_part, {}):
+                elif hash_part and hash_part not in file_headers.get(file_part, set()):
                     print(f"⚠️ Broken section link in {mdx_file}: {link}")
 
 if __name__ == "__main__":
diff --git a/scripts/url-test.py b/scripts/url_test.py
similarity index 83%
rename from scripts/url-test.py
rename to scripts/url_test.py
index f1dd4089..917f80bb 100644
--- a/scripts/url-test.py
+++ b/scripts/url_test.py
@@ -26,7 +26,10 @@ def check_links_in_mdx(directory):
                 try:
                     response = requests.head(link, allow_redirects=True, timeout=5)
                     if response.status_code >= 400:
-                        print(f"❌ Broken link in {mdx_file}: {link} (Status: {response.status_code})")
+                        print(
+                            f"❌ Broken link in {mdx_file}: {link} "
+                            f"(Status: {response.status_code})"
+                        )
                 except requests.RequestException:
                     print(f"⚠️ Error checking {link} in {mdx_file}")
 
-- 
GitLab