Support any language

Author: AlexanderDokuchaev

md_dead_link_check/preprocess.py

@@ -68,7 +68,11 @@ def process_header_to_fragment(header: str) -> str:
             fragment = fragment.replace(res.group(0), res.group(2))
 
     fragment = fragment.lower().replace(" ", "-")
-    fragment = re.sub(r"[^a-z0-9-_]", "", fragment)
+
+    def filter_header_symbols(c: str) -> bool:
+        return c.isalpha() or c.isdigit() or c in ["-", "_"]
+
+    fragment = "".join(filter(filter_header_symbols, fragment))
     return fragment
 
 

tests/test_preprocess.py

@@ -35,6 +35,9 @@ def test_find_all_markdowns_in_repo():
         ("H $ maths $", "h--maths-"),
         ("H [text](link)", "h-text"),
         ("H [![text](link)](link)", "h-"),
+        ("🙀 header with icon", "-header-with-icon"),
+        ("דוגמא", "דוגמא"),
+        ("例子", "例子"),
     ),
 )
 def test_process_header_to_fragment(header, fragment):