Detect headers under list

md_dead_link_check/preprocess.py

@@ -8,7 +8,7 @@
 
 from git import Repo
 
-RE_HEADER = r"^[#]{1,6}\s*(.*)"
+RE_HEADER = r"^(?:\s*[-+*]\s+|)[#]{1,6}\s*(.*)"
 RE_LINK = r"([!]{0,1})\[([^\]!]*)\]\(([^()\s]+(?:\([^()\s]*\))*)\s*(.*?)\)"
 RE_HTML_A_TAG_ID = r"<\w+\s+(?:[^>]*?\s+)?id=([\"'])(.*?)\1"
 RE_HTML_A_TAG_HREF = r"<\w+\s+(?:[^>]*?\s+)?href=([\"'])(.*?)\1"
@@ -96,7 +96,12 @@ def process_md_file(path: Path, root_dir: Path) -> MarkdownInfo:
             # Detect headers
             res = re.match(RE_HEADER, line)
             if res:
-                fragment = process_header_to_fragment(res.group(1))
+                _fragment = process_header_to_fragment(res.group(1))
+                fragment = _fragment
+                repeat = 0
+                while fragment in fragments:
+                    repeat += 1
+                    fragment = f"{_fragment}-{repeat}"
                 fragments.append(fragment)
                 continue
 

tests/test_md_files/a.md

@@ -40,3 +40,12 @@ Some text
 [top](#)
 
 [top](./b.md#)
+
+
+- ## badge
+
+ + ## badge
+
+[0](#badge)
+[1](#badge-1)
+[1](#badge-2)

tests/test_preprocess.py

@@ -57,6 +57,8 @@ def test_process_md_file():
         "links",
         "header-with-quotes-and-math",
         "badge",
+        "badge-1",
+        "badge-2",
     ]
 
     ref_links = [
@@ -110,5 +112,20 @@ def test_process_md_file():
             location=Path("tests/test_md_files/a.md"),
             line_num=42,
         ),
+        LinkInfo(
+            link="#badge",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=49,
+        ),
+        LinkInfo(
+            link="#badge-1",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=50,
+        ),
+        LinkInfo(
+            link="#badge-2",
+            location=Path("tests/test_md_files/a.md"),
+            line_num=51,
+        ),
     ]
     assert md_info.links == ref_links