initial

_pdf_build/md_common.py

@@ -0,0 +1,48 @@
+"""Shared markdown heading / slug helpers for docs PDF and TOC scripts."""
+
+from __future__ import annotations
+
+import re
+
+TOC_START = "<!-- toc -->"
+TOC_END = "<!-- /toc -->"
+
+
+def github_slug(text: str) -> str:
+    """GitHub/Cursor-compatible heading anchor."""
+    text = text.strip().lower()
+    text = re.sub(r"`([^`]+)`", r"\1", text)
+    text = re.sub(r"\*\*([^*]+)\*\*", r"\1", text)
+    text = re.sub(r"[*_]+", "", text)
+    text = re.sub(r"[^\w\s-]", "", text)
+    text = re.sub(r"\s+", "-", text)
+    text = re.sub(r"-+", "-", text)
+    return text.strip("-")
+
+
+def collect_headings(lines: list[str]) -> list[tuple[int, str, str]]:
+    """Return (level, title, slug) for ## and ### headings."""
+    out: list[tuple[int, str, str]] = []
+    used: dict[str, int] = {}
+    for line in lines:
+        m = re.match(r"^(#{2,3})\s+(.+?)\s*$", line)
+        if not m:
+            continue
+        level = len(m.group(1))
+        title = m.group(2).strip()
+        if title == "Table of contents":
+            continue
+        base = github_slug(title)
+        if not base:
+            continue
+        n = used.get(base, 0)
+        slug = base if n == 0 else f"{base}-{n}"
+        used[base] = n + 1
+        out.append((level, title, slug))
+    return out
+
+
+def strip_md_link_text(title: str) -> str:
+    t = re.sub(r"\*\*([^*]+)\*\*", r"\1", title)
+    t = re.sub(r"`([^`]+)`", r"\1", t)
+    return t