61 lines
1.5 KiB
Python
61 lines
1.5 KiB
Python
from __future__ import annotations
|
|
|
|
import re
|
|
from dataclasses import dataclass
|
|
from pathlib import Path
|
|
|
|
|
|
@dataclass(frozen=True)
|
|
class Heading:
|
|
level: int
|
|
title: str
|
|
slug: str
|
|
|
|
|
|
def slugify_heading(text: str) -> str:
|
|
slug = text.strip().casefold()
|
|
slug = re.sub(r"[^\w\s\u4e00-\u9fff-]", "", slug)
|
|
slug = re.sub(r"[\s_]+", "-", slug)
|
|
slug = re.sub(r"-{2,}", "-", slug)
|
|
return slug.strip("-")
|
|
|
|
|
|
def extract_headings_from_text(markdown_text: str) -> list[Heading]:
|
|
headings: list[Heading] = []
|
|
seen: dict[str, int] = {}
|
|
in_fenced_block = False
|
|
|
|
for line in markdown_text.splitlines():
|
|
stripped = line.strip()
|
|
if stripped.startswith("```") or stripped.startswith("~~~"):
|
|
in_fenced_block = not in_fenced_block
|
|
continue
|
|
if in_fenced_block:
|
|
continue
|
|
|
|
match = re.match(r"^(#{1,6})\s+(.+?)\s*#*\s*$", stripped)
|
|
if not match:
|
|
continue
|
|
|
|
title = match.group(2).strip()
|
|
slug = slugify_heading(title)
|
|
if not slug:
|
|
continue
|
|
|
|
count = seen.get(slug, 0)
|
|
seen[slug] = count + 1
|
|
if count:
|
|
slug = f"{slug}-{count + 1}"
|
|
|
|
headings.append(Heading(level=len(match.group(1)), title=title, slug=slug))
|
|
|
|
return headings
|
|
|
|
|
|
def extract_headings(path: Path) -> list[Heading]:
|
|
try:
|
|
return extract_headings_from_text(path.read_text(encoding="utf-8"))
|
|
except UnicodeDecodeError:
|
|
return []
|
|
|