"""Build the offline HTML5 edition of the Week 8 Markdown report."""
from __future__ import annotations
import html
import re
from pathlib import Path
from urllib.parse import unquote, urlsplit
import mistune
from bs4 import BeautifulSoup
ROOT = Path(__file__).resolve().parent
SOURCE = ROOT / "Week8_研究报告.md"
OUTPUT = ROOT / "Week8_研究报告.html"
class ReportRenderer(mistune.HTMLRenderer):
def __init__(self):
super().__init__(escape=False)
self.headings: list[tuple[int, str, str]] = []
self.used_ids: set[str] = set()
def heading(self, text, level, **attrs):
label = BeautifulSoup(text, "html.parser").get_text(" ", strip=True)
base = re.sub(r"[^\w\u4e00-\u9fff]+", "-", label).strip("-").lower() or "section"
anchor, index = base, 2
while anchor in self.used_ids:
anchor = f"{base}-{index}"
index += 1
self.used_ids.add(anchor)
self.headings.append((level, anchor, label))
return f'{text}\n'
def block_code(self, code, info=None):
language = (info or "").strip().split(" ", 1)[0]
if language == "math":
lines = "\n".join(f'{html.escape(line) or " "}
' for line in code.rstrip().splitlines())
return f'{lines}
\n'
label = f'{html.escape(language)}
' if language else ""
return f'{label}
{html.escape(code)}
{soup}
'''
OUTPUT.write_text(document, encoding="utf-8")
rendered = BeautifulSoup(document, "html.parser")
ids = [tag["id"] for tag in rendered.find_all(id=True)]
assert len(ids) == len(set(ids)), "Duplicate HTML anchors"
for link in rendered.select("nav a[href^='#']"):
assert link["href"][1:] in ids, f"Broken navigation: {link['href']}"
local_targets = []
for element in rendered.select("[href], [src]"):
target = element.get("href") or element.get("src")
if target.startswith("#") or urlsplit(target).scheme:
continue
local_targets.append(target)
assert (ROOT / unquote(urlsplit(target).path)).exists(), f"Missing local reference: {target}"
assert rendered.html.get("lang") == "zh-CN"
assert len(rendered.select(".equation")) == len(re.findall(r"^```math\s*$", SOURCE.read_text(encoding="utf-8-sig"), re.M))
print(f"Created: {OUTPUT.name}")
print(f"Sections: {len(renderer.headings)}; tables: {len(rendered.find_all('table'))}; equations: {len(rendered.select('.equation'))}")
print(f"Verified local references: {len(local_targets)}")
if __name__ == "__main__":
main()