#!/usr/bin/env python3 # SPDX-License-Identifier: MIT # Copyright (c) 2026 Pablo Nogueira Grossi / G6 LLC """ build_rh_paper.py — render RH_arithmetic_contact_structure.md as an HTML edition. The markdown is the manuscript; book4/rh-paper.html is a *rendering* of it, in the shape a reader expects from a preprint server: title block, abstract, numbered sections, a table of contents, MathJax, and the DOI at the top where somebody looking for it will find it. Two files, one source. Nothing is retyped, so the HTML cannot drift from the manuscript the way a hand-maintained copy would — which is the same argument build_book3.py and build_rungs.py make about their own sources. USAGE python3 tools/build_rh_paper.py # report what would change python3 tools/build_rh_paper.py --write # write book4/rh-paper.html Exit status is 1 when the HTML is missing or stale, so it can gate a check. """ from __future__ import annotations import html as H import re import sys from pathlib import Path ROOT = Path(__file__).resolve().parent.parent SRC = ROOT / "RH_arithmetic_contact_structure.md" OUT = ROOT / "book4" / "rh-paper.html" DOI = "10.5281/zenodo.22179684" def inline(t: str) -> str: """Markdown inline -> HTML. Math between $ and `code` are protected while bold, italic and links are applied, so emphasis may span them (**no `sorryAx`**).""" keep: list[str] = [] def stash(m: "re.Match[str]") -> str: seg = m.group(0) keep.append(f"{H.escape(seg[1:-1])}" if seg.startswith("`") else seg) return f"\x00{len(keep) - 1}\x00" t = re.sub(r"(\$\$[^$]*\$\$|\$[^$\n]*\$|`[^`]*`)", stash, t) t = H.escape(t) def img(m: "re.Match[str]") -> str: src = m.group(2) png = src[:-4] + ".png" if src.endswith(".pdf") and (OUT.parent / (src[:-4] + ".png")).exists() else src return f'figure
{m.group(1)}' t = re.sub(r"!\[([^\]]*)\]\(([^)\s]+)\)(?:\{[^}]*\})?", img, t) t = re.sub(r"\[([^\]]+)\]\(((?:https?://|\.{0,2}/)?[^)\s]+)\)", r'\1', t) t = re.sub(r"\*\*([^*]+)\*\*", r"\1", t) t = re.sub(r"(?\1", t) return re.sub(r"\x00(\d+)\x00", lambda m: keep[int(m.group(1))], t) def render(md: str) -> tuple[str, list[tuple[int, str, str]]]: body, toc, lines, i = [], [], md.split("\n"), 0 n_sec = 0 while i < len(lines): ln = lines[i] if ln.startswith("|") and i + 1 < len(lines) and set(lines[i + 1].replace("|", "").strip()) <= set("-: "): head = [c.strip() for c in ln.strip("|").split("|")] i += 2 rows = [] while i < len(lines) and lines[i].startswith("|"): rows.append([c.strip() for c in lines[i].strip("|").split("|")]) i += 1 body.append("
" + "".join(f"" for c in head) + "" + "".join("" + "".join(f"" for c in r) + "" for r in rows) + "
{inline(c)}
{inline(c)}
") continue m = re.match(r"^(#{1,3})\s+(.*)$", ln) if m: lvl, txt = len(m.group(1)), m.group(2).strip() if lvl == 1: body.append(f"

{inline(txt)}

") else: n_sec += 1 sid = f"s{n_sec}" tag = "h2" if lvl == 2 else "h3" body.append(f'<{tag} id="{sid}">{inline(txt)}') toc.append((lvl, sid, txt)) i += 1 continue if re.match(r"^\d+\.\s", ln) or ln.startswith("- "): ordered = bool(re.match(r"^\d+\.\s", ln)) items = [] while i < len(lines) and (re.match(r"^\d+\.\s", lines[i]) or lines[i].startswith("- ") or (items and lines[i].startswith(" ") and lines[i].strip())): if re.match(r"^\d+\.\s", lines[i]) or lines[i].startswith("- "): items.append(re.sub(r"^(\d+\.|-)\s+", "", lines[i])) else: items[-1] += " " + lines[i].strip() i += 1 t = "ol" if ordered else "ul" body.append(f"<{t}>" + "".join(f"
  • {inline(x)}
    • " for x in items) + f"") continue if ln.strip() == "---": body.append("
    ") i += 1 continue if ln.strip() == "": i += 1 continue para = [ln] i += 1 while i < len(lines) and lines[i].strip() and not re.match(r"^(#{1,3}\s|\||-\s|\d+\.\s|---$)", lines[i]): para.append(lines[i]) i += 1 body.append(f"

    {inline(' '.join(para))}

    ") return "\n".join(body), toc PAGE = """ The Riemann Hypothesis as Non-Integrability of an Arithmetic Contact Structure · Principia Orthogona Book 4
    ⚜ PRINCIPIA ORTHOGONA · Book 4 Ch 12 · The Critical Contact · Zenodo ↗
    Preprint · not peer reviewed · Book 4 · the arithmetic arc
    __TITLE__

    Pablo Nogueira Grossi (framework) · Collaborative Draft

    DOI reserved: __DOI__ — Zenodo community Principia Orthogona.
    Deposit pending; the DOI will not resolve until the record is published.
    Manuscript source: RH_arithmetic_contact_structure.md · this page is generated from it by tools/build_rh_paper.py.
    Contents
    __TOC__
    __BODY__
    """ def main() -> int: write = "--write" in sys.argv md = SRC.read_text(encoding="utf-8") body, toc = render(md) m = re.search(r"^# (.+)$", md, re.M) title = f"

    {inline(m.group(1))}

    " if m else "

    Untitled

    " body = re.sub(r"

    .*?

    \s*", "", body, count=1, flags=re.S) toc_html = "".join( f'{H.escape(txt)}' for lvl, sid, txt in toc) page = (PAGE.replace("__TITLE__", " " + title) .replace("__TOC__", toc_html) .replace("__BODY__", body) .replace("__DOI__", DOI)) old = OUT.read_text(encoding="utf-8") if OUT.exists() else "" print(f"source {SRC.name}: {len(md.splitlines())} lines") print(f"rendered {OUT.relative_to(ROOT)}: {len(toc)} sections, {len(page)} bytes") if page == old: print("\nUP TO DATE — the HTML matches the manuscript.") return 0 if write: OUT.write_text(page, encoding="utf-8") print("\nWROTE " + str(OUT.relative_to(ROOT))) return 0 print("\nSTALE — the HTML does not match the manuscript. Re-run with --write.") return 1 if __name__ == "__main__": sys.exit(main())