H2W-Public-Legal/scripts/build-manifest.py

#!/usr/bin/env python3
"""Builds dist/legal-manifest.json (HT-14): renders each project's markdown legal documents
to HTML+PDF and computes a content_hash, producing the single canonical manifest every
consumer backend imports at deploy time (HT-15) instead of hashing independently.

content_hash source (interim, per the HT-3 "Design döntés" comment): the source markdown's
git blob hash (`git hash-object`), NOT the rendered artifact's hash yet — that requires a
proven byte-for-byte-deterministic render, which this pandoc+WeasyPrint combination hasn't
been tested for (ResidentFirst's HRF-34 proved a *different* render pipeline deterministic,
not this one). Switching later doesn't invalidate old receipts, since a receipt is bound to
document_version, not content_hash alone.

effective_from source: parsed from each document's own "Hatálybalépés napja: <dátum>" line —
the one human-controlled field carrying the legally relevant date. A document whose date is
still the unfilled "[dátum]" placeholder gets effective_from: null (not yet effective)
rather than an invented date.

version: the short hash of the last commit that actually touched this file (NOT repo HEAD —
see HT-15's belépő ellenőrzés) — same convention as the two consumer sync scripts already
use for document_version.

Usage: python3 scripts/build-manifest.py
"""

import json
import re
import subprocess
from pathlib import Path

REPO_ROOT = Path(__file__).resolve().parent.parent
OUTPUT_DIR = REPO_ROOT / "dist"

HUNGARIAN_MONTHS = {
    "január": 1, "február": 2, "március": 3, "április": 4, "május": 5, "június": 6,
    "július": 7, "augusztus": 8, "szeptember": 9, "október": 10, "november": 11, "december": 12,
}

# e.g. "*Hatálybalépés napja: 2026. július 17. · Verzió: 1.0*"
DATE_LINE_RE = re.compile(r"Hatálybalépés napja:\s*(.+?)\s*·\s*Verzió:")
HU_DATE_RE = re.compile(r"(\d{4})\.\s*([a-záéíóöőúüű]+)\s*(\d{1,2})\.")


def parse_effective_from(markdown: str) -> str | None:
    m = DATE_LINE_RE.search(markdown)
    if not m:
        return None
    hu = HU_DATE_RE.match(m.group(1).strip())
    if not hu:
        return None  # still the "[dátum]" placeholder, or an unrecognized format
    year, month_name, day = hu.groups()
    month = HUNGARIAN_MONTHS.get(month_name.lower())
    if month is None:
        return None
    return f"{int(year):04d}-{month:02d}-{int(day):02d}"


def _git(*args: str) -> str:
    return subprocess.run(
        ["git", *args], cwd=REPO_ROOT, check=True, capture_output=True, text=True
    ).stdout.strip()


def git_blob_hash(path: Path) -> str:
    return _git("hash-object", str(path))


def last_commit_hash(path: Path) -> str:
    relative = path.relative_to(REPO_ROOT)
    # NOTE: requires full history (fetch-depth: 0 in CI) — a shallow clone would silently
    # resolve every file to the same single available commit. See HT-15.
    return _git("log", "-1", "--format=%h", "--", str(relative))


def render_html(markdown_path: Path, html_path: Path) -> None:
    subprocess.run(
        ["pandoc", str(markdown_path), "-o", str(html_path), "--standalone", "--metadata", "lang=hu"],
        check=True,
    )


def render_pdf(html_path: Path, pdf_path: Path) -> None:
    from weasyprint import HTML

    # full_fonts=True: WeasyPrint's default font subsetting is not byte-for-byte
    # deterministic (confirmed empirically while building HRF-34) — full embedding is.
    HTML(filename=str(html_path)).write_pdf(str(pdf_path), full_fonts=True)


def build_manifest_for_project(project_dir: Path) -> dict:
    manifest = {}
    for md_path in sorted(project_dir.glob("*.md")):
        doc_type = md_path.stem
        markdown = md_path.read_text(encoding="utf-8")

        out_dir = OUTPUT_DIR / project_dir.name
        out_dir.mkdir(parents=True, exist_ok=True)
        html_path = out_dir / f"{doc_type}.html"
        pdf_path = out_dir / f"{doc_type}.pdf"

        render_html(md_path, html_path)
        render_pdf(html_path, pdf_path)

        manifest[doc_type] = {
            "version": last_commit_hash(md_path),
            "effective_from": parse_effective_from(markdown),
            "content_hash": git_blob_hash(md_path),
            "html": f"{project_dir.name}/{doc_type}.html",
            "pdf": f"{project_dir.name}/{doc_type}.pdf",
        }
    return manifest


def main() -> None:
    OUTPUT_DIR.mkdir(exist_ok=True)
    full_manifest = {}
    for project_dir in sorted(REPO_ROOT.iterdir()):
        if not project_dir.is_dir() or project_dir.name.startswith(".") or project_dir.name in ("dist", "scripts"):
            continue
        if not list(project_dir.glob("*.md")):
            continue
        print(f"Renderelés: {project_dir.name}/")
        full_manifest[project_dir.name] = build_manifest_for_project(project_dir)

    manifest_path = OUTPUT_DIR / "legal-manifest.json"
    manifest_path.write_text(json.dumps(full_manifest, indent=2, ensure_ascii=False), encoding="utf-8")
    print(f"Manifest írva: {manifest_path}")


if __name__ == "__main__":
    main()