#!/usr/bin/env python3 """Verify the SubjectNest Year 6 authored opening sequence from pinned sources. Copyright 2026 NeuroForgeIO Pty Ltd SPDX-License-Identifier: Apache-2.0 Run from any directory: python3 products/curriculum-studio/content/year-6/verify_pack.py The verifier reads the canonical ACARA import and workbook; it writes nothing. """ from __future__ import annotations import hashlib import json import re import struct import subprocess import sys import xml.etree.ElementTree as ET from pathlib import Path ROOT = Path(__file__).resolve().parent CURRICULUM_STUDIO = ROOT.parent.parent CANONICAL = CURRICULUM_STUDIO / "data/frameworks/acara-v9.json" WORKBOOK = ( CURRICULUM_STUDIO / "research/sources/acara-australian-curriculum-v9-download-2026-09-29.xlsx" ) WORKBOOK_SHA256 = "db446882d2c00cf7c085a03e250e2442fda6c44011fc114680c46c1dc7a822c3" CODE_RE = re.compile(r"AC9[A-Z0-9]+") LINK_RE = re.compile(r"\[[^]]+\]\(([^)]+)\)") DAY_RE = re.compile(r"^## Day (\d+)\b[^\n]*$", re.MULTILINE) MOVE_RE = re.compile(r"^\d+\. \*\*[^*]*?(\d+):\*\*", re.MULTILINE) def sha256(path: Path) -> str: return hashlib.sha256(path.read_bytes()).hexdigest() def headings_slug(text: str) -> set[str]: result: set[str] = set() for heading in re.findall(r"^#{1,6}\s+(.+)$", text, re.MULTILINE): plain = heading.replace("`", "").lower() plain = "".join(char for char in plain if char.isalnum() or char in " -_") result.add(plain.replace(" ", "-")) return result def canonical_year6_codes(data: object) -> set[str]: result: set[str] = set() def visit(node: object) -> None: if isinstance(node, dict): if ( node.get("record_type") == "content_description" and isinstance(node.get("attributes"), dict) and node["attributes"].get("level") in {"Year 6", "Years 5 and 6"} and isinstance(node.get("code"), str) ): result.add(node["code"]) for value in node.values(): visit(value) elif isinstance(node, list): for value in node: visit(value) visit(data) return result def verify_markdown(codes: set[str], errors: list[str]) -> int: used: set[str] = set() for path in ROOT.rglob("*.md"): body = path.read_text(encoding="utf-8") used.update(CODE_RE.findall(body)) # Later subpacks carry their rights at pack level and verify locally. if "weeks-03-04" not in path.parts and "CC BY 4.0" not in body: errors.append(f"missing original-material rights: {path.relative_to(ROOT)}") for target in LINK_RE.findall(body): if target.startswith(("https://", "http://")): continue filename, _, anchor = target.partition("#") linked = (path.parent / filename).resolve() if filename else path.resolve() if not linked.exists(): errors.append(f"broken local link: {path.relative_to(ROOT)} -> {target}") elif anchor and linked.suffix == ".md" and anchor not in headings_slug(linked.read_text(encoding="utf-8")): errors.append(f"broken heading anchor: {path.relative_to(ROOT)} -> {target}") for code in sorted(used - codes): errors.append(f"not a Year 6/Years 5 and 6 content-description code: {code}") return len(used) def verify_sequence(errors: list[str]) -> None: planning = (ROOT / "year-sequence.md").read_text(encoding="utf-8") weeks = [int(n) for n in re.findall(r"^\| (\d+) \|", planning, re.MULTILINE)] if weeks != list(range(1, 41)): errors.append(f"planning weeks are not 1–40 in order: {weeks}") for subject in ("mathematics", "english"): path = ROOT / subject / "term-1/weeks-01-02/lessons.md" verify_days(path, 10, 25, errors) for name in ("week-01-choice-lab.md", "week-02-sun-earth-model.md"): verify_days(ROOT / "term-1" / name, 5, 35, errors) def verify_later_subpacks(errors: list[str]) -> None: for relative in ( "english/term-1/weeks-03-04", "mathematics/term-1/weeks-03-04", "integrated/term-1/weeks-03-04", "supplementary/term-1/weeks-03-04", ): verifier = ROOT / relative / "verify_pack.py" result = subprocess.run([sys.executable, str(verifier)], capture_output=True, text=True, check=False) if result.returncode: errors.append(f"subpack verification failed: {relative}: {(result.stdout + result.stderr).strip()}") def verify_days(path: Path, expected_days: int, expected_minutes: int, errors: list[str]) -> None: body = path.read_text(encoding="utf-8") matches = list(DAY_RE.finditer(body)) numbers = [int(match.group(1)) for match in matches] if numbers != list(range(1, expected_days + 1)): errors.append(f"day headings out of order in {path.relative_to(ROOT)}: {numbers}") for index, match in enumerate(matches): end = matches[index + 1].start() if index + 1 < len(matches) else len(body) moves = [int(n) for n in MOVE_RE.findall(body[match.end() : end])] # End material after the final lesson may contain numbered prose; only # the first five move rows define the day. moves = moves[:5] if len(moves) != 5 or sum(moves) != expected_minutes: errors.append( f"timing in {path.relative_to(ROOT)} Day {match.group(1)}: {moves}" ) def verify_visuals(errors: list[str]) -> int: svg_paths = list(ROOT.rglob("*.svg")) for path in svg_paths: try: ET.parse(path) except ET.ParseError as exc: errors.append(f"invalid SVG {path.relative_to(ROOT)}: {exc}") if not (path.with_suffix(".png").exists() or path.with_suffix(".pdf").exists()): errors.append(f"missing rendered PNG/PDF for {path.relative_to(ROOT)}") body = path.read_text(encoding="utf-8") if "II", header[16:24]) if width < 700 or height < 700: errors.append(f"PNG preview too small: {path.relative_to(ROOT)} {width}×{height}") return len(svg_paths) def verify_manifests(errors: list[str]) -> int: manifests = sorted(ROOT.rglob("manifest.sha256")) if len(manifests) != 4: errors.append(f"expected root, maths, English and integrated manifests; found {len(manifests)}") for manifest in manifests: listed: set[Path] = set() for line in manifest.read_text(encoding="utf-8").splitlines(): match = re.fullmatch(r"([0-9a-f]{64}) (.+)", line) if not match: errors.append(f"invalid manifest row in {manifest.relative_to(ROOT)}: {line}") continue digest, name = match.groups() path = (manifest.parent / name).resolve() if path in listed or not path.is_file() or path == manifest: errors.append(f"duplicate/missing/self manifest item: {name}") continue listed.add(path) if sha256(path) != digest: errors.append(f"hash mismatch: {path.relative_to(ROOT)}") if manifest == ROOT / "manifest.sha256": expected = {p.resolve() for p in ROOT.rglob("*") if p.is_file() and p != manifest and "__pycache__" not in p.parts} else: expected = {p.resolve() for p in manifest.parent.iterdir() if p.is_file() and p != manifest} if listed != expected: missing = sorted(str(p.relative_to(ROOT)) for p in expected - listed) extra = sorted(str(p.relative_to(ROOT)) for p in listed - expected) errors.append(f"manifest inventory {manifest.relative_to(ROOT)} missing={missing} extra={extra}") return len(manifests) def main() -> int: errors: list[str] = [] if not CANONICAL.is_file() or not WORKBOOK.is_file(): print("Pinned ACARA canonical import or workbook is missing", file=sys.stderr) return 1 if sha256(WORKBOOK) != WORKBOOK_SHA256: errors.append("official pinned workbook SHA-256 changed") codes = canonical_year6_codes(json.loads(CANONICAL.read_text(encoding="utf-8"))) used_count = verify_markdown(codes, errors) verify_sequence(errors) verify_later_subpacks(errors) visual_count = verify_visuals(errors) manifest_count = verify_manifests(errors) if errors: for error in errors: print(f"FAIL {error}", file=sys.stderr) return 1 print( f"PASS Year 6: {used_count} exact Year 6/band codes, 40 planning weeks, " f"40 English/maths lessons and 20 integrated sessions through Week 4, " f"50 optional five-area blocks in Weeks 3–4, {visual_count} SVG aids, " f"{manifest_count} opening/root hash manifests and 4 verified later subpacks" ) return 0 if __name__ == "__main__": raise SystemExit(main())