#!/usr/bin/env python3 # SPDX-License-Identifier: Apache-2.0 """Read-only Year 2 supplementary audit. Explicit flags update derived files.""" from __future__ import annotations import argparse import hashlib import json import re import subprocess import sys import xml.etree.ElementTree as ET from pathlib import Path from urllib.parse import unquote ROOT = Path(__file__).resolve().parent IMPORT = ROOT.parents[4] / "data/frameworks/acara-v9.json" SHA = "db446882d2c00cf7c085a03e250e2442fda6c44011fc114680c46c1dc7a822c3" SUBJECTS = ("science", "hass", "hpe", "arts") EXPECTED = { "science": set("AC9S2U02 AC9S2U03 AC9S2H01 AC9S2I01 AC9S2I02 AC9S2I03 AC9S2I04 AC9S2I05 AC9S2I06".split()), "hass": set("AC9HS2K02 AC9HS2K03 AC9HS2S01 AC9HS2S02 AC9HS2S03 AC9HS2S04 AC9HS2S05 AC9HS2S06".split()), "hpe": set("AC9HP2P02 AC9HP2P03 AC9HP2P04 AC9HP2P05 AC9HP2M01 AC9HP2M02 AC9HP2M04 AC9HP2M05".split()), "arts": set("AC9ADA2D01 AC9ADA2C01 AC9ADA2P01 AC9ADR2D01 AC9ADR2C01 AC9ADR2P01 AC9AMA2D01 AC9AMA2C01 AC9AMA2P01 AC9AMU2D01 AC9AMU2C01 AC9AMU2P01 AC9AVA2D01 AC9AVA2C01 AC9AVA2P01".split()), } AREAS = { "science": ("Science", "Year 2"), "hass": ("Humanities and Social Sciences", "Year 2"), "hpe": ("Health and Physical Education", "Years 1 and 2"), "arts": ("The Arts", "Years 1 and 2"), } def require(ok: bool, message: str) -> None: if not ok: raise AssertionError(message) def norm(value: str) -> str: return " ".join(value.split()) def source_records() -> tuple[dict, dict[str, dict]]: require(IMPORT.is_file(), f"Pinned official import missing: {IMPORT}") data = json.loads(IMPORT.read_text(encoding="utf-8")) require(data["source_sha256"] == SHA, "Official workbook SHA drift") require("australiancurriculum.edu.au" in data["source_url"], "Official workbook URL drift") require(data["framework"] == "Australian Curriculum Version 9.0", "Framework drift") records = {r["code"]: r for r in data["records"] if r.get("record_type") == "content_description"} require(len(records) > 1000, "Import lacks content descriptions") return data, records def crosswalk(data: dict, records: dict[str, dict]) -> str: rows = [ "# Australian Curriculum v9 crosswalk · Year 2 supplementary fortnight", "", "These are **partial links**, not complete coverage or achievement-standard judgments. Science and HASS rows are Year 2; HPE and all five Arts subjects use the official **Years 1 and 2** band. HASS technology facts use a linked museum source, while the invented map only rehearses scale language; actual `AC9HS2K03` evidence requires a checked local map. `AC9HS2K01` and `AC9HS2K04` are deliberately deferred for verified local and community-authorised sources. HPE movement/cooperation, Dance performance, Music sound/listening, and Media Arts technology/presentation are counted only when the named action actually occurs through an accessible route. A paper plan alone cannot supply that evidence.", "", f"Official source: [ACARA curriculum workbook]({data['source_url']}), accessed {data['retrieved_at']}; source SHA-256 `{data['source_sha256']}`. Wording below is the pinned import's content-description text with whitespace normalised. The source workbook row is retained for audit.", "", "| Pack | Official code | Source row | Official level | Official subject | Official content description |", "|---|---|---:|---|---|---|", ] for subject in SUBJECTS: for code in sorted(EXPECTED[subject]): record = records[code] a = record["attributes"] cells = [subject.upper(), code, str(record["source_row"]), a["level"], a["subject"], norm(record["plain_text"])] rows.append("| " + " | ".join(cell.replace("|", "\\|") for cell in cells) + " |") rows += [ "", "© Australian Curriculum, Assessment and Reporting Authority (ACARA) 2010 to present, unless otherwise indicated. Downloaded from the Australian Curriculum website (accessed 29 September 2026) and modified for plain-text display. Curriculum material is licensed under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/). [Terms and exclusions](https://www.australiancurriculum.edu.au/copyright-and-terms-of-use). ACARA does not endorse SubjectNest, and SubjectNest is not affiliated with, sponsored or approved by ACARA.", "", "The pinned import is a dated snapshot, not live synchronisation. Check the current official source and local state/territory implementation before future reissue. See [source, rights and review ledger](SOURCES-AND-REVIEW.md).", "", ] return "\n".join(rows) def check_content(records: dict[str, dict]) -> None: total = 0 for subject in SUBJECTS: teacher = (ROOT / subject / "TEACHER.md").read_text(encoding="utf-8") learner = (ROOT / subject / "LEARNER.md").read_text(encoding="utf-8") assess = (ROOT / subject / "ASSESSMENT.md").read_text(encoding="utf-8") declared_lines = re.findall(r"^\*\*Codes:\*\* ([^\n]+)", teacher, flags=re.M) require(len(declared_lines) == 10, f"{subject}: each day needs a code declaration") codes = set(re.findall(r"\bAC9[A-Z0-9]+\b", " ".join(declared_lines))) require(codes == EXPECTED[subject], f"{subject}: code set mismatch {codes ^ EXPECTED[subject]}") area, level = AREAS[subject] for code in codes: require(code in records, f"Unknown official code {code}") a = records[code]["attributes"] require(a["learning_area"] == area and a["level"] == level, f"{code}: area/level mismatch") for label, doc in (("teacher", teacher), ("learner", learner)): days = [int(n) for n in re.findall(r"^## Day (\d+)\b", doc, flags=re.M)] require(days == list(range(1, 11)), f"{subject}/{label}: expected Days 1–10 exactly") sections = re.split(r"^## Day \d+\b", teacher, flags=re.M)[1:] require(len(sections) == 10, f"{subject}: teacher sections") for day, section in enumerate(sections, 1): phases = re.findall(r"^([123])\. \*\*[^*]+ · (\d+) min\.\*\*", section, flags=re.M) require(phases == [("1", "2"), ("2", "7"), ("3", "3")], f"{subject} Day {day}: 2+7+3 phases") require("**Home/low-material:**" in section, f"{subject} Day {day}: missing home/low-material route") keyed = [int(n) for n in re.findall(r"^\| (\d+)\b", assess, flags=re.M)] require(keyed == list(range(1, 11)), f"{subject}: key must cover Days 1–10") require("next move" in assess.lower() or "recheck" in assess.lower(), f"{subject}: missing next move") require(not re.search(r"ASSESSMENT\.md|\*\*Answer key\*\*", learner, flags=re.I), f"{subject}: learner key leakage") total += len(sections) require(total == 40, "Expected 40 short blocks") arts = (ROOT / "arts/TEACHER.md").read_text(encoding="utf-8") for form in ("Dance", "Drama", "Media Arts", "Music", "Visual Arts"): require(len(re.findall(rf"^## Day \d+ — {form}:", arts, flags=re.M)) == 2, f"Arts: expected two {form} days") def check_links() -> int: count = 0 for path in ROOT.rglob("*.md"): content = path.read_text(encoding="utf-8") for url in re.findall(r"(? {url}") count += 1 return count def check_assets() -> None: ns = {"s": "http://www.w3.org/2000/svg"} alternatives = (ROOT / "print/TEXT-ALTERNATIVES.md").read_text(encoding="utf-8") subprocess.run([sys.executable, str(ROOT / "print/generate_print.py")], check=True, capture_output=True, text=True) for subject in SUBJECTS: svg = ROOT / "print" / f"{subject}-aid.svg" pdf = svg.with_suffix(".pdf") require(svg.is_file() and pdf.is_file(), f"{subject}: missing SVG/PDF") root = ET.parse(svg).getroot() require(root.attrib.get("width") == "210mm" and root.attrib.get("height") == "297mm", f"{subject}: SVG not A4") require(root.find("s:title", ns) is not None and root.find("s:desc", ns) is not None, f"{subject}: missing SVG access text") info = subprocess.run(["pdfinfo", str(pdf)], capture_output=True, text=True, check=True).stdout require("(A4)" in info and "Pages: 1" in info, f"{subject}: PDF not one A4 page") searchable = subprocess.run(["pdftotext", str(pdf), "-"], capture_output=True, text=True, check=True).stdout require(len(searchable) > 200 and "CC BY 4.0" in searchable, f"{subject}: PDF text/credit missing") fonts = subprocess.run(["pdffonts", str(pdf)], capture_output=True, text=True, check=True).stdout require("DejaVu" in fonts, f"{subject}: expected embedded DejaVu subset") require(re.search(rf"^## (?:The )?{subject}\b", alternatives, flags=re.I | re.M) is not None, f"{subject}: text alternative missing") require(re.search(r"ASSESSMENT\.md|\| Day \| Exact check|^Correct:", alternatives, flags=re.I | re.M) is None, "Print alternative leaks key") def file_hashes() -> str: files = sorted(p for p in ROOT.rglob("*") if p.is_file() and p.name != "MANIFEST.sha256" and "__pycache__" not in p.parts) return "".join(f"{hashlib.sha256(p.read_bytes()).hexdigest()} {p.relative_to(ROOT)}\n" for p in files) def main() -> None: parser = argparse.ArgumentParser() parser.add_argument("--write-crosswalk", action="store_true") parser.add_argument("--write-manifest", action="store_true") args = parser.parse_args() data, records = source_records() expected_crosswalk = crosswalk(data, records) crosswalk_path = ROOT / "CURRICULUM-CROSSWALK.md" if args.write_crosswalk: crosswalk_path.write_text(expected_crosswalk, encoding="utf-8") require(crosswalk_path.read_text(encoding="utf-8") == expected_crosswalk, "Crosswalk differs from pinned official import") check_content(records) links = check_links() check_assets() expected_manifest = file_hashes() manifest = ROOT / "MANIFEST.sha256" if args.write_manifest: manifest.write_text(expected_manifest, encoding="utf-8") require(manifest.read_text(encoding="utf-8") == expected_manifest, "Hash manifest mismatch") print(f"PASS: 4 subjects · 40 blocks · {sum(map(len, EXPECTED.values()))} pinned codes · 4 SVG/PDF aids · {links} local links · {len(expected_manifest.splitlines())} hashes") if __name__ == "__main__": try: main() except (AssertionError, KeyError, FileNotFoundError, subprocess.CalledProcessError) as exc: print(f"FAIL: {exc}", file=sys.stderr) raise SystemExit(1)