#!/usr/bin/env python3 # SPDX-License-Identifier: Apache-2.0 """Read-only source/content/link/print/hash audit for Year 3 supplement. Only --write-crosswalk and --write-manifest change derived files. Rendered lesson pages and SVG/PDF assets have their own opt-in generation commands. """ 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 from build_content import CARDS, LEARNER_PROMPTS, render ROOT = Path(__file__).resolve().parent SOURCE = ROOT.parents[4] / "data/frameworks/acara-v9.json" SHA = "db446882d2c00cf7c085a03e250e2442fda6c44011fc114680c46c1dc7a822c3" SUBJECTS = ("science", "hass", "hpe", "technologies", "arts") EXPECTED = { "science": {"AC9S3H01", "AC9S3H02", "AC9S3I01", "AC9S3I02", "AC9S3I03", "AC9S3I04", "AC9S3I05", "AC9S3I06", "AC9S3U02", "AC9S3U03"}, "hass": {"AC9HS3K06", "AC9HS3K07", "AC9HS3S01", "AC9HS3S02", "AC9HS3S03", "AC9HS3S04", "AC9HS3S05", "AC9HS3S06", "AC9HS3S07"}, "hpe": {"AC9HP4M01", "AC9HP4M02", "AC9HP4M03", "AC9HP4M07", "AC9HP4M08", "AC9HP4M09", "AC9HP4P04", "AC9HP4P05", "AC9HP4P06", "AC9HP4P07", "AC9HP4P08", "AC9HP4P09"}, "technologies": {"AC9TDE4K01", "AC9TDE4K02", "AC9TDE4P01", "AC9TDE4P02", "AC9TDE4P03", "AC9TDE4P04", "AC9TDE4P05", "AC9TDI4K03", "AC9TDI4P01", "AC9TDI4P02", "AC9TDI4P03", "AC9TDI4P05"}, "arts": {"AC9ADA4C01", "AC9ADA4D01", "AC9ADA4P01", "AC9ADR4C01", "AC9ADR4D01", "AC9ADR4P01", "AC9AMA4C01", "AC9AMA4D01", "AC9AMA4P01", "AC9AMU4C01", "AC9AMU4D01", "AC9AMU4P01", "AC9AVA4C01", "AC9AVA4D01", "AC9AVA4P01"}, } AREA_LEVEL = { "science": ("Science", "Year 3"), "hass": ("Humanities and Social Sciences", "Year 3"), "hpe": ("Health and Physical Education", "Years 3 and 4"), "technologies": ("Technologies", "Years 3 and 4"), "arts": ("The Arts", "Years 3 and 4"), } 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]]: data = json.loads(SOURCE.read_text(encoding="utf-8")) require(data["source_sha256"] == SHA, "Pinned workbook checksum drift") require(data["framework"] == "Australian Curriculum Version 9.0", "Framework drift") require("australiancurriculum.edu.au" in data["source_url"], "Official source URL drift") records = {r["code"]: r for r in data["records"] if r.get("record_type") == "content_description"} require(len(records) > 1000, "Import too small") return data, records def crosswalk(data: dict, records: dict[str, dict]) -> str: out = [ "# Australian Curriculum v9 crosswalk · Year 3 supplementary Weeks 3–4", "", "These are **partial content-description links**, not complete curriculum or achievement-standard coverage. Science and HASS are Year 3. HPE, both Technologies subjects and all five Arts subjects are officially in the **Years 3 and 4** band. The cards exercise selected descriptions; a 12-minute activity alone cannot establish achievement. Real local HASS rules/community claims need a current approved source. No First Nations Country/Place content, cultural forms or translations are invented. Actual action matters: paper movement plans, paper media storyboards and silent beat cards do not show bodily performance, media-tool production or sounded music.", "", f"Source: [ACARA official workbook]({data['source_url']}), retrieved {data['retrieved_at']}; SHA-256 `{data['source_sha256']}`. Wording below is the pinned import's content-description text with whitespace normalised. Original workbook rows are 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]): r = records[code] a = r["attributes"] cells = [subject.upper(), code, str(r["source_row"]), a["level"], a["subject"], norm(r["plain_text"])] out.append("| " + " | ".join(cell.replace("|", "\\|") for cell in cells) + " |") out += [ "", "© 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.", "", "This is a dated import, not a live update feed. Check the current official curriculum and state or territory implementation before reissue. See [source and rights ledger](SOURCES-AND-REVIEW.md).", "", ] return "\n".join(out) def check_cards(records: dict[str, dict]) -> None: require(tuple(CARDS) == SUBJECTS, "Subject order drift") all_codes: set[str] = set() for subject in SUBJECTS: cards = CARDS[subject] require(len(cards) == len(LEARNER_PROMPTS[subject]) == 10, f"{subject}: need ten distinct cards") subject_codes = {code for card in cards for code in card.codes.split()} require(subject_codes == EXPECTED[subject], f"{subject}: code set differs") for code in subject_codes: require(code in records, f"Unknown code {code}") a = records[code]["attributes"] require((a["learning_area"], a["level"]) == AREA_LEVEL[subject], f"{code}: area or band mismatch") all_codes |= subject_codes for idx, card in enumerate(cards, 11): require(all((card.title, card.codes, card.notice, card.try_, card.show, card.choices, card.check, card.next_, card.prepare, card.home)), f"{subject} Day {idx}: empty teaching field") require(len(LEARNER_PROMPTS[subject][idx - 11]) >= 110, f"{subject} Day {idx}: thin learner task") for name, expected in render(subject).items(): path = ROOT / subject / name require(path.is_file() and path.read_text(encoding="utf-8") == expected, f"{subject}/{name}: generated lesson drift") teacher = (ROOT / subject / "TEACHER.md").read_text(encoding="utf-8") learner = (ROOT / subject / "LEARNER.md").read_text(encoding="utf-8") key = (ROOT / subject / "ASSESSMENT.md").read_text(encoding="utf-8") for label, doc in (("teacher", teacher), ("learner", learner)): days = [int(n) for n in re.findall(r"^## Day (\d+)\b", doc, flags=re.MULTILINE)] require(days == list(range(11, 21)), f"{subject}/{label}: need Days 11–20 exactly") require(len(re.findall(r"^1\. \*\*Notice · 2 min\.\*\*", teacher, flags=re.MULTILINE)) == 10, f"{subject}: notice timings") require(len(re.findall(r"^2\. \*\*Try/make · 7 min\.\*\*", teacher, flags=re.MULTILINE)) == 10, f"{subject}: making timings") require(len(re.findall(r"^3\. \*\*Show · 3 min\.\*\*", teacher, flags=re.MULTILINE)) == 10, f"{subject}: show timings") require(len(re.findall(r"^\| (?:1[1-9]|20) \|", key, flags=re.MULTILINE)) == 10, f"{subject}: separate key rows") require("ASSESSMENT.md" not in learner and "answer key" not in learner.lower(), f"{subject}: teacher key leakage") require(len(all_codes) == 58, "Unique code count drift") for form in ("Dance", "Drama", "Media Arts", "Music", "Visual Arts"): require(sum(card.title.startswith(form + ":") for card in CARDS["arts"]) == 2, f"Arts: need two {form} cards") require(all("MODEL" in LEARNER_PROMPTS["science"][i] for i in (3, 5, 7, 8, 9)), "Science model labels missing") 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: subprocess.run([sys.executable, str(ROOT / "print/generate_print.py")], check=True, capture_output=True, text=True) alternatives = (ROOT / "print/TEXT-ALTERNATIVES.md").read_text(encoding="utf-8") ns = {"svg": "http://www.w3.org/2000/svg"} 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("svg:title", ns) is not None and root.find("svg:desc", ns) is not None, f"{subject}: missing SVG title/description") info = subprocess.run(["pdfinfo", str(pdf)], check=True, capture_output=True, text=True).stdout require("(A4)" in info and "Pages: 1" in info, f"{subject}: PDF not one A4 page") words = subprocess.run(["pdftotext", str(pdf), "-"], check=True, capture_output=True, text=True).stdout require(len(words) > 250 and "CC BY 4.0" in words, f"{subject}: PDF text/credit missing") fonts = subprocess.run(["pdffonts", str(pdf)], check=True, capture_output=True, text=True).stdout require("DejaVu" in fonts, f"{subject}: DejaVu subset missing") require(re.search(rf"^## {subject}\b", alternatives, flags=re.MULTILINE | re.IGNORECASE), f"{subject}: text equivalent missing") require("dejavu-font-copyright.txt" in (ROOT / "print/FONT-RIGHTS.md").read_text(encoding="utf-8"), "Font rights notice") def 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() crosswalk_text = crosswalk(data, records) crosswalk_path = ROOT / "CURRICULUM-CROSSWALK.md" if args.write_crosswalk: crosswalk_path.write_text(crosswalk_text, encoding="utf-8") require(crosswalk_path.read_text(encoding="utf-8") == crosswalk_text, "Crosswalk differs from pinned source") check_cards(records) links = check_links() check_assets() expected = hashes() manifest = ROOT / "MANIFEST.sha256" if args.write_manifest: manifest.write_text(expected, encoding="utf-8") require(manifest.read_text(encoding="utf-8") == expected, "Hash manifest mismatch") print(f"PASS: 5 subjects · 50 distinct 12-minute blocks · 58 pinned codes · 5 original SVG/PDF aids · {links} local links · {len(expected.splitlines())} file hashes") if __name__ == "__main__": try: main() except (AssertionError, KeyError, FileNotFoundError, subprocess.CalledProcessError) as exc: print(f"FAIL: {exc}", file=sys.stderr) raise SystemExit(1)