# SPDX-License-Identifier: Apache-2.0
"""Fail-closed, read-only by default receipt for HASS Weeks 9-10."""

from __future__ import annotations

import argparse
import ast
import hashlib
import json
import re
import subprocess
import xml.etree.ElementTree as ET
from pathlib import Path
from urllib.parse import unquote

ROOT = Path(__file__).resolve().parent
STUDIO = ROOT.parents[4]
SOURCE_SHA = "db446882d2c00cf7c085a03e250e2442fda6c44011fc114680c46c1dc7a822c3"
ROWS = {
    "AC9HSFK01": 1213,
    "AC9HSFK02": 1217,
    "AC9HSFK03": 1221,
    "AC9HSFK04": 1226,
    "AC9HSFS01": 1233,
    "AC9HSFS02": 1237,
    "AC9HSFS03": 1241,
    "AC9HSFS04": 1245,
    "AC9HSFS05": 1251,
}
HELD_CODES = {"AC9HSFK01", "AC9HSFK02", "AC9HSFK04"}
PARTIAL_CODES = set(ROWS) - HELD_CODES
QCAA_URL = (
    "https://www.qcaa.qld.edu.au/p-10/aciq/version-9/"
    "learning-areas/p-10-humanities-and-social-sciences/hass"
)
QCAA_ALIGNMENT_URL = (
    "https://www.qcaa.qld.edu.au/downloads/aciqv9/"
    "humanities-and-social-sciences/curriculum/ac9_hass_prep_as_cd_alignment.pdf"
)
STEMS = (
    "pebble-room-sketch",
    "rafi-request",
    "mara-plan",
    "ivo-later-note",
    "pebble-views",
    "source-effect-mat",
    "check-a-sage-room",
    "check-b-horizon-room",
)
FINAL_DAY = 50
CHECK_COUNT = 2
MIN_PDF_WORDS = 20
EXPECTED_CODES = {
    41: {"AC9HSFK03", "AC9HSFS01", "AC9HSFS02"},
    42: {"AC9HSFS02", "AC9HSFS05", "AC9HSFK03"},
    43: {"AC9HSFS01", "AC9HSFS04", "AC9HSFK03"},
    44: {"AC9HSFS03", "AC9HSFS04", "AC9HSFK03"},
    45: {"AC9HSFS01", "AC9HSFS02", "AC9HSFS04", "AC9HSFS05"},
    46: {"AC9HSFS02", "AC9HSFS04", "AC9HSFS05"},
    47: {"AC9HSFS01", "AC9HSFS04", "AC9HSFK03"},
    48: {"AC9HSFS03", "AC9HSFS04", "AC9HSFK03"},
    49: {"AC9HSFK03", "AC9HSFS01", "AC9HSFS03", "AC9HSFS04", "AC9HSFS05"},
    50: set(PARTIAL_CODES),
}
PDF_PHRASES = {
    "pebble-room-sketch": ("WIDE BENCH", "RETURN TRAY", "DISPLAY BOARD", "CENTRE"),
    "rafi-request": ("RAFI", "picture label", "return tray"),
    "mara-plan": ("MARA", "LABEL PLAN", "DASHED = PLANNED"),
    "ivo-later-note": ("IVO", "large picture label", "wide bench"),
    "pebble-views": ("RAFI", "UMA", "display board", "return tray"),
    "source-effect-mat": ("REQUEST", "REPORTED LATER", "EFFECT STILL UNKNOWN"),
    "check-a-sage-room": ("LONG LOW SHELF", "ROUND MAT", "NELL", "ARI"),
    "check-b-horizon-room": ("WIDE DESK", "TWO POCKETS", "LEA", "NOAH", "JAE", "MINA"),
}


def need(ok: object, message: str) -> None:
    """Fail with one actionable explanation."""
    if not ok:
        raise AssertionError(message)


def read(name: str) -> str:
    """Read authored UTF-8 text."""
    return (ROOT / name).read_text(encoding="utf-8")


def source() -> None:
    """Pin exact official rows and Queensland Prep entry points."""
    workbook = (
        STUDIO
        / "research/sources/acara-australian-curriculum-v9-download-2026-09-29.xlsx"
    )
    imported = json.loads(
        (STUDIO / "data/frameworks/acara-v9.json").read_text(encoding="utf-8")
    )
    snapshot = json.loads(read("source-snapshot.json"))
    crosswalk = read("CURRICULUM-CROSSWALK.md")
    need(
        hashlib.sha256(workbook.read_bytes()).hexdigest()
        == imported["source_sha256"]
        == snapshot["workbook_sha256"]
        == SOURCE_SHA,
        "ACARA official workbook/import/snapshot SHA drift",
    )
    need(snapshot["content_rows"] == ROWS, "ACARA row pin drift")
    need(
        set(snapshot["baseline_partial_codes"]) == PARTIAL_CODES
        and set(snapshot["not_claimed_without_local_sources"]) == HELD_CODES,
        "Partial/held source accounting drift",
    )
    need(
        snapshot["queensland_prep_entry_point_url"] == QCAA_URL
        and snapshot["queensland_prep_alignment_url"] == QCAA_ALIGNMENT_URL
        and QCAA_URL in crosswalk
        and QCAA_ALIGNMENT_URL in crosswalk,
        "QCAA Prep URL pin drift",
    )
    records = {
        record["code"]: record
        for record in imported["records"]
        if record.get("record_type") == "content_description"
        and record.get("code") in ROWS
    }
    need(set(records) == set(ROWS), "Foundation HASS rows missing")
    for code, row in ROWS.items():
        item = records[code]
        attrs = item["attributes"]
        need(
            item["source_row"] == row
            and attrs["learning_area"] == "Humanities and Social Sciences"
            and attrs["subject"] == "HASS F-6"
            and attrs["level"] == "Foundation Year",
            f"Official exact record drift: {code}",
        )
        pattern = (
            rf"^\| {code} \| {row} \| Humanities and Social Sciences · HASS F-6 · "
            rf"Foundation Year \| {re.escape(item['plain_text'])} \|"
        )
        need(
            re.search(pattern, crosswalk, re.MULTILINE),
            f"Verbatim crosswalk drift: {code}",
        )
        if code in HELD_CODES:
            need(
                re.search(rf"^\| {code} \|.*\*\*Hold:", crosswalk, re.MULTILINE),
                f"Local/private/cultural hold absent: {code}",
            )
    need(
        "k01, k02 and k04 remain open" in crosswalk.lower()
        and "country/place" in crosswalk.lower()
        and "not secure exams" in crosswalk.lower(),
        "Crosswalk evidence boundary absent",
    )
    print("PASS nine exact ACARA v9 Foundation HASS rows and QCAA Prep pins")


def sections(body: str, pattern: str) -> list[tuple[int, str]]:
    """Split numbered day sections without accepting duplicates."""
    marks = list(re.finditer(pattern, body, re.MULTILINE))
    return [
        (
            int(mark.group(1)),
            body[
                mark.end() : marks[index + 1].start()
                if index + 1 < len(marks)
                else len(body)
            ],
        )
        for index, mark in enumerate(marks)
    ]


def pedagogy() -> None:
    """Check ten timed scripts, thirty access routes and twenty worked swaps."""
    lessons = read("LESSONS.md")
    teacher_days = sections(lessons, r"^## Week \d+ · Day (\d+)\b")
    need(
        [day for day, _ in teacher_days] == list(range(41, 51)),
        "Teacher day sequence",
    )
    for day, body in teacher_days:
        minutes = [
            int(value)
            for value in re.findall(
                r"^\d+\. \*\*[^\n]*? · (\d+) min\.\*\*", body, re.MULTILINE
            )
        ]
        need(minutes == [3, 4, 5, 7, 4, 2], f"Day {day} 25-min timing: {minutes}")
        target = re.search(r"^\*\*Target/codes:\*\* ([^\n]+)", body, re.MULTILINE)
        need(target is not None, f"Day {day} target absent")
        codes = set(re.findall(r"\bAC9HSF(?:K|S)\d\d\b", target.group(1)))
        if day == FINAL_DAY:
            need(len(codes) == len(PARTIAL_CODES), "Day 50 all sampled codes absent")
        need(codes == EXPECTED_CODES[day], f"Day {day} code drift: {codes}")
        need(
            "**Check/respond" in body
            and any(token in body.lower() for token in ("record", "collect"))
            and "**Exit" in body,
            f"Day {day} feedback/record absent",
        )
    cards = read("LEARNER-CARDS.md")
    learner_days = sections(cards, r"^## Day (\d+)\b")
    need([day for day, _ in learner_days] == list(range(41, 51)), "Learner days")
    for day, body in learner_days:
        need(
            "**Shared target:**" in body
            and all(
                re.search(rf"^- \*\*{route} ·", body, re.MULTILINE) for route in "ABC"
            )
            and "\n\n- **A ·" in body
            and "\n\n**Home:**" in body,
            f"Day {day} routes/home or CommonMark list spacing",
        )
    swaps = read("PRACTICE-SWAPS.md")
    rows = re.findall(r"^\| (\d+) \| (.+) \| (.+) \|$", swaps, re.MULTILINE)
    need(
        [int(day) for day, _, _ in rows] == list(range(41, 51))
        and all(one.startswith("**") and two.startswith("**") for _, one, two in rows),
        "Twenty worked context swaps absent",
    )
    need(
        "not fixed learning styles" in cards.lower()
        and "no child must" in read("README.md").lower()
        and "cultural authority" in read("LOCAL-SOURCE-INSERT.md").lower(),
        "Access/privacy/cultural boundary absent",
    )
    print("PASS ten 25-minute scripts, 30 routes, 20 worked swaps")


def checks() -> None:
    """Check fresh public cases, separation and worked-answer integrity."""
    student = read("STUDENT-CHECKS.md")
    key = read("teacher/KEY-AND-NEXT.md")
    linear_key = " ".join(re.sub(r"[*_]", "", key.lower()).split())
    need(
        re.findall(r"^## Check ([AB]) · Day (\d+)\b", student, re.MULTILINE)
        == [("A", "45"), ("B", "50")],
        "Fresh check schedule drift",
    )
    need(student.count("\n\n1. ") == CHECK_COUNT, "Student list spacing drift")
    need(
        "teacher/KEY-AND-NEXT.md" not in student
        and "teacher/KEY-AND-NEXT.md" not in read("LEARNER-CARDS.md")
        and "publicly accessible" in key.lower()
        and "not secure exams" in student.lower(),
        "Public check/key separation absent",
    )
    routine = read("PRACTICE-SWAPS.md") + " ".join(
        body
        for day, body in sections(read("LEARNER-CARDS.md"), r"^## Day (\d+)\b")
        if day not in (45, 50)
    )
    for leaked in (
        "Sage Room",
        "Nell",
        "Ari",
        "Horizon Room",
        "Lea",
        "Noah",
        "Jae",
        "Mina",
    ):
        need(
            leaked not in routine,
            f"Held source leaked into earlier routine: {leaked}",
        )
    for phrase in (
        "long low shelf",
        "round mat",
        "Nell",
        "Ari",
        "No source shows a square label",
        "wide desk left",
        "two paper pockets right",
        "Lea",
        "Noah",
        "Jae",
        "Mina",
        "No real use or benefit",
    ):
        need(phrase.lower() in linear_key, f"Worked key fact missing: {phrase}")
    need(
        "No actual Sage Room" in student
        and "No real pocket" in student
        and "no real child/classroom outcome" in key.lower(),
        "Check action-observed boundary absent",
    )
    print("PASS two fresh public formative checks and separate public key")


def svg_text_positions(stem: str) -> dict[str, int]:
    """Return first x position of each SVG text label."""
    top = ET.parse(ROOT / "print" / f"{stem}.svg").getroot()
    ns = {"svg": "http://www.w3.org/2000/svg"}
    return {
        "".join(node.itertext()): int(node.get("x", "0"))
        for node in top.findall(".//svg:text", ns)
    }


def assets() -> None:
    """Check eight A4 pairs, source geometry and full linear equivalents."""
    alternatives = read("print/TEXT-ALTERNATIVES.md")
    tree = ast.parse(read("print/generate_print.py"))
    pages = next(
        node.value
        for node in tree.body
        if isinstance(node, ast.Assign)
        and any(
            isinstance(target, ast.Name) and target.id == "PAGES"
            for target in node.targets
        )
    )
    need(
        isinstance(pages, ast.Dict)
        and {key.value for key in pages.keys if isinstance(key, ast.Constant)}
        == set(STEMS),
        "Generated aid inventory drift",
    )
    ns = {"svg": "http://www.w3.org/2000/svg"}
    linear_alt = " ".join(re.sub(r"[*_]", "", alternatives.lower()).split())
    check_pages: dict[str, str] = {}
    for stem in STEMS:
        top = ET.parse(ROOT / "print" / f"{stem}.svg").getroot()
        pdf = ROOT / "print" / f"{stem}.pdf"
        need(
            top.get("width") == "210mm"
            and top.get("height") == "297mm"
            and top.find("svg:title", ns) is not None
            and top.find("svg:desc", ns) is not None,
            f"A4 SVG/metadata drift: {stem}",
        )
        info = subprocess.check_output(["pdfinfo", str(pdf)], text=True)
        content = subprocess.check_output(["pdftotext", str(pdf), "-"], text=True)
        linear_pdf = " ".join(content.lower().split())
        if stem.startswith("check-"):
            check_pages[stem] = linear_pdf
        need(
            re.search(r"Pages:\s+1\b", info)
            and "(A4)" in info
            and "CC BY 4.0" in content
            and len(content.split()) >= MIN_PDF_WORDS
            and f"{stem}.svg" in alternatives
            and f"{stem}.pdf" in alternatives,
            f"PDF/selectable text/full alternative drift: {stem}",
        )
        for phrase in PDF_PHRASES[stem]:
            need(
                phrase.lower() in linear_pdf and phrase.lower() in linear_alt,
                f"PDF/linear source mismatch: {stem}: {phrase}",
            )
    need(
        "no later report or installed label is shown"
        not in check_pages["check-a-sage-room"]
        and "no real use or benefit is shown"
        not in check_pages["check-b-horizon-room"],
        "Assessment source page states its own inferred answer",
    )
    drawing = svg_text_positions("pebble-room-sketch")
    check_a = svg_text_positions("check-a-sage-room")
    check_b = svg_text_positions("check-b-horizon-room")
    ns = {"svg": "http://www.w3.org/2000/svg"}
    check_a_root = ET.parse(ROOT / "print/check-a-sage-room.svg").getroot()
    check_b_root = ET.parse(ROOT / "print/check-b-horizon-room.svg").getroot()
    need(
        drawing["WIDE BENCH"] < drawing["RETURN TRAY"] < drawing["DISPLAY BOARD"]
        and check_a["LONG LOW SHELF · LEFT"] < check_a["ROUND MAT · RIGHT"]
        and check_b["WIDE DESK · LEFT"] < check_b["TWO POCKETS · RIGHT"]
        and len(check_a_root.findall(".//svg:circle", ns)) == 1
        and len(
            [
                node
                for node in check_b_root.findall(".//svg:path", ns)
                if "M430 303" in node.get("d", "") or "M569 303" in node.get("d", "")
            ]
        )
        == 2,
        "Fictional source geometry drift",
    )
    need(
        "untagged" in alternatives
        and "tactile" in alternatives.lower()
        and "the class did not visit" in alternatives.lower(),
        "Accessible alternative or fiction boundary absent",
    )
    print("PASS eight A4 SVG/PDF pairs, geometry, selectable text and alternatives")


def slug(title: str) -> str:
    """Reproduce local Markdown heading anchors."""
    title = re.sub(r"\[[^]]+\]\([^)]+\)", "", title)
    title = re.sub(r"[*_]", "", title).strip().lower()
    title = re.sub(r"[^\w -]", "", title)
    return title.replace(" ", "-")


def links(*, allow_manifest_bootstrap: bool) -> int:
    """Check local Markdown paths and heading targets."""
    count = 0
    for path in ROOT.rglob("*.md"):
        body = path.read_text(encoding="utf-8")
        for url in re.findall(r"(?<!!)\[[^]]+\]\(([^)]+)\)", body):
            if url.startswith(("https://", "http://", "mailto:")):
                continue
            name, marker, anchor = unquote(url).partition("#")
            target = (path.parent / name).resolve() if name else path
            if allow_manifest_bootstrap and target == ROOT / "manifest.json":
                count += 1
                continue
            need(target.is_file(), f"Broken link: {path.relative_to(ROOT)} -> {url}")
            if marker and target.suffix.lower() == ".md":
                headings = [
                    slug(value)
                    for value in re.findall(
                        r"^#{1,6} (.+)$",
                        target.read_text(encoding="utf-8"),
                        re.MULTILINE,
                    )
                ]
                need(anchor in headings, f"Broken heading anchor: {url}")
            count += 1
    print(f"PASS {count} local file/heading links")
    return count


def manifest_data() -> dict:
    """Hash authored files, excluding the self-referential manifest."""
    files = sorted(
        path
        for path in ROOT.rglob("*")
        if path.is_file()
        and path.name != "manifest.json"
        and "__pycache__" not in path.parts
    )
    return {
        "schema": "subjectnest-authored-pack-manifest-v1",
        "pack": "foundation/hass/term-1/weeks-09-10",
        "created_at": "2026-09-30",
        "review_status": "author_desk_checked_pending_school_material_and_child_review",
        "curriculum_source_sha256": SOURCE_SHA,
        "curriculum_codes_partial_conditional": sorted(PARTIAL_CODES),
        "curriculum_codes_held_for_authentic_local_sources": sorted(HELD_CODES),
        "files": {
            str(path.relative_to(ROOT)): {
                "sha256": hashlib.sha256(path.read_bytes()).hexdigest(),
                "bytes": path.stat().st_size,
            }
            for path in files
        },
    }


def main() -> None:
    """Run offline checks and optionally write a deterministic SHA receipt."""
    parser = argparse.ArgumentParser()
    parser.add_argument("--write-manifest", action="store_true")
    args = parser.parse_args()
    source()
    pedagogy()
    checks()
    assets()
    links(allow_manifest_bootstrap=args.write_manifest)
    expected = manifest_data()
    manifest = ROOT / "manifest.json"
    if args.write_manifest:
        manifest.write_text(
            json.dumps(expected, ensure_ascii=False, indent=2) + "\n", encoding="utf-8"
        )
        print(f"WROTE SHA-256 manifest for {len(expected['files'])} files")
    else:
        need(
            json.loads(manifest.read_text(encoding="utf-8")) == expected,
            "SHA-256 manifest missing or stale",
        )
        print(f"PASS SHA-256 manifest for {len(expected['files'])} files")
    print("PACK PASS · author desk QA only; no physical or child trial")


if __name__ == "__main__":
    main()