"""Phase 4AI: read-only PN/APL accounting of sealed Phase 4AG-r2 records."""
import hashlib
import importlib.util
import json
import sys
from pathlib import Path

ROOT = Path('/data/digital-drosophila')
MODEL = Path(__file__).resolve().parent
EXP = ROOT / 'experiments/phase4ai-pn-recruitment-audit'
AH_MODEL = ROOT / 'models/male-cns-lif/kc-drive-audit-v1'
AH = ROOT / 'experiments/phase4ah-kc-drive-audit'
AG_MODEL = ROOT / 'models/male-cns-lif/author-apl-lab-v2'
AG = ROOT / 'experiments/phase4ag-author-apl-r2'
META = ROOT / 'datasets/male-cns-v1.0/processed/neuron-only/neuron-index/unified-metadata.parquet'
COEFF = ROOT / 'experiments/phase4af-author-fullgraph/oracle/no_input/coefficients.json'
GROUPS = ('KC', 'APL', 'ALPN', 'MBON', 'anatomical_DAN', 'dopamine_annotation_only',
          'ALLN', 'ALIN', 'ALON', 'olfactory_sensory', 'other', 'unclassified')


def load_module(name, path):
    spec = importlib.util.spec_from_file_location(name, path)
    module = importlib.util.module_from_spec(spec)
    sys.modules[name] = module
    spec.loader.exec_module(module)
    return module


def digest(path):
    h = hashlib.sha256()
    with Path(path).open('rb') as f:
        for b in iter(lambda: f.read(8 << 20), b''):
            h.update(b)
    return h.hexdigest()


def read(path):
    return json.loads(Path(path).read_text(encoding='utf-8'))


def save(path, value):
    path = Path(path)
    path.parent.mkdir(parents=True, exist_ok=True)
    with path.open('x', encoding='utf-8') as f:
        json.dump(value, f, indent=2, ensure_ascii=False, allow_nan=False)
        f.write('\n')


def sources():
    return {p.name: digest(p) for p in sorted(MODEL.iterdir()) if p.is_file()
            and p.name not in ('manifest.json', 'checksums.sha256')}


def integrity():
    prior = load_module('sealed_ah_context_ai', AH_MODEL / 'context.py')
    result = prior.integrity()
    sys.path.insert(0, str(ROOT / 'models/male-cns-lif/terminal-scope-diagnostic-v1'))
    from diagnostic import manifest_check
    for path in (AH_MODEL, AH):
        result[str(path.relative_to(ROOT))] = manifest_check(path, digest)
    assert all(row['pass'] for row in result.values())
    return result


def check():
    record = read(EXP / 'protocol/preregistered.json')
    assert record['sources'] == sources(), 'Registered source changed'
    for row in record['inputs']:
        assert digest(ROOT / row['path']) == row['sha256'], row['path']
    for row in read(EXP / 'protocol/prepared-hashes.json'):
        assert digest(EXP / row['path']) == row['sha256'], row['path']
    return record


def seal(root):
    rows = [dict(path=str(p.relative_to(root)), bytes=p.stat().st_size, sha256=digest(p))
            for p in sorted(root.rglob('*')) if p.is_file() and '__pycache__' not in p.parts]
    save(root / 'manifest.json', dict(root=str(root), files=rows))
    with (root / 'checksums.sha256').open('x') as f:
        for row in rows:
            f.write(row['sha256'] + '  ' + row['path'] + '\n')
        f.write(digest(root / 'manifest.json') + '  manifest.json\n')


def bit_equal(a, b):
    return a.dtype == b.dtype and a.shape == b.shape and a.tobytes() == b.tobytes()