Digital Drosophila Archive
50 lines
2.0 KiB
Python
50 lines
2.0 KiB
Python
import hashlib
|
|
import importlib.util
|
|
import json
|
|
from pathlib import Path
|
|
|
|
ROOT=Path('/data/digital-drosophila')
|
|
MODEL=Path(__file__).resolve().parent
|
|
EXP=ROOT/'experiments/phase4ag-author-apl'
|
|
AF_MODEL=ROOT/'models/male-cns-lif/author-fullgraph-lab-v1'
|
|
AF_EXP=ROOT/'experiments/phase4af-author-fullgraph'
|
|
AD_EXP=ROOT/'experiments/phase4ad-author-semantics'
|
|
CFG=json.loads((MODEL/'config.json').read_text(encoding='utf-8'))
|
|
|
|
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 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():
|
|
spec=importlib.util.spec_from_file_location('frozen_af_context',AF_MODEL/'context.py')
|
|
mod=importlib.util.module_from_spec(spec);spec.loader.exec_module(mod)
|
|
result=mod.integrity()
|
|
import sys
|
|
sys.path.insert(0,str(ROOT/'models/male-cns-lif/terminal-scope-diagnostic-v1'))
|
|
from diagnostic import manifest_check
|
|
for p in (AF_MODEL,AF_EXP):result[str(p.relative_to(ROOT))]=manifest_check(p,digest)
|
|
assert all(r['pass'] for r in result.values())
|
|
return result
|
|
|
|
def check():
|
|
p=json.loads((EXP/'protocol/preregistered.json').read_text())
|
|
assert p['sources']==sources(),'Source changed after preregistration'
|
|
for row in p['inputs']:assert digest(ROOT/row['path'])==row['sha256'],row['path']
|
|
for row in json.loads((EXP/'protocol/prepared-hashes.json').read_text()):
|
|
assert digest(EXP/row['path'])==row['sha256'],row['path']
|
|
return p
|
|
|
|
def budget():
|
|
size=sum(p.stat().st_size for p in EXP.rglob('*') if p.is_file())
|
|
assert size<CFG['output_budget_bytes'],'New output resource budget exceeded'
|
|
return size
|