mirror of
https://github.com/morluto/rea.git
synced 2026-10-26 17:35:11 +00:00
gensokyo-dev
b5c42dfc2a
* perf(entropy): separate physical reads from report blocks * test(entropy): type the injected positional short-read boundary * test(entropy): retain full catalog transport capacity in task probe * docs(perf): record real entropy task costs and limits * docs(perf): record latest-main entropy qualification
57 lines
2.9 KiB
Python
57 lines
2.9 KiB
Python
"""Independent Python histogram oracle; reads artifact bytes without execution."""
|
|
import argparse
|
|
from collections import Counter
|
|
import hashlib
|
|
import json
|
|
import math
|
|
from pathlib import Path
|
|
|
|
def entropy(counts, size):
|
|
if not size:
|
|
return 0
|
|
value = -sum((counts[k] / size) * math.log2(counts[k] / size) for k in sorted(counts) if counts[k])
|
|
return math.floor(value * 10000 + 0.5) / 10000
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--path', required=True)
|
|
parser.add_argument('--output', required=True)
|
|
parser.add_argument('--block-size', type=int, required=True)
|
|
parser.add_argument('--offset', type=int, default=0)
|
|
parser.add_argument('--length', type=int)
|
|
args = parser.parse_args()
|
|
path = Path(args.path)
|
|
before = path.stat()
|
|
counts = Counter()
|
|
digest = hashlib.sha256()
|
|
with path.open('rb') as source:
|
|
while chunk := source.read(1024 * 1024):
|
|
digest.update(chunk)
|
|
counts.update(chunk)
|
|
length = args.length if args.length is not None else before.st_size - args.offset
|
|
assert 0 <= args.offset <= before.st_size and 0 <= length <= before.st_size - args.offset
|
|
blocks, runs = [], []
|
|
source.seek(args.offset)
|
|
for offset in range(args.offset, args.offset + length, args.block_size):
|
|
chunk = source.read(min(args.block_size, args.offset + length - offset))
|
|
value = entropy(Counter(chunk), len(chunk))
|
|
block = {'offset': offset, 'length': len(chunk), 'entropy': value}
|
|
blocks.append(block)
|
|
classification = 'high' if value >= 7.2 else 'low' if value <= 1 else None
|
|
if classification is not None:
|
|
if runs and runs[-1]['classification'] == classification and runs[-1]['offset'] + runs[-1]['length'] == offset:
|
|
runs[-1]['length'] += len(chunk)
|
|
else:
|
|
runs.append({'offset': offset, 'length': len(chunk), 'classification': classification})
|
|
after = path.stat()
|
|
assert (before.st_dev, before.st_ino, before.st_size, before.st_mtime_ns, before.st_ctime_ns) == (after.st_dev, after.st_ino, after.st_size, after.st_mtime_ns, after.st_ctime_ns)
|
|
expected = {'artifact': {'path': args.path, 'bytes': before.st_size, 'sha256': digest.hexdigest()}, 'block_size':args.block_size,'window':{'offset':args.offset,'length':length},'file_entropy':entropy(counts,before.st_size),'thresholds':{'high':7.2,'low':1},'blocks':blocks,'runs':runs}
|
|
request = {'path':args.path,'block_size':args.block_size,'offset':args.offset}
|
|
if args.length is not None:
|
|
request['length'] = args.length
|
|
Path(args.output).write_text(json.dumps({'input':request,'expected':expected},indent=2)+'\n')
|
|
print(json.dumps({'path':args.path,'sha256':digest.hexdigest(),'blocks':len(blocks),'runs':len(runs)}))
|
|
|
|
if __name__ == '__main__':
|
|
main()
|