wyj
11e703e33d
Archive fixed catalog subsets and captured events, manifests, reproducible commands, raw timing and regression logs, and device resource evidence. Document distribution-dependent tile reduction gains and independent indexed producer throughput. Update the GPU plan and renderer design while retaining the production atomic path. Preserve historical measurement metadata and exclude generated Python bytecode.
19 lines
1.0 KiB
Python
19 lines
1.0 KiB
Python
#!/usr/bin/env python3
|
|
"""Recreate the fixed, bounded source subsets (never the full catalog)."""
|
|
from pathlib import Path
|
|
import hashlib,json
|
|
root=Path(__file__).resolve().parent
|
|
repo=root.parents[1]
|
|
manifest={}
|
|
for region,name in [('ordinary','tile_ra252_dec048.csv'),('center','tile_ra262_dec060.csv')]:
|
|
source=repo/'assets/2mass/processed/all_sky'/name
|
|
raw=source.read_bytes();lines=raw.decode().splitlines();n=min(8192,len(lines)-1)
|
|
sample=('\n'.join([lines[0]]+[lines[1+i*(len(lines)-1)//n] for i in range(n)])+'\n').encode()
|
|
target=root/(region+'.csv')
|
|
if target.exists() and target.read_bytes()!=sample:raise RuntimeError('existing subset differs')
|
|
target.write_bytes(sample)
|
|
manifest[region]={'source':str(source.relative_to(repo)),'source_sha256':hashlib.sha256(raw).hexdigest(),
|
|
'source_stars':len(lines)-1,'sample_sha256':hashlib.sha256(sample).hexdigest(),'sample_stars':n,
|
|
'selection':'row 1+floor(i*N/n), i=0..n-1, n=min(8192,N)'}
|
|
(root/'input_manifest.json').write_text(json.dumps(manifest,indent=2)+'\n')
|