import csv
import hashlib
from pathlib import Path
import numpy as np
from PIL import Image

def sha(path):
    return hashlib.sha256(Path(path).read_bytes()).hexdigest()

def read_manifest(path):
    path=Path(path)
    with path.open(newline='') as stream:
        rows=list(csv.DictReader(stream))
    if not rows or not {'id','image','mask','split','group'} <= set(rows[0]):
        raise ValueError('Manifest requires id,image,mask,split,group')
    ids=set(); groups={}; hashes={}
    for r in rows:
        if r['id'] in ids or not r['id'] or '/' in r['id'] or '\\' in r['id'] or r['id'] in ('.','..'):
            raise ValueError('Duplicate/unsafe id')
        ids.add(r['id'])
        if r['split'] not in ('train','dev','cal','test') or not r['group']:
            raise ValueError('Invalid split/group')
        if r['group'] in groups and groups[r['group']]!=r['split']:
            raise ValueError('Scene group crosses splits')
        groups[r['group']]=r['split']
        for k in ('image','mask'):
            r[k]=str((path.parent/r[k]).resolve())
            if not Path(r[k]).is_file(): raise FileNotFoundError(r[k])
        h=sha(r['image'])
        if h in hashes and hashes[h]!=r['split']:
            raise ValueError('Identical image bytes cross splits')
        hashes[h]=r['split']
    return rows

def read_pair(row):
    with Image.open(row['image']) as img:
        image=np.asarray(img).copy()
    with Image.open(row['mask']) as img:
        mask=np.asarray(img).copy()
    if image.ndim!=2 or image.dtype!=np.uint8:
        raise ValueError('Prototype requires native-resolution 8-bit grayscale; no implicit conversion')
    if mask.ndim!=2 or mask.shape!=image.shape:
        raise ValueError('Mask shape/format mismatch')
    return image.astype(np.float32)/255., mask>0