"""Plan + preprocess the nnU-Net dataset (always --clean), then write the
subject-level splits_final.json: val = split_val cases, train = the rest
(all base + pseudo cases), same 5-fold content so -f 0 is the one we use.

Usage: python scripts_nnu/02_nnu_plan_preprocess.py --val data/manifests/split_val.jsonl [--npp 8]
"""
import argparse
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from src.common import load_jsonl
from nnu_common import run, nnu_env, plan_preprocess_cmd, dataset_case_keys, write_splits, preproc_ds


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--val", required=True, help="jsonl of internal-validation cases (subject-disjoint)")
    ap.add_argument("--npp", type=int, default=8, help="preprocess processes")
    ap.add_argument("--log", default=None)
    args = ap.parse_args()
    log = args.log or os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), "logs", "nnu_plan.log")
    run(plan_preprocess_cmd(args.npp), log, env=nnu_env())
    val_keys = [r["key"] for r in load_jsonl(args.val)]
    all_keys = dataset_case_keys()
    assert all_keys, "raw dataset is empty; run 01_nnu_prepare_dataset.py first"
    assert set(val_keys) <= set(all_keys), f"val keys not in dataset: {set(val_keys) - set(all_keys)}"
    n_tr, n_va = write_splits(all_keys, val_keys)
    print(f"[nnu:plan] splits_final.json written to {preproc_ds()}: train={n_tr} val={n_va}", flush=True)


if __name__ == "__main__":
    main()