"""Build the training manifest for one pseudo-labeling round.

base = labeled patient-level train split (w=1.0) — the same train/val usage as
Pipeline A: the val split is never trained on (it is the internal-validation
set). Accepted pseudo-label rows (pos + neg) are appended with w=<pseudo-weight>
(negative rows point at the zero mask written by stage 03), de-duplicated by
key (first occurrence wins). Every row must point at existing pimg/plabel
niftis.

Usage:
    python scripts_monai/01_monai_build_rows.py \
        --train data/manifests/split_train.jsonl \
        --accepted data/pseudo_monai/round1/accepted.jsonl \
        --pseudo-weight 0.3 --out data/pseudo_monai/round1_rows.jsonl
"""
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, save_jsonl


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--train", required=True, help="labeled train split jsonl ({key,pimg,plabel})")
    ap.add_argument("--accepted", action="append", default=None,
                    help="accepted pseudo jsonl (repeatable); pos + neg rows")
    ap.add_argument("--pseudo-weight", type=float, default=0.3)
    ap.add_argument("--no-neg", action="store_true", help="drop negative pseudo rows")
    ap.add_argument("--out", required=True)
    args = ap.parse_args()

    rows, seen = [], set()
    for r in load_jsonl(args.train):
        rows.append({"key": r["key"], "subject": r.get("subject"), "pimg": r["pimg"],
                     "plabel": r["plabel"], "w": 1.0, "role": "labeled"})
        seen.add(r["key"])
    n_pos, n_neg = 0, 0
    for f in (args.accepted or []):
        for r in load_jsonl(f):
            if not r.get("label") or r["key"] in seen:
                continue
            if r["role"] == "neg" and args.no_neg:
                continue
            seen.add(r["key"])
            rows.append({"key": r["key"], "subject": r.get("subject"), "pimg": r["pimg"],
                         "plabel": r["label"], "w": args.pseudo_weight, "role": r["role"]})
            if r["role"] == "pos":
                n_pos += 1
            else:
                n_neg += 1
    missing = [r["key"] for r in rows
               if not (os.path.exists(r["pimg"]) and os.path.exists(r["plabel"]))]
    if missing:
        raise FileNotFoundError(f"{len(missing)} rows missing pimg/plabel, e.g. {missing[:3]}")
    save_jsonl(rows, args.out)
    n_labeled = len(rows) - n_pos - n_neg
    print(f"[monai:rows] {args.out}: total={len(rows)} labeled={n_labeled} pos={n_pos} neg={n_neg}",
          flush=True)


if __name__ == "__main__":
    main()