"""Build NTUH2022G4 labeled manifest: native T1c + tumor seg pairs from register_inv.

Fast listing-only pass (no volume decoding); content validated during preprocessing.
"""
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import re
import json
from src.common import ROOT, save_jsonl

T1C_RE = re.compile(r"T1.*\+C")
EXCL_RE = re.compile(r"MRA|FLAIR|TOF|T2|SWI|DWI", re.I)


def main(limit=None):
    out = os.path.join(ROOT, "data", "manifests", "ntuh.jsonl")
    reg_inv = "/mnt/pve/SRS/NTUH2022G4/register_inv"
    rows = []
    n_subj = 0
    for s in sorted(os.listdir(reg_inv)):
        fp = os.path.join(reg_inv, s)
        if not os.path.isdir(fp):
            continue
        n_subj += 1
        for c in os.listdir(fp):
            cp = os.path.join(fp, c)
            if not os.path.isdir(cp):
                continue
            fl = set(os.listdir(cp))
            for f in sorted(fl):
                if not f.endswith(".nii.gz") or f.endswith((".seg.nii.gz", ".label.nii.gz")):
                    continue
                if not T1C_RE.search(f) or EXCL_RE.search(f):
                    continue
                seg = f[: -len(".nii.gz")] + ".seg.nii.gz"
                if seg not in fl:
                    continue
                rows.append({"key": f"ntuh_{s}_{c}", "subject": s, "case": c,
                             "date": c2date(c), "img": os.path.join(cp, f),
                             "label": os.path.join(cp, seg), "source": "ntuh"})
        if limit and n_subj >= limit:
            break
    save_jsonl(rows, out)
    print(f"subjects={n_subj} rows={len(rows)}")


def c2date(c):
    m = re.match(r"case?(\d{4})\.(\d{2})\.(\d{2})\.", c)
    return f"{m.group(1)}-{m.group(2)}-{m.group(3)}" if m else c


if __name__ == "__main__":
    main()