"""Dedup-by-tid aggregate. Handles both live eval*.log and finished eval*.log.gz."""
import re
import gzip
import glob
import os

EVALS = "/imotion-vepfs/imotion_zxnet/workspace_wei/ry-dynamics-vln-ryworld/checkpoints/ryworld_stage1_discrete_20260510_025317_cw07_iw25/evals"
pat = re.compile(
    r'"shortest_path_length":\s*([\d.]+).*?"NE":\s*([\d.]+).*?"success":\s*([\d.]+).*?'
    r'"osr":\s*([\d.]+).*?"TL":\s*([\d.]+).*?"spl":\s*([\d.]+).*?"ndtw":\s*([\d.]+).*?'
    r'"trajectory_id":\s*"([^"]+)"',
    re.S,
)

all_eps = {}
log_paths = glob.glob(f"{EVALS}/*full835*/eval*.log") + glob.glob(f"{EVALS}/*full835*/eval*.log.gz")
for p in sorted(log_paths):
    if p.endswith(".gz"):
        content = gzip.open(p, "rt").read()
    else:
        content = open(p).read()
    for m in pat.finditer(content):
        spg, ne, succ, osr, tl, spl, ndtw, tid = m.groups()
        all_eps[tid] = {
            "spg": float(spg), "NE": float(ne),
            "success": int(float(succ) == 1.0),
            "osr": int(float(osr) == 1.0),
            "SPL": float(spl), "nDTW": float(ndtw),
        }

n = len(all_eps)
if n == 0:
    print("no eps found")
    raise SystemExit
eps = list(all_eps.values())
def avg(field):
    return sum(e[field] for e in eps) / n

print(f"=== TOTAL {n}/835 ({100*n/835:.1f}%) ===")
print(f"  SR={100*avg('success'):.1f}%  OSR={100*avg('osr'):.1f}%  NE={avg('NE'):.2f}  SPL={100*avg('SPL'):.1f}%  nDTW={avg('nDTW'):.3f}")
for lo, hi in [(0, 5), (5, 8), (8, 12), (12, 18)]:
    bk = [e for e in eps if lo <= e["spg"] < hi]
    if bk:
        b_sr = sum(e["success"] for e in bk) / len(bk)
        print(f"  short [{lo:>2},{hi:>2})m: n={len(bk):>3}  SR={100*b_sr:>4.1f}%")