#!/usr/bin/env bash
# SUM Parts - list an archive's contents without extracting it
#
# Used to count tiles per split, which is what turns a per-iteration benchmark
# into a wall-clock training estimate.
set -euo pipefail

ARCHIVE="${1:-$HOME/sum-parts/data/_archives/mesh.zip}"

source "$HOME/miniconda3/etc/profile.d/conda.sh"
conda activate sumparts

python - "$ARCHIVE" <<'PY'
import re
import sys
import zipfile
from collections import Counter
from pathlib import Path

path = Path(sys.argv[1])
z = zipfile.ZipFile(path)
names = z.namelist()

print(f"=== {path.name} : {len(names)} entries ===\n")

dirs = Counter()
for n in names:
    p = "/".join(n.split("/")[:-1]) or "."
    dirs[p] += 1
for d, c in sorted(dirs.items()):
    print(f"  {c:>5}  {d}/")

print()
splits = Counter()
for n in names:
    m = re.search(r"(?:^|/)(train|val|test|training|validation)(?:/|_)", n, re.I)
    if m:
        splits[m.group(1).lower()] += 1
if splits:
    print("split hints:", dict(splits))

ply = [n for n in names if n.lower().endswith(".ply")]
print(f"\n.ply entries: {len(ply)}")

per_split = Counter(n.split("/")[0] for n in ply)
for s, c in sorted(per_split.items()):
    print(f"   {c:>4} ply  in {s}/")

for n in ply[:5]:
    print(f"   e.g. {n}")

total = sum(i.file_size for i in z.infolist())
print(f"\nuncompressed total: {total / 1e9:.2f} GB")
PY