#!/usr/bin/env python3
import os
import sys
import shlex
from collections import defaultdict

def parse_sums(path):
    mapping = defaultdict(list)
    with open(path, "r", encoding="utf-8", errors="replace") as f:
        for line in f:
            line = line.strip()
            if not line:
                continue
            if len(line) < 66:
                continue
            h = line[:64]
            rest = line[64:].strip()
            # sha256sum style: "hash  filename" or "hash *filename"
            if rest.startswith("*") or rest.startswith(" "):
                rest = rest[1:].lstrip()
            mapping[h].append(rest)
    return mapping

def choose_keeper(paths):
    # 1) Prefer files whose basename starts with "cts" (case-insensitive)
    cts = [p for p in paths if os.path.basename(p).lower().startswith("cts")]
    if cts:
        # If multiple, pick the shortest path, then lexicographically
        cts.sort(key=lambda p: (len(p), p))
        return cts[0]

    # 2) Otherwise, prefer basenames that are already all-lowercase
    lowercase = [p for p in paths if os.path.basename(p) == os.path.basename(p).lower()]
    if lowercase:
        lowercase.sort(key=lambda p: (len(p), p))
        return lowercase[0]

    # 3) Fallback: lexicographically smallest full path
    return sorted(paths)[0]


def main():
    if len(sys.argv) > 1:
        sums_path = sys.argv[1]
    else:
        sums_path = "sha256sums.txt"

    if not os.path.exists(sums_path):
        print(f"ERROR: sums file {sums_path!r} not found", file=sys.stderr)
        sys.exit(1)

    hashes = parse_sums(sums_path)

    for h, paths in hashes.items():
        if len(paths) < 2:
            continue

        keeper = choose_keeper(paths)
        print(f"# hash {h}")
        print(f"# keeping: {keeper}")
        for p in paths:
            if p == keeper:
                continue
            # Print rm commands for duplicates (you can review before running)
            print("rm -v -- " + shlex.quote(p))
        print()

if __name__ == "__main__":
    main()