#!/usr/bin/env python3
"""Merge a Dockerfile's split `apt-get update` + `apt-get install` into one RUN.

Why: several imported challenge Dockerfiles run

    RUN apt-get -o Acquire::AllowInsecureRepositories=true update
    RUN apt-get -y --allow-unauthenticated install -y ...

as two separate layers. The bundled apt-insecure.conf enables insecure/downgrade
repositories, and a second apt invocation in a later layer re-resolves against
whatever index the first one left behind — which on the EOL bullseye-security
mirror returns 404 for every package:

    Err:1 http://deb.debian.org/debian-security bullseye-security/main amd64 libsystemd0
      404  Not Found

Merging them into a single `update && install` layer (the pattern the working
gemastik18 challenges use) makes apt resolve once, from a fresh index.

Idempotent: a Dockerfile that already has the combined form is left untouched.
"""
import re
import sys
from pathlib import Path

SERVICES = Path("/opt/gemastik18-final/services")

UPDATE_RE = re.compile(
    r"^RUN\s+apt-get\s+(?P<opts>(?:-o\s+\S+\s+)*)update\s*$"
)
INSTALL_RE = re.compile(r"^RUN\s+(?P<rest>apt-get\s+.*\binstall\b.*)$")


def fix(text: str) -> tuple[str, bool]:
    lines = text.splitlines()
    out: list[str] = []
    i = 0
    changed = False
    while i < len(lines):
        m = UPDATE_RE.match(lines[i])
        if not m:
            out.append(lines[i])
            i += 1
            continue
        # look ahead: is the very next non-empty line an install?
        j = i + 1
        while j < len(lines) and not lines[j].strip():
            j += 1
        if j < len(lines):
            mi = INSTALL_RE.match(lines[j])
            if mi:
                out.append(f"RUN apt-get {m.group('opts')}update && \\")
                out.append(f"    {mi.group('rest')}")
                changed = True
                i = j + 1
                continue
        out.append(lines[i])
        i += 1
    return "\n".join(out) + ("\n" if text.endswith("\n") else ""), changed


def main(argv):
    names = argv[1:] or [p.name for p in sorted(SERVICES.iterdir())
                         if p.is_dir() and (p / "Dockerfile").exists()]
    changed = []
    for name in names:
        p = SERVICES / name / "Dockerfile"
        if not p.exists():
            continue
        text = p.read_text()
        new, did = fix(text)
        if did:
            p.write_text(new)
            changed.append(name)
            print(f"{name}: merged apt update+install into one RUN")
    print("rewritten:", ", ".join(changed) if changed else "(none)")
    return 0


if __name__ == "__main__":
    raise SystemExit(main(sys.argv))