#!/usr/bin/env bash

# This repository is public, and server/ describes real infrastructure. The
# rule that makes that safe has three parts, and each is pinned here because
# each fails silently:
#
#   1. No tracked file under server/ carries a secret. Compose files reference
#      secrets as ${VAR} interpolations resolved from the .env beside them on
#      the machine; .env.example names the variables with CHANGE_ME in place
#      of every value that matters.
#   2. .gitignore keeps .env and data/ out of server/containers/ even when a
#      cutover or a mistake puts one there. The live files belong in
#      ~/Server/<Name>/, outside the checkout entirely -- the ignore is a
#      seatbelt, and a seatbelt that got deleted should fail loudly.
#   3. Nothing named .env is tracked, full stop.

set -uo pipefail

repo_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
server_dir="$repo_dir/server"

findings=()
note() { findings+=("$1"); }

[[ -d "$server_dir" ]] || { printf 'compose secrets contract: no server/ directory\n' >&2; exit 1; }

# ── 1. Tracked content is clean ──────────────────────────────────────────────
#
# Only tracked files: the live .env a cutover briefly leaves in a service
# directory is exactly what the gitignore exists for, and flagging it here
# would punish the ignore for working.

while IFS= read -r file; do
    path="$repo_dir/$file"
    [[ -f "$path" ]] || continue

    # A secret-bearing key with a literal value. ${VAR} interpolations, empty
    # values, the CHANGE_ME placeholder, and booleans (ALLOW_EMPTY_PASSWORD=yes
    # is a switch, not a credential) are the allowed shapes; anything else
    # after PASSWORD/SECRET/TOKEN/KEY is treated as a leak. Keys that merely
    # configure where a secret lives (a *_FILE path, a key NAME) are not
    # values.
    while IFS= read -r hit; do
        note "$file looks like it carries a secret: ${hit%%[=:]*}"
    done < <(grep -inE '(password|secret|token|api_key|private_key|access_key)[a-z0-9_]*[[:space:]]*[:=]' "$path" 2>/dev/null \
        | grep -vE '[:=][[:space:]]*["'"'"']?(\$\{|CHANGE_ME|(true|false|yes|no|[01])["'"'"']?[[:space:]]*$|["'"'"']?[[:space:]]*$)' \
        | grep -viE '(_file|_path|_name|_key_name)[[:space:]]*[:=]' \
        | grep -vE '^[0-9]+:[[:space:]]*#')

    if grep -qE 'BEGIN [A-Z ]*PRIVATE KEY' "$path" 2>/dev/null; then
        note "$file contains a private key"
    fi
    if grep -qE 'sk-ant-[A-Za-z0-9]|ghp_[A-Za-z0-9]{20}|xox[baprs]-[A-Za-z0-9]' "$path" 2>/dev/null; then
        note "$file contains something that looks like an API token"
    fi
done < <(git -C "$repo_dir" ls-files 'server/')

# ── 2. The ignore still stands ───────────────────────────────────────────────
#
# check-ignore consults the real gitignore for a path that need not exist, so
# this asserts the rule rather than the current absence of violations.

git -C "$repo_dir" check-ignore -q 'server/containers/AnyService/.env' \
    || note '.gitignore no longer covers .env under server/containers/'
git -C "$repo_dir" check-ignore -q 'server/containers/AnyService/data/dump.sql' \
    || note '.gitignore no longer covers data/ under server/containers/'

# ── 3. No .env is tracked ────────────────────────────────────────────────────

while IFS= read -r tracked; do
    note "a live .env is tracked: $tracked"
done < <(git -C "$repo_dir" ls-files 'server/**/.env' 'server/.env')

# ── Report ───────────────────────────────────────────────────────────────────

if (( ${#findings[@]} > 0 )); then
    mapfile -t findings < <(printf '%s\n' "${findings[@]}" | sort -u)
    printf 'compose secrets contract: %d finding(s)\n' "${#findings[@]}" >&2
    printf '  - %s\n' "${findings[@]}" >&2
    exit 1
fi

printf 'compose secrets contract: PASS\n'