#!/usr/bin/env bash
# CTAO portal demo — poll the content repo, rebuild, publish atomically.
# Triggered every 10 s by ctao-portal-build.timer; systemd oneshot semantics
# guarantee runs never overlap. The 99.9% case is one local curl and exit 0.
# No secrets anywhere: the portal repo is public-read on the local Gitea.
set -euo pipefail

# Defaults match the machine; every var is env-overridable so the whole
# pipeline can be tested locally against a sandbox dir + local Gitea.
BASE="${BASE:-$HOME/ctao-portal-demo}"
GITEA_URL="${GITEA_URL:-http://localhost:3000}"   # published by ctao-demo-gitea
REPO="${REPO:-ctao/portal}"                       # owner/repo in Gitea
BRANCH="${BRANCH:-main}"
BUILD_IMAGE="${BUILD_IMAGE:-localhost/ctao-portal-build:1}"
# The build joins the Gitea container's network namespace: localhost inside
# the build = Gitea's loopback (port 3000), host loopback stays unreachable.
# (A netavark bridge would be equivalent, but rootless bridges need the
# ip_tables kernel module, absent on the machine — pasta needs nothing.)
BUILD_NETNS="${BUILD_NETNS:-container:ctao-demo-gitea}"
REPO_INTERNAL="${REPO_INTERNAL:-http://localhost:3000/$REPO.git}"
KEEP="${KEEP:-3}"                                 # released builds to retain
mkdir -p "$BASE/repo" "$BASE/releases" "$BASE/state" "$BASE/npm-cache"

# Host prerequisites (everything else runs inside containers). Fail loud —
# a missing tool is permanent, unlike a Gitea hiccup below.
for tool in curl jq podman; do
  command -v "$tool" >/dev/null || { echo "missing host tool: $tool"; exit 1; }
done

# --- 1. Cheap poll: branch head via the local Gitea API (host curl + jq) ---
sha=$(curl -fsS --max-time 5 "$GITEA_URL/api/v1/repos/$REPO/branches/$BRANCH" \
      | jq -r '.commit.id' || true)
# Gitea down/unreachable is a transient, not a unit failure — exit 0 quietly
# instead of painting the journal red every 10 s.
if [[ ! "$sha" =~ ^[0-9a-f]{40}$ ]]; then
  echo "poll failed (gitea unreachable?) — skipping this tick"
  exit 0
fi
# Skip only if this sha is both recorded AND still present in releases/
# (a deleted release dir must trigger a rebuild, not an eternal skip).
[[ "$sha" == "$(cat "$BASE/state/last-built" 2>/dev/null)" \
   && -d "$BASE/releases/$sha" ]] && exit 0

echo "building $sha"
t0=$(date +%s)

# --- 2. Build in the ephemeral container (git + pinned node live there).
# SECURITY: the container runs npm lifecycle scripts from the repo, so it is
# confined to Gitea's netns — it reaches Gitea on localhost:3000 and the
# internet (for `npm ci` when the lockfile changed), but NOT the host's
# loopback services (code-server). Never use --network=host here.
# node_modules and .deps-hash are untracked, so they survive checkouts.
podman run --rm --network="$BUILD_NETNS" --memory=1g \
  -e ASTRO_TELEMETRY_DISABLED=1 \
  -e SHA="$sha" -e REPO_URL="$REPO_INTERNAL" -e BRANCH="$BRANCH" \
  -v "$BASE/repo:/work/repo:z" \
  -v "$BASE/releases:/work/releases:z" \
  -v "$BASE/npm-cache:/root/.npm:z" \
  -w /work "$BUILD_IMAGE" sh -ec '
    git config --global safe.directory /work/repo
    [ -d repo/.git ] || git clone --branch "$BRANCH" "$REPO_URL" repo
    git -C repo remote set-url origin "$REPO_URL"   # self-heal if the URL changes
    git -C repo fetch --quiet origin "$BRANCH"
    # --force: the working copy is disposable; a stray tracked-file edit must
    # not wedge every future build.
    git -C repo checkout --quiet --force "$SHA"
    cd repo
    lock=$(sha256sum package-lock.json | cut -d" " -f1)
    if [ ! -d node_modules ] || [ "$lock" != "$(cat .deps-hash 2>/dev/null)" ]; then
      # --ignore-scripts: (1) removes the install-time postinstall vector from
      # npm deps (build-time repo code still runs `npm run build` below — the
      # netns confinement is the control for that), (2) avoids the esbuild
      # ETXTBSY postinstall race in rootless containers. esbuild ships its
      # binary as an optional dep, so nothing here needs lifecycle scripts.
      npm ci --ignore-scripts --no-audit --no-fund
      echo "$lock" > .deps-hash
    fi
    npm run build
    rm -rf "../releases/$SHA"
    cp -a dist "../releases/$SHA"
  '

# --- 3. Atomic publish: symlink flip via rename(2) — no half-published moment.
# mv -T is GNU (the target host is Rocky); when testing on macOS put a
# coreutils `mv` (gmv) first in PATH.
rm -f "$BASE/releases/".current.*   # stale temps from a crash mid-flip
ln -s "$sha" "$BASE/releases/.current.$$"
mv -Tf "$BASE/releases/.current.$$" "$BASE/releases/current"
echo "$sha" > "$BASE/state/last-built"

# --- 4. Prune old releases. `current`'s target is excluded explicitly —
# mtime ordering makes it newest today, but nothing should depend on that.
# `|| true`: an empty match must not fail the unit after a successful publish
# (grep exits 1 under pipefail when there is nothing to prune).
cd "$BASE/releases"
cur=$(readlink current || true)
ls -1t | grep -vx current | grep -vx -- "$cur" | tail -n +"$((KEEP + 1))" | while read -r old; do
  rm -rf -- "$old"
done || true

echo "published $sha in $(( $(date +%s) - t0 ))s"