#!/usr/bin/env bash
# Cluster lifecycle, plus what else is running on this machine.
#
# `list` and `free` live here rather than in a separate script because a
# near-identical second name (cluster / clusters) is a trap — you reach for one
# and get the other. One target, one file, unambiguous subcommands.
#
# "Idempotent" here means CONVERGENT, not "exits early if the cluster exists".
# That distinction matters: an interrupted first run can leave a cluster created
# but not finished, and returning early on the re-run would strand it there.
# The create step is conditional; every step after it always runs, and each one
# is individually idempotent.
#
# Usage: cluster.sh up | down | reset | list | free
set -euo pipefail
cd "$(dirname "$0")"

source ./lib/config.sh
load_config

up() {
    if kind get clusters 2>/dev/null | grep -qx "$CLUSTER"; then
        echo "cluster '$CLUSTER' exists — converging"
    else
        # Say what this profile locks in BEFORE spending minutes building it:
        # the kind config is fixed at creation and cannot be changed later.
        echo "creating cluster '$CLUSTER' from profile '$PROFILE_NAME'"
        echo "  kind config ${KIND_CONFIG}"
        echo "  nodes       $NODES"
        echo "  image       $NODE_IMAGE"
        echo "  ingress     $INGRESS_MODE"
        echo "  registry    $REGISTRY_MODE"
        echo "  (fixed at creation — edit the kind config, then 'make cluster reset')"
        echo

        render_kind_config | kind create cluster --config -
    fi

    # The cluster can exist while its context does not — a reset or a switched
    # KUBECONFIG loses it, and then nothing works despite a healthy cluster.
    if ! kubectl config get-contexts -o name 2>/dev/null | grep -qx "$KUBECONTEXT"; then
        echo "context '$KUBECONTEXT' missing from kubeconfig — re-exporting"
        kind export kubeconfig --name "$CLUSTER"
    fi
    kubectl config use-context "$KUBECONTEXT" >/dev/null

    bash registry.sh up

    if [ -n "${ADDONS// /}" ]; then
        bash addons.sh install
    fi

    echo
    echo "cluster '$CLUSTER' ready (context $KUBECONTEXT)"
}

down() {
    # The registry is a standalone container outside the cluster; take it down
    # first so a reset doesn't leave it orphaned and holding a port.
    bash registry.sh down || true

    if kind get clusters 2>/dev/null | grep -qx "$CLUSTER"; then
        echo "deleting cluster '$CLUSTER'..."
        kind delete cluster --name "$CLUSTER"
    else
        echo "no cluster '$CLUSTER' to delete"
    fi
}

# The escape hatch for a wedged cluster, and the only way to change a
# creation-time setting such as the node count or port mappings.
reset() {
    down
    echo
    up
}

# ── the whole machine ──────────────────────────────────────────────────────
# Every cluster is a running container tree whether or not you are using it, and
# an idle one is the usual reason a new one will not fit.

list() {
    local total avail
    total=$(awk '/^MemTotal:/{printf "%.1f", $2/1024/1024}' /proc/meminfo)
    avail=$(awk '/^MemAvailable:/{printf "%.1f", $2/1024/1024}' /proc/meminfo)
    echo "memory: ${avail} GB available of ${total} GB"
    echo

    local names; names=$(kind get clusters 2>/dev/null || true)
    if [ -z "$names" ]; then
        echo "no clusters"
        return
    fi

    printf "%-16s %-10s %8s %6s  %-13s %s\n" CLUSTER STATE MEM NODES PORTS ""
    local c nodes state mem base
    for c in $names; do
        nodes=$(docker ps -a --filter "label=io.x-k8s.kind.cluster=$c" --format '{{.Names}}' | wc -l)
        state=$(docker inspect -f '{{.State.Status}}' "${c}-control-plane" 2>/dev/null || echo unknown)
        if [ "$state" = "running" ]; then
            mem=$(docker stats --no-stream --format '{{.MemUsage}}' \
                  $(docker ps --filter "label=io.x-k8s.kind.cluster=$c" -q) 2>/dev/null \
                  | awk '{gsub(/GiB/,"");gsub(/MiB/,"e-3");s+=$1} END {printf "%.1fG", s}')
        else
            mem="-"
        fi
        # A cluster's name is its directory slug, so its port block is derivable
        # here without reading that directory's config.
        base=$(derive_port_base "$c")
        printf "%-16s %-10s %8s %6s  %-13s %s\n" "$c" "$state" "$mem" "$nodes" \
            "${base}-$((base + 3))" \
            "$([ "$c" = "$CLUSTER" ] && echo "<- this one")"
    done
}

# Stop the OTHER clusters to free memory. Stops, never deletes — a stopped
# cluster restarts with `docker start`, so nothing is lost.
free() {
    local targets=("$@")
    if [ ${#targets[@]} -eq 0 ]; then
        mapfile -t targets < <(kind get clusters 2>/dev/null | grep -vx "$CLUSTER" || true)
    fi
    if [ ${#targets[@]} -eq 0 ]; then
        echo "nothing to stop"
        return
    fi

    local c ids
    for c in "${targets[@]}"; do
        ids=$(docker ps --filter "label=io.x-k8s.kind.cluster=$c" -q)
        if [ -z "$ids" ]; then
            echo "cluster '$c' is not running"
            continue
        fi
        echo "stopping '$c' (restart with: docker start \$(docker ps -aq -f label=io.x-k8s.kind.cluster=$c))"
        # shellcheck disable=SC2086
        docker stop $ids >/dev/null
    done
}

case "${1:-up}" in
    up)    up ;;
    down)  down ;;
    reset) reset ;;
    list)  list ;;
    free)  shift; free "$@" ;;
    *)     echo "usage: $0 [up|down|reset|list|free]" >&2; exit 1 ;;
esac