#!/bin/bash
# ansipa_pbs — CheckMK local check for a Proxmox Backup Server.
#
# Install: copy to /usr/lib/check_mk_agent/local/ansipa_pbs and chmod 755
# (ansipa-infra-checkmk-install.sh does this for you, along with installing
# the CheckMK agent itself and registering the host).
#
# Requires only `proxmox-backup-manager` (ships with proxmox-backup-server)
# and `df` — no jq/python3 dependency. JSON is requested as "json-pretty"
# (one key per line) and scraped with a small grep/awk parser. Any command
# that fails or returns nothing degrades that one service to CheckMK state 3
# (UNKNOWN) rather than aborting the others.
#
# Emits (CheckMK local-check format: "<state> <service> <perfdata> <text>"):
#   Ansipa_PBS_Datastores    worst datastore disk utilisation (via df on path)
#   Ansipa_PBS_LastBackup    freshness + outcome of the last backup task
#   Ansipa_PBS_TaskFailures  any failed task (GC/verify/sync/prune/backup) in 24h
#
# CPU/RAM/disk-root are already covered by CheckMK's stock Linux checks —
# not duplicated here.

command -v proxmox-backup-manager >/dev/null 2>&1 \
    || { echo "3 Ansipa_PBS - proxmox-backup-manager not found (not a PBS host?)"; exit 0; }

# Extract every value of a JSON key from json-pretty text (one "key": value per line).
_jp() { grep -oP "^\s*\"$1\"\s*:\s*\"?\K[^\",]+" || true; }

# ── Datastore disk usage (df on each datastore path — version-independent) ───
DSTAT=$(proxmox-backup-manager datastore list --output-format json-pretty 2>/dev/null || true)
if [[ -z "$DSTAT" ]]; then
    echo "3 Ansipa_PBS_Datastores - could not query datastore list"
else
    mapfile -t DNAMES < <(_jp name <<< "$DSTAT")
    mapfile -t DPATHS < <(_jp path <<< "$DSTAT")
    WORST=0; WORST_NAME=""; PERF=""
    for i in "${!DNAMES[@]}"; do
        p="${DPATHS[$i]:-}"
        [[ -d "$p" ]] || continue
        pct=$(df -P "$p" 2>/dev/null | awk 'NR==2{gsub("%","",$5); print $5}')
        [[ "$pct" =~ ^[0-9]+$ ]] || continue
        PERF+=" ${DNAMES[$i]}_pct=${pct}%;85;95"
        (( pct > WORST )) && { WORST=$pct; WORST_NAME="${DNAMES[$i]}"; }
    done
    if [[ -z "$WORST_NAME" ]]; then
        echo "3 Ansipa_PBS_Datastores - no readable datastore paths found"
    elif (( WORST >= 95 )); then
        echo "2 Ansipa_PBS_Datastores${PERF} CRIT — ${WORST_NAME} at ${WORST}%"
    elif (( WORST >= 85 )); then
        echo "1 Ansipa_PBS_Datastores${PERF} WARN — ${WORST_NAME} at ${WORST}%"
    else
        echo "0 Ansipa_PBS_Datastores${PERF} worst: ${WORST_NAME} at ${WORST}%"
    fi
fi

# ── Recent task history (shared by the next two checks) ──────────────────────
TSTAT=$(proxmox-backup-manager task list --output-format json-pretty --limit 500 2>/dev/null || true)
if [[ -z "$TSTAT" ]]; then
    echo "3 Ansipa_PBS_LastBackup - could not query task list"
    echo "3 Ansipa_PBS_TaskFailures - could not query task list"
else
    mapfile -t WTYPE   < <(_jp worker_type <<< "$TSTAT")
    mapfile -t TSTATUS < <(_jp status      <<< "$TSTAT")
    mapfile -t TSTART  < <(_jp starttime   <<< "$TSTAT")

    # ── Most recent backup task ──────────────────────────────────────────────
    LAST_TS=0; LAST_STATUS=""
    for i in "${!WTYPE[@]}"; do
        [[ "${WTYPE[$i]}" == "backup" ]] || continue
        st="${TSTART[$i]:-0}"
        [[ "$st" =~ ^[0-9]+$ ]] || continue
        if (( st > LAST_TS )); then LAST_TS=$st; LAST_STATUS="${TSTATUS[$i]:-}"; fi
    done
    if [[ "$LAST_TS" -eq 0 ]]; then
        echo "1 Ansipa_PBS_LastBackup - no backup task found in recent history"
    else
        AGE_H=$(( ( $(date +%s) - LAST_TS ) / 3600 ))
        PERF="last_backup_hours=${AGE_H}"
        if [[ "$LAST_STATUS" != "OK" ]]; then
            echo "2 Ansipa_PBS_LastBackup ${PERF} Last backup task FAILED (${AGE_H}h ago): ${LAST_STATUS}"
        elif (( AGE_H >= 48 )); then
            echo "1 Ansipa_PBS_LastBackup ${PERF} Last successful backup ${AGE_H}h ago (stale)"
        else
            echo "0 Ansipa_PBS_LastBackup ${PERF} Last backup OK, ${AGE_H}h ago"
        fi
    fi

    # ── Any failed task in the last 24h (GC / verify / sync / prune / backup) ─
    NOW=$(date +%s); FAILED=0; TOTAL24=0
    for i in "${!TSTART[@]}"; do
        st="${TSTART[$i]:-0}"
        [[ "$st" =~ ^[0-9]+$ ]] || continue
        (( NOW - st <= 86400 )) || continue
        TOTAL24=$((TOTAL24+1))
        [[ "${TSTATUS[$i]:-}" == "OK" ]] || FAILED=$((FAILED+1))
    done
    PERF="failed=${FAILED};1;3 total=${TOTAL24}"
    if (( FAILED >= 3 )); then
        echo "2 Ansipa_PBS_TaskFailures ${PERF} ${FAILED}/${TOTAL24} tasks failed in the last 24h"
    elif (( FAILED >= 1 )); then
        echo "1 Ansipa_PBS_TaskFailures ${PERF} ${FAILED}/${TOTAL24} task(s) failed in the last 24h"
    else
        echo "0 Ansipa_PBS_TaskFailures ${PERF} ${TOTAL24} task(s) in last 24h, none failed"
    fi
fi