#!/bin/bash
# Health check dashboard script for Arrs Media Stack
# Generated by Ansible

LOG_DIR="{{ docker_root }}/logs/system"
TIMESTAMP=$(date '+%Y-%m-%d %H:%M:%S')
DASHBOARD_LOG="$LOG_DIR/health-dashboard-$(date '+%Y%m%d').log"

# Ensure log directory exists
mkdir -p "$LOG_DIR"

# Function to log with timestamp
log_health() {
    echo "[$TIMESTAMP] $1" >> "$DASHBOARD_LOG"
}

# Colors for terminal output
RED='\033[0;31m'
GREEN='\033[0;32m'
YELLOW='\033[1;33m'
BLUE='\033[0;34m'
NC='\033[0m' # No Color

# Function to display colored output
display_status() {
    local service="$1"
    local status="$2"
    local details="$3"
    
    case "$status" in
        "OK"|"RUNNING")
            echo -e "${GREEN}✓${NC} $service: ${GREEN}$status${NC} $details"
            ;;
        "WARNING"|"DEGRADED")
            echo -e "${YELLOW}⚠${NC} $service: ${YELLOW}$status${NC} $details"
            ;;
        "CRITICAL"|"FAILED"|"DOWN")
            echo -e "${RED}✗${NC} $service: ${RED}$status${NC} $details"
            ;;
        *)
            echo -e "${BLUE}ℹ${NC} $service: ${BLUE}$status${NC} $details"
            ;;
    esac
}

log_health "=== HEALTH DASHBOARD STARTED ==="

echo "=================================================================="
echo "           ARRS MEDIA STACK HEALTH DASHBOARD"
echo "=================================================================="
echo "Generated: $TIMESTAMP"
echo "=================================================================="

# System Health
echo -e "\n${BLUE}SYSTEM HEALTH${NC}"
echo "------------------------------------------------------------------"

# CPU Usage
CPU_USAGE=$(top -bn1 | grep "Cpu(s)" | awk '{print $2}' | cut -d'%' -f1)
if (( $(echo "$CPU_USAGE > 80" | bc -l) )); then
    display_status "CPU Usage" "CRITICAL" "(${CPU_USAGE}%)"
    log_health "SYSTEM_HEALTH CPU_USAGE CRITICAL ${CPU_USAGE}%"
elif (( $(echo "$CPU_USAGE > 60" | bc -l) )); then
    display_status "CPU Usage" "WARNING" "(${CPU_USAGE}%)"
    log_health "SYSTEM_HEALTH CPU_USAGE WARNING ${CPU_USAGE}%"
else
    display_status "CPU Usage" "OK" "(${CPU_USAGE}%)"
    log_health "SYSTEM_HEALTH CPU_USAGE OK ${CPU_USAGE}%"
fi

# Memory Usage
MEMORY_PERCENT=$(free | grep Mem | awk '{printf "%.1f", $3/$2 * 100.0}')
if (( $(echo "$MEMORY_PERCENT > 90" | bc -l) )); then
    display_status "Memory Usage" "CRITICAL" "(${MEMORY_PERCENT}%)"
    log_health "SYSTEM_HEALTH MEMORY_USAGE CRITICAL ${MEMORY_PERCENT}%"
elif (( $(echo "$MEMORY_PERCENT > 75" | bc -l) )); then
    display_status "Memory Usage" "WARNING" "(${MEMORY_PERCENT}%)"
    log_health "SYSTEM_HEALTH MEMORY_USAGE WARNING ${MEMORY_PERCENT}%"
else
    display_status "Memory Usage" "OK" "(${MEMORY_PERCENT}%)"
    log_health "SYSTEM_HEALTH MEMORY_USAGE OK ${MEMORY_PERCENT}%"
fi

# Disk Usage
DISK_USAGE=$(df -h {{ docker_root }} | tail -1 | awk '{print $5}' | cut -d'%' -f1)
if [[ $DISK_USAGE -gt 90 ]]; then
    display_status "Disk Usage" "CRITICAL" "(${DISK_USAGE}%)"
    log_health "SYSTEM_HEALTH DISK_USAGE CRITICAL ${DISK_USAGE}%"
elif [[ $DISK_USAGE -gt 80 ]]; then
    display_status "Disk Usage" "WARNING" "(${DISK_USAGE}%)"
    log_health "SYSTEM_HEALTH DISK_USAGE WARNING ${DISK_USAGE}%"
else
    display_status "Disk Usage" "OK" "(${DISK_USAGE}%)"
    log_health "SYSTEM_HEALTH DISK_USAGE OK ${DISK_USAGE}%"
fi

# Load Average
LOAD_1MIN=$(uptime | awk -F'load average:' '{print $2}' | awk '{print $1}' | cut -d',' -f1 | xargs)
if (( $(echo "$LOAD_1MIN > 2.0" | bc -l) )); then
    display_status "Load Average" "WARNING" "(${LOAD_1MIN})"
    log_health "SYSTEM_HEALTH LOAD_AVERAGE WARNING ${LOAD_1MIN}"
else
    display_status "Load Average" "OK" "(${LOAD_1MIN})"
    log_health "SYSTEM_HEALTH LOAD_AVERAGE OK ${LOAD_1MIN}"
fi

# Docker Services
echo -e "\n${BLUE}DOCKER SERVICES${NC}"
echo "------------------------------------------------------------------"

if command -v docker >/dev/null 2>&1; then
    cd {{ docker_compose_dir }}
    
    SERVICES=("sonarr" "radarr" "lidarr" "bazarr" "prowlarr" "whisparr" "deluge" "sabnzbd" "plex" "tautulli" "jellyseerr" "tubearchivist" "gluetun" "watchtower" "logrotate")
    
    for service in "${SERVICES[@]}"; do
        CONTAINER_ID=$(docker-compose ps -q "$service" 2>/dev/null)
        if [[ -n "$CONTAINER_ID" ]]; then
            CONTAINER_STATUS=$(docker inspect "$CONTAINER_ID" --format='{{ "{{.State.Status}}" }}' 2>/dev/null)
            CONTAINER_HEALTH=$(docker inspect "$CONTAINER_ID" --format='{{ "{{.State.Health.Status}}" }}' 2>/dev/null)
            
            if [[ "$CONTAINER_STATUS" == "running" ]]; then
                if [[ "$CONTAINER_HEALTH" == "healthy" ]] || [[ -z "$CONTAINER_HEALTH" ]] || [[ "$CONTAINER_HEALTH" == "<no value>" ]]; then
                    display_status "$service" "RUNNING" ""
                    log_health "DOCKER_SERVICE $service RUNNING"
                else
                    display_status "$service" "DEGRADED" "(health: $CONTAINER_HEALTH)"
                    log_health "DOCKER_SERVICE $service DEGRADED $CONTAINER_HEALTH"
                fi
            else
                display_status "$service" "DOWN" "(status: $CONTAINER_STATUS)"
                log_health "DOCKER_SERVICE $service DOWN $CONTAINER_STATUS"
            fi
        else
            display_status "$service" "NOT_FOUND" ""
            log_health "DOCKER_SERVICE $service NOT_FOUND"
        fi
    done
else
    display_status "Docker" "NOT_INSTALLED" ""
    log_health "DOCKER_SERVICE docker NOT_INSTALLED"
fi

# Network Connectivity
echo -e "\n${BLUE}NETWORK CONNECTIVITY${NC}"
echo "------------------------------------------------------------------"

# Internet connectivity
if ping -c 1 8.8.8.8 >/dev/null 2>&1; then
    display_status "Internet" "OK" ""
    log_health "NETWORK_CONNECTIVITY internet OK"
else
    display_status "Internet" "FAILED" ""
    log_health "NETWORK_CONNECTIVITY internet FAILED"
fi

# DNS resolution
if nslookup google.com >/dev/null 2>&1; then
    display_status "DNS Resolution" "OK" ""
    log_health "NETWORK_CONNECTIVITY dns OK"
else
    display_status "DNS Resolution" "FAILED" ""
    log_health "NETWORK_CONNECTIVITY dns FAILED"
fi

# Service ports - Check on Tailscale network interface
TAILSCALE_IP="{{ tailscale_bind_ip }}"
SERVICES_PORTS=(
    "sonarr:{{ ports.sonarr }}"
    "radarr:{{ ports.radarr }}"
    "lidarr:{{ ports.lidarr }}"
    "bazarr:{{ ports.bazarr }}"
    "prowlarr:{{ ports.prowlarr }}"
    "deluge:{{ ports.deluge }}"
    "sabnzbd:{{ ports.sabnzbd }}"
    "plex:{{ ports.plex }}"
    "tautulli:{{ ports.tautulli }}"
    "jellyseerr:{{ ports.jellyseerr }}"
    "tubearchivist:{{ ports.tubearchivist }}"
    "whisparr:{{ ports.whisparr }}"
)

for service_port in "${SERVICES_PORTS[@]}"; do
    SERVICE=$(echo "$service_port" | cut -d: -f1)
    PORT=$(echo "$service_port" | cut -d: -f2)
    
    # Check on Tailscale IP first, fallback to localhost for services that might bind to both
    if nc -z "$TAILSCALE_IP" "$PORT" 2>/dev/null; then
        display_status "$SERVICE Port" "OK" "(port $PORT on $TAILSCALE_IP)"
        log_health "NETWORK_CONNECTIVITY ${SERVICE}_port OK $PORT $TAILSCALE_IP"
    elif nc -z localhost "$PORT" 2>/dev/null; then
        display_status "$SERVICE Port" "OK" "(port $PORT on localhost)"
        log_health "NETWORK_CONNECTIVITY ${SERVICE}_port OK $PORT localhost"
    else
        display_status "$SERVICE Port" "FAILED" "(port $PORT)"
        log_health "NETWORK_CONNECTIVITY ${SERVICE}_port FAILED $PORT"
    fi
done

# Security Status
echo -e "\n${BLUE}SECURITY STATUS${NC}"
echo "------------------------------------------------------------------"

# UFW Status
if command -v ufw >/dev/null 2>&1; then
    UFW_STATUS=$(ufw status | head -1 | awk '{print $2}')
    if [[ "$UFW_STATUS" == "active" ]]; then
        display_status "UFW Firewall" "OK" "(active)"
        log_health "SECURITY_STATUS ufw OK active"
    else
        display_status "UFW Firewall" "WARNING" "(inactive)"
        log_health "SECURITY_STATUS ufw WARNING inactive"
    fi
fi

# Fail2ban Status
if command -v fail2ban-client >/dev/null 2>&1; then
    if systemctl is-active fail2ban >/dev/null 2>&1; then
        display_status "Fail2ban" "OK" "(active)"
        log_health "SECURITY_STATUS fail2ban OK active"
    else
        display_status "Fail2ban" "WARNING" "(inactive)"
        log_health "SECURITY_STATUS fail2ban WARNING inactive"
    fi
fi

# Recent failed login attempts
FAILED_LOGINS=$(grep "Failed password" /var/log/auth.log 2>/dev/null | grep "$(date '+%b %d')" | wc -l)
if [[ $FAILED_LOGINS -gt 10 ]]; then
    display_status "Failed Logins" "WARNING" "($FAILED_LOGINS today)"
    log_health "SECURITY_STATUS failed_logins WARNING $FAILED_LOGINS"
elif [[ $FAILED_LOGINS -gt 0 ]]; then
    display_status "Failed Logins" "OK" "($FAILED_LOGINS today)"
    log_health "SECURITY_STATUS failed_logins OK $FAILED_LOGINS"
else
    display_status "Failed Logins" "OK" "(none today)"
    log_health "SECURITY_STATUS failed_logins OK 0"
fi

# Storage Status
echo -e "\n${BLUE}STORAGE STATUS${NC}"
echo "------------------------------------------------------------------"

# Media directories
MEDIA_DIRS=(
    "{{ media_root }}/movies"
    "{{ media_root }}/tv"
    "{{ media_root }}/music"
    "{{ media_root }}/downloads"
)

for media_dir in "${MEDIA_DIRS[@]}"; do
    DIR_NAME=$(basename "$media_dir")
    if [[ -d "$media_dir" ]]; then
        SIZE=$(du -sh "$media_dir" 2>/dev/null | cut -f1)
        FILE_COUNT=$(find "$media_dir" -type f 2>/dev/null | wc -l)
        display_status "$DIR_NAME Directory" "OK" "($SIZE, $FILE_COUNT files)"
        log_health "STORAGE_STATUS ${DIR_NAME}_directory OK $SIZE $FILE_COUNT"
    else
        display_status "$DIR_NAME Directory" "NOT_FOUND" ""
        log_health "STORAGE_STATUS ${DIR_NAME}_directory NOT_FOUND"
    fi
done

# Recent Activity Summary
echo -e "\n${BLUE}RECENT ACTIVITY${NC}"
echo "------------------------------------------------------------------"

# Check for recent downloads (last 24 hours)
RECENT_DOWNLOADS=0
for media_dir in "${MEDIA_DIRS[@]}"; do
    if [[ -d "$media_dir" ]]; then
        COUNT=$(find "$media_dir" -type f -mtime -1 2>/dev/null | wc -l)
        RECENT_DOWNLOADS=$((RECENT_DOWNLOADS + COUNT))
    fi
done

display_status "Recent Downloads" "INFO" "($RECENT_DOWNLOADS files in last 24h)"
log_health "ACTIVITY_SUMMARY recent_downloads INFO $RECENT_DOWNLOADS"

# System uptime
UPTIME=$(uptime -p)
display_status "System Uptime" "INFO" "($UPTIME)"
log_health "ACTIVITY_SUMMARY system_uptime INFO $UPTIME"

# Overall Health Summary
echo -e "\n${BLUE}OVERALL HEALTH SUMMARY${NC}"
echo "=================================================================="

# Count issues
CRITICAL_ISSUES=$(grep "CRITICAL" "$DASHBOARD_LOG" | wc -l)
WARNING_ISSUES=$(grep "WARNING" "$DASHBOARD_LOG" | wc -l)

if [[ $CRITICAL_ISSUES -gt 0 ]]; then
    echo -e "${RED}SYSTEM STATUS: CRITICAL${NC} ($CRITICAL_ISSUES critical issues)"
    log_health "OVERALL_HEALTH CRITICAL $CRITICAL_ISSUES"
elif [[ $WARNING_ISSUES -gt 0 ]]; then
    echo -e "${YELLOW}SYSTEM STATUS: WARNING${NC} ($WARNING_ISSUES warnings)"
    log_health "OVERALL_HEALTH WARNING $WARNING_ISSUES"
else
    echo -e "${GREEN}SYSTEM STATUS: HEALTHY${NC}"
    log_health "OVERALL_HEALTH HEALTHY 0"
fi

echo "=================================================================="
echo "Dashboard log: $DASHBOARD_LOG"
echo "=================================================================="

log_health "=== HEALTH DASHBOARD COMPLETED ==="

# Cleanup old dashboard logs (keep 7 days)
find "$LOG_DIR" -name "health-dashboard-*.log" -mtime +7 -delete 2>/dev/null

exit 0