ja4-platform/services/dashboard/backend/routes/metrics.py

"""
Endpoints pour les métriques du dashboard
"""
from fastapi import APIRouter, HTTPException
from ..database import db
from ..models import MetricsResponse, MetricsSummary, TimeSeriesPoint
from ..config import settings

router = APIRouter(prefix="/api/metrics", tags=["metrics"])


@router.get("", response_model=MetricsResponse, summary="Métriques globales du dashboard")
async def get_metrics():
    """
    Récupère les métriques globales du dashboard
    """
    try:
        # Résumé des métriques
        summary_query = f"""
        SELECT
            count() AS total_detections,
            countIf(threat_level = 'CRITICAL') AS critical_count,
            countIf(threat_level = 'HIGH') AS high_count,
            countIf(threat_level = 'MEDIUM') AS medium_count,
            countIf(threat_level = 'LOW') AS low_count,
            countIf(bot_name != '') AS known_bots_count,
            countIf(bot_name = '') AS anomalies_count,
            uniq(src_ip) AS unique_ips
        FROM {settings.CLICKHOUSE_DB_PROCESSING}.ml_detected_anomalies
        WHERE detected_at >= now() - INTERVAL 24 HOUR
        """
        
        summary_result = db.query(summary_query)
        summary_row = summary_result.result_rows[0] if summary_result.result_rows else None
        
        if not summary_row:
            raise HTTPException(status_code=404, detail="Aucune donnée disponible")
        
        summary = MetricsSummary(
            total_detections=summary_row[0],
            critical_count=summary_row[1],
            high_count=summary_row[2],
            medium_count=summary_row[3],
            low_count=summary_row[4],
            known_bots_count=summary_row[5],
            anomalies_count=summary_row[6],
            unique_ips=summary_row[7]
        )
        
        # Série temporelle (par heure)
        timeseries_query = f"""
        SELECT
            toStartOfHour(detected_at) AS hour,
            count() AS total,
            countIf(threat_level = 'CRITICAL') AS critical,
            countIf(threat_level = 'HIGH') AS high,
            countIf(threat_level = 'MEDIUM') AS medium,
            countIf(threat_level = 'LOW') AS low
        FROM {settings.CLICKHOUSE_DB_PROCESSING}.ml_detected_anomalies
        WHERE detected_at >= now() - INTERVAL 24 HOUR
        GROUP BY hour
        ORDER BY hour
        """
        
        timeseries_result = db.query(timeseries_query)
        timeseries = [
            TimeSeriesPoint(
                hour=row[0],
                total=row[1],
                critical=row[2],
                high=row[3],
                medium=row[4],
                low=row[5]
            )
            for row in timeseries_result.result_rows
        ]
        
        # Distribution par menace
        threat_distribution = {
            "CRITICAL": summary.critical_count,
            "HIGH": summary.high_count,
            "MEDIUM": summary.medium_count,
            "LOW": summary.low_count
        }
        
        return MetricsResponse(
            summary=summary,
            timeseries=timeseries,
            threat_distribution=threat_distribution
        )
        
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Erreur lors de la récupération des métriques: {str(e)}")


@router.get("/threats")
async def get_threat_distribution():
    """
    Récupère la répartition par niveau de menace
    """
    try:
        query = f"""
        SELECT
            threat_level,
            count() AS count,
            round(count() * 100.0 / sum(count()) OVER (), 2) AS percentage
        FROM {settings.CLICKHOUSE_DB_PROCESSING}.ml_detected_anomalies
        WHERE detected_at >= now() - INTERVAL 24 HOUR
        GROUP BY threat_level
        ORDER BY count DESC
        """
        
        result = db.query(query)
        
        return {
            "items": [
                {"threat_level": row[0], "count": row[1], "percentage": row[2]}
                for row in result.result_rows
            ]
        }
        
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Erreur: {str(e)}")


@router.get("/baseline")
async def get_metrics_baseline():
    """
    Compare les métriques actuelles (24h) vs hier (24h-48h) pour afficher les tendances.
    """
    try:
        query = f"""
        SELECT
            countIf(detected_at >= now() - INTERVAL 24 HOUR)                            AS today_total,
            countIf(detected_at >= now() - INTERVAL 48 HOUR AND detected_at < now() - INTERVAL 24 HOUR) AS yesterday_total,
            uniqIf(src_ip, detected_at >= now() - INTERVAL 24 HOUR)                     AS today_ips,
            uniqIf(src_ip, detected_at >= now() - INTERVAL 48 HOUR AND detected_at < now() - INTERVAL 24 HOUR) AS yesterday_ips,
            countIf(threat_level = 'CRITICAL' AND detected_at >= now() - INTERVAL 24 HOUR) AS today_critical,
            countIf(threat_level = 'CRITICAL' AND detected_at >= now() - INTERVAL 48 HOUR AND detected_at < now() - INTERVAL 24 HOUR) AS yesterday_critical
        FROM {settings.CLICKHOUSE_DB_PROCESSING}.ml_detected_anomalies
        WHERE detected_at >= now() - INTERVAL 48 HOUR
        """
        r = db.query(query)
        row = r.result_rows[0] if r.result_rows else None

        def pct_change(today: int, yesterday: int) -> float:
            """Calcule la variation en pourcentage entre aujourd'hui et hier. Retourne 100 si hier=0 et aujourd'hui>0."""
            if yesterday == 0:
                return 100.0 if today > 0 else 0.0
            return round((today - yesterday) / yesterday * 100, 1)

        today_total     = int(row[0] or 0) if row else 0
        yesterday_total = int(row[1] or 0) if row else 0
        today_ips       = int(row[2] or 0) if row else 0
        yesterday_ips   = int(row[3] or 0) if row else 0
        today_crit      = int(row[4] or 0) if row else 0
        yesterday_crit  = int(row[5] or 0) if row else 0

        return {
            "total_detections": {
                "today":      today_total,
                "yesterday":  yesterday_total,
                "pct_change": pct_change(today_total, yesterday_total),
            },
            "unique_ips": {
                "today":      today_ips,
                "yesterday":  yesterday_ips,
                "pct_change": pct_change(today_ips, yesterday_ips),
            },
            "critical_alerts": {
                "today":      today_crit,
                "yesterday":  yesterday_crit,
                "pct_change": pct_change(today_crit, yesterday_crit),
            },
        }
    except Exception as e:
        raise HTTPException(status_code=500, detail=f"Erreur baseline: {str(e)}")