feat(stats): store source mileage candidates

2026-07-08 14:25:09 +08:00
parent 009e50a902
commit 08e2d8c0f0
5 changed files with 298 additions and 12 deletions
--- a/go/vehicle-gateway/internal/stats/source_mileage.go
+++ b/go/vehicle-gateway/internal/stats/source_mileage.go
@@ -0,0 +1,151 @@
+package stats
+
+import (
+	"context"
+	"strings"
+	"time"
+
+	"lingniu-vehicle-ingest/go/vehicle-gateway/internal/envelope"
+)
+
+const (
+	QualityOK                 = "OK"
+	QualityNoPreviousBaseline = "NO_PREVIOUS_BASELINE"
+	QualityInvalidDelta       = "INVALID_DELTA"
+)
+
+type SourceMileageSample struct {
+	VIN             string
+	StatDate        string
+	Protocol        envelope.Protocol
+	SourceKey       string
+	SourceIP        string
+	SourceEndpoint  string
+	Phone           string
+	DeviceID        string
+	PlatformName    string
+	FirstTotalKM    float64
+	LatestTotalKM   float64
+	DailyKM         float64
+	SampleCount     int64
+	FirstEventTime  time.Time
+	LatestEventTime time.Time
+	QualityStatus   string
+	QualityReason   string
+}
+
+func SourceKey(protocol envelope.Protocol, phone string, deviceID string, sourceIP string) string {
+	identity := strings.TrimSpace(phone)
+	if identity == "" {
+		identity = strings.TrimSpace(deviceID)
+	}
+	if identity == "" {
+		identity = "unknown"
+	}
+	return string(protocol) + ":" + identity + "@" + strings.TrimSpace(sourceIP)
+}
+
+func SourceMileageSampleFromMetric(sample MetricSample, identity SourceIdentity) SourceMileageSample {
+	eventTime := sample.EventTime
+	return SourceMileageSample{
+		VIN:             sample.VIN,
+		StatDate:        sample.StatDate,
+		Protocol:        sample.Protocol,
+		SourceKey:       SourceKey(sample.Protocol, sample.Phone, sample.DeviceID, identity.SourceIP),
+		SourceIP:        identity.SourceIP,
+		SourceEndpoint:  identity.SourceEndpoint,
+		Phone:           sample.Phone,
+		DeviceID:        sample.DeviceID,
+		FirstTotalKM:    sample.TotalMileageKM,
+		LatestTotalKM:   sample.TotalMileageKM,
+		DailyKM:         0,
+		SampleCount:     1,
+		FirstEventTime:  eventTime,
+		LatestEventTime: eventTime,
+		QualityStatus:   QualityOK,
+		QualityReason:   "realtime_sample",
+	}
+}
+
+func UpsertSourceMileage(ctx context.Context, exec Execer, sample SourceMileageSample) error {
+	if exec == nil {
+		panic("stats execer must not be nil")
+	}
+	if sample.VIN == "" || sample.SourceKey == "" {
+		return nil
+	}
+	if sample.QualityStatus == "" {
+		sample.QualityStatus = QualityOK
+	}
+	_, err := exec.ExecContext(ctx, upsertSourceMileageSQL,
+		sample.VIN,
+		sample.StatDate,
+		string(sample.Protocol),
+		sample.SourceKey,
+		sample.SourceIP,
+		sample.SourceEndpoint,
+		sample.Phone,
+		sample.DeviceID,
+		sample.PlatformName,
+		sample.FirstTotalKM,
+		sample.LatestTotalKM,
+		sample.DailyKM,
+		sample.SampleCount,
+		sample.FirstEventTime,
+		sample.LatestEventTime,
+		sample.QualityStatus,
+		sample.QualityReason,
+	)
+	return err
+}
+
+const upsertSourceMileageSQL = `
+INSERT INTO vehicle_daily_mileage_source
+  (vin, stat_date, protocol, source_key, source_ip, source_endpoint, phone, device_id, platform_name,
+   first_total_mileage_km, latest_total_mileage_km, daily_mileage_km, sample_count,
+   first_event_time, latest_event_time, quality_status, quality_reason)
+VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+ON DUPLICATE KEY UPDATE
+  source_ip = VALUES(source_ip),
+  source_endpoint = VALUES(source_endpoint),
+  phone = VALUES(phone),
+  device_id = VALUES(device_id),
+  platform_name = COALESCE(VALUES(platform_name), platform_name),
+  first_total_mileage_km = CASE
+    WHEN first_total_mileage_km IS NULL OR first_total_mileage_km <= 0
+      THEN VALUES(first_total_mileage_km)
+    ELSE LEAST(first_total_mileage_km, VALUES(first_total_mileage_km))
+  END,
+  latest_total_mileage_km = CASE
+    WHEN latest_total_mileage_km IS NULL OR latest_total_mileage_km <= 0
+      THEN VALUES(latest_total_mileage_km)
+    ELSE GREATEST(latest_total_mileage_km, VALUES(latest_total_mileage_km))
+  END,
+  /* daily_mileage_km = VALUES(daily_mileage_km) */
+  daily_mileage_km = GREATEST(
+    CASE
+      WHEN latest_total_mileage_km IS NULL OR latest_total_mileage_km <= 0
+        THEN VALUES(latest_total_mileage_km)
+      ELSE latest_total_mileage_km
+    END,
+    VALUES(latest_total_mileage_km)
+  ) - CASE
+    WHEN first_total_mileage_km IS NULL OR first_total_mileage_km <= 0
+      THEN VALUES(first_total_mileage_km)
+    ELSE LEAST(first_total_mileage_km, VALUES(first_total_mileage_km))
+  END,
+  sample_count = sample_count + VALUES(sample_count),
+  first_event_time = CASE
+    WHEN first_event_time IS NULL OR VALUES(first_event_time) < first_event_time
+      THEN VALUES(first_event_time)
+    ELSE first_event_time
+  END,
+  latest_event_time = CASE
+    WHEN latest_event_time IS NULL OR VALUES(latest_event_time) > latest_event_time
+      THEN VALUES(latest_event_time)
+    ELSE latest_event_time
+  END,
+  quality_status = VALUES(quality_status),
+  quality_reason = VALUES(quality_reason),
+  updated_at = CURRENT_TIMESTAMP
+`