aiops/backend/controller/trace_proxy.go

package controller

import (
	"crypto/tls"
	"encoding/json"
	"fmt"
	"io"
	"math"
	"net/http"
	"sort"
	"strings"
	"time"

	"ezops/model"

	"github.com/gin-gonic/gin"
)

// TraceProxyHandler 链路追踪查询代理（Jaeger / Tempo 兼容） // Logan.Li
// 转发查询请求到外部 Jaeger/Tempo 服务，并将响应转换为前端期望的格式
// 无数据源时返回 demo 数据让 UI 保持可用
type TraceProxyHandler struct {
	ds *TraceDSHandler
}

func NewTraceProxyHandler(ds *TraceDSHandler) *TraceProxyHandler {
	return &TraceProxyHandler{ds: ds}
}

// ---- Jaeger 原始响应结构 ----

type jaegerServicesResp struct {
	Data []string `json:"data"`
}

type jaegerTraceResp struct {
	Data []jaegerTrace `json:"data"`
	Total int          `json:"total"`
}

type jaegerTrace struct {
	TraceID  string                 `json:"traceID"`
	Spans    []jaegerSpan           `json:"spans"`
	Processes map[string]jaegerProc `json:"processes"`
}

type jaegerSpan struct {
	TraceID       string            `json:"traceID"`
	SpanID        string            `json:"spanID"`
	OperationName string            `json:"operationName"`
	References    []jaegerRef       `json:"references"`
	StartTime     int64             `json:"startTime"` // microseconds
	Duration      int64             `json:"duration"`  // microseconds
	Tags          []jaegerTag       `json:"tags"`
	ProcessID     string            `json:"processID"`
	Logs          []jaegerLog       `json:"logs"`
}

type jaegerRef struct {
	RefType  string `json:"refType"`
	TraceID  string `json:"traceID"`
	SpanID   string `json:"spanID"`
}

type jaegerProc struct {
	ServiceName string       `json:"serviceName"`
	Tags        []jaegerTag  `json:"tags"`
}

type jaegerTag struct {
	Key   string      `json:"key"`
	Type  string      `json:"type"`
	Value interface{} `json:"value"`
}

type jaegerLog struct {
	Timestamp int64         `json:"timestamp"`
	Fields    []jaegerTag   `json:"fields"`
}

// ---- 前端期望的格式 ----

type traceListItem struct {
	ID            string            `json:"id"`
	TraceID       string            `json:"traceId"`
	ServiceName   string            `json:"serviceName"`
	OperationName string            `json:"operationName"`
	StartTime     string            `json:"startTime"`
	Duration      float64           `json:"duration"` // ms
	Status        string            `json:"status"`
	SpanCount     int               `json:"spanCount"`
	Tags          map[string]string `json:"tags"`
}

type spanItem struct {
	ID            string            `json:"id"`
	SpanID        string            `json:"spanId"`
	ParentSpanID  string            `json:"parentSpanId,omitempty"`
	ServiceName   string            `json:"serviceName"`
	OperationName string            `json:"operationName"`
	StartTime     string            `json:"startTime"`
	Duration      float64           `json:"duration"` // ms
	Status        string            `json:"status"`
	Kind          string            `json:"kind"`
	Tags          map[string]string `json:"tags"`
	Logs          []spanLogItem     `json:"logs"`
}

type spanLogItem struct {
	Timestamp string            `json:"timestamp"`
	Fields    map[string]string `json:"fields"`
}

type serviceMetric struct {
	ServiceName  string  `json:"serviceName"`
	RequestCount int     `json:"requestCount"`
	ErrorRate    float64 `json:"errorRate"`
	AvgDuration  float64 `json:"avgDuration"`  // ms
	P95Duration  float64 `json:"p95Duration"`
	P99Duration  float64 `json:"p99Duration"`
}

// ---- HTTP 辅助 ----

func newTraceHTTPClient(skipTLS bool, timeout time.Duration) *http.Client {
	tr := &http.Transport{TLSClientConfig: &tls.Config{InsecureSkipVerify: skipTLS}}
	return &http.Client{Transport: tr, Timeout: timeout}
}

func (h *TraceProxyHandler) doGet(ds *model.TraceDataSource, path string) ([]byte, int, error) {
	target := ds.URL + path
	client := newTraceHTTPClient(ds.SkipTLSVerify, 30*time.Second)
	req, _ := http.NewRequest("GET", target, nil)
	if ds.BasicAuth && ds.BasicAuthUser != "" {
		req.SetBasicAuth(ds.BasicAuthUser, ds.BasicAuthPass)
	}
	resp, err := client.Do(req)
	if err != nil {
		return nil, 0, err
	}
	defer resp.Body.Close()
	body, _ := io.ReadAll(resp.Body)
	return body, resp.StatusCode, nil
}

// ---- 转换函数 ----

func tagsToMap(tags []jaegerTag) map[string]string {
	m := map[string]string{}
	for _, t := range tags {
		m[t.Key] = fmt.Sprintf("%v", t.Value)
	}
	return m
}

func spanStatus(spans []jaegerSpan) string {
	for _, s := range spans {
		for _, t := range s.Tags {
			if t.Key == "error" {
				if b, ok := t.Value.(bool); ok && b {
					return "error"
				}
			}
			if t.Key == "http.status_code" {
				if code, ok := toInt(t.Value); ok && code >= 400 {
					return "error"
				}
			}
		}
	}
	return "success"
}

func toInt(v interface{}) (int, bool) {
	switch n := v.(type) {
	case float64:
		return int(n), true
	case int:
		return n, true
	case int64:
		return int(n), true
	}
	return 0, false
}

func formatTraceTime(us int64) string {
	return time.UnixMicro(us).Format("2006-01-02 15:04:05")
}

func kindFromTags(tags []jaegerTag) string {
	for _, t := range tags {
		if t.Key == "span.kind" {
			if s, ok := t.Value.(string); ok {
				return s
			}
		}
	}
	return "internal"
}

// ---- API: GetServices GET /api/v1/traces/services ----

func (h *TraceProxyHandler) GetServices(c *gin.Context) {
	timeRange := c.DefaultQuery("timeRange", "1h")
	ds, err := h.ds.getDefaultTraceDS()
	if err != nil || ds == nil {
		// demo 数据
		c.JSON(200, model.Response{Code: 200, Data: gin.H{
			"data":  demoServiceMetrics(),
			"total": 5,
			"demo":  true,
		}})
		return
	}

	body, status, err := h.doGet(ds, "/api/services")
	if err != nil || status != 200 {
		c.JSON(200, model.Response{Code: 200, Data: gin.H{
			"data":  demoServiceMetrics(),
			"total": 5,
			"demo":  true,
		}})
		return
	}

	var svcResp jaegerServicesResp
	if json.Unmarshal(body, &svcResp) != nil {
		c.JSON(500, model.Response{Code: 500, Message: "解析服务列表失败"})
		return
	}

	// 查询 traces 来计算服务指标
	services := buildServiceMetricsFromTraces(h, ds, svcResp.Data, timeRange)
	c.JSON(200, model.Response{Code: 200, Data: gin.H{
		"data":  services,
		"total": len(services),
	}})
}

func buildServiceMetricsFromTraces(h *TraceProxyHandler, ds *model.TraceDataSource, serviceNames []string, timeRange string) []serviceMetric {
	// 查询最近 traces 来聚合服务指标
	dur := parseTraceRange(timeRange)
	end := time.Now()
	start := end.Add(-dur)
	traces := h.queryTraces(ds, "", 200, start, end)

	// 按服务聚合
	type agg struct {
		durations []float64
		errors    int
	}
	aggMap := map[string]*agg{}
	for _, name := range serviceNames {
		aggMap[name] = &agg{}
	}

	for _, t := range traces {
		for _, sp := range t.Spans {
			proc, ok := t.Processes[sp.ProcessID]
			if !ok {
				continue
			}
			svcName := proc.ServiceName
			a, exists := aggMap[svcName]
			if !exists {
				a = &agg{}
				aggMap[svcName] = a
			}
			a.durations = append(a.durations, float64(sp.Duration)/1000.0) // μs→ms
			isErr := false
			for _, tag := range sp.Tags {
				if tag.Key == "error" {
					if b, ok := tag.Value.(bool); ok && b {
						isErr = true
					}
				}
			}
			if isErr {
				a.errors++
			}
		}
	}

	result := []serviceMetric{}
	for _, name := range serviceNames {
		a := aggMap[name]
		if len(a.durations) == 0 {
			result = append(result, serviceMetric{
				ServiceName: name, RequestCount: 0, ErrorRate: 0,
				AvgDuration: 0, P95Duration: 0, P99Duration: 0,
			})
			continue
		}
		sort.Float64s(a.durations)
		total := len(a.durations)
		sum := 0.0
		for _, d := range a.durations {
			sum += d
		}
		avg := sum / float64(total)
		p95 := percentile(a.durations, 0.95)
		p99 := percentile(a.durations, 0.99)
		errRate := float64(a.errors) / float64(total) * 100
		result = append(result, serviceMetric{
			ServiceName:  name,
			RequestCount: total,
			ErrorRate:    math.Round(errRate*100) / 100,
			AvgDuration:  math.Round(avg*100) / 100,
			P95Duration:  math.Round(p95*100) / 100,
			P99Duration:  math.Round(p99*100) / 100,
		})
	}
	return result
}

func percentile(sorted []float64, p float64) float64 {
	if len(sorted) == 0 {
		return 0
	}
	idx := int(float64(len(sorted)-1) * p)
	return sorted[idx]
}

func parseTraceRange(r string) time.Duration {
	switch r {
	case "15m":
		return 15 * time.Minute
	case "1h":
		return time.Hour
	case "6h":
		return 6 * time.Hour
	case "24h":
		return 24 * time.Hour
	case "7d":
		return 7 * 24 * time.Hour
	default:
		return time.Hour
	}
}

// ---- API: GetTraces GET /api/v1/traces ----

func (h *TraceProxyHandler) GetTraces(c *gin.Context) {
	service := c.Query("service")
	status := c.DefaultQuery("status", "all")
	timeRange := c.DefaultQuery("timeRange", "1h")
	limit := 50

	ds, err := h.ds.getDefaultTraceDS()
	if err != nil || ds == nil {
		// demo 数据
		demoTraces := demoTraces(service, status)
		c.JSON(200, model.Response{Code: 200, Data: gin.H{
			"data":  demoTraces,
			"total": len(demoTraces),
			"demo":  true,
		}})
		return
	}

	dur := parseTraceRange(timeRange)
	end := time.Now()
	start := end.Add(-dur)
	traces := h.queryTraces(ds, service, limit, start, end)

	items := []traceListItem{}
	for _, t := range traces {
		if len(t.Spans) == 0 {
			continue
		}
		rootSpan := t.Spans[0]
		svcName := ""
		if proc, ok := t.Processes[rootSpan.ProcessID]; ok {
			svcName = proc.ServiceName
		}
		st := spanStatus(t.Spans)
		// 按状态过滤
		if status != "all" && st != status {
			continue
		}
		items = append(items, traceListItem{
			ID:            t.TraceID,
			TraceID:       t.TraceID,
			ServiceName:   svcName,
			OperationName: rootSpan.OperationName,
			StartTime:     formatTraceTime(rootSpan.StartTime),
			Duration:      math.Round(float64(rootSpan.Duration)/1000.0*100) / 100, // μs→ms
			Status:        st,
			SpanCount:     len(t.Spans),
			Tags:          tagsToMap(rootSpan.Tags),
		})
	}
	c.JSON(200, model.Response{Code: 200, Data: gin.H{
		"data":  items,
		"total": len(items),
	}})
}

// queryTraces 查询 Jaeger traces
func (h *TraceProxyHandler) queryTraces(ds *model.TraceDataSource, service string, limit int, start, end time.Time) []jaegerTrace {
	path := fmt.Sprintf("/api/traces?limit=%d&start=%d&end=%d", limit, start.UnixMicro(), end.UnixMicro())
	if service != "" && service != "all" {
		path += "&service=" + service
	}
	body, status, err := h.doGet(ds, path)
	if err != nil || status != 200 {
		return nil
	}
	var resp jaegerTraceResp
	if json.Unmarshal(body, &resp) != nil {
		return nil
	}
	return resp.Data
}

// ---- API: GetTraceDetail GET /api/v1/traces/:traceId ----

func (h *TraceProxyHandler) GetTraceDetail(c *gin.Context) {
	traceID := c.Param("traceId")

	ds, err := h.ds.getDefaultTraceDS()
	if err != nil || ds == nil {
		// demo
		c.JSON(200, model.Response{Code: 200, Data: gin.H{
			"spans": demoSpans(traceID),
			"demo":  true,
		}})
		return
	}

	body, status, err := h.doGet(ds, "/api/traces/"+traceID)
	if err != nil || status != 200 {
		c.JSON(200, model.Response{Code: 200, Data: gin.H{"spans": []spanItem{}}})
		return
	}

	var resp jaegerTraceResp
	if json.Unmarshal(body, &resp) != nil || len(resp.Data) == 0 {
		c.JSON(200, model.Response{Code: 200, Data: gin.H{"spans": []spanItem{}}})
		return
	}

	t := resp.Data[0]
	spans := []spanItem{}
	for _, sp := range t.Spans {
		svcName := ""
		if proc, ok := t.Processes[sp.ProcessID]; ok {
			svcName = proc.ServiceName
		}
		parentID := ""
		for _, ref := range sp.References {
			if ref.RefType == "CHILD_OF" {
				parentID = ref.SpanID
				break
			}
		}
		st := "success"
		for _, tag := range sp.Tags {
			if tag.Key == "error" {
				if b, ok := tag.Value.(bool); ok && b {
					st = "error"
				}
			}
		}
		logs := []spanLogItem{}
		for _, l := range sp.Logs {
			fields := map[string]string{}
			for _, f := range l.Fields {
				fields[f.Key] = fmt.Sprintf("%v", f.Value)
			}
			logs = append(logs, spanLogItem{
				Timestamp: formatTraceTime(l.Timestamp),
				Fields:    fields,
			})
		}
		spans = append(spans, spanItem{
			ID:            sp.SpanID,
			SpanID:        sp.SpanID,
			ParentSpanID:  parentID,
			ServiceName:   svcName,
			OperationName: sp.OperationName,
			StartTime:     formatTraceTime(sp.StartTime),
			Duration:      math.Round(float64(sp.Duration)/1000.0*100) / 100,
			Status:        st,
			Kind:          kindFromTags(sp.Tags),
			Tags:          tagsToMap(sp.Tags),
			Logs:          logs,
		})
	}
	c.JSON(200, model.Response{Code: 200, Data: gin.H{"spans": spans}})
}

// ---- Demo 数据 ----

func demoServiceMetrics() []serviceMetric {
	return []serviceMetric{
		{ServiceName: "api-gateway", RequestCount: 15230, ErrorRate: 0.32, AvgDuration: 45.2, P95Duration: 120.5, P99Duration: 250.1},
		{ServiceName: "user-service", RequestCount: 8421, ErrorRate: 0.15, AvgDuration: 28.7, P95Duration: 75.3, P99Duration: 150.8},
		{ServiceName: "order-service", RequestCount: 6754, ErrorRate: 1.23, AvgDuration: 89.4, P95Duration: 200.6, P99Duration: 450.2},
		{ServiceName: "payment-service", RequestCount: 3210, ErrorRate: 0.08, AvgDuration: 156.3, P95Duration: 350.4, P99Duration: 680.7},
		{ServiceName: "inventory-service", RequestCount: 4567, ErrorRate: 0.45, AvgDuration: 32.1, P95Duration: 85.7, P99Duration: 170.3},
	}
}

func demoTraces(serviceFilter, statusFilter string) []traceListItem {
	now := time.Now()
	all := []traceListItem{
		{ID: "trace-001", TraceID: "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4", ServiceName: "api-gateway", OperationName: "GET /api/v1/orders", StartTime: now.Add(-2 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 125.4, Status: "success", SpanCount: 8, Tags: map[string]string{"http.method": "GET", "http.status_code": "200"}},
		{ID: "trace-002", TraceID: "b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5", ServiceName: "user-service", OperationName: "POST /api/v1/users/login", StartTime: now.Add(-5 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 45.7, Status: "success", SpanCount: 4, Tags: map[string]string{"http.method": "POST", "http.status_code": "200"}},
		{ID: "trace-003", TraceID: "c3d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6", ServiceName: "order-service", OperationName: "POST /api/v1/orders", StartTime: now.Add(-8 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 380.2, Status: "error", SpanCount: 12, Tags: map[string]string{"http.method": "POST", "http.status_code": "500", "error": "true"}},
		{ID: "trace-004", TraceID: "d4e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1", ServiceName: "payment-service", OperationName: "POST /api/v1/payments", StartTime: now.Add(-12 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 220.8, Status: "success", SpanCount: 6, Tags: map[string]string{"http.method": "POST", "http.status_code": "200"}},
		{ID: "trace-005", TraceID: "e5f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2", ServiceName: "inventory-service", OperationName: "GET /api/v1/inventory/:id", StartTime: now.Add(-15 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 32.1, Status: "success", SpanCount: 3, Tags: map[string]string{"http.method": "GET", "http.status_code": "200"}},
		{ID: "trace-006", TraceID: "f6a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3", ServiceName: "api-gateway", OperationName: "GET /api/v1/products", StartTime: now.Add(-20 * time.Minute).Format("2006-01-02 15:04:05"), Duration: 95.3, Status: "success", SpanCount: 5, Tags: map[string]string{"http.method": "GET", "http.status_code": "200"}},
	}
	result := []traceListItem{}
	for _, t := range all {
		if serviceFilter != "" && serviceFilter != "all" && t.ServiceName != serviceFilter {
			continue
		}
		if statusFilter != "all" && t.Status != statusFilter {
			continue
		}
		result = append(result, t)
	}
	return result
}

func demoSpans(traceID string) []spanItem {
	now := time.Now().Add(-2 * time.Minute)
	return []spanItem{
		{ID: "span-1", SpanID: "span-1", ServiceName: "api-gateway", OperationName: "GET /api/v1/orders", StartTime: now.Format("2006-01-02 15:04:05"), Duration: 125.4, Status: "success", Kind: "server", Tags: map[string]string{"http.method": "GET", "http.url": "/api/v1/orders"}, Logs: []spanLogItem{}},
		{ID: "span-2", SpanID: "span-2", ParentSpanID: "span-1", ServiceName: "user-service", OperationName: "auth.check", StartTime: now.Add(2 * time.Millisecond).Format("2006-01-02 15:04:05"), Duration: 15.2, Status: "success", Kind: "client", Tags: map[string]string{"rpc.system": "grpc"}, Logs: []spanLogItem{}},
		{ID: "span-3", SpanID: "span-3", ParentSpanID: "span-1", ServiceName: "order-service", OperationName: "order.list", StartTime: now.Add(20 * time.Millisecond).Format("2006-01-02 15:04:05"), Duration: 65.8, Status: "success", Kind: "client", Tags: map[string]string{"db.system": "mysql", "db.statement": "SELECT"}, Logs: []spanLogItem{}},
		{ID: "span-4", SpanID: "span-4", ParentSpanID: "span-3", ServiceName: "inventory-service", OperationName: "inventory.check", StartTime: now.Add(30 * time.Millisecond).Format("2006-01-02 15:04:05"), Duration: 22.1, Status: "success", Kind: "client", Tags: map[string]string{"rpc.system": "grpc"}, Logs: []spanLogItem{}},
		{ID: "span-5", SpanID: "span-5", ParentSpanID: "span-3", ServiceName: "order-service", OperationName: "db.query", StartTime: now.Add(50 * time.Millisecond).Format("2006-01-02 15:04:05"), Duration: 10.5, Status: "success", Kind: "internal", Tags: map[string]string{"db.system": "mysql"}, Logs: []spanLogItem{}},
	}
}

// 确保 strings 包被使用（避免 unused import 在某些构建条件下）
var _ = strings.TrimSpace