feat: add log for export error

Reviewed-on: #5

.gitignore

@@ -8,3 +8,4 @@ texpixel
 /vendor
 
 dev_deploy.sh
+speed_take.sh

api/router.go

@@ -1,11 +1,12 @@
 package api
 
 import (
-	"gitea.com/bitwsd/document_ai/api/v1/formula"
+	"gitea.com/texpixel/document_ai/api/v1/analytics"
-	"gitea.com/bitwsd/document_ai/api/v1/oss"
+	"gitea.com/texpixel/document_ai/api/v1/formula"
-	"gitea.com/bitwsd/document_ai/api/v1/task"
+	"gitea.com/texpixel/document_ai/api/v1/oss"
-	"gitea.com/bitwsd/document_ai/api/v1/user"
+	"gitea.com/texpixel/document_ai/api/v1/task"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/api/v1/user"
+	"gitea.com/texpixel/document_ai/pkg/common"
 	"github.com/gin-gonic/gin"
 )
 
@@ -26,6 +27,7 @@ func SetupRouter(engine *gin.RouterGroup) {
 			endpoint := task.NewTaskEndpoint()
 			taskRouter.POST("/evaluate", endpoint.EvaluateTask)
 			taskRouter.GET("/list", common.MustAuthMiddleware(), endpoint.GetTaskList)
+			taskRouter.POST("/export", endpoint.ExportTask)
 		}
 
 		ossRouter := v1.Group("/oss", common.GetAuthMiddleware())
@@ -36,15 +38,27 @@ func SetupRouter(engine *gin.RouterGroup) {
 			ossRouter.POST("/file/upload", endpoint.UploadFile)
 		}
 
-		userRouter := v1.Group("/user", common.GetAuthMiddleware())
-		{
 		userEndpoint := user.NewUserEndpoint()
+
+		userRouter := v1.Group("/user")
 		{
 			userRouter.POST("/sms", userEndpoint.SendVerificationCode)
 			userRouter.POST("/register", userEndpoint.RegisterByEmail)
 			userRouter.POST("/login", userEndpoint.LoginByEmail)
-				userRouter.GET("/info", common.MustAuthMiddleware(), userEndpoint.GetUserInfo)
+			userRouter.GET("/oauth/google/url", userEndpoint.GetGoogleOAuthUrl)
+			userRouter.POST("/oauth/google/callback", userEndpoint.GoogleOAuthCallback)
 		}
+
+		userAuthRouter := v1.Group("/user", common.GetAuthMiddleware())
+		{
+			userAuthRouter.GET("/info", common.MustAuthMiddleware(), userEndpoint.GetUserInfo)
+		}
+
+		// 数据埋点路由
+		analyticsRouter := v1.Group("/analytics", common.GetAuthMiddleware())
+		{
+			analyticsHandler := analytics.NewAnalyticsHandler()
+			analyticsRouter.POST("/track", analyticsHandler.TrackEvent)
 		}
 	}
 

api/v1/analytics/handler.go

@@ -0,0 +1,50 @@
+package analytics
+
+import (
+	"net/http"
+
+	"gitea.com/texpixel/document_ai/internal/model/analytics"
+	"gitea.com/texpixel/document_ai/internal/service"
+	"gitea.com/texpixel/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/log"
+	"github.com/gin-gonic/gin"
+)
+
+type AnalyticsHandler struct {
+	analyticsService *service.AnalyticsService
+}
+
+func NewAnalyticsHandler() *AnalyticsHandler {
+	return &AnalyticsHandler{
+		analyticsService: service.NewAnalyticsService(),
+	}
+}
+
+// TrackEvent 记录单个事件
+// @Summary 记录单个埋点事件
+// @Description 记录用户行为埋点事件
+// @Tags Analytics
+// @Accept json
+// @Produce json
+// @Param request body analytics.TrackEventRequest true "事件信息"
+// @Success 200 {object} common.Response
+// @Router /api/v1/analytics/track [post]
+func (h *AnalyticsHandler) TrackEvent(c *gin.Context) {
+	var req analytics.TrackEventRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		log.Error(c.Request.Context(), "bind request failed", "error", err)
+		c.JSON(http.StatusOK, common.ErrorResponse(c, common.CodeParamError, "invalid request"))
+		return
+	}
+
+	userID := common.GetUserIDFromContext(c)
+	req.UserID = userID
+
+	if err := h.analyticsService.TrackEvent(c.Request.Context(), &req); err != nil {
+		log.Error(c.Request.Context(), "track event failed", "error", err)
+		c.JSON(http.StatusOK, common.ErrorResponse(c, common.CodeSystemError, "failed to track event"))
+		return
+	}
+
+	c.JSON(http.StatusOK, common.SuccessResponse(c, "success"))
+}

api/v1/formula/handler.go

@@ -5,12 +5,12 @@ import (
 	"path/filepath"
 	"strings"
 
-	"gitea.com/bitwsd/document_ai/internal/model/formula"
+	"gitea.com/texpixel/document_ai/internal/model/formula"
-	"gitea.com/bitwsd/document_ai/internal/service"
+	"gitea.com/texpixel/document_ai/internal/service"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/constant"
+	"gitea.com/texpixel/document_ai/pkg/constant"
-	"gitea.com/bitwsd/document_ai/pkg/utils"
+	"gitea.com/texpixel/document_ai/pkg/utils"
 
 	"github.com/gin-gonic/gin"
 )

api/v1/oss/handler.go

@@ -8,11 +8,11 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/oss"
+	"gitea.com/texpixel/document_ai/pkg/oss"
-	"gitea.com/bitwsd/document_ai/pkg/utils"
+	"gitea.com/texpixel/document_ai/pkg/utils"
 	"github.com/gin-gonic/gin"
 	"gorm.io/gorm"
 )

api/v1/task/handler.go

@@ -3,10 +3,10 @@ package task
 import (
 	"net/http"
 
-	"gitea.com/bitwsd/document_ai/internal/model/task"
+	"gitea.com/texpixel/document_ai/internal/model/task"
-	"gitea.com/bitwsd/document_ai/internal/service"
+	"gitea.com/texpixel/document_ai/internal/service"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 	"github.com/gin-gonic/gin"
 )
 
@@ -61,3 +61,31 @@ func (h *TaskEndpoint) GetTaskList(c *gin.Context) {
 
 	c.JSON(http.StatusOK, common.SuccessResponse(c, resp))
 }
+
+func (h *TaskEndpoint) ExportTask(c *gin.Context) {
+	var req task.ExportTaskRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		log.Error(c, "func", "ExportTask", "msg", "Invalid parameters", "error", err)
+		c.JSON(http.StatusOK, common.ErrorResponse(c, common.CodeParamError, "Invalid parameters"))
+		return
+	}
+	fileData, contentType, err := h.taskService.ExportTask(c, &req)
+	if err != nil {
+		c.JSON(http.StatusOK, common.ErrorResponse(c, common.CodeSystemError, "导出任务失败"))
+		return
+	}
+
+	// set filename based on export type
+	var filename string
+	switch req.Type {
+	case "pdf":
+		filename = "texpixel_export.pdf"
+	case "docx":
+		filename = "texpixel_export.docx"
+	default:
+		filename = "texpixel_export"
+	}
+
+	c.Header("Content-Disposition", "attachment; filename="+filename)
+	c.Data(http.StatusOK, contentType, fileData)
+}

api/v1/user/handler.go

@@ -1,15 +1,17 @@
 package user
 
 import (
+	"fmt"
 	"net/http"
+	"net/url"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
-	model "gitea.com/bitwsd/document_ai/internal/model/user"
+	model "gitea.com/texpixel/document_ai/internal/model/user"
-	"gitea.com/bitwsd/document_ai/internal/service"
+	"gitea.com/texpixel/document_ai/internal/service"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/constant"
+	"gitea.com/texpixel/document_ai/pkg/constant"
-	"gitea.com/bitwsd/document_ai/pkg/jwt"
+	"gitea.com/texpixel/document_ai/pkg/jwt"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 	"github.com/gin-gonic/gin"
 )
 
@@ -98,15 +100,9 @@ func (h *UserEndpoint) GetUserInfo(ctx *gin.Context) {
 		return
 	}
 
-	status := 0
-	if user.ID > 0 {
-		status = 1
-	}
-
 	ctx.JSON(http.StatusOK, common.SuccessResponse(ctx, model.UserInfoResponse{
 		Username: user.Username,
-		Phone:    user.Phone,
+		Email:    user.Email,
-		Status:   status,
 	}))
 }
 
@@ -169,3 +165,69 @@ func (h *UserEndpoint) LoginByEmail(ctx *gin.Context) {
 		ExpiresAt: tokenResult.ExpiresAt,
 	}))
 }
+
+func (h *UserEndpoint) GetGoogleOAuthUrl(ctx *gin.Context) {
+	req := model.GoogleAuthUrlRequest{}
+	if err := ctx.ShouldBindQuery(&req); err != nil {
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeParamError, common.CodeParamErrorMsg))
+		return
+	}
+
+	googleConfig := config.GlobalConfig.Google
+	if googleConfig.ClientID == "" {
+		log.Error(ctx, "func", "GetGoogleOAuthUrl", "msg", "Google OAuth not configured")
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeSystemError, common.CodeSystemErrorMsg))
+		return
+	}
+
+	authURL := fmt.Sprintf(
+		"https://accounts.google.com/o/oauth2/v2/auth?client_id=%s&redirect_uri=%s&response_type=code&scope=openid%%20email%%20profile&state=%s",
+		url.QueryEscape(googleConfig.ClientID),
+		url.QueryEscape(req.RedirectURI),
+		url.QueryEscape(req.State),
+	)
+
+	ctx.JSON(http.StatusOK, common.SuccessResponse(ctx, model.GoogleAuthUrlResponse{
+		AuthURL: authURL,
+	}))
+}
+
+func (h *UserEndpoint) GoogleOAuthCallback(ctx *gin.Context) {
+	req := model.GoogleOAuthCallbackRequest{}
+	if err := ctx.ShouldBindJSON(&req); err != nil {
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeParamError, common.CodeParamErrorMsg))
+		return
+	}
+
+	googleConfig := config.GlobalConfig.Google
+	if googleConfig.ClientID == "" || googleConfig.ClientSecret == "" {
+		log.Error(ctx, "func", "GoogleOAuthCallback", "msg", "Google OAuth not configured")
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeSystemError, common.CodeSystemErrorMsg))
+		return
+	}
+
+	userInfo, err := h.userService.ExchangeGoogleCodeAndGetUserInfo(ctx, googleConfig.ClientID, googleConfig.ClientSecret, req.Code, req.RedirectURI)
+	if err != nil {
+		log.Error(ctx, "func", "GoogleOAuthCallback", "msg", "exchange code failed", "error", err)
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeSystemError, common.CodeSystemErrorMsg))
+		return
+	}
+
+	uid, err := h.userService.FindOrCreateGoogleUser(ctx, userInfo)
+	if err != nil {
+		log.Error(ctx, "func", "GoogleOAuthCallback", "msg", "find or create user failed", "error", err)
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeSystemError, common.CodeSystemErrorMsg))
+		return
+	}
+
+	tokenResult, err := jwt.CreateToken(jwt.User{UserId: uid})
+	if err != nil {
+		ctx.JSON(http.StatusOK, common.ErrorResponse(ctx, common.CodeUnauthorized, common.CodeUnauthorizedMsg))
+		return
+	}
+
+	ctx.JSON(http.StatusOK, common.SuccessResponse(ctx, model.GoogleOAuthCallbackResponse{
+		Token:     tokenResult.Token,
+		ExpiresAt: tokenResult.ExpiresAt,
+	}))
+}

cmd/migrate/README.md

@@ -0,0 +1,73 @@
+# 数据迁移工具
+
+用于将测试数据库的数据迁移到生产数据库，避免ID冲突，使用事务确保数据一致性。
+
+## 功能特性
+
+- ✅ 自动避免ID冲突（使用数据库自增ID）
+- ✅ 使用事务确保每个任务和结果数据的一致性
+- ✅ 自动跳过已存在的任务（基于task_uuid）
+- ✅ 保留原始时间戳
+- ✅ 处理NULL值
+- ✅ 详细的日志输出和统计信息
+
+## 使用方法
+
+### 基本用法
+
+```bash
+# 从dev环境迁移到prod环境
+go run cmd/migrate/main.go -test-env=dev -prod-env=prod
+
+# 从prod环境迁移到dev环境（测试反向迁移）
+go run cmd/migrate/main.go -test-env=prod -prod-env=dev
+```
+
+### 参数说明
+
+- `-test-env`: 测试环境配置文件名（dev/prod），默认值：dev
+- `-prod-env`: 生产环境配置文件名（dev/prod），默认值：prod
+
+### 编译后使用
+
+```bash
+# 编译
+go build -o migrate cmd/migrate/main.go
+
+# 运行
+./migrate -test-env=dev -prod-env=prod
+```
+
+## 工作原理
+
+1. **连接数据库**：同时连接测试数据库和生产数据库
+2. **读取数据**：从测试数据库读取所有任务和结果数据（LEFT JOIN）
+3. **检查重复**：基于`task_uuid`检查生产数据库中是否已存在
+4. **事务迁移**：为每个任务创建独立事务：
+   - 创建任务记录（自动生成新ID）
+   - 如果存在结果数据，创建结果记录（关联新任务ID）
+   - 提交事务或回滚
+5. **统计报告**：输出迁移统计信息
+
+## 注意事项
+
+1. **配置文件**：确保`config/config_dev.yaml`和`config/config_prod.yaml`存在且配置正确
+2. **数据库权限**：确保数据库用户有读写权限
+3. **网络连接**：确保能同时连接到两个数据库
+4. **数据备份**：迁移前建议备份生产数据库
+5. **ID冲突**：脚本会自动处理ID冲突，使用数据库自增ID，不会覆盖现有数据
+
+## 输出示例
+
+```
+从测试数据库读取到 100 条任务记录
+[1/100] 创建任务成功: task_uuid=xxx, 新ID=1001
+[1/100] 创建结果成功: task_id=1001
+[2/100] 跳过已存在的任务: task_uuid=yyy, id=1002
+...
+迁移完成统计:
+  成功: 95 条
+  跳过: 3 条
+  失败: 2 条
+数据迁移完成！
+```

cmd/migrate/main.go

@@ -0,0 +1,255 @@
+package main
+
+import (
+	"context"
+	"flag"
+	"fmt"
+	"log"
+	"time"
+
+	"gitea.com/texpixel/document_ai/config"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
+	"github.com/spf13/viper"
+	"gorm.io/driver/mysql"
+	"gorm.io/gorm"
+	"gorm.io/gorm/logger"
+)
+
+func main() {
+	// 解析命令行参数
+	testEnv := flag.String("test-env", "dev", "测试环境配置 (dev/prod)")
+	prodEnv := flag.String("prod-env", "prod", "生产环境配置 (dev/prod)")
+	flag.Parse()
+
+	// 加载测试环境配置
+	testConfigPath := fmt.Sprintf("./config/config_%s.yaml", *testEnv)
+	testConfig, err := loadDatabaseConfig(testConfigPath)
+	if err != nil {
+		log.Fatalf("加载测试环境配置失败: %v", err)
+	}
+
+	// 连接测试数据库
+	testDSN := fmt.Sprintf("%s:%s@tcp(%s:%d)/%s?charset=utf8mb4&parseTime=True&loc=Asia%%2FShanghai",
+		testConfig.Username, testConfig.Password, testConfig.Host, testConfig.Port, testConfig.DBName)
+	testDB, err := gorm.Open(mysql.Open(testDSN), &gorm.Config{
+		Logger: logger.Default.LogMode(logger.Info),
+	})
+	if err != nil {
+		log.Fatalf("连接测试数据库失败: %v", err)
+	}
+
+	// 加载生产环境配置
+	prodConfigPath := fmt.Sprintf("./config/config_%s.yaml", *prodEnv)
+	prodConfig, err := loadDatabaseConfig(prodConfigPath)
+	if err != nil {
+		log.Fatalf("加载生产环境配置失败: %v", err)
+	}
+
+	// 连接生产数据库
+	prodDSN := fmt.Sprintf("%s:%s@tcp(%s:%d)/%s?charset=utf8mb4&parseTime=True&loc=Asia%%2FShanghai",
+		prodConfig.Username, prodConfig.Password, prodConfig.Host, prodConfig.Port, prodConfig.DBName)
+	prodDB, err := gorm.Open(mysql.Open(prodDSN), &gorm.Config{
+		Logger: logger.Default.LogMode(logger.Info),
+	})
+	if err != nil {
+		log.Fatalf("连接生产数据库失败: %v", err)
+	}
+
+	// 执行迁移
+	if err := migrateData(testDB, prodDB); err != nil {
+		log.Fatalf("数据迁移失败: %v", err)
+	}
+
+	log.Println("数据迁移完成！")
+}
+
+func migrateData(testDB, prodDB *gorm.DB) error {
+	_ = context.Background() // 保留以备将来使用
+
+	// 从测试数据库读取所有任务数据（包含结果）
+	type TaskWithResult struct {
+		// Task 字段
+		TaskID        int64     `gorm:"column:id"`
+		UserID        int64     `gorm:"column:user_id"`
+		TaskUUID      string    `gorm:"column:task_uuid"`
+		FileName      string    `gorm:"column:file_name"`
+		FileHash      string    `gorm:"column:file_hash"`
+		FileURL       string    `gorm:"column:file_url"`
+		TaskType      string    `gorm:"column:task_type"`
+		Status        int       `gorm:"column:status"`
+		CompletedAt   time.Time `gorm:"column:completed_at"`
+		Remark        string    `gorm:"column:remark"`
+		IP            string    `gorm:"column:ip"`
+		TaskCreatedAt time.Time `gorm:"column:created_at"`
+		TaskUpdatedAt time.Time `gorm:"column:updated_at"`
+		// Result 字段
+		ResultID        *int64     `gorm:"column:result_id"`
+		ResultTaskID    *int64     `gorm:"column:result_task_id"`
+		ResultTaskType  *string    `gorm:"column:result_task_type"`
+		Latex           *string    `gorm:"column:latex"`
+		Markdown        *string    `gorm:"column:markdown"`
+		MathML          *string    `gorm:"column:mathml"`
+		ResultCreatedAt *time.Time `gorm:"column:result_created_at"`
+		ResultUpdatedAt *time.Time `gorm:"column:result_updated_at"`
+	}
+
+	var tasksWithResults []TaskWithResult
+	query := `
+		SELECT 
+			t.id,
+			t.user_id,
+			t.task_uuid,
+			t.file_name,
+			t.file_hash,
+			t.file_url,
+			t.task_type,
+			t.status,
+			t.completed_at,
+			t.remark,
+			t.ip,
+			t.created_at,
+			t.updated_at,
+			r.id as result_id,
+			r.task_id as result_task_id,
+			r.task_type as result_task_type,
+			r.latex,
+			r.markdown,
+			r.mathml,
+			r.created_at as result_created_at,
+			r.updated_at as result_updated_at
+		FROM recognition_tasks t
+		LEFT JOIN recognition_results r ON t.id = r.task_id
+		ORDER BY t.id
+	`
+
+	if err := testDB.Raw(query).Scan(&tasksWithResults).Error; err != nil {
+		return fmt.Errorf("读取测试数据失败: %v", err)
+	}
+
+	log.Printf("从测试数据库读取到 %d 条任务记录", len(tasksWithResults))
+
+	successCount := 0
+	skipCount := 0
+	errorCount := 0
+
+	// 为每个任务使用独立事务，确保单个任务失败不影响其他任务
+	for i, item := range tasksWithResults {
+		// 开始事务
+		tx := prodDB.Begin()
+
+		// 检查生产数据库中是否已存在相同的 task_uuid
+		var existingTask dao.RecognitionTask
+		err := tx.Where("task_uuid = ?", item.TaskUUID).First(&existingTask).Error
+		if err == nil {
+			log.Printf("[%d/%d] 跳过已存在的任务: task_uuid=%s, id=%d", i+1, len(tasksWithResults), item.TaskUUID, existingTask.ID)
+			tx.Rollback()
+			skipCount++
+			continue
+		}
+		if err != gorm.ErrRecordNotFound {
+			log.Printf("[%d/%d] 检查任务是否存在时出错: task_uuid=%s, error=%v", i+1, len(tasksWithResults), item.TaskUUID, err)
+			tx.Rollback()
+			errorCount++
+			continue
+		}
+
+		// 创建新任务（不指定ID，让数据库自动生成）
+		newTask := &dao.RecognitionTask{
+			UserID:      item.UserID,
+			TaskUUID:    item.TaskUUID,
+			FileName:    item.FileName,
+			FileHash:    item.FileHash,
+			FileURL:     item.FileURL,
+			TaskType:    dao.TaskType(item.TaskType),
+			Status:      dao.TaskStatus(item.Status),
+			CompletedAt: item.CompletedAt,
+			Remark:      item.Remark,
+			IP:          item.IP,
+		}
+		// 保留原始时间戳
+		newTask.CreatedAt = item.TaskCreatedAt
+		newTask.UpdatedAt = item.TaskUpdatedAt
+
+		if err := tx.Create(newTask).Error; err != nil {
+			log.Printf("[%d/%d] 创建任务失败: task_uuid=%s, error=%v", i+1, len(tasksWithResults), item.TaskUUID, err)
+			tx.Rollback()
+			errorCount++
+			continue
+		}
+
+		log.Printf("[%d/%d] 创建任务成功: task_uuid=%s, 新ID=%d", i+1, len(tasksWithResults), item.TaskUUID, newTask.ID)
+
+		// 如果有结果数据，创建结果记录
+		if item.ResultID != nil {
+			// 处理可能为NULL的字段
+			latex := ""
+			if item.Latex != nil {
+				latex = *item.Latex
+			}
+			markdown := ""
+			if item.Markdown != nil {
+				markdown = *item.Markdown
+			}
+			mathml := ""
+			if item.MathML != nil {
+				mathml = *item.MathML
+			}
+
+			newResult := dao.RecognitionResult{
+				TaskID:   newTask.ID, // 使用新任务的ID
+				TaskType: dao.TaskType(item.TaskType),
+				Latex:    latex,
+				Markdown: markdown,
+				MathML:   mathml,
+			}
+			// 保留原始时间戳
+			if item.ResultCreatedAt != nil {
+				newResult.CreatedAt = *item.ResultCreatedAt
+			}
+			if item.ResultUpdatedAt != nil {
+				newResult.UpdatedAt = *item.ResultUpdatedAt
+			}
+
+			if err := tx.Create(&newResult).Error; err != nil {
+				log.Printf("[%d/%d] 创建结果失败: task_id=%d, error=%v", i+1, len(tasksWithResults), newTask.ID, err)
+				tx.Rollback() // 回滚整个事务（包括任务）
+				errorCount++
+				continue
+			}
+
+			log.Printf("[%d/%d] 创建结果成功: task_id=%d", i+1, len(tasksWithResults), newTask.ID)
+		}
+
+		// 提交事务
+		if err := tx.Commit().Error; err != nil {
+			log.Printf("[%d/%d] 提交事务失败: task_uuid=%s, error=%v", i+1, len(tasksWithResults), item.TaskUUID, err)
+			errorCount++
+			continue
+		}
+
+		successCount++
+	}
+
+	log.Printf("迁移完成统计:")
+	log.Printf("  成功: %d 条", successCount)
+	log.Printf("  跳过: %d 条", skipCount)
+	log.Printf("  失败: %d 条", errorCount)
+
+	return nil
+}
+
+// loadDatabaseConfig 从配置文件加载数据库配置
+func loadDatabaseConfig(configPath string) (config.DatabaseConfig, error) {
+	v := viper.New()
+	v.SetConfigFile(configPath)
+	if err := v.ReadInConfig(); err != nil {
+		return config.DatabaseConfig{}, err
+	}
+
+	var dbConfig config.DatabaseConfig
+	if err := v.UnmarshalKey("database", &dbConfig); err != nil {
+		return config.DatabaseConfig{}, err
+	}
+
+	return dbConfig, nil
+}

config/config.go

@@ -1,7 +1,7 @@
 package config
 
 import (
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 	"github.com/spf13/viper"
 )
 
@@ -14,6 +14,19 @@ type Config struct {
 	Limit     LimitConfig       `mapstructure:"limit"`
 	Aliyun    AliyunConfig      `mapstructure:"aliyun"`
 	Mathpix   MathpixConfig     `mapstructure:"mathpix"`
+	BaiduOCR  BaiduOCRConfig    `mapstructure:"baidu_ocr"`
+	Google    GoogleOAuthConfig `mapstructure:"google"`
+}
+
+type BaiduOCRConfig struct {
+	Token string `mapstructure:"token"`
+}
+
+type GoogleOAuthConfig struct {
+	ClientID     string `mapstructure:"client_id"`
+	ClientSecret string `mapstructure:"client_secret"`
+	RedirectURI  string `mapstructure:"redirect_uri"`
+	Proxy        string `mapstructure:"proxy"`
 }
 
 type MathpixConfig struct {

config/config_dev.yaml

@@ -4,8 +4,8 @@ server:
 
 database:
   driver: mysql
-  host: mysql
+  host: localhost
-  port: 3306 
+  port: 3006
   username: root
   password: texpixel#pwd123!
   dbname: doc_ai
@@ -13,7 +13,7 @@ database:
   max_open: 100
 
 redis:
-  addr: redis:6379  
+  addr: localhost:6079
   password: yoge@123321!
   db: 0
 
@@ -30,7 +30,6 @@ log:
   maxBackups: 1 # 保留的旧日志文件最大数量
   compress: false # 是否压缩旧日志
 
-
 aliyun:
   sms:
     access_key_id: "LTAI5tB9ur4ExCF4dYPq7hLz"
@@ -43,8 +42,17 @@ aliyun:
     inner_endpoint: oss-cn-beijing-internal.aliyuncs.com
     access_key_id: LTAI5t8qXhow6NCdYDtu1saF
     access_key_secret: qZ2SwYsNCEBckCVSOszH31yYwXU44A
-    bucket_name: texpixel-doc
+    bucket_name: texpixel-doc1
 
 mathpix:
   app_id: "ocr_eede6f_ea9b5c"
   app_key: "fb72d251e33ac85c929bfd4eec40d78368d08d82fb2ee1cffb04a8bb967d1db5"
+
+baidu_ocr:
+  token: "e3a47bd2438f1f38840c203fc5939d17a54482d1"
+
+google:
+  client_id: "404402221037-nqdsk11bkpk5a7oh396mrg1ieh28u6q1.apps.googleusercontent.com"
+  client_secret: "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"
+  redirect_uri: "https://app.cloud.texpixel.com:10443/auth/google/callback"
+  proxy: "http://localhost:7890"

config/config_prod.yaml

@@ -42,9 +42,17 @@ aliyun:
     inner_endpoint: oss-cn-beijing-internal.aliyuncs.com
     access_key_id: LTAI5t8qXhow6NCdYDtu1saF
     access_key_secret: qZ2SwYsNCEBckCVSOszH31yYwXU44A
-    bucket_name: texpixel-doc
+    bucket_name: texpixel-doc1
-
 
 mathpix:
   app_id: "ocr_eede6f_ea9b5c"
   app_key: "fb72d251e33ac85c929bfd4eec40d78368d08d82fb2ee1cffb04a8bb967d1db5"
+
+baidu_ocr:
+  token: "e3a47bd2438f1f38840c203fc5939d17a54482d1"
+
+google:
+  client_id: "404402221037-nqdsk11bkpk5a7oh396mrg1ieh28u6q1.apps.googleusercontent.com"
+  client_secret: "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"
+  redirect_uri: "https://texpixel.com/auth/google/callback"
+  proxy: "http://100.115.184.74:7890"

deploy_dev.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+
+git push origin test
+
+ssh ubuntu << 'ENDSSH'
+cd /home/yoge/Dev/doc_ai_backed
+git checkout test
+git pull origin test
+docker compose -f docker-compose.infra.yml up -d
+docker compose down
+docker image rm doc_ai_backed-doc_ai:latest
+docker compose up -d
+ENDSSH

deploy_prod.sh

@@ -0,0 +1,10 @@
+#!/bin/bash
+
+docker build -t crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/doc_ai_backend:latest . && docker push crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/doc_ai_backend:latest
+
+ssh ecs << 'ENDSSH'
+docker stop doc_ai doc_ai_backend 2>/dev/null || true
+docker rm doc_ai doc_ai_backend 2>/dev/null || true
+docker pull crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/doc_ai_backend:latest
+docker run -d --name doc_ai -p 8024:8024 --restart unless-stopped crpi-8s2ierii2xan4klg.cn-beijing.personal.cr.aliyuncs.com/texpixel/doc_ai_backend:latest -env=prod
+ENDSSH

docker-compose.infra.yml

@@ -0,0 +1,32 @@
+services:
+  mysql:
+    image: mysql:8.0
+    container_name: mysql
+    environment:
+      MYSQL_ROOT_PASSWORD: texpixel#pwd123!
+      MYSQL_DATABASE: doc_ai
+      MYSQL_USER: texpixel
+      MYSQL_PASSWORD: texpixel#pwd123!
+    ports:
+      - "3006:3306"
+    volumes:
+      - mysql_data:/var/lib/mysql
+    healthcheck:
+      test: ["CMD", "mysqladmin", "ping", "-h", "localhost", "-uroot", "-ptexpixel#pwd123!"]
+      interval: 5s
+      timeout: 5s
+      retries: 10
+      start_period: 30s
+    restart: always
+
+  redis:
+    image: redis:latest
+    container_name: redis
+    command: redis-server --requirepass "yoge@123321!"
+    ports:
+      - "6079:6379"
+    restart: always
+
+volumes:
+  mysql_data:
+    driver: local

docker-compose.yml

@@ -2,58 +2,9 @@ services:
   doc_ai:
     build: .
     container_name: doc_ai
-    ports:
+    network_mode: host
-      - "8024:8024"
     volumes:
       - ./config:/app/config
       - ./logs:/app/logs
-    networks:
-      - backend
-    depends_on:
-      mysql:
-        condition: service_healthy
-      redis:
-        condition: service_started
     command: ["-env", "dev"]
     restart: always
-
-  mysql:
-    image: mysql:8.0
-    container_name: mysql
-    environment:
-      MYSQL_ROOT_PASSWORD: texpixel#pwd123!
-      MYSQL_DATABASE: doc_ai
-      MYSQL_USER: texpixel
-      MYSQL_PASSWORD: texpixel#pwd123!
-    ports:
-      - "3006:3306"
-    volumes:
-      - mysql_data:/var/lib/mysql
-    networks:
-      - backend
-    healthcheck:
-      test: ["CMD", "mysqladmin", "ping", "-h", "localhost", "-uroot", "-ptexpixel#pwd123!"]
-      interval: 5s
-      timeout: 5s
-      retries: 10
-      start_period: 30s
-    restart: always
-
-  redis:
-    image: redis:latest
-    container_name: redis
-    command: redis-server --requirepass "yoge@123321!"
-    ports:
-      - "6079:6379"
-    networks:
-      - backend
-    restart: always
-
-volumes:
-  mysql_data:
-    # 持久化MySQL数据卷
-    driver: local
-
-networks:
-  backend:
-    driver: bridge

go.mod

@@ -1,4 +1,4 @@
-module gitea.com/bitwsd/document_ai
+module gitea.com/texpixel/document_ai
 
 go 1.20
 
@@ -11,18 +11,21 @@ require (
 	github.com/dgrijalva/jwt-go v3.2.0+incompatible
 	github.com/gin-gonic/gin v1.10.0
 	github.com/google/uuid v1.6.0
+	github.com/jtolds/gls v4.20.0+incompatible
 	github.com/redis/go-redis/v9 v9.7.0
 	github.com/rs/zerolog v1.33.0
 	github.com/spf13/viper v1.19.0
 	golang.org/x/crypto v0.23.0
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1
+	gorm.io/datatypes v1.2.7
 	gorm.io/driver/mysql v1.5.7
-	gorm.io/gorm v1.25.12
+	gorm.io/gorm v1.30.0
 )
 
-require github.com/go-sql-driver/mysql v1.7.0 // indirect
+require github.com/go-sql-driver/mysql v1.8.1 // indirect
 
 require (
+	filippo.io/edwards25519 v1.1.0 // indirect
 	github.com/alibabacloud-go/alibabacloud-gateway-spi v0.0.4 // indirect
 	github.com/alibabacloud-go/debug v0.0.0-20190504072949-9472017b5c68 // indirect
 	github.com/alibabacloud-go/endpoint-util v1.1.0 // indirect
@@ -43,6 +46,7 @@ require (
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-playground/validator/v10 v10.20.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
+	github.com/gopherjs/gopherjs v0.0.0-20200217142428-fce0ec30dd00 // indirect
 	github.com/hashicorp/hcl v1.0.0 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
@@ -72,7 +76,7 @@ require (
 	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
 	golang.org/x/net v0.25.0 // indirect
 	golang.org/x/sys v0.20.0 // indirect
-	golang.org/x/text v0.15.0 // indirect
+	golang.org/x/text v0.20.0 // indirect
 	golang.org/x/time v0.5.0 // indirect
 	google.golang.org/protobuf v1.34.1 // indirect
 	gopkg.in/ini.v1 v1.67.0 // indirect

go.sum

@@ -1,3 +1,5 @@
+filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
+filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
 github.com/alibabacloud-go/alibabacloud-gateway-spi v0.0.4 h1:iC9YFYKDGEy3n/FtqJnOkZsene9olVspKmkX5A2YBEo=
 github.com/alibabacloud-go/alibabacloud-gateway-spi v0.0.4/go.mod h1:sCavSAvdzOjul4cEqeVtvlSaSScfNsTQ+46HwlTL1hc=
 github.com/alibabacloud-go/darabonba-openapi v0.1.18/go.mod h1:PB4HffMhJVmAgNKNq3wYbTUlFvPgxJpTzd1F5pTuUsc=
@@ -69,19 +71,27 @@ github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJn
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
 github.com/go-playground/validator/v10 v10.20.0 h1:K9ISHbSaI0lyB2eWMPJo+kOS/FBExVwjEviJTixqxL8=
 github.com/go-playground/validator/v10 v10.20.0/go.mod h1:dbuPbCMFw/DrkbEynArYaCwl3amGuJotoKCe95atGMM=
-github.com/go-sql-driver/mysql v1.7.0 h1:ueSltNNllEqE3qcWBTD0iQd3IpL/6U+mJxLkazJ7YPc=
 github.com/go-sql-driver/mysql v1.7.0/go.mod h1:OXbVy3sEdcQ2Doequ6Z5BW6fXNQTmx+9S1MCJN5yJMI=
+github.com/go-sql-driver/mysql v1.8.1 h1:LedoTUt/eveggdHS9qUFC1EFSa8bU2+1pZjSRpvNJ1Y=
+github.com/go-sql-driver/mysql v1.8.1/go.mod h1:wEBSXgmK//2ZFJyE+qWnIsVGmvmEKlqwuVSjsCm7DZg=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
+github.com/golang-sql/civil v0.0.0-20220223132316-b832511892a9 h1:au07oEsX2xN0ktxqI+Sida1w446QrXBRJ0nee3SNZlA=
+github.com/golang-sql/sqlexp v0.1.0 h1:ZCD6MBpcuOVfGVqsEmY5/4FtYiKz6tSyUv9LPEDei6A=
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/gopherjs/gopherjs v0.0.0-20181017120253-0766667cb4d1/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
+github.com/gopherjs/gopherjs v0.0.0-20200217142428-fce0ec30dd00 h1:l5lAOZEym3oK3SQ2HBHWsJUfbNBiTXJDeW2QDxw9AQ0=
 github.com/gopherjs/gopherjs v0.0.0-20200217142428-fce0ec30dd00/go.mod h1:wJfORRmW1u3UXTncJ5qlYoELFm8eSnnEO6hX4iZ3EWY=
 github.com/hashicorp/hcl v1.0.0 h1:0Anlzjpi4vEasTeNFn2mLJgTSwt0+6sfsiTG8qcWGx4=
 github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
+github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
+github.com/jackc/pgservicefile v0.0.0-20231201235250-de7065d80cb9 h1:L0QtFUgDarD7Fpv9jeVMgy/+Ec0mtnmYuImjTz6dtDA=
+github.com/jackc/pgx/v5 v5.5.5 h1:amBjrZVmksIdNjxGW/IiIMzxMKZFelXbUoPNb+8sjQw=
+github.com/jackc/puddle/v2 v2.2.1 h1:RhxXJtFG022u4ibrCSMSiu5aOq1i77R3OHKNJj77OAk=
 github.com/jinzhu/inflection v1.0.0 h1:K317FqzuhWc8YvSVlFMCCUb36O/S9MCKRDI7QkRKD/E=
 github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
 github.com/jinzhu/now v1.1.5 h1:/o9tlHleP7gOFmsnYNz3RGnqzefHA47wQpKrrdTIwXQ=
@@ -89,6 +99,7 @@ github.com/jinzhu/now v1.1.5/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/
 github.com/json-iterator/go v1.1.10/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/jtolds/gls v4.20.0+incompatible h1:xdiiI2gbIgH/gLH7ADydsJ1uDOEzR8yvV7C0MuV77Wo=
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
 github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
 github.com/klauspost/cpuid/v2 v2.2.7 h1:ZWSB3igEs+d0qvnxR/ZBzXVmxkgt8DdzP6m9pfuVLDM=
@@ -108,6 +119,8 @@ github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/
 github.com/mattn/go-isatty v0.0.19/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
 github.com/mattn/go-isatty v0.0.20 h1:xfD0iDuEKnDkl03q4limB+vH+GxLEtL/jb4xVJSWWEY=
 github.com/mattn/go-isatty v0.0.20/go.mod h1:W+V8PltTTMOvKvAeJH7IuucS94S2C6jfK/D7dTCTo3Y=
+github.com/mattn/go-sqlite3 v1.14.15 h1:vfoHhTN1af61xCRSWzFIWzx2YskyMTwHLrExkBOjvxI=
+github.com/microsoft/go-mssqldb v1.7.2 h1:CHkFJiObW7ItKTJfHo1QX7QBBD1iV+mn1eOyRP3b/PA=
 github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
 github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
@@ -197,6 +210,7 @@ golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20200317015054-43a5402ce75a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.9.0 h1:fEo0HyrW1GIgZdpbhCRO0PkJajUS5H9IFUztCgEo2jQ=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -209,8 +223,8 @@ golang.org/x/sys v0.20.0 h1:Od9JTbYCk261bKm4M/mw7AklTlFYIa0bIp9BgSm1S8Y=
 golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
-golang.org/x/text v0.15.0 h1:h1V/4gjBv8v9cjcR6+AR5+/cIYK5N/WAgiv4xlsEtAk=
+golang.org/x/text v0.20.0 h1:gK/Kv2otX8gz+wn7Rmb3vT96ZwuoxnQlY+HlJVj7Qug=
-golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/text v0.20.0/go.mod h1:D4IsuqiFMhST5bX19pQ9ikHC2GsaKyk/oF+pn3ducp4=
 golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
 golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -235,10 +249,15 @@ gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gorm.io/datatypes v1.2.7 h1:ww9GAhF1aGXZY3EB3cJPJ7//JiuQo7DlQA7NNlVaTdk=
+gorm.io/datatypes v1.2.7/go.mod h1:M2iO+6S3hhi4nAyYe444Pcb0dcIiOMJ7QHaUXxyiNZY=
 gorm.io/driver/mysql v1.5.7 h1:MndhOPYOfEp2rHKgkZIhJ16eVUIRf2HmzgoPmh7FCWo=
 gorm.io/driver/mysql v1.5.7/go.mod h1:sEtPWMiqiN1N1cMXoXmBbd8C6/l+TESwriotuRRpkDM=
+gorm.io/driver/postgres v1.5.0 h1:u2FXTy14l45qc3UeCJ7QaAXZmZfDDv0YrthvmRq1l0U=
+gorm.io/driver/sqlite v1.4.3 h1:HBBcZSDnWi5BW3B3rwvVTc510KGkBkexlOg0QrmLUuU=
+gorm.io/driver/sqlserver v1.6.0 h1:VZOBQVsVhkHU/NzNhRJKoANt5pZGQAS1Bwc6m6dgfnc=
 gorm.io/gorm v1.25.7/go.mod h1:hbnx/Oo0ChWMn1BIhpy1oYozzpM15i4YPuHDmfYtwg8=
-gorm.io/gorm v1.25.12 h1:I0u8i2hWQItBq1WfE0o2+WuL9+8L21K9e2HHSTE/0f8=
+gorm.io/gorm v1.30.0 h1:qbT5aPv1UH8gI99OsRlvDToLxW5zR7FzS9acZDOZcgs=
-gorm.io/gorm v1.25.12/go.mod h1:xh7N7RHfYlNc5EmcI/El95gXusucDrQnHXe0+CgWcLQ=
+gorm.io/gorm v1.30.0/go.mod h1:8Z33v652h4//uMA76KjeDH8mJXPm1QNCYrMeatR0DOE=
 nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50=
 rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=

internal/model/analytics/request.go

@@ -0,0 +1,34 @@
+package analytics
+
+import "time"
+
+// TrackEventRequest 埋点事件请求
+type TrackEventRequest struct {
+	TaskNo     string                 `json:"task_no" binding:"required"`
+	UserID     int64                  `json:"user_id"`
+	EventName  string                 `json:"event_name" binding:"required"`
+	Properties map[string]interface{} `json:"properties"`
+	DeviceInfo map[string]interface{} `json:"device_info"`
+	MetaData   map[string]interface{} `json:"meta_data"`
+}
+
+// BatchTrackEventRequest 批量埋点事件请求
+type BatchTrackEventRequest struct {
+	Events []TrackEventRequest `json:"events" binding:"required,min=1,max=100"`
+}
+
+// QueryEventsRequest 查询事件请求
+type QueryEventsRequest struct {
+	UserID    *int64     `json:"user_id" form:"user_id"`
+	EventName string     `json:"event_name" form:"event_name"`
+	StartTime *time.Time `json:"start_time" form:"start_time"`
+	EndTime   *time.Time `json:"end_time" form:"end_time"`
+	Page      int        `json:"page" form:"page" binding:"required,min=1"`
+	PageSize  int        `json:"page_size" form:"page_size" binding:"required,min=1,max=100"`
+}
+
+// EventStatsRequest 事件统计请求
+type EventStatsRequest struct {
+	StartTime time.Time `json:"start_time" form:"start_time" binding:"required"`
+	EndTime   time.Time `json:"end_time" form:"end_time" binding:"required"`
+}

internal/model/analytics/response.go

@@ -0,0 +1,36 @@
+package analytics
+
+import "time"
+
+// EventResponse 事件响应
+type EventResponse struct {
+	ID         int64                  `json:"id"`
+	UserID     int64                  `json:"user_id"`
+	EventName  string                 `json:"event_name"`
+	Properties map[string]interface{} `json:"properties"`
+	DeviceInfo map[string]interface{} `json:"device_info"`
+	MetaData   map[string]interface{} `json:"meta_data"`
+	CreatedAt  time.Time              `json:"created_at"`
+}
+
+// EventListResponse 事件列表响应
+type EventListResponse struct {
+	Events []*EventResponse `json:"events"`
+	Total  int64            `json:"total"`
+	Page   int              `json:"page"`
+	Size   int              `json:"size"`
+}
+
+// EventStatsResponse 事件统计响应
+type EventStatsResponse struct {
+	EventName   string `json:"event_name"`
+	Count       int64  `json:"count"`
+	UniqueUsers int64  `json:"unique_users"`
+}
+
+// EventStatsListResponse 事件统计列表响应
+type EventStatsListResponse struct {
+	Stats     []*EventStatsResponse `json:"stats"`
+	StartTime time.Time             `json:"start_time"`
+	EndTime   time.Time             `json:"end_time"`
+}

internal/model/formula/response.go

@@ -12,13 +12,18 @@ type GetFormulaTaskResponse struct {
 	Latex    string `json:"latex"`
 	Markdown string `json:"markdown"`
 	MathML   string `json:"mathml"`
-	MathMLMW  string `json:"mathml_mw"`
+	MML      string `json:"mml"`
-	ImageBlob string `json:"image_blob"`
-	DocxURL   string `json:"docx_url"`
-	PDFURL    string `json:"pdf_url"`
 }
 
 // FormulaRecognitionResponse 公式识别服务返回的响应
 type FormulaRecognitionResponse struct {
 	Result string `json:"result"`
 }
+
+// ImageOCRResponse 图片OCR接口返回的响应
+type ImageOCRResponse struct {
+	Markdown string `json:"markdown"` // Markdown 格式内容
+	Latex    string `json:"latex"`    // LaTeX 格式内容 (无公式时为空)
+	MathML   string `json:"mathml"`   // MathML 格式（无公式时为空）
+	MML      string `json:"mml"`      // MML 格式（无公式时为空）
+}

internal/model/task/request.go

@@ -24,13 +24,15 @@ type TaskListDTO struct {
 	Latex     string `json:"latex"`
 	Markdown  string `json:"markdown"`
 	MathML    string `json:"mathml"`
-	MathMLMW  string `json:"mathml_mw"`
+	MML       string `json:"mml"`
-	ImageBlob string `json:"image_blob"`
-	DocxURL   string `json:"docx_url"`
-	PDFURL    string `json:"pdf_url"`
 }
 
 type TaskListResponse struct {
 	TaskList []*TaskListDTO `json:"task_list"`
 	Total    int64          `json:"total"`
 }
+
+type ExportTaskRequest struct {
+	TaskNo string `json:"task_no" binding:"required"`
+	Type   string `json:"type" binding:"required,oneof=pdf docx"`
+}

internal/model/user/user.go

@@ -20,8 +20,7 @@ type PhoneLoginResponse struct {
 
 type UserInfoResponse struct {
 	Username string `json:"username"`
-	Phone    string `json:"phone"`
+	Email    string `json:"email"`
-	Status   int    `json:"status"` // 0: not login, 1: login
 }
 
 type EmailRegisterRequest struct {
@@ -43,3 +42,31 @@ type EmailLoginResponse struct {
 	Token     string `json:"token"`
 	ExpiresAt int64  `json:"expires_at"`
 }
+
+type GoogleAuthUrlRequest struct {
+	RedirectURI string `form:"redirect_uri" binding:"required"`
+	State       string `form:"state" binding:"required"`
+}
+
+type GoogleAuthUrlResponse struct {
+	AuthURL string `json:"auth_url"`
+}
+
+type GoogleOAuthCallbackRequest struct {
+	Code        string `json:"code" binding:"required"`
+	State       string `json:"state" binding:"required"`
+	RedirectURI string `json:"redirect_uri" binding:"required"`
+}
+
+type GoogleOAuthCallbackResponse struct {
+	Token     string `json:"token"`
+	ExpiresAt int64  `json:"expires_at"`
+}
+
+type GoogleUserInfo struct {
+	ID            string `json:"id"`
+	Email         string `json:"email"`
+	Name          string `json:"name"`
+	Picture       string `json:"picture"`
+	VerifiedEmail bool   `json:"verified_email"`
+}

internal/service/analytics_service.go

@@ -0,0 +1,232 @@
+package service
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"time"
+
+	"gitea.com/texpixel/document_ai/internal/model/analytics"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/pkg/log"
+	"gorm.io/datatypes"
+)
+
+type AnalyticsService struct {
+	eventDao *dao.AnalyticsEventDao
+}
+
+func NewAnalyticsService() *AnalyticsService {
+	return &AnalyticsService{
+		eventDao: dao.NewAnalyticsEventDao(),
+	}
+}
+
+// TrackEvent 记录单个事件
+func (s *AnalyticsService) TrackEvent(ctx context.Context, req *analytics.TrackEventRequest) error {
+	// 将 map 转换为 JSON
+	propertiesJSON, err := json.Marshal(req.Properties)
+	if err != nil {
+		log.Error(ctx, "marshal properties failed", "error", err)
+		return fmt.Errorf("invalid properties format")
+	}
+
+	deviceInfoJSON, err := json.Marshal(req.DeviceInfo)
+	if err != nil {
+		log.Error(ctx, "marshal device_info failed", "error", err)
+		return fmt.Errorf("invalid device_info format")
+	}
+
+	metaDataJSON, err := json.Marshal(req.MetaData)
+	if err != nil {
+		log.Error(ctx, "marshal meta_data failed", "error", err)
+		return fmt.Errorf("invalid meta_data format")
+	}
+
+	event := &dao.AnalyticsEvent{
+		UserID:     req.UserID,
+		EventName:  req.EventName,
+		Properties: datatypes.JSON(propertiesJSON),
+		DeviceInfo: datatypes.JSON(deviceInfoJSON),
+		MetaData:   datatypes.JSON(metaDataJSON),
+		CreatedAt:  time.Now(),
+	}
+
+	if err := s.eventDao.Create(dao.DB.WithContext(ctx), event); err != nil {
+		log.Error(ctx, "create analytics event failed", "error", err)
+		return fmt.Errorf("failed to track event")
+	}
+
+	log.Info(ctx, "event tracked successfully",
+		"event_id", event.ID,
+		"user_id", req.UserID,
+		"event_name", req.EventName)
+
+	return nil
+}
+
+// BatchTrackEvents 批量记录事件
+func (s *AnalyticsService) BatchTrackEvents(ctx context.Context, req *analytics.BatchTrackEventRequest) error {
+	events := make([]*dao.AnalyticsEvent, 0, len(req.Events))
+
+	for _, eventReq := range req.Events {
+		propertiesJSON, err := json.Marshal(eventReq.Properties)
+		if err != nil {
+			log.Error(ctx, "marshal properties failed", "error", err)
+			continue
+		}
+
+		deviceInfoJSON, err := json.Marshal(eventReq.DeviceInfo)
+		if err != nil {
+			log.Error(ctx, "marshal device_info failed", "error", err)
+			continue
+		}
+
+		metaDataJSON, err := json.Marshal(eventReq.MetaData)
+		if err != nil {
+			log.Error(ctx, "marshal meta_data failed", "error", err)
+			continue
+		}
+
+		event := &dao.AnalyticsEvent{
+			UserID:     eventReq.UserID,
+			EventName:  eventReq.EventName,
+			Properties: datatypes.JSON(propertiesJSON),
+			DeviceInfo: datatypes.JSON(deviceInfoJSON),
+			MetaData:   datatypes.JSON(metaDataJSON),
+			CreatedAt:  time.Now(),
+		}
+		events = append(events, event)
+	}
+
+	if len(events) == 0 {
+		return fmt.Errorf("no valid events to track")
+	}
+
+	if err := s.eventDao.BatchCreate(dao.DB.WithContext(ctx), events); err != nil {
+		log.Error(ctx, "batch create analytics events failed", "error", err)
+		return fmt.Errorf("failed to batch track events")
+	}
+
+	log.Info(ctx, "batch events tracked successfully", "count", len(events))
+	return nil
+}
+
+// QueryEvents 查询事件
+func (s *AnalyticsService) QueryEvents(ctx context.Context, req *analytics.QueryEventsRequest) (*analytics.EventListResponse, error) {
+	var events []*dao.AnalyticsEvent
+	var total int64
+	var err error
+
+	// 根据不同条件查询
+	if req.UserID != nil && req.EventName != "" {
+		// 查询用户的指定事件
+		events, total, err = s.eventDao.GetUserEventsByName(dao.DB.WithContext(ctx), *req.UserID, req.EventName, req.Page, req.PageSize)
+	} else if req.UserID != nil {
+		// 查询用户的所有事件
+		events, total, err = s.eventDao.GetUserEvents(dao.DB.WithContext(ctx), *req.UserID, req.Page, req.PageSize)
+	} else if req.EventName != "" {
+		// 查询指定事件
+		events, total, err = s.eventDao.GetEventsByName(dao.DB.WithContext(ctx), req.EventName, req.Page, req.PageSize)
+	} else if req.StartTime != nil && req.EndTime != nil {
+		// 查询时间范围内的事件
+		events, total, err = s.eventDao.GetEventsByTimeRange(dao.DB.WithContext(ctx), *req.StartTime, *req.EndTime, req.Page, req.PageSize)
+	} else {
+		return nil, fmt.Errorf("invalid query parameters")
+	}
+
+	if err != nil {
+		log.Error(ctx, "query events failed", "error", err)
+		return nil, fmt.Errorf("failed to query events")
+	}
+
+	// 转换为响应格式
+	eventResponses := make([]*analytics.EventResponse, 0, len(events))
+	for _, event := range events {
+		var properties, deviceInfo, metaData map[string]interface{}
+
+		if len(event.Properties) > 0 {
+			json.Unmarshal(event.Properties, &properties)
+		}
+		if len(event.DeviceInfo) > 0 {
+			json.Unmarshal(event.DeviceInfo, &deviceInfo)
+		}
+		if len(event.MetaData) > 0 {
+			json.Unmarshal(event.MetaData, &metaData)
+		}
+
+		eventResponses = append(eventResponses, &analytics.EventResponse{
+			ID:         event.ID,
+			UserID:     event.UserID,
+			EventName:  event.EventName,
+			Properties: properties,
+			DeviceInfo: deviceInfo,
+			MetaData:   metaData,
+			CreatedAt:  event.CreatedAt,
+		})
+	}
+
+	return &analytics.EventListResponse{
+		Events: eventResponses,
+		Total:  total,
+		Page:   req.Page,
+		Size:   req.PageSize,
+	}, nil
+}
+
+// GetEventStats 获取事件统计
+func (s *AnalyticsService) GetEventStats(ctx context.Context, req *analytics.EventStatsRequest) (*analytics.EventStatsListResponse, error) {
+	results, err := s.eventDao.GetEventStats(dao.DB.WithContext(ctx), req.StartTime, req.EndTime)
+	if err != nil {
+		log.Error(ctx, "get event stats failed", "error", err)
+		return nil, fmt.Errorf("failed to get event stats")
+	}
+
+	stats := make([]*analytics.EventStatsResponse, 0, len(results))
+	for _, result := range results {
+		stats = append(stats, &analytics.EventStatsResponse{
+			EventName:   result["event_name"].(string),
+			Count:       result["count"].(int64),
+			UniqueUsers: result["unique_users"].(int64),
+		})
+	}
+
+	return &analytics.EventStatsListResponse{
+		Stats:     stats,
+		StartTime: req.StartTime,
+		EndTime:   req.EndTime,
+	}, nil
+}
+
+// CountUserEvents 统计用户事件数量
+func (s *AnalyticsService) CountUserEvents(ctx context.Context, userID int64) (int64, error) {
+	count, err := s.eventDao.CountUserEvents(dao.DB.WithContext(ctx), userID)
+	if err != nil {
+		log.Error(ctx, "count user events failed", "error", err, "user_id", userID)
+		return 0, fmt.Errorf("failed to count user events")
+	}
+	return count, nil
+}
+
+// CountEventsByName 统计指定事件的数量
+func (s *AnalyticsService) CountEventsByName(ctx context.Context, eventName string) (int64, error) {
+	count, err := s.eventDao.CountEventsByName(dao.DB.WithContext(ctx), eventName)
+	if err != nil {
+		log.Error(ctx, "count events by name failed", "error", err, "event_name", eventName)
+		return 0, fmt.Errorf("failed to count events")
+	}
+	return count, nil
+}
+
+// CleanOldEvents 清理旧数据（可以定时执行）
+func (s *AnalyticsService) CleanOldEvents(ctx context.Context, retentionDays int) error {
+	beforeTime := time.Now().AddDate(0, 0, -retentionDays)
+
+	if err := s.eventDao.DeleteOldEvents(dao.DB.WithContext(ctx), beforeTime); err != nil {
+		log.Error(ctx, "clean old events failed", "error", err, "before_time", beforeTime)
+		return fmt.Errorf("failed to clean old events")
+	}
+
+	log.Info(ctx, "old events cleaned successfully", "retention_days", retentionDays)
+	return nil
+}

internal/service/recognition_service.go

@@ -7,21 +7,23 @@ import (
 	"encoding/json"
 	"fmt"
 	"io"
+	"mime/multipart"
 	"net/http"
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
-	"gitea.com/bitwsd/document_ai/internal/model/formula"
+	"gitea.com/texpixel/document_ai/internal/model/formula"
-	"gitea.com/bitwsd/document_ai/internal/storage/cache"
+	"gitea.com/texpixel/document_ai/internal/storage/cache"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/constant"
+	"gitea.com/texpixel/document_ai/pkg/constant"
-	"gitea.com/bitwsd/document_ai/pkg/httpclient"
+	"gitea.com/texpixel/document_ai/pkg/httpclient"
-	"gitea.com/bitwsd/document_ai/pkg/oss"
+	"gitea.com/texpixel/document_ai/pkg/oss"
-	"gitea.com/bitwsd/document_ai/pkg/utils"
+	"gitea.com/texpixel/document_ai/pkg/requestid"
+	"gitea.com/texpixel/document_ai/pkg/utils"
 	"gorm.io/gorm"
 )
 
@@ -178,6 +180,7 @@ func (s *RecognitionService) GetFormualTask(ctx context.Context, taskNo string)
 		Latex:    taskRet.Latex,
 		Markdown: markdown,
 		MathML:   taskRet.MathML,
+		MML:      taskRet.MML,
 		Status:   int(task.Status),
 	}, nil
 }
@@ -379,6 +382,44 @@ type MathpixErrorInfo struct {
 	Message string `json:"message"`
 }
 
+// BaiduOCRRequest 百度 OCR 版面分析请求结构
+type BaiduOCRRequest struct {
+	// 文件内容 base64 编码
+	File string `json:"file"`
+	// 文件类型: 0=PDF, 1=图片
+	FileType int `json:"fileType"`
+	// 是否启用文档方向分类
+	UseDocOrientationClassify bool `json:"useDocOrientationClassify"`
+	// 是否启用文档扭曲矫正
+	UseDocUnwarping bool `json:"useDocUnwarping"`
+	// 是否启用图表识别
+	UseChartRecognition bool `json:"useChartRecognition"`
+}
+
+// BaiduOCRResponse 百度 OCR 版面分析响应结构
+type BaiduOCRResponse struct {
+	ErrorCode int             `json:"errorCode"`
+	ErrorMsg  string          `json:"errorMsg"`
+	Result    *BaiduOCRResult `json:"result"`
+}
+
+// BaiduOCRResult 百度 OCR 响应结果
+type BaiduOCRResult struct {
+	LayoutParsingResults []BaiduLayoutParsingResult `json:"layoutParsingResults"`
+}
+
+// BaiduLayoutParsingResult 单页版面解析结果
+type BaiduLayoutParsingResult struct {
+	Markdown     BaiduMarkdownResult `json:"markdown"`
+	OutputImages map[string]string   `json:"outputImages"`
+}
+
+// BaiduMarkdownResult markdown 结果
+type BaiduMarkdownResult struct {
+	Text   string            `json:"text"`
+	Images map[string]string `json:"images"`
+}
+
 // GetMathML 从响应中获取MathML
 func (r *MathpixResponse) GetMathML() string {
 	for _, item := range r.Data {
@@ -472,8 +513,8 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	// 设置Content-Type头为application/json
 	headers := map[string]string{"Content-Type": "application/json", utils.RequestIDHeaderKey: utils.GetRequestIDFromContext(ctx)}
 
-	// 发送请求时会使用带超时的context
+	// 发送请求到新的 OCR 接口
-	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, "https://cloud.texpixel.com:10443/vlm/formula/predict", bytes.NewReader(jsonData), headers)
+	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, "https://cloud.texpixel.com:10443/doc_process/v1/image/ocr", bytes.NewReader(jsonData), headers)
 	if err != nil {
 		if ctx.Err() == context.DeadlineExceeded {
 			log.Error(ctx, "func", "processFormulaTask", "msg", "请求超时")
@@ -493,12 +534,19 @@ func (s *RecognitionService) processFormulaTask(ctx context.Context, taskID int6
 	log.Info(ctx, "func", "processFormulaTask", "msg", "响应内容", "body", body.String())
 
 	// 解析 JSON 响应
-	var formulaResp formula.FormulaRecognitionResponse
+	var ocrResp formula.ImageOCRResponse
-	if err := json.Unmarshal(body.Bytes(), &formulaResp); err != nil {
+	if err := json.Unmarshal(body.Bytes(), &ocrResp); err != nil {
 		log.Error(ctx, "func", "processFormulaTask", "msg", "解析响应JSON失败", "error", err)
 		return err
 	}
-	err = resultDao.Create(tx, dao.RecognitionResult{TaskID: taskID, TaskType: dao.TaskTypeFormula, Latex: formulaResp.Result})
+	err = resultDao.Create(tx, dao.RecognitionResult{
+		TaskID:   taskID,
+		TaskType: dao.TaskTypeFormula,
+		Latex:    ocrResp.Latex,
+		Markdown: ocrResp.Markdown,
+		MathML:   ocrResp.MathML,
+		MML:      ocrResp.MML,
+	})
 	if err != nil {
 		log.Error(ctx, "func", "processFormulaTask", "msg", "保存任务结果失败", "error", err)
 		return err
@@ -608,21 +656,20 @@ func (s *RecognitionService) processVLFormulaTask(ctx context.Context, taskID in
 	}
 
 	resultDao := dao.NewRecognitionResultDao()
-	var formulaRes *dao.RecognitionResult
 	result, err := resultDao.GetByTaskID(dao.DB.WithContext(ctx), taskID)
 	if err != nil {
 		log.Error(ctx, "func", "processVLFormulaTask", "msg", "获取任务结果失败", "error", err)
 		return err
 	}
 	if result == nil {
-		formulaRes = &dao.RecognitionResult{TaskID: taskID, TaskType: dao.TaskTypeFormula, Latex: latex}
+		formulaRes := &dao.RecognitionResult{TaskID: taskID, TaskType: dao.TaskTypeFormula, Latex: latex}
 		err = resultDao.Create(dao.DB.WithContext(ctx), *formulaRes)
 		if err != nil {
 			log.Error(ctx, "func", "processVLFormulaTask", "msg", "创建任务结果失败", "error", err)
 			return err
 		}
 	} else {
-		formulaRes.Latex = latex
+		result.Latex = latex
 		err = resultDao.Update(dao.DB.WithContext(ctx), result.ID, map[string]interface{}{"latex": latex})
 		if err != nil {
 			log.Error(ctx, "func", "processVLFormulaTask", "msg", "更新任务结果失败", "error", err)
@@ -667,15 +714,19 @@ func (s *RecognitionService) processOneTask(ctx context.Context) {
 	}
 
 	ctx = context.WithValue(ctx, utils.RequestIDKey, task.TaskUUID)
+
+	// 使用 gls 设置 request_id，确保在整个任务处理过程中可用
+	requestid.SetRequestID(task.TaskUUID, func() {
 		log.Info(ctx, "func", "processFormulaQueue", "msg", "获取任务成功", "task_id", taskID)
 
-	err = s.processMathpixTask(ctx, taskID, task.FileURL)
+		err = s.processFormulaTask(ctx, taskID, task.FileURL)
 		if err != nil {
 			log.Error(ctx, "func", "processFormulaQueue", "msg", "处理任务失败", "error", err)
 			return
 		}
 
 		log.Info(ctx, "func", "processFormulaQueue", "msg", "处理任务成功", "task_id", taskID)
+	})
 }
 
 // processMathpixTask 使用 Mathpix API 处理公式识别任务（用于增强识别）
@@ -738,6 +789,10 @@ func (s *RecognitionService) processMathpixTask(ctx context.Context, taskID int6
 
 	endpoint := "https://api.mathpix.com/v3/text"
 
+	startTime := time.Now()
+
+	log.Info(ctx, "func", "processMathpixTask", "msg", "MathpixApi_Start", "start_time", startTime)
+
 	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, endpoint, bytes.NewReader(jsonData), headers)
 	if err != nil {
 		log.Error(ctx, "func", "processMathpixTask", "msg", "Mathpix API 请求失败", "error", err)
@@ -745,6 +800,8 @@ func (s *RecognitionService) processMathpixTask(ctx context.Context, taskID int6
 	}
 	defer resp.Body.Close()
 
+	log.Info(ctx, "func", "processMathpixTask", "msg", "MathpixApi_End", "end_time", time.Now(), "duration", time.Since(startTime))
+
 	body := &bytes.Buffer{}
 	if _, err = body.ReadFrom(resp.Body); err != nil {
 		log.Error(ctx, "func", "processMathpixTask", "msg", "读取响应体失败", "error", err)
@@ -790,6 +847,8 @@ func (s *RecognitionService) processMathpixTask(ctx context.Context, taskID int6
 		return err
 	}
 
+	log.Info(ctx, "func", "processMathpixTask", "msg", "saveLog", "end_time", time.Now(), "duration", time.Since(startTime))
+
 	if result == nil {
 		// 创建新结果
 		err = resultDao.Create(dao.DB.WithContext(ctx), dao.RecognitionResult{
@@ -820,6 +879,182 @@ func (s *RecognitionService) processMathpixTask(ctx context.Context, taskID int6
 	return nil
 }
 
+func (s *RecognitionService) processBaiduOCRTask(ctx context.Context, taskID int64, fileURL string) error {
+	isSuccess := false
+	logDao := dao.NewRecognitionLogDao()
+
+	defer func() {
+		if !isSuccess {
+			err := dao.NewRecognitionTaskDao().Update(dao.DB.WithContext(ctx), map[string]interface{}{"id": taskID}, map[string]interface{}{"status": dao.TaskStatusFailed})
+			if err != nil {
+				log.Error(ctx, "func", "processBaiduOCRTask", "msg", "更新任务状态失败", "error", err)
+			}
+			return
+		}
+		err := dao.NewRecognitionTaskDao().Update(dao.DB.WithContext(ctx), map[string]interface{}{"id": taskID}, map[string]interface{}{"status": dao.TaskStatusCompleted})
+		if err != nil {
+			log.Error(ctx, "func", "processBaiduOCRTask", "msg", "更新任务状态失败", "error", err)
+		}
+	}()
+
+	// 从 OSS 下载文件
+	reader, err := oss.DownloadFile(ctx, fileURL)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "从OSS下载文件失败", "error", err)
+		return err
+	}
+	defer reader.Close()
+
+	// 读取文件内容
+	fileBytes, err := io.ReadAll(reader)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "读取文件内容失败", "error", err)
+		return err
+	}
+
+	// Base64 编码
+	fileData := base64.StdEncoding.EncodeToString(fileBytes)
+
+	// 根据文件扩展名确定 fileType: 0=PDF, 1=图片
+	fileType := 1 // 默认为图片
+	lowerFileURL := strings.ToLower(fileURL)
+	if strings.HasSuffix(lowerFileURL, ".pdf") {
+		fileType = 0
+	}
+
+	// 创建百度 OCR API 请求
+	baiduReq := BaiduOCRRequest{
+		File:                      fileData,
+		FileType:                  fileType,
+		UseDocOrientationClassify: false,
+		UseDocUnwarping:           false,
+		UseChartRecognition:       false,
+	}
+
+	jsonData, err := json.Marshal(baiduReq)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "JSON编码失败", "error", err)
+		return err
+	}
+
+	headers := map[string]string{
+		"Content-Type":  "application/json",
+		"Authorization": fmt.Sprintf("token %s", config.GlobalConfig.BaiduOCR.Token),
+	}
+
+	endpoint := "https://j5veh2l2r6ubk6cb.aistudio-app.com/layout-parsing"
+
+	startTime := time.Now()
+
+	log.Info(ctx, "func", "processBaiduOCRTask", "msg", "BaiduOCRApi_Start", "start_time", startTime)
+
+	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, endpoint, bytes.NewReader(jsonData), headers)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "百度 OCR API 请求失败", "error", err)
+		return err
+	}
+	defer resp.Body.Close()
+
+	log.Info(ctx, "func", "processBaiduOCRTask", "msg", "BaiduOCRApi_End", "end_time", time.Now(), "duration", time.Since(startTime))
+
+	body := &bytes.Buffer{}
+	if _, err = body.ReadFrom(resp.Body); err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "读取响应体失败", "error", err)
+		return err
+	}
+
+	// 创建日志记录（不记录请求体中的 base64 数据以节省存储）
+	requestLogData := map[string]interface{}{
+		"fileType":                  fileType,
+		"useDocOrientationClassify": false,
+		"useDocUnwarping":           false,
+		"useChartRecognition":       false,
+		"fileSize":                  len(fileBytes),
+	}
+	requestLogBytes, _ := json.Marshal(requestLogData)
+	recognitionLog := &dao.RecognitionLog{
+		TaskID:       taskID,
+		Provider:     dao.ProviderBaiduOCR,
+		RequestBody:  string(requestLogBytes),
+		ResponseBody: body.String(),
+	}
+
+	// 解析响应
+	var baiduResp BaiduOCRResponse
+	if err := json.Unmarshal(body.Bytes(), &baiduResp); err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "解析响应失败", "error", err)
+		return err
+	}
+
+	// 检查错误
+	if baiduResp.ErrorCode != 0 {
+		errMsg := fmt.Sprintf("errorCode: %d, errorMsg: %s", baiduResp.ErrorCode, baiduResp.ErrorMsg)
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "百度 OCR API 返回错误", "error", errMsg)
+		return fmt.Errorf("baidu ocr error: %s", errMsg)
+	}
+
+	// 保存日志
+	err = logDao.Create(dao.DB.WithContext(ctx), recognitionLog)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "保存日志失败", "error", err)
+	}
+
+	// 合并所有页面的 markdown 结果
+	var markdownTexts []string
+	if baiduResp.Result != nil && len(baiduResp.Result.LayoutParsingResults) > 0 {
+		for _, res := range baiduResp.Result.LayoutParsingResults {
+			if res.Markdown.Text != "" {
+				markdownTexts = append(markdownTexts, res.Markdown.Text)
+			}
+		}
+	}
+	markdownResult := strings.Join(markdownTexts, "\n\n---\n\n")
+
+	latex, mml, e := s.HandleConvert(ctx, markdownResult)
+	if e != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "转换失败", "error", err)
+	}
+
+	// 更新或创建识别结果
+	resultDao := dao.NewRecognitionResultDao()
+	result, err := resultDao.GetByTaskID(dao.DB.WithContext(ctx), taskID)
+	if err != nil {
+		log.Error(ctx, "func", "processBaiduOCRTask", "msg", "获取任务结果失败", "error", err)
+		return err
+	}
+
+	log.Info(ctx, "func", "processBaiduOCRTask", "msg", "saveLog", "end_time", time.Now(), "duration", time.Since(startTime))
+
+	if result == nil {
+		// 创建新结果
+		err = resultDao.Create(dao.DB.WithContext(ctx), dao.RecognitionResult{
+			TaskID:   taskID,
+			TaskType: dao.TaskTypeFormula,
+			Markdown: markdownResult,
+			Latex:    latex,
+			MathML:   mml,
+		})
+		if err != nil {
+			log.Error(ctx, "func", "processBaiduOCRTask", "msg", "创建任务结果失败", "error", err)
+			return err
+		}
+	} else {
+		// 更新现有结果
+		err = resultDao.Update(dao.DB.WithContext(ctx), result.ID, map[string]interface{}{
+			"markdown": markdownResult,
+			"latex":    latex,
+			"mathml":   mml,
+		})
+		if err != nil {
+			log.Error(ctx, "func", "processBaiduOCRTask", "msg", "更新任务结果失败", "error", err)
+			return err
+		}
+	}
+
+	isSuccess = true
+	return nil
+}
+
 func (s *RecognitionService) TestProcessMathpixTask(ctx context.Context, taskID int64) error {
 	task, err := dao.NewRecognitionTaskDao().GetTaskByID(dao.DB.WithContext(ctx), taskID)
 	if err != nil {
@@ -832,3 +1067,55 @@ func (s *RecognitionService) TestProcessMathpixTask(ctx context.Context, taskID
 	}
 	return s.processMathpixTask(ctx, taskID, task.FileURL)
 }
+
+// ConvertResponse Python 接口返回结构
+type ConvertResponse struct {
+	Latex  string `json:"latex"`
+	MathML string `json:"mathml"`
+	Error  string `json:"error,omitempty"`
+}
+
+func (s *RecognitionService) HandleConvert(ctx context.Context, markdown string) (latex string, mml string, err error) {
+	url := "https://cloud.texpixel.com:10443/doc_converter/v1/convert"
+
+	// 构建 multipart form
+	body := &bytes.Buffer{}
+	writer := multipart.NewWriter(body)
+	_ = writer.WriteField("markdown_input", markdown)
+	writer.Close()
+
+	// 使用正确的 Content-Type（包含 boundary）
+	headers := map[string]string{
+		"Content-Type": writer.FormDataContentType(),
+	}
+
+	resp, err := s.httpClient.RequestWithRetry(ctx, http.MethodPost, url, body, headers)
+	if err != nil {
+		return "", "", err
+	}
+	defer resp.Body.Close()
+
+	// 读取响应体
+	respBody, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return "", "", err
+	}
+
+	// 检查 HTTP 状态码
+	if resp.StatusCode != http.StatusOK {
+		return "", "", fmt.Errorf("convert failed: status %d, body: %s", resp.StatusCode, string(respBody))
+	}
+
+	// 解析 JSON 响应
+	var convertResp ConvertResponse
+	if err := json.Unmarshal(respBody, &convertResp); err != nil {
+		return "", "", fmt.Errorf("unmarshal response failed: %v, body: %s", err, string(respBody))
+	}
+
+	// 检查业务错误
+	if convertResp.Error != "" {
+		return "", "", fmt.Errorf("convert error: %s", convertResp.Error)
+	}
+
+	return convertResp.Latex, convertResp.MathML, nil
+}

internal/service/task.go

@@ -1,15 +1,19 @@
 package service
 
 import (
+	"bytes"
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
+	"io"
+	"net/http"
 	"strings"
 
-	"gitea.com/bitwsd/document_ai/internal/model/task"
+	"gitea.com/texpixel/document_ai/internal/model/task"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
-	"gitea.com/bitwsd/document_ai/pkg/oss"
+	"gitea.com/texpixel/document_ai/pkg/oss"
 )
 
 type TaskService struct {
@@ -87,13 +91,14 @@ func (svc *TaskService) GetTaskList(ctx context.Context, req *task.TaskListReque
 	for _, item := range tasks {
 		var latex string
 		var markdown string
+		var mathML string
+		var mml string
 		recognitionResult := recognitionResultMap[item.ID]
 		if recognitionResult != nil {
 			latex = recognitionResult.Latex
 			markdown = recognitionResult.Markdown
-			if markdown == "" {
+			mathML = recognitionResult.MathML
-				markdown = fmt.Sprintf("$$%s$$", latex)
+			mml = recognitionResult.MML
-			}
 		}
 		originURL, err := oss.GetDownloadURL(ctx, item.FileURL)
 		if err != nil {
@@ -102,6 +107,8 @@ func (svc *TaskService) GetTaskList(ctx context.Context, req *task.TaskListReque
 		resp.TaskList = append(resp.TaskList, &task.TaskListDTO{
 			Latex:     latex,
 			Markdown:  markdown,
+			MathML:    mathML,
+			MML:       mml,
 			TaskID:    item.TaskUUID,
 			FileName:  item.FileName,
 			Status:    int(item.Status),
@@ -112,3 +119,87 @@ func (svc *TaskService) GetTaskList(ctx context.Context, req *task.TaskListReque
 	}
 	return resp, nil
 }
+
+func (svc *TaskService) ExportTask(ctx context.Context, req *task.ExportTaskRequest) ([]byte, string, error) {
+	recognitionTask, err := svc.recognitionTaskDao.GetByTaskNo(dao.DB.WithContext(ctx), req.TaskNo)
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "get task by task id failed", "error", err)
+		return nil, "", err
+	}
+
+	if recognitionTask == nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "task not found")
+		return nil, "", errors.New("task not found")
+	}
+
+	if recognitionTask.Status != dao.TaskStatusCompleted {
+		log.Error(ctx, "func", "ExportTask", "msg", "task not finished")
+		return nil, "", errors.New("task not finished")
+	}
+
+	recognitionResult, err := svc.recognitionResultDao.GetByTaskID(dao.DB.WithContext(ctx), recognitionTask.ID)
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "get recognition result by task id failed", "error", err)
+		return nil, "", err
+	}
+
+	if recognitionResult == nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "recognition result not found")
+		return nil, "", errors.New("recognition result not found")
+	}
+
+	markdown := recognitionResult.Markdown
+	if markdown == "" {
+		log.Error(ctx, "func", "ExportTask", "msg", "markdown not found")
+		return nil, "", errors.New("markdown not found")
+	}
+
+	// 获取文件名（去掉扩展名）
+	filename := strings.TrimSuffix(recognitionTask.FileName, "."+strings.ToLower(strings.Split(recognitionTask.FileName, ".")[len(strings.Split(recognitionTask.FileName, "."))-1]))
+	if filename == "" {
+		filename = "texpixel"
+	}
+
+	// 构建 JSON 请求体
+	requestBody := map[string]string{
+		"markdown": markdown,
+		"filename": filename,
+	}
+	jsonData, err := json.Marshal(requestBody)
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "json marshal failed", "error", err)
+		return nil, "", err
+	}
+
+	httpReq, err := http.NewRequestWithContext(ctx, http.MethodPost, "https://cloud.texpixel.com:10443/doc_process/v1/convert/file", bytes.NewReader(jsonData))
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "create http request failed", "error", err)
+		return nil, "", err
+	}
+	httpReq.Header.Set("Content-Type", "application/json")
+
+	client := &http.Client{}
+	resp, err := client.Do(httpReq)
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "http request failed", "error", err)
+		return nil, "", err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(resp.Body)
+		log.Error(ctx, "func", "ExportTask", "msg", "http request failed", "status", resp.StatusCode, "body", string(body))
+		return nil, "", fmt.Errorf("export service returned status: %d", resp.StatusCode)
+	}
+
+	fileData, err := io.ReadAll(resp.Body)
+	if err != nil {
+		log.Error(ctx, "func", "ExportTask", "msg", "read response body failed", "error", err)
+		return nil, "", err
+	}
+
+	// 新接口只返回 DOCX 格式
+	contentType := "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+
+	return fileData, contentType, nil
+}

internal/service/user_service.go

@@ -2,15 +2,20 @@ package service
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"math/rand"
+	"net/http"
+	"net/url"
 
-	"gitea.com/bitwsd/document_ai/internal/storage/cache"
+	"gitea.com/texpixel/document_ai/config"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	model "gitea.com/texpixel/document_ai/internal/model/user"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/internal/storage/cache"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/sms"
+	"gitea.com/texpixel/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/sms"
 	"golang.org/x/crypto/bcrypt"
 )
 
@@ -159,3 +164,126 @@ func (svc *UserService) LoginByEmail(ctx context.Context, email, password string
 
 	return user.ID, nil
 }
+
+type googleTokenResponse struct {
+	AccessToken string `json:"access_token"`
+	IDToken     string `json:"id_token"`
+	ExpiresIn   int    `json:"expires_in"`
+	TokenType   string `json:"token_type"`
+}
+
+func (svc *UserService) googleHTTPClient() *http.Client {
+	if config.GlobalConfig.Google.Proxy == "" {
+		return &http.Client{}
+	}
+	proxyURL, err := url.Parse(config.GlobalConfig.Google.Proxy)
+	if err != nil {
+		return &http.Client{}
+	}
+	return &http.Client{Transport: &http.Transport{Proxy: http.ProxyURL(proxyURL)}}
+}
+
+func (svc *UserService) ExchangeGoogleCodeAndGetUserInfo(ctx context.Context, clientID, clientSecret, code, redirectURI string) (*model.GoogleUserInfo, error) {
+	tokenURL := "https://oauth2.googleapis.com/token"
+	formData := url.Values{
+		"client_id":     {clientID},
+		"client_secret": {clientSecret},
+		"code":          {code},
+		"grant_type":    {"authorization_code"},
+		"redirect_uri":  {redirectURI},
+	}
+
+	client := svc.googleHTTPClient()
+	resp, err := client.PostForm(tokenURL, formData)
+	if err != nil {
+		log.Error(ctx, "func", "ExchangeGoogleCodeAndGetUserInfo", "msg", "exchange code failed", "error", err)
+		return nil, err
+	}
+	defer resp.Body.Close()
+
+	var tokenResp googleTokenResponse
+	if err := json.NewDecoder(resp.Body).Decode(&tokenResp); err != nil {
+		log.Error(ctx, "func", "ExchangeGoogleCodeAndGetUserInfo", "msg", "decode token response failed", "error", err)
+		return nil, err
+	}
+
+	if tokenResp.AccessToken == "" {
+		log.Error(ctx, "func", "ExchangeGoogleCodeAndGetUserInfo", "msg", "no access token in response")
+		return nil, errors.New("no access token in response")
+	}
+
+	userInfo, err := svc.getGoogleUserInfo(ctx, tokenResp.AccessToken)
+	if err != nil {
+		log.Error(ctx, "func", "ExchangeGoogleCodeAndGetUserInfo", "msg", "get user info failed", "error", err)
+		return nil, err
+	}
+
+	return &model.GoogleUserInfo{
+		ID:    userInfo.ID,
+		Email: userInfo.Email,
+		Name:  userInfo.Name,
+	}, nil
+}
+
+func (svc *UserService) getGoogleUserInfo(ctx context.Context, accessToken string) (*model.GoogleUserInfo, error) {
+	req, err := http.NewRequestWithContext(ctx, "GET", "https://www.googleapis.com/oauth2/v2/userinfo", nil)
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Authorization", "Bearer "+accessToken)
+
+	client := svc.googleHTTPClient()
+	resp, err := client.Do(req)
+	if err != nil {
+		return nil, err
+	}
+	defer resp.Body.Close()
+
+	var userInfo model.GoogleUserInfo
+	if err := json.NewDecoder(resp.Body).Decode(&userInfo); err != nil {
+		return nil, err
+	}
+
+	return &userInfo, nil
+}
+
+func (svc *UserService) FindOrCreateGoogleUser(ctx context.Context, userInfo *model.GoogleUserInfo) (uid int64, err error) {
+	existingUser, err := svc.userDao.GetByGoogleID(dao.DB.WithContext(ctx), userInfo.ID)
+	if err != nil {
+		log.Error(ctx, "func", "FindOrCreateGoogleUser", "msg", "get user by google id error", "error", err)
+		return 0, err
+	}
+
+	if existingUser != nil {
+		return existingUser.ID, nil
+	}
+
+	existingUser, err = svc.userDao.GetByEmail(dao.DB.WithContext(ctx), userInfo.Email)
+	if err != nil {
+		log.Error(ctx, "func", "FindOrCreateGoogleUser", "msg", "get user by email error", "error", err)
+		return 0, err
+	}
+
+	if existingUser != nil {
+		existingUser.GoogleID = userInfo.ID
+		err = svc.userDao.Update(dao.DB.WithContext(ctx), existingUser)
+		if err != nil {
+			log.Error(ctx, "func", "FindOrCreateGoogleUser", "msg", "update user google id error", "error", err)
+			return 0, err
+		}
+		return existingUser.ID, nil
+	}
+
+	user := &dao.User{
+		Email:    userInfo.Email,
+		GoogleID: userInfo.ID,
+		Username: userInfo.Name,
+	}
+	err = svc.userDao.Create(dao.DB.WithContext(ctx), user)
+	if err != nil {
+		log.Error(ctx, "func", "FindOrCreateGoogleUser", "msg", "create user error", "error", err)
+		return 0, err
+	}
+
+	return user.ID, nil
+}

internal/storage/cache/engine.go

@@ -5,7 +5,7 @@ import (
 	"fmt"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
 	"github.com/redis/go-redis/v9"
 )
 

internal/storage/dao/analytics_event.go

@@ -0,0 +1,170 @@
+package dao
+
+import (
+	"time"
+
+	"gorm.io/datatypes"
+	"gorm.io/gorm"
+	"gorm.io/gorm/clause"
+)
+
+// AnalyticsEvent 数据埋点事件表
+type AnalyticsEvent struct {
+	ID         int64          `gorm:"bigint;primaryKey;autoIncrement;column:id;comment:主键ID" json:"id"`
+	UserID     int64          `gorm:"column:user_id;not null;index:idx_user_id;comment:用户ID" json:"user_id"`
+	EventName  string         `gorm:"column:event_name;varchar(128);not null;index:idx_event_name;comment:事件名称" json:"event_name"`
+	Properties datatypes.JSON `gorm:"column:properties;type:json;comment:事件属性(JSON)" json:"properties"`
+	DeviceInfo datatypes.JSON `gorm:"column:device_info;type:json;comment:设备信息(JSON)" json:"device_info"`
+	MetaData   datatypes.JSON `gorm:"column:meta_data;type:json;comment:元数据(JSON，包含task_id等)" json:"meta_data"`
+	CreatedAt  time.Time      `gorm:"column:created_at;comment:创建时间;not null;default:current_timestamp;index:idx_created_at" json:"created_at"`
+}
+
+func (e *AnalyticsEvent) TableName() string {
+	return "analytics_events"
+}
+
+// AnalyticsEventDao 数据埋点事件DAO
+type AnalyticsEventDao struct{}
+
+func NewAnalyticsEventDao() *AnalyticsEventDao {
+	return &AnalyticsEventDao{}
+}
+
+// Create 创建事件记录
+func (dao *AnalyticsEventDao) Create(tx *gorm.DB, event *AnalyticsEvent) error {
+	return tx.Create(event).Error
+}
+
+// BatchCreate 批量创建事件记录
+func (dao *AnalyticsEventDao) BatchCreate(tx *gorm.DB, events []*AnalyticsEvent) error {
+	if len(events) == 0 {
+		return nil
+	}
+	return tx.CreateInBatches(events, 100).Error
+}
+
+// GetByID 根据ID获取事件
+func (dao *AnalyticsEventDao) GetByID(tx *gorm.DB, id int64) (*AnalyticsEvent, error) {
+	event := &AnalyticsEvent{}
+	err := tx.Where("id = ?", id).First(event).Error
+	if err != nil {
+		if err == gorm.ErrRecordNotFound {
+			return nil, nil
+		}
+		return nil, err
+	}
+	return event, nil
+}
+
+// GetUserEvents 获取用户的事件列表
+func (dao *AnalyticsEventDao) GetUserEvents(tx *gorm.DB, userID int64, page, pageSize int) ([]*AnalyticsEvent, int64, error) {
+	var events []*AnalyticsEvent
+	var total int64
+
+	offset := (page - 1) * pageSize
+	query := tx.Model(&AnalyticsEvent{}).Where("user_id = ?", userID)
+
+	err := query.Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
+
+	err = query.Offset(offset).Limit(pageSize).
+		Order(clause.OrderByColumn{Column: clause.Column{Name: "created_at"}, Desc: true}).
+		Find(&events).Error
+
+	return events, total, err
+}
+
+// GetEventsByName 根据事件名称获取事件列表
+func (dao *AnalyticsEventDao) GetEventsByName(tx *gorm.DB, eventName string, page, pageSize int) ([]*AnalyticsEvent, int64, error) {
+	var events []*AnalyticsEvent
+	var total int64
+
+	offset := (page - 1) * pageSize
+	query := tx.Model(&AnalyticsEvent{}).Where("event_name = ?", eventName)
+
+	err := query.Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
+
+	err = query.Offset(offset).Limit(pageSize).
+		Order(clause.OrderByColumn{Column: clause.Column{Name: "created_at"}, Desc: true}).
+		Find(&events).Error
+
+	return events, total, err
+}
+
+// GetUserEventsByName 获取用户指定事件的列表
+func (dao *AnalyticsEventDao) GetUserEventsByName(tx *gorm.DB, userID int64, eventName string, page, pageSize int) ([]*AnalyticsEvent, int64, error) {
+	var events []*AnalyticsEvent
+	var total int64
+
+	offset := (page - 1) * pageSize
+	query := tx.Model(&AnalyticsEvent{}).Where("user_id = ? AND event_name = ?", userID, eventName)
+
+	err := query.Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
+
+	err = query.Offset(offset).Limit(pageSize).
+		Order(clause.OrderByColumn{Column: clause.Column{Name: "created_at"}, Desc: true}).
+		Find(&events).Error
+
+	return events, total, err
+}
+
+// GetEventsByTimeRange 根据时间范围获取事件列表
+func (dao *AnalyticsEventDao) GetEventsByTimeRange(tx *gorm.DB, startTime, endTime time.Time, page, pageSize int) ([]*AnalyticsEvent, int64, error) {
+	var events []*AnalyticsEvent
+	var total int64
+
+	offset := (page - 1) * pageSize
+	query := tx.Model(&AnalyticsEvent{}).Where("created_at BETWEEN ? AND ?", startTime, endTime)
+
+	err := query.Count(&total).Error
+	if err != nil {
+		return nil, 0, err
+	}
+
+	err = query.Offset(offset).Limit(pageSize).
+		Order(clause.OrderByColumn{Column: clause.Column{Name: "created_at"}, Desc: true}).
+		Find(&events).Error
+
+	return events, total, err
+}
+
+// CountEventsByName 统计指定事件的数量
+func (dao *AnalyticsEventDao) CountEventsByName(tx *gorm.DB, eventName string) (int64, error) {
+	var count int64
+	err := tx.Model(&AnalyticsEvent{}).Where("event_name = ?", eventName).Count(&count).Error
+	return count, err
+}
+
+// CountUserEvents 统计用户的事件数量
+func (dao *AnalyticsEventDao) CountUserEvents(tx *gorm.DB, userID int64) (int64, error) {
+	var count int64
+	err := tx.Model(&AnalyticsEvent{}).Where("user_id = ?", userID).Count(&count).Error
+	return count, err
+}
+
+// GetEventStats 获取事件统计信息（按事件名称分组）
+func (dao *AnalyticsEventDao) GetEventStats(tx *gorm.DB, startTime, endTime time.Time) ([]map[string]interface{}, error) {
+	var results []map[string]interface{}
+
+	err := tx.Model(&AnalyticsEvent{}).
+		Select("event_name, COUNT(*) as count, COUNT(DISTINCT user_id) as unique_users").
+		Where("created_at BETWEEN ? AND ?", startTime, endTime).
+		Group("event_name").
+		Order("count DESC").
+		Find(&results).Error
+
+	return results, err
+}
+
+// DeleteOldEvents 删除旧事件（数据清理）
+func (dao *AnalyticsEventDao) DeleteOldEvents(tx *gorm.DB, beforeTime time.Time) error {
+	return tx.Where("created_at < ?", beforeTime).Delete(&AnalyticsEvent{}).Error
+}

internal/storage/dao/engine.go

@@ -3,16 +3,19 @@ package dao
 import (
 	"fmt"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
 	"gorm.io/driver/mysql"
 	"gorm.io/gorm"
+	"gorm.io/gorm/logger"
 )
 
 var DB *gorm.DB
 
 func InitDB(conf config.DatabaseConfig) {
 	dns := fmt.Sprintf("%s:%s@tcp(%s:%d)/%s?charset=utf8mb4&parseTime=True&loc=Asia%%2FShanghai", conf.Username, conf.Password, conf.Host, conf.Port, conf.DBName)
-	db, err := gorm.Open(mysql.Open(dns), &gorm.Config{})
+	db, err := gorm.Open(mysql.Open(dns), &gorm.Config{
+		Logger: logger.Default.LogMode(logger.Silent), // 禁用 GORM 日志输出
+	})
 	if err != nil {
 		panic(err)
 	}

internal/storage/dao/recognition_log.go

@@ -11,6 +11,7 @@ const (
 	ProviderMathpix     RecognitionLogProvider = "mathpix"
 	ProviderSiliconflow RecognitionLogProvider = "siliconflow"
 	ProviderTexpixel    RecognitionLogProvider = "texpixel"
+	ProviderBaiduOCR    RecognitionLogProvider = "baidu_ocr"
 )
 
 // RecognitionLog 识别调用日志表，记录第三方API调用请求和响应

internal/storage/dao/result.go

@@ -9,8 +9,9 @@ type RecognitionResult struct {
 	TaskID   int64    `gorm:"column:task_id;bigint;not null;default:0;comment:任务ID" json:"task_id"`
 	TaskType TaskType `gorm:"column:task_type;varchar(16);not null;comment:任务类型;default:''" json:"task_type"`
 	Latex    string   `json:"latex" gorm:"column:latex;type:text;not null;default:''"`
-	Markdown string   `json:"markdown" gorm:"column:markdown;type:text;not null;default:''"` // Mathpix Markdown 格式
+	Markdown string   `json:"markdown" gorm:"column:markdown;type:text;not null;default:''"` // Markdown 格式
 	MathML   string   `json:"mathml" gorm:"column:mathml;type:text;not null;default:''"`     // MathML 格式
+	MML      string   `json:"mml" gorm:"column:mml;type:text;not null;default:''"`           // MML 格式
 }
 
 type RecognitionResultDao struct {

internal/storage/dao/user.go

@@ -14,6 +14,7 @@ type User struct {
 	Password      string `gorm:"column:password" json:"password"`
 	WechatOpenID  string `gorm:"column:wechat_open_id" json:"wechat_open_id"`
 	WechatUnionID string `gorm:"column:wechat_union_id" json:"wechat_union_id"`
+	GoogleID      string `gorm:"column:google_id" json:"google_id"`
 }
 
 func (u *User) TableName() string {
@@ -63,3 +64,18 @@ func (dao *UserDao) GetByEmail(tx *gorm.DB, email string) (*User, error) {
 	}
 	return &user, nil
 }
+
+func (dao *UserDao) GetByGoogleID(tx *gorm.DB, googleID string) (*User, error) {
+	var user User
+	if err := tx.Where("google_id = ?", googleID).First(&user).Error; err != nil {
+		if errors.Is(err, gorm.ErrRecordNotFound) {
+			return nil, nil
+		}
+		return nil, err
+	}
+	return &user, nil
+}
+
+func (dao *UserDao) Update(tx *gorm.DB, user *User) error {
+	return tx.Save(user).Error
+}

main.go

@@ -10,23 +10,26 @@ import (
 	"syscall"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/api"
+	"gitea.com/texpixel/document_ai/api"
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
-	"gitea.com/bitwsd/document_ai/internal/storage/cache"
+	"gitea.com/texpixel/document_ai/internal/storage/cache"
-	"gitea.com/bitwsd/document_ai/internal/storage/dao"
+	"gitea.com/texpixel/document_ai/internal/storage/dao"
-	"gitea.com/bitwsd/document_ai/pkg/common"
+	"gitea.com/texpixel/document_ai/pkg/common"
-	"gitea.com/bitwsd/document_ai/pkg/cors"
+	"gitea.com/texpixel/document_ai/pkg/cors"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
-	"gitea.com/bitwsd/document_ai/pkg/middleware"
+	"gitea.com/texpixel/document_ai/pkg/middleware"
-	"gitea.com/bitwsd/document_ai/pkg/sms"
+	"gitea.com/texpixel/document_ai/pkg/sms"
 	"github.com/gin-gonic/gin"
 )
 
 func main() {
 	// 加载配置
-	env := "dev"
+	env := ""
 	flag.StringVar(&env, "env", "dev", "environment (dev/prod)")
 	flag.Parse()
+
+	fmt.Println("env:", env)
+
 	configPath := fmt.Sprintf("./config/config_%s.yaml", env)
 	if err := config.Init(configPath); err != nil {
 		panic(err)

migrations/analytics_events.sql

@@ -0,0 +1,18 @@
+-- 数据埋点事件表
+CREATE TABLE IF NOT EXISTS `analytics_events` (
+  `id` BIGINT NOT NULL AUTO_INCREMENT COMMENT '主键ID',
+  `user_id` BIGINT NOT NULL COMMENT '用户ID',
+  `event_name` VARCHAR(128) NOT NULL COMMENT '事件名称',
+  `properties` JSON DEFAULT NULL COMMENT '事件属性(JSON)',
+  `device_info` JSON DEFAULT NULL COMMENT '设备信息(JSON)',
+  `meta_data` JSON DEFAULT NULL COMMENT '元数据(JSON，包含task_id等)',
+  `created_at` TIMESTAMP NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT '创建时间',
+  PRIMARY KEY (`id`),
+  INDEX `idx_user_id` (`user_id`),
+  INDEX `idx_event_name` (`event_name`),
+  INDEX `idx_created_at` (`created_at`)
+) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COMMENT='数据埋点事件表';
+
+-- 创建复合索引以提高查询性能
+CREATE INDEX `idx_user_event` ON `analytics_events` (`user_id`, `event_name`);
+CREATE INDEX `idx_event_time` ON `analytics_events` (`event_name`, `created_at`);

pkg/common/middleware.go

@@ -6,8 +6,8 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/pkg/constant"
+	"gitea.com/texpixel/document_ai/pkg/constant"
-	"gitea.com/bitwsd/document_ai/pkg/jwt"
+	"gitea.com/texpixel/document_ai/pkg/jwt"
 	"github.com/gin-gonic/gin"
 )
 

pkg/common/response.go

@@ -3,7 +3,7 @@ package common
 import (
 	"context"
 
-	"gitea.com/bitwsd/document_ai/pkg/constant"
+	"gitea.com/texpixel/document_ai/pkg/constant"
 )
 
 type Response struct {

pkg/httpclient/client.go

@@ -10,7 +10,7 @@ import (
 	"net/http"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 )
 
 // RetryConfig 重试配置
@@ -23,9 +23,9 @@ type RetryConfig struct {
 
 // DefaultRetryConfig 默认重试配置
 var DefaultRetryConfig = RetryConfig{
-	MaxRetries:      2,
+	MaxRetries:      1,
 	InitialInterval: 100 * time.Millisecond,
-	MaxInterval:     5 * time.Second,
+	MaxInterval:     30 * time.Second,
 	SkipTLSVerify:   true,
 }
 

pkg/log/logger.go

@@ -8,6 +8,8 @@ import (
 	"runtime"
 	"time"
 
+	"gitea.com/texpixel/document_ai/pkg/requestid"
+
 	"github.com/rs/zerolog"
 	"gopkg.in/natefinch/lumberjack.v2"
 )
@@ -67,8 +69,13 @@ func log(ctx context.Context, level zerolog.Level, logType LogType, kv ...interf
 	// 添加日志类型
 	event.Str("type", string(logType))
 
-	// 添加请求ID
+	reqID := requestid.GetRequestID()
-	if reqID, exists := ctx.Value("request_id").(string); exists {
+	if reqID == "" {
+		if id, exists := ctx.Value("request_id").(string); exists {
+			reqID = id
+		}
+	}
+	if reqID != "" {
 		event.Str("request_id", reqID)
 	}
 
@@ -149,4 +156,3 @@ func Fatal(ctx context.Context, kv ...interface{}) {
 func Access(ctx context.Context, kv ...interface{}) {
 	log(ctx, zerolog.InfoLevel, TypeAccess, kv...)
 }
-

pkg/middleware/access.go

@@ -6,7 +6,7 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 	"github.com/gin-gonic/gin"
 )
 
@@ -72,4 +72,3 @@ func AccessLog() gin.HandlerFunc {
 		)
 	}
 }
-

pkg/middleware/requestid.go

@@ -1,19 +1,23 @@
 package middleware
 
 import (
+	"gitea.com/texpixel/document_ai/pkg/requestid"
+
 	"github.com/gin-gonic/gin"
 	"github.com/google/uuid"
 )
 
 func RequestID() gin.HandlerFunc {
 	return func(c *gin.Context) {
-		requestID := c.Request.Header.Get("X-Request-ID")
+		reqID := c.Request.Header.Get("X-Request-ID")
-		if requestID == "" {
+		if reqID == "" {
-			requestID = uuid.New().String()
+			reqID = uuid.New().String()
 		}
-		c.Request.Header.Set("X-Request-ID", requestID)
+		c.Request.Header.Set("X-Request-ID", reqID)
-		c.Set("request_id", requestID)
+		c.Set("request_id", reqID)
+
+		requestid.SetRequestID(reqID, func() {
 			c.Next()
+		})
 	}
 }
-

pkg/oss/policy.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 	"github.com/aliyun/aliyun-oss-go-sdk/oss"
 )
 

pkg/requestid/requestid.go

@@ -0,0 +1,27 @@
+package requestid
+
+import (
+	"github.com/jtolds/gls"
+)
+
+// requestIDKey 是 gls 中存储 request_id 的 key
+var requestIDKey = gls.GenSym()
+
+// glsMgr 是 gls 管理器
+var glsMgr = gls.NewContextManager()
+
+// SetRequestID 在 gls 中设置 request_id，并在 fn 执行期间保持有效
+func SetRequestID(requestID string, fn func()) {
+	glsMgr.SetValues(gls.Values{requestIDKey: requestID}, fn)
+}
+
+// GetRequestID 从 gls 中获取当前 goroutine 的 request_id
+func GetRequestID() string {
+	val, ok := glsMgr.GetValue(requestIDKey)
+	if !ok {
+		return ""
+	}
+	reqID, _ := val.(string)
+	return reqID
+}
+

pkg/sms/sms.go

@@ -4,7 +4,7 @@ import (
 	"errors"
 	"sync"
 
-	"gitea.com/bitwsd/document_ai/config"
+	"gitea.com/texpixel/document_ai/config"
 	openapi "github.com/alibabacloud-go/darabonba-openapi/client"
 	dysmsapi "github.com/alibabacloud-go/dysmsapi-20170525/v2/client"
 	aliutil "github.com/alibabacloud-go/tea-utils/service"

pkg/utils/routine.go

@@ -3,7 +3,7 @@ package utils
 import (
 	"context"
 
-	"gitea.com/bitwsd/document_ai/pkg/log"
+	"gitea.com/texpixel/document_ai/pkg/log"
 )
 
 func SafeGo(fn func()) {