feat: add PDF document recognition with 10-page pre-hook

- Migrate recognition_results table to JSON schema (meta_data + content),
  replacing flat latex/markdown/mathml/mml columns
- Add TaskTypePDF constant and update all formula read/write paths
- Add PDFRecognitionService using pdftoppm (Poppler) for CGO-free page
  rendering; limits processing to first 10 pages (pre-hook)
- Reuse existing downstream OCR endpoint (cloud.texpixel.com) for each
  page image; stores results as [{page_number, markdown}] JSON array
- Add Redis queue + distributed lock for PDF worker goroutine
- Add REST endpoints: POST /v1/pdf/recognition, GET /v1/pdf/recognition/:task_no
- Add .pdf to OSS upload file type whitelist
- Add migrations/pdf_recognition.sql for safe data migration

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

internal/service/task.go

@@ -89,17 +89,17 @@ func (svc *TaskService) GetTaskList(ctx context.Context, req *task.TaskListReque
 		Total:    total,
 	}
 	for _, item := range tasks {
-		var latex string
-		var markdown string
-		var mathML string
-		var mml string
+		var latex, markdown, mathML, mml string
 		recognitionResult := recognitionResultMap[item.ID]
-		if recognitionResult != nil {
-			latex = recognitionResult.Latex
-			markdown = recognitionResult.Markdown
-			mathML = recognitionResult.MathML
-			mml = recognitionResult.MML
+		if recognitionResult != nil && recognitionResult.TaskType == dao.TaskTypeFormula {
+			if fc, err := recognitionResult.GetFormulaContent(); err == nil {
+				latex = fc.Latex
+				markdown = fc.Markdown
+				mathML = fc.MathML
+				mml = fc.MML
+			}
 		}
+		// PDF 类型的 TaskListDTO 暂不展开 content（列表页只显示状态）
 		originURL, err := oss.GetDownloadURL(ctx, item.FileURL)
 		if err != nil {
 			log.Error(ctx, "func", "GetTaskList", "msg", "get origin url failed", "error", err)
@@ -148,10 +148,18 @@ func (svc *TaskService) ExportTask(ctx context.Context, req *task.ExportTaskRequ
 		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")
+	var markdown string
+	switch recognitionResult.TaskType {
+	case dao.TaskTypeFormula:
+		fc, err := recognitionResult.GetFormulaContent()
+		if err != nil || fc.Markdown == "" {
+			log.Error(ctx, "func", "ExportTask", "msg", "公式结果解析失败或markdown为空", "error", err)
+			return nil, "", errors.New("markdown not found")
+		}
+		markdown = fc.Markdown
+	default:
+		log.Error(ctx, "func", "ExportTask", "msg", "不支持的导出任务类型", "task_type", recognitionResult.TaskType)
+		return nil, "", errors.New("unsupported task type for export")
 	}
 
 	// 获取文件名（去掉扩展名）