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/storage/dao/result.go

@@ -1,45 +1,104 @@
 package dao
 
 import (
+	"encoding/json"
+
 	"gorm.io/gorm"
 )
 
-type RecognitionResult struct {
-	BaseModel
-	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:''"` // 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
+// FormulaContent 公式识别的 content 字段结构
+type FormulaContent struct {
+	Latex    string `json:"latex"`
+	Markdown string `json:"markdown"`
+	MathML   string `json:"mathml"`
+	MML      string `json:"mml"`
 }
 
-type RecognitionResultDao struct {
+// PDFPageContent PDF 单页识别结果
+type PDFPageContent struct {
+	PageNumber int    `json:"page_number"`
+	Markdown   string `json:"markdown"`
 }
 
+// ResultMetaData recognition_results.meta_data 字段结构
+type ResultMetaData struct {
+	TotalNum int `json:"total_num"`
+}
+
+// RecognitionResult recognition_results 表模型
+type RecognitionResult struct {
+	BaseModel
+	TaskID   int64    `gorm:"column:task_id;bigint;not null;default:0;index;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"`
+	MetaData string   `gorm:"column:meta_data;type:json;comment:元数据" json:"meta_data"`
+	Content  string   `gorm:"column:content;type:json;comment:识别内容JSON" json:"content"`
+}
+
+// SetMetaData 序列化并写入 MetaData 字段
+func (r *RecognitionResult) SetMetaData(meta ResultMetaData) error {
+	b, err := json.Marshal(meta)
+	if err != nil {
+		return err
+	}
+	r.MetaData = string(b)
+	return nil
+}
+
+// GetFormulaContent 从 Content 字段反序列化公式结果
+func (r *RecognitionResult) GetFormulaContent() (*FormulaContent, error) {
+	var c FormulaContent
+	if err := json.Unmarshal([]byte(r.Content), &c); err != nil {
+		return nil, err
+	}
+	return &c, nil
+}
+
+// GetPDFContent 从 Content 字段反序列化 PDF 分页结果
+func (r *RecognitionResult) GetPDFContent() ([]PDFPageContent, error) {
+	var pages []PDFPageContent
+	if err := json.Unmarshal([]byte(r.Content), &pages); err != nil {
+		return nil, err
+	}
+	return pages, nil
+}
+
+// MarshalFormulaContent 将公式结果序列化为 JSON 字符串（供写入 Content）
+func MarshalFormulaContent(c FormulaContent) (string, error) {
+	b, err := json.Marshal(c)
+	return string(b), err
+}
+
+// MarshalPDFContent 将 PDF 分页结果序列化为 JSON 字符串（供写入 Content）
+func MarshalPDFContent(pages []PDFPageContent) (string, error) {
+	b, err := json.Marshal(pages)
+	return string(b), err
+}
+
+type RecognitionResultDao struct{}
+
 func NewRecognitionResultDao() *RecognitionResultDao {
 	return &RecognitionResultDao{}
 }
 
-// 模型方法
 func (dao *RecognitionResultDao) Create(tx *gorm.DB, data RecognitionResult) error {
 	return tx.Create(&data).Error
 }
 
-func (dao *RecognitionResultDao) GetByTaskID(tx *gorm.DB, taskID int64) (result *RecognitionResult, err error) {
-	result = &RecognitionResult{}
-	err = tx.Where("task_id = ?", taskID).First(result).Error
+func (dao *RecognitionResultDao) GetByTaskID(tx *gorm.DB, taskID int64) (*RecognitionResult, error) {
+	result := &RecognitionResult{}
+	err := tx.Where("task_id = ?", taskID).First(result).Error
 	if err != nil && err == gorm.ErrRecordNotFound {
 		return nil, nil
 	}
-	return
-}
-
-func (dao *RecognitionResultDao) GetByTaskIDs(tx *gorm.DB, taskIDs []int64) (results []*RecognitionResult, err error) {
-	err = tx.Where("task_id IN (?)", taskIDs).Find(&results).Error
-	return
+	return result, err
 }
 
 func (dao *RecognitionResultDao) Update(tx *gorm.DB, id int64, updates map[string]interface{}) error {
 	return tx.Model(&RecognitionResult{}).Where("id = ?", id).Updates(updates).Error
 }
+
+func (dao *RecognitionResultDao) GetByTaskIDs(tx *gorm.DB, taskIDs []int64) ([]*RecognitionResult, error) {
+	var results []*RecognitionResult
+	err := tx.Where("task_id IN (?)", taskIDs).Find(&results).Error
+	return results, err
+}

internal/storage/dao/task.go

@@ -20,6 +20,7 @@ const (
 	TaskTypeText    TaskType = "TEXT"
 	TaskTypeTable   TaskType = "TABLE"
 	TaskTypeLayout  TaskType = "LAYOUT"
+	TaskTypePDF     TaskType = "PDF"
 )
 
 func (t TaskType) String() string {