refactor(data-management): 优化PDF文本提取服务的事务处理

- 添加TransactionSynchronization相关依赖注入
- 实现事务提交后异步执行PDF文本提取功能
- 增加数据集ID和文件ID的空值检查
- 在活跃事务中注册同步回调确保正确执行
- 避免在事务未提交时提前执行异步任务

backend/services/data-management-service/src/main/java/com/datamate/datamanagement/application/DatasetFileApplicationService.java

@@ -43,6 +43,8 @@ import org.springframework.core.io.UrlResource;
 import org.springframework.http.HttpHeaders;
 import org.springframework.stereotype.Service;
 import org.springframework.transaction.annotation.Transactional;
+import org.springframework.transaction.support.TransactionSynchronization;
+import org.springframework.transaction.support.TransactionSynchronizationManager;
 
 import java.io.File;
 import java.io.IOException;
@@ -961,6 +963,20 @@ public class DatasetFileApplicationService {
         if (fileType == null || !DOCUMENT_TEXT_FILE_TYPES.contains(fileType.toLowerCase(Locale.ROOT))) {
             return;
         }
-        pdfTextExtractAsyncService.extractPdfText(dataset.getId(), datasetFile.getId());
+        String datasetId = dataset.getId();
+        String fileId = datasetFile.getId();
+        if (datasetId == null || fileId == null) {
+            return;
+        }
+        if (TransactionSynchronizationManager.isSynchronizationActive()) {
+            TransactionSynchronizationManager.registerSynchronization(new TransactionSynchronization() {
+                @Override
+                public void afterCommit() {
+                    pdfTextExtractAsyncService.extractPdfText(datasetId, fileId);
+                }
+            });
+            return;
+        }
+        pdfTextExtractAsyncService.extractPdfText(datasetId, fileId);
     }
 }