q792602257/DataMate
0
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

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

Browse Source 
- 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
This commit is contained in:
Jerry Yan
2026-01-31 13:59:03 +08:00
parent 4fa0ac1df4
commit 595a758d05
1 changed files with 33 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
backend/services/data-management-service/src/main/java/com/datamate/datamanagement/application/DatasetFileApplicationService.java
View File

@@ -40,9 +40,11 @@ import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.beans.factory.annotation.Value; import org.springframework.beans.factory.annotation.Value;
import org.springframework.core.io.Resource; import org.springframework.core.io.Resource;
import org.springframework.core.io.UrlResource; import org.springframework.core.io.UrlResource;
import org.springframework.http.HttpHeaders; import org.springframework.http.HttpHeaders;
import org.springframework.stereotype.Service; import org.springframework.stereotype.Service;
import org.springframework.transaction.annotation.Transactional; 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.File;
import java.io.IOException; import java.io.IOException;
@@ -950,17 +952,31 @@ public class DatasetFileApplicationService {
return addedFiles; return addedFiles;
} }
private void triggerPdfTextExtraction(Dataset dataset, DatasetFile datasetFile) { private void triggerPdfTextExtraction(Dataset dataset, DatasetFile datasetFile) {
if (dataset == null || datasetFile == null) { if (dataset == null || datasetFile == null) {
return; return;
} }
if (dataset.getDatasetType() != DatasetType.TEXT) { if (dataset.getDatasetType() != DatasetType.TEXT) {
return; return;
} }
String fileType = datasetFile.getFileType(); String fileType = datasetFile.getFileType();
if (fileType == null || !DOCUMENT_TEXT_FILE_TYPES.contains(fileType.toLowerCase(Locale.ROOT))) { if (fileType == null || !DOCUMENT_TEXT_FILE_TYPES.contains(fileType.toLowerCase(Locale.ROOT))) {
return; 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);
}
}