mirror of
https://github.com/arsvendg/Stirling-PDF.git
synced 2026-07-16 19:33:11 +02:00
Support multi-file async job results and ZIP extraction (#3922)
# Description of Changes
This PR introduces multi-file support for asynchronous jobs in the
Stirling PDF backend, enabling jobs to return and manage multiple result
files. Previously, job results were limited to a single file represented
by fileId, originalFileName, and contentType. This change replaces that
legacy structure with a new ResultFile abstraction and expands the
functionality throughout the core system.
ZIP File Support
If a job result is a ZIP file:
It is automatically unpacked using buffered streaming.
Each contained file is stored individually and recorded as a ResultFile.
The original ZIP is deleted after successful extraction.
If ZIP extraction fails, the job result is treated as a single file.
New and Updated API Endpoints
1. GET /api/v1/general/job/{jobId}/result
If the job has multiple files → returns a JSON metadata list.
If the job has a single file → streams the file directly.
Includes UTF-8-safe Content-Disposition headers for filename support.
2. GET /api/v1/general/job/{jobId}/result/files
New endpoint that returns:
```json
{
"jobId": "123",
"fileCount": 2,
"files": [
{
"fileId": "abc",
"fileName": "page1.pdf",
"contentType": "application/pdf",
"fileSize": 12345
},
...
]
}
```
3. GET /api/v1/general/files/{fileId}/metadata
Returns metadata for a specific file:
4. GET /api/v1/general/files/{fileId}
Downloads a file by fileId, using metadata to determine filename and
content type.
---------
Co-authored-by: Copilot <[email protected]>
Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
This commit is contained in:
Anthony Stirling
co-authored by
Copilot
pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Copilot
pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
parent
d17d10b240
commit
bbf5d5f6d4
@@ -1,7 +1,11 @@
|
||||
package stirling.software.common.controller;
|
||||
|
||||
import java.net.URLEncoder;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.List;
|
||||
import java.util.Map;
|
||||
|
||||
import org.springframework.http.MediaType;
|
||||
import org.springframework.http.ResponseEntity;
|
||||
import org.springframework.web.bind.annotation.DeleteMapping;
|
||||
import org.springframework.web.bind.annotation.GetMapping;
|
||||
@@ -14,6 +18,7 @@ import lombok.RequiredArgsConstructor;
|
||||
import lombok.extern.slf4j.Slf4j;
|
||||
|
||||
import stirling.software.common.model.job.JobResult;
|
||||
import stirling.software.common.model.job.ResultFile;
|
||||
import stirling.software.common.service.FileStorage;
|
||||
import stirling.software.common.service.JobQueue;
|
||||
import stirling.software.common.service.TaskManager;
|
||||
@@ -78,16 +83,31 @@ public class JobController {
|
||||
return ResponseEntity.badRequest().body("Job failed: " + result.getError());
|
||||
}
|
||||
|
||||
if (result.getFileId() != null) {
|
||||
// Handle multiple files - return metadata for client to download individually
|
||||
if (result.hasMultipleFiles()) {
|
||||
return ResponseEntity.ok()
|
||||
.contentType(MediaType.APPLICATION_JSON)
|
||||
.body(
|
||||
Map.of(
|
||||
"jobId",
|
||||
jobId,
|
||||
"hasMultipleFiles",
|
||||
true,
|
||||
"files",
|
||||
result.getAllResultFiles()));
|
||||
}
|
||||
|
||||
// Handle single file (download directly)
|
||||
if (result.hasFiles() && !result.hasMultipleFiles()) {
|
||||
try {
|
||||
byte[] fileContent = fileStorage.retrieveBytes(result.getFileId());
|
||||
List<ResultFile> files = result.getAllResultFiles();
|
||||
ResultFile singleFile = files.get(0);
|
||||
byte[] fileContent = fileStorage.retrieveBytes(singleFile.getFileId());
|
||||
return ResponseEntity.ok()
|
||||
.header("Content-Type", result.getContentType())
|
||||
.header("Content-Type", singleFile.getContentType())
|
||||
.header(
|
||||
"Content-Disposition",
|
||||
"form-data; name=\"attachment\"; filename=\""
|
||||
+ result.getOriginalFileName()
|
||||
+ "\"")
|
||||
createContentDispositionHeader(singleFile.getFileName()))
|
||||
.body(fileContent);
|
||||
} catch (Exception e) {
|
||||
log.error("Error retrieving file for job {}: {}", jobId, e.getMessage(), e);
|
||||
@@ -170,4 +190,127 @@ public class JobController {
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Get the list of files for a job
|
||||
*
|
||||
* @param jobId The job ID
|
||||
* @return List of files for the job
|
||||
*/
|
||||
@GetMapping("/api/v1/general/job/{jobId}/result/files")
|
||||
public ResponseEntity<?> getJobFiles(@PathVariable("jobId") String jobId) {
|
||||
JobResult result = taskManager.getJobResult(jobId);
|
||||
if (result == null) {
|
||||
return ResponseEntity.notFound().build();
|
||||
}
|
||||
|
||||
if (!result.isComplete()) {
|
||||
return ResponseEntity.badRequest().body("Job is not complete yet");
|
||||
}
|
||||
|
||||
if (result.getError() != null) {
|
||||
return ResponseEntity.badRequest().body("Job failed: " + result.getError());
|
||||
}
|
||||
|
||||
List<ResultFile> files = result.getAllResultFiles();
|
||||
return ResponseEntity.ok(
|
||||
Map.of(
|
||||
"jobId", jobId,
|
||||
"fileCount", files.size(),
|
||||
"files", files));
|
||||
}
|
||||
|
||||
/**
|
||||
* Get metadata for an individual file by its file ID
|
||||
*
|
||||
* @param fileId The file ID
|
||||
* @return The file metadata
|
||||
*/
|
||||
@GetMapping("/api/v1/general/files/{fileId}/metadata")
|
||||
public ResponseEntity<?> getFileMetadata(@PathVariable("fileId") String fileId) {
|
||||
try {
|
||||
// Verify file exists
|
||||
if (!fileStorage.fileExists(fileId)) {
|
||||
return ResponseEntity.notFound().build();
|
||||
}
|
||||
|
||||
// Find the file metadata from any job that contains this file
|
||||
ResultFile resultFile = taskManager.findResultFileByFileId(fileId);
|
||||
|
||||
if (resultFile != null) {
|
||||
return ResponseEntity.ok(resultFile);
|
||||
} else {
|
||||
// File exists but no metadata found, get basic info efficiently
|
||||
long fileSize = fileStorage.getFileSize(fileId);
|
||||
return ResponseEntity.ok(
|
||||
Map.of(
|
||||
"fileId",
|
||||
fileId,
|
||||
"fileName",
|
||||
"unknown",
|
||||
"contentType",
|
||||
"application/octet-stream",
|
||||
"fileSize",
|
||||
fileSize));
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.error("Error retrieving file metadata {}: {}", fileId, e.getMessage(), e);
|
||||
return ResponseEntity.internalServerError()
|
||||
.body("Error retrieving file metadata: " + e.getMessage());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Download an individual file by its file ID
|
||||
*
|
||||
* @param fileId The file ID
|
||||
* @return The file content
|
||||
*/
|
||||
@GetMapping("/api/v1/general/files/{fileId}")
|
||||
public ResponseEntity<?> downloadFile(@PathVariable("fileId") String fileId) {
|
||||
try {
|
||||
// Verify file exists
|
||||
if (!fileStorage.fileExists(fileId)) {
|
||||
return ResponseEntity.notFound().build();
|
||||
}
|
||||
|
||||
// Retrieve file content
|
||||
byte[] fileContent = fileStorage.retrieveBytes(fileId);
|
||||
|
||||
// Find the file metadata from any job that contains this file
|
||||
// This is for getting the original filename and content type
|
||||
ResultFile resultFile = taskManager.findResultFileByFileId(fileId);
|
||||
|
||||
String fileName = resultFile != null ? resultFile.getFileName() : "download";
|
||||
String contentType =
|
||||
resultFile != null ? resultFile.getContentType() : "application/octet-stream";
|
||||
|
||||
return ResponseEntity.ok()
|
||||
.header("Content-Type", contentType)
|
||||
.header("Content-Disposition", createContentDispositionHeader(fileName))
|
||||
.body(fileContent);
|
||||
} catch (Exception e) {
|
||||
log.error("Error retrieving file {}: {}", fileId, e.getMessage(), e);
|
||||
return ResponseEntity.internalServerError()
|
||||
.body("Error retrieving file: " + e.getMessage());
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Create Content-Disposition header with UTF-8 filename support
|
||||
*
|
||||
* @param fileName The filename to encode
|
||||
* @return Content-Disposition header value
|
||||
*/
|
||||
private String createContentDispositionHeader(String fileName) {
|
||||
try {
|
||||
String encodedFileName =
|
||||
URLEncoder.encode(fileName, StandardCharsets.UTF_8)
|
||||
.replace("+", "%20"); // URLEncoder uses + for spaces, but we want %20
|
||||
return "attachment; filename=\"" + fileName + "\"; filename*=UTF-8''" + encodedFileName;
|
||||
} catch (Exception e) {
|
||||
// Fallback to basic filename if encoding fails
|
||||
return "attachment; filename=\"" + fileName + "\"";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
+3
-2
@@ -19,6 +19,7 @@ import jakarta.servlet.http.HttpSession;
|
||||
|
||||
import stirling.software.common.model.job.JobResult;
|
||||
import stirling.software.common.model.job.JobStats;
|
||||
import stirling.software.common.model.job.ResultFile;
|
||||
import stirling.software.common.service.FileStorage;
|
||||
import stirling.software.common.service.JobQueue;
|
||||
import stirling.software.common.service.TaskManager;
|
||||
@@ -138,7 +139,7 @@ class JobControllerTest {
|
||||
|
||||
JobResult mockResult = new JobResult();
|
||||
mockResult.setJobId(jobId);
|
||||
mockResult.completeWithFile(fileId, originalFileName, contentType);
|
||||
mockResult.completeWithSingleFile(fileId, originalFileName, contentType, fileContent.length);
|
||||
|
||||
when(taskManager.getJobResult(jobId)).thenReturn(mockResult);
|
||||
when(fileStorage.retrieveBytes(fileId)).thenReturn(fileContent);
|
||||
@@ -215,7 +216,7 @@ class JobControllerTest {
|
||||
|
||||
JobResult mockResult = new JobResult();
|
||||
mockResult.setJobId(jobId);
|
||||
mockResult.completeWithFile(fileId, originalFileName, contentType);
|
||||
mockResult.completeWithSingleFile(fileId, originalFileName, contentType, 1024L);
|
||||
|
||||
when(taskManager.getJobResult(jobId)).thenReturn(mockResult);
|
||||
when(fileStorage.retrieveBytes(fileId)).thenThrow(new RuntimeException("File not found"));
|
||||
|
||||
Reference in New Issue
Block a user