Ma77Ball commented on code in PR #6447:
URL: https://github.com/apache/texera/pull/6447#discussion_r3610273350
##########
file-service/src/main/scala/org/apache/texera/service/resource/DatasetResource.scala:
##########
@@ -1298,6 +1305,187 @@ class DatasetResource extends LazyLogging {
}
}
+ @POST
+ @RolesAllowed(Array("REGULAR", "ADMIN"))
+ @Path("/{did}/drive-export")
+ @Consumes(Array(MediaType.APPLICATION_JSON))
+ def exportDatasetToDrive(
+ @PathParam("did") did: Integer,
+ @QueryParam("dvid") dvid: Integer,
+ @QueryParam("latest") latest: java.lang.Boolean,
+ request: DriveExportRequest,
+ @Auth user: SessionUser
+ ): Response = {
+ if
(!request.sessionUri.startsWith("https://www.googleapis.com/upload/drive/";)) {
+ throw new BadRequestException("Invalid session URI")
+ }
+ withTransaction(context) { ctx =>
+ if ((dvid != null && latest != null) || (dvid == null && latest ==
null)) {
+ throw new BadRequestException("Specify exactly one: dvid=<ID> OR
latest=true")
+ }
+
+ val uid = user.getUid
+ if (!userHasReadAccess(ctx, did, uid)) {
+ throw new ForbiddenException(ERR_USER_HAS_NO_ACCESS_TO_DATASET_MESSAGE)
+ }
+
+ val dataset = getDatasetByID(ctx, did)
+ if (!userOwnDataset(ctx, did, uid) && !dataset.getIsDownloadable) {
+ throw new ForbiddenException("Dataset download is not allowed")
+ }
+
+ val datasetVersion = if (dvid != null) {
+ getDatasetVersionByID(ctx, dvid)
+ } else {
+ getLatestDatasetVersion(ctx, did).getOrElse(
+ throw new NotFoundException(ERR_DATASET_VERSION_NOT_FOUND_MESSAGE)
+ )
+ }
+
+ val repositoryName = dataset.getRepositoryName
+ val versionHash = datasetVersion.getVersionHash
+ val objects = withLakeFSErrorHandling(
+ s"listing files of version '$versionHash' of dataset
'${dataset.getName}'"
+ ) {
+ LakeFSStorageClient.retrieveObjectsOfVersion(repositoryName,
versionHash)
+ }
+
+ if (objects.isEmpty) {
+ throw new NotFoundException(s"No objects found in version
$versionHash")
+ }
+
+ val totalBytes = objects.map(_.getSizeBytes.longValue()).sum
+ // TODO: remove this limit once chunked resumable upload to Drive is
implemented
+ if (totalBytes > DRIVE_EXPORT_MAX_DATASET_BYTES) {
+ throw new BadRequestException("Dataset version exceeds the 500 MB
export limit.")
+ }
+ if (totalBytes > DRIVE_EXPORT_MAX_FILE_BYTES) {
+ throw new ForbiddenException("Dataset version exceeds the 5 TB Google
Drive export limit.")
+ }
Review Comment:
The 500 MB check is the first to run for any size over 500 MB, so this 5 TB
branch is unreachable dead code here. I recommend dropping it until the feature
is added:
```suggestion
if (totalBytes > DRIVE_EXPORT_MAX_DATASET_BYTES) {
throw new BadRequestException("Dataset version exceeds the 500 MB
export limit.")
}
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
