kou commented on code in PR #39298:
URL: https://github.com/apache/arrow/pull/39298#discussion_r1431915437
##########
cpp/src/arrow/filesystem/azurefs.cc:
##########
@@ -786,8 +789,71 @@ class ObjectAppendStream final : public io::OutputStream {
Storage::Metadata metadata_;
};
+bool IsDfsEmulator(const AzureOptions& options) {
+ return options.dfs_storage_authority != ".dfs.core.windows.net";
+}
+
} // namespace
+// -----------------------------------------------------------------------
+// internal implementation
+
+namespace internal {
+
+Result<HNSSupport> CheckIfHierarchicalNamespaceIsEnabled(
+ DataLake::DataLakeFileSystemClient& adlfs_client, const AzureOptions&
options) {
+ try {
+ auto directory_client = adlfs_client.GetDirectoryClient("");
+ // GetAccessControlList will fail on storage accounts
+ // without hierarchical namespace enabled.
+ directory_client.GetAccessControlList();
+ return HNSSupport::kEnabled;
+ } catch (std::out_of_range& exception) {
+ // Azurite issue detected.
+ DCHECK(IsDfsEmulator(options));
+ return HNSSupport::kDisabled;
+ } catch (const Storage::StorageException& exception) {
+ // Flat namespace storage accounts with "soft delete" enabled return
+ //
+ // "Conflict - This endpoint does not support BlobStorageEvents
+ // or SoftDelete. [...]" [1],
+ //
+ // otherwise it returns:
+ //
+ // "BadRequest - This operation is only supported on a hierarchical
namespace
+ // account."
+ //
+ // [1]:
+ //
https://learn.microsoft.com/en-us/answers/questions/1069779/this-endpoint-does-not-support-blobstorageevents-o
+ switch (exception.StatusCode) {
+ case Http::HttpStatusCode::BadRequest:
+ case Http::HttpStatusCode::Conflict:
+ return HNSSupport::kDisabled;
+ case Http::HttpStatusCode::NotFound:
+ if (IsDfsEmulator(options)) {
+ return HNSSupport::kDisabled;
+ }
+ // Did we get an error because of the container not existing?
+ if (IsContainerNotFound(exception)) {
+ return HNSSupport::kContainerNotFound;
+ }
+ [[fallthrough]];
+ default:
+ if (exception.ErrorCode == "HierarchicalNamespaceNotEnabled") {
+ return HNSSupport::kDisabled;
+ }
+ return ExceptionToStatus("Check for hierarchical namespace support on
'" +
+ adlfs_client.GetUrl() +
+ "' failed with an unexpected error.",
+ exception);
+ }
+ }
+ DCHECK(false) << "Unreachable";
+ return HNSSupport::kUnknown;
Review Comment:
Do we need this?
It seems that all cases have `return`. Does compiler complain without this?
##########
cpp/src/arrow/filesystem/azurefs.cc:
##########
@@ -1177,18 +1269,19 @@ class AzureFileSystem::Impl {
}
}
- ARROW_ASSIGN_OR_RAISE(auto hierarchical_namespace_enabled,
- hns_detector_.Enabled(location.container));
- if (!hierarchical_namespace_enabled) {
+ auto adlfs_client =
datalake_service_client_->GetFileSystemClient(location.container);
+ ARROW_ASSIGN_OR_RAISE(auto hns_support,
HierarchicalNamespaceSupport(adlfs_client));
+ if (hns_support == HNSSupport::kContainerNotFound) {
+ return PathNotFound(location);
+ }
+ if (hns_support == HNSSupport::kDisabled && !IsDfsEmulator(options_)) {
Review Comment:
Do we need `&& !IsDfsEmulator(options_)` here?
--
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]
