Ensuring that empty S3 files are not moved between S3 Buckets when a …

…Work is published (#1591)

app/services/s3_query_service.rb

@@ -209,6 +209,16 @@ def data_profile
   def publish_files(current_user)
     source_bucket = S3QueryService.pre_curation_config[:bucket]
     target_bucket = S3QueryService.post_curation_config[:bucket]
+    empty_files = client_s3_empty_files(reload: true, bucket_name: source_bucket)
+    # Do not move the empty files, however, ensure that it is noted that the
+    #   presence of empty files is specified in the provenance log.
+    unless empty_files.empty?
+      empty_files.each do |empty_file|
+        message = "Warning: Attempted to publish empty S3 file #{empty_file.filename}."
+        WorkActivity.add_work_activity(model.id, message, current_user.id, activity_type: WorkActivity::SYSTEM)
+      end
+    end
+
     files = client_s3_files(reload: true, bucket_name: source_bucket)
     snapshot = ApprovedUploadSnapshot.new(work: model)
     snapshot.store_files(files, current_user:)

spec/fixtures/s3_list_bucket_empty_result.xml

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<ListBucketResult xmlns="http://s3.amazonaws.com/doc/2006-03-01/">
+  <Name>pdc-describe-test1</Name>
+  <Prefix>10-34770/pe9w-x904</Prefix>
+  <KeyCount>4</KeyCount>
+  <MaxKeys>1000</MaxKeys>
+  <IsTruncated>false</IsTruncated>
+  <Contents>
+    <Key>10-34770/pe9w-x904/SCoData_combined_v1_2020-07_README.txt</Key>
+    <LastModified>2022-04-21T18:29:40.000Z</LastModified>
+    <ETag>&quot;008eec11c39e7038409739c0160a793a&quot;</ETag>
+    <Size>10759</Size>
+    <StorageClass>STANDARD</StorageClass>
+  </Contents>
+  <Contents>
+    <Key>10-34770/pe9w-x904/SCoData_combined_v1_2020-07_README.empty.txt</Key>
+    <LastModified>2022-04-21T18:29:40.000Z</LastModified>
+    <ETag>&quot;008eec11c39e7038409739c0160a793b&quot;</ETag>
+    <Size>0</Size>
+    <StorageClass>STANDARD</StorageClass>
+  </Contents>
+  <Contents>
+    <Key>10-34770/pe9w-x904/SCoData_combined_v1_2020-07_datapackage.json</Key>
+    <LastModified>2022-04-21T18:30:07.000Z</LastModified>
+    <ETag>&quot;7bd3d4339c034ebc663b990657714688&quot;</ETag>
+    <Size>12739</Size>
+    <StorageClass>STANDARD</StorageClass>
+  </Contents>
+  <Contents>
+    <Key>10-34770/pe9w-x904/foo/</Key>
+    <LastModified>2022-04-21T18:29:40.000Z</LastModified>
+    <ETag>&quot;008eec11c39e7038409739c0160a793c&quot;</ETag>
+    <Size>0</Size>
+    <StorageClass>STANDARD</StorageClass>
+  </Contents>
+</ListBucketResult>