Use Tempfiles, rather than StringIO, when decompressing a tarball (#719)

Co-authored-by: Max Kadel <[email protected]> Co-authored-by: Mark Zelesky <[email protected]> Co-authored-by: Christina Chortaria <[email protected]>
pulibrary · Mar 14, 2024 · fa0e961 · fa0e961
1 parent 5a9e970
commit fa0e961
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 3 deletions.
diff --git a/app/models/tarball.rb b/app/models/tarball.rb
@@ -5,7 +5,7 @@
 
 # take some .tar.gz IO (File, Net::SFTP::Operations::File, StringIO,
 # or similar) and make its uncompressed contents available as an
-# array of IO objects
+# array of Tempfile objects
 class Tarball
   def initialize(file)
     @file = file
@@ -14,7 +14,12 @@ def initialize(file)
   def contents
     @contents ||= untar.map do |entry|
       next unless entry.file?
-      StringIO.new entry.read
+      tempfile = Tempfile.new(binmode: true)
+      while (chunk = entry.read(10))
+        tempfile.write chunk
+      end
+      tempfile.rewind
+      tempfile
     end.compact
   end
 

diff --git a/spec/models/alma_submit_collection/alma_recap_file_list_spec.rb b/spec/models/alma_submit_collection/alma_recap_file_list_spec.rb
@@ -49,7 +49,7 @@
                     '<subfield code="b">Indian agriculture after liberalization /</subfield>'\
                     '<subfield code="c">edited by R. Ramakumar.</subfield></datafield>'
       decompressed_file_contents = alma_recap_file_list.download_and_decompress_file(alma_recap_filename)
-      expect(decompressed_file_contents.first.string).to include(title_field)
+      expect(decompressed_file_contents.first.read).to include(title_field)
     end
   end
   describe '#mark_files_as_processed' do