handle zip upload

lib/templates/create_attachments.rb

@@ -3,6 +3,19 @@
 module Templates
   module CreateAttachments
     PDF_CONTENT_TYPE = 'application/pdf'
+    ZIP_CONTENT_TYPE = 'application/zip'
+    JSON_CONTENT_TYPE = 'application/json'
+    DOCUMENT_EXTENSIONS = %w[.docx .doc .xlsx .xls .odt .rtf].freeze
+
+    DOCUMENT_CONTENT_TYPES = %w[
+      application/vnd.openxmlformats-officedocument.wordprocessingml.document
+      application/msword
+      application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
+      application/vnd.ms-excel
+      application/vnd.oasis.opendocument.text
+      application/rtf
+    ].freeze
+
     ANNOTATIONS_SIZE_LIMIT = 6.megabytes
     InvalidFileType = Class.new(StandardError)
     PdfEncrypted = Class.new(StandardError)
@@ -10,7 +23,7 @@ module Templates
     module_function
 
     def call(template, params, extract_fields: false)
-      Array.wrap(params[:files].presence || params[:file]).map do |file|
+      extract_zip_files(params[:files].presence || params[:file]).flat_map do |file|
         handle_file_types(template, file, params, extract_fields:)
       end
     end
@@ -53,6 +66,40 @@ module Templates
       raise PdfEncrypted
     end
 
+    def extract_zip_files(files)
+      extracted_files = []
+
+      Array.wrap(files).each do |file|
+        if file.content_type == ZIP_CONTENT_TYPE
+          Zip::File.open(file.tempfile).each do |entry|
+            next if entry.directory?
+
+            tempfile = Tempfile.new(entry.name)
+            tempfile.binmode
+            entry.get_input_stream { |in_stream| IO.copy_stream(in_stream, tempfile) }
+            tempfile.rewind
+
+            type = Marcel::MimeType.for(tempfile, name: entry.name)
+
+            next if type.exclude?('image') &&
+                    type != PDF_CONTENT_TYPE &&
+                    type != JSON_CONTENT_TYPE &&
+                    DOCUMENT_CONTENT_TYPES.exclude?(type)
+
+            extracted_files << ActionDispatch::Http::UploadedFile.new(
+              filename: File.basename(entry.name),
+              type:,
+              tempfile:
+            )
+          end
+        else
+          extracted_files << file
+        end
+      end
+
+      extracted_files
+    end
+
     def handle_file_types(template, file, params, extract_fields:)
       if file.content_type.include?('image') || file.content_type == PDF_CONTENT_TYPE
         return handle_pdf_or_image(template, file, file.read, params, extract_fields:)