Add body_as_text, default_body.

Main intent here is to be more explicit about what form you're
getting the attachment body in - valid UTF-8 or binary, and has it
been cleaned up in order to be UTF-8?

1 files changed, 15 insertions, 6 deletions

diff --git a/app/models/foi_attachment.rb b/app/models/foi_attachment.rb
index 978e11a17..37a9c9827 100644
--- a/app/models/foi_attachment.rb
+++ b/app/models/foi_attachment.rb
@@ -62,19 +62,18 @@ class FoiAttachment < ActiveRecord::Base
         }
         update_display_size!
         @cached_body = d
+        if String.method_defined?(:encode)
+            @cached_body = @cached_body.force_encoding("ASCII-8BIT")
+        end
     end
 
+    # raw body, encoded as binary
     def body
         if @cached_body.nil?
             tries = 0
             delay = 1
             begin
-                binary_data = File.open(self.filepath, "rb" ){ |file| file.read }
-                if text_type?
-                    @cached_body = convert_string_to_utf8(binary_data, 'UTF-8').string
-                else
-                    @cached_body = binary_data
-                end
+                @cached_body = File.open(filepath, "rb" ){ |file| file.read }
             rescue Errno::ENOENT
                 # we've lost our cached attachments for some reason.  Reparse them.
                 if tries > BODY_MAX_TRIES
@@ -93,6 +92,16 @@ class FoiAttachment < ActiveRecord::Base
         return @cached_body
     end
 
+    # body as UTF-8 text, with scrubbing of invalid chars if needed
+    def body_as_text
+        convert_string_to_utf8(body, 'UTF-8')
+    end
+
+    # for text types, the scrubbed UTF-8 text. For all other types, the
+    # raw binary
+    def default_body
+        text_type? ? body_as_text.string : body
+    end
 
     # List of DSN codes taken from RFC 3463
     # http://tools.ietf.org/html/rfc3463