Encode Content-Disposition filenames

Users downloading non-ASCII attachments would see garbled characters.
When used with object storage, AWS S3 would return an InvalidArgument
error: Header value cannot be represented using ISO-8859-1.

Per RFC 5987 and RFC 6266, Content-Disposition should be encoded
properly. This commit takes the Rails 6 implementation of
ActiveSuppport::Http::ContentDisposition
(https://github.com/rails/rails/pull/33829) and ports it here.

Closes https://gitlab.com/gitlab-org/gitlab-ce/issues/47673

2 files changed, 49 insertions, 8 deletions

diff --git a/lib/api/helpers.rb b/lib/api/helpers.rb
index fa6c9777824..e3d0b981065 100644
--- a/lib/api/helpers.rb
+++ b/lib/api/helpers.rb
@@ -422,7 +422,7 @@ module API
 
     def present_disk_file!(path, filename, content_type = 'application/octet-stream')
       filename ||= File.basename(path)
-      header['Content-Disposition'] = "attachment; filename=#{filename}"
+      header['Content-Disposition'] = ::Gitlab::ContentDisposition.format(disposition: 'attachment', filename: filename)
       header['Content-Transfer-Encoding'] = 'binary'
       content_type content_type
 
@@ -496,7 +496,7 @@ module API
     def send_git_blob(repository, blob)
       env['api.format'] = :txt
       content_type 'text/plain'
-      header['Content-Disposition'] = content_disposition('inline', blob.name)
+      header['Content-Disposition'] = ::Gitlab::ContentDisposition.format(disposition: 'inline', filename: blob.name)
 
       # Let Workhorse examine the content and determine the better content disposition
       header[Gitlab::Workhorse::DETECT_HEADER] = "true"
@@ -533,11 +533,5 @@ module API
 
       params[:archived]
     end
-
-    def content_disposition(disposition, filename)
-      disposition += %(; filename=#{filename.inspect}) if filename.present?
-
-      disposition
-    end
   end
 end
diff --git a/lib/gitlab/content_disposition.rb b/lib/gitlab/content_disposition.rb
new file mode 100644
index 00000000000..96ead8a9fbf
--- /dev/null
+++ b/lib/gitlab/content_disposition.rb
@@ -0,0 +1,47 @@
+# frozen_string_literal: true
+# This ports ActionDispatch::Http::ContentDisposition (https://github.com/rails/rails/pull/33829,
+# which will be available in Rails 6.
+module Gitlab
+  class ContentDisposition # :nodoc:
+    def self.format(disposition:, filename:)
+      new(disposition: disposition, filename: filename).to_s
+    end
+
+    attr_reader :disposition, :filename
+
+    def initialize(disposition:, filename:)
+      @disposition = disposition
+      @filename = filename
+    end
+
+    # rubocop:disable Style/VariableInterpolation
+    TRADITIONAL_ESCAPED_CHAR = /[^ A-Za-z0-9!#$+.^_`|~-]/
+
+    def ascii_filename
+      'filename="' + percent_escape(::I18n.transliterate(filename), TRADITIONAL_ESCAPED_CHAR) + '"'
+    end
+
+    RFC_5987_ESCAPED_CHAR = /[^A-Za-z0-9!#$&+.^_`|~-]/
+    # rubocop:enable Style/VariableInterpolation
+
+    def utf8_filename
+      "filename*=UTF-8''" + percent_escape(filename, RFC_5987_ESCAPED_CHAR)
+    end
+
+    def to_s
+      if filename
+        "#{disposition}; #{ascii_filename}; #{utf8_filename}"
+      else
+        "#{disposition}"
+      end
+    end
+
+    private
+
+    def percent_escape(string, pattern)
+      string.gsub(pattern) do |char|
+        char.bytes.map { |byte| "%%%02X" % byte }.join
+      end
+    end
+  end
+end