Validate HTTP response length while receiving (#6891)

to_s method of HTTP::Response keeps blocking while it receives the whole
content, no matter how it is big. This means it may waste time to receive
unacceptably large files. It may also consume memory and disk in the
process. This solves the inefficency by checking response length while
receiving.

1 files changed, 6 insertions, 5 deletions

diff --git a/app/services/fetch_atom_service.rb b/app/services/fetch_atom_service.rb
index 48ad5dcd3..62dea8298 100644
--- a/app/services/fetch_atom_service.rb
+++ b/app/services/fetch_atom_service.rb
@@ -38,13 +38,14 @@ class FetchAtomService < BaseService
     return nil if response.code != 200
 
     if response.mime_type == 'application/atom+xml'
-      [@url, { prefetched_body: response.to_s }, :ostatus]
+      [@url, { prefetched_body: response.body_with_limit }, :ostatus]
     elsif ['application/activity+json', 'application/ld+json; profile="https://www.w3.org/ns/activitystreams"'].include?(response.mime_type)
-      json = body_to_json(response.to_s)
+      body = response.body_with_limit
+      json = body_to_json(body)
       if supported_context?(json) && json['type'] == 'Person' && json['inbox'].present?
-        [json['id'], { prefetched_body: response.to_s, id: true }, :activitypub]
+        [json['id'], { prefetched_body: body, id: true }, :activitypub]
       elsif supported_context?(json) && json['type'] == 'Note'
-        [json['id'], { prefetched_body: response.to_s, id: true }, :activitypub]
+        [json['id'], { prefetched_body: body, id: true }, :activitypub]
       else
         @unsupported_activity = true
         nil
@@ -61,7 +62,7 @@ class FetchAtomService < BaseService
   end
 
   def process_html(response)
-    page = Nokogiri::HTML(response.to_s)
+    page = Nokogiri::HTML(response.body_with_limit)
 
     json_link = page.xpath('//link[@rel="alternate"]').find { |link| ['application/activity+json', 'application/ld+json; profile="https://www.w3.org/ns/activitystreams"'].include?(link['type']) }
     atom_link = page.xpath('//link[@rel="alternate"]').find { |link| link['type'] == 'application/atom+xml' }