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.

3 files changed, 31 insertions, 3 deletions

diff --git a/app/lib/exceptions.rb b/app/lib/exceptions.rb
index 95e3365c2..e88e98eae 100644
--- a/app/lib/exceptions.rb
+++ b/app/lib/exceptions.rb
@@ -5,6 +5,7 @@ module Mastodon
   class NotPermittedError < Error; end
   class ValidationError < Error; end
   class HostValidationError < ValidationError; end
+  class LengthValidationError < ValidationError; end
   class RaceConditionError < Error; end
 
   class UnexpectedResponseError < Error
diff --git a/app/lib/provider_discovery.rb b/app/lib/provider_discovery.rb
index bbd3a2d43..3bec7211b 100644
--- a/app/lib/provider_discovery.rb
+++ b/app/lib/provider_discovery.rb
@@ -18,7 +18,7 @@ class ProviderDiscovery < OEmbed::ProviderDiscovery
              else
                Request.new(:get, url).perform do |res|
                  raise OEmbed::NotFound, url if res.code != 200 || res.mime_type != 'text/html'
-                 Nokogiri::HTML(res.to_s)
+                 Nokogiri::HTML(res.body_with_limit)
                end
              end
 
diff --git a/app/lib/request.rb b/app/lib/request.rb
index 8a127c65f..dca93a6e9 100644
--- a/app/lib/request.rb
+++ b/app/lib/request.rb
@@ -40,7 +40,7 @@ class Request
     end
 
     begin
-      yield response
+      yield response.extend(ClientLimit)
     ensure
       http_client.close
     end
@@ -99,6 +99,33 @@ class Request
     @http_client ||= HTTP.timeout(:per_operation, timeout).follow(max_hops: 2)
   end
 
+  module ClientLimit
+    def body_with_limit(limit = 1.megabyte)
+      raise Mastodon::LengthValidationError if content_length.present? && content_length > limit
+
+      if charset.nil?
+        encoding = Encoding::BINARY
+      else
+        begin
+          encoding = Encoding.find(charset)
+        rescue ArgumentError
+          encoding = Encoding::BINARY
+        end
+      end
+
+      contents = String.new(encoding: encoding)
+
+      while (chunk = readpartial)
+        contents << chunk
+        chunk.clear
+
+        raise Mastodon::LengthValidationError if contents.bytesize > limit
+      end
+
+      contents
+    end
+  end
+
   class Socket < TCPSocket
     class << self
       def open(host, *args)
@@ -118,5 +145,5 @@ class Request
     end
   end
 
-  private_constant :Socket
+  private_constant :ClientLimit, :Socket
 end