Set the 'ruby code' encoding for all files to UTF-8. This has the

effect that all string literals are UTF-8 now.

This was achieved with:
sed -i -e '1 { /^# encoding: utf-8/! { i # encoding: utf-8
} }' lib/logstash/**/*.rb

lib/logstash/JRUBY-6970-openssl.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # TODO(sissel): require "openssl" takes *ages* from the logstash jar
 # TODO(sissel): monkeypatch Kernel.require to apply this monkeypatch only after
 # a 'require "openssl" has occurred.

lib/logstash/JRUBY-6970.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # Monkeypatch for JRUBY-6970
 module Kernel
   alias_method :require_JRUBY_6970_hack, :require

lib/logstash/agent.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "clamp" # gem 'clamp'
 require "logstash/errors"
 require "i18n"

lib/logstash/codecs/base.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 require "logstash/event"
 require "logstash/plugin"

lib/logstash/codecs/compress_spooler.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::CompressSpooler < LogStash::Codecs::Base

lib/logstash/codecs/dots.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::Dots < LogStash::Codecs::Base

lib/logstash/codecs/fluent.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/util/charset"
 

lib/logstash/codecs/graphite.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/codecs/line"
 require "json"

lib/logstash/codecs/json.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/codecs/line"
 require "json"

lib/logstash/codecs/json_lines.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/codecs/line"
 require "json"

lib/logstash/codecs/json_spooler.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/codecs/spool"
 

lib/logstash/codecs/line.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/util/charset"
 

lib/logstash/codecs/msgpack.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::Msgpack < LogStash::Codecs::Base

lib/logstash/codecs/multiline.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 # The multiline codec is for taking line-oriented text and merging them into a

lib/logstash/codecs/netflow.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/codecs/netflow/util.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "bindata"
 require "ipaddr"
 

lib/logstash/codecs/noop.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::Noop < LogStash::Codecs::Base

lib/logstash/codecs/oldlogstashjson.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::OldLogStashJSON < LogStash::Codecs::Base

lib/logstash/codecs/plain.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 require "logstash/util/charset"
 

lib/logstash/codecs/rubydebug.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::RubyDebug < LogStash::Codecs::Base

lib/logstash/codecs/spool.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/codecs/base"
 
 class LogStash::Codecs::Spool < LogStash::Codecs::Base

lib/logstash/config/config_ast.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "treetop"
 class Treetop::Runtime::SyntaxNode
   def compile

lib/logstash/config/file.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 require "logstash/config/grammar"
 require "logstash/config/config_ast"

lib/logstash/config/grammar.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # Autogenerated from a Treetop grammar. Edits may be lost.
 
 

lib/logstash/config/mixin.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 
 require "logstash/namespace"
 require "logstash/config/registry"

lib/logstash/config/registry.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 
 # Global config registry.

lib/logstash/errors.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 module LogStash
   class Error < ::StandardError; end
   class ConfigurationError < Error; end

lib/logstash/event.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "json"
 require "time"
 require "date"

lib/logstash/filters/advisor.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/alter.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/anonymize.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/base.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 require "logstash/logging"
 require "logstash/plugin"

lib/logstash/filters/checksum.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "yaml"

lib/logstash/filters/cidr.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "ipaddr"

lib/logstash/filters/cipher.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/clone.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/collate.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/csv.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/date.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/dns.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # DNS Filter
 #
 # This filter will resolve any IP addresses from a field of your choosing.

lib/logstash/filters/drop.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/environment.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/extractnumbers.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require 'logstash/namespace'
 require 'logstash/filters/base'
 

lib/logstash/filters/gelfify.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/geoip.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "tempfile"

lib/logstash/filters/grep.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/grok.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "set"

lib/logstash/filters/grokdiscovery.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/json.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/json_encode.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/kv.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/metaevent.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/metrics.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "securerandom"
 require "logstash/filters/base"
 require "logstash/namespace"

lib/logstash/filters/multiline.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # multiline filter
 #
 # This filter will collapse multiline messages into a single event.

lib/logstash/filters/mutate.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/noop.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/prune.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/railsparallelrequest.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # parallel request filter
 #
 # This filter will separate out the parallel requests into separate events.

lib/logstash/filters/range.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/ruby.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/sleep.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/split.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/syslog_pri.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/translate.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/unique.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/urldecode.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "uri"

lib/logstash/filters/useragent.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "tempfile"

lib/logstash/filters/uuid.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 require "securerandom"

lib/logstash/filters/xml.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filters/zeromq.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/filters/base"
 require "logstash/namespace"
 

lib/logstash/filterworker.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 require "logstash/logging"
 require "logstash/plugin"

lib/logstash/inputs/base.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/namespace"
 require "logstash/event"
 require "logstash/plugin"

lib/logstash/inputs/drupal_dblog.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "date"
 require "logstash/inputs/base"
 require "logstash/namespace"

lib/logstash/inputs/drupal_dblog/jdbcconnection.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "java"
 require "rubygems"
 require "jdbc/mysql"

lib/logstash/inputs/elasticsearch.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "logstash/util/socket_peer"

lib/logstash/inputs/eventlog.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "socket"

lib/logstash/inputs/eventlog/racob_fix.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # The jruby-win32ole gem uses 'java.lang.System.set_property' to
 # tell java(?) where to find the racob dll.
 #

lib/logstash/inputs/exec.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "socket" # for Socket.gethostname

lib/logstash/inputs/file.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 

lib/logstash/inputs/ganglia.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "date"
 require "logstash/filters/grok"
 require "logstash/filters/date"

lib/logstash/inputs/ganglia/gmondpacket.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # Inspiration
 # https://github.com/fastly/ganglia/blob/master/lib/gm_protocol.x
 # https://github.com/igrigorik/gmetric/blob/master/lib/gmetric.rb

lib/logstash/inputs/ganglia/xdr.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 # xdr.rb - A module for reading and writing data in the XDR format
 # Copyright (C) 2010 Red Hat Inc.
 #

lib/logstash/inputs/gelf.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "date"
 require "logstash/inputs/base"
 require "logstash/namespace"

lib/logstash/inputs/gemfire.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/threadable"
 require "logstash/namespace"
 

lib/logstash/inputs/generator.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/threadable"
 require "logstash/namespace"
 require "socket" # for Socket.gethostname

lib/logstash/inputs/graphite.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/tcp"
 require "logstash/namespace"
 

lib/logstash/inputs/heroku.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 

lib/logstash/inputs/imap.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "stud/interval"

lib/logstash/inputs/irc.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "thread"

lib/logstash/inputs/log4j.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "logstash/util/socket_peer"

lib/logstash/inputs/lumberjack.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 
@@ -44,7 +45,7 @@ class LogStash::Inputs::Lumberjack < LogStash::Inputs::Base
     @lumberjack.run do |l|
       @codec.decode(l.delete("line")) do |event|
         decorate(event)
-        l.each { |k,v| event[k] = v }
+        l.each { |k,v| event[k] = v; v.force_encoding("UTF-8") }
         output_queue << event
       end
     end

lib/logstash/inputs/pipe.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "socket" # for Socket.gethostname

lib/logstash/inputs/rabbitmq.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/threadable"
 require "logstash/namespace"
 

lib/logstash/inputs/rabbitmq/bunny.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 class LogStash::Inputs::RabbitMQ
   module BunnyImpl
     def register

lib/logstash/inputs/rabbitmq/hot_bunnies.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 class LogStash::Inputs::RabbitMQ
   # HotBunnies-based implementation for JRuby
   module HotBunniesImpl

lib/logstash/inputs/redis.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/inputs/threadable"
 require "logstash/namespace"

lib/logstash/inputs/relp.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "logstash/util/relp"

lib/logstash/inputs/s3.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 

lib/logstash/inputs/snmptrap.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 

lib/logstash/inputs/sqlite.rb

@@ -1,3 +1,4 @@
+# encoding: utf-8
 require "logstash/inputs/base"
 require "logstash/namespace"
 require "socket"