char_converter.rb

# config/initializers/char_converter.rb
require 'uri'

module Support
  class CharConverter

    def initialize(app)
      @app = app
    end

    def call(env)
      @app.call(self.class.sanitize_env(env))
    end

    def self.sanitize_env(env)
      ["HTTP_REFERER", "PATH_INFO", "QUERY_STRING", "REQUEST_PATH", "REQUEST_URI"].each do |key|
        next unless value = env[key]
        fixed = sanitize_string(URI.decode(value))
        env[key] = URI.encode(fixed) if fixed
      end
      ["HTTP_COOKIE"].each do |key|
        next unless value = env[key]
        fixed = sanitize_string(value)
        env[key] = fixed if fixed
      end
      env
    end

    def self.sanitize_string(string)
      return if !string.is_a?(String) || string == ''

      # Try it as UTF-8 directly
      cleaned = string.dup.force_encoding(Encoding::UTF_8)
      # Some of it might be old Windows code page
      # GBK for IE
      cleaned.encode(Encoding::UTF_8, Encoding::GBK) unless cleaned.valid_encoding?
    rescue EncodingError
      # Force it to UTF-8, throwing out invalid bits
      cleaned.encode(Encoding::UTF_8, invalid: :replace, undef: :replace)
    end

  end
end