- (Object) limit(limit)

'こんにちは'.mb_chars.limit(7).to_s # => "こん"

s.each_char.each_with_object('') do|char, result|
  if result.bytesize + char.bytesize > 255
    break result
  else
    result << char
  end
end

def limit_bytesize(str, size)
  str.encoding.name == 'UTF-8' or raise ArgumentError, "str must have UTF-8 encoding"

  # Change to canonical unicode form (compose any decomposed characters).
  # Works only if you're using active_support
  str = str.mb_chars.compose.to_s if str.respond_to?(:mb_chars)

  # Start with a string of the correct byte size, but
  # with a possibly incomplete char at the end.
  new_str = str.byteslice(0, size)

  # We need to force_encoding from utf-8 to utf-8 so ruby will re-validate
  # (idea from halfelf).
  until new_str[-1].force_encoding('utf-8').valid_encoding?
    # remove the invalid char
    new_str = new_str.slice(0..-2)
  end
  new_str
end

>> limit_bytesize("abcu2014d", 4)
=> "abc"
>> limit_bytesize("abcu2014d", 5)
=> "abc"
>> limit_bytesize("abcu2014d", 6)
=> "abc—"
>> limit_bytesize("abcu2014d", 7)
=> "abc—d"

>> limit_bytesize("abcu0065u0301d", 4)
=> "abce"
>> limit_bytesize("abcu0065u0301d", 5)
=> "abce"
>> limit_bytesize("abcu0065u0301d", 6)
=> "abcé"
>> limit_bytesize("abcu0065u0301d", 7)
=> "abcéd"

>> limit_bytesize("abcu0065u0301d", 4)
=> "abc"
>> limit_bytesize("abcu0065u0301d", 5)
=> "abcé"
>> limit_bytesize("abcu0065u0301d", 6)
=> "abcéd"

s = "δogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδogδog"
count = 0
while true
  more_truncate = "a" + (255-count).to_s
  s2 = s.unpack(more_truncate)[0]
  s2.force_encoding 'utf-8'

  if s2[-1].valid_encoding?
    break
  else
    count += 1
  end
end

s2.force_encoding 'utf-8'
puts s2

>> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".size
=> 20
>> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".bytesize
=> 80
>> "🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪🔪".truncate_bytes(20)
=> "🔪🔪🔪🔪…"