I caught a rude character interfering with my data migration...

byte_size.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import unittest

RUDE = b"\xe3\x80\x82".decode("utf-8")

def limit_slice(maxlen, text):
  """Given a maximum length and text, return the text truncated to the provided
     length."""

  encoded = text.encode("utf-8", errors="replace")[:maxlen]
  return encoded.decode("utf-8", errors="replace")

def limit_count(maxlen, text):
  """Given a maximum length and text, return the text truncated to the provided
     length."""

  truncated = ""
  tl = 0

  for c in text:
    size = len(c.encode("utf-8"))

    if tl + size <= maxlen:
      truncated += c
      tl += size
    else:
      break

  return truncated

class TestLimits(unittest.TestCase):

  def test_slicing(self):

    testlen = 8
    truncated = limit_slice(testlen, "Hello " + RUDE + " world")
    self.assertTrue(len(truncated.encode("utf-8")) <= testlen)

  def test_count(self):

    testlen = 8
    truncated = limit_count(testlen, "Hello " + RUDE + " world")
    self.assertTrue(len(truncated.encode("utf-8")) <= testlen)

if __name__ == "__main__":
  unittest.main()

(Sorry for the delay)