"""The assignment's measurement, in one place (shared by training and evaluation)."""
import regex

# one faithful unit = a run of letters/marks/numbers, or one visible non-space symbol
UNIT = regex.compile(r"[\p{L}\p{M}\p{N}]+|[^\s\p{L}\p{M}\p{N}]")


def units(text):
    return len(UNIT.findall(text))


def visible(text):
    return "".join(text.split())