erickrf

# -*- coding: utf-8 -*-

from __future__ import unicode_literals
from nltk.tokenize import RegexpTokenizer
import argparse
import os

"""
Script for tokenizing Portuguese text according to the Universal Dependencies
(UD) tokenization standards. This script was not created by the UD team; it was

paniq

max(-x,-y) = -min(x,y)
min(-x,-y) = -max(x,y)

abs(x) = abs(-x)
abs(x) = max(x,-x) = -min(x,-x)
abs(x*a) = if (a >= 0) abs(x)*a
              (a <  0) -abs(x)*a

// basically any commutative operation
min(x,y) + max(x,y) = x + y