#!/usr/bin/python3

import sys
from nltk import word_tokenize
import pyphen
import re

if len(sys.argv) != 2:
    print(f'Usage: {sys.argv[0]} <text file>')
    sys.exit(1)

with open(sys.argv[1], 'r') as f:
    text = f.readlines()

dic = pyphen.Pyphen(lang='es',left=1, right=1)

tokenized_lines = [word_tokenize(line, language='spanish') for line in text]

#print(tokenized_lines)

syllabificated_lines = []
for line in tokenized_lines:
    syllabificated_lines.append([dic.inserted(word).replace('-', ' -- ') for word in line])


for line in syllabificated_lines:
    line_as_str = ' '.join(line)
    print(re.sub(r'\s+([.,!?;:])', r'\1', line_as_str))