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

# # Test/create feature 'unaccented' and 'transliteration'

# ## Table of content <a class="anchor" id="TOC"></a>
# * <a href="#bullet1">1 - test]</a>
# 

# In[8]:


import os
from unidecode import unidecode
import unicodedata

# Following variable should contain the relative path to the tf file to read 
# FileToRead = "..//tf//0.4//word.tf"

def make_transliteration(text):
    return unidecode(text)


def remove_accents(text):
    return ''.join(c for c in unicodedata.normalize('NFD', text) if unicodedata.category(c) != 'Mn')

greek_text_with_accents = "ἐν ἀρχῇ ἦν ὁ λόγος, καὶ ὁ λόγος ἦν πρὸς τὸν θεόν, καὶ θεὸς ἦν ὁ λόγος."
transliterated_text = make_transliteration(greek_text_with_accents)
unaccented_text= remove_accents(greek_text_with_accents)

print(transliterated_text) 
print(unaccented_text)


# In[ ]: