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

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

# This is a playground for the development of two new features.
# 
# It depends on Python library:
# 
# * unidecode  = ASCII transliteration of unicode text

# In[5]:


from unidecode import unidecode
import unicodedata

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')

# test with John 1:1

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)      # in TF>0.5 use with: fmt='text-transliterated'
print(unaccented_text)          # in TF>0.5 use with: fmt='text-unaccented'
print(greek_text_with_accents)


# In[ ]: