spaCy/spacy/lang/sr/norm_exceptions.py

27 lines
636 B
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
_exc = {
# Slang
"ћале": "отац",
"кева": "мајка",
"смор": "досада",
"кец": "јединица",
"тебра": "брат",
"штребер": "ученик",
"факс": "факултет",
"профа": "професор",
"бус": "аутобус",
"пискарало": "службеник",
"бакутанер": "бака",
"џибер": "простак",
}
NORM_EXCEPTIONS = {}
for string, norm in _exc.items():
NORM_EXCEPTIONS[string] = norm
NORM_EXCEPTIONS[string.title()] = norm