spaCy/spacy/lang/ro/tokenizer_exceptions.py
ines c6fea3e5f6 Add Romanian and Croatian skeletons (experimental)
Add language data templates to make it easier for others to contribute to the language support
2017-11-01 23:04:28 +01:00

18 lines
359 B
Python

# coding: utf8
from __future__ import unicode_literals
from ...symbols import ORTH
_exc = {}
# Source: https://en.wiktionary.org/wiki/Category:Romanian_abbreviations
for orth in [
"1-a", "1-ul", "10-a", "10-lea", "2-a", "3-a", "3-lea", "6-lea",
"d-voastră", "dvs.", "Rom.", "str."]:
_exc[orth] = [{ORTH: orth}]
TOKENIZER_EXCEPTIONS = _exc