spaCy/spacy/en/language_data.py

26 lines
819 B
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
from __future__ import unicode_literals
2016-12-18 15:54:19 +00:00
from .. import language_data as base
from ..language_data import update_exc, strings_to_exc, expand_exc
from ..symbols import ORTH, LEMMA
2016-12-18 14:36:50 +00:00
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
from .morph_rules import MORPH_RULES
2016-12-18 15:54:19 +00:00
TAG_MAP = dict(TAG_MAP)
STOP_WORDS = set(STOP_WORDS)
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
2016-12-18 15:54:19 +00:00
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, expand_exc(TOKENIZER_EXCEPTIONS, "'", ""))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
2016-12-07 19:29:52 +00:00
__all__ = ["TOKENIZER_EXCEPTIONS", "TAG_MAP", "STOP_WORDS", "MORPH_RULES"]