spaCy/spacy/en/language_data.py

26 lines
819 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
from .. import language_data as base
from ..language_data import update_exc, strings_to_exc, expand_exc
from ..symbols import ORTH, LEMMA
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
TAG_MAP = dict(TAG_MAP)
STOP_WORDS = set(STOP_WORDS)
TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
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))
__all__ = ["TOKENIZER_EXCEPTIONS", "TAG_MAP", "STOP_WORDS", "MORPH_RULES"]