spaCy/spacy/lang/en/__init__.py
Sofie Van Landeghem 1b2ec94382
Hyphen infix (#5770)
* infix split on hyphen when preceded by number

* clean up

* skip ukranian test instead of xfail
2020-07-20 14:48:51 +02:00

41 lines
1.2 KiB
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.

from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_INFIXES
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language
from ...attrs import LANG
from ...util import update_exc
def _return_en(_):
return "en"
class EnglishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = _return_en
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
syntax_iterators = SYNTAX_ITERATORS
infixes = TOKENIZER_INFIXES
single_orth_variants = [
{"tags": ["NFP"], "variants": ["", "..."]},
{"tags": [":"], "variants": ["-", "", "", "--", "---", "——"]},
]
paired_orth_variants = [
{"tags": ["``", "''"], "variants": [("'", "'"), ("", "")]},
{"tags": ["``", "''"], "variants": [('"', '"'), ("", "")]},
]
class English(Language):
lang = "en"
Defaults = EnglishDefaults
__all__ = ["English"]