spaCy/spacy/lang/hu/__init__.py

35 lines
1.0 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2017-05-08 16:49:56 +03:00
from __future__ import unicode_literals
2017-05-08 16:49:56 +03:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from .stop_words import STOP_WORDS
2017-05-08 23:29:04 +03:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
2017-05-08 23:29:04 +03:00
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2017-05-08 16:49:56 +03:00
class HungarianDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: "hu"
lex_attr_getters[NORM] = add_lookups(
Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
prefixes = TOKENIZER_PREFIXES
suffixes = TOKENIZER_SUFFIXES
infixes = TOKENIZER_INFIXES
token_match = TOKEN_MATCH
2017-05-03 12:01:42 +03:00
class Hungarian(Language):
lang = "hu"
Defaults = HungarianDefaults
2017-05-03 12:01:42 +03:00
__all__ = ["Hungarian"]