spaCy/spacy/lang/hu/__init__.py
Ines Montani e0cf4796a5 Move lookup tables out of the core library (#4346)
* Add default to util.get_entry_point

* Tidy up entry points

* Read lookups from entry points

* Remove lookup tables and related tests

* Add lookups install option

* Remove lemmatizer tests

* Remove logic to process language data files

* Update setup.cfg
2019-10-01 00:01:27 +02:00

35 lines
1.0 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from .stop_words import STOP_WORDS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
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
class Hungarian(Language):
lang = "hu"
Defaults = HungarianDefaults
__all__ = ["Hungarian"]