mirror of https://github.com/explosion/spaCy.git
39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from pathlib import Path
|
|
|
|
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, load_language_data
|
|
|
|
|
|
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
|
|
lemma_path = Path(__file__).parent / "lemmas.json"
|
|
lemma_lookup = load_language_data(lemma_path)
|
|
|
|
|
|
class Hungarian(Language):
|
|
lang = "hu"
|
|
Defaults = HungarianDefaults
|
|
|
|
|
|
__all__ = ["Hungarian"]
|