mirror of https://github.com/explosion/spaCy.git
36 lines
1.0 KiB
Python
36 lines
1.0 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .stop_words import STOP_WORDS
|
|
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, TOKEN_MATCH
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class IndonesianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'id'
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = set(STOP_WORDS)
|
|
token_match = TOKEN_MATCH
|
|
prefixes = tuple(TOKENIZER_PREFIXES)
|
|
suffixes = tuple(TOKENIZER_SUFFIXES)
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
|
|
|
|
|
class Indonesian(Language):
|
|
lang = 'id'
|
|
Defaults = IndonesianDefaults
|
|
|
|
|
|
__all__ = ['Indonesian']
|