25 lines
698 B
Python
25 lines
698 B
Python
|
from ...language import BaseDefaults, Language
|
||
|
|
from .lex_attrs import LEX_ATTRS
|
||
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
|
||
|
|
from .stop_words import STOP_WORDS
|
||
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
||
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
|
|
|
||
|
|
|
||
|
|
class IndonesianDefaults(BaseDefaults):
|
||
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
||
|
|
prefixes = TOKENIZER_PREFIXES
|
||
|
|
suffixes = TOKENIZER_SUFFIXES
|
||
|
|
infixes = TOKENIZER_INFIXES
|
||
|
|
syntax_iterators = SYNTAX_ITERATORS
|
||
|
|
lex_attr_getters = LEX_ATTRS
|
||
|
|
stop_words = STOP_WORDS
|
||
|
|
|
||
|
|
|
||
|
|
class Indonesian(Language):
|
||
|
|
lang = "id"
|
||
|
|
Defaults = IndonesianDefaults
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ["Indonesian"]
|