mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-28 02:46:35 +03:00
873c16a4df
* add malay lang * fix token len * black format * reformat conftest malay * remove exceptions not exist in dbp * format code
25 lines
678 B
Python
25 lines
678 B
Python
from .stop_words import STOP_WORDS
|
|
from .punctuation import TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
|
from ...language import Language, BaseDefaults
|
|
|
|
|
|
class MalayDefaults(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 Malay(Language):
|
|
lang = "ms"
|
|
Defaults = MalayDefaults
|
|
|
|
|
|
__all__ = ["Malay"]
|