mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
2f981d5af1
Remove corpus-specific tag maps from the language data for languages without custom tokenizers. For languages with custom word segmenters that also provide tags (Japanese and Korean), the tag maps for the custom tokenizers are kept as the default. The default tag maps for languages without custom tokenizers are now the default tag map from `lang/tag_map/py`, UPOS -> UPOS.
27 lines
773 B
Python
27 lines
773 B
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...language import Language
|
|
from ...attrs import LANG
|
|
from ...util import update_exc
|
|
|
|
|
|
class BengaliDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: "bn"
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
|
|
class Bengali(Language):
|
|
lang = "bn"
|
|
Defaults = BengaliDefaults
|
|
|
|
|
|
__all__ = ["Bengali"]
|