mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 10:26:35 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
29 lines
824 B
Python
29 lines
824 B
Python
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
|
|
from .tag_map import TAG_MAP
|
|
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)
|
|
tag_map = TAG_MAP
|
|
stop_words = STOP_WORDS
|
|
prefixes = TOKENIZER_PREFIXES
|
|
suffixes = TOKENIZER_SUFFIXES
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
|
|
class Bengali(Language):
|
|
lang = "bn"
|
|
Defaults = BengaliDefaults
|
|
|
|
|
|
__all__ = ["Bengali"]
|