mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 02:16:32 +03:00
428bae66b5
* add Tatar lang support * add Tatar letters * add Tatar tests * sign contributor agreement * sign contributor agreement [x] * remove comments from Language class * remove all template comments
32 lines
794 B
Python
32 lines
794 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .punctuation import TOKENIZER_INFIXES
|
|
from .stop_words import STOP_WORDS
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from ...attrs import LANG
|
|
from ...language import Language
|
|
from ...util import update_exc
|
|
|
|
|
|
class TatarDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'tt'
|
|
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
|
|
|
stop_words = STOP_WORDS
|
|
|
|
|
|
class Tatar(Language):
|
|
lang = 'tt'
|
|
Defaults = TatarDefaults
|
|
|
|
|
|
__all__ = ['Tatar']
|