mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
31 lines
765 B
Python
31 lines
765 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
||
|
|
from .stop_words import STOP_WORDS
|
||
|
|
from .lex_attrs import LEX_ATTRS
|
||
|
|
from ..tag_map import TAG_MAP
|
||
|
|
|
||
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
|
|
from ...language import Language
|
||
|
|
from ...attrs import LANG, NORM
|
||
|
|
from ...util import update_exc
|
||
|
|
|
||
|
|
|
||
|
|
class UrduDefaults(Language.Defaults):
|
||
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
||
|
|
lex_attr_getters.update(LEX_ATTRS)
|
||
|
|
lex_attr_getters[LANG] = lambda text: 'ur'
|
||
|
|
|
||
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
||
|
|
tag_map = TAG_MAP
|
||
|
|
stop_words = STOP_WORDS
|
||
|
|
|
||
|
|
|
||
|
|
class Urdu(Language):
|
||
|
|
lang = 'ur'
|
||
|
|
Defaults = UrduDefaults
|
||
|
|
|
||
|
|
|
||
|
|
__all__ = ['Urdu']
|