2017-03-12 15:07:28 +03:00
|
|
|
# coding: utf8
|
2017-02-28 04:48:37 +03:00
|
|
|
from __future__ import unicode_literals, print_function
|
|
|
|
|
|
|
|
|
|
from ..language import Language
|
|
|
|
|
from ..attrs import LANG
|
|
|
|
|
|
|
|
|
|
from .language_data import *
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class Bengali(Language):
|
|
|
|
|
lang = 'bn'
|
|
|
|
|
|
|
|
|
|
class Defaults(Language.Defaults):
|
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'bn'
|
|
|
|
|
|
|
|
|
|
tokenizer_exceptions = TOKENIZER_EXCEPTIONS
|
2017-03-04 09:20:08 +03:00
|
|
|
tag_map = TAG_MAP
|
2017-02-28 04:48:37 +03:00
|
|
|
stop_words = STOP_WORDS
|
2017-03-04 09:20:08 +03:00
|
|
|
lemma_rules = LEMMA_RULES
|
2017-02-28 18:07:14 +03:00
|
|
|
|
|
|
|
|
prefixes = tuple(TOKENIZER_PREFIXES)
|
|
|
|
|
suffixes = tuple(TOKENIZER_SUFFIXES)
|
|
|
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
