2017-03-12 12:07:28 +00:00
|
|
|
# coding: utf8
|
2017-05-08 13:43:50 +00:00
|
|
|
from __future__ import unicode_literals
|
2017-02-28 01:48:37 +00:00
|
|
|
|
2017-05-08 13:43:50 +00:00
|
|
|
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 .lemmatizer import LEMMA_RULES
|
|
|
|
|
2017-05-08 20:29:04 +00:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
|
|
from ...language import Language
|
|
|
|
from ...attrs import LANG
|
|
|
|
from ...util import update_exc
|
2017-02-28 01:48:37 +00:00
|
|
|
|
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
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)
|
2017-10-11 00:22:49 +00:00
|
|
|
tag_map = dict(TAG_MAP)
|
|
|
|
stop_words = set(STOP_WORDS)
|
|
|
|
lemma_rules = dict(LEMMA_RULES)
|
2017-05-20 17:02:27 +00:00
|
|
|
prefixes = tuple(TOKENIZER_PREFIXES)
|
|
|
|
suffixes = tuple(TOKENIZER_SUFFIXES)
|
|
|
|
infixes = tuple(TOKENIZER_INFIXES)
|
2017-02-28 01:48:37 +00:00
|
|
|
|
2017-02-28 15:07:14 +00:00
|
|
|
|
2017-05-20 17:02:27 +00:00
|
|
|
class Bengali(Language):
|
|
|
|
lang = 'bn'
|
|
|
|
Defaults = BengaliDefaults
|
2017-05-03 09:01:42 +00:00
|
|
|
|
2017-05-08 13:43:50 +00:00
|
|
|
|
|
|
|
__all__ = ['Bengali']
|