2017-03-12 15:07:28 +03:00
|
|
|
# coding: utf8
|
2017-05-08 16:44:26 +03:00
|
|
|
from __future__ import unicode_literals
|
2015-09-06 22:56:47 +03:00
|
|
|
|
2017-05-08 16:44:26 +03:00
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
2017-06-03 21:54:18 +03:00
|
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
2017-09-16 21:40:15 +03:00
|
|
|
from .punctuation import TOKENIZER_INFIXES
|
2017-05-08 16:44:26 +03:00
|
|
|
from .tag_map import TAG_MAP
|
|
|
|
from .stop_words import STOP_WORDS
|
|
|
|
from .lemmatizer import LOOKUP
|
2017-05-17 12:37:48 +03:00
|
|
|
from .syntax_iterators import SYNTAX_ITERATORS
|
2015-09-06 22:56:47 +03:00
|
|
|
|
2017-05-08 23:29:04 +03:00
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
2017-06-03 21:54:18 +03:00
|
|
|
from ..norm_exceptions import BASE_NORMS
|
2017-05-08 23:29:04 +03:00
|
|
|
from ...language import Language
|
2017-06-03 21:54:18 +03:00
|
|
|
from ...attrs import LANG, NORM
|
|
|
|
from ...util import update_exc, add_lookups
|
2015-09-06 22:56:47 +03:00
|
|
|
|
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class GermanDefaults(Language.Defaults):
|
|
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
|
|
lex_attr_getters[LANG] = lambda text: 'de'
|
2017-06-03 21:54:18 +03:00
|
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
|
2017-06-03 22:52:06 +03:00
|
|
|
NORM_EXCEPTIONS, BASE_NORMS)
|
2017-05-20 20:02:27 +03:00
|
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
2017-10-11 16:34:55 +03:00
|
|
|
infixes = TOKENIZER_INFIXES
|
|
|
|
tag_map = TAG_MAP
|
|
|
|
stop_words = STOP_WORDS
|
|
|
|
syntax_iterators = SYNTAX_ITERATORS
|
|
|
|
lemma_lookup = LOOKUP
|
2016-05-02 17:04:53 +03:00
|
|
|
|
2017-05-03 12:01:42 +03:00
|
|
|
|
2017-05-20 20:02:27 +03:00
|
|
|
class German(Language):
|
|
|
|
lang = 'de'
|
|
|
|
Defaults = GermanDefaults
|
2017-05-03 13:14:42 +03:00
|
|
|
|
2017-05-03 12:01:42 +03:00
|
|
|
|
2017-05-08 16:44:26 +03:00
|
|
|
__all__ = ['German']
|