spaCy/spacy/lang/de/__init__.py

38 lines
1.1 KiB
Python
Raw Normal View History

2017-03-12 12:07:28 +00:00
# coding: utf8
2017-05-08 13:44:26 +00:00
from __future__ import unicode_literals
2015-09-06 19:56:47 +00:00
2017-05-08 13:44:26 +00:00
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
2017-06-03 18:54:18 +00:00
from .norm_exceptions import NORM_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES
2017-05-08 13:44:26 +00:00
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
from .lemmatizer import LOOKUP
from .syntax_iterators import SYNTAX_ITERATORS
2015-09-06 19:56:47 +00:00
2017-05-08 20:29:04 +00:00
from ..tokenizer_exceptions import BASE_EXCEPTIONS
2017-06-03 18:54:18 +00:00
from ..norm_exceptions import BASE_NORMS
2017-05-08 20:29:04 +00:00
from ...language import Language
2017-06-03 18:54:18 +00:00
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
2015-09-06 19:56:47 +00:00
class GermanDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters[LANG] = lambda text: 'de'
2017-06-03 18:54:18 +00:00
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM],
2017-06-03 19:52:06 +00:00
NORM_EXCEPTIONS, BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
infixes = TOKENIZER_INFIXES
tag_map = TAG_MAP
stop_words = STOP_WORDS
syntax_iterators = SYNTAX_ITERATORS
lemma_lookup = LOOKUP
2017-05-03 09:01:42 +00:00
class German(Language):
lang = 'de'
Defaults = GermanDefaults
2017-05-03 09:01:42 +00:00
2017-05-08 13:44:26 +00:00
__all__ = ['German']