spaCy/spacy/lang/lb/__init__.py
Peter Gilles 428887b8f2 Initial commit: New language Luxembourgish (lb) (#4424)
* new language: Luxembourgish (lb)

* update

* update

* Update and rename .github/CONTRIBUTOR_AGREEMENT.md to .github/contributors/PeterGilles.md

* Update and rename .github/contributors/PeterGilles.md to .github/CONTRIBUTOR_AGREEMENT.md

* Update norm_exceptions.py

* Delete README.md

* moved test_lemma.py

* deactivated 'lemma_lookup = LOOKUP'

* update

* Update conftest.py

* update

* tests updated

* import unicode_literals

* Update spacy/tests/lang/lb/test_text.py

Co-Authored-By: Ines Montani <ines@ines.io>

* Create PeterGilles.md
2019-10-14 12:27:50 +02:00

38 lines
1.1 KiB
Python

# coding: utf8
from __future__ import unicode_literals
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .norm_exceptions import NORM_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES
from .lex_attrs import LEX_ATTRS
from .tag_map import TAG_MAP
from .stop_words import STOP_WORDS
#from .lemmatizer import LOOKUP
#from .syntax_iterators import SYNTAX_ITERATORS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..norm_exceptions import BASE_NORMS
from ...language import Language
from ...attrs import LANG, NORM
from ...util import update_exc, add_lookups
class LuxembourgishDefaults(Language.Defaults):
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
lex_attr_getters.update(LEX_ATTRS)
lex_attr_getters[LANG] = lambda text: 'lb'
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
stop_words = STOP_WORDS
#suffixes = TOKENIZER_SUFFIXES
#lemma_lookup = LOOKUP
class Luxembourgish(Language):
lang = 'lb'
Defaults = LuxembourgishDefaults
__all__ = ['Luxembourgish']