mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
0e08e49e87
* Add Romanian lemmatizer lookup table. Adapted from http://www.lexiconista.com/datasets/lemmatization/ by replacing cedillas with commas (ș and ț). The original dataset is licensed under the Open Database License. * Fix one blatant issue in the Romanian lemmatizer * Romanian examples file * Add ro_tokenizer in conftest * Add Romanian lemmatizer test
31 lines
863 B
Python
31 lines
863 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lemmatizer import LOOKUP
|
|
|
|
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 RomanianDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'ro'
|
|
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
|
|
lemma_lookup = LOOKUP
|
|
|
|
|
|
class Romanian(Language):
|
|
lang = 'ro'
|
|
Defaults = RomanianDefaults
|
|
|
|
|
|
__all__ = ['Romanian']
|
|
|