mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-12 04:38:28 +03:00
6c498f9ff4
* Add words to portuguese language _num_words * Add words to portuguese language _num_words * Portuguese - Add/remove stopwords, fix tokenizer, add currency symbols * Extended punctuation and norm_exceptions in the Portuguese language
37 lines
1.2 KiB
Python
37 lines
1.2 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
|
|
from .stop_words import STOP_WORDS
|
|
from .lex_attrs import LEX_ATTRS
|
|
from .lemmatizer import LOOKUP
|
|
from .tag_map import TAG_MAP
|
|
from .norm_exceptions import NORM_EXCEPTIONS
|
|
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
|
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES
|
|
from ..norm_exceptions import BASE_NORMS
|
|
from ...language import Language
|
|
from ...attrs import LANG, NORM
|
|
from ...util import update_exc, add_lookups
|
|
|
|
|
|
class PortugueseDefaults(Language.Defaults):
|
|
lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
|
|
lex_attr_getters[LANG] = lambda text: 'pt'
|
|
lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS, NORM_EXCEPTIONS)
|
|
lex_attr_getters.update(LEX_ATTRS)
|
|
tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
|
|
stop_words = STOP_WORDS
|
|
lemma_lookup = LOOKUP
|
|
tag_map = TAG_MAP
|
|
infixes = TOKENIZER_INFIXES
|
|
prefixes = TOKENIZER_PREFIXES
|
|
|
|
class Portuguese(Language):
|
|
lang = 'pt'
|
|
Defaults = PortugueseDefaults
|
|
|
|
|
|
__all__ = ['Portuguese']
|