mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-14 13:47:13 +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
19 lines
545 B
Python
19 lines
545 B
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
|
|
from ..punctuation import TOKENIZER_SUFFIXES as BASE_TOKENIZER_SUFFIXES
|
|
from ..punctuation import TOKENIZER_INFIXES as BASE_TOKENIZER_INFIXES
|
|
|
|
_prefixes = ([r'\w{1,3}\$'] + BASE_TOKENIZER_PREFIXES)
|
|
|
|
_suffixes = (BASE_TOKENIZER_SUFFIXES)
|
|
|
|
_infixes = ([r'(\w+-\w+(-\w+)*)'] +
|
|
BASE_TOKENIZER_INFIXES
|
|
)
|
|
|
|
TOKENIZER_PREFIXES = _prefixes
|
|
TOKENIZER_SUFFIXES = _suffixes
|
|
TOKENIZER_INFIXES = _infixes
|