Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Import and combine Portuguese tokenizer exceptions (see #943)

This commit is contained in:
ines 2017-04-01 10:37:42 +02:00
parent f8b2d9c3b7
commit ad8bf1829f
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/pt/language_data.py
View File

@ -5,13 +5,15 @@ from .. import language_data as base
from ..language_data import update_exc, strings_to_exc from ..language_data import update_exc, strings_to_exc
from .stop_words import STOP_WORDS from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS, ORTH_ONLY
STOP_WORDS = set(STOP_WORDS) STOP_WORDS = set(STOP_WORDS)
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS) TOKENIZER_EXCEPTIONS = dict(TOKENIZER_EXCEPTIONS)
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS)) update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
__all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"] __all__ = ["TOKENIZER_EXCEPTIONS", "STOP_WORDS"]