explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-12 18:26:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

[issue 805] Fix issue

Browse Source
This commit is contained in:
Michael Wallin 2017-02-04 16:22:21 +02:00
parent 35100c8bdd
commit d25556bf80
2 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/sv/language_data.py
View File

@ -5,12 +5,14 @@ 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 = dict(TOKENIZER_EXCEPTIONS)
TOKENIZER_EXCEPTIONS = strings_to_exc(base.EMOTICONS) update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(ORTH_ONLY))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.EMOTICONS))
update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS)) update_exc(TOKENIZER_EXCEPTIONS, strings_to_exc(base.ABBREVIATIONS))

1
spacy/sv/tokenizer_exceptions.py
View File

@ -107,7 +107,6 @@ ORTH_ONLY = [
"p.g.a.", "p.g.a.",
"ref.", "ref.",
"resp.", "resp.",
"s.",
"s.a.s.", "s.a.s.",
"s.k.", "s.k.",
"st.", "st.",