explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-03-13 07:55:49 +03:00
Code Issues Packages Projects Releases Wiki Activity

Adjust exceptions for same tokenization as v3.1

Browse Source
This commit is contained in:
Adriane Boyd 2021-10-11 14:48:04 +02:00
parent 97fb19d7d3
commit 7251014380
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/lang/tokenizer_exceptions.py
View File

@ -254,6 +254,5 @@ for orth in emoticons:
# Moved from a suffix setting due to #9155 removing prefixes from consideration
# for lookbehinds
for u in "cfk":
BASE_EXCEPTIONS[f"°{u}."] = [{ORTH: f"°{u}"}, {ORTH: "."}]
BASE_EXCEPTIONS[f"°{u.upper()}."] = [{ORTH: f"°{u.upper()}"}, {ORTH: "."}]
for u in "cfkCFK":
BASE_EXCEPTIONS[f"°{u}."] = [{ORTH: "°"}, {ORTH: f"{u}"}, {ORTH: "."}]