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

Update punctuation.py

This commit is contained in:
questoph 2020-02-13 22:18:51 +01:00
parent 99a543367d
commit d1f0b397b5
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
spacy/lang/lb/punctuation.py
View File

@ -5,11 +5,13 @@ from ..char_classes import LIST_ELLIPSES, LIST_ICONS, ALPHA, ALPHA_LOWER, ALPHA_
ELISION = " ' ’ ".strip().replace(" ", "") ELISION = " ' ’ ".strip().replace(" ", "")
abbrev = ("d", "D")
_infixes = ( _infixes = (
LIST_ELLIPSES LIST_ELLIPSES
+ LIST_ICONS + LIST_ICONS
+ [ + [
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION), r"(?<=^[{ab}][{el}])(?=[{a}])".format(ab=abbrev, a=ALPHA, el=ELISION),
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER), r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA), r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA), r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),