explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5019 from questoph/master

Browse Source 
Optimizing tokenization for Luxembourgish (dealing with apostrophe infixes)
This commit is contained in:
Ines Montani 2020-02-25 14:48:50 +01:00 committed by GitHub
commit d50152b917
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 5 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(" ", "")
abbrev = ("d", "D")
_infixes = (
LIST_ELLIPSES
+ 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"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA),

2
spacy/lang/lb/tokenizer_exceptions.py
View File

@ -10,6 +10,8 @@ _exc = {}
# translate / delete what is not necessary
for exc_data in [
{ORTH: "’t", LEMMA: "et", NORM: "et"},
{ORTH: "’T", LEMMA: "et", NORM: "et"},
{ORTH: "'t", LEMMA: "et", NORM: "et"},
{ORTH: "'T", LEMMA: "et", NORM: "et"},
{ORTH: "wgl.", LEMMA: "wannechgelift", NORM: "wannechgelift"},