From 4f8daa4f003785e23cf2612683f78476dac7baca Mon Sep 17 00:00:00 2001 From: Jacobo Myerston <43222279+jmyerston@users.noreply.github.com> Date: Thu, 20 Jul 2023 02:16:01 -0700 Subject: [PATCH] Add Left and Right Pointing Angle Brackets as punctuation to ancient Greek (#12829) * Update universe.json * Update universe.json add some missing commas in the greCy's description. * Update punctuation.py Add mathematical left and right angle brackets as punctuation for ancient Greek for better tokenization. --- spacy/lang/grc/punctuation.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/spacy/lang/grc/punctuation.py b/spacy/lang/grc/punctuation.py index 8e9fc8bf2..59037617d 100644 --- a/spacy/lang/grc/punctuation.py +++ b/spacy/lang/grc/punctuation.py @@ -15,6 +15,7 @@ _prefixes = ( [ "†", "⸏", + "〈", ] + LIST_PUNCT + LIST_ELLIPSES @@ -31,6 +32,7 @@ _suffixes = ( + [ "†", "⸎", + "〉", r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]", ] )