mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-26 01:46:28 +03:00
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.
This commit is contained in:
parent
ea54d1775a
commit
4f8daa4f00
|
@ -15,6 +15,7 @@ _prefixes = (
|
|||
[
|
||||
"†",
|
||||
"⸏",
|
||||
"〈",
|
||||
]
|
||||
+ LIST_PUNCT
|
||||
+ LIST_ELLIPSES
|
||||
|
@ -31,6 +32,7 @@ _suffixes = (
|
|||
+ [
|
||||
"†",
|
||||
"⸎",
|
||||
"〉",
|
||||
r"(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]",
|
||||
]
|
||||
)
|
||||
|
|
Loading…
Reference in New Issue
Block a user