Continue to split . after °CFK if ° is not a prefix

spacy/lang/punctuation.py

@@ -21,6 +21,7 @@ TOKENIZER_SUFFIXES = (
     + ["'s", "'S", "’s", "’S", "—", "–"]
     + [
         r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
         r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
         r"(?<=[0-9])(?:{u})".format(u=UNITS),
         r"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(

spacy/lang/tokenizer_exceptions.py

@@ -255,4 +255,5 @@ for orth in emoticons:
 # Moved from a suffix setting due to #9155 removing prefixes from consideration
 # for lookbehinds
 for u in "cfkCFK":
-    BASE_EXCEPTIONS[f"°{u}."] = [{ORTH: "°"}, {ORTH: f"{u}"}, {ORTH: "."}]
+    BASE_EXCEPTIONS[f"°{u}"] = [{ORTH: f"°{u}"}]
+    BASE_EXCEPTIONS[f"°{u}."] = [{ORTH: f"°{u}"}, {ORTH: "."}]

spacy/tests/tokenizer/test_exceptions.py

@@ -49,5 +49,5 @@ def test_tokenizer_handles_emoji(tokenizer, text, length):
 
 def test_tokenizer_degree(tokenizer):
     for u in "cfkCFK":
-        assert [t.text for t in tokenizer(f"°{u}.")] == ["°", f"{u}", "."]
-        assert [t[1] for t in tokenizer.explain(f"°{u}.")] == ["°", f"{u}", "."]
+        assert [t.text for t in tokenizer(f"°{u}.")] == [f"°{u}", "."]
+        assert [t[1] for t in tokenizer.explain(f"°{u}.")] == [f"°{u}", "."]