Keep infixes of punctuation + hyphens as one token (see #801)

explosion · Feb 2, 2017 · 012f482 · 012f482
1 parent 1219a5f
commit 012f482
Showing 1 changed file with 1 addition and 1 deletion.
diff --git a/spacy/language_data/punctuation.py b/spacy/language_data/punctuation.py
@@ -106,7 +106,7 @@
         r'(?<=[0-9])[+\-\*^](?=[0-9-])',
         r'(?<=[{al}])\.(?=[{au}])'.format(al=ALPHA_LOWER, au=ALPHA_UPPER),
         r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
-        r'(?<=[{a}])(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
+        r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
         r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA)
     ]
 )