Split off period after two or more uppercase letters (fixes #483)

explosion · Jan 8, 2017 · eef94e3 · eef94e3
1 parent a89a600
commit eef94e3
Showing 1 changed file with 1 addition and 0 deletions.
diff --git a/spacy/language_data/punctuation.py b/spacy/language_data/punctuation.py
@@ -92,6 +92,7 @@
  r'(?<=[0-9])(?:{c})'.format(c=CURRENCY),
  r'(?<=[0-9])(?:{u})'.format(u=UNITS),
  r'(?<=[0-9{al}{p}(?:{q})])\.'.format(al=ALPHA_LOWER, p=r'%²\-\)\]\+', q=QUOTES),
+ r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER),
  "'s", "'S", "’s", "’S"
  ]
 )