Add tokenizer exception for "gonna" (fixes #691)

explosion · Dec 17, 2016 · d8d50a0 · d8d50a0
1 parent c69b77d
commit d8d50a0
Showing 1 changed file with 10 additions and 0 deletions.
diff --git a/spacy/en/language_data.py b/spacy/en/language_data.py
@@ -1493,6 +1493,16 @@ def get_time_exc(hours):
  {ORTH: "ma"}
  ],
 
+ "gonna": [
+ {ORTH: "gon", LEMMA: "go"},
+ {ORTH: "na", LEMMA: "to"}
+ ],
+
+ "Gonna": [
+ {ORTH: "Gon", LEMMA: "go"},
+ {ORTH: "na", LEMMA: "to"}
+ ],
+
  "whats": [
  {ORTH: "what"},
  {ORTH: "s"}