fixes for issue #28

Georgetown-IR-Lab · Oct 18, 2018 · e02723e · e02723e
1 parent 4a32fa8
commit e02723e
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 0 deletions.
diff --git a/quickumls.py b/quickumls.py
@@ -267,6 +267,8 @@ def _get_all_matches(self, ngrams):
                         n=self.ngram_length,
                         similarity_name=self.similarity_name
                     )
+                    if match_similarity == 0:
+                        continue
 
                     if not self._is_ok_semtype(semtypes):
                         continue

diff --git a/toolbox.py b/toolbox.py
@@ -71,6 +71,11 @@ def make_ngrams(s, n):
 
 
 def get_similarity(x, y, n, similarity_name):
+    if len(x) == 0 or len(y) == 0:
+        # we define similarity between two strings
+        # to be 0 if any of the two is empty.
+        return 0.
+
     X, Y = set(make_ngrams(x, n)), set(make_ngrams(y, n))
     intersec = len(X.intersection(Y))