Merge pull request #866 from juanmirocks/master

Fix lemmatization of OOV words

spacy/lemmatizer.py

@@ -70,11 +70,14 @@ def lemmatize(string, index, exceptions, rules):
     #if string in index:
     #    forms.append(string)
     forms.extend(exceptions.get(string, []))
+    oov_forms = []
     for old, new in rules:
         if string.endswith(old):
             form = string[:len(string) - len(old)] + new
             if form in index or not form.isalpha():
                 forms.append(form)
+            else:
+                oov_forms.append(form)
     if not forms:
-        forms.append(string)
+        forms.extend(oov_forms)
     return set(forms)

spacy/tests/regression/test_issue781.py

@@ -0,0 +1,10 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+
+# Note: "chromosomes" worked previous the bug fix
+@pytest.mark.parametrize('word,lemmas', [("chromosomes", ["chromosome"]), ("endosomes", ["endosome"]), ("colocalizes", ["colocalize", "colocaliz"])])
+def test_issue781(path, lemmatizer, word, lemmas):
+    assert lemmatizer(word, 'noun', morphology={'number': 'plur'}) == set(lemmas)