Merge pull request #111 from pavlin99th/patch-1

Fix terms overlap test in doc.to_terms_list
chartbeat-labs · Jun 15, 2017 · 5b91cf7 · 5b91cf7
2 parents a7ad803 + d6f3d3d
commit 5b91cf7
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/tests/test_readme.py b/tests/test_readme.py
@@ -114,8 +114,8 @@ def test_term_counting(self):
         # sort by term ascending, then count descending
         observed_2 = sorted(bot.items(), key=itemgetter(1, 0), reverse=True)[:10]
         expected_2 = [
-            ('nation', 6), ('world', 4), ('u.s.', 4), ('incarceration', 4),
-            ('decade', 4), ('system', 3), ('state', 3), ('record', 3),
-            ('problem', 3), ('people', 3)]
+            ('nation', 6), ('world', 4), ('incarceration', 4), ('system', 3),
+            ('state', 3), ('problem', 3), ('people', 3), ('minimum', 3),
+            ('mandatory', 3), ('lead', 3)]
         self.assertEqual(observed_1, expected_1)
         self.assertEqual(observed_2, expected_2)
diff --git a/textacy/doc.py b/textacy/doc.py
@@ -472,7 +472,7 @@ def to_terms_list(self, ngrams=(1, 2, 3), named_entities=True,
                 if n == 1:
                     terms.append(
                         (word for word in textacy.extract.words(self, **ngram_kwargs)
-                         if (word.idx, word.idx + 1) not in ent_idxs))
+                         if (word.i, word.i + 1) not in ent_idxs))
                 else:
                     terms.append(
                         (ngram for ngram in textacy.extract.ngrams(self, n, **ngram_kwargs)