Add test_get_ngrams_that_match_in_string

Author: Hiromu Hota

tests/utils/data_model_utils/test_visual.py

@@ -141,3 +141,25 @@ def test_get_horz_ngrams(doc_setup):
         "orange",
         ".",
     ]
+
+
+def test_get_ngrams_that_match_in_string(doc_setup):
+    """Test if ngrams can be obtained even if they match mention's span in string."""
+    doc = doc_setup
+    sentence: Sentence = doc.sentences[0]
+    # Assert this sentence is visual.
+    assert sentence.is_visual()
+    # Assert this sentence is not tabular.
+    assert not sentence.is_tabular()
+
+    # Create 1-gram span mentions
+    space = MentionNgrams(n_min=1, n_max=1)
+    mentions = [tc for tc in space.apply(doc)]
+    assert len(mentions) == len([word for sent in doc.sentences for word in sent.words])
+
+    # Pick "is" from the apple sentence that matches "is" in the orange sentence.
+    mention = mentions[1]
+    assert mention.get_span() == "is"
+    # Check if the "is" in the orange sentence can be obtained.
+    ngrams = list(get_horz_ngrams(mention, from_sentence=False))
+    assert "is" in ngrams