explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-27 02:16:32 +03:00
Code Issues Packages Projects Releases Wiki Activity

Add xfailing test for out-of-bounds heads

Browse Source
This commit is contained in:
Ines Montani 2019-02-15 13:09:07 +01:00
parent d8051e89ca
commit 819768483f
1 changed files with 13 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/tests/doc/test_doc_spilt.py
View File

@ -66,6 +66,19 @@ def test_split_heads_error(en_vocab):
retokenizer.split(doc[0], ["Los", "Angeles"], [0, 0]) retokenizer.split(doc[0], ["Los", "Angeles"], [0, 0])
@pytest.mark.xfail
def test_split_heads_out_of_bounds(en_vocab):
"""Test that the retokenizer raises an error for out-of-bounds heads. The
indices are relative, so head 1 for "Angeles" would be the token following
it, which is out-of-bounds. Previously, the retokenizer would accept this
and spaCy would then fail later.
"""
doc = Doc(en_vocab, words=["Start", "LosAngeles"])
with pytest.raises(ValueError):
with doc.retokenize() as retokenizer:
retokenizer.split(doc[1], ["Los", "Angeles"], [0, 1])
def test_spans_entity_merge_iob(): def test_spans_entity_merge_iob():
# Test entity IOB stays consistent after merging # Test entity IOB stays consistent after merging
words = ["abc", "d", "e"] words = ["abc", "d", "e"]