From 0f28418446581dd5df8807f44dcfa72371bdbd98 Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Wed, 4 Sep 2019 20:42:24 +0200 Subject: [PATCH] Add regression test for #1061 back to test suite --- spacy/tests/regression/test_issue1001-1500.py | 22 +++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/spacy/tests/regression/test_issue1001-1500.py b/spacy/tests/regression/test_issue1001-1500.py index 15da1061b..9074b34b7 100644 --- a/spacy/tests/regression/test_issue1001-1500.py +++ b/spacy/tests/regression/test_issue1001-1500.py @@ -13,6 +13,28 @@ from spacy.lemmatizer import Lemmatizer from spacy.symbols import ORTH, LEMMA, POS, VERB, VerbForm_part +@pytest.mark.xfail +def test_issue1061(): + '''Test special-case works after tokenizing. Was caching problem.''' + text = 'I like _MATH_ even _MATH_ when _MATH_, except when _MATH_ is _MATH_! but not _MATH_.' + tokenizer = English.Defaults.create_tokenizer() + doc = tokenizer(text) + assert 'MATH' in [w.text for w in doc] + assert '_MATH_' not in [w.text for w in doc] + + tokenizer.add_special_case('_MATH_', [{ORTH: '_MATH_'}]) + doc = tokenizer(text) + assert '_MATH_' in [w.text for w in doc] + assert 'MATH' not in [w.text for w in doc] + + # For sanity, check it works when pipeline is clean. + tokenizer = English.Defaults.create_tokenizer() + tokenizer.add_special_case('_MATH_', [{ORTH: '_MATH_'}]) + doc = tokenizer(text) + assert '_MATH_' in [w.text for w in doc] + assert 'MATH' not in [w.text for w in doc] + + @pytest.mark.xfail( reason="g is split of as a unit, as the suffix regular expression can not look back further (variable-width)" )