explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-10 19:57:17 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #4239 from adrianeboyd/bugfix/tokenizer-cache-test-1061

Browse Source 
Add regression test for #1061 back to test suite
This commit is contained in:
Matthew Honnibal 2019-09-04 23:10:12 +02:00 committed by GitHub
commit b94c34ec8f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
spacy/tests/regression/test_issue1001-1500.py
View File

@ -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)"
)