explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 17:36:30 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update regression test for variable-length pattern problem in the matcher.

Browse Source
This commit is contained in:
Matthew Honnibal 2017-03-07 16:08:32 +01:00
parent 6d67213b80
commit 4e75e74247
1 changed files with 25 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
spacy/tests/regression/test_issue850.py
View File

@ -2,6 +2,7 @@
Test Matcher matches with '*' operator and Boolean flag
'''
from __future__ import unicode_literals
from __future__ import print_function
import pytest
from ...matcher import Matcher
@ -10,9 +11,30 @@ from ...attrs import LOWER
from ...tokens import Doc
def test_basic_case():
matcher = Matcher(Vocab(
lex_attr_getters={LOWER: lambda string: string.lower()}))
IS_ANY_TOKEN = matcher.vocab.add_flag(lambda x: True)
matcher.add_pattern(
"FarAway",
[
{LOWER: "bob"},
{'OP': '*', LOWER: 'and'},
{LOWER: 'frank'}
])
doc = Doc(matcher.vocab, words=['bob', 'and', 'and', 'frank'])
match = matcher(doc)
assert len(match) == 1
ent_id, label, start, end = match[0]
assert start == 0
assert end == 4
@pytest.mark.xfail
def test_issue850():
matcher = Matcher(Vocab())
'''The problem here is that the variable-length pattern matches the
succeeding token. We then don't handle the ambiguity correctly.'''
matcher = Matcher(Vocab(
lex_attr_getters={LOWER: lambda string: string.lower()}))
IS_ANY_TOKEN = matcher.vocab.add_flag(lambda x: True)
matcher.add_pattern(
"FarAway",
@ -21,9 +43,9 @@ def test_issue850():
{'OP': '*', IS_ANY_TOKEN: True},
{LOWER: 'frank'}
])
doc = Doc(matcher.vocab, words=['bob', 'and', 'and', 'cat', 'frank'])
doc = Doc(matcher.vocab, words=['bob', 'and', 'and', 'frank'])
match = matcher(doc)
assert len(match) == 1
start, end, label, ent_id = match
ent_id, label, start, end = match[0]
assert start == 0
assert end == 4