def test_regex_match(doc_setup):
"""Test RegexMatch matcher."""
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=2)
# a wrong option name should raise an excetiopn
with pytest.raises(Exception):
RegexMatchSpan(regex=r"apple")
# Test if matcher raises an error when _f is given non-TemporarySpanMention
matcher = RegexMatchSpan(rgx=r"apple")
with pytest.raises(ValueError):
list(matcher.apply(doc.sentences[0].words))
matcher = RegexMatchEach(rgx=r"apple")
with pytest.raises(ValueError):
list(matcher.apply(doc.sentences[0].words))
# Test if RegexMatchEach works as expected.
assert set(tc.get_span()
for tc in matcher.apply(space.apply(doc))) == {"apple"}
# Test ignore_case option
matcher = RegexMatchEach(rgx=r"Apple", ignore_case=False)
assert list(matcher.apply(space.apply(doc))) == []
# Test sep option
matcher = RegexMatchSpan(rgx=r"isapple", sep=" ")
assert set(tc.get_span()
for tc in matcher.apply(space.apply(doc))) == {"is apple"}
def test_inverse(doc_setup):
"""Test inverse matcher."""
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=2)
tc: TemporarySpanMention
assert set(tc.get_span() for tc in space.apply(doc)) == {
"This is",
"is apple",
"This",
"is",
"apple",
}
# Match any span that contains "apple" with longest_match_only=False
matcher0 = RegexMatchSpan(
rgx=r"apple", search=True, full_match=True, longest_match_only=False
)
assert set(tc.get_span() for tc in matcher0.apply(space.apply(doc))) == {
"is apple",
"apple",
}
# Take an inverse
matcher = Inverse(matcher0, longest_match_only=False)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"This is",
"This",
"is",
}
# longest_match_only=True
matcher = Inverse(matcher0, longest_match_only=True)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {"This is"}
# Match any span that contains "apple" with longest_match_only=True
matcher0 = RegexMatchSpan(
rgx=r"apple", search=True, full_match=True, longest_match_only=True
)
assert set(tc.get_span() for tc in matcher0.apply(space.apply(doc))) == {"is apple"}
# longest_match_only=False on Inverse is in effect.
matcher = Inverse(matcher0, longest_match_only=False)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"This is",
"This",
"is",
}
# longest_match_only=True on Inverse is in effect.
matcher = Inverse(matcher0, longest_match_only=True)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {"This is"}
# Check if Inverse raises an error when no child matcher is provided.
with pytest.raises(ValueError):
Inverse()
# Check if Inverse raises an error when two child matchers are provided.
with pytest.raises(ValueError):
Inverse(matcher0, matcher0)
def test_union(doc_setup):
"""Test union matcher."""
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=2)
tc: TemporarySpanMention
assert set(tc.get_span() for tc in space.apply(doc)) == {
"This is",
"is apple",
"This",
"is",
"apple",
}
# Match any span that contains "apple"
matcher0 = RegexMatchSpan(rgx=r"apple",
search=True,
full_match=True,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher0.apply(space.apply(doc))) == {
"is apple",
"apple",
}
# Match any span that contains "this" (case insensitive)
matcher1 = RegexMatchSpan(rgx=r"this",
search=False,
full_match=False,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher1.apply(space.apply(doc))) == {
"This is",
"This",
}
matcher = Union(matcher0, matcher1, longest_match_only=False)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"is apple",
"apple",
"This is",
"This",
}
# longest_match_only of each matcher is ignored.
matcher = Union(matcher0, matcher1, longest_match_only=True)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"This is",
"is apple",
}
# Unsupported option should raise an exception
with pytest.raises(Exception):
Union(matcher0, matcher1, long_match_only=False)
def test_union(caplog, doc_setup):
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=2)
tc: TemporarySpanMention
assert set(tc.get_span() for tc in space.apply(doc)) == {
"This is",
"is apple",
"This",
"is",
"apple",
}
# Match any span that contains "apple"
matcher0 = RegexMatchSpan(rgx=r"apple",
search=True,
full_match=True,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher0.apply(space.apply(doc))) == {
"is apple",
"apple",
}
# Match any span that contains "this" (case insensitive)
matcher1 = RegexMatchSpan(rgx=r"this",
search=False,
full_match=False,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher1.apply(space.apply(doc))) == {
"This is",
"This",
}
matcher = Union(matcher0, matcher1, longest_match_only=False)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"is apple",
"apple",
"This is",
"This",
}
# longest_match_only of each matcher is ignored.
matcher = Union(matcher0, matcher1, longest_match_only=True)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"This is",
"is apple",
}
def test_intersect(doc_setup):
"""Test intersect matcher."""
doc = doc_setup
space = MentionNgrams(n_min=1, n_max=3)
tc: TemporarySpanMention
# Match any span that contains "apple"
matcher0 = RegexMatchSpan(rgx=r"apple",
search=True,
full_match=True,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher0.apply(space.apply(doc))) == {
"This is apple",
"is apple",
"apple",
}
# Match any span that contains "this" (case insensitive)
matcher1 = RegexMatchSpan(rgx=r"this",
search=False,
full_match=False,
longest_match_only=False)
assert set(tc.get_span() for tc in matcher1.apply(space.apply(doc))) == {
"This is apple",
"This is",
"This",
}
# Intersection of matcher0 and matcher1
matcher = Intersect(matcher0, matcher1, longest_match_only=False)
assert set(tc.get_span()
for tc in matcher.apply(space.apply(doc))) == {"This is apple"}
# Intersection of matcher0 and matcher0
matcher = Intersect(matcher0, matcher0, longest_match_only=False)
assert set(tc.get_span() for tc in matcher.apply(space.apply(doc))) == {
"This is apple",
"is apple",
"apple",
}
# longest_match_only=True overrides that of child matchers.
matcher = Intersect(matcher0, matcher0, longest_match_only=True)
assert set(tc.get_span()
for tc in matcher.apply(space.apply(doc))) == {"This is apple"}
