Skip to content

ARROW-1143: C++: Fix comparison of NullArray #772

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
xhochy wants to merge 1 commit into from
Closed

ARROW-1143: C++: Fix comparison of NullArray #772

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions cpp/src/arrow/array-test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,6 +95,16 @@ TEST_F(TestArray, TestEquality) {
EXPECT_FALSE(array->RangeEquals(1, 2, 1, unequal_array));
}

TEST_F(TestArray, TestNullArrayEquality) {
auto array_1 = std::make_shared<NullArray>(10);
auto array_2 = std::make_shared<NullArray>(10);
auto array_3 = std::make_shared<NullArray>(20);

EXPECT_TRUE(array_1->Equals(array_1));
EXPECT_TRUE(array_1->Equals(array_2));
EXPECT_FALSE(array_1->Equals(array_3));
}

TEST_F(TestArray, SliceRecomputeNullCount) {
vector<uint8_t> valid_bytes = {1, 0, 1, 1, 0, 1, 0, 0, 0};

Expand Down
7 changes: 5 additions & 2 deletions cpp/src/arrow/compare.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,7 +322,10 @@ class ArrayEqualsVisitor : public RangeEqualsVisitor {
explicit ArrayEqualsVisitor(const Array& right)
: RangeEqualsVisitor(right, 0, right.length(), 0) {}

Status Visit(const NullArray& left) { return Status::OK(); }
Status Visit(const NullArray& left) {
result_ = true;
return Status::OK();
}

Status Visit(const BooleanArray& left) {
const auto& right = static_cast<const BooleanArray&>(right_);
Expand Down Expand Up @@ -529,7 +532,7 @@ static bool BaseDataEquals(const Array& left, const Array& right) {
left.type_id() != right.type_id()) {
return false;
}
if (left.null_count() > 0) {
if (left.null_count() > 0 && left.null_count() < left.length()) {
return BitmapEquals(left.null_bitmap()->data(), left.offset(),
right.null_bitmap()->data(), right.offset(), left.length());
}
Expand Down
6 changes: 6 additions & 0 deletions python/pyarrow/tests/test_convert_pandas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,12 @@ def test_all_none_objects(self):
self._check_pandas_roundtrip(df)


def test_all_none_category(self):
df = pd.DataFrame({'a': [None, None, None]})
df['a'] = df['a'].astype('category')
self._check_pandas_roundtrip(df)


def test_float_no_nulls(self):
data = {}
fields = []
Expand Down
6 changes: 5 additions & 1 deletion python/pyarrow/tests/test_parquet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,8 +225,12 @@ def _test_dataframe(size=10000, seed=0):
'float32': np.random.randn(size).astype(np.float32),
'float64': np.arange(size, dtype=np.float64),
'bool': np.random.randn(size) > 0,
'strings': [tm.rands(10) for i in range(size)]
'strings': [tm.rands(10) for i in range(size)],
'all_none': [None] * size,
'all_none_category': [None] * size
})
# TODO(PARQUET-1015)
# df['all_none_category'] = df['all_none_category'].astype('category')
return df


Expand Down