Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
14 changes: 11 additions & 3 deletions cpp/src/arrow/scalar.cc
Original file line number Diff line number Diff line change
Expand Up @@ -90,9 +90,13 @@ struct ScalarHashImpl {
return Status::OK();
}

Status Visit(const DictionaryScalar& s) {
AccumulateHashFrom(*s.value.index);
return Status::OK();
}

// TODO(bkietz) implement less wimpy hashing when these have ValueType
Status Visit(const UnionScalar& s) { return Status::OK(); }
Status Visit(const DictionaryScalar& s) { return Status::OK(); }
Status Visit(const ExtensionScalar& s) { return Status::OK(); }

template <typename T>
Expand Down Expand Up @@ -127,14 +131,18 @@ struct ScalarHashImpl {
return Status::OK();
}

explicit ScalarHashImpl(const Scalar& scalar) { AccumulateHashFrom(scalar); }
explicit ScalarHashImpl(const Scalar& scalar) : hash_(scalar.type->Hash()) {
if (scalar.is_valid) {
AccumulateHashFrom(scalar);
}
}

void AccumulateHashFrom(const Scalar& scalar) {
DCHECK_OK(StdHash(scalar.type->fingerprint()));
DCHECK_OK(VisitScalarInline(scalar, this));
}

size_t hash_ = 0;
size_t hash_;
};

size_t Scalar::Hash::hash(const Scalar& scalar) { return ScalarHashImpl(scalar).hash_; }
Expand Down
19 changes: 19 additions & 0 deletions cpp/src/arrow/scalar_test.cc
Original file line number Diff line number Diff line change
Expand Up @@ -111,10 +111,12 @@ TYPED_TEST(TestNumericScalar, Hashing) {
using ScalarType = typename TypeTraits<TypeParam>::ScalarType;

std::unordered_set<std::shared_ptr<Scalar>, Scalar::Hash, Scalar::PtrsEqual> set;
set.emplace(std::make_shared<ScalarType>());
for (T i = 0; i < 10; ++i) {
set.emplace(std::make_shared<ScalarType>(i));
}

ASSERT_FALSE(set.emplace(std::make_shared<ScalarType>()).second);
for (T i = 0; i < 10; ++i) {
ASSERT_FALSE(set.emplace(std::make_shared<ScalarType>(i)).second);
}
Expand Down Expand Up @@ -406,6 +408,23 @@ TEST(TestBinaryScalar, Basics) {
ASSERT_FALSE(two->Equals(BinaryScalar(Buffer::FromString("else"))));
}

TEST(TestBinaryScalar, Hashing) {
auto FromInt = [](int i) {
return std::make_shared<BinaryScalar>(Buffer::FromString(std::to_string(i)));
};

std::unordered_set<std::shared_ptr<Scalar>, Scalar::Hash, Scalar::PtrsEqual> set;
set.emplace(std::make_shared<BinaryScalar>());
for (int i = 0; i < 10; ++i) {
set.emplace(FromInt(i));
}

ASSERT_FALSE(set.emplace(std::make_shared<BinaryScalar>()).second);
for (int i = 0; i < 10; ++i) {
ASSERT_FALSE(set.emplace(FromInt(i)).second);
}
}

TEST(TestStringScalar, MakeScalar) {
auto three = MakeScalar("three");
ASSERT_EQ(StringScalar("three"), *three);
Expand Down