Skip to content

ARROW-8025: [C++] Implement cast from String to Binary #7470

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
kszucs wants to merge 1 commit into from
Closed

ARROW-8025: [C++] Implement cast from String to Binary #7470

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
3 changes: 3 additions & 0 deletions cpp/src/arrow/compute/kernels/scalar_cast_string.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,10 +147,13 @@ void AddNumberToStringCasts(std::shared_ptr<DataType> out_ty, CastFunction* func
std::vector<std::shared_ptr<CastFunction>> GetBinaryLikeCasts() {
auto cast_binary = std::make_shared<CastFunction>("cast_binary", Type::BINARY);
AddCommonCasts(Type::BINARY, binary(), cast_binary.get());
AddZeroCopyCast(Type::STRING, {utf8()}, binary(), cast_binary.get());

auto cast_large_binary =
std::make_shared<CastFunction>("cast_large_binary", Type::LARGE_BINARY);
AddCommonCasts(Type::LARGE_BINARY, large_binary(), cast_large_binary.get());
AddZeroCopyCast(Type::LARGE_STRING, {large_utf8()}, large_binary(),
cast_large_binary.get());

auto cast_fsb =
std::make_shared<CastFunction>("cast_fixed_size_binary", Type::FIXED_SIZE_BINARY);
Expand Down
27 changes: 27 additions & 0 deletions cpp/src/arrow/compute/kernels/scalar_cast_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,6 +157,27 @@ class TestCast : public TestBase {
src_type, strings, all, dest_type, strings, options);
}

template <typename SourceType, typename DestType>
void TestCastStringToBinary() {
CastOptions options;
auto src_type = TypeTraits<SourceType>::type_singleton();
auto dest_type = TypeTraits<DestType>::type_singleton();

// All valid except the last one
std::vector<bool> all = {1, 1, 1, 1, 1};
std::vector<bool> valid = {1, 1, 1, 1, 0};
std::vector<std::string> strings = {"Hi", "olá mundo", "你好世界", "", kInvalidUtf8};

std::shared_ptr<Array> array;

// Should accept when invalid but null.
ArrayFromVector<SourceType, std::string>(src_type, valid, strings, &array);
CheckZeroCopy(*array, dest_type);

CheckCase<SourceType, std::string, DestType, std::string>(
src_type, strings, all, dest_type, strings, options);
}

template <typename DestType>
void TestCastNumberToString() {
auto dest_type = TypeTraits<DestType>::type_singleton();
Expand Down Expand Up @@ -1363,6 +1384,12 @@ TEST_F(TestCast, LargeBinaryToLargeString) {
TestCastBinaryToString<LargeBinaryType, LargeStringType>();
}

TEST_F(TestCast, StringToBinary) { TestCastStringToBinary<StringType, BinaryType>(); }

TEST_F(TestCast, LargeStringToLargeBinary) {
TestCastStringToBinary<LargeStringType, LargeBinaryType>();
}

TEST_F(TestCast, NumberToString) { TestCastNumberToString<StringType>(); }

TEST_F(TestCast, NumberToLargeString) { TestCastNumberToString<LargeStringType>(); }
Expand Down