Skip to content

GH-40128: [C++][Python] Preserve dictionaries in empty casts #50837

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

Open
LarryHu0217 wants to merge 1 commit into
base: main
Choose a base branch
from
+21 −1
Open

GH-40128: [C++][Python] Preserve dictionaries in empty casts #50837

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
9 changes: 8 additions & 1 deletion cpp/src/arrow/compute/exec.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -783,7 +783,14 @@ class ScalarExecutor : public KernelExecutorImpl<ScalarKernel> {
Status Execute(const ExecBatch& batch, ExecListener* listener) override {
RETURN_NOT_OK(span_iterator_.Init(batch, exec_context()->exec_chunksize()));

if (batch.length == 0) {
// A dictionary-to-dictionary cast must run to preserve unreferenced dictionary
// values even when there are no indices to process.
const bool changes_dictionary_type =
batch.num_values() == 1 && batch.values[0].type() != nullptr &&
is_dictionary(batch.values[0].type()->id()) &&
is_dictionary(output_type_.type->id()) &&
!batch.values[0].type()->Equals(*output_type_.type);
if (batch.length == 0 && !changes_dictionary_type) {
// For zero-length batches, we do nothing except return a zero-length
// array of the correct output type
ARROW_ASSIGN_OR_RAISE(std::shared_ptr<Array> result,
Expand Down
13 changes: 13 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 @@ -4573,6 +4573,19 @@ TEST(Cast, DictTypeToAnotherDict) {
Cast(arr, dictionary(int8(), int8()), CastOptions::Safe()));
}

TEST(Cast, EmptyDictionaryToAnotherDictionary) {
auto dictionary_values = ArrayFromJSON(utf8(), R"(["foo", "bar"])");

ASSERT_OK_AND_ASSIGN(auto input, DictionaryArray::FromArrays(
dictionary(int32(), utf8()),
ArrayFromJSON(int32(), "[]"), dictionary_values));
ASSERT_OK_AND_ASSIGN(auto result, Cast(*input, dictionary(int64(), utf8())));
auto dictionary_result = checked_pointer_cast<DictionaryArray>(result);

ASSERT_TRUE(dictionary_result->indices()->type()->Equals(int64()));
AssertArraysEqual(*dictionary_values, *dictionary_result->dictionary());
}

TEST(Cast, NoOutBitmapIfInIsAllValid) {
auto a = ArrayFromJSON(int8(), "[1]");
CastOptions options;
Expand Down
Loading