Skip to content

GH-50517: [C++] RunEndEncodedBuilder does not merge consecutive NaN values #51325

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
andishgar wants to merge 1 commit into
base: main
Choose a base branch
from
+33 −2
Open

GH-50517: [C++] RunEndEncodedBuilder does not merge consecutive NaN values #51325

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
26 changes: 26 additions & 0 deletions cpp/src/arrow/array/array_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2558,6 +2558,32 @@ TEST(TestPrimitiveAdHoc, FloatingUlpDistanceEquality) {
CheckFloatApproxEqualsWithUlpDistance<DoubleType>();
}

TEST(TestRunEncodedBuilder, MergeConsecutiveNaNs) {
auto run_end_encoded_type = run_end_encoded(int32(), float32());
std::shared_ptr<RunEndEncodedArray> result;
auto run_end_builder = std::make_shared<Int32Builder>();
auto value_builder = std::make_shared<FloatBuilder>();
RunEndEncodedBuilder builder(default_memory_pool(), run_end_builder, value_builder,
run_end_encoded_type);
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), 1), 15));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), 1), 10));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), 2), 20));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), std::nanf("")), 25));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), std::nanf("")), 5));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), 3), 15));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), std::nanf("")), 20));
ASSERT_OK(builder.AppendScalar(**MakeScalar(float32(), 4), 25));
ASSERT_OK(builder.Finish(&result));

std::shared_ptr<Array> expected_run_end_array;
std::shared_ptr<Array> expected_value_array;
ArrayFromVector<Int32Type>({25, 45, 75, 90, 110, 135}, &expected_run_end_array);
ArrayFromVector<FloatType>({1.0, 2.0, std::nanf(""), 3.0, std::nanf(""), 4.0},
&expected_value_array);
AssertArraysEqual(*expected_run_end_array, *result->run_ends());
AssertArraysEqual(*expected_value_array, *result->values());
}

// ----------------------------------------------------------------------
// FixedSizeBinary tests

Expand Down
4 changes: 3 additions & 1 deletion cpp/src/arrow/array/builder_run_end.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@
#include <utility>
#include <vector>

#include "arrow/array/array_run_end.h"
#include "arrow/array/util.h"
#include "arrow/scalar.h"
#include "arrow/util/checked_cast.h"
#include "arrow/util/int_util_overflow.h"
Expand Down Expand Up @@ -102,7 +104,7 @@ Status RunCompressorBuilder::AppendScalar(const Scalar& scalar, int64_t n_repeat
current_value_ = scalar.is_valid ? scalar.shared_from_this() : NULLPTR;
current_run_length_ = n_repeats;
} else if ((current_value_ == NULLPTR && !scalar.is_valid) ||
(current_value_ != NULLPTR && current_value_->Equals(scalar))) {
(current_value_ != NULLPTR && current_value_->Equals(scalar, options_))) {
// Extend the currently open run
current_run_length_ += n_repeats;
} else {
Expand Down
5 changes: 4 additions & 1 deletion cpp/src/arrow/array/builder_run_end.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,8 +23,10 @@
#include <utility>
#include <vector>

#include "arrow/array.h"
#include "arrow/array/array_base.h"
#include "arrow/array/array_run_end.h"
#include "arrow/array/builder_base.h"
#include "arrow/compare.h"

namespace arrow {

Expand Down Expand Up @@ -161,6 +163,7 @@ class RunCompressorBuilder : public ArrayBuilder {
std::shared_ptr<ArrayBuilder> inner_builder_;
std::shared_ptr<const Scalar> current_value_ = NULLPTR;
int64_t current_run_length_ = 0;
const EqualOptions options_ = EqualOptions::Defaults().nans_equal(true);
};

} // namespace internal
Expand Down
Loading