Skip to content

GH-44827: [C++] Skip null slots when transposing dictionary indices #54686

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
Nayana-Naik73 wants to merge 1 commit into from
Closed

GH-44827: [C++] Skip null slots when transposing dictionary indices #54686

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
25 changes: 18 additions & 7 deletions cpp/src/arrow/array/array_dict.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@
#include <algorithm>
#include <climits>
#include <cstdint>
#include <cstring>
#include <limits>
#include <utility>
#include <vector>
Expand All @@ -36,6 +37,7 @@
#include "arrow/table.h"
#include "arrow/type.h"
#include "arrow/type_traits.h"
#include "arrow/util/bit_run_reader.h"
#include "arrow/util/bit_util.h"
#include "arrow/util/bitmap_ops.h"
#include "arrow/util/checked_cast.h"
Expand Down Expand Up @@ -187,9 +189,8 @@ Result<std::shared_ptr<ArrayData>> TransposeDictIndices(
}

// Default path: compute a buffer of transposed indices.
ARROW_ASSIGN_OR_RAISE(
auto out_buffer,
AllocateBuffer(data->length * (out_index_type.bit_width() / CHAR_BIT), pool));
const int64_t out_buffer_size = data->length * (out_index_type.bit_width() / CHAR_BIT);
ARROW_ASSIGN_OR_RAISE(auto out_buffer, AllocateBuffer(out_buffer_size, pool));

// Shift null buffer if the original offset is non-zero
std::shared_ptr<Buffer> null_bitmap;
Expand All @@ -203,10 +204,20 @@ Result<std::shared_ptr<ArrayData>> TransposeDictIndices(
auto out_data = ArrayData::Make(out_type, data->length,
{null_bitmap, std::move(out_buffer)}, data->null_count);
out_data->dictionary = dictionary;
RETURN_NOT_OK(internal::TransposeInts(
in_index_type, out_index_type, data->GetValues<uint8_t>(1, 0),
out_data->GetMutableValues<uint8_t>(1, 0), data->offset, out_data->offset,
data->length, transpose_map));
const uint8_t* in_indices = data->GetValues<uint8_t>(1, 0);
uint8_t* out_indices = out_data->GetMutableValues<uint8_t>(1, 0);
// Indices under null slots are unspecified and may be out of bounds for
// transpose_map, so zero them and only transpose the valid runs.
if (data->MayHaveNulls()) {
std::memset(out_indices, 0, static_cast<size_t>(out_buffer_size));
}
RETURN_NOT_OK(internal::VisitSetBitRuns(data->buffers[0], data->offset, data->length,
[&](int64_t position, int64_t length) {
return internal::TransposeInts(
in_index_type, out_index_type, in_indices,
out_indices, data->offset + position,
position, length, transpose_map);
}));
return out_data;
}

Expand Down
30 changes: 30 additions & 0 deletions cpp/src/arrow/array/array_dict_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1439,6 +1439,36 @@ TEST(TestDictionary, TransposeNulls) {
CheckTranspose(sliced, transpose_map.data(), out_dict_type, out_dict, expected_indices);
}

TEST(TestDictionary, TransposeNullsWithOutOfBoundsIndex) {
// Index values under null slots are not checked by ValidateFull(),
// so they must not be looked up in the transpose map.
auto dict = ArrayFromJSON(utf8(), "[\"A\", \"B\", \"C\"]");
auto dict_type = dictionary(int32(), utf8());
auto valid_indices = ArrayFromJSON(int32(), "[1, null, 0, null]");
auto indices = MakeArray(ArrayData::Make(
int32(), 4,
{valid_indices->data()->buffers[0],
Buffer::FromVector(std::vector<int32_t>{1, 1 << 30, 0, -(1 << 30)})},
/*null_count=*/2));
auto arr = std::make_shared<DictionaryArray>(dict_type, indices, dict);
ASSERT_OK(arr->ValidateFull());

auto out_dict = ArrayFromJSON(utf8(), "[\"Z\", \"A\", \"C\", \"B\"]");
std::vector<int32_t> transpose_map = {1, 3, 2};
CheckTranspose(arr, transpose_map.data(), dict_type, out_dict,
ArrayFromJSON(int32(), "[3, null, 1, null]"));
CheckTranspose(arr->Slice(1, 2), transpose_map.data(), dict_type, out_dict,
ArrayFromJSON(int32(), "[null, 1]"));

ASSERT_OK_AND_ASSIGN(auto compacted, arr->Compact());
ASSERT_OK(compacted->ValidateFull());
ASSERT_OK_AND_ASSIGN(
auto expected,
DictionaryArray::FromArrays(dict_type, ArrayFromJSON(int32(), "[1, null, 0, null]"),
ArrayFromJSON(utf8(), "[\"A\", \"B\"]")));
AssertArraysEqual(*compacted, *expected);
}

TEST(TestDictionary, ListOfDictionary) {
std::unique_ptr<ArrayBuilder> root_builder;
ASSERT_OK(MakeBuilder(default_memory_pool(), list(dictionary(int8(), utf8())),
Expand Down
Loading