Skip to content

GH-51779: [C++][IPC] Read a DictionaryEncoding without indexType as int32 indices #51807

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
CaptainAni187 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

GH-51779: [C++][IPC] Read a DictionaryEncoding without indexType as int32 indices #51807

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
24 changes: 24 additions & 0 deletions cpp/src/arrow/ipc/message_internal_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@
#include <iosfwd>
#include <memory>
#include <sstream>
#include <string>

#include <flatbuffers/flatbuffers.h>

Expand Down Expand Up @@ -114,6 +115,29 @@ TEST(TestMessageInternal, TestEndiannessRoundtrip) {
}
}

// GH-51779: Schema.fbs allows DictionaryEncoding.indexType to be omitted, in
// which case the indices are signed int32.
TEST(TestMessageInternal, DictionaryEncodingWithoutIndexType) {
FBB fbb;
auto name = fbb.CreateString("f0");
auto value_type = flatbuf::CreateUtf8(fbb);
auto encoding = flatbuf::CreateDictionaryEncoding(fbb, /*id=*/0, /*indexType=*/0);
auto fb_field = flatbuf::CreateField(fbb, name, /*nullable=*/true, flatbuf::Type_Utf8,
value_type.Union(), encoding);
auto fb_schema = flatbuf::CreateSchema(fbb, flatbuf::Endianness_Little,
fbb.CreateVector({fb_field}));
fbb.Finish(flatbuf::CreateMessage(fbb, flatbuf::MetadataVersion_V5,
flatbuf::MessageHeader_Schema, fb_schema.Union()));
auto metadata = Buffer::FromString(
std::string(reinterpret_cast<const char*>(fbb.GetBufferPointer()), fbb.GetSize()));

ASSERT_OK_AND_ASSIGN(auto message, Message::Open(metadata, /*body=*/nullptr));
DictionaryMemo memo;
ASSERT_OK_AND_ASSIGN(auto schema, ReadSchema(*message, &memo));
AssertSchemaEqual(*::arrow::schema({field("f0", dictionary(int32(), utf8()))}),
*schema);
}

struct SampleMessageParams {
std::shared_ptr<const KeyValueMetadata> custom_metadata = {};
int64_t body_length = 0;
Expand Down
8 changes: 6 additions & 2 deletions cpp/src/arrow/ipc/metadata_internal.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -898,8 +898,12 @@ Status FieldFromFlatbuffer(const flatbuf::Field* field, FieldPosition field_pos,
// dictionary_memo
std::shared_ptr<DataType> index_type;
auto int_data = encoding->indexType();
CHECK_FLATBUFFERS_NOT_NULL(int_data, "DictionaryEncoding.indexType");
RETURN_NOT_OK(IntFromFlatbuffer(int_data, &index_type));
if (int_data == nullptr) {
// Schema.fbs: "If this field is null, the indices must be signed int32."
index_type = int32();
} else {
RETURN_NOT_OK(IntFromFlatbuffer(int_data, &index_type));
}
dict_value_type = type;
ARROW_ASSIGN_OR_RAISE(type,
DictionaryType::Make(index_type, type, encoding->isOrdered()));
Expand Down
Loading