Skip to content

fix(ipc): Decode a DictionaryEncoding without indexType as int32 indices #957

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

Merged
ianmcook merged 1 commit into from
Oct 9, 2026
Merged

fix(ipc): Decode a DictionaryEncoding without indexType as int32 indices #957

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
10 changes: 8 additions & 2 deletions src/nanoarrow/ipc/decoder.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1246,8 +1246,14 @@ static int ArrowIpcSetDictionaryEncoding(
error);
NANOARROW_RETURN_NOT_OK_WITH_ERROR(ArrowSchemaSetName(schema->dictionary, ""), error);

NANOARROW_RETURN_NOT_OK(ArrowIpcDecoderSetTypeInt(
schema, ns(DictionaryEncoding_indexType_get(dictionary_encoding)), error));
// Schema.fbs: "If this field is null, the indices must be signed int32."
if (ns(DictionaryEncoding_indexType_is_present(dictionary_encoding))) {
NANOARROW_RETURN_NOT_OK(ArrowIpcDecoderSetTypeInt(
schema, ns(DictionaryEncoding_indexType_get(dictionary_encoding)), error));
} else {
NANOARROW_RETURN_NOT_OK(
ArrowIpcDecoderSetTypeSimple(schema, NANOARROW_TYPE_INT32, error));
}

if (ns(DictionaryEncoding_isOrdered_get(dictionary_encoding))) {
schema->flags |= ARROW_FLAG_DICTIONARY_ORDERED;
Expand Down
44 changes: 44 additions & 0 deletions src/nanoarrow/ipc/decoder_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,6 +195,23 @@ alignas(8) static uint8_t kDictionarySchema[] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x08, 0x00, 0x00, 0x00, 0x04, 0x00, 0x04, 0x00,
0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00};

// Schema message with one field, some_col: dictionary<values=string, indices=int32>,
// written by pyarrow 25.0.1 with DictionaryEncoding.indexType removed (null means
// signed int32 per Schema.fbs)
alignas(8) static uint8_t kDictionarySchemaNoIndexType[] = {
0xff, 0xff, 0xff, 0xff, 0xa0, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x00, 0x00, 0x00,
0x0a, 0x00, 0x0c, 0x00, 0x06, 0x00, 0x05, 0x00, 0x08, 0x00, 0x0a, 0x00, 0x00, 0x00,
0x00, 0x01, 0x04, 0x00, 0x04, 0x00, 0x00, 0x00, 0xb4, 0xff, 0xff, 0xff, 0x04, 0x00,
0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x10, 0x00, 0x18, 0x00,
0x08, 0x00, 0x06, 0x00, 0x07, 0x00, 0x0c, 0x00, 0x10, 0x00, 0x14, 0x00, 0x10, 0x00,
0x00, 0x00, 0x00, 0x00, 0x01, 0x05, 0x14, 0x00, 0x00, 0x00, 0x48, 0x00, 0x00, 0x00,
0x24, 0x00, 0x00, 0x00, 0x04, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00,
0x00, 0x00, 0x73, 0x6f, 0x6d, 0x65, 0x5f, 0x63, 0x6f, 0x6c, 0x00, 0x00, 0x00, 0x00,
0x08, 0x00, 0x08, 0x00, 0x00, 0x00, 0x04, 0x00, 0xd8, 0xff, 0xff, 0xff, 0x0c, 0x00,
0x00, 0x00, 0x08, 0x00, 0x0c, 0x00, 0x08, 0x00, 0x07, 0x00, 0x08, 0x00, 0x00, 0x00,
0x00, 0x00, 0x00, 0x01, 0x20, 0x00, 0x00, 0x00, 0x04, 0x00, 0x04, 0x00, 0x04, 0x00,
0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x08, 0x00, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00};

alignas(8) static uint8_t kDictionaryBatch[] = {
0xff, 0xff, 0xff, 0xff, 0xa8, 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x00,
0x00, 0x00, 0x0c, 0x00, 0x14, 0x00, 0x06, 0x00, 0x05, 0x00, 0x08, 0x00, 0x0c, 0x00,
Expand Down Expand Up @@ -664,6 +681,33 @@ TEST(NanoarrowIpcTest, NanoarrowIpcDecodeDictionarySchema) {
ArrowIpcDecoderReset(&decoder);
}

TEST(NanoarrowIpcTest, NanoarrowIpcDecodeDictionarySchemaWithoutIndexType) {
struct ArrowIpcDecoder decoder;
struct ArrowError error;
struct ArrowSchema schema;

struct ArrowBufferView data;
data.data.as_uint8 = kDictionarySchemaNoIndexType;
data.size_bytes = sizeof(kDictionarySchemaNoIndexType);

ASSERT_EQ(ArrowIpcDecoderInit(&decoder), NANOARROW_OK);

ASSERT_EQ(ArrowIpcDecoderDecodeHeader(&decoder, data, &error), NANOARROW_OK)
<< error.message;
ASSERT_EQ(decoder.message_type, NANOARROW_IPC_MESSAGE_TYPE_SCHEMA);

ASSERT_EQ(ArrowIpcDecoderDecodeSchema(&decoder, &schema, &error), NANOARROW_OK)
<< error.message;
ASSERT_EQ(schema.n_children, 1);
EXPECT_STREQ(schema.children[0]->name, "some_col");
EXPECT_STREQ(schema.children[0]->format, "i");
ASSERT_NE(schema.children[0]->dictionary, nullptr);
EXPECT_STREQ(schema.children[0]->dictionary->format, "u");

ArrowSchemaRelease(&schema);
ArrowIpcDecoderReset(&decoder);
}

TEST(NanoarrowIpcTest, NanoarrowIpcDictionaryEncodingsUniqueIds) {
// Create dictionary encodings there is at least one duplicated identifier
struct ArrowIpcDictionaryEncodings dictionary_encodings;
Expand Down
Loading