Skip to content

GH-37875: [C++][Parquet] Preserve large_string/large_binary dictionary value type on read #53259

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
nil68657 wants to merge 1 commit into from
Closed

GH-37875: [C++][Parquet] Preserve large_string/large_binary dictionary value type on read #53259

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
16 changes: 16 additions & 0 deletions cpp/src/parquet/arrow/arrow_reader_writer_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3811,6 +3811,22 @@ TEST(TestArrowReadWrite, DictionaryIndexBitwidthRoundtrip) {
}
}

TEST(TestArrowReadWrite, DictionaryValueTypeRoundtrip) {
// GH-37875: the binary layout of dictionary values should be preserved
for (const auto& value_type : {::arrow::utf8(), ::arrow::large_utf8(),
::arrow::binary(), ::arrow::large_binary()}) {
ARROW_SCOPED_TRACE("value_type = ", *value_type);
auto dict_type = ::arrow::dictionary(::arrow::int32(), value_type);
auto schema = ::arrow::schema({field("dictionary", dict_type)});
auto array = DictArrayFromJSON(dict_type, R"([0, 1, null, 0])", R"(["foo", "bar"])");
auto table = Table::Make(schema, {array});
auto arrow_writer_props =
parquet::ArrowWriterProperties::Builder().store_schema()->build();

CheckSimpleRoundtrip(table, table->num_rows(), arrow_writer_props);
}
}

TEST(TestArrowWrite, CheckChunkSize) {
const int num_columns = 2;
const int num_rows = 128;
Expand Down
11 changes: 10 additions & 1 deletion cpp/src/parquet/arrow/schema.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1110,8 +1110,17 @@ Result<bool> ApplyOriginalStorageMetadata(const Field& origin_field,
// so no need to recurse on value types.
const auto& dict_origin_type =
checked_cast<const ::arrow::DictionaryType&>(*origin_type);
auto value_type = inferred_type;
const auto& origin_value_type = dict_origin_type.value_type();
// Restore large dictionary values (GH-37875)
if ((origin_value_type->id() == ::arrow::Type::LARGE_STRING &&
inferred_type->id() == ::arrow::Type::STRING) ||
(origin_value_type->id() == ::arrow::Type::LARGE_BINARY &&
inferred_type->id() == ::arrow::Type::BINARY)) {
value_type = origin_value_type;
}
inferred->field = inferred->field->WithType(::arrow::dictionary(
dict_origin_type.index_type(), inferred_type, dict_origin_type.ordered()));
dict_origin_type.index_type(), value_type, dict_origin_type.ordered()));
modified = true;
}

Expand Down
Loading