Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 2 additions & 2 deletions cpp/src/arrow/record_batch.cc
Original file line number Diff line number Diff line change
Expand Up @@ -414,8 +414,8 @@ Result<std::shared_ptr<RecordBatch>> RecordBatch::RenameColumns(
fields[i] = schema()->field(i)->WithName(names[i]);
}

return RecordBatch::Make(::arrow::schema(std::move(fields)), num_rows(),
std::move(columns), GetSyncEvent());
return RecordBatch::Make(::arrow::schema(std::move(fields), schema()->metadata()),
num_rows(), std::move(columns), GetSyncEvent());
}

Result<std::shared_ptr<RecordBatch>> RecordBatch::SelectColumns(
Expand Down
26 changes: 26 additions & 0 deletions cpp/src/arrow/record_batch_test.cc
Original file line number Diff line number Diff line change
Expand Up @@ -521,6 +521,32 @@ TEST_F(TestRecordBatch, RenameColumns) {
ASSERT_RAISES(Invalid, batch->RenameColumns({"hello", "world"}));
}

TEST_F(TestRecordBatch, RenameColumnsPreservesMetadata) {
const int length = 10;

auto field1 = field("f1", int32());
auto field2 = field("f2", uint8());
auto field3 = field("f3", int16());

auto metadata = key_value_metadata({"foo", "bar"}, {"fizz", "buzz"});
auto schema1 = ::arrow::schema({field1, field2, field3})->WithMetadata(metadata);

random::RandomArrayGenerator gen(42);

auto array1 = gen.ArrayOf(int32(), length);
auto array2 = gen.ArrayOf(uint8(), length);
auto array3 = gen.ArrayOf(int16(), length);

auto batch = RecordBatch::Make(schema1, length, {array1, array2, array3});

ASSERT_OK_AND_ASSIGN(auto renamed, batch->RenameColumns({"zero", "one", "two"}));
EXPECT_THAT(renamed->ColumnNames(), testing::ElementsAre("zero", "one", "two"));

// Verify metadata is preserved
ASSERT_NE(nullptr, renamed->schema()->metadata());
ASSERT_TRUE(renamed->schema()->metadata()->Equals(*metadata));
}

TEST_F(TestRecordBatch, SelectColumns) {
const int length = 10;

Expand Down
3 changes: 2 additions & 1 deletion cpp/src/arrow/table.cc
Original file line number Diff line number Diff line change
Expand Up @@ -366,7 +366,8 @@ Result<std::shared_ptr<Table>> Table::RenameColumns(
columns[i] = column(i);
fields[i] = field(i)->WithName(names[i]);
}
return Table::Make(::arrow::schema(std::move(fields)), std::move(columns), num_rows());
return Table::Make(::arrow::schema(std::move(fields), schema()->metadata()),
std::move(columns), num_rows());
}

Result<std::shared_ptr<Table>> Table::SelectColumns(
Expand Down
14 changes: 14 additions & 0 deletions cpp/src/arrow/table_test.cc
Original file line number Diff line number Diff line change
Expand Up @@ -801,6 +801,20 @@ TEST_F(TestTable, RenameColumns) {
ASSERT_RAISES(Invalid, table->RenameColumns({"hello", "world"}));
}

TEST_F(TestTable, RenameColumnsPreservesMetadata) {
MakeExample1(10);
auto metadata = key_value_metadata({"foo", "bar"}, {"fizz", "buzz"});
auto schema_with_metadata = schema_->WithMetadata(metadata);
auto table = Table::Make(schema_with_metadata, columns_);

ASSERT_OK_AND_ASSIGN(auto renamed, table->RenameColumns({"zero", "one", "two"}));
EXPECT_THAT(renamed->ColumnNames(), testing::ElementsAre("zero", "one", "two"));

// Verify metadata is preserved
ASSERT_NE(nullptr, renamed->schema()->metadata());
ASSERT_TRUE(renamed->schema()->metadata()->Equals(*metadata));
}

TEST_F(TestTable, SelectColumns) {
MakeExample1(10);
auto table = Table::Make(schema_, columns_);
Expand Down
2 changes: 1 addition & 1 deletion cpp/src/arrow/type.cc
Original file line number Diff line number Diff line change
Expand Up @@ -2459,7 +2459,7 @@ Result<std::shared_ptr<Schema>> Schema::WithNames(
for (const auto& field : impl_->fields_) {
new_fields.push_back(field->WithName(*names_itr++));
}
return schema(std::move(new_fields));
return schema(std::move(new_fields), metadata());
}

std::shared_ptr<Schema> Schema::WithMetadata(
Expand Down
20 changes: 20 additions & 0 deletions cpp/src/arrow/type_test.cc
Original file line number Diff line number Diff line change
Expand Up @@ -713,6 +713,26 @@ TEST_F(TestSchema, TestRemoveMetadata) {
ASSERT_TRUE(new_schema->metadata() == nullptr);
}

TEST_F(TestSchema, TestWithNamesPreservesMetadata) {
auto f0 = field("f0", int32());
auto f1 = field("f1", uint8(), false);
auto f2 = field("f2", utf8());
auto metadata = key_value_metadata({{"foo", "bar"}, {"fizz", "buzz"}});
auto schema_with_metadata = std::make_shared<Schema>(
std::vector<std::shared_ptr<Field>>{f0, f1, f2}, metadata);

ASSERT_OK_AND_ASSIGN(auto renamed, schema_with_metadata->WithNames({"a", "b", "c"}));

// Verify names are updated
ASSERT_EQ("a", renamed->field(0)->name());
ASSERT_EQ("b", renamed->field(1)->name());
ASSERT_EQ("c", renamed->field(2)->name());

// Verify metadata is preserved
ASSERT_NE(nullptr, renamed->metadata());
ASSERT_TRUE(renamed->metadata()->Equals(*metadata));
}

void AssertSchemaBuilderYield(const SchemaBuilder& builder,
const std::shared_ptr<Schema>& expected) {
ASSERT_OK_AND_ASSIGN(auto schema, builder.Finish());
Expand Down
25 changes: 25 additions & 0 deletions python/pyarrow/tests/test_table.py
Original file line number Diff line number Diff line change
Expand Up @@ -1801,6 +1801,31 @@ def test_table_rename_columns(cls):
table.rename_columns('not a list')


@pytest.mark.parametrize(
('cls'),
[
(pa.Table),
(pa.RecordBatch)
]
)
def test_rename_columns_preserves_metadata(cls):
# GH-48024: rename_columns() should preserve schema metadata
schema = pa.schema(
[pa.field("n_legs", pa.int64()), pa.field("animals", pa.string())],
metadata={"source": "zoo"},
)
if cls == pa.Table:
obj = cls.from_arrays([[2, 4], ["Flamingo", "Horse"]], schema=schema)
else:
obj = cls.from_arrays([pa.array([2, 4]), pa.array(["Flamingo", "Horse"])],
schema=schema)
assert obj.schema.metadata == {b"source": b"zoo"}

new_obj = obj.rename_columns(["n", "name"])
assert new_obj.column_names == ["n", "name"]
assert new_obj.schema.metadata == {b"source": b"zoo"}


@pytest.mark.parametrize(
('cls'),
[
Expand Down