Skip to content

ARROW-18087: [C++] RecordBatch::Equals should not ignore field names #14451

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
pitrou merged 5 commits into from
Oct 26, 2022
Merged

ARROW-18087: [C++] RecordBatch::Equals should not ignore field names #14451

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
1a30c07
ARROW-18087: [C++] RecordBatch::Equals should not ignore field names
jorisvandenbossche Oct 18, 2022
32f97a0
add test
jorisvandenbossche Oct 19, 2022
fe9380e
Merge remote-tracking branch 'upstream/master' into ARROW-18087-recor…
jorisvandenbossche Oct 20, 2022
3067b87
remove unnecessary true
jorisvandenbossche Oct 20, 2022
a947156
Merge remote-tracking branch 'upstream/master' into ARROW-18087-recor…
jorisvandenbossche Oct 26, 2022
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
2 changes: 1 addition & 1 deletion cpp/src/arrow/dataset/test_util.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -157,7 +157,7 @@ class DatasetFixtureMixin : public ::testing::Test {
std::shared_ptr<RecordBatch> lhs;
ASSERT_OK(expected->ReadNext(&lhs));
EXPECT_NE(lhs, nullptr);
AssertBatchesEqual(*lhs, batch, true);
AssertBatchesEqual(*lhs, batch);
}

/// \brief Ensure that record batches found in reader are equals to the
Expand Down
6 changes: 2 additions & 4 deletions cpp/src/arrow/record_batch.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,10 +231,8 @@ bool RecordBatch::Equals(const RecordBatch& other, bool check_metadata) const {
return false;
}

if (check_metadata) {
if (!schema_->Equals(*other.schema(), /*check_metadata=*/true)) {
return false;
}
if (!schema_->Equals(*other.schema(), check_metadata)) {
return false;
}

for (int i = 0; i < num_columns(); ++i) {
Expand Down
6 changes: 6 additions & 0 deletions cpp/src/arrow/record_batch_test.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,13 +47,15 @@ TEST_F(TestRecordBatch, Equals) {
auto f0 = field("f0", int32());
auto f1 = field("f1", uint8());
auto f2 = field("f2", int16());
auto f2b = field("f2b", int16());

auto metadata = key_value_metadata({"foo"}, {"bar"});

std::vector<std::shared_ptr<Field>> fields = {f0, f1, f2};
auto schema = ::arrow::schema({f0, f1, f2});
auto schema2 = ::arrow::schema({f0, f1});
auto schema3 = ::arrow::schema({f0, f1, f2}, metadata);
auto schema4 = ::arrow::schema({f0, f1, f2b});

random::RandomArrayGenerator gen(42);

Expand All @@ -65,11 +67,15 @@ TEST_F(TestRecordBatch, Equals) {
auto b2 = RecordBatch::Make(schema3, length, {a0, a1, a2});
auto b3 = RecordBatch::Make(schema2, length, {a0, a1});
auto b4 = RecordBatch::Make(schema, length, {a0, a1, a1});
auto b5 = RecordBatch::Make(schema4, length, {a0, a1, a2});

ASSERT_TRUE(b1->Equals(*b1));
ASSERT_FALSE(b1->Equals(*b3));
ASSERT_FALSE(b1->Equals(*b4));

// Same values and types, but different field names
ASSERT_FALSE(b1->Equals(*b5));

// Different metadata
ASSERT_TRUE(b1->Equals(*b2));
ASSERT_FALSE(b1->Equals(*b2, /*check_metadata=*/true));
Expand Down