Skip to content
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.

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

GH-41317: [C++] Fix crash on invalid Parquet file #41366

Merged
merged 2 commits into from
Apr 30, 2024
Merged
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
2 changes: 2 additions & 0 deletions cpp/src/arrow/table.cc
Original file line number Diff line number Diff line change
Expand Up @@ -619,6 +619,7 @@ TableBatchReader::TableBatchReader(const Table& table)
for (int i = 0; i < table.num_columns(); ++i) {
column_data_[i] = table.column(i).get();
}
DCHECK(table_.Validate().ok());
}

TableBatchReader::TableBatchReader(std::shared_ptr<Table> table)
Expand All @@ -632,6 +633,7 @@ TableBatchReader::TableBatchReader(std::shared_ptr<Table> table)
for (int i = 0; i < owned_table_->num_columns(); ++i) {
column_data_[i] = owned_table_->column(i).get();
}
DCHECK(table_.Validate().ok());
}

std::shared_ptr<Schema> TableBatchReader::schema() const { return table_.schema(); }
Expand Down
2 changes: 2 additions & 0 deletions cpp/src/arrow/table.h
Original file line number Diff line number Diff line change
Expand Up @@ -241,6 +241,8 @@ class ARROW_EXPORT Table {
///
/// The conversion is zero-copy: each record batch is a view over a slice
/// of the table's columns.
///
/// The table is expected to be valid prior to using it with the batch reader.
class ARROW_EXPORT TableBatchReader : public RecordBatchReader {
public:
/// \brief Construct a TableBatchReader for the given table
Expand Down
10 changes: 10 additions & 0 deletions cpp/src/parquet/arrow/reader.cc
Original file line number Diff line number Diff line change
Expand Up @@ -1043,6 +1043,16 @@ Status FileReaderImpl::GetRecordBatchReader(const std::vector<int>& row_groups,
}
}

// Check all columns has same row-size
if (!columns.empty()) {
int64_t row_size = columns[0]->length();
for (size_t i = 1; i < columns.size(); ++i) {
if (columns[i]->length() != row_size) {
return ::arrow::Status::Invalid("columns do not have the same size");
}
}
}

auto table = ::arrow::Table::Make(batch_schema, std::move(columns));
auto table_reader = std::make_shared<::arrow::TableBatchReader>(*table);

Expand Down
Loading