【发布时间】:2021-12-06 12:40:57
【问题描述】:
我正在尝试将 Apache Arrow 表写入字符串。我的大例子有问题,我无法让这个小例子工作。这在 WriteTable 调用中的 Arrow 内部发生了段错误。我更大的例子似乎没有正确序列化。
#include <arrow/api.h>
#include <arrow/io/memory.h>
#include <arrow/ipc/api.h>
std::shared_ptr<arrow::Table> makeSimpleFakeArrowTable() {
std::vector<std::shared_ptr<arrow::Field>> arrowFields;
arrowFields.emplace_back(std::make_shared<arrow::Field>("Field1", arrow::int64()));
arrowFields.emplace_back(std::make_shared<arrow::Field>("Field2", arrow::float64()));
auto schema = std::make_shared<arrow::Schema>(arrowFields);
std::vector<std::shared_ptr<arrow::Array>> columns(schema->num_fields());
arrow::Int64Builder longBuilder;
longBuilder.Append(20);
longBuilder.Finish(&(columns.at(0)));
arrow::DoubleBuilder doubleBuilder;
doubleBuilder.Append(10.0);
longBuilder.Finish(&(columns.at(1)));
return arrow::Table::Make(schema, columns);
}
std::shared_ptr<arrow::RecordBatch>
getArrowBatchFromBytes(const std::string& bytes) {
arrow::io::BufferReader arrowBufferReader{bytes};
auto streamReader =
arrow::ipc::RecordBatchStreamReader::Open(&arrowBufferReader).ValueOrDie();
auto batch = streamReader->Next().ValueOrDie();
return batch;
}
std::string arrowTableToByteString(const std::shared_ptr<arrow::Table>& table) {
auto stream = arrow::io::BufferOutputStream::Create().ValueOrDie();
auto batchWriter = arrow::ipc::MakeStreamWriter(stream, table->schema()).ValueOrDie();
auto status = batchWriter->WriteTable(*table);
if (not status.ok()) {
throw std::runtime_error(
"Couldn't write Arrow Table to byte string. Arrow status was: '" +
status.ToString() + "'.");
}
std::shared_ptr<arrow::Buffer> buffer = stream->Finish().ValueOrDie();
return buffer->ToHexString();
}
int main(int argc, char** argv) {
auto simpleFakeArrowTable = makeSimpleFakeArrowTable();
std::string tableAsByteString = arrowTableToByteString(simpleFakeArrowTable);
auto batch = getArrowBatchFromBytes(tableAsByteString);
assert(batch != nullptr);
}
【问题讨论】:
-
longBuilder.Finish(&(columns.at(0)));-- 在向量中使用项目地址是一种代码味道。该向量是否会调整大小? -
@PaulMcKenzie 感谢您的提问。它不会在该代码中调整大小。我使用需要大小的向量 ctor 来初始化它。我理解你关于调整大小的气味的观点,并且会说这种方法可能仍然最好是在堆上创建一个动态的 c 样式数组。
标签: c++ apache-arrow apache-arrow-cpp