lidavidm commented on a change in pull request #9620:
URL: https://github.com/apache/arrow/pull/9620#discussion_r643134379
##########
File path: cpp/src/parquet/arrow/arrow_reader_writer_test.cc
##########
@@ -2331,6 +2330,63 @@ TEST(TestArrowReadWrite, GetRecordBatchReaderNoColumns) {
ASSERT_EQ(actual_batch->num_rows(), num_rows);
}
+TEST(TestArrowReadWrite, GetRecordBatchGenerator) {
+ ArrowReaderProperties properties = default_arrow_reader_properties();
+ const int num_rows = 1024;
+ const int row_group_size = 512;
+ const int num_columns = 2;
+
+ std::shared_ptr<Table> table;
+ ASSERT_NO_FATAL_FAILURE(MakeDoubleTable(num_columns, num_rows, 1, &table));
+
+ std::shared_ptr<Buffer> buffer;
+ ASSERT_NO_FATAL_FAILURE(WriteTableToBuffer(table, row_group_size,
+
default_arrow_writer_properties(), &buffer));
+
+ std::shared_ptr<FileReader> reader;
+ {
+ std::unique_ptr<FileReader> unique_reader;
+ FileReaderBuilder builder;
+ ASSERT_OK(builder.Open(std::make_shared<BufferReader>(buffer)));
+ ASSERT_OK(builder.properties(properties)->Build(&unique_reader));
+ reader = std::move(unique_reader);
+ }
+
+ auto check_batches = [](const std::shared_ptr<::arrow::RecordBatch>& batch,
+ int num_columns, int num_rows) {
+ ASSERT_NE(batch, nullptr);
+ ASSERT_EQ(batch->num_columns(), num_columns);
+ ASSERT_EQ(batch->num_rows(), num_rows);
+ };
+ {
+ ASSERT_OK_AND_ASSIGN(auto batch_generator,
+ reader->GetRecordBatchGenerator(reader, {0, 1}, {0,
1}));
+ auto fut1 = batch_generator();
+ auto fut2 = batch_generator();
+ auto fut3 = batch_generator();
+ ASSERT_OK_AND_ASSIGN(auto batch1, fut1.result());
+ ASSERT_OK_AND_ASSIGN(auto batch2, fut2.result());
+ ASSERT_OK_AND_ASSIGN(auto batch3, fut3.result());
+ ASSERT_EQ(batch3, nullptr);
+ check_batches(batch1, num_columns, row_group_size);
+ check_batches(batch2, num_columns, row_group_size);
+ }
+ {
+ // No columns case
+ ASSERT_OK_AND_ASSIGN(auto batch_generator,
+ reader->GetRecordBatchGenerator(reader, {0, 1}, {}));
Review comment:
Yes, I figured this is a lower-level API. We could add overloads to ease
this.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
