lidavidm commented on a change in pull request #9620:
URL: https://github.com/apache/arrow/pull/9620#discussion_r643540804
##########
File path: cpp/src/parquet/file_reader.cc
##########
@@ -264,23 +264,92 @@ class SerializedFile : public ParquetFileReader::Contents
{
}
}
PARQUET_THROW_NOT_OK(cached_source_->Cache(ranges));
- return cached_source_->Wait();
}
+ ::arrow::Future<> WhenBuffered(const std::vector<int>& row_groups,
+ const std::vector<int>& column_indices) const
{
+ if (!cached_source_) {
+ return ::arrow::Status::Invalid("Must call PreBuffer before
WhenBuffered");
+ }
+ std::vector<::arrow::io::ReadRange> ranges;
+ for (int row : row_groups) {
+ for (int col : column_indices) {
+ ranges.push_back(
+ ComputeColumnChunkRange(file_metadata_.get(), source_size_, row,
col));
+ }
+ }
+ return cached_source_->WaitFor(ranges);
+ }
+
+ // Metadata/footer parsing. Divided up to separate sync/async paths, and to
use
+ // exceptions for error handling (with the async path converting to
Future/Status).
+
void ParseMetaData() {
Review comment:
I've updated the current encryption tests to test both Open and
OpenAsync (though let's hope they don't make the test flaky again).
##########
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);
Review comment:
I've adjusted the test to check equality below.
--
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]
