pitrou commented on a change in pull request #9791:
URL: https://github.com/apache/arrow/pull/9791#discussion_r601647099
##########
File path: cpp/src/parquet/file_serialize_test.cc
##########
@@ -123,16 +123,30 @@ class TestSerialize : public PrimitiveTypedTest<TestType>
{
for (int rg = 0; rg < num_rowgroups_; ++rg) {
auto rg_reader = file_reader->RowGroup(rg);
- ASSERT_EQ(num_columns_, rg_reader->metadata()->num_columns());
- ASSERT_EQ(rows_per_rowgroup_, rg_reader->metadata()->num_rows());
+ auto rg_metadata = rg_reader->metadata();
+ ASSERT_EQ(num_columns_, rg_metadata->num_columns());
+ ASSERT_EQ(rows_per_rowgroup_, rg_metadata->num_rows());
// Check that the specified compression was actually used.
- ASSERT_EQ(expected_codec_type,
- rg_reader->metadata()->ColumnChunk(0)->compression());
+ ASSERT_EQ(expected_codec_type,
rg_metadata->ColumnChunk(0)->compression());
+
+ const int64_t total_byte_size = rg_metadata->total_byte_size();
+ const int64_t total_compressed_size =
rg_metadata->total_compressed_size();
+ if (expected_codec_type == Compression::UNCOMPRESSED) {
+ ASSERT_EQ(total_byte_size, total_compressed_size);
+ } else {
+ ASSERT_NE(total_byte_size, total_compressed_size);
Review comment:
Well, with small buffers you may indeed get a size growth (some of the
files in `parquet-testing` actually exhibit that).
--
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]
