github-actions[bot] commented on code in PR #17054: URL: https://github.com/apache/doris/pull/17054#discussion_r1115277448
########## be/src/vec/exec/format/parquet/vparquet_column_chunk_reader.cpp: ########## @@ -83,31 +97,58 @@ Status ColumnChunkReader::load_page_data() { if (_block_compress_codec != nullptr) { Slice compressed_data; RETURN_IF_ERROR(_page_reader->get_page_data(compressed_data)); - // check decompressed buffer size - _reserve_decompress_buf(uncompressed_size); - _page_data = Slice(_decompress_buf.get(), uncompressed_size); - SCOPED_RAW_TIMER(&_statistics.decompress_time); - _statistics.decompress_cnt++; - RETURN_IF_ERROR(_block_compress_codec->decompress(compressed_data, &_page_data)); + if (header.__isset.data_page_header_v2) { + tparquet::DataPageHeaderV2 header_v2 = header.data_page_header_v2; + uncompressed_size -= header_v2.repetition_levels_byte_length + + header_v2.definition_levels_byte_length; + get_uncompressed_levels(header_v2, compressed_data); + } + bool is_v2_compressed = + header.__isset.data_page_header_v2 && header.data_page_header_v2.is_compressed; + if (header.__isset.data_page_header || is_v2_compressed) { + // check decompressed buffer size + _reserve_decompress_buf(uncompressed_size); + _page_data = Slice(_decompress_buf.get(), uncompressed_size); + SCOPED_RAW_TIMER(&_statistics.decompress_time); + _statistics.decompress_cnt++; + RETURN_IF_ERROR(_block_compress_codec->decompress(compressed_data, &_page_data)); + } else { + // Don't need decompress + _page_data = Slice(compressed_data.data, compressed_data.size); + } } else { RETURN_IF_ERROR(_page_reader->get_page_data(_page_data)); + if (header.__isset.data_page_header_v2) { Review Comment: warning: use of undeclared identifier 'get_levels' [clang-diagnostic-error] ```cpp RETURN_IF_ERROR(get_levels(header_v2, _page_data)); ^ ``` -- 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. To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: commits-unsubscr...@doris.apache.org For additional commands, e-mail: commits-h...@doris.apache.org