Method transform

src/Processors/Transforms/PartialSortingTransform.cpp:104–189

}

void PartialSortingTransform::transform(Chunk & chunk)
{
    if (chunk.getNumRows())
    {
        // The following code works with Blocks and will lose the number of
        // rows when there are no columns. We shouldn't get such block, because
        // we have to sort by at least one column.
        chassert(chunk.getNumColumns());
    }

    if (read_rows)
        read_rows->add(chunk.getNumRows());

    auto block = getInputPort().getHeader().cloneWithColumns(chunk.detachColumns());

    /// Materialize sort key columns that are ColumnReplicated to avoid index indirection during comparison and sorting.
    for (const auto & col_desc : description)
    {
        auto & column_entry = block.getByName(col_desc.column_name);
        column_entry.column = convertToFullColumnIfReplicationNotUseful(column_entry.column);
    }

    /** If we've saved columns from previously blocks we could filter all rows from current block
      * which are unnecessary for sortBlock(...) because they obviously won't be in the top LIMIT rows.
      */
    if (!sort_description_threshold_columns.empty() && !threshold_tracker)
    {
        UInt64 rows_num = block.rows();
        auto block_columns = extractRawColumns(block, description_with_positions);

        size_t result_size_hint = getFilterMask(
                block_columns, sort_description_threshold_columns,
                description, rows_num, filter, rows_to_compare, compare_results);

        /// Everything was filtered. Skip whole chunk.
        if (result_size_hint == 0)
            return;

        if (result_size_hint < rows_num)
        {
            for (auto & column : block)
                column.column = column.column->filter(filter, result_size_hint);
        }
    }

    sortBlock(block, description, limit);

    /// Check if we can use this block for optimization.
    if ((min_limit_for_partial_sort_optimization <= limit || threshold_tracker) && limit <= block.rows())
    {
        /** If we filtered more than limit rows from block take block last row.
          * Otherwise take last limit row.
          *
          * If current threshold value is empty, update current threshold value.
          * If min block value is less than current threshold value, update current threshold value.
          */
        size_t min_row_to_compare = limit - 1;
        auto raw_block_columns = extractRawColumns(block, description_with_positions);