std::unique_ptr<IMergeTreeIndex> minmaxIndexCreator(
const NamesAndTypesList & new_columns,
std::shared_ptr<ASTIndexDeclaration> node,
const Context & context)
{
if (node->name.empty())
throw Exception("Index must have unique name", ErrorCodes::INCORRECT_QUERY);
if (node->type->arguments)
throw Exception("Minmax index have not any arguments", ErrorCodes::INCORRECT_QUERY);
ASTPtr expr_list = MergeTreeData::extractKeyExpressionList(node->expr->clone());
auto syntax = SyntaxAnalyzer(context, {}).analyze(
expr_list, new_columns);
auto minmax_expr = ExpressionAnalyzer(expr_list, syntax, context).getActions(false);
auto sample = ExpressionAnalyzer(expr_list, syntax, context)
.getActions(true)->getSampleBlock();
Names columns;
DataTypes data_types;
for (size_t i = 0; i < expr_list->children.size(); ++i)
{
const auto & column = sample.getByPosition(i);
columns.emplace_back(column.name);
data_types.emplace_back(column.type);
}
return std::make_unique<MergeTreeMinMaxIndex>(
node->name, std::move(minmax_expr), columns, data_types, sample, node->granularity);
}
NameSet MergeTreeReadPool::injectRequiredColumns(const MergeTreeData::DataPartPtr & part, Names & columns) const
{
NameSet required_columns{std::begin(columns), std::end(columns)};
NameSet injected_columns;
auto all_column_files_missing = true;
for (size_t i = 0; i < columns.size(); ++i)
{
const auto & column_name = columns[i];
/// column has files and hence does not require evaluation
if (part->hasColumnFiles(column_name))
{
all_column_files_missing = false;
continue;
}
const auto default_it = data.column_defaults.find(column_name);
/// columns has no explicit default expression
if (default_it == std::end(data.column_defaults))
continue;
/// collect identifiers required for evaluation
IdentifierNameSet identifiers;
default_it->second.expression->collectIdentifierNames(identifiers);
for (const auto & identifier : identifiers)
{
if (data.hasColumn(identifier))
{
/// ensure each column is added only once
if (required_columns.count(identifier) == 0)
{
columns.emplace_back(identifier);
required_columns.emplace(identifier);
injected_columns.emplace(identifier);
}
}
}
}
/** Добавить столбец минимального размера.
* Используется в случае, когда ни один столбец не нужен или файлы отсутствуют, но нужно хотя бы знать количество строк.
* Добавляет в columns.
*/
if (all_column_files_missing)
{
const auto minimum_size_column_name = part->getColumnNameWithMinumumCompressedSize();
columns.push_back(minimum_size_column_name);
/// correctly report added column
injected_columns.insert(columns.back());
}
return injected_columns;
}