ClickHouse/dbms/src/Interpreters/ExpressionAnalyzer.cpp

2972 lines
113 KiB
C++
Raw Normal View History

#include <Poco/Util/Application.h>
2016-11-20 12:43:20 +00:00
#include <Poco/String.h>
#include <DataTypes/FieldToDataType.h>
#include <Parsers/ASTFunction.h>
#include <Parsers/ASTIdentifier.h>
#include <Parsers/ASTLiteral.h>
#include <Parsers/ASTAsterisk.h>
#include <Parsers/ASTQualifiedAsterisk.h>
#include <Parsers/ASTExpressionList.h>
#include <Parsers/ASTSelectQuery.h>
#include <Parsers/ASTSubquery.h>
#include <Parsers/ASTOrderByElement.h>
#include <DataTypes/DataTypeSet.h>
#include <DataTypes/DataTypeArray.h>
2017-12-25 00:38:45 +00:00
#include <DataTypes/DataTypeNullable.h>
#include <DataTypes/DataTypeTuple.h>
#include <DataTypes/DataTypeExpression.h>
#include <DataTypes/NestedUtils.h>
#include <DataTypes/DataTypesNumber.h>
#include <Columns/ColumnSet.h>
#include <Columns/ColumnExpression.h>
ColumnConst unification (#1011) * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * Fixed error in ColumnArray::replicateGeneric [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150]. * ColumnConst: unification (incomplete) [#CLICKHOUSE-3150].
2017-07-21 06:35:58 +00:00
#include <Columns/ColumnConst.h>
#include <Interpreters/InterpreterSelectQuery.h>
#include <Interpreters/ExpressionAnalyzer.h>
#include <Interpreters/ExpressionActions.h>
#include <Interpreters/InJoinSubqueriesPreprocessor.h>
#include <Interpreters/LogicalExpressionsOptimizer.h>
#include <Interpreters/ExternalDictionaries.h>
#include <Interpreters/Set.h>
#include <Interpreters/Join.h>
#include <AggregateFunctions/AggregateFunctionFactory.h>
#include <AggregateFunctions/parseAggregateFunctionParameters.h>
2015-04-16 06:12:35 +00:00
#include <Storages/StorageDistributed.h>
#include <Storages/StorageMemory.h>
#include <Storages/StorageSet.h>
#include <Storages/StorageJoin.h>
#include <DataStreams/LazyBlockInputStream.h>
#include <DataStreams/copyData.h>
#include <Dictionaries/IDictionary.h>
#include <Common/typeid_cast.h>
#include <Common/StringUtils/StringUtils.h>
#include <Parsers/formatAST.h>
#include <Functions/FunctionFactory.h>
#include <Functions/IFunction.h>
2014-12-17 15:26:24 +00:00
2017-06-06 17:18:32 +00:00
#include <ext/range.h>
#include <DataTypes/DataTypeFactory.h>
namespace DB
{
namespace ErrorCodes
{
extern const int MULTIPLE_EXPRESSIONS_FOR_ALIAS;
extern const int UNKNOWN_IDENTIFIER;
extern const int CYCLIC_ALIASES;
extern const int INCORRECT_RESULT_OF_SCALAR_SUBQUERY;
extern const int TOO_MUCH_ROWS;
extern const int NOT_FOUND_COLUMN_IN_BLOCK;
extern const int INCORRECT_ELEMENT_OF_SET;
extern const int ALIAS_REQUIRED;
extern const int EMPTY_NESTED_TABLE;
extern const int NOT_AN_AGGREGATE;
extern const int UNEXPECTED_EXPRESSION;
extern const int DUPLICATE_COLUMN;
extern const int FUNCTION_CANNOT_HAVE_PARAMETERS;
extern const int ILLEGAL_AGGREGATION;
extern const int SUPPORT_IS_DISABLED;
extern const int TOO_DEEP_AST;
extern const int NUMBER_OF_ARGUMENTS_DOESNT_MATCH;
}
2014-07-31 08:14:19 +00:00
/** Calls to these functions in the GROUP BY statement would be
* replaced by their immediate argument.
*/
2014-08-19 23:12:31 +00:00
const std::unordered_set<String> injective_function_names
{
"negate",
"bitNot",
"reverse",
"reverseUTF8",
"toString",
"toFixedString",
"IPv4NumToString",
"IPv4StringToNum",
"hex",
"unhex",
"bitmaskToList",
"bitmaskToArray",
"tuple",
"regionToName",
"concatAssumeInjective",
};
const std::unordered_set<String> possibly_injective_function_names
{
"dictGetString",
"dictGetUInt8",
"dictGetUInt16",
"dictGetUInt32",
"dictGetUInt64",
"dictGetInt8",
"dictGetInt16",
"dictGetInt32",
"dictGetInt64",
"dictGetFloat32",
"dictGetFloat64",
"dictGetDate",
"dictGetDateTime"
};
2015-09-18 13:36:10 +00:00
namespace
{
bool functionIsInOperator(const String & name)
{
return name == "in" || name == "notIn";
}
2015-09-18 13:36:10 +00:00
bool functionIsInOrGlobalInOperator(const String & name)
{
return name == "in" || name == "notIn" || name == "globalIn" || name == "globalNotIn";
}
void removeDuplicateColumns(NamesAndTypesList & columns)
{
std::set<String> names;
for (auto it = columns.begin(); it != columns.end();)
{
if (names.emplace(it->name).second)
++it;
else
columns.erase(it++);
}
}
2015-09-18 13:36:10 +00:00
}
Squashed commit of the following: commit e712f469a55ff34ad34b482b15cc4153b7ad7233 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:59:13 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2a002823084e3a79bffcc17d479620a68eb0644b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:58:30 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 9e06f407c8ee781ed8ddf98bdfcc31846bf2a0fe Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:55:14 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 9581620f1e839f456fa7894aa1f996d5162ac6cd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:54:22 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2a8564c68cb6cc3649fafaf401256d43c9a2e777 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:47:34 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit cf60632d78ec656be3304ef4565e859bb6ce80ba Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:40:09 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit ee3d1dc6e0c4ca60e3ac1e0c30d4b3ed1e66eca0 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:22:49 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 65592ef7116a90104fcd524b53ef8b7cf22640f2 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:18:17 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 37972c257320d3b7e7b294e0fdeffff218647bfd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:17:06 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit dd909d149974ce5bed2456de1261aa5a368fd3ff Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:16:28 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 3cf43266ca7e30adf01212b1a739ba5fe43639fd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:15:42 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 6731a3df96d1609286e2536b6432916af7743f0f Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:13:35 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 1b5727e0d56415b7add4cb76110105358663602c Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:11:18 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit bbcf726a55685b8e72f5b40ba0bf1904bd1c0407 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:09:04 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit c03b477d5e2e65014e8906ecfa2efb67ee295af1 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:06:30 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2986e2fb0466bc18d73693dcdded28fccc0dc66b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:05:44 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 5d6cdef13d2e02bd5c4954983334e9162ab2635b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:04:53 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit f2b819b25ce8b2ccdcb201eefb03e1e6f5aab590 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:01:47 2017 +0300 Less dependencies [#CLICKHOUSE-2]
2017-01-14 09:00:19 +00:00
ExpressionAnalyzer::ExpressionAnalyzer(
const ASTPtr & ast_,
const Context & context_,
const StoragePtr & storage_,
const NamesAndTypesList & columns_,
size_t subquery_depth_,
bool do_global_)
: ast(ast_), context(context_), settings(context.getSettings()),
subquery_depth(subquery_depth_), columns(columns_),
storage(storage_ ? storage_ : getTable()),
do_global(do_global_)
{
init();
Squashed commit of the following: commit e712f469a55ff34ad34b482b15cc4153b7ad7233 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:59:13 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2a002823084e3a79bffcc17d479620a68eb0644b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:58:30 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 9e06f407c8ee781ed8ddf98bdfcc31846bf2a0fe Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:55:14 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 9581620f1e839f456fa7894aa1f996d5162ac6cd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:54:22 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2a8564c68cb6cc3649fafaf401256d43c9a2e777 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:47:34 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit cf60632d78ec656be3304ef4565e859bb6ce80ba Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:40:09 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit ee3d1dc6e0c4ca60e3ac1e0c30d4b3ed1e66eca0 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:22:49 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 65592ef7116a90104fcd524b53ef8b7cf22640f2 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:18:17 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 37972c257320d3b7e7b294e0fdeffff218647bfd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:17:06 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit dd909d149974ce5bed2456de1261aa5a368fd3ff Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:16:28 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 3cf43266ca7e30adf01212b1a739ba5fe43639fd Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:15:42 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 6731a3df96d1609286e2536b6432916af7743f0f Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:13:35 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 1b5727e0d56415b7add4cb76110105358663602c Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:11:18 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit bbcf726a55685b8e72f5b40ba0bf1904bd1c0407 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:09:04 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit c03b477d5e2e65014e8906ecfa2efb67ee295af1 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:06:30 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 2986e2fb0466bc18d73693dcdded28fccc0dc66b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:05:44 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit 5d6cdef13d2e02bd5c4954983334e9162ab2635b Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:04:53 2017 +0300 Less dependencies [#CLICKHOUSE-2] commit f2b819b25ce8b2ccdcb201eefb03e1e6f5aab590 Author: Alexey Milovidov <milovidov@yandex-team.ru> Date: Sat Jan 14 11:01:47 2017 +0300 Less dependencies [#CLICKHOUSE-2]
2017-01-14 09:00:19 +00:00
}
void ExpressionAnalyzer::init()
{
removeDuplicateColumns(columns);
select_query = typeid_cast<ASTSelectQuery *>(ast.get());
translateQualifiedNames();
2017-04-02 17:37:49 +00:00
/// Depending on the user's profile, check for the execution rights
/// distributed subqueries inside the IN or JOIN sections and process these subqueries.
InJoinSubqueriesPreprocessor(context).process(select_query);
2015-09-18 13:36:10 +00:00
2017-04-02 17:37:49 +00:00
/// Optimizes logical expressions.
LogicalExpressionsOptimizer(select_query, settings).perform();
2017-04-02 17:37:49 +00:00
/// Creates a dictionary `aliases`: alias -> ASTPtr
addASTAliases(ast);
/// Common subexpression elimination. Rewrite rules.
normalizeTree();
2017-04-02 17:37:49 +00:00
/// ALIAS columns should not be substituted for ASTAsterisk, we will add them now, after normalizeTree.
addAliasColumns();
2017-04-02 17:37:49 +00:00
/// Executing scalar subqueries - replacing them with constant values.
executeScalarSubqueries();
2017-07-16 22:55:40 +00:00
/// Optimize if with constant condition after constants was substituted instead of sclalar subqueries.
optimizeIfWithConstantCondition();
/// GROUP BY injective function elimination.
optimizeGroupBy();
2017-04-02 17:37:49 +00:00
/// Remove duplicate items from ORDER BY.
optimizeOrderBy();
// Remove duplicated elements from LIMIT BY clause.
optimizeLimitBy();
/// array_join_alias_to_name, array_join_result_to_source.
getArrayJoinedColumns();
2017-04-02 17:37:49 +00:00
/// Delete the unnecessary from `columns` list. Create `unknown_required_columns`. Form `columns_added_by_join`.
collectUsedColumns();
2017-04-02 17:37:49 +00:00
/// external_tables, subqueries_for_sets for global subqueries.
/// Replaces global subqueries with the generated names of temporary tables that will be sent to remote servers.
initGlobalSubqueriesAndExternalTables();
/// has_aggregation, aggregation_keys, aggregate_descriptions, aggregated_columns.
2017-04-02 17:37:49 +00:00
/// This analysis should be performed after processing global subqueries, because otherwise,
/// if the aggregate function contains a global subquery, then `analyzeAggregation` method will save
/// in `aggregate_descriptions` the information about the parameters of this aggregate function, among which
/// global subquery. Then, when you call `initGlobalSubqueriesAndExternalTables` method, this
/// the global subquery will be replaced with a temporary table, resulting in aggregate_descriptions
/// will contain out-of-date information, which will lead to an error when the query is executed.
analyzeAggregation();
}
void ExpressionAnalyzer::translateQualifiedNames()
{
String database_name;
String table_name;
String alias;
if (!select_query || !select_query->tables || select_query->tables->children.empty())
return;
ASTTablesInSelectQueryElement & element = static_cast<ASTTablesInSelectQueryElement &>(*select_query->tables->children[0]);
if (!element.table_expression) /// This is ARRAY JOIN without a table at the left side.
return;
ASTTableExpression & table_expression = static_cast<ASTTableExpression &>(*element.table_expression);
if (table_expression.database_and_table_name)
{
const ASTIdentifier & identifier = static_cast<const ASTIdentifier &>(*table_expression.database_and_table_name);
alias = identifier.tryGetAlias();
if (table_expression.database_and_table_name->children.empty())
{
database_name = context.getCurrentDatabase();
table_name = identifier.name;
}
else
{
if (table_expression.database_and_table_name->children.size() != 2)
throw Exception("Logical error: number of components in table expression not equal to two", ErrorCodes::LOGICAL_ERROR);
database_name = static_cast<const ASTIdentifier &>(*identifier.children[0]).name;
table_name = static_cast<const ASTIdentifier &>(*identifier.children[1]).name;
}
}
else if (table_expression.table_function)
{
alias = table_expression.table_function->tryGetAlias();
}
else if (table_expression.subquery)
{
alias = table_expression.subquery->tryGetAlias();
}
else
throw Exception("Logical error: no known elements in ASTTableExpression", ErrorCodes::LOGICAL_ERROR);
translateQualifiedNamesImpl(ast, database_name, table_name, alias);
}
void ExpressionAnalyzer::translateQualifiedNamesImpl(ASTPtr & ast, const String & database_name, const String & table_name, const String & alias)
{
if (ASTIdentifier * ident = typeid_cast<ASTIdentifier *>(ast.get()))
{
if (ident->kind == ASTIdentifier::Column)
{
/// It is compound identifier
if (!ast->children.empty())
{
size_t num_components = ast->children.size();
size_t num_qualifiers_to_strip = 0;
/// database.table.column
if (num_components >= 3
&& !database_name.empty()
&& static_cast<const ASTIdentifier &>(*ast->children[0]).name == database_name
&& static_cast<const ASTIdentifier &>(*ast->children[1]).name == table_name)
{
num_qualifiers_to_strip = 2;
}
/// table.column or alias.column. If num_components > 2, it is like table.nested.column.
if (num_components >= 2
&& ((!table_name.empty() && static_cast<const ASTIdentifier &>(*ast->children[0]).name == table_name)
|| (!alias.empty() && static_cast<const ASTIdentifier &>(*ast->children[0]).name == alias)))
{
num_qualifiers_to_strip = 1;
}
if (num_qualifiers_to_strip)
{
/// plain column
if (num_components - num_qualifiers_to_strip == 1)
{
String node_alias = ast->tryGetAlias();
ast = ast->children.back();
if (!node_alias.empty())
ast->setAlias(node_alias);
}
else
/// nested column
{
ident->children.erase(ident->children.begin(), ident->children.begin() + num_qualifiers_to_strip);
String new_name;
for (const auto & child : ident->children)
{
if (!new_name.empty())
new_name += '.';
new_name += static_cast<const ASTIdentifier &>(*child.get()).name;
}
ident->name = new_name;
}
}
}
}
}
2017-06-19 03:18:30 +00:00
else if (typeid_cast<ASTQualifiedAsterisk *>(ast.get()))
{
if (ast->children.size() != 1)
throw Exception("Logical error: qualified asterisk must have exactly one child", ErrorCodes::LOGICAL_ERROR);
ASTIdentifier * ident = typeid_cast<ASTIdentifier *>(ast->children[0].get());
if (!ident)
throw Exception("Logical error: qualified asterisk must have identifier as its child", ErrorCodes::LOGICAL_ERROR);
size_t num_components = ident->children.size();
if (num_components > 2)
throw Exception("Qualified asterisk cannot have more than two qualifiers", ErrorCodes::UNKNOWN_ELEMENT_IN_AST);
/// database.table.*, table.* or alias.*
if ( (num_components == 2
&& !database_name.empty()
&& static_cast<const ASTIdentifier &>(*ident->children[0]).name == database_name
&& static_cast<const ASTIdentifier &>(*ident->children[1]).name == table_name)
|| (num_components == 0
&& ((!table_name.empty() && ident->name == table_name)
|| (!alias.empty() && ident->name == alias))))
{
/// Replace to plain asterisk.
ast = std::make_shared<ASTAsterisk>(ast->range);
}
}
else
{
for (auto & child : ast->children)
{
/// Do not go to FROM, JOIN, UNION.
if (!typeid_cast<const ASTTableExpression *>(child.get())
&& child.get() != select_query->next_union_all.get())
{
translateQualifiedNamesImpl(child, database_name, table_name, alias);
}
}
}
}
void ExpressionAnalyzer::optimizeIfWithConstantCondition()
{
optimizeIfWithConstantConditionImpl(ast, aliases);
}
bool ExpressionAnalyzer::tryExtractConstValueFromCondition(const ASTPtr & condition, bool & value) const
{
/// numeric constant in condition
if (const ASTLiteral * literal = typeid_cast<ASTLiteral *>(condition.get()))
{
if (literal->value.getType() == Field::Types::Int64 ||
literal->value.getType() == Field::Types::UInt64)
{
value = literal->value.get<Int64>();
return true;
}
}
/// cast of numeric constant in condition to UInt8
if (const ASTFunction * function = typeid_cast<ASTFunction * >(condition.get()))
{
if (function->name == "CAST")
{
if (ASTExpressionList * expr_list = typeid_cast<ASTExpressionList *>(function->arguments.get()))
{
const ASTPtr & type_ast = expr_list->children.at(1);
if (const ASTLiteral * type_literal = typeid_cast<ASTLiteral *>(type_ast.get()))
{
if (type_literal->value.getType() == Field::Types::String &&
type_literal->value.get<std::string>() == "UInt8")
return tryExtractConstValueFromCondition(expr_list->children.at(0), value);
}
}
}
}
return false;
}
void ExpressionAnalyzer::optimizeIfWithConstantConditionImpl(ASTPtr & current_ast, ExpressionAnalyzer::Aliases & aliases) const
{
if (!current_ast)
return;
for (ASTPtr & child : current_ast->children)
{
ASTFunction * function_node = typeid_cast<ASTFunction *>(child.get());
if (!function_node || function_node->name != "if")
{
optimizeIfWithConstantConditionImpl(child, aliases);
continue;
}
optimizeIfWithConstantConditionImpl(function_node->arguments, aliases);
ASTExpressionList * args = typeid_cast<ASTExpressionList *>(function_node->arguments.get());
ASTPtr condition_expr = args->children.at(0);
ASTPtr then_expr = args->children.at(1);
ASTPtr else_expr = args->children.at(2);
bool condition;
if (tryExtractConstValueFromCondition(condition_expr, condition))
{
ASTPtr replace_ast = condition ? then_expr : else_expr;
ASTPtr child_copy = child;
String replace_alias = replace_ast->tryGetAlias();
String if_alias = child->tryGetAlias();
if (replace_alias.empty())
{
replace_ast->setAlias(if_alias);
child = replace_ast;
}
else
{
/// Only copy of one node is required here.
/// But IAST has only method for deep copy of subtree.
/// This can be a reason of performance degradation in case of deep queries.
ASTPtr replace_ast_deep_copy = replace_ast->clone();
replace_ast_deep_copy->setAlias(if_alias);
child = replace_ast_deep_copy;
}
if (!if_alias.empty())
{
auto alias_it = aliases.find(if_alias);
if (alias_it != aliases.end() && alias_it->second.get() == child_copy.get())
alias_it->second = child;
}
}
}
}
void ExpressionAnalyzer::analyzeAggregation()
{
2017-04-02 17:37:49 +00:00
/** Find aggregation keys (aggregation_keys), information about aggregate functions (aggregate_descriptions),
* as well as a set of columns obtained after the aggregation, if any,
* or after all the actions that are usually performed before aggregation (aggregated_columns).
*
2017-04-02 17:37:49 +00:00
* Everything below (compiling temporary ExpressionActions) - only for the purpose of query analysis (type output).
*/
if (select_query && (select_query->group_expression_list || select_query->having_expression))
has_aggregation = true;
ExpressionActionsPtr temp_actions = std::make_shared<ExpressionActions>(columns, settings);
if (select_query && select_query->array_join_expression_list())
{
getRootActions(select_query->array_join_expression_list(), true, false, temp_actions);
addMultipleArrayJoinAction(temp_actions);
}
if (select_query)
{
const ASTTablesInSelectQueryElement * join = select_query->join();
if (join)
{
if (static_cast<const ASTTableJoin &>(*join->table_join).using_expression_list)
getRootActions(static_cast<const ASTTableJoin &>(*join->table_join).using_expression_list, true, false, temp_actions);
addJoinAction(temp_actions, true);
}
}
getAggregates(ast, temp_actions);
if (has_aggregation)
{
assertSelect();
/// Find out aggregation keys.
if (select_query->group_expression_list)
{
NameSet unique_keys;
ASTs & group_asts = select_query->group_expression_list->children;
for (ssize_t i = 0; i < ssize_t(group_asts.size()); ++i)
{
ssize_t size = group_asts.size();
getRootActions(group_asts[i], true, false, temp_actions);
const auto & column_name = group_asts[i]->getColumnName();
const auto & block = temp_actions->getSampleBlock();
if (!block.has(column_name))
throw Exception("Unknown identifier (in GROUP BY): " + column_name, ErrorCodes::UNKNOWN_IDENTIFIER);
const auto & col = block.getByName(column_name);
/// Constant expressions have non-null column pointer at this stage.
if (const auto is_constexpr = col.column)
{
/// But don't remove last key column if no aggregate functions, otherwise aggregation will not work.
if (!aggregate_descriptions.empty() || size > 1)
{
if (i + 1 < static_cast<ssize_t>(size))
group_asts[i] = std::move(group_asts.back());
group_asts.pop_back();
--i;
continue;
}
}
NameAndTypePair key{column_name, col.type};
/// Aggregation keys are uniqued.
if (!unique_keys.count(key.name))
{
unique_keys.insert(key.name);
aggregation_keys.push_back(key);
/// Key is no longer needed, therefore we can save a little by moving it.
aggregated_columns.push_back(std::move(key));
}
}
if (group_asts.empty())
{
select_query->group_expression_list = nullptr;
has_aggregation = select_query->having_expression || aggregate_descriptions.size();
}
}
for (size_t i = 0; i < aggregate_descriptions.size(); ++i)
{
AggregateDescription & desc = aggregate_descriptions[i];
aggregated_columns.emplace_back(desc.column_name, desc.function->getReturnType());
}
}
else
{
aggregated_columns = temp_actions->getSampleBlock().getNamesAndTypesList();
}
}
void ExpressionAnalyzer::initGlobalSubqueriesAndExternalTables()
{
2017-04-02 17:37:49 +00:00
/// Adds existing external tables (not subqueries) to the external_tables dictionary.
findExternalTables(ast);
2017-04-02 17:37:49 +00:00
/// Converts GLOBAL subqueries to external tables; Puts them into the external_tables dictionary: name -> StoragePtr.
initGlobalSubqueries(ast);
}
void ExpressionAnalyzer::initGlobalSubqueries(ASTPtr & ast)
{
2017-04-02 17:37:49 +00:00
/// Recursive calls. We do not go into subqueries.
for (auto & child : ast->children)
if (!typeid_cast<ASTSelectQuery *>(child.get()))
initGlobalSubqueries(child);
2017-04-02 17:37:49 +00:00
/// Bottom-up actions.
if (ASTFunction * node = typeid_cast<ASTFunction *>(ast.get()))
{
2017-04-02 17:37:49 +00:00
/// For GLOBAL IN.
if (do_global && (node->name == "globalIn" || node->name == "globalNotIn"))
addExternalStorage(node->arguments->children.at(1));
}
else if (ASTTablesInSelectQueryElement * node = typeid_cast<ASTTablesInSelectQueryElement *>(ast.get()))
{
2017-04-02 17:37:49 +00:00
/// For GLOBAL JOIN.
if (do_global && node->table_join
&& static_cast<const ASTTableJoin &>(*node->table_join).locality == ASTTableJoin::Locality::Global)
addExternalStorage(node->table_expression);
}
}
void ExpressionAnalyzer::findExternalTables(ASTPtr & ast)
{
2017-04-02 17:37:49 +00:00
/// Traverse from the bottom. Intentionally go into subqueries.
for (auto & child : ast->children)
findExternalTables(child);
2017-04-02 17:37:49 +00:00
/// If table type identifier
StoragePtr external_storage;
if (ASTIdentifier * node = typeid_cast<ASTIdentifier *>(ast.get()))
if (node->kind == ASTIdentifier::Table)
if ((external_storage = context.tryGetExternalTable(node->name)))
external_tables[node->name] = external_storage;
}
static std::pair<String, String> getDatabaseAndTableNameFromIdentifier(const ASTIdentifier & identifier)
{
std::pair<String, String> res;
res.second = identifier.name;
if (!identifier.children.empty())
{
if (identifier.children.size() != 2)
throw Exception("Qualified table name could have only two components", ErrorCodes::LOGICAL_ERROR);
res.first = typeid_cast<const ASTIdentifier &>(*identifier.children[0]).name;
res.second = typeid_cast<const ASTIdentifier &>(*identifier.children[1]).name;
}
return res;
}
static std::shared_ptr<InterpreterSelectQuery> interpretSubquery(
const ASTPtr & subquery_or_table_name, const Context & context, size_t subquery_depth, const Names & required_columns)
{
/// Subquery or table name. The name of the table is similar to the subquery `SELECT * FROM t`.
const ASTSubquery * subquery = typeid_cast<const ASTSubquery *>(subquery_or_table_name.get());
const ASTIdentifier * table = typeid_cast<const ASTIdentifier *>(subquery_or_table_name.get());
if (!subquery && !table)
throw Exception("IN/JOIN supports only SELECT subqueries.", ErrorCodes::BAD_ARGUMENTS);
/** The subquery in the IN / JOIN section does not have any restrictions on the maximum size of the result.
* Because the result of this query is not the result of the entire query.
* Constraints work instead
* max_rows_in_set, max_bytes_in_set, set_overflow_mode,
* max_rows_in_join, max_bytes_in_join, join_overflow_mode,
* which are checked separately (in the Set, Join objects).
*/
Context subquery_context = context;
Settings subquery_settings = context.getSettings();
subquery_settings.limits.max_result_rows = 0;
subquery_settings.limits.max_result_bytes = 0;
/// The calculation of `extremes` does not make sense and is not necessary (if you do it, then the `extremes` of the subquery can be taken instead of the whole query).
subquery_settings.extremes = 0;
subquery_context.setSettings(subquery_settings);
ASTPtr query;
if (table)
{
/// create ASTSelectQuery for "SELECT * FROM table" as if written by hand
const auto select_query = std::make_shared<ASTSelectQuery>();
query = select_query;
const auto select_expression_list = std::make_shared<ASTExpressionList>();
select_query->select_expression_list = select_expression_list;
select_query->children.emplace_back(select_query->select_expression_list);
/// get columns list for target table
auto database_table = getDatabaseAndTableNameFromIdentifier(*table);
const auto & storage = context.getTable(database_table.first, database_table.second);
const auto & columns = storage->getColumnsListNonMaterialized();
select_expression_list->children.reserve(columns.size());
/// manually substitute column names in place of asterisk
for (const auto & column : columns)
select_expression_list->children.emplace_back(std::make_shared<ASTIdentifier>(
StringRange{}, column.name));
select_query->replaceDatabaseAndTable(database_table.first, database_table.second);
}
else
{
query = subquery->children.at(0);
/** Columns with the same name can be specified in a subquery. For example, SELECT x, x FROM t
* This is bad, because the result of such a query can not be saved to the table, because the table can not have the same name columns.
* Saving to the table is required for GLOBAL subqueries.
*
* To avoid this situation, we will rename the same columns.
*/
std::set<std::string> all_column_names;
std::set<std::string> assigned_column_names;
if (ASTSelectQuery * select = typeid_cast<ASTSelectQuery *>(query.get()))
{
for (auto & expr : select->select_expression_list->children)
all_column_names.insert(expr->getAliasOrColumnName());
for (auto & expr : select->select_expression_list->children)
{
auto name = expr->getAliasOrColumnName();
if (!assigned_column_names.insert(name).second)
{
size_t i = 1;
while (all_column_names.end() != all_column_names.find(name + "_" + toString(i)))
++i;
name = name + "_" + toString(i);
expr = expr->clone(); /// Cancels fuse of the same expressions in the tree.
expr->setAlias(name);
all_column_names.insert(name);
assigned_column_names.insert(name);
}
}
}
}
if (required_columns.empty())
return std::make_shared<InterpreterSelectQuery>(
query, subquery_context, QueryProcessingStage::Complete, subquery_depth + 1);
else
return std::make_shared<InterpreterSelectQuery>(
query, subquery_context, required_columns, QueryProcessingStage::Complete, subquery_depth + 1);
}
void ExpressionAnalyzer::addExternalStorage(ASTPtr & subquery_or_table_name_or_table_expression)
{
2017-04-02 17:37:49 +00:00
/// With nondistributed queries, creating temporary tables does not make sense.
if (!(storage && storage->isRemote()))
return;
ASTPtr subquery;
ASTPtr table_name;
ASTPtr subquery_or_table_name;
if (typeid_cast<const ASTIdentifier *>(subquery_or_table_name_or_table_expression.get()))
{
table_name = subquery_or_table_name_or_table_expression;
subquery_or_table_name = table_name;
}
else if (auto ast_table_expr = typeid_cast<const ASTTableExpression *>(subquery_or_table_name_or_table_expression.get()))
{
if (ast_table_expr->database_and_table_name)
{
table_name = ast_table_expr->database_and_table_name;
subquery_or_table_name = table_name;
}
else if (ast_table_expr->subquery)
{
subquery = ast_table_expr->subquery;
subquery_or_table_name = subquery;
}
}
else if (typeid_cast<const ASTSubquery *>(subquery_or_table_name_or_table_expression.get()))
{
subquery = subquery_or_table_name_or_table_expression;
subquery_or_table_name = subquery;
}
if (!subquery_or_table_name)
throw Exception("Logical error: unknown AST element passed to ExpressionAnalyzer::addExternalStorage method", ErrorCodes::LOGICAL_ERROR);
if (table_name)
{
2017-04-02 17:37:49 +00:00
/// If this is already an external table, you do not need to add anything. Just remember its presence.
if (external_tables.end() != external_tables.find(static_cast<const ASTIdentifier &>(*table_name).name))
return;
}
2017-04-02 17:37:49 +00:00
/// Generate the name for the external table.
String external_table_name = "_data" + toString(external_table_id);
while (external_tables.count(external_table_name))
{
++external_table_id;
external_table_name = "_data" + toString(external_table_id);
}
auto interpreter = interpretSubquery(subquery_or_table_name, context, subquery_depth, {});
Block sample = interpreter->getSampleBlock();
NamesAndTypesList columns = sample.getNamesAndTypesList();
StoragePtr external_storage = StorageMemory::create(external_table_name, columns, NamesAndTypesList{}, NamesAndTypesList{}, ColumnDefaults{});
external_storage->startup();
2017-04-02 17:37:49 +00:00
/** There are two ways to perform distributed GLOBAL subqueries.
*
2017-04-02 17:37:49 +00:00
* "push" method:
* Subquery data is sent to all remote servers, where they are then used.
* For this method, the data is sent in the form of "external tables" and will be available on each remote server by the name of the type _data1.
* Replace in the query a subquery for this name.
*
2017-04-02 17:37:49 +00:00
* "pull" method:
* Remote servers download the subquery data from the request initiating server.
* For this method, replace the subquery with another subquery of the form (SELECT * FROM remote ('host: port', _query_QUERY_ID, _data1))
* This subquery, in fact, says - "you need to download data from there."
*
2017-04-02 17:37:49 +00:00
* The "pull" method takes precedence, because in it a remote server can decide that it does not need data and does not download it in such cases.
*/
if (settings.global_subqueries_method == GlobalSubqueriesMethod::PUSH)
{
2017-04-02 17:37:49 +00:00
/** We replace the subquery with the name of the temporary table.
* It is in this form, the request will go to the remote server.
* This temporary table will go to the remote server, and on its side,
* instead of doing a subquery, you just need to read it.
*/
auto database_and_table_name = std::make_shared<ASTIdentifier>(StringRange(), external_table_name, ASTIdentifier::Table);
if (auto ast_table_expr = typeid_cast<ASTTableExpression *>(subquery_or_table_name_or_table_expression.get()))
{
ast_table_expr->subquery.reset();
ast_table_expr->database_and_table_name = database_and_table_name;
ast_table_expr->children.clear();
ast_table_expr->children.emplace_back(database_and_table_name);
}
else
subquery_or_table_name_or_table_expression = database_and_table_name;
}
else if (settings.global_subqueries_method == GlobalSubqueriesMethod::PULL)
{
throw Exception("Support for 'pull' method of execution of global subqueries is disabled.", ErrorCodes::SUPPORT_IS_DISABLED);
/// TODO
/* String host_port = getFQDNOrHostName() + ":" + toString(context.getTCPPort());
String database = "_query_" + context.getCurrentQueryId();
auto subquery = std::make_shared<ASTSubquery>();
subquery_or_table_name = subquery;
auto select = std::make_shared<ASTSelectQuery>();
subquery->children.push_back(select);
auto exp_list = std::make_shared<ASTExpressionList>();
select->select_expression_list = exp_list;
select->children.push_back(select->select_expression_list);
Names column_names = external_storage->getColumnNamesList();
for (const auto & name : column_names)
exp_list->children.push_back(std::make_shared<ASTIdentifier>(StringRange(), name));
auto table_func = std::make_shared<ASTFunction>();
select->table = table_func;
select->children.push_back(select->table);
table_func->name = "remote";
auto args = std::make_shared<ASTExpressionList>();
table_func->arguments = args;
table_func->children.push_back(table_func->arguments);
auto address_lit = std::make_shared<ASTLiteral>(StringRange(), host_port);
args->children.push_back(address_lit);
auto database_lit = std::make_shared<ASTLiteral>(StringRange(), database);
args->children.push_back(database_lit);
auto table_lit = std::make_shared<ASTLiteral>(StringRange(), external_table_name);
args->children.push_back(table_lit);*/
}
else
throw Exception("Unknown global subqueries execution method", ErrorCodes::UNKNOWN_GLOBAL_SUBQUERIES_METHOD);
external_tables[external_table_name] = external_storage;
subqueries_for_sets[external_table_name].source = interpreter->execute().in;
subqueries_for_sets[external_table_name].source_sample = interpreter->getSampleBlock();
subqueries_for_sets[external_table_name].table = external_storage;
2017-04-02 17:37:49 +00:00
/** NOTE If it was written IN tmp_table - the existing temporary (but not external) table,
* then a new temporary table will be created (for example, _data1),
* and the data will then be copied to it.
* Maybe this can be avoided.
*/
}
NamesAndTypesList::iterator ExpressionAnalyzer::findColumn(const String & name, NamesAndTypesList & cols)
{
return std::find_if(cols.begin(), cols.end(),
[&](const NamesAndTypesList::value_type & val) { return val.name == name; });
}
2017-04-02 17:37:49 +00:00
/// ignore_levels - aliases in how many upper levels of the subtree should be ignored.
/// For example, with ignore_levels=1 ast can not be put in the dictionary, but its children can.
void ExpressionAnalyzer::addASTAliases(ASTPtr & ast, int ignore_levels)
{
2017-04-02 17:37:49 +00:00
/// Bottom-up traversal. We do not go into subqueries.
for (auto & child : ast->children)
{
int new_ignore_levels = std::max(0, ignore_levels - 1);
2017-04-02 17:37:49 +00:00
/// The top-level aliases in the ARRAY JOIN section have a special meaning, we will not add them
/// (skip the expression list itself and its children).
if (typeid_cast<ASTArrayJoin *>(ast.get()))
new_ignore_levels = 3;
/// Don't descent into UNION ALL, table functions and subqueries.
if (!typeid_cast<ASTTableExpression *>(child.get())
&& !typeid_cast<ASTSelectQuery *>(child.get()))
addASTAliases(child, new_ignore_levels);
}
if (ignore_levels > 0)
return;
String alias = ast->tryGetAlias();
if (!alias.empty())
{
if (aliases.count(alias) && ast->getTreeHash() != aliases[alias]->getTreeHash())
throw Exception("Different expressions with the same alias " + alias, ErrorCodes::MULTIPLE_EXPRESSIONS_FOR_ALIAS);
aliases[alias] = ast;
}
2017-07-26 01:21:19 +00:00
else if (typeid_cast<ASTSubquery *>(ast.get()))
{
/// Set unique aliases for all subqueries. This is needed, because content of subqueries could change after recursive analysis,
/// and auto-generated column names could become incorrect.
size_t subquery_index = 1;
while (true)
{
alias = "_subquery" + toString(subquery_index);
if (!aliases.count("_subquery" + toString(subquery_index)))
break;
++subquery_index;
}
ast->setAlias(alias);
aliases[alias] = ast;
}
}
StoragePtr ExpressionAnalyzer::getTable()
{
if (const ASTSelectQuery * select = typeid_cast<const ASTSelectQuery *>(ast.get()))
{
auto select_database = select->database();
auto select_table = select->table();
if (select_table
&& !typeid_cast<const ASTSelectQuery *>(select_table.get())
&& !typeid_cast<const ASTFunction *>(select_table.get()))
{
String database = select_database
? typeid_cast<const ASTIdentifier &>(*select_database).name
: "";
const String & table = typeid_cast<const ASTIdentifier &>(*select_table).name;
return context.tryGetTable(database, table);
}
}
return StoragePtr();
}
void ExpressionAnalyzer::normalizeTree()
{
SetOfASTs tmp_set;
MapOfASTs tmp_map;
normalizeTreeImpl(ast, tmp_map, tmp_set, "", 0);
}
2017-04-02 17:37:49 +00:00
/// finished_asts - already processed vertices (and by what they replaced)
/// current_asts - vertices in the current call stack of this method
/// current_alias - the alias referencing to the ancestor of ast (the deepest ancestor with aliases)
2015-05-12 20:09:18 +00:00
void ExpressionAnalyzer::normalizeTreeImpl(
ASTPtr & ast, MapOfASTs & finished_asts, SetOfASTs & current_asts, std::string current_alias, size_t level)
{
if (level > settings.limits.max_ast_depth)
throw Exception("Normalized AST is too deep. Maximum: " + settings.limits.max_ast_depth.toString(), ErrorCodes::TOO_DEEP_AST);
if (finished_asts.count(ast))
{
ast = finished_asts[ast];
return;
}
ASTPtr initial_ast = ast;
current_asts.insert(initial_ast.get());
String my_alias = ast->tryGetAlias();
if (!my_alias.empty())
current_alias = my_alias;
2017-04-02 17:37:49 +00:00
/// rewrite rules that act when you go from top to bottom.
bool replaced = false;
ASTIdentifier * identifier_node = nullptr;
ASTFunction * func_node = nullptr;
if ((func_node = typeid_cast<ASTFunction *>(ast.get())))
{
2017-04-02 17:37:49 +00:00
/** Is there a column in the table whose name fully matches the function entry?
* For example, in the table there is a column "domain(URL)", and we requested domain(URL).
*/
String function_string = func_node->getColumnName();
auto it = findColumn(function_string);
if (columns.end() != it)
{
ast = std::make_shared<ASTIdentifier>(func_node->range, function_string);
current_asts.insert(ast.get());
replaced = true;
}
2017-04-02 17:37:49 +00:00
/// `IN t` can be specified, where t is a table, which is equivalent to `IN (SELECT * FROM t)`.
if (functionIsInOrGlobalInOperator(func_node->name))
if (ASTIdentifier * right = typeid_cast<ASTIdentifier *>(func_node->arguments->children.at(1).get()))
right->kind = ASTIdentifier::Table;
/// Special cases for count function.
String func_name_lowercase = Poco::toLower(func_node->name);
if (startsWith(func_name_lowercase, "count"))
{
/// Select implementation of countDistinct based on settings.
/// Important that it is done as query rewrite. It means rewritten query
/// will be sent to remote servers during distributed query execution,
/// and on all remote servers, function implementation will be same.
if (endsWith(func_node->name, "Distinct") && func_name_lowercase == "countdistinct")
func_node->name = settings.count_distinct_implementation;
/// As special case, treat count(*) as count(), not as count(list of all columns).
if (func_name_lowercase == "count" && func_node->arguments->children.size() == 1
&& typeid_cast<const ASTAsterisk *>(func_node->arguments->children[0].get()))
{
func_node->arguments->children.clear();
}
}
}
else if ((identifier_node = typeid_cast<ASTIdentifier *>(ast.get())))
{
if (identifier_node->kind == ASTIdentifier::Column)
{
2017-04-02 17:37:49 +00:00
/// If it is an alias, but not a parent alias (for constructs like "SELECT column + 1 AS column").
auto it_alias = aliases.find(identifier_node->name);
if (it_alias != aliases.end() && current_alias != identifier_node->name)
{
2017-04-02 17:37:49 +00:00
/// Let's replace it with the corresponding tree node.
if (current_asts.count(it_alias->second.get()))
throw Exception("Cyclic aliases", ErrorCodes::CYCLIC_ALIASES);
if (!my_alias.empty() && my_alias != it_alias->second->getAliasOrColumnName())
{
/// Avoid infinite recursion here
auto replace_to_identifier = typeid_cast<ASTIdentifier *>(it_alias->second.get());
bool is_cycle = replace_to_identifier &&
replace_to_identifier->kind == ASTIdentifier::Column &&
replace_to_identifier->name == identifier_node->name;
if (!is_cycle)
{
/// In a construct like "a AS b", where a is an alias, you must set alias b to the result of substituting alias a.
ast = it_alias->second->clone();
ast->setAlias(my_alias);
replaced = true;
}
}
else
{
ast = it_alias->second;
replaced = true;
}
}
}
}
else if (ASTExpressionList * node = typeid_cast<ASTExpressionList *>(ast.get()))
{
2017-04-02 17:37:49 +00:00
/// Replace * with a list of columns.
ASTs & asts = node->children;
for (int i = static_cast<int>(asts.size()) - 1; i >= 0; --i)
{
if (ASTAsterisk * asterisk = typeid_cast<ASTAsterisk *>(asts[i].get()))
{
ASTs all_columns;
for (const auto & column_name_type : columns)
all_columns.emplace_back(std::make_shared<ASTIdentifier>(asterisk->range, column_name_type.name));
asts.erase(asts.begin() + i);
asts.insert(asts.begin() + i, all_columns.begin(), all_columns.end());
}
}
}
else if (ASTTablesInSelectQueryElement * node = typeid_cast<ASTTablesInSelectQueryElement *>(ast.get()))
{
if (node->table_expression)
{
auto & database_and_table_name = static_cast<ASTTableExpression &>(*node->table_expression).database_and_table_name;
if (database_and_table_name)
{
if (ASTIdentifier * right = typeid_cast<ASTIdentifier *>(database_and_table_name.get()))
{
right->kind = ASTIdentifier::Table;
}
}
}
}
2017-04-02 17:37:49 +00:00
/// If we replace the root of the subtree, we will be called again for the new root, in case the alias is replaced by an alias.
if (replaced)
{
normalizeTreeImpl(ast, finished_asts, current_asts, current_alias, level + 1);
current_asts.erase(initial_ast.get());
current_asts.erase(ast.get());
finished_asts[initial_ast] = ast;
return;
}
/// Recurring calls. Don't go into subqueries. Don't go into components of compound identifiers.
2017-04-02 17:37:49 +00:00
/// We also do not go to the left argument of lambda expressions, so as not to replace the formal parameters
/// on aliases in expressions of the form 123 AS x, arrayMap(x -> 1, [2]).
if (func_node && func_node->name == "lambda")
{
2017-04-02 17:37:49 +00:00
/// We skip the first argument. We also assume that the lambda function can not have parameters.
for (size_t i = 1, size = func_node->arguments->children.size(); i < size; ++i)
{
auto & child = func_node->arguments->children[i];
if (typeid_cast<const ASTSelectQuery *>(child.get())
|| typeid_cast<const ASTTableExpression *>(child.get()))
continue;
normalizeTreeImpl(child, finished_asts, current_asts, current_alias, level + 1);
}
}
else if (identifier_node)
{
}
else
{
for (auto & child : ast->children)
{
if (typeid_cast<const ASTSelectQuery *>(child.get())
|| typeid_cast<const ASTTableExpression *>(child.get()))
continue;
normalizeTreeImpl(child, finished_asts, current_asts, current_alias, level + 1);
}
}
2017-04-02 17:37:49 +00:00
/// If the WHERE clause or HAVING consists of a single alias, the reference must be replaced not only in children, but also in where_expression and having_expression.
if (ASTSelectQuery * select = typeid_cast<ASTSelectQuery *>(ast.get()))
{
if (select->prewhere_expression)
normalizeTreeImpl(select->prewhere_expression, finished_asts, current_asts, current_alias, level + 1);
if (select->where_expression)
normalizeTreeImpl(select->where_expression, finished_asts, current_asts, current_alias, level + 1);
if (select->having_expression)
normalizeTreeImpl(select->having_expression, finished_asts, current_asts, current_alias, level + 1);
}
2017-04-02 17:37:49 +00:00
/// Actions to be performed from the bottom up.
if (ASTFunction * node = typeid_cast<ASTFunction *>(ast.get()))
{
if (node->kind == ASTFunction::TABLE_FUNCTION)
{
}
else if (node->name == "lambda")
{
node->kind = ASTFunction::LAMBDA_EXPRESSION;
}
else if (AggregateFunctionFactory::instance().isAggregateFunctionName(node->name))
{
node->kind = ASTFunction::AGGREGATE_FUNCTION;
}
else if (node->name == "arrayJoin")
{
node->kind = ASTFunction::ARRAY_JOIN;
}
else
{
node->kind = ASTFunction::FUNCTION;
}
if (node->parameters && node->kind != ASTFunction::AGGREGATE_FUNCTION)
throw Exception("The only parametric functions (functions with two separate parenthesis pairs) are aggregate functions"
", and '" + node->name + "' is not an aggregate function.", ErrorCodes::FUNCTION_CANNOT_HAVE_PARAMETERS);
}
current_asts.erase(initial_ast.get());
current_asts.erase(ast.get());
finished_asts[initial_ast] = ast;
}
void ExpressionAnalyzer::addAliasColumns()
{
if (!select_query)
return;
if (!storage)
return;
columns.insert(std::end(columns), std::begin(storage->alias_columns), std::end(storage->alias_columns));
}
void ExpressionAnalyzer::executeScalarSubqueries()
{
if (!select_query)
executeScalarSubqueriesImpl(ast);
else
{
for (auto & child : ast->children)
{
2017-04-02 17:37:49 +00:00
/// Do not go to FROM, JOIN, UNION.
if (!typeid_cast<const ASTTableExpression *>(child.get())
&& child.get() != select_query->next_union_all.get())
{
executeScalarSubqueriesImpl(child);
}
}
}
}
static ASTPtr addTypeConversion(std::unique_ptr<ASTLiteral> && ast, const String & type_name)
{
auto func = std::make_shared<ASTFunction>(ast->range);
ASTPtr res = func;
func->alias = ast->alias;
func->prefer_alias_to_column_name = ast->prefer_alias_to_column_name;
ast->alias.clear();
func->kind = ASTFunction::FUNCTION;
func->name = "CAST";
auto exp_list = std::make_shared<ASTExpressionList>(ast->range);
func->arguments = exp_list;
func->children.push_back(func->arguments);
exp_list->children.emplace_back(ast.release());
exp_list->children.emplace_back(std::make_shared<ASTLiteral>(StringRange(), type_name));
return res;
}
void ExpressionAnalyzer::executeScalarSubqueriesImpl(ASTPtr & ast)
{
2017-04-02 17:37:49 +00:00
/** Replace subqueries that return exactly one row
* ("scalar" subqueries) to the corresponding constants.
*
2017-04-02 17:37:49 +00:00
* If the subquery returns more than one column, it is replaced by a tuple of constants.
*
2017-04-02 17:37:49 +00:00
* Features
*
2017-04-02 17:37:49 +00:00
* A replacement occurs during query analysis, and not during the main runtime.
* This means that the progress indicator will not work during the execution of these requests,
* and also such queries can not be aborted.
*
2017-04-02 17:37:49 +00:00
* But the query result can be used for the index in the table.
*
2017-04-02 17:37:49 +00:00
* Scalar subqueries are executed on the request-initializer server.
* The request is sent to remote servers with already substituted constants.
*/
if (ASTSubquery * subquery = typeid_cast<ASTSubquery *>(ast.get()))
{
Context subquery_context = context;
Settings subquery_settings = context.getSettings();
subquery_settings.limits.max_result_rows = 1;
subquery_settings.extremes = 0;
subquery_context.setSettings(subquery_settings);
ASTPtr query = subquery->children.at(0);
BlockIO res = InterpreterSelectQuery(query, subquery_context, QueryProcessingStage::Complete, subquery_depth + 1).execute();
Block block;
try
{
block = res.in->read();
if (!block)
{
/// Interpret subquery with empty result as Null literal
auto ast_new = std::make_unique<ASTLiteral>(ast->range, Null());
ast_new->setAlias(ast->tryGetAlias());
ast = std::move(ast_new);
return;
}
if (block.rows() != 1 || res.in->read())
throw Exception("Scalar subquery returned more than one row", ErrorCodes::INCORRECT_RESULT_OF_SCALAR_SUBQUERY);
}
catch (const Exception & e)
{
if (e.code() == ErrorCodes::TOO_MUCH_ROWS)
throw Exception("Scalar subquery returned more than one row", ErrorCodes::INCORRECT_RESULT_OF_SCALAR_SUBQUERY);
else
throw;
}
size_t columns = block.columns();
if (columns == 1)
{
auto lit = std::make_unique<ASTLiteral>(ast->range, (*block.safeGetByPosition(0).column)[0]);
lit->alias = subquery->alias;
lit->prefer_alias_to_column_name = subquery->prefer_alias_to_column_name;
ast = addTypeConversion(std::move(lit), block.safeGetByPosition(0).type->getName());
}
else
{
auto tuple = std::make_shared<ASTFunction>(ast->range);
tuple->alias = subquery->alias;
ast = tuple;
tuple->kind = ASTFunction::FUNCTION;
tuple->name = "tuple";
auto exp_list = std::make_shared<ASTExpressionList>(ast->range);
tuple->arguments = exp_list;
tuple->children.push_back(tuple->arguments);
exp_list->children.resize(columns);
for (size_t i = 0; i < columns; ++i)
{
exp_list->children[i] = addTypeConversion(
std::make_unique<ASTLiteral>(ast->range, (*block.safeGetByPosition(i).column)[0]),
block.safeGetByPosition(i).type->getName());
}
}
}
else
{
/** Don't descend into subqueries in FROM section.
*/
if (!typeid_cast<ASTTableExpression *>(ast.get()))
{
/** Don't descend into subqueries in arguments of IN operator.
* But if an argument is not subquery, than deeper may be scalar subqueries and we need to descend in them.
*/
ASTFunction * func = typeid_cast<ASTFunction *>(ast.get());
if (func && func->kind == ASTFunction::FUNCTION
&& functionIsInOrGlobalInOperator(func->name))
{
for (auto & child : ast->children)
{
if (child != func->arguments)
executeScalarSubqueriesImpl(child);
else
for (size_t i = 0, size = func->arguments->children.size(); i < size; ++i)
if (i != 1 || !typeid_cast<ASTSubquery *>(func->arguments->children[i].get()))
executeScalarSubqueriesImpl(func->arguments->children[i]);
}
}
else
for (auto & child : ast->children)
executeScalarSubqueriesImpl(child);
}
}
}
void ExpressionAnalyzer::optimizeGroupBy()
{
if (!(select_query && select_query->group_expression_list))
return;
2018-01-10 00:04:08 +00:00
const auto is_literal = [] (const ASTPtr & ast)
{
return typeid_cast<const ASTLiteral *>(ast.get());
};
auto & group_exprs = select_query->group_expression_list->children;
/// removes expression at index idx by making it last one and calling .pop_back()
const auto remove_expr_at_index = [&group_exprs] (const size_t idx)
{
if (idx < group_exprs.size() - 1)
std::swap(group_exprs[idx], group_exprs.back());
group_exprs.pop_back();
};
/// iterate over each GROUP BY expression, eliminate injective function calls and literals
for (size_t i = 0; i < group_exprs.size();)
{
if (const auto function = typeid_cast<ASTFunction *>(group_exprs[i].get()))
{
/// assert function is injective
if (possibly_injective_function_names.count(function->name))
{
/// do not handle semantic errors here
if (function->arguments->children.size() < 2)
{
++i;
continue;
}
const auto & dict_name = typeid_cast<const ASTLiteral &>(*function->arguments->children[0])
.value.safeGet<String>();
const auto & dict_ptr = context.getExternalDictionaries().getDictionary(dict_name);
const auto & attr_name = typeid_cast<const ASTLiteral &>(*function->arguments->children[1])
.value.safeGet<String>();
if (!dict_ptr->isInjective(attr_name))
{
++i;
continue;
}
}
else if (!injective_function_names.count(function->name))
{
++i;
continue;
}
/// copy shared pointer to args in order to ensure lifetime
auto args_ast = function->arguments;
/** remove function call and take a step back to ensure
* next iteration does not skip not yet processed data
*/
remove_expr_at_index(i);
/// copy non-literal arguments
std::remove_copy_if(
std::begin(args_ast->children), std::end(args_ast->children),
std::back_inserter(group_exprs), is_literal
);
}
else if (is_literal(group_exprs[i]))
{
remove_expr_at_index(i);
}
else
{
/// if neither a function nor literal - advance to next expression
++i;
}
}
if (group_exprs.empty())
{
2017-04-02 17:37:49 +00:00
/** You can not completely remove GROUP BY. Because if there were no aggregate functions, then it turns out that there will be no aggregation.
* Instead, leave `GROUP BY const`.
* Next, see deleting the constants in the analyzeAggregation method.
*/
2017-04-02 17:37:49 +00:00
/// You must insert a constant that is not the name of the column in the table. Such a case is rare, but it happens.
UInt64 unused_column = 0;
String unused_column_name = toString(unused_column);
while (columns.end() != std::find_if(columns.begin(), columns.end(),
[&unused_column_name](const NameAndTypePair & name_type) { return name_type.name == unused_column_name; }))
{
++unused_column;
unused_column_name = toString(unused_column);
}
select_query->group_expression_list = std::make_shared<ASTExpressionList>();
select_query->group_expression_list->children.emplace_back(std::make_shared<ASTLiteral>(StringRange(), UInt64(unused_column)));
}
}
void ExpressionAnalyzer::optimizeOrderBy()
{
if (!(select_query && select_query->order_expression_list))
return;
2017-04-02 17:37:49 +00:00
/// Make unique sorting conditions.
using NameAndLocale = std::pair<String, String>;
std::set<NameAndLocale> elems_set;
ASTs & elems = select_query->order_expression_list->children;
ASTs unique_elems;
unique_elems.reserve(elems.size());
for (const auto & elem : elems)
{
String name = elem->children.front()->getColumnName();
const ASTOrderByElement & order_by_elem = typeid_cast<const ASTOrderByElement &>(*elem);
if (elems_set.emplace(name, order_by_elem.collation ? order_by_elem.collation->getColumnName() : "").second)
unique_elems.emplace_back(elem);
}
if (unique_elems.size() < elems.size())
elems = unique_elems;
}
void ExpressionAnalyzer::optimizeLimitBy()
{
if (!(select_query && select_query->limit_by_expression_list))
return;
std::set<String> elems_set;
ASTs & elems = select_query->limit_by_expression_list->children;
ASTs unique_elems;
unique_elems.reserve(elems.size());
for (const auto & elem : elems)
{
if (elems_set.emplace(elem->getColumnName()).second)
unique_elems.emplace_back(elem);
}
if (unique_elems.size() < elems.size())
elems = unique_elems;
}
2014-04-10 08:57:01 +00:00
void ExpressionAnalyzer::makeSetsForIndex()
{
if (storage && ast && storage->supportsIndexForIn())
makeSetsForIndexImpl(ast, storage->getSampleBlock());
}
void ExpressionAnalyzer::tryMakeSetFromSubquery(const ASTPtr & subquery_or_table_name)
{
BlockIO res = interpretSubquery(subquery_or_table_name, context, subquery_depth + 1, {})->execute();
SetPtr set = std::make_shared<Set>(settings.limits);
while (Block block = res.in->read())
{
/// If the limits have been exceeded, give up and let the default subquery processing actions take place.
if (!set->insertFromBlock(block, true))
return;
}
set->makeOrderedSet();
prepared_sets[subquery_or_table_name.get()] = std::move(set);
}
void ExpressionAnalyzer::makeSetsForIndexImpl(const ASTPtr & node, const Block & sample_block)
{
for (auto & child : node->children)
makeSetsForIndexImpl(child, sample_block);
const ASTFunction * func = typeid_cast<const ASTFunction *>(node.get());
if (func && func->kind == ASTFunction::FUNCTION && functionIsInOperator(func->name))
{
const IAST & args = *func->arguments;
const ASTPtr & arg = args.children.at(1);
if (!prepared_sets.count(arg.get())) /// Not already prepared.
{
if (typeid_cast<ASTSubquery *>(arg.get()) || typeid_cast<ASTIdentifier *>(arg.get()))
{
if (settings.try_primary_key_for_in_with_subqueries && storage->mayBenefitFromIndexForIn(args.children.at(0)))
tryMakeSetFromSubquery(arg);
}
else
{
try
{
makeExplicitSet(func, sample_block, true);
}
catch (const Exception & e)
{
/// in `sample_block` there are no columns that add `getActions`
if (e.code() != ErrorCodes::NOT_FOUND_COLUMN_IN_BLOCK)
throw;
}
}
}
}
}
void ExpressionAnalyzer::makeSet(const ASTFunction * node, const Block & sample_block)
{
2017-04-02 17:37:49 +00:00
/** You need to convert the right argument to a set.
* This can be a table name, a value, a value enumeration, or a subquery.
* The enumeration of values is parsed as a function `tuple`.
*/
const IAST & args = *node->arguments;
const ASTPtr & arg = args.children.at(1);
2017-04-02 17:37:49 +00:00
/// Already converted.
if (prepared_sets.count(arg.get()))
return;
2017-04-02 17:37:49 +00:00
/// If the subquery or table name for SELECT.
const ASTIdentifier * identifier = typeid_cast<const ASTIdentifier *>(arg.get());
if (typeid_cast<const ASTSubquery *>(arg.get()) || identifier)
{
2017-04-02 17:37:49 +00:00
/// We get the stream of blocks for the subquery. Create Set and put it in place of the subquery.
String set_id = arg->getColumnName();
/// A special case is if the name of the table is specified on the right side of the IN statement,
/// and the table has the type Set (a previously prepared set).
if (identifier)
{
auto database_table = getDatabaseAndTableNameFromIdentifier(*identifier);
StoragePtr table = context.tryGetTable(database_table.first, database_table.second);
if (table)
{
2017-11-04 16:46:14 +00:00
StorageSet * storage_set = dynamic_cast<StorageSet *>(table.get());
if (storage_set)
{
prepared_sets[arg.get()] = storage_set->getSet();
return;
}
}
}
SubqueryForSet & subquery_for_set = subqueries_for_sets[set_id];
2017-04-02 17:37:49 +00:00
/// If you already created a Set with the same subquery / table.
if (subquery_for_set.set)
{
prepared_sets[arg.get()] = subquery_for_set.set;
return;
}
SetPtr set = std::make_shared<Set>(settings.limits);
2017-04-02 17:37:49 +00:00
/** The following happens for GLOBAL INs:
* - in the addExternalStorage function, the IN (SELECT ...) subquery is replaced with IN _data1,
* in the subquery_for_set object, this subquery is set as source and the temporary table _data1 as the table.
* - this function shows the expression IN_data1.
*/
if (!subquery_for_set.source)
{
auto interpreter = interpretSubquery(arg, context, subquery_depth, {});
subquery_for_set.source = std::make_shared<LazyBlockInputStream>(
[interpreter]() mutable { return interpreter->execute().in; });
subquery_for_set.source_sample = interpreter->getSampleBlock();
2017-04-02 17:37:49 +00:00
/** Why is LazyBlockInputStream used?
*
2018-01-10 00:04:08 +00:00
* The fact is that when processing a query of the form
* SELECT ... FROM remote_test WHERE column GLOBAL IN (subquery),
2017-04-02 17:37:49 +00:00
* if the distributed remote_test table contains localhost as one of the servers,
2018-01-10 00:04:08 +00:00
* the query will be interpreted locally again (and not sent over TCP, as in the case of a remote server).
*
2017-04-02 17:37:49 +00:00
* The query execution pipeline will be:
* CreatingSets
2017-04-02 17:37:49 +00:00
* subquery execution, filling the temporary table with _data1 (1)
* CreatingSets
2017-04-02 17:37:49 +00:00
* reading from the table _data1, creating the set (2)
* read from the table subordinate to remote_test.
*
2018-01-10 00:04:08 +00:00
* (The second part of the pipeline under CreateSets is a reinterpretation of the query inside StorageDistributed,
2017-04-02 17:37:49 +00:00
* the query differs in that the database name and tables are replaced with subordinates, and the subquery is replaced with _data1.)
*
2017-04-02 17:37:49 +00:00
* But when creating the pipeline, when creating the source (2), it will be found that the _data1 table is empty
* (because the query has not started yet), and empty source will be returned as the source.
* And then, when the query is executed, an empty set will be created in step (2).
*
2017-04-02 17:37:49 +00:00
* Therefore, we make the initialization of step (2) lazy
* - so that it does not occur until step (1) is completed, on which the table will be populated.
*
2017-04-02 17:37:49 +00:00
* Note: this solution is not very good, you need to think better.
*/
}
subquery_for_set.set = set;
prepared_sets[arg.get()] = set;
}
else
{
2017-04-02 17:37:49 +00:00
/// An explicit enumeration of values in parentheses.
makeExplicitSet(node, sample_block, false);
}
}
2017-04-02 17:37:49 +00:00
/// The case of an explicit enumeration of values.
void ExpressionAnalyzer::makeExplicitSet(const ASTFunction * node, const Block & sample_block, bool create_ordered_set)
{
const IAST & args = *node->arguments;
if (args.children.size() != 2)
throw Exception("Wrong number of arguments passed to function in", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
const ASTPtr & arg = args.children.at(1);
DataTypes set_element_types;
const ASTPtr & left_arg = args.children.at(0);
const ASTFunction * left_arg_tuple = typeid_cast<const ASTFunction *>(left_arg.get());
/** NOTE If tuple in left hand side specified non-explicitly
* Example: identity((a, b)) IN ((1, 2), (3, 4))
* instead of (a, b)) IN ((1, 2), (3, 4))
* then set creation doesn't work correctly.
*/
if (left_arg_tuple && left_arg_tuple->name == "tuple")
{
for (const auto & arg : left_arg_tuple->arguments->children)
{
const auto & data_type = sample_block.getByName(arg->getColumnName()).type;
/// NOTE prevent crash in query: SELECT (1, [1]) in (1, 1)
if (const auto array = typeid_cast<const DataTypeArray * >(data_type.get()))
throw Exception("Incorrect element of tuple: " + array->getName(), ErrorCodes::INCORRECT_ELEMENT_OF_SET);
set_element_types.push_back(data_type);
}
}
else
{
DataTypePtr left_type = sample_block.getByName(left_arg->getColumnName()).type;
if (const DataTypeArray * array_type = typeid_cast<const DataTypeArray *>(left_type.get()))
set_element_types.push_back(array_type->getNestedType());
else
set_element_types.push_back(left_type);
}
2017-04-02 17:37:49 +00:00
/// The case `x in (1, 2)` distinguishes from the case `x in 1` (also `x in (1)`).
bool single_value = false;
ASTPtr elements_ast = arg;
if (ASTFunction * set_func = typeid_cast<ASTFunction *>(arg.get()))
{
if (set_func->name == "tuple")
{
if (set_func->arguments->children.empty())
{
2017-04-02 17:37:49 +00:00
/// Empty set.
elements_ast = set_func->arguments;
}
else
{
2017-04-02 17:37:49 +00:00
/// Distinguish the case `(x, y) in ((1, 2), (3, 4))` from the case `(x, y) in (1, 2)`.
ASTFunction * any_element = typeid_cast<ASTFunction *>(set_func->arguments->children.at(0).get());
if (set_element_types.size() >= 2 && (!any_element || any_element->name != "tuple"))
single_value = true;
else
elements_ast = set_func->arguments;
}
}
else
{
if (set_element_types.size() >= 2)
throw Exception("Incorrect type of 2nd argument for function " + node->name
+ ". Must be subquery or set of " + toString(set_element_types.size()) + "-element tuples.",
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
single_value = true;
}
}
else if (typeid_cast<ASTLiteral *>(arg.get()))
{
single_value = true;
}
else
{
throw Exception("Incorrect type of 2nd argument for function " + node->name + ". Must be subquery or set of values.",
ErrorCodes::ILLEGAL_TYPE_OF_ARGUMENT);
}
if (single_value)
{
ASTPtr exp_list = std::make_shared<ASTExpressionList>();
exp_list->children.push_back(elements_ast);
elements_ast = exp_list;
}
SetPtr set = std::make_shared<Set>(settings.limits);
set->createFromAST(set_element_types, elements_ast, context, create_ordered_set);
prepared_sets[arg.get()] = std::move(set);
}
static String getUniqueName(const Block & block, const String & prefix)
{
int i = 1;
while (block.has(prefix + toString(i)))
++i;
return prefix + toString(i);
}
2017-04-02 17:37:49 +00:00
/** For getActionsImpl.
* A stack of ExpressionActions corresponding to nested lambda expressions.
* The new action should be added to the highest possible level.
* For example, in the expression "select arrayMap(x -> x + column1 * column2, array1)"
* calculation of the product must be done outside the lambda expression (it does not depend on x), and the calculation of the sum is inside (depends on x).
2014-06-12 19:53:36 +00:00
*/
struct ExpressionAnalyzer::ScopeStack
{
struct Level
{
ExpressionActionsPtr actions;
NameSet new_columns;
};
using Levels = std::vector<Level>;
Levels stack;
Settings settings;
ScopeStack(const ExpressionActionsPtr & actions, const Settings & settings_)
: settings(settings_)
{
stack.emplace_back();
stack.back().actions = actions;
const Block & sample_block = actions->getSampleBlock();
for (size_t i = 0, size = sample_block.columns(); i < size; ++i)
stack.back().new_columns.insert(sample_block.getByPosition(i).name);
}
void pushLevel(const NamesAndTypesList & input_columns)
{
stack.emplace_back();
Level & prev = stack[stack.size() - 2];
ColumnsWithTypeAndName all_columns;
NameSet new_names;
for (NamesAndTypesList::const_iterator it = input_columns.begin(); it != input_columns.end(); ++it)
{
all_columns.emplace_back(nullptr, it->type, it->name);
new_names.insert(it->name);
stack.back().new_columns.insert(it->name);
}
const Block & prev_sample_block = prev.actions->getSampleBlock();
for (size_t i = 0, size = prev_sample_block.columns(); i < size; ++i)
{
const ColumnWithTypeAndName & col = prev_sample_block.getByPosition(i);
if (!new_names.count(col.name))
all_columns.push_back(col);
}
stack.back().actions = std::make_shared<ExpressionActions>(all_columns, settings);
}
size_t getColumnLevel(const std::string & name)
{
for (int i = static_cast<int>(stack.size()) - 1; i >= 0; --i)
if (stack[i].new_columns.count(name))
return i;
throw Exception("Unknown identifier: " + name, ErrorCodes::UNKNOWN_IDENTIFIER);
}
void addAction(const ExpressionAction & action, const Names & additional_required_columns = Names())
{
size_t level = 0;
for (size_t i = 0; i < additional_required_columns.size(); ++i)
level = std::max(level, getColumnLevel(additional_required_columns[i]));
Names required = action.getNeededColumns();
for (size_t i = 0; i < required.size(); ++i)
level = std::max(level, getColumnLevel(required[i]));
Names added;
stack[level].actions->add(action, added);
stack[level].new_columns.insert(added.begin(), added.end());
for (size_t i = 0; i < added.size(); ++i)
{
const ColumnWithTypeAndName & col = stack[level].actions->getSampleBlock().getByName(added[i]);
for (size_t j = level + 1; j < stack.size(); ++j)
stack[j].actions->addInput(col);
}
}
ExpressionActionsPtr popLevel()
{
ExpressionActionsPtr res = stack.back().actions;
stack.pop_back();
return res;
}
const Block & getSampleBlock() const
{
return stack.back().actions->getSampleBlock();
}
2014-06-12 19:53:36 +00:00
};
void ExpressionAnalyzer::getRootActions(const ASTPtr & ast, bool no_subqueries, bool only_consts, ExpressionActionsPtr & actions)
{
ScopeStack scopes(actions, settings);
getActionsImpl(ast, no_subqueries, only_consts, scopes);
actions = scopes.popLevel();
}
void ExpressionAnalyzer::getArrayJoinedColumns()
{
if (select_query && select_query->array_join_expression_list())
{
ASTs & array_join_asts = select_query->array_join_expression_list()->children;
for (const auto & ast : array_join_asts)
{
const String nested_table_name = ast->getColumnName();
const String nested_table_alias = ast->getAliasOrColumnName();
if (nested_table_alias == nested_table_name && !typeid_cast<const ASTIdentifier *>(ast.get()))
throw Exception("No alias for non-trivial value in ARRAY JOIN: " + nested_table_name, ErrorCodes::ALIAS_REQUIRED);
if (array_join_alias_to_name.count(nested_table_alias) || aliases.count(nested_table_alias))
throw Exception("Duplicate alias in ARRAY JOIN: " + nested_table_alias, ErrorCodes::MULTIPLE_EXPRESSIONS_FOR_ALIAS);
array_join_alias_to_name[nested_table_alias] = nested_table_name;
array_join_name_to_alias[nested_table_name] = nested_table_alias;
}
getArrayJoinedColumnsImpl(ast);
2017-04-02 17:37:49 +00:00
/// If the result of ARRAY JOIN is not used, it is necessary to ARRAY-JOIN any column,
/// to get the correct number of rows.
if (array_join_result_to_source.empty())
{
ASTPtr expr = select_query->array_join_expression_list()->children.at(0);
String source_name = expr->getColumnName();
String result_name = expr->getAliasOrColumnName();
2017-04-02 17:37:49 +00:00
/// This is an array.
if (!typeid_cast<ASTIdentifier *>(expr.get()) || findColumn(source_name, columns) != columns.end())
{
array_join_result_to_source[result_name] = source_name;
}
2017-04-02 17:37:49 +00:00
else /// This is a nested table.
{
bool found = false;
for (const auto & column_name_type : columns)
{
auto splitted = Nested::splitName(column_name_type.name);
if (splitted.first == source_name && !splitted.second.empty())
{
array_join_result_to_source[Nested::concatenateName(result_name, splitted.second)] = column_name_type.name;
found = true;
break;
}
}
if (!found)
throw Exception("No columns in nested table " + source_name, ErrorCodes::EMPTY_NESTED_TABLE);
}
}
}
}
2017-04-02 17:37:49 +00:00
/// Fills the array_join_result_to_source: on which columns-arrays to replicate, and how to call them after that.
void ExpressionAnalyzer::getArrayJoinedColumnsImpl(const ASTPtr & ast)
{
if (typeid_cast<ASTTablesInSelectQuery *>(ast.get()))
return;
if (ASTIdentifier * node = typeid_cast<ASTIdentifier *>(ast.get()))
{
if (node->kind == ASTIdentifier::Column)
{
auto splitted = Nested::splitName(node->name); /// ParsedParams, Key1
if (array_join_alias_to_name.count(node->name))
{
2017-04-02 17:37:49 +00:00
/// ARRAY JOIN was written with an array column. Example: SELECT K1 FROM ... ARRAY JOIN ParsedParams.Key1 AS K1
array_join_result_to_source[node->name] = array_join_alias_to_name[node->name]; /// K1 -> ParsedParams.Key1
}
else if (array_join_alias_to_name.count(splitted.first) && !splitted.second.empty())
{
2017-04-02 17:37:49 +00:00
/// ARRAY JOIN was written with a nested table. Example: SELECT PP.KEY1 FROM ... ARRAY JOIN ParsedParams AS PP
array_join_result_to_source[node->name] /// PP.Key1 -> ParsedParams.Key1
= Nested::concatenateName(array_join_alias_to_name[splitted.first], splitted.second);
}
else if (array_join_name_to_alias.count(node->name))
{
/** Example: SELECT ParsedParams.Key1 FROM ... ARRAY JOIN ParsedParams.Key1 AS PP.Key1.
2017-04-02 17:37:49 +00:00
* That is, the query uses the original array, replicated by itself.
*/
array_join_result_to_source[ /// PP.Key1 -> ParsedParams.Key1
array_join_name_to_alias[node->name]] = node->name;
}
else if (array_join_name_to_alias.count(splitted.first) && !splitted.second.empty())
{
/** Example: SELECT ParsedParams.Key1 FROM ... ARRAY JOIN ParsedParams AS PP.
*/
array_join_result_to_source[ /// PP.Key1 -> ParsedParams.Key1
Nested::concatenateName(array_join_name_to_alias[splitted.first], splitted.second)] = node->name;
}
}
}
else
{
for (auto & child : ast->children)
if (!typeid_cast<const ASTSubquery *>(child.get())
&& !typeid_cast<const ASTSelectQuery *>(child.get()))
getArrayJoinedColumnsImpl(child);
}
}
void ExpressionAnalyzer::getActionsImpl(const ASTPtr & ast, bool no_subqueries, bool only_consts, ScopeStack & actions_stack)
{
2017-04-02 17:37:49 +00:00
/// If the result of the calculation already exists in the block.
if ((typeid_cast<ASTFunction *>(ast.get()) || typeid_cast<ASTLiteral *>(ast.get()))
&& actions_stack.getSampleBlock().has(ast->getColumnName()))
return;
if (ASTIdentifier * node = typeid_cast<ASTIdentifier *>(ast.get()))
{
std::string name = node->getColumnName();
if (!only_consts && !actions_stack.getSampleBlock().has(name))
{
2017-04-02 17:37:49 +00:00
/// The requested column is not in the block.
/// If such a column exists in the table, then the user probably forgot to surround it with an aggregate function or add it to GROUP BY.
bool found = false;
for (const auto & column_name_type : columns)
if (column_name_type.name == name)
found = true;
if (found)
throw Exception("Column " + name + " is not under aggregate function and not in GROUP BY.",
ErrorCodes::NOT_AN_AGGREGATE);
}
}
else if (ASTFunction * node = typeid_cast<ASTFunction *>(ast.get()))
{
if (node->kind == ASTFunction::LAMBDA_EXPRESSION)
throw Exception("Unexpected lambda expression", ErrorCodes::UNEXPECTED_EXPRESSION);
2017-04-02 17:37:49 +00:00
/// Function arrayJoin.
if (node->kind == ASTFunction::ARRAY_JOIN)
{
if (node->arguments->children.size() != 1)
throw Exception("arrayJoin requires exactly 1 argument", ErrorCodes::TYPE_MISMATCH);
ASTPtr arg = node->arguments->children.at(0);
getActionsImpl(arg, no_subqueries, only_consts, actions_stack);
if (!only_consts)
{
String result_name = node->getColumnName();
actions_stack.addAction(ExpressionAction::copyColumn(arg->getColumnName(), result_name));
NameSet joined_columns;
joined_columns.insert(result_name);
actions_stack.addAction(ExpressionAction::arrayJoin(joined_columns, false, context));
}
return;
}
if (node->kind == ASTFunction::FUNCTION)
{
if (functionIsInOrGlobalInOperator(node->name))
{
if (!no_subqueries)
{
2017-04-02 17:37:49 +00:00
/// Let's find the type of the first argument (then getActionsImpl will be called again and will not affect anything).
getActionsImpl(node->arguments->children.at(0), no_subqueries, only_consts, actions_stack);
2017-04-02 17:37:49 +00:00
/// Transform tuple or subquery into a set.
makeSet(node, actions_stack.getSampleBlock());
}
else
{
if (!only_consts)
{
2017-04-02 17:37:49 +00:00
/// We are in the part of the tree that we are not going to compute. You just need to define types.
/// Do not subquery and create sets. We insert an arbitrary column of the correct type.
ColumnWithTypeAndName fake_column;
fake_column.name = node->getColumnName();
fake_column.type = std::make_shared<DataTypeUInt8>();
actions_stack.addAction(ExpressionAction::addColumn(fake_column));
getActionsImpl(node->arguments->children.at(0), no_subqueries, only_consts, actions_stack);
}
return;
}
}
2017-04-02 17:37:49 +00:00
/// A special function `indexHint`. Everything that is inside it is not calculated
/// (and is used only for index analysis, see PKCondition).
if (node->name == "indexHint")
{
actions_stack.addAction(ExpressionAction::addColumn(ColumnWithTypeAndName(
ColumnConst::create(ColumnUInt8::create(1, 1), 1), std::make_shared<DataTypeUInt8>(), node->getColumnName())));
return;
}
const FunctionPtr & function = FunctionFactory::instance().get(node->name, context);
Names argument_names;
DataTypes argument_types;
bool arguments_present = true;
2017-04-02 17:37:49 +00:00
/// If the function has an argument-lambda expression, you need to determine its type before the recursive call.
bool has_lambda_arguments = false;
for (auto & child : node->arguments->children)
{
ASTFunction * lambda = typeid_cast<ASTFunction *>(child.get());
if (lambda && lambda->name == "lambda")
{
2017-04-02 17:37:49 +00:00
/// If the argument is a lambda expression, just remember its approximate type.
if (lambda->arguments->children.size() != 2)
throw Exception("lambda requires two arguments", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
ASTFunction * lambda_args_tuple = typeid_cast<ASTFunction *>(lambda->arguments->children.at(0).get());
if (!lambda_args_tuple || lambda_args_tuple->name != "tuple")
throw Exception("First argument of lambda must be a tuple", ErrorCodes::TYPE_MISMATCH);
has_lambda_arguments = true;
argument_types.emplace_back(std::make_shared<DataTypeExpression>(DataTypes(lambda_args_tuple->arguments->children.size())));
2017-04-02 17:37:49 +00:00
/// Select the name in the next cycle.
argument_names.emplace_back();
}
else if (prepared_sets.count(child.get()))
{
ColumnWithTypeAndName column;
column.type = std::make_shared<DataTypeSet>();
const SetPtr & set = prepared_sets[child.get()];
/// If the argument is a set given by an enumeration of values (so, the set was already built), give it a unique name,
2017-04-02 17:37:49 +00:00
/// so that sets with the same record do not fuse together (they can have different types).
if (!set->empty())
column.name = getUniqueName(actions_stack.getSampleBlock(), "__set");
else
column.name = child->getColumnName();
if (!actions_stack.getSampleBlock().has(column.name))
{
column.column = ColumnSet::create(1, set);
actions_stack.addAction(ExpressionAction::addColumn(column));
}
argument_types.push_back(column.type);
argument_names.push_back(column.name);
}
else
{
2017-04-02 17:37:49 +00:00
/// If the argument is not a lambda expression, call it recursively and find out its type.
getActionsImpl(child, no_subqueries, only_consts, actions_stack);
std::string name = child->getColumnName();
if (actions_stack.getSampleBlock().has(name))
{
argument_types.push_back(actions_stack.getSampleBlock().getByName(name).type);
argument_names.push_back(name);
}
else
{
if (only_consts)
{
arguments_present = false;
}
else
{
throw Exception("Unknown identifier: " + name, ErrorCodes::UNKNOWN_IDENTIFIER);
}
}
}
}
if (only_consts && !arguments_present)
return;
Names additional_requirements;
if (has_lambda_arguments && !only_consts)
{
function->getLambdaArgumentTypes(argument_types);
2017-04-02 17:37:49 +00:00
/// Call recursively for lambda expressions.
for (size_t i = 0; i < node->arguments->children.size(); ++i)
{
ASTPtr child = node->arguments->children[i];
ASTFunction * lambda = typeid_cast<ASTFunction *>(child.get());
if (lambda && lambda->name == "lambda")
{
const DataTypeExpression * lambda_type = typeid_cast<const DataTypeExpression *>(argument_types[i].get());
ASTFunction * lambda_args_tuple = typeid_cast<ASTFunction *>(lambda->arguments->children.at(0).get());
ASTs lambda_arg_asts = lambda_args_tuple->arguments->children;
NamesAndTypesList lambda_arguments;
for (size_t j = 0; j < lambda_arg_asts.size(); ++j)
{
ASTIdentifier * identifier = typeid_cast<ASTIdentifier *>(lambda_arg_asts[j].get());
if (!identifier)
throw Exception("lambda argument declarations must be identifiers", ErrorCodes::TYPE_MISMATCH);
String arg_name = identifier->name;
lambda_arguments.emplace_back(arg_name, lambda_type->getArgumentTypes()[j]);
}
actions_stack.pushLevel(lambda_arguments);
getActionsImpl(lambda->arguments->children.at(1), no_subqueries, only_consts, actions_stack);
ExpressionActionsPtr lambda_actions = actions_stack.popLevel();
String result_name = lambda->arguments->children.at(1)->getColumnName();
lambda_actions->finalize(Names(1, result_name));
DataTypePtr result_type = lambda_actions->getSampleBlock().getByName(result_name).type;
argument_types[i] = std::make_shared<DataTypeExpression>(lambda_type->getArgumentTypes(), result_type);
Names captured = lambda_actions->getRequiredColumns();
for (size_t j = 0; j < captured.size(); ++j)
if (findColumn(captured[j], lambda_arguments) == lambda_arguments.end())
additional_requirements.push_back(captured[j]);
2017-04-02 17:37:49 +00:00
/// We can not name `getColumnName()`,
/// because it does not uniquely define the expression (the types of arguments can be different).
argument_names[i] = getUniqueName(actions_stack.getSampleBlock(), "__lambda");
ColumnWithTypeAndName lambda_column;
lambda_column.column = ColumnExpression::create(1, lambda_actions, lambda_arguments, result_type, result_name);
lambda_column.type = argument_types[i];
lambda_column.name = argument_names[i];
actions_stack.addAction(ExpressionAction::addColumn(lambda_column));
}
}
}
if (only_consts)
{
for (size_t i = 0; i < argument_names.size(); ++i)
{
if (!actions_stack.getSampleBlock().has(argument_names[i]))
{
arguments_present = false;
break;
}
}
}
if (arguments_present)
actions_stack.addAction(ExpressionAction::applyFunction(function, argument_names, node->getColumnName()),
additional_requirements);
}
}
else if (ASTLiteral * node = typeid_cast<ASTLiteral *>(ast.get()))
{
DataTypePtr type = applyVisitor(FieldToDataType(), node->value);
ColumnWithTypeAndName column;
2017-12-10 22:44:04 +00:00
column.column = type->createColumnConst(1, node->value);
column.type = type;
column.name = node->getColumnName();
actions_stack.addAction(ExpressionAction::addColumn(column));
}
else
{
for (auto & child : ast->children)
getActionsImpl(child, no_subqueries, only_consts, actions_stack);
}
}
2016-03-05 02:30:20 +00:00
void ExpressionAnalyzer::getAggregates(const ASTPtr & ast, ExpressionActionsPtr & actions)
{
2017-04-02 17:37:49 +00:00
/// There can not be aggregate functions inside the WHERE and PREWHERE.
if (select_query && (ast.get() == select_query->where_expression.get() || ast.get() == select_query->prewhere_expression.get()))
{
assertNoAggregates(ast, "in WHERE or PREWHERE");
return;
}
2017-04-02 17:37:49 +00:00
/// If we are not analyzing a SELECT query, but a separate expression, then there can not be aggregate functions in it.
if (!select_query)
{
assertNoAggregates(ast, "in wrong place");
return;
}
const ASTFunction * node = typeid_cast<const ASTFunction *>(ast.get());
if (node && node->kind == ASTFunction::AGGREGATE_FUNCTION)
{
has_aggregation = true;
AggregateDescription aggregate;
aggregate.column_name = node->getColumnName();
2017-04-02 17:37:49 +00:00
/// Make unique aggregate functions.
for (size_t i = 0; i < aggregate_descriptions.size(); ++i)
if (aggregate_descriptions[i].column_name == aggregate.column_name)
return;
const ASTs & arguments = node->arguments->children;
aggregate.argument_names.resize(arguments.size());
DataTypes types(arguments.size());
for (size_t i = 0; i < arguments.size(); ++i)
{
2017-04-02 17:37:49 +00:00
/// There can not be other aggregate functions within the aggregate functions.
assertNoAggregates(arguments[i], "inside another aggregate function");
getRootActions(arguments[i], true, false, actions);
const std::string & name = arguments[i]->getColumnName();
types[i] = actions->getSampleBlock().getByName(name).type;
aggregate.argument_names[i] = name;
}
aggregate.parameters = (node->parameters) ? getAggregateFunctionParametersArray(node->parameters) : Array();
aggregate.function = AggregateFunctionFactory::instance().get(node->name, types, aggregate.parameters);
aggregate_descriptions.push_back(aggregate);
}
else
{
for (const auto & child : ast->children)
if (!typeid_cast<const ASTSubquery *>(child.get())
&& !typeid_cast<const ASTSelectQuery *>(child.get()))
getAggregates(child, actions);
}
}
2016-03-05 02:30:20 +00:00
void ExpressionAnalyzer::assertNoAggregates(const ASTPtr & ast, const char * description)
{
const ASTFunction * node = typeid_cast<const ASTFunction *>(ast.get());
2016-03-05 02:30:20 +00:00
if (node && node->kind == ASTFunction::AGGREGATE_FUNCTION)
throw Exception("Aggregate function " + node->getColumnName()
+ " is found " + String(description) + " in query", ErrorCodes::ILLEGAL_AGGREGATION);
2016-03-05 02:30:20 +00:00
for (const auto & child : ast->children)
if (!typeid_cast<const ASTSubquery *>(child.get())
&& !typeid_cast<const ASTSelectQuery *>(child.get()))
assertNoAggregates(child, description);
2016-03-05 02:30:20 +00:00
}
2015-04-18 22:30:43 +00:00
void ExpressionAnalyzer::assertSelect() const
{
if (!select_query)
throw Exception("Not a select query", ErrorCodes::LOGICAL_ERROR);
}
2013-06-14 16:38:54 +00:00
2015-04-18 22:30:43 +00:00
void ExpressionAnalyzer::assertAggregation() const
{
if (!has_aggregation)
throw Exception("No aggregation", ErrorCodes::LOGICAL_ERROR);
}
2013-06-14 16:38:54 +00:00
void ExpressionAnalyzer::initChain(ExpressionActionsChain & chain, const NamesAndTypesList & columns) const
{
if (chain.steps.empty())
{
chain.settings = settings;
chain.steps.emplace_back(std::make_shared<ExpressionActions>(columns, settings));
}
}
2016-07-23 02:25:09 +00:00
/// "Big" ARRAY JOIN.
2015-04-18 22:30:43 +00:00
void ExpressionAnalyzer::addMultipleArrayJoinAction(ExpressionActionsPtr & actions) const
{
NameSet result_columns;
for (const auto & result_source : array_join_result_to_source)
{
/// Assign new names to columns, if needed.
if (result_source.first != result_source.second)
actions->add(ExpressionAction::copyColumn(result_source.second, result_source.first));
2017-04-02 17:37:49 +00:00
/// Make ARRAY JOIN (replace arrays with their insides) for the columns in these new names.
result_columns.insert(result_source.first);
}
actions->add(ExpressionAction::arrayJoin(result_columns, select_query->array_join_is_left(), context));
}
bool ExpressionAnalyzer::appendArrayJoin(ExpressionActionsChain & chain, bool only_types)
{
assertSelect();
if (!select_query->array_join_expression_list())
return false;
initChain(chain, columns);
ExpressionActionsChain::Step & step = chain.steps.back();
getRootActions(select_query->array_join_expression_list(), only_types, false, step.actions);
addMultipleArrayJoinAction(step.actions);
return true;
}
2015-04-18 22:30:43 +00:00
void ExpressionAnalyzer::addJoinAction(ExpressionActionsPtr & actions, bool only_types) const
{
if (only_types)
actions->add(ExpressionAction::ordinaryJoin(nullptr, columns_added_by_join));
else
for (auto & subquery_for_set : subqueries_for_sets)
if (subquery_for_set.second.join)
actions->add(ExpressionAction::ordinaryJoin(subquery_for_set.second.join, columns_added_by_join));
}
bool ExpressionAnalyzer::appendJoin(ExpressionActionsChain & chain, bool only_types)
{
assertSelect();
if (!select_query->join())
return false;
initChain(chain, columns);
ExpressionActionsChain::Step & step = chain.steps.back();
const ASTTablesInSelectQueryElement & join_element = static_cast<const ASTTablesInSelectQueryElement &>(*select_query->join());
const ASTTableJoin & join_params = static_cast<const ASTTableJoin &>(*join_element.table_join);
const ASTTableExpression & table_to_join = static_cast<const ASTTableExpression &>(*join_element.table_expression);
if (join_params.using_expression_list)
getRootActions(join_params.using_expression_list, only_types, false, step.actions);
2017-04-02 17:37:49 +00:00
/// Two JOINs are not supported with the same subquery, but different USINGs.
String join_id = join_element.getTreeID();
SubqueryForSet & subquery_for_set = subqueries_for_sets[join_id];
2017-04-02 17:37:49 +00:00
/// Special case - if table name is specified on the right of JOIN, then the table has the type Join (the previously prepared mapping).
/// TODO This syntax does not support specifying a database name.
if (table_to_join.database_and_table_name)
{
auto database_table = getDatabaseAndTableNameFromIdentifier(static_cast<const ASTIdentifier &>(*table_to_join.database_and_table_name));
StoragePtr table = context.tryGetTable(database_table.first, database_table.second);
if (table)
{
2017-11-04 16:46:14 +00:00
StorageJoin * storage_join = dynamic_cast<StorageJoin *>(table.get());
if (storage_join)
{
storage_join->assertCompatible(join_params.kind, join_params.strictness);
2017-04-02 17:37:49 +00:00
/// TODO Check the set of keys.
JoinPtr & join = storage_join->getJoin();
subquery_for_set.join = join;
}
}
}
if (!subquery_for_set.join)
{
JoinPtr join = std::make_shared<Join>(
join_key_names_left, join_key_names_right,
settings.join_use_nulls, settings.limits,
join_params.kind, join_params.strictness);
Names required_joined_columns(join_key_names_right.begin(), join_key_names_right.end());
for (const auto & name_type : columns_added_by_join)
required_joined_columns.push_back(name_type.name);
2017-04-02 17:37:49 +00:00
/** For GLOBAL JOINs (in the case, for example, of the push method for executing GLOBAL subqueries), the following occurs
* - in the addExternalStorage function, the JOIN (SELECT ...) subquery is replaced with JOIN _data1,
* in the subquery_for_set object this subquery is exposed as source and the temporary table _data1 as the `table`.
* - this function shows the expression JOIN _data1.
*/
if (!subquery_for_set.source)
{
ASTPtr table;
if (table_to_join.database_and_table_name)
table = table_to_join.database_and_table_name;
else
table = table_to_join.subquery;
auto interpreter = interpretSubquery(table, context, subquery_depth, required_joined_columns);
subquery_for_set.source = std::make_shared<LazyBlockInputStream>([interpreter]() mutable { return interpreter->execute().in; });
subquery_for_set.source_sample = interpreter->getSampleBlock();
}
2017-04-02 17:37:49 +00:00
/// TODO You do not need to set this up when JOIN is only needed on remote servers.
subquery_for_set.join = join;
subquery_for_set.join->setSampleBlock(subquery_for_set.source_sample);
}
addJoinAction(step.actions, false);
return true;
}
bool ExpressionAnalyzer::appendWhere(ExpressionActionsChain & chain, bool only_types)
{
assertSelect();
if (!select_query->where_expression)
return false;
initChain(chain, columns);
ExpressionActionsChain::Step & step = chain.steps.back();
step.required_output.push_back(select_query->where_expression->getColumnName());
getRootActions(select_query->where_expression, only_types, false, step.actions);
return true;
}
bool ExpressionAnalyzer::appendGroupBy(ExpressionActionsChain & chain, bool only_types)
{
assertAggregation();
if (!select_query->group_expression_list)
return false;
initChain(chain, columns);
ExpressionActionsChain::Step & step = chain.steps.back();
ASTs asts = select_query->group_expression_list->children;
for (size_t i = 0; i < asts.size(); ++i)
{
step.required_output.push_back(asts[i]->getColumnName());
getRootActions(asts[i], only_types, false, step.actions);
}
return true;
}
void ExpressionAnalyzer::appendAggregateFunctionsArguments(ExpressionActionsChain & chain, bool only_types)
{
assertAggregation();
initChain(chain, columns);
ExpressionActionsChain::Step & step = chain.steps.back();
for (size_t i = 0; i < aggregate_descriptions.size(); ++i)
{
for (size_t j = 0; j < aggregate_descriptions[i].argument_names.size(); ++j)
{
step.required_output.push_back(aggregate_descriptions[i].argument_names[j]);
}
}
getActionsBeforeAggregation(select_query->select_expression_list, step.actions, only_types);
if (select_query->having_expression)
getActionsBeforeAggregation(select_query->having_expression, step.actions, only_types);
if (select_query->order_expression_list)
getActionsBeforeAggregation(select_query->order_expression_list, step.actions, only_types);
}
bool ExpressionAnalyzer::appendHaving(ExpressionActionsChain & chain, bool only_types)
{
assertAggregation();
if (!select_query->having_expression)
return false;
initChain(chain, aggregated_columns);
ExpressionActionsChain::Step & step = chain.steps.back();
step.required_output.push_back(select_query->having_expression->getColumnName());
getRootActions(select_query->having_expression, only_types, false, step.actions);
return true;
}
void ExpressionAnalyzer::appendSelect(ExpressionActionsChain & chain, bool only_types)
{
assertSelect();
initChain(chain, aggregated_columns);
ExpressionActionsChain::Step & step = chain.steps.back();
getRootActions(select_query->select_expression_list, only_types, false, step.actions);
ASTs asts = select_query->select_expression_list->children;
for (size_t i = 0; i < asts.size(); ++i)
{
step.required_output.push_back(asts[i]->getColumnName());
}
}
bool ExpressionAnalyzer::appendOrderBy(ExpressionActionsChain & chain, bool only_types)
{
assertSelect();
if (!select_query->order_expression_list)
return false;
initChain(chain, aggregated_columns);
ExpressionActionsChain::Step & step = chain.steps.back();
getRootActions(select_query->order_expression_list, only_types, false, step.actions);
ASTs asts = select_query->order_expression_list->children;
for (size_t i = 0; i < asts.size(); ++i)
{
ASTOrderByElement * ast = typeid_cast<ASTOrderByElement *>(asts[i].get());
if (!ast || ast->children.size() < 1)
throw Exception("Bad order expression AST", ErrorCodes::UNKNOWN_TYPE_OF_AST_NODE);
ASTPtr order_expression = ast->children.at(0);
step.required_output.push_back(order_expression->getColumnName());
}
return true;
}
2017-12-01 21:13:25 +00:00
void ExpressionAnalyzer::appendProjectResult(ExpressionActionsChain & chain) const
{
assertSelect();
initChain(chain, aggregated_columns);
ExpressionActionsChain::Step & step = chain.steps.back();
NamesWithAliases result_columns;
ASTs asts = select_query->select_expression_list->children;
for (size_t i = 0; i < asts.size(); ++i)
{
result_columns.emplace_back(asts[i]->getColumnName(), asts[i]->getAliasOrColumnName());
step.required_output.push_back(result_columns.back().second);
}
step.actions->add(ExpressionAction::project(result_columns));
}
Block ExpressionAnalyzer::getSelectSampleBlock()
{
assertSelect();
ExpressionActionsPtr temp_actions = std::make_shared<ExpressionActions>(aggregated_columns, settings);
NamesWithAliases result_columns;
ASTs asts = select_query->select_expression_list->children;
for (size_t i = 0; i < asts.size(); ++i)
{
result_columns.emplace_back(asts[i]->getColumnName(), asts[i]->getAliasOrColumnName());
getRootActions(asts[i], true, false, temp_actions);
}
temp_actions->add(ExpressionAction::project(result_columns));
return temp_actions->getSampleBlock();
}
void ExpressionAnalyzer::getActionsBeforeAggregation(const ASTPtr & ast, ExpressionActionsPtr & actions, bool no_subqueries)
{
ASTFunction * node = typeid_cast<ASTFunction *>(ast.get());
if (node && node->kind == ASTFunction::AGGREGATE_FUNCTION)
for (auto & argument : node->arguments->children)
getRootActions(argument, no_subqueries, false, actions);
else
for (auto & child : ast->children)
getActionsBeforeAggregation(child, actions, no_subqueries);
}
2013-06-03 13:17:17 +00:00
ExpressionActionsPtr ExpressionAnalyzer::getActions(bool project_result)
{
ExpressionActionsPtr actions = std::make_shared<ExpressionActions>(columns, settings);
NamesWithAliases result_columns;
Names result_names;
ASTs asts;
if (auto node = typeid_cast<const ASTExpressionList *>(ast.get()))
asts = node->children;
else
asts = ASTs(1, ast);
for (size_t i = 0; i < asts.size(); ++i)
{
std::string name = asts[i]->getColumnName();
std::string alias;
if (project_result)
alias = asts[i]->getAliasOrColumnName();
else
alias = name;
result_columns.emplace_back(name, alias);
result_names.push_back(alias);
getRootActions(asts[i], false, false, actions);
}
if (project_result)
{
actions->add(ExpressionAction::project(result_columns));
}
else
{
2017-04-02 17:37:49 +00:00
/// We will not delete the original columns.
for (const auto & column_name_type : columns)
result_names.push_back(column_name_type.name);
}
actions->finalize(result_names);
return actions;
}
ExpressionActionsPtr ExpressionAnalyzer::getConstActions()
{
ExpressionActionsPtr actions = std::make_shared<ExpressionActions>(NamesAndTypesList(), settings);
getRootActions(ast, true, true, actions);
return actions;
}
2015-04-18 22:30:43 +00:00
void ExpressionAnalyzer::getAggregateInfo(Names & key_names, AggregateDescriptions & aggregates) const
{
for (const auto & name_and_type : aggregation_keys)
key_names.emplace_back(name_and_type.name);
2015-03-12 02:22:55 +00:00
aggregates = aggregate_descriptions;
}
void ExpressionAnalyzer::collectUsedColumns()
{
2017-04-02 17:37:49 +00:00
/** Calculate which columns are required to execute the expression.
* Then, delete all other columns from the list of available columns.
* After execution, columns will only contain the list of columns needed to read from the table.
*/
NameSet required;
NameSet ignored;
NameSet available_columns;
for (const auto & column : columns)
available_columns.insert(column.name);
if (select_query && select_query->array_join_expression_list())
{
ASTs & expressions = select_query->array_join_expression_list()->children;
for (size_t i = 0; i < expressions.size(); ++i)
{
2017-04-02 17:37:49 +00:00
/// Ignore the top-level identifiers from the ARRAY JOIN section.
/// Then add them separately.
if (typeid_cast<ASTIdentifier *>(expressions[i].get()))
{
ignored.insert(expressions[i]->getColumnName());
}
else
{
2017-04-02 17:37:49 +00:00
/// Nothing needs to be ignored for expressions in ARRAY JOIN.
NameSet empty;
getRequiredColumnsImpl(expressions[i], available_columns, required, empty, empty, empty);
}
ignored.insert(expressions[i]->getAliasOrColumnName());
}
}
2017-04-02 17:37:49 +00:00
/** You also need to ignore the identifiers of the columns that are obtained by JOIN.
* (Do not assume that they are required for reading from the "left" table).
*/
NameSet available_joined_columns;
collectJoinedColumns(available_joined_columns, columns_added_by_join);
NameSet required_joined_columns;
getRequiredColumnsImpl(ast, available_columns, required, ignored, available_joined_columns, required_joined_columns);
for (NamesAndTypesList::iterator it = columns_added_by_join.begin(); it != columns_added_by_join.end();)
{
if (required_joined_columns.count(it->name))
++it;
else
columns_added_by_join.erase(it++);
}
2017-04-02 17:37:49 +00:00
/// Insert the columns required for the ARRAY JOIN calculation into the required columns list.
NameSet array_join_sources;
for (const auto & result_source : array_join_result_to_source)
array_join_sources.insert(result_source.second);
for (const auto & column_name_type : columns)
if (array_join_sources.count(column_name_type.name))
required.insert(column_name_type.name);
2017-04-02 17:37:49 +00:00
/// You need to read at least one column to find the number of rows.
if (required.empty())
required.insert(ExpressionActions::getSmallestColumn(columns));
unknown_required_columns = required;
for (NamesAndTypesList::iterator it = columns.begin(); it != columns.end();)
{
unknown_required_columns.erase(it->name);
if (!required.count(it->name))
columns.erase(it++);
else
++it;
}
2017-04-02 17:37:49 +00:00
/// Perhaps, there are virtual columns among the unknown columns. Remove them from the list of unknown and add
/// in columns list, so that when further processing the request they are perceived as real.
if (storage)
{
for (auto it = unknown_required_columns.begin(); it != unknown_required_columns.end();)
{
if (storage->hasColumn(*it))
{
columns.push_back(storage->getColumn(*it));
unknown_required_columns.erase(it++);
}
else
++it;
}
}
}
void ExpressionAnalyzer::collectJoinedColumns(NameSet & joined_columns, NamesAndTypesList & joined_columns_name_type)
2014-06-12 23:21:38 +00:00
{
if (!select_query)
return;
const ASTTablesInSelectQueryElement * node = select_query->join();
if (!node)
return;
const ASTTableJoin & table_join = static_cast<const ASTTableJoin &>(*node->table_join);
const ASTTableExpression & table_expression = static_cast<const ASTTableExpression &>(*node->table_expression);
Block nested_result_sample;
if (table_expression.database_and_table_name)
{
auto database_table = getDatabaseAndTableNameFromIdentifier(static_cast<const ASTIdentifier &>(*table_expression.database_and_table_name));
const auto & table = context.getTable(database_table.first, database_table.second);
nested_result_sample = table->getSampleBlockNonMaterialized();
}
else if (table_expression.subquery)
{
const auto & subquery = table_expression.subquery->children.at(0);
nested_result_sample = InterpreterSelectQuery::getSampleBlock(subquery, context);
}
if (table_join.using_expression_list)
{
auto & keys = typeid_cast<ASTExpressionList &>(*table_join.using_expression_list);
for (const auto & key : keys.children)
{
if (join_key_names_left.end() == std::find(join_key_names_left.begin(), join_key_names_left.end(), key->getColumnName()))
join_key_names_left.push_back(key->getColumnName());
else
throw Exception("Duplicate column " + key->getColumnName() + " in USING list", ErrorCodes::DUPLICATE_COLUMN);
if (join_key_names_right.end() == std::find(join_key_names_right.begin(), join_key_names_right.end(), key->getAliasOrColumnName()))
join_key_names_right.push_back(key->getAliasOrColumnName());
else
throw Exception("Duplicate column " + key->getAliasOrColumnName() + " in USING list", ErrorCodes::DUPLICATE_COLUMN);
}
}
for (const auto i : ext::range(0, nested_result_sample.columns()))
{
const auto & col = nested_result_sample.safeGetByPosition(i);
if (join_key_names_right.end() == std::find(join_key_names_right.begin(), join_key_names_right.end(), col.name)
2017-04-02 17:37:49 +00:00
&& !joined_columns.count(col.name)) /// Duplicate columns in the subquery for JOIN do not make sense.
{
joined_columns.insert(col.name);
2017-12-25 00:38:45 +00:00
bool make_nullable = settings.join_use_nulls && (table_join.kind == ASTTableJoin::Kind::Left || table_join.kind == ASTTableJoin::Kind::Full);
joined_columns_name_type.emplace_back(col.name, make_nullable ? makeNullable(col.type) : col.type);
}
}
2014-06-12 23:21:38 +00:00
}
2016-07-23 02:25:09 +00:00
2017-10-13 17:47:59 +00:00
Names ExpressionAnalyzer::getRequiredColumns() const
{
if (!unknown_required_columns.empty())
throw Exception("Unknown identifier: " + *unknown_required_columns.begin(), ErrorCodes::UNKNOWN_IDENTIFIER);
Names res;
for (const auto & column_name_type : columns)
res.push_back(column_name_type.name);
2014-06-12 21:12:47 +00:00
return res;
}
2016-07-23 02:25:09 +00:00
void ExpressionAnalyzer::getRequiredColumnsImpl(const ASTPtr & ast,
const NameSet & available_columns, NameSet & required_columns, NameSet & ignored_names,
const NameSet & available_joined_columns, NameSet & required_joined_columns)
{
2017-04-02 17:37:49 +00:00
/** Find all the identifiers in the query.
* We will look for them recursively, bypassing by depth AST.
* In this case
* - for lambda functions we will not take formal parameters;
* - do not go into subqueries (there are their identifiers);
* - is some exception for the ARRAY JOIN section (it has a slightly different identifier);
* - identifiers available from JOIN, we put in required_joined_columns.
*/
if (ASTIdentifier * node = typeid_cast<ASTIdentifier *>(ast.get()))
{
if (node->kind == ASTIdentifier::Column
&& !ignored_names.count(node->name)
&& !ignored_names.count(Nested::extractTableName(node->name)))
{
if (!available_joined_columns.count(node->name)
|| available_columns.count(node->name)) /// Read column from left table if has.
required_columns.insert(node->name);
else
required_joined_columns.insert(node->name);
}
return;
}
if (ASTFunction * node = typeid_cast<ASTFunction *>(ast.get()))
{
if (node->kind == ASTFunction::LAMBDA_EXPRESSION)
{
if (node->arguments->children.size() != 2)
throw Exception("lambda requires two arguments", ErrorCodes::NUMBER_OF_ARGUMENTS_DOESNT_MATCH);
ASTFunction * lambda_args_tuple = typeid_cast<ASTFunction *>(node->arguments->children.at(0).get());
if (!lambda_args_tuple || lambda_args_tuple->name != "tuple")
throw Exception("First argument of lambda must be a tuple", ErrorCodes::TYPE_MISMATCH);
2017-04-02 17:37:49 +00:00
/// You do not need to add formal parameters of the lambda expression in required_columns.
Names added_ignored;
for (auto & child : lambda_args_tuple->arguments->children)
{
ASTIdentifier * identifier = typeid_cast<ASTIdentifier *>(child.get());
if (!identifier)
throw Exception("lambda argument declarations must be identifiers", ErrorCodes::TYPE_MISMATCH);
String & name = identifier->name;
if (!ignored_names.count(name))
{
ignored_names.insert(name);
added_ignored.push_back(name);
}
}
getRequiredColumnsImpl(node->arguments->children.at(1),
available_columns, required_columns, ignored_names,
available_joined_columns, required_joined_columns);
for (size_t i = 0; i < added_ignored.size(); ++i)
ignored_names.erase(added_ignored[i]);
return;
}
2017-04-02 17:37:49 +00:00
/// A special function `indexHint`. Everything that is inside it is not calculated
/// (and is used only for index analysis, see PKCondition).
if (node->name == "indexHint")
return;
}
2017-04-02 17:37:49 +00:00
/// Recursively traverses an expression.
for (auto & child : ast->children)
{
2017-04-02 17:37:49 +00:00
/** We will not go to the ARRAY JOIN section, because we need to look at the names of non-ARRAY-JOIN columns.
* There, `collectUsedColumns` will send us separately.
*/
if (!typeid_cast<ASTSelectQuery *>(child.get())
&& !typeid_cast<ASTArrayJoin *>(child.get()))
getRequiredColumnsImpl(child, available_columns, required_columns,
ignored_names, available_joined_columns, required_joined_columns);
}
}
}