1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
|
#include <Storages/IStorage.h>
#include <Parsers/ASTOptimizeQuery.h>
#include <Interpreters/Context.h>
#include <Interpreters/executeDDLQueryOnCluster.h>
#include <Interpreters/InterpreterOptimizeQuery.h>
#include <Access/Common/AccessRightsElement.h>
#include <Common/typeid_cast.h>
#include <Parsers/ASTExpressionList.h>
#include <Storages/MergeTree/MergeTreeData.h>
#include <Interpreters/processColumnTransformers.h>
#include <memory>
namespace DB
{
namespace ErrorCodes
{
extern const int THERE_IS_NO_COLUMN;
}
BlockIO InterpreterOptimizeQuery::execute()
{
const auto & ast = query_ptr->as<ASTOptimizeQuery &>();
if (!ast.cluster.empty())
{
DDLQueryOnClusterParams params;
params.access_to_check = getRequiredAccess();
return executeDDLQueryOnCluster(query_ptr, getContext(), params);
}
getContext()->checkAccess(getRequiredAccess());
auto table_id = getContext()->resolveStorageID(ast);
StoragePtr table = DatabaseCatalog::instance().getTable(table_id, getContext());
checkStorageSupportsTransactionsIfNeeded(table, getContext());
auto metadata_snapshot = table->getInMemoryMetadataPtr();
auto storage_snapshot = table->getStorageSnapshot(metadata_snapshot, getContext());
// Empty list of names means we deduplicate by all columns, but user can explicitly state which columns to use.
Names column_names;
if (ast.deduplicate_by_columns)
{
// User requested custom set of columns for deduplication, possibly with Column Transformer expression.
{
// Expand asterisk, column transformers, etc into list of column names.
const auto cols
= processColumnTransformers(getContext()->getCurrentDatabase(), table, metadata_snapshot, ast.deduplicate_by_columns);
for (const auto & col : cols->children)
column_names.emplace_back(col->getColumnName());
}
storage_snapshot->check(column_names);
Names required_columns;
{
required_columns = metadata_snapshot->getColumnsRequiredForSortingKey();
const auto partitioning_cols = metadata_snapshot->getColumnsRequiredForPartitionKey();
required_columns.reserve(required_columns.size() + partitioning_cols.size());
required_columns.insert(required_columns.end(), partitioning_cols.begin(), partitioning_cols.end());
}
for (const auto & required_col : required_columns)
{
// Deduplication is performed only for adjacent rows in a block,
// and all rows in block are in the sorting key order within a single partition,
// hence deduplication always implicitly takes sorting keys and partition keys in account.
// So we just explicitly state that limitation in order to avoid confusion.
if (std::find(column_names.begin(), column_names.end(), required_col) == column_names.end())
throw Exception(ErrorCodes::THERE_IS_NO_COLUMN,
"DEDUPLICATE BY expression must include all columns used in table's"
" ORDER BY, PRIMARY KEY, or PARTITION BY but '{}' is missing."
" Expanded DEDUPLICATE BY columns expression: ['{}']",
required_col, fmt::join(column_names, "', '"));
}
}
if (auto * snapshot_data = dynamic_cast<MergeTreeData::SnapshotData *>(storage_snapshot->data.get()))
snapshot_data->parts = {};
table->optimize(query_ptr, metadata_snapshot, ast.partition, ast.final, ast.deduplicate, column_names, ast.cleanup, getContext());
return {};
}
AccessRightsElements InterpreterOptimizeQuery::getRequiredAccess() const
{
const auto & optimize = query_ptr->as<const ASTOptimizeQuery &>();
AccessRightsElements required_access;
required_access.emplace_back(AccessType::OPTIMIZE, optimize.getDatabase(), optimize.getTable());
return required_access;
}
}
|
