Merge pull request #1 from nikvas0/nikvas0/index_creation

Nikvas0/index creation

dbms/src/Storages/MergeTree/MergeTreeData.cpp

@@ -94,6 +94,7 @@ MergeTreeData::MergeTreeData(
     const ASTPtr & order_by_ast_,
     const ASTPtr & primary_key_ast_,
     const ASTPtr & sample_by_ast_,
+    const ASTs & indexes_ast_,
     const MergingParams & merging_params_,
     const MergeTreeSettings & settings_,
     bool require_part_metadata_,
@@ -185,6 +186,12 @@ MergeTreeData::MergeTreeData(
         throw Exception(
             "MergeTree data format version on disk doesn't support custom partitioning",
             ErrorCodes::METADATA_MISMATCH);
+
+    for (const auto & index_ast : indexes_ast_) {
+        indexes.push_back(
+                std::move(MergeTreeIndexFactory::instance().get(
+                        std::dynamic_pointer_cast<ASTIndexDeclaration>(index_ast))));
+    }
 }
 
 

dbms/src/Storages/MergeTree/MergeTreeData.h

@@ -5,6 +5,7 @@
 #include <Interpreters/ExpressionActions.h>
 #include <Storages/ITableDeclaration.h>
 #include <Storages/AlterCommands.h>
+#include <Storages/MergeTree/MergeTreeIndexes.h>
 #include <Storages/MergeTree/MergeTreePartInfo.h>
 #include <Storages/MergeTree/MergeTreeSettings.h>
 #include <IO/ReadBufferFromString.h>
@@ -306,6 +307,7 @@ class MergeTreeData : public ITableDeclaration
                   const ASTPtr & order_by_ast_,
                   const ASTPtr & primary_key_ast_,
                   const ASTPtr & sample_by_ast_, /// nullptr, if sampling is not supported.
+                  const ASTs & indexes_ast_,
                   const MergingParams & merging_params_,
                   const MergeTreeSettings & settings_,
                   bool require_part_metadata_,
@@ -578,6 +580,9 @@ class MergeTreeData : public ITableDeclaration
     Int64 minmax_idx_date_column_pos = -1; /// In a common case minmax index includes a date column.
     Int64 minmax_idx_time_column_pos = -1; /// In other cases, minmax index often includes a dateTime column.
 
+    /// Secondary indexes for MergeTree
+    MergeTreeIndexes indexes;
+
     /// Names of columns for primary key + secondary sorting columns.
     Names sorting_key_columns;
     ASTPtr sorting_key_expr_ast;

dbms/src/Storages/MergeTree/MergeTreeIndexes.cpp

@@ -0,0 +1,31 @@
+#include <Storages/MergeTree/MergeTreeIndexes.h>
+
+namespace DB
+{
+
+namespace ErrorCodes
+{
+    extern const int LOGICAL_ERROR;
+    extern const int INCORRECT_QUERY;
+}
+
+void MergeTreeIndexFactory::registerIndex(const std::string &name, Creator creator) {
+    if (!indexes.emplace(name, std::move(creator)).second)
+        throw Exception("MergeTreeIndexFactory: the Index creator name '" + name + "' is not unique",
+                        ErrorCodes::LOGICAL_ERROR);
+}
+
+std::unique_ptr<MergeTreeIndex> MergeTreeIndexFactory::get(std::shared_ptr<ASTIndexDeclaration> node) const {
+    if (!node->type)
+        throw Exception(
+                "for INDEX TYPE is required",
+                ErrorCodes::INCORRECT_QUERY);
+    auto it = indexes.find(node->type->name);
+    if (it == indexes.end())
+        throw Exception(
+                "Unknown Index type '" + node->type->name + "'",
+                ErrorCodes::INCORRECT_QUERY);
+    return it->second(node);
+}
+
+}

dbms/src/Storages/MergeTree/MergeTreeIndexes.h

@@ -0,0 +1,64 @@
+#pragma once
+
+#include <string>
+#include <unordered_map>
+#include <vector>
+#include <memory>
+#include <Core/Block.h>
+#include <ext/singleton.h>
+#include <Interpreters/ExpressionActions.h>
+#include <Storages/MergeTree/MergeTreeDataPartChecksum.h>
+#include <Parsers/ASTIndexDeclaration.h>
+
+namespace DB
+{
+
+
+/// Interface for secondary MergeTree indexes
+class MergeTreeIndex
+{
+public:
+    virtual ~MergeTreeIndex() {};
+
+    virtual void load(const String & part_path) = 0;
+    virtual void store(const String & part_path, MergeTreeDataPartChecksums & checksums) const = 0;
+
+    virtual void update(const Block & block, const Names & column_names) = 0;
+    virtual void merge(const MergeTreeIndex & other) = 0;
+
+    virtual bool alwaysUnknownOrTrue() const = 0;
+    virtual bool maybeTrue() const = 0;
+
+    String name;
+    ExpressionActionsPtr expr;
+    Block header;
+};
+
+using MergeTreeIndexPtr = std::unique_ptr<MergeTreeIndex>;
+using MergeTreeIndexes = std::vector<MergeTreeIndexPtr>;
+
+
+class MergeTreeIndexFactory : public ext::singleton<MergeTreeIndexFactory>
+{
+    friend class ext::singleton<MergeTreeIndexFactory>;
+
+public:
+    using Creator = std::function<std::unique_ptr<MergeTreeIndex>(std::shared_ptr<ASTIndexDeclaration> node)>;
+
+    std::unique_ptr<MergeTreeIndex> get(std::shared_ptr<ASTIndexDeclaration> node) const;
+
+    void registerIndex(const std::string & name, Creator creator);
+
+    const auto & getAllIndexes() const {
+        return indexes;
+    }
+
+protected:
+    MergeTreeIndexFactory() {};
+
+private:
+    using Indexes = std::unordered_map<std::string, Creator>;
+    Indexes indexes;
+};
+
+}

dbms/src/Storages/MergeTree/registerStorageMergeTree.cpp

@@ -336,7 +336,8 @@ static StoragePtr create(const StorageFactory::Arguments & args)
         */
 
     bool is_extended_storage_def =
-        args.storage_def->partition_by || args.storage_def->primary_key || args.storage_def->order_by || args.storage_def->sample_by || args.storage_def->settings;
+        args.storage_def->partition_by || args.storage_def->primary_key || args.storage_def->order_by
+        || args.storage_def->sample_by || !args.storage_def->indexes.empty() || args.storage_def->settings;
 
     String name_part = args.engine_name.substr(0, args.engine_name.size() - strlen("MergeTree"));
 
@@ -559,6 +560,7 @@ static StoragePtr create(const StorageFactory::Arguments & args)
     ASTPtr order_by_ast;
     ASTPtr primary_key_ast;
     ASTPtr sample_by_ast;
+    ASTs indexes_ast;
     MergeTreeSettings storage_settings = args.context.getMergeTreeSettings();
 
     if (is_extended_storage_def)
@@ -579,6 +581,10 @@ static StoragePtr create(const StorageFactory::Arguments & args)
         if (args.storage_def->sample_by)
             sample_by_ast = args.storage_def->sample_by->ptr();
 
+        for (auto& index : args.storage_def->indexes) {
+            indexes_ast.push_back(index->ptr());
+        }
+
         storage_settings.loadFromQuery(*args.storage_def);
     }
     else
@@ -615,13 +621,13 @@ static StoragePtr create(const StorageFactory::Arguments & args)
             zookeeper_path, replica_name, args.attach, args.data_path, args.database_name, args.table_name,
             args.columns,
             args.context, date_column_name, partition_by_ast, order_by_ast, primary_key_ast,
-            sample_by_ast, merging_params, storage_settings,
+            sample_by_ast, indexes_ast, merging_params, storage_settings,
             args.has_force_restore_data_flag);
     else
         return StorageMergeTree::create(
             args.data_path, args.database_name, args.table_name, args.columns, args.attach,
             args.context, date_column_name, partition_by_ast, order_by_ast, primary_key_ast,
-            sample_by_ast, merging_params, storage_settings,
+            sample_by_ast, indexes_ast, merging_params, storage_settings,
             args.has_force_restore_data_flag);
 }
 

dbms/src/Storages/StorageMergeTree.cpp

@@ -51,6 +51,7 @@ StorageMergeTree::StorageMergeTree(
     const ASTPtr & order_by_ast_,
     const ASTPtr & primary_key_ast_,
     const ASTPtr & sample_by_ast_, /// nullptr, if sampling is not supported.
+    const ASTs & indexes_ast_,
     const MergeTreeData::MergingParams & merging_params_,
     const MergeTreeSettings & settings_,
     bool has_force_restore_data_flag)
@@ -59,7 +60,7 @@ StorageMergeTree::StorageMergeTree(
     data(database_name, table_name,
          full_path, columns_,
          context_, date_column_name, partition_by_ast_, order_by_ast_, primary_key_ast_,
-         sample_by_ast_, merging_params_,
+         sample_by_ast_, indexes_ast_, merging_params_,
          settings_, false, attach),
     reader(data), writer(data), merger_mutator(data, context.getBackgroundPool()),
     log(&Logger::get(database_name_ + "." + table_name + " (StorageMergeTree)"))

dbms/src/Storages/StorageMergeTree.h

@@ -174,6 +174,7 @@ class StorageMergeTree : public ext::shared_ptr_helper<StorageMergeTree>, public
         const ASTPtr & order_by_ast_,
         const ASTPtr & primary_key_ast_,
         const ASTPtr & sample_by_ast_, /// nullptr, if sampling is not supported.
+        const ASTs & indexes_ast_,
         const MergeTreeData::MergingParams & merging_params_,
         const MergeTreeSettings & settings_,
         bool has_force_restore_data_flag);

dbms/src/Storages/StorageReplicatedMergeTree.cpp

@@ -203,6 +203,7 @@ StorageReplicatedMergeTree::StorageReplicatedMergeTree(
     const ASTPtr & order_by_ast_,
     const ASTPtr & primary_key_ast_,
     const ASTPtr & sample_by_ast_,
+    const ASTs & indexes_ast_,
     const MergeTreeData::MergingParams & merging_params_,
     const MergeTreeSettings & settings_,
     bool has_force_restore_data_flag)
@@ -214,7 +215,7 @@ StorageReplicatedMergeTree::StorageReplicatedMergeTree(
     data(database_name, table_name,
         full_path, columns_,
         context_, date_column_name, partition_by_ast_, order_by_ast_, primary_key_ast_,
-        sample_by_ast_, merging_params_,
+        sample_by_ast_, indexes_ast_, merging_params_,
         settings_, true, attach,
         [this] (const std::string & name) { enqueuePartForCheck(name); }),
     reader(data), writer(data), merger_mutator(data, context.getBackgroundPool()), queue(*this),

dbms/src/Storages/StorageReplicatedMergeTree.h

@@ -548,6 +548,7 @@ class StorageReplicatedMergeTree : public ext::shared_ptr_helper<StorageReplicat
         const ASTPtr & order_by_ast_,
         const ASTPtr & primary_key_ast_,
         const ASTPtr & sample_by_ast_,
+        const ASTs & indexes_ast_,
         const MergeTreeData::MergingParams & merging_params_,
         const MergeTreeSettings & settings_,
         bool has_force_restore_data_flag);