[ 
https://issues.apache.org/jira/browse/DRILL-6381?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16647419#comment-16647419
 ] 

ASF GitHub Bot commented on DRILL-6381:
---------------------------------------

vdiravka commented on a change in pull request #1466: DRILL-6381: Add support 
for index based planning and execution
URL: https://github.com/apache/drill/pull/1466#discussion_r217475464
 
 

 ##########
 File path: 
contrib/format-maprdb/src/main/java/org/apache/drill/exec/planner/index/MapRDBIndexDescriptor.java
 ##########
 @@ -0,0 +1,222 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements.  See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership.  The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License.  You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+package org.apache.drill.exec.planner.index;
+
+
+import java.util.Collection;
+import java.util.List;
+import java.util.Set;
+
+import com.google.common.collect.Lists;
+import com.google.common.collect.Sets;
+
+import org.apache.calcite.plan.RelOptCost;
+import org.apache.calcite.plan.RelOptPlanner;
+import org.apache.calcite.rel.RelFieldCollation.NullDirection;
+import org.apache.drill.common.expression.SchemaPath;
+import org.apache.drill.exec.expr.CloneVisitor;
+import org.apache.drill.exec.physical.base.DbGroupScan;
+import org.apache.drill.exec.physical.base.GroupScan;
+import org.apache.drill.exec.planner.cost.DrillCostBase;
+import org.apache.drill.exec.planner.cost.DrillCostBase.DrillCostFactory;
+import org.apache.drill.exec.planner.cost.PluginCost;
+import org.apache.drill.exec.planner.index.IndexProperties;
+import org.apache.drill.exec.store.mapr.PluginConstants;
+import org.apache.drill.exec.util.EncodedSchemaPathSet;
+import org.apache.drill.common.expression.LogicalExpression;
+
+import com.google.common.base.Preconditions;
+import com.google.common.collect.ImmutableSet;
+
+public class MapRDBIndexDescriptor extends DrillIndexDescriptor {
+
+  protected final Object desc;
+  protected final Set<LogicalExpression> allFields;
+  protected final Set<LogicalExpression> indexedFields;
+  protected MapRDBFunctionalIndexInfo functionalInfo;
+  protected PluginCost pluginCost;
+
+  public MapRDBIndexDescriptor(List<LogicalExpression> indexCols,
+                               CollationContext indexCollationContext,
+                               List<LogicalExpression> nonIndexCols,
+                               List<LogicalExpression> rowKeyColumns,
+                               String indexName,
+                               String tableName,
+                               IndexType type,
+                               Object desc,
+                               DbGroupScan scan,
+                               NullDirection nullsDirection) {
+    super(indexCols, indexCollationContext, nonIndexCols, rowKeyColumns, 
indexName, tableName, type, nullsDirection);
+    this.desc = desc;
+    this.indexedFields = ImmutableSet.copyOf(indexColumns);
+    this.allFields = new ImmutableSet.Builder<LogicalExpression>()
+        .add(PluginConstants.DOCUMENT_SCHEMA_PATH)
+        .addAll(indexColumns)
+        .addAll(nonIndexColumns)
+        .build();
+    this.pluginCost = scan.getPluginCostModel();
+  }
+
+  public Object getOriginalDesc(){
+    return desc;
+  }
+
+  @Override
+  public boolean isCoveringIndex(List<LogicalExpression> expressions) {
+    List<LogicalExpression> decodedCols = new 
DecodePathinExpr().parseExpressions(expressions);
+    return columnsInIndexFields(decodedCols, allFields);
+  }
+
+  @Override
+  public boolean allColumnsIndexed(Collection<LogicalExpression> expressions) {
+    List<LogicalExpression> decodedCols = new 
DecodePathinExpr().parseExpressions(expressions);
+    return columnsInIndexFields(decodedCols, indexedFields);
+  }
+
+  @Override
+  public boolean someColumnsIndexed(Collection<LogicalExpression> columns) {
+    return columnsIndexed(columns, false);
+  }
+
+  private boolean columnsIndexed(Collection<LogicalExpression> expressions, 
boolean allColsIndexed) {
+    List<LogicalExpression> decodedCols = new 
DecodePathinExpr().parseExpressions(expressions);
+    if (allColsIndexed) {
+      return columnsInIndexFields(decodedCols, indexedFields);
+    } else {
+      return someColumnsInIndexFields(decodedCols, indexedFields);
+    }
+  }
+
+  public FunctionalIndexInfo getFunctionalInfo() {
+    if (this.functionalInfo == null) {
+      this.functionalInfo = new MapRDBFunctionalIndexInfo(this);
+    }
+    return this.functionalInfo;
+  }
+
+  /**
+   * Search through a LogicalExpression, finding all referenced schema paths
+   * and replace them with decoded paths.
+   * If one encoded path could be decoded to multiple paths, add these decoded 
paths to
+   * the end of returned list of expressions from parseExpressions.
+   */
+  private class DecodePathinExpr extends CloneVisitor {
+    Set<SchemaPath> schemaPathSet = Sets.newHashSet();
+
+    public List<LogicalExpression> 
parseExpressions(Collection<LogicalExpression> expressions) {
+      List<LogicalExpression> allCols = Lists.newArrayList();
+      Collection<SchemaPath> decoded;
+
+      for(LogicalExpression expr : expressions) {
 
 Review comment:
   add space here and after `if`

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org


> Add capability to do index based planning and execution
> -------------------------------------------------------
>
>                 Key: DRILL-6381
>                 URL: https://issues.apache.org/jira/browse/DRILL-6381
>             Project: Apache Drill
>          Issue Type: New Feature
>          Components: Execution - Relational Operators, Query Planning &amp; 
> Optimization
>            Reporter: Aman Sinha
>            Assignee: Aman Sinha
>            Priority: Major
>             Fix For: 1.15.0
>
>
> If the underlying data source supports indexes (primary and secondary 
> indexes), Drill should leverage those during planning and execution in order 
> to improve query performance.  
> On the planning side, Drill planner should be enhanced to provide an 
> abstraction layer which express the index metadata and statistics.  Further, 
> a cost-based index selection is needed to decide which index(es) are 
> suitable.  
> On the execution side, appropriate operator enhancements would be needed to 
> handle different categories of indexes such as covering, non-covering 
> indexes, taking into consideration the index data may not be co-located with 
> the primary table, i.e a global index.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

Reply via email to