[
https://issues.apache.org/jira/browse/DRILL-6381?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16647439#comment-16647439
]
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_r223667409
##########
File path:
exec/java-exec/src/main/java/org/apache/drill/exec/planner/index/DrillIndexDefinition.java
##########
@@ -0,0 +1,278 @@
+/*
+ * 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 com.fasterxml.jackson.annotation.JsonIgnore;
+import com.fasterxml.jackson.annotation.JsonProperty;
+import org.apache.drill.shaded.guava.com.google.common.collect.Sets;
+
+import org.apache.calcite.rel.RelCollation;
+import org.apache.calcite.rel.RelCollations;
+import org.apache.calcite.rel.RelFieldCollation;
+import org.apache.calcite.rel.RelFieldCollation.NullDirection;
+import org.apache.drill.common.expression.CastExpression;
+import org.apache.drill.common.expression.LogicalExpression;
+import org.apache.drill.common.expression.SchemaPath;
+
+import java.util.Collection;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+public class DrillIndexDefinition implements IndexDefinition {
+ /**
+ * The indexColumns is the list of column(s) on which this index is created.
If there is more than 1 column,
+ * the order of the columns is important: index on {a, b} is not the same as
index on {b, a}
+ * NOTE: the indexed column could be of type columnfamily.column
+ */
+ @JsonProperty
+ protected final List<LogicalExpression> indexColumns;
+
+ /**
+ * nonIndexColumns: the list of columns that are included in the index as
'covering'
+ * columns but are not themselves indexed. These are useful for covering
indexes where the
+ * query request can be satisfied directly by the index and avoid accessing
the table altogether.
+ */
+ @JsonProperty
+ protected final List<LogicalExpression> nonIndexColumns;
+
+ @JsonIgnore
+ protected final Set<LogicalExpression> allIndexColumns;
+
+ @JsonProperty
+ protected final List<LogicalExpression> rowKeyColumns;
+
+ @JsonProperty
+ protected final CollationContext indexCollationContext;
+
+ /**
+ * indexName: name of the index that should be unique within the scope of a
table
+ */
+ @JsonProperty
+ protected final String indexName;
+
+ protected final String tableName;
+
+ @JsonProperty
+ protected final IndexDescriptor.IndexType indexType;
+
+ @JsonProperty
+ protected final NullDirection nullsDirection;
+
+ public DrillIndexDefinition(List<LogicalExpression> indexCols,
+ CollationContext indexCollationContext,
+ List<LogicalExpression> nonIndexCols,
+ List<LogicalExpression> rowKeyColumns,
+ String indexName,
+ String tableName,
+ IndexType type,
+ NullDirection nullsDirection) {
+ this.indexColumns = indexCols;
+ this.nonIndexColumns = nonIndexCols;
+ this.rowKeyColumns = rowKeyColumns;
+ this.indexName = indexName;
+ this.tableName = tableName;
+ this.indexType = type;
+ this.allIndexColumns = Sets.newHashSet(indexColumns);
+ this.allIndexColumns.addAll(nonIndexColumns);
+ this.indexCollationContext = indexCollationContext;
+ this.nullsDirection = nullsDirection;
+
+ }
+
+ @Override
+ public int getIndexColumnOrdinal(LogicalExpression path) {
+ int id = indexColumns.indexOf(path);
+ return id;
+ }
+
+ @Override
+ public boolean isCoveringIndex(List<LogicalExpression> columns) {
+ return allIndexColumns.containsAll(columns);
+ }
+
+ @Override
+ public boolean allColumnsIndexed(Collection<LogicalExpression> columns) {
+ return columnsInIndexFields(columns, indexColumns);
+ }
+
+ @Override
+ public boolean someColumnsIndexed(Collection<LogicalExpression> columns) {
+ return someColumnsInIndexFields(columns, indexColumns);
+ }
+
+ public boolean pathExactIn(SchemaPath path, Collection<LogicalExpression>
exprs) {
+ for (LogicalExpression expr : exprs) {
+ if (expr instanceof SchemaPath) {
+ if (((SchemaPath) expr).toExpr().equals(path.toExpr())) {
+ return true;
+ }
+ }
+ }
+
+ return false;
+ }
+
+ boolean castIsCompatible(CastExpression castExpr,
Collection<LogicalExpression> indexFields) {
+ for(LogicalExpression indexExpr : indexFields) {
+ if(indexExpr.getClass() != castExpr.getClass()) {
+ continue;
+ }
+ CastExpression indexCastExpr = (CastExpression)indexExpr;
+ //we compare input using equals because we know we are comparing
SchemaPath,
+ //if we extend to support other expression, make sure the equals of that
expression
+ //is implemented properly, otherwise it will fall to identity comparison
+ if ( !castExpr.getInput().equals(indexCastExpr.getInput()) ) {
Review comment:
formatting
----------------------------------------------------------------
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 &
> 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)
