[
https://issues.apache.org/jira/browse/DRILL-5152?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15808134#comment-15808134
]
ASF GitHub Bot commented on DRILL-5152:
---------------------------------------
Github user paul-rogers commented on a diff in the pull request:
https://github.com/apache/drill/pull/708#discussion_r95063860
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/store/mock/ExtendedMockRecordReader.java
---
@@ -0,0 +1,149 @@
+/*
+ * 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.store.mock;
+
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+import org.apache.drill.common.exceptions.ExecutionSetupException;
+import org.apache.drill.common.types.TypeProtos.MajorType;
+import org.apache.drill.exec.exception.OutOfMemoryException;
+import org.apache.drill.exec.exception.SchemaChangeException;
+import org.apache.drill.exec.expr.TypeHelper;
+import org.apache.drill.exec.ops.FragmentContext;
+import org.apache.drill.exec.ops.OperatorContext;
+import org.apache.drill.exec.physical.impl.OutputMutator;
+import org.apache.drill.exec.record.MaterializedField;
+import org.apache.drill.exec.store.AbstractRecordReader;
+import org.apache.drill.exec.store.mock.MockGroupScanPOP.MockColumn;
+import org.apache.drill.exec.store.mock.MockGroupScanPOP.MockScanEntry;
+import org.apache.drill.exec.vector.AllocationHelper;
+import org.apache.drill.exec.vector.ValueVector;
+
+public class ExtendedMockRecordReader extends AbstractRecordReader {
+
+ private ValueVector[] valueVectors;
+ private int batchRecordCount;
+ private int recordsRead;
+
+ private final MockScanEntry config;
+ private final FragmentContext context;
+ private final ColumnDef fields[];
+
+ public ExtendedMockRecordReader(FragmentContext context, MockScanEntry
config) {
+ this.context = context;
+ this.config = config;
+
+ fields = buildColumnDefs( );
+ }
+
+ private ColumnDef[] buildColumnDefs() {
+ List<ColumnDef> defs = new ArrayList<>( );
+
+ // Look for duplicate names. Bad things happen when the sama name
--- End diff --
Fixed.
> Enhance the mock data source: better data, SQL access
> -----------------------------------------------------
>
> Key: DRILL-5152
> URL: https://issues.apache.org/jira/browse/DRILL-5152
> Project: Apache Drill
> Issue Type: Improvement
> Components: Tools, Build & Test
> Affects Versions: 1.9.0
> Reporter: Paul Rogers
> Assignee: Paul Rogers
> Priority: Minor
>
> Drill provides a mock data storage engine that generates random data. The
> mock engine is used in some older unit tests that need a volume of data, but
> that are not too particular about the details of the data.
> The mock data source continues to have use even for modern tests. For
> example, the work in the external storage batch requires tests with varying
> amounts of data, but the exact form of the data is not important, just the
> quantity. For example, if we want to ensure that spilling happens at various
> trigger points, we need to read the right amount of data for that trigger.
> The existing mock data source has two limitations:
> 1. It generates only "black/white" (alternating) values, which is awkward for
> use in sorting.
> 2. The mock generator is accessible only from a physical plan, but not from
> SQL queries.
> This enhancement proposes to fix both limitations:
> 1. Generate a uniform, randomly distributed set of values.
> 2. Provide an encoding that lets a SQL query specify the data to be generated.
> Example SQL query:
> {code}
> SELECT id_i, name_s50 FROM `mock`.employee_10K;
> {code}
> The above says to generate two fields: INTEGER (the "_i" suffix) and
> VARCHAR(50) (the "_s50") suffix; and to generate 10,000 rows (the "_10K"
> suffix on the table.)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
