Github user jacques-n commented on a diff in the pull request:
https://github.com/apache/drill/pull/257#discussion_r44883499
--- Diff:
exec/java-exec/src/main/java/org/apache/drill/exec/record/SchemaUtil.java ---
@@ -0,0 +1,159 @@
+/**
+ * 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
+ * <p/>
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * <p/>
+ * 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.record;
+
+import com.google.common.base.Preconditions;
+import com.google.common.collect.Lists;
+import com.google.common.collect.Maps;
+import com.google.common.collect.Sets;
+import org.apache.drill.common.expression.SchemaPath;
+import org.apache.drill.common.types.TypeProtos.DataMode;
+import org.apache.drill.common.types.TypeProtos.MajorType;
+import org.apache.drill.common.types.TypeProtos.MinorType;
+import org.apache.drill.common.types.Types;
+import org.apache.drill.exec.expr.TypeHelper;
+import org.apache.drill.exec.memory.BufferAllocator;
+import org.apache.drill.exec.ops.OperatorContext;
+import org.apache.drill.exec.physical.impl.sort.RecordBatchData;
+import org.apache.drill.exec.record.BatchSchema.SelectionVectorMode;
+import org.apache.drill.exec.vector.ValueVector;
+import org.apache.drill.exec.vector.complex.UnionVector;
+
+import java.util.List;
+import java.util.Map;
+import java.util.Set;
+
+/**
+ * Utility class for dealing with changing schemas
+ */
+public class SchemaUtil {
+
+ /**
+ * Returns the merger of schemas. The merged schema will include the
union all columns. If there is a type conflict
+ * between columns with the same schemapath but different types, the
merged schema will contain a Union type.
+ * @param schemas
+ * @return
+ */
+ public static BatchSchema mergeSchemas(BatchSchema... schemas) {
+ Map<SchemaPath,Set<MinorType>> typeSetMap = Maps.newLinkedHashMap();
+
+ for (BatchSchema s : schemas) {
+ for (MaterializedField field : s) {
+ SchemaPath path = field.getPath();
+ Set<MinorType> currentTypes = typeSetMap.get(path);
+ if (currentTypes == null) {
+ currentTypes = Sets.newHashSet();
+ typeSetMap.put(path, currentTypes);
+ }
+ MinorType newType = field.getType().getMinorType();
+ if (newType == MinorType.UNION) {
+ for (MinorType subType : field.getType().getSubTypeList()) {
+ currentTypes.add(subType);
+ }
+ } else {
+ currentTypes.add(newType);
+ }
+ }
+ }
+
+ List<MaterializedField> fields = Lists.newArrayList();
+
+ for (SchemaPath path : typeSetMap.keySet()) {
+ Set<MinorType> types = typeSetMap.get(path);
+ if (types.size() > 1) {
--- End diff --
Isn't it possible two different map types would be added above? If so, it
seems like we would produce a union when we shouldn't.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
