Github user hyunsik commented on a diff in the pull request:
https://github.com/apache/tajo/pull/579#discussion_r34988886
--- Diff:
tajo-storage/tajo-storage-hdfs/src/main/java/org/apache/tajo/storage/orc/ORCScanner.java
---
@@ -0,0 +1,328 @@
+/**
+ * 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.tajo.storage.orc;
+
+import com.google.protobuf.InvalidProtocolBufferException;
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.fs.FSDataInputStream;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
+import org.apache.tajo.catalog.Schema;
+import org.apache.tajo.catalog.TableMeta;
+import org.apache.tajo.common.TajoDataTypes;
+import org.apache.tajo.conf.TajoConf;
+import org.apache.tajo.datum.*;
+import org.apache.tajo.exception.UnsupportedException;
+import org.apache.tajo.plan.expr.EvalNode;
+import org.apache.tajo.storage.FileScanner;
+import org.apache.tajo.storage.StorageConstants;
+import org.apache.tajo.storage.Tuple;
+import org.apache.tajo.storage.VTuple;
+import org.apache.tajo.storage.fragment.Fragment;
+import com.facebook.presto.orc.*;
+import com.facebook.presto.orc.metadata.OrcMetadataReader;
+import org.apache.tajo.storage.thirdparty.orc.HdfsOrcDataSource;
+import org.apache.tajo.util.datetime.DateTimeUtil;
+import org.joda.time.DateTimeZone;
+
+import java.io.IOException;
+import java.util.HashSet;
+import java.util.Set;
+
+/**
+ * OrcScanner for reading ORC files
+ */
+public class ORCScanner extends FileScanner {
+ private static final Log LOG = LogFactory.getLog(ORCScanner.class);
+ private OrcRecordReader recordReader;
+ private Vector [] vectors;
+ private int currentPosInBatch = 0;
+ private int batchSize = 0;
+
+ public ORCScanner(Configuration conf, final Schema schema, final
TableMeta meta, final Fragment fragment) {
+ super(conf, schema, meta, fragment);
+ }
+
+ private Vector createOrcVector(TajoDataTypes.DataType type) {
+ switch (type.getType()) {
+ case INT1: case INT2: case INT4: case INT8:
+ case UINT1: case UINT2: case UINT4: case UINT8:
+ case INET4:
+ case TIMESTAMP:
--- End diff --
Does ORC use long type for timestamp, date, and INET4?
As far as I know, Tajo represents INET4 or date values as a integer value
and timestamp as a long value. So, if you use LongVector for those types, it
won't be compatible.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
