Github user kavinderd commented on a diff in the pull request:
https://github.com/apache/incubator-hawq/pull/821#discussion_r72674048
--- Diff:
pxf/pxf-hive/src/main/java/org/apache/hawq/pxf/plugins/hive/HiveORCAccessor.java
---
@@ -0,0 +1,170 @@
+package org.apache.hawq.pxf.plugins.hive;
+
+/*
+ * 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.
+ */
+
+
+import org.apache.hadoop.hive.ql.exec.vector.BytesColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.ColumnVector;
+import org.apache.hadoop.hive.ql.exec.vector.VectorizedRowBatch;
+import org.apache.hadoop.hive.ql.io.orc.OrcInputFormat;
+import org.apache.hadoop.hive.ql.io.sarg.SearchArgument;
+import org.apache.hadoop.hive.ql.io.sarg.SearchArgumentFactory;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.hadoop.mapred.InputSplit;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hawq.pxf.api.FilterParser;
+import org.apache.hawq.pxf.api.OneRow;
+import org.apache.hawq.pxf.api.utilities.ColumnDescriptor;
+import org.apache.hawq.pxf.api.utilities.InputData;
+import org.apache.orc.Reader;
+import org.apache.orc.RecordReader;
+import org.apache.orc.TypeDescription;
+import org.apache.commons.lang.StringUtils;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+import static
org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter.PXF_HIVE_SERDES;
+
+/**
+ * Specialization of HiveAccessor for a Hive table that stores only ORC
files.
+ * This class replaces the generic HiveAccessor for a case where a table
is stored entirely as ORC files.
+ * Use together with {@link HiveInputFormatFragmenter}/{@link
HiveColumnarSerdeResolver}
+ */
+public class HiveORCAccessor extends HiveAccessor {
+
+ private RecordReader batchReader = null;
+ private Reader reader = null;
+ private VectorizedRowBatch batch = null;
+
+ private final String READ_COLUMN_IDS_CONF_STR =
"hive.io.file.readcolumn.ids";
+ private final String READ_ALL_COLUMNS =
"hive.io.file.read.all.columns";
+ private final String READ_COLUMN_NAMES_CONF_STR =
"hive.io.file.readcolumn.names";
+ private final String SARG_PUSHDOWN = "sarg.pushdown";
+
+ /**
+ * Constructs a HiveRCFileAccessor.
--- End diff --
Spelling `HiveORCAcessor`
---
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.
---
