You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hawq.apache.org by shivzone <gi...@git.apache.org> on 2018/01/02 19:39:59 UTC
[GitHub] incubator-hawq pull request #1326: HAWQ-1575. Implemented readable Parquet p...
Github user shivzone commented on a diff in the pull request:
https://github.com/apache/incubator-hawq/pull/1326#discussion_r159298191
--- Diff: pxf/pxf-hdfs/src/main/java/org/apache/hawq/pxf/plugins/hdfs/ParquetDataFragmenter.java ---
@@ -0,0 +1,103 @@
+package org.apache.hawq.pxf.plugins.hdfs;
+
+/*
+ * 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.conf.Configuration;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.mapreduce.InputSplit;
+import org.apache.hadoop.mapreduce.lib.input.FileSplit;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hawq.pxf.api.Fragment;
+import org.apache.hawq.pxf.api.Fragmenter;
+import org.apache.hawq.pxf.api.utilities.InputData;
+import org.apache.hawq.pxf.plugins.hdfs.utilities.HdfsUtilities;
+import org.apache.parquet.format.converter.ParquetMetadataConverter;
+import org.apache.parquet.hadoop.ParquetFileReader;
+import org.apache.parquet.hadoop.ParquetInputFormat;
+import org.apache.parquet.example.data.Group;
+import org.apache.parquet.hadoop.metadata.ParquetMetadata;
+import org.apache.parquet.schema.MessageType;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.List;
+
+public class ParquetDataFragmenter extends Fragmenter {
+ private Job job;
+
+ public ParquetDataFragmenter(InputData md) {
+ super(md);
+ JobConf jobConf = new JobConf(new Configuration(), ParquetDataFragmenter.class);
+ try {
+ job = Job.getInstance(jobConf);
+ } catch (IOException e) {
+ throw new RuntimeException("Unable to instantiate a job for reading fragments", e);
+ }
+ }
+
+
+ @Override
--- End diff --
Comments would be useful describing the components of the Fragment data here
---