spark SparkOrcNewRecordReader 源码

spark SparkOrcNewRecordReader 代码

文件路径：/sql/hive/src/main/java/org/apache/hadoop/hive/ql/io/orc/SparkOrcNewRecordReader.java

/*
 * 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.hadoop.hive.ql.io.orc;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hive.serde2.objectinspector.ObjectInspector;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

import java.io.IOException;

/**
 * This is based on hive-exec-1.2.1
 * {@link org.apache.hadoop.hive.ql.io.orc.OrcNewInputFormat.OrcRecordReader}.
 * This class exposes getObjectInspector which can be used for reducing
 * NameNode calls in OrcRelation.
 */
public class SparkOrcNewRecordReader extends
    org.apache.hadoop.mapreduce.RecordReader<NullWritable, OrcStruct> {
  private final org.apache.hadoop.hive.ql.io.orc.RecordReader reader;
  private final int numColumns;
  OrcStruct value;
  private float progress = 0.0f;
  private ObjectInspector objectInspector;

  public SparkOrcNewRecordReader(Reader file, Configuration conf,
      long offset, long length) throws IOException {
    // TypeDescription.children is null in case of primitive types.
    // However, it doesn't happen on Reader.getSchema()
    numColumns = file.getSchema().getChildren().size();
    value = new OrcStruct(numColumns);
    this.reader = OrcInputFormat.createReaderFromFile(file, conf, offset,
        length);
    this.objectInspector = file.getObjectInspector();
  }

  @Override
  public void close() throws IOException {
    reader.close();
  }

  @Override
  public NullWritable getCurrentKey() throws IOException,
      InterruptedException {
    return NullWritable.get();
  }

  @Override
  public OrcStruct getCurrentValue() throws IOException,
      InterruptedException {
    return value;
  }

  @Override
  public float getProgress() throws IOException, InterruptedException {
    return progress;
  }

  @Override
  public void initialize(InputSplit split, TaskAttemptContext context)
      throws IOException, InterruptedException {
  }

  @Override
  public boolean nextKeyValue() throws IOException, InterruptedException {
    if (reader.hasNext()) {
      reader.next(value);
      progress = reader.getProgress();
      return true;
    } else {
      return false;
    }
  }

  public ObjectInspector getObjectInspector() {
    return objectInspector;
  }
}

相关信息

spark 源码目录

相关文章

spark ArrayWrappers 源码

spark InMemoryStore 源码

spark KVIndex 源码

spark KVStore 源码

spark KVStoreIterator 源码

spark KVStoreSerializer 源码

spark KVStoreView 源码

spark KVTypeInfo 源码

spark LevelDB 源码

spark LevelDBIterator 源码