org.apache.avro.mapred.PipesCompatibleAvroInputFormat.java Source code

Introduction

Here is the source code for org.apache.avro.mapred.PipesCompatibleAvroInputFormat.java

Source

/**
 * 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.avro.mapred;

import java.io.IOException;

import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.InputSplit;
import org.apache.hadoop.mapred.FileSplit;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.RecordReader;

/**
 * An {@code InputFormat} for Avro data files that
 * is compatible with Hadoop Pipes.
 * <p>
 * This is a default implementation for Avro files; if parsing a Avro file that
 * deserializes to a specific class, a new {@link InputFormat} extending this
 * one should be used instead. The new {@code InputFormat} should also pass a
 * new implementation of {@link KeyValueGetter} meant for the specific schema
 * to the {@link PipesCompatibleAvroRecordReader}.
 * <p>
 * Uses avro.mapred.key.field.name and avro.mapred.value.field.name properties
 * to identify the key and value fields in an Avro file. By default, they are
 * "key" and "value". These fields must be in the bytes, string, enum, or fixed
 * Avro data type, and must not be nested.
 * <p>
 * By default, when pointed at a directory, this will silently skip over any
 * files in it that do not have .avro extension. To instead include all files,
 * set the avro.mapred.ignore.inputs.without.extension property to false.
 * 
 * @param <T> the type of the input object
 */
public class PipesCompatibleAvroInputFormat<T> extends FileInputFormat<BytesWritable, BytesWritable> {

    private final AvroInputFormat<T> avroInputFormat = new AvroInputFormat<T>();

    /** The name of the key field in the Avro file */
    public static final String KEY_FIELD_NAME = "avro.mapred.key.field.name";

    /** The default name of the key field in the Avro file */
    public static final String KEY_FIELD_NAME_DEFAULT = "key";

    /** The name of the value field in the Avro file */
    public static final String VALUE_FIELD_NAME = "avro.mapred.value.field.name";

    /** The default name of the value field in the Avro file */
    public static final String VALUE_FIELD_NAME_DEFAULT = "value";

    @Override
    protected FileStatus[] listStatus(JobConf job) throws IOException {
        return avroInputFormat.listStatus(job);
    }

    /**
     * Returns the {@code PipesCompatibleAvroRecordReader} to be used
     * 
     * @return              the PipesCompatibleAvroRecordReader to be used
     * @throws IOException  if instantiating the
     *                      PipesCompatibleAvroRecordReader fails
     */
    @Override
    public RecordReader<BytesWritable, BytesWritable> getRecordReader(InputSplit split, JobConf job,
            Reporter reporter) throws IOException {
        reporter.setStatus(split.toString());

        return new PipesCompatibleAvroRecordReader<T>(job, (FileSplit) split,
                new AvroKeyValueGetter<T>(job.get(KEY_FIELD_NAME, KEY_FIELD_NAME_DEFAULT),
                        job.get(VALUE_FIELD_NAME, VALUE_FIELD_NAME_DEFAULT)));
    }

}