Example usage for org.apache.hadoop.mapreduce RecordReader subclass-usage

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce RecordReader subclass-usage.

Usage

From source file org.apache.pig.impl.util.avro.AvroArrayReader.java

/**
 * RecordReader for Avro files
 */
public final class AvroArrayReader extends RecordReader<NullWritable, GenericData.Record> {

    private FileReader<GenericData.Array<Object>> reader;

From source file org.apache.pig.impl.util.avro.AvroRecordReader.java

/**
 * RecordReader for Avro files
 */
public final class AvroRecordReader extends RecordReader<NullWritable, GenericData.Record> {

    private FileReader<GenericData.Record> reader;

From source file org.apache.pig.piggybank.storage.avro.PigAvroRecordReader.java

/**
 * This is an implementation of record reader which reads in avro data and
 * convert them into <NullWritable, Writable> pairs.
 */
public class PigAvroRecordReader extends RecordReader<NullWritable, Writable> {

From source file org.apache.pig.piggybank.storage.hiverc.HiveRCRecordReader.java

/**
 * This class delegates the work to the RCFileRecordReader<br/>
 */
public class HiveRCRecordReader extends RecordReader<LongWritable, BytesRefArrayWritable> {

    LongWritable key;

From source file org.apache.pirk.inputformat.hadoop.json.JSONRecordReader.java

/**
 * Record reader to parse files of JSON string representations, one per line
 *
 */
public class JSONRecordReader extends RecordReader<Text, MapWritable> {
    private static final Logger logger = LoggerFactory.getLogger(JSONRecordReader.class);

From source file org.apache.spark.sql.execution.datasources.orc.OrcColumnarBatchReader.java

/**
 * To support vectorization in WholeStageCodeGen, this reader returns ColumnarBatch.
 * After creating, `initialize` and `initBatch` should be called sequentially.
 */
public class OrcColumnarBatchReader extends RecordReader<Void, ColumnarBatch> {

From source file org.apache.spark.sql.execution.datasources.parquet.SpecificParquetRecordReaderBase.java

/**
 * Base class for custom RecordReaders for Parquet that directly materialize to `T`.
 * This class handles computing row groups, filtering on them, setting up the column readers,
 * etc.
 * This is heavily based on parquet-mr's RecordReader.
 * TODO: move this to the parquet-mr project. There are performance benefits of doing it

From source file org.apache.sqoop.mapreduce.AvroRecordReader.java

/** An {@link RecordReader} for Avro data files. */
public class AvroRecordReader<T> extends RecordReader<AvroWrapper<T>, NullWritable> {

    private FileReader<T> reader;
    private long start;
    private long end;

From source file org.apache.sqoop.mapreduce.CombineFileRecordReader.java

/**
 * A generic RecordReader that can hand out different recordReaders
 * for each chunk in a {@link CombineFileSplit}.
 * A CombineFileSplit can combine data chunks from multiple files.
 * This class allows using different RecordReaders for processing
 * these data chunks from different files.

From source file org.apache.sqoop.mapreduce.CombineShimRecordReader.java

/**
 * RecordReader that CombineFileRecordReader can instantiate, which itself
 * translates a CombineFileSplit into a FileSplit.
 */
public class CombineShimRecordReader extends RecordReader<LongWritable, Object> {