List of usage examples for org.apache.hadoop.mapreduce RecordReader subclass-usage
From source file matrixFormat.MatrixRecordReader.java
public class MatrixRecordReader extends RecordReader<IntArrayWritable, DoubleArrayWritable> { private static final Log LOG = LogFactory.getLog(MatrixRecordReader.class); private CompressionCodecFactory compressionCodecs = null; //We will have two matrix to read at the same time. private long start1;
From source file ml.shifu.guagua.mapreduce.GuaguaMRRecordReader.java
/**
* {@link GuaguaMRRecordReader} is used as a mock for mapreduce reader interface, not real reading data.
*
* <p>
* To update progress, {@link #currentIteration} and {@link #totalIterations} should be set. {@link #currentIteration}
* only can be set in GuaguaMapper.run.
From source file ml.shifu.shifu.core.mr.input.CombineRecordReader.java
/** * Copy from Hadoop LineRecordReder to support multiple file splits into one mapper task. */ public class CombineRecordReader extends RecordReader<LongWritable, Text> { private final static Logger LOG = LoggerFactory.getLogger(CombineRecordReader.class);
From source file mr.ZipFileRecordReader.java
/** * This RecordReader implementation extracts individual files from a ZIP * file and hands them over to the Mapper. The "key" is the decompressed * file name, the "value" is the file contents. */ public class ZipFileRecordReader extends RecordReader<Text, BytesWritable> {
From source file net.jarcec.sqoop.data.gen.mr.GeneratorRecordReader.java
/** * Record reader for generator input format. */ public class GeneratorRecordReader extends RecordReader { GeneratorSplit split;
From source file net.mooncloud.mapreduce.lib.db.DBRecordReader.java
/**
* A RecordReader that reads records from a SQL table. Emits LongWritables
* containing the record number as key and DBWritables as value.
*/
@InterfaceAudience.Public
@InterfaceStability.Evolving
From source file net.shun.mapreduce.lib.input.XmlRecordReader.java
/** * Treats keys as offset in file and value as line. */ public class XmlRecordReader extends RecordReader<LongWritable, Text> { private static final Log LOG = LogFactory.getLog(XmlRecordReader.class);
From source file net.thevis.groovyhadoop.backport.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 nl.basjes.hadoop.input.ApacheHttpdLogfileRecordReader.java
@SuppressWarnings({ "PMD.OnlyOneReturn", "PMD.BeanMembersShouldSerialize" }) public class ApacheHttpdLogfileRecordReader extends RecordReader<LongWritable, ParsedRecord> { private static final Logger LOG = LoggerFactory.getLogger(ApacheHttpdLogfileRecordReader.class); private static final String HTTPD_LOGFILE_INPUT_FORMAT = "HTTPD Access Logfile InputFormat";
From source file nl.bioinf.wvanhelvoirt.HadoopPhredCalculator.NReadRecordReader.java
/**
* NReadRecordReader
*
* This is a custom class to create a RecordReader for each split.
*
* @author Wout van Helvoirt