@Override public TupleEntryIterator openForRead(FlowProcess<JobConf> flowProcess, RecordReader input) throws IOException { return new HadoopTupleEntrySchemeIterator(flowProcess, this, input); }
@Override public TupleEntryCollector openForWrite(FlowProcess<JobConf> flowProcess, OutputCollector output) throws IOException { return new HadoopTupleEntrySchemeCollector(flowProcess, this, output); }
private static CloseableIterator<RecordReader> makeIterator( FlowProcess<? extends Configuration> flowProcess, Tap parentTap, RecordReader recordReader ) throws IOException { if( recordReader != null ) return new RecordReaderIterator( recordReader ); return new MultiRecordReaderIterator( flowProcess, parentTap ); }
@Override public FileStatus[] globStatus( Path path, PathFilter pathFilter ) throws IOException { FileStatus fileStatus = getFileStatus( path ); if( fileStatus == null ) return null; return new FileStatus[]{fileStatus}; }
/** * Method hasNext returns true if there more {@link Tuple} instances available. * * @return boolean */ public boolean hasNext() { getNextReader(); return !complete; }
@Override public FileStatus[] listStatus( Path path ) throws IOException { return new FileStatus[]{getFileStatus( path )}; }
/** * Constructor FSDigestInputStream creates a new FSDigestInputStream instance. * * @param inputStream of type InputStream * @param digestHex of type String * @throws IOException if unable to get md5 digest */ public FSDigestInputStream( InputStream inputStream, String digestHex ) throws IOException { this( inputStream, getMD5Digest(), digestHex ); }
private static OutputCollector makeCollector( FlowProcess<? extends Configuration> flowProcess, Tap<Configuration, RecordReader, OutputCollector> tap, OutputCollector outputCollector ) throws IOException { if( outputCollector != null ) return outputCollector; return new TapOutputCollector( flowProcess, tap ); }
@Override public TupleEntryIterator openForRead( FlowProcess<? extends Configuration> flowProcess, RecordReader input ) throws IOException { // input may be null when this method is called on the client side or cluster side when accumulating // for a HashJoin return new HadoopTupleEntrySchemeIterator( flowProcess, this, input ); }
@Override public TupleEntryCollector openForWrite(FlowProcess<JobConf> flowProcess, OutputCollector output) throws IOException { return new HadoopTupleEntrySchemeCollector(flowProcess, this, output); }
private static CloseableIterator<RecordReader> makeIterator( FlowProcess<? extends Configuration> flowProcess, Tap parentTap, RecordReader recordReader ) throws IOException { if( recordReader != null ) return new RecordReaderIterator( recordReader ); return new MultiRecordReaderIterator( flowProcess, parentTap ); }
@Override public FileStatus[] globStatus( Path path, PathFilter pathFilter ) throws IOException { FileStatus fileStatus = getFileStatus( path ); if( fileStatus == null ) return null; return new FileStatus[]{fileStatus}; }
/** * Method hasNext returns true if there more {@link Tuple} instances available. * * @return boolean */ public boolean hasNext() { getNextReader(); return !complete; }
@Override public FileStatus[] listStatus( Path path ) throws IOException { return new FileStatus[]{getFileStatus( path )}; }
/** * Constructor FSDigestInputStream creates a new FSDigestInputStream instance. * * @param inputStream of type InputStream * @param digestHex of type String * @throws IOException if unable to get md5 digest */ public FSDigestInputStream( InputStream inputStream, String digestHex ) throws IOException { this( inputStream, getMD5Digest(), digestHex ); }
private static OutputCollector makeCollector( FlowProcess<? extends Configuration> flowProcess, Tap<Configuration, RecordReader, OutputCollector> tap, OutputCollector outputCollector ) throws IOException { if( outputCollector != null ) return outputCollector; return new TapOutputCollector( flowProcess, tap ); }
@Override public TupleEntryIterator openForRead( FlowProcess<? extends Configuration> flowProcess, RecordReader input ) throws IOException { // input may be null when this method is called on the client side or cluster side when accumulating // for a HashJoin return new HadoopTupleEntrySchemeIterator( flowProcess, this, input ); }
@Override public TupleEntryIterator openForRead( FlowProcess<JobConf> flowProcess, RecordReader<TupleWrapper, NullWritable> input ) throws IOException { // input may be null when this method is called on the client side or cluster side when accumulating // for a HashJoin return new HadoopTupleEntrySchemeIterator( flowProcess, this, input ); }
@Override public TupleEntryIterator openForRead( FlowProcess<? extends Configuration> flowProcess, RecordReader input ) throws IOException { // input may be null when this method is called on the client side or // cluster side when accumulating for a HashJoin return new HadoopTupleEntrySchemeIterator( flowProcess, this, input ); }
@Override public TupleEntryIterator openForRead(FlowProcess<JobConf> jobConfFlowProcess, RecordReader recordReader) throws IOException { return new HadoopTupleEntrySchemeIterator(jobConfFlowProcess, this, recordReader); }