Example usage for org.apache.hadoop.mapred FileOutputFormat subclass-usage

Introduction

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

Usage

From source file org.apache.trevni.avro.AvroTrevniOutputFormat.java

/** An {@link org.apache.hadoop.mapred.OutputFormat} that writes Avro data to
 * Trevni files.
 *
 * <p>Writes a directory of files per task, each comprising a single filesystem
 * block.  To reduce the number of files, increase the default filesystem block
 * size for the job.  Each task also requires enough memory to buffer a

From source file org.archive.hadoop.PerMapOutputFormat.java

/**
 * OutputFormat that directs the output to a file named according to
 * the input file.  For instance, if the input file is "foo", then the
 * output file is also named "foo".  A suffix can be easily added, or
 * a regex+replace applied to the input filename to produce an output
 * filename.

From source file org.archive.jbs.lucene.LuceneOutputFormat.java

/**
 * This class is inspired by Nutch's LuceneOutputFormat class.  It does
 * primarily three things of interest:
 *
 *  1. Creates a Lucene index in a local (not HDFS) ${temp} directory,
 *     into which the documents are added.

From source file org.archive.jbs.solr.SolrOutputFormat.java

/**
 * This class is inspired by the technique used in Nutch's
 * LuceneOutputFormat class.  However, rather than creating a Lucene
 * index and writing documents to it, we use the SolrJ API to send the
 * documents to a (remote) Solr server.
 *

From source file org.archive.jbs.util.PerMapOutputFormat.java

/**
 * 
 */
public class PerMapOutputFormat<K, V> extends FileOutputFormat<K, V> {
    private String getOutputFilename(JobConf job) throws IOException {
        String regex = job.get("permap.regex", null);

From source file org.commoncrawl.mapred.ec2.parser.ParserOutputFormat.java

/** 
 * OutputFormat that splits the output from the ParseMapper into a bunch of 
 * distinct files, including: 
 * 
 * (1) A metadata file, that contains the crawl status, the http headers, the
 * meta tags,title,links (if HTML), and Feed related data (if RSS/ATOM) in a

From source file org.hbasene.index.create.mapred.IndexOutputFormat.java

/**
 * Create a local index, unwrap Lucene documents created by reduce, add them to
 * the index, and copy the index to the destination.
 */
@Deprecated
public class IndexOutputFormat extends FileOutputFormat<ImmutableBytesWritable, LuceneDocumentWrapper> {

From source file org.saarus.service.hadoop.util.JsonOutputFormat.java

/** An {@link JsonOutputFormat} that writes Json Objects as output. 
  */

public class JsonOutputFormat<K, V> extends FileOutputFormat<K, V> {

    protected static class JsonRecordWriter<K, V> implements RecordWriter<K, V> {

From source file org.zuinnote.hadoop.office.format.mapred.AbstractSpreadSheetDocumentFileOutputFormat.java

public abstract class AbstractSpreadSheetDocumentFileOutputFormat<K> extends FileOutputFormat<NullWritable, K> {

    @Override
    public abstract RecordWriter<NullWritable, K> getRecordWriter(FileSystem ignored, JobConf conf, String name,
            Progressable progress) throws IOException;

From source file parquet.hadoop.mapred.DeprecatedParquetOutputFormat.java

@SuppressWarnings("deprecation")
public class DeprecatedParquetOutputFormat<V> extends org.apache.hadoop.mapred.FileOutputFormat<Void, V> {
    private static final Log LOG = Log.getLog(DeprecatedParquetOutputFormat.class);

    public static void setWriteSupportClass(Configuration configuration, Class<?> writeSupportClass) {
        configuration.set(ParquetOutputFormat.WRITE_SUPPORT_CLASS, writeSupportClass.getName());