List of usage examples for org.apache.hadoop.mapreduce.lib.input CombineFileInputFormat subclass-usage
From source file com.alexholmes.hadooputils.combine.common.mapreduce.SplitMetricsCombineInputFormat.java
/**
* An input format that writes split details to a sink, the default sink being a logger.
*
* @param <K> The key type.
* @param <V> The value type.
*/
From source file com.blackberry.logdriver.mapreduce.avro.AvroBlockInputFormat.java
public class AvroBlockInputFormat extends CombineFileInputFormat<AvroFileHeader, BytesWritable> { private static final Logger LOG = LoggerFactory.getLogger(AvroBlockInputFormat.class); private static final long MAX_SPLIT_LOCATIONS = 100000; /** * Avro files are always splitable.
From source file com.blackberry.logdriver.mapreduce.boom.BoomInputFormat.java
public class BoomInputFormat extends CombineFileInputFormat<LogLineData, Text> { private static final Logger LOG = LoggerFactory.getLogger(BoomInputFormat.class); private static final long MAX_SPLIT_LOCATIONS = 100000; @Override
From source file com.bonc.mr_roamRecognition_hjpt.comm.FirstJobCombineTextInputFormat.java
/**
* Input format that is a <code>CombineFileInputFormat</code>-equivalent for
* <code>TextInputFormat</code>.
*
* @see CombineFileInputFormat
*/
From source file com.bonc.mr_roamRecognition_hjpt.comm.PathCombineTextInputFormat.java
/**
* Input format that is a <code>CombineFileInputFormat</code>-equivalent for
* <code>TextInputFormat</code>.
*
* @see CombineFileInputFormat
*/
From source file com.cloudera.science.avro2parquet.CombinedAvroKeyInputFormat.java
/**
* A combined input format for reading Avro data.
*
* @author "Matthew Hayes"
*
* @param <T> Type of data to be read
From source file com.conversantmedia.mapreduce.input.CombineTextFileInputFormat.java
/**
* Simple implementation of a combinefile input format.
*
* Concept for FileLineWritable borrowed from:
* http://www.idryman.org/blog/2013/09/22/process-small-files-on-hadoop-using-combinefileinputformat-1/
* Needed to rewrite to work properly in new API
From source file com.conversantmedia.mapreduce.io.avro.CombineAvroKeyFileInputFormat.java
/**
* Custom implementation/extension of the combine file input format designed to
* combine small Avro files and skip any empty files or bad records.
*
* @param <T> The Avro record type
*/
From source file com.ikanow.aleph2.analytics.spark.assets.BeFileInputFormat_Pure.java
/** The file input format specific to batch enrichment modules - uses the default Hadoop CombineFileInputFormat * for cases when the Hadoop version of google.commons.base.Stopwatch is first on the classpath! * OTHERWISE IDENTICAL TO BeFileInputForm in hadoop_analytic_services * @author jfreydank */ public class BeFileInputFormat_Pure extends CombineFileInputFormat<String, Tuple2<Long, IBatchRecord>> {
From source file com.ikanow.infinit.e.data_model.custom.InfiniteFileInputFormat.java
public class InfiniteFileInputFormat extends CombineFileInputFormat<Object, BSONObject> { @Override protected boolean isSplitable(JobContext context, Path filename) { return false; }