public class KafkaETLInputFormat extends org.apache.hadoop.mapred.SequenceFileInputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
Modifier and Type | Field and Description |
---|---|
protected int |
_bufferSize |
protected kafka.consumer.SimpleConsumer |
_consumer |
protected long |
_count |
protected boolean |
_ignoreErrors |
protected org.apache.hadoop.mapred.lib.MultipleOutputs |
_mos |
protected int |
_nodeId |
protected java.util.Map<java.lang.Integer,java.net.URI> |
_nodes |
protected long |
_offset |
protected org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.BytesWritable> |
_offsetOut |
protected long[] |
_offsetRange |
protected int |
_partition |
protected Props |
_props |
protected int |
_retry |
protected int |
_soTimeout |
protected long |
_startOffset |
protected long |
_timestamp |
protected boolean |
_toContinue |
protected java.lang.String |
_topic |
Constructor and Description |
---|
KafkaETLInputFormat() |
Modifier and Type | Method and Description |
---|---|
org.apache.hadoop.mapred.RecordReader<KafkaETLKey,org.apache.hadoop.io.BytesWritable> |
getRecordReader(org.apache.hadoop.mapred.InputSplit split,
org.apache.hadoop.mapred.JobConf job,
org.apache.hadoop.mapred.Reporter reporter) |
org.apache.hadoop.mapred.InputSplit[] |
getSplits(org.apache.hadoop.mapred.JobConf conf,
int numSplits) |
protected boolean |
isSplitable(org.apache.hadoop.fs.FileSystem fs,
org.apache.hadoop.fs.Path file) |
protected Props _props
protected int _bufferSize
protected int _soTimeout
protected java.util.Map<java.lang.Integer,java.net.URI> _nodes
protected int _partition
protected int _nodeId
protected java.lang.String _topic
protected kafka.consumer.SimpleConsumer _consumer
protected org.apache.hadoop.mapred.lib.MultipleOutputs _mos
protected org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.BytesWritable,org.apache.hadoop.io.BytesWritable> _offsetOut
protected long[] _offsetRange
protected long _startOffset
protected long _offset
protected boolean _toContinue
protected int _retry
protected long _timestamp
protected long _count
protected boolean _ignoreErrors
public org.apache.hadoop.mapred.RecordReader<KafkaETLKey,org.apache.hadoop.io.BytesWritable> getRecordReader(org.apache.hadoop.mapred.InputSplit split, org.apache.hadoop.mapred.JobConf job, org.apache.hadoop.mapred.Reporter reporter) throws java.io.IOException
getRecordReader
in interface org.apache.hadoop.mapred.InputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
getRecordReader
in class org.apache.hadoop.mapred.SequenceFileInputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
java.io.IOException
protected boolean isSplitable(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.fs.Path file)
isSplitable
in class org.apache.hadoop.mapred.FileInputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
public org.apache.hadoop.mapred.InputSplit[] getSplits(org.apache.hadoop.mapred.JobConf conf, int numSplits) throws java.io.IOException
getSplits
in interface org.apache.hadoop.mapred.InputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
getSplits
in class org.apache.hadoop.mapred.FileInputFormat<KafkaETLKey,org.apache.hadoop.io.BytesWritable>
java.io.IOException