public class BitPostingIndexInputFormat extends org.apache.hadoop.mapred.FileInputFormat<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>>
Constructor and Description |
---|
BitPostingIndexInputFormat() |
Modifier and Type | Method and Description |
---|---|
protected long |
getBlockSize(org.apache.hadoop.fs.Path path,
org.apache.hadoop.fs.FileStatus fss)
Returns the block size of the specified file.
|
org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>> |
getRecordReader(org.apache.hadoop.mapred.InputSplit _split,
org.apache.hadoop.mapred.JobConf job,
org.apache.hadoop.mapred.Reporter reporter)
Get a record reader for the specified split
|
static int |
getSplit_EntryCount(org.apache.hadoop.mapred.InputSplit s)
Returns the number of entries in specified split
|
static int |
getSplit_StartingEntryIndex(org.apache.hadoop.mapred.InputSplit s)
Provides the starting entry id for the specified split
|
org.apache.hadoop.mapred.InputSplit[] |
getSplits(org.apache.hadoop.mapred.JobConf job,
int numSplits) |
static void |
main(String[] args)
Test method, runs splits for inverted/lexicon with the command line specified index
|
static void |
setStructures(org.apache.hadoop.mapred.JobConf jc,
String bitStructureName,
String lookupStructureName)
Save in the JobConf, the names of the bit and pointer lookup structures that this inputformat should look for
|
void |
validateInput(org.apache.hadoop.mapred.JobConf job)
Checks to see if required keys are present
|
public org.apache.hadoop.mapred.RecordReader<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>> getRecordReader(org.apache.hadoop.mapred.InputSplit _split, org.apache.hadoop.mapred.JobConf job, org.apache.hadoop.mapred.Reporter reporter) throws IOException
getRecordReader
in interface org.apache.hadoop.mapred.InputFormat<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>>
getRecordReader
in class org.apache.hadoop.mapred.FileInputFormat<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>>
IOException
protected long getBlockSize(org.apache.hadoop.fs.Path path, org.apache.hadoop.fs.FileStatus fss)
public org.apache.hadoop.mapred.InputSplit[] getSplits(org.apache.hadoop.mapred.JobConf job, int numSplits) throws IOException
getSplits
in interface org.apache.hadoop.mapred.InputFormat<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>>
getSplits
in class org.apache.hadoop.mapred.FileInputFormat<org.apache.hadoop.io.IntWritable,Wrapper.IntObjectWrapper<IterablePosting>>
IOException
public void validateInput(org.apache.hadoop.mapred.JobConf job) throws IOException
IOException
public static int getSplit_StartingEntryIndex(org.apache.hadoop.mapred.InputSplit s)
public static int getSplit_EntryCount(org.apache.hadoop.mapred.InputSplit s)
public static void setStructures(org.apache.hadoop.mapred.JobConf jc, String bitStructureName, String lookupStructureName)
Terrier 4.0. Copyright © 2004-2014 University of Glasgow