public static class Generator.Selector extends Object implements org.apache.hadoop.mapred.Mapper<org.apache.hadoop.io.Text,CrawlDatum,org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry>, org.apache.hadoop.mapred.Partitioner<org.apache.hadoop.io.FloatWritable,org.apache.hadoop.io.Writable>, org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry,org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry>
Constructor and Description |
---|
Generator.Selector() |
Modifier and Type | Method and Description |
---|---|
void |
close() |
void |
configure(org.apache.hadoop.mapred.JobConf job) |
int |
getPartition(org.apache.hadoop.io.FloatWritable key,
org.apache.hadoop.io.Writable value,
int numReduceTasks)
Partition by host / domain or IP.
|
void |
map(org.apache.hadoop.io.Text key,
CrawlDatum value,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry> output,
org.apache.hadoop.mapred.Reporter reporter)
Select & invert subset due for fetch.
|
void |
reduce(org.apache.hadoop.io.FloatWritable key,
Iterator<Generator.SelectorEntry> values,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry> output,
org.apache.hadoop.mapred.Reporter reporter)
Collect until limit is reached.
|
public void configure(org.apache.hadoop.mapred.JobConf job)
configure
in interface org.apache.hadoop.mapred.JobConfigurable
public void close()
close
in interface Closeable
close
in interface AutoCloseable
public void map(org.apache.hadoop.io.Text key, CrawlDatum value, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry> output, org.apache.hadoop.mapred.Reporter reporter) throws IOException
map
in interface org.apache.hadoop.mapred.Mapper<org.apache.hadoop.io.Text,CrawlDatum,org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry>
IOException
public int getPartition(org.apache.hadoop.io.FloatWritable key, org.apache.hadoop.io.Writable value, int numReduceTasks)
getPartition
in interface org.apache.hadoop.mapred.Partitioner<org.apache.hadoop.io.FloatWritable,org.apache.hadoop.io.Writable>
public void reduce(org.apache.hadoop.io.FloatWritable key, Iterator<Generator.SelectorEntry> values, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry> output, org.apache.hadoop.mapred.Reporter reporter) throws IOException
reduce
in interface org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry,org.apache.hadoop.io.FloatWritable,Generator.SelectorEntry>
IOException
Copyright © 2014 The Apache Software Foundation