public static class WebGraph.OutlinkDb extends org.apache.hadoop.conf.Configured implements org.apache.hadoop.mapred.Mapper<org.apache.hadoop.io.Text,org.apache.hadoop.io.Writable,org.apache.hadoop.io.Text,NutchWritable>, org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text,NutchWritable,org.apache.hadoop.io.Text,LinkDatum>
Modifier and Type | Field and Description |
---|---|
static String |
URL_FILTERING |
static String |
URL_NORMALIZING |
Constructor and Description |
---|
WebGraph.OutlinkDb()
Default constructor.
|
WebGraph.OutlinkDb(org.apache.hadoop.conf.Configuration conf)
Configurable constructor.
|
Modifier and Type | Method and Description |
---|---|
void |
close() |
void |
configure(org.apache.hadoop.mapred.JobConf conf)
Configures the OutlinkDb job.
|
void |
map(org.apache.hadoop.io.Text key,
org.apache.hadoop.io.Writable value,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,NutchWritable> output,
org.apache.hadoop.mapred.Reporter reporter)
Passes through existing LinkDatum objects from an existing OutlinkDb and
maps out new LinkDatum objects from new crawls ParseData.
|
void |
reduce(org.apache.hadoop.io.Text key,
Iterator<NutchWritable> values,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,LinkDatum> output,
org.apache.hadoop.mapred.Reporter reporter) |
public static final String URL_NORMALIZING
public static final String URL_FILTERING
public WebGraph.OutlinkDb()
public WebGraph.OutlinkDb(org.apache.hadoop.conf.Configuration conf)
public void configure(org.apache.hadoop.mapred.JobConf conf)
configure
in interface org.apache.hadoop.mapred.JobConfigurable
public void map(org.apache.hadoop.io.Text key, org.apache.hadoop.io.Writable value, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,NutchWritable> output, org.apache.hadoop.mapred.Reporter reporter) throws IOException
map
in interface org.apache.hadoop.mapred.Mapper<org.apache.hadoop.io.Text,org.apache.hadoop.io.Writable,org.apache.hadoop.io.Text,NutchWritable>
IOException
public void reduce(org.apache.hadoop.io.Text key, Iterator<NutchWritable> values, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,LinkDatum> output, org.apache.hadoop.mapred.Reporter reporter) throws IOException
reduce
in interface org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text,NutchWritable,org.apache.hadoop.io.Text,LinkDatum>
IOException
public void close()
close
in interface Closeable
close
in interface AutoCloseable
Copyright © 2014 The Apache Software Foundation