public class CrawlDBScanner extends org.apache.hadoop.conf.Configured implements org.apache.hadoop.util.Tool, org.apache.hadoop.mapred.Mapper<org.apache.hadoop.io.Text,CrawlDatum,org.apache.hadoop.io.Text,CrawlDatum>, org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text,CrawlDatum,org.apache.hadoop.io.Text,CrawlDatum>
Modifier and Type | Field and Description |
---|---|
static org.slf4j.Logger |
LOG |
Constructor and Description |
---|
CrawlDBScanner() |
CrawlDBScanner(org.apache.hadoop.conf.Configuration conf) |
Modifier and Type | Method and Description |
---|---|
void |
close() |
void |
configure(org.apache.hadoop.mapred.JobConf job) |
static void |
main(String[] args) |
void |
map(org.apache.hadoop.io.Text url,
CrawlDatum crawlDatum,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,CrawlDatum> output,
org.apache.hadoop.mapred.Reporter reporter) |
void |
reduce(org.apache.hadoop.io.Text key,
Iterator<CrawlDatum> values,
org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,CrawlDatum> output,
org.apache.hadoop.mapred.Reporter reporter) |
int |
run(String[] args) |
public CrawlDBScanner()
public CrawlDBScanner(org.apache.hadoop.conf.Configuration conf)
public void close()
close
in interface Closeable
close
in interface AutoCloseable
public void configure(org.apache.hadoop.mapred.JobConf job)
configure
in interface org.apache.hadoop.mapred.JobConfigurable
public void map(org.apache.hadoop.io.Text url, CrawlDatum crawlDatum, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,CrawlDatum> 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.Text,CrawlDatum>
IOException
public void reduce(org.apache.hadoop.io.Text key, Iterator<CrawlDatum> values, org.apache.hadoop.mapred.OutputCollector<org.apache.hadoop.io.Text,CrawlDatum> output, org.apache.hadoop.mapred.Reporter reporter) throws IOException
reduce
in interface org.apache.hadoop.mapred.Reducer<org.apache.hadoop.io.Text,CrawlDatum,org.apache.hadoop.io.Text,CrawlDatum>
IOException
Copyright © 2013 The Apache Software Foundation