Constructor and Description |
---|
ParseOutputFormat() |
Modifier and Type | Method and Description |
---|---|
void |
checkOutputSpecs(org.apache.hadoop.fs.FileSystem fs,
org.apache.hadoop.mapred.JobConf job) |
static String |
filterNormalize(String fromUrl,
String toUrl,
String fromHost,
boolean ignoreExternalLinks,
URLFilters filters,
URLNormalizers normalizers) |
static String |
filterNormalize(String fromUrl,
String toUrl,
String fromHost,
boolean ignoreExternalLinks,
URLFilters filters,
URLNormalizers normalizers,
String urlNormalizerScope) |
org.apache.hadoop.mapred.RecordWriter<org.apache.hadoop.io.Text,Parse> |
getRecordWriter(org.apache.hadoop.fs.FileSystem fs,
org.apache.hadoop.mapred.JobConf job,
String name,
org.apache.hadoop.util.Progressable progress) |
public void checkOutputSpecs(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.mapred.JobConf job) throws IOException
checkOutputSpecs
in interface org.apache.hadoop.mapred.OutputFormat<org.apache.hadoop.io.Text,Parse>
IOException
public org.apache.hadoop.mapred.RecordWriter<org.apache.hadoop.io.Text,Parse> getRecordWriter(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.mapred.JobConf job, String name, org.apache.hadoop.util.Progressable progress) throws IOException
getRecordWriter
in interface org.apache.hadoop.mapred.OutputFormat<org.apache.hadoop.io.Text,Parse>
IOException
public static String filterNormalize(String fromUrl, String toUrl, String fromHost, boolean ignoreExternalLinks, URLFilters filters, URLNormalizers normalizers)
public static String filterNormalize(String fromUrl, String toUrl, String fromHost, boolean ignoreExternalLinks, URLFilters filters, URLNormalizers normalizers, String urlNormalizerScope)
Copyright © 2014 The Apache Software Foundation