public class ParseOutputFormat extends Object implements OutputFormat<Text,Parse>
Constructor and Description |
---|
ParseOutputFormat() |
Modifier and Type | Method and Description |
---|---|
void |
checkOutputSpecs(FileSystem fs,
JobConf job) |
static String |
filterNormalize(String fromUrl,
String toUrl,
String fromHost,
boolean ignoreInternalLinks,
boolean ignoreExternalLinks,
String ignoreExternalLinksMode,
URLFilters filters,
URLExemptionFilters exemptionFilters,
URLNormalizers normalizers) |
static String |
filterNormalize(String fromUrl,
String toUrl,
String origin,
boolean ignoreInternalLinks,
boolean ignoreExternalLinks,
String ignoreExternalLinksMode,
URLFilters filters,
URLExemptionFilters exemptionFilters,
URLNormalizers normalizers,
String urlNormalizerScope) |
RecordWriter<Text,Parse> |
getRecordWriter(FileSystem fs,
JobConf job,
String name,
Progressable progress) |
public void checkOutputSpecs(FileSystem fs, JobConf job) throws IOException
checkOutputSpecs
in interface OutputFormat<Text,Parse>
IOException
public RecordWriter<Text,Parse> getRecordWriter(FileSystem fs, JobConf job, String name, Progressable progress) throws IOException
getRecordWriter
in interface OutputFormat<Text,Parse>
IOException
public static String filterNormalize(String fromUrl, String toUrl, String fromHost, boolean ignoreInternalLinks, boolean ignoreExternalLinks, String ignoreExternalLinksMode, URLFilters filters, URLExemptionFilters exemptionFilters, URLNormalizers normalizers)
public static String filterNormalize(String fromUrl, String toUrl, String origin, boolean ignoreInternalLinks, boolean ignoreExternalLinks, String ignoreExternalLinksMode, URLFilters filters, URLExemptionFilters exemptionFilters, URLNormalizers normalizers, String urlNormalizerScope)
Copyright © 2016 The Apache Software Foundation