Package org.apache.nutch.parse

Class ParseOutputFormat

java.lang.Object

org.apache.hadoop.mapreduce.OutputFormat<Text,Parse>

org.apache.nutch.parse.ParseOutputFormat

public class ParseOutputFormat
extends OutputFormat<Text,Parse>

Constructor Summary

Constructors

Constructor	Description
ParseOutputFormat()

Method Summary

Modifier and Type	Method	Description
void	checkOutputSpecs(JobContext context)
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)
OutputCommitter	getOutputCommitter(TaskAttemptContext context)
RecordWriter<Text,Parse>	getRecordWriter(TaskAttemptContext context)
String	getUniqueFile(TaskAttemptContext context, String name)

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ParseOutputFormat

public ParseOutputFormat()

Method Details

getOutputCommitter

public OutputCommitter getOutputCommitter(TaskAttemptContext context)
                                   throws IOException

Specified by:

getOutputCommitter in class OutputFormat<Text,Parse>

Throws:

IOException

checkOutputSpecs

public void checkOutputSpecs(JobContext context)
                      throws IOException

Specified by:

checkOutputSpecs in class OutputFormat<Text,Parse>

Throws:

IOException

getUniqueFile

public String getUniqueFile(TaskAttemptContext context,
 String name)

getRecordWriter

public RecordWriter<Text,Parse> getRecordWriter(TaskAttemptContext context)
                                         throws IOException

Specified by:

getRecordWriter in class OutputFormat<Text,Parse>

Throws:

IOException

filterNormalize

public static String filterNormalize(String fromUrl,
 String toUrl,
 String fromHost,
 boolean ignoreInternalLinks,
 boolean ignoreExternalLinks,
 String ignoreExternalLinksMode,
 URLFilters filters,
 URLExemptionFilters exemptionFilters,
 URLNormalizers normalizers)

filterNormalize

public static String filterNormalize(String fromUrl,
 String toUrl,
 String origin,
 boolean ignoreInternalLinks,
 boolean ignoreExternalLinks,
 String ignoreExternalLinksMode,
 URLFilters filters,
 URLExemptionFilters exemptionFilters,
 URLNormalizers normalizers,
 String urlNormalizerScope)