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 and Description
ParseOutputFormat()

Method Summary

Modifier and Type	Method and Description
void	checkOutputSpecs(JobContext context)
static java.lang.String	filterNormalize(java.lang.String fromUrl, java.lang.String toUrl, java.lang.String fromHost, boolean ignoreInternalLinks, boolean ignoreExternalLinks, java.lang.String ignoreExternalLinksMode, URLFilters filters, URLExemptionFilters exemptionFilters, URLNormalizers normalizers)
static java.lang.String	filterNormalize(java.lang.String fromUrl, java.lang.String toUrl, java.lang.String origin, boolean ignoreInternalLinks, boolean ignoreExternalLinks, java.lang.String ignoreExternalLinksMode, URLFilters filters, URLExemptionFilters exemptionFilters, URLNormalizers normalizers, java.lang.String urlNormalizerScope)
OutputCommitter	getOutputCommitter(TaskAttemptContext context)
RecordWriter<Text,Parse>	getRecordWriter(TaskAttemptContext context)
java.lang.String	getUniqueFile(TaskAttemptContext context, java.lang.String name)

Methods inherited from class java.lang.Object

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

Constructor Detail

ParseOutputFormat

public ParseOutputFormat()

Method Detail

getOutputCommitter

public OutputCommitter getOutputCommitter(TaskAttemptContext context)
                                   throws java.io.IOException

Specified by:

getOutputCommitter in class OutputFormat<Text,Parse>

Throws:

java.io.IOException

checkOutputSpecs

public void checkOutputSpecs(JobContext context)
                      throws java.io.IOException

Specified by:

checkOutputSpecs in class OutputFormat<Text,Parse>

Throws:

java.io.IOException

getUniqueFile

public java.lang.String getUniqueFile(TaskAttemptContext context,
                                      java.lang.String name)

getRecordWriter

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

Specified by:

getRecordWriter in class OutputFormat<Text,Parse>

Throws:

java.io.IOException

filterNormalize

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

filterNormalize

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