Package org.codelibs.fess.helper

Class DocumentHelper

java.lang.Object

org.codelibs.fess.helper.DocumentHelper

public class DocumentHelper
extends Object

Field Summary

Fields

Modifier and Type	Field	Description
protected static String	SIMILAR_DOC_HASH_PREFIX

Constructor Summary

Constructors

Constructor	Description
DocumentHelper()

Method Summary

Modifier and Type	Method	Description
String	appendLineNumber(String prefix, String content)
String	decodeSimilarDocHash(String hash)
String	encodeSimilarDocHash(String hash)
String	getContent(CrawlingConfig crawlingConfig, org.codelibs.fess.crawler.entity.ResponseData responseData, String content, Map<String,Object> dataMap)
String	getDigest(org.codelibs.fess.crawler.entity.ResponseData responseData, String content, Map<String,Object> dataMap, int maxWidth)
protected int	getMaxAlphanumTermSize()
protected int	getMaxSymbolTermSize()
protected int[]	getSpaceChars()
String	getTitle(org.codelibs.fess.crawler.entity.ResponseData responseData, String title, Map<String,Object> dataMap)
void	init()
protected boolean	isDuplicateTermRemoved()
Map<String,Object>	processRequest(CrawlingConfig crawlingConfig, String crawlingInfoId, String url)

Methods inherited from class java.lang.Object

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

Field Detail

SIMILAR_DOC_HASH_PREFIX

protected static final String SIMILAR_DOC_HASH_PREFIX

See Also:

Constant Field Values

Constructor Detail

DocumentHelper

public DocumentHelper()

Method Detail

init

@PostConstruct
public void init()

getTitle

public String getTitle(org.codelibs.fess.crawler.entity.ResponseData responseData,
                       String title,
                       Map<String,Object> dataMap)

getContent

public String getContent(CrawlingConfig crawlingConfig,
                         org.codelibs.fess.crawler.entity.ResponseData responseData,
                         String content,
                         Map<String,Object> dataMap)

getMaxAlphanumTermSize

protected int getMaxAlphanumTermSize()

getMaxSymbolTermSize

protected int getMaxSymbolTermSize()

isDuplicateTermRemoved

protected boolean isDuplicateTermRemoved()

getSpaceChars

protected int[] getSpaceChars()

getDigest

public String getDigest(org.codelibs.fess.crawler.entity.ResponseData responseData,
                        String content,
                        Map<String,Object> dataMap,
                        int maxWidth)

processRequest

public Map<String,Object> processRequest(CrawlingConfig crawlingConfig,
                                               String crawlingInfoId,
                                               String url)

decodeSimilarDocHash

public String decodeSimilarDocHash(String hash)

encodeSimilarDocHash

public String encodeSimilarDocHash(String hash)

appendLineNumber

public String appendLineNumber(String prefix,
                               String content)