Package org.codelibs.fess.helper
Class DocumentHelper
- java.lang.Object
-
- org.codelibs.fess.helper.DocumentHelper
-
public class DocumentHelper extends java.lang.Object
-
-
Field Summary
Fields Modifier and Type Field Description protected static java.lang.StringSIMILAR_DOC_HASH_PREFIX
-
Constructor Summary
Constructors Constructor Description DocumentHelper()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description java.lang.StringdecodeSimilarDocHash(java.lang.String hash)java.lang.StringencodeSimilarDocHash(java.lang.String hash)java.lang.StringgetContent(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String content, java.util.Map<java.lang.String,java.lang.Object> dataMap)java.lang.StringgetDigest(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String content, java.util.Map<java.lang.String,java.lang.Object> dataMap, int maxWidth)protected intgetMaxAlphanumTermSize()protected intgetMaxSymbolTermSize()protected int[]getSpaceChars()java.lang.StringgetTitle(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String title, java.util.Map<java.lang.String,java.lang.Object> dataMap)protected booleanisDuplicateTermRemoved()java.util.Map<java.lang.String,java.lang.Object>processRequest(CrawlingConfig crawlingConfig, java.lang.String crawlingInfoId, java.lang.String url)
-
-
-
Field Detail
-
SIMILAR_DOC_HASH_PREFIX
protected static final java.lang.String SIMILAR_DOC_HASH_PREFIX
- See Also:
- Constant Field Values
-
-
Method Detail
-
getTitle
public java.lang.String getTitle(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String title, java.util.Map<java.lang.String,java.lang.Object> dataMap)
-
getContent
public java.lang.String getContent(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String content, java.util.Map<java.lang.String,java.lang.Object> dataMap)
-
getMaxAlphanumTermSize
protected int getMaxAlphanumTermSize()
-
getMaxSymbolTermSize
protected int getMaxSymbolTermSize()
-
isDuplicateTermRemoved
protected boolean isDuplicateTermRemoved()
-
getSpaceChars
protected int[] getSpaceChars()
-
getDigest
public java.lang.String getDigest(org.codelibs.fess.crawler.entity.ResponseData responseData, java.lang.String content, java.util.Map<java.lang.String,java.lang.Object> dataMap, int maxWidth)
-
processRequest
public java.util.Map<java.lang.String,java.lang.Object> processRequest(CrawlingConfig crawlingConfig, java.lang.String crawlingInfoId, java.lang.String url)
-
decodeSimilarDocHash
public java.lang.String decodeSimilarDocHash(java.lang.String hash)
-
encodeSimilarDocHash
public java.lang.String encodeSimilarDocHash(java.lang.String hash)
-
-