com.hrstc.lucene
Class Utils

java.lang.Object
  com.hrstc.lucene.Utils

public class Utils
extends java.lang.Object

Field Summary

static org.apache.lucene.document.Document	doc
static int	docTermCount
static java.util.Hashtable<java.lang.String,java.lang.Float>	idfTbl
static float	maxIdf
static java.util.Vector<org.apache.lucene.search.TermQuery>	terms

Constructor Summary

Utils()

Method Summary

static float	coord(java.util.Vector<org.apache.lucene.search.TermQuery> terms, org.apache.lucene.document.Document doc, int docId, org.apache.lucene.search.Similarity similarity, org.apache.lucene.index.FilterIndexReader idxReader)
static float	getBoostNorm(org.apache.lucene.search.TermQuery termQuery, java.util.Vector<org.apache.lucene.search.TermQuery> terms) Returns normalized boost factor
static int	getDocTermCount(org.apache.lucene.document.Document doc)
static int	getDocTermCount(org.apache.lucene.document.Document doc, boolean cache)
static float	getIDF(java.lang.String termStr, org.apache.lucene.search.Searcher searcher, org.apache.lucene.search.Similarity similarity)
static float	getIDFNorm(java.lang.String termStr, java.util.Vector<org.apache.lucene.search.TermQuery> terms, org.apache.lucene.search.Searcher searcher, org.apache.lucene.search.Similarity similarity)
static float	getIDFNorm(java.lang.String termStr, java.util.Vector<org.apache.lucene.search.TermQuery> terms, org.apache.lucene.search.Searcher searcher, org.apache.lucene.search.Similarity similarity, boolean cache)
private static float	getLengthNorm(org.apache.lucene.document.Document doc, org.apache.lucene.search.Similarity similarity) Use similarity class instead
private static float	getMaxIDF(java.util.Vector<org.apache.lucene.search.TermQuery> terms, org.apache.lucene.search.Searcher searcher, org.apache.lucene.search.Similarity similarity)
static float	getTF(java.lang.String term, int docId, org.apache.lucene.index.FilterIndexReader idxReader)
static float	getTFNorm(java.lang.String termStr, org.apache.lucene.document.Document doc, int docId, org.apache.lucene.search.Similarity similarity, org.apache.lucene.index.FilterIndexReader idxReader)
static float	getTFNorm(java.lang.String termStr, org.apache.lucene.document.Document doc, int docId, org.apache.lucene.search.Similarity similarity, org.apache.lucene.index.FilterIndexReader idxReader, boolean cache)
static float	scoreTerm(org.apache.lucene.document.Document doc, java.lang.String termStr, int docId, org.apache.lucene.search.Similarity similarity, org.apache.lucene.index.FilterIndexReader idxReader, org.apache.lucene.search.Searcher searcher) score(q,d) =?(t in q) tf(t in d) * idf(t) * getBoost(t.field in d) * lengthNorm(t.field in d) * coord(q,d) * queryNorm(q)

Methods inherited from class java.lang.Object

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

Field Detail

maxIdf

public static float maxIdf

idfTbl

public static java.util.Hashtable<java.lang.String,java.lang.Float> idfTbl

terms

public static java.util.Vector<org.apache.lucene.search.TermQuery> terms

doc

public static org.apache.lucene.document.Document doc

docTermCount

public static int docTermCount

Constructor Detail

Utils

public Utils()

Method Detail

scoreTerm

public static float scoreTerm(org.apache.lucene.document.Document doc,
                              java.lang.String termStr,
                              int docId,
                              org.apache.lucene.search.Similarity similarity,
                              org.apache.lucene.index.FilterIndexReader idxReader,
                              org.apache.lucene.search.Searcher searcher)
                       throws java.io.IOException

score(q,d) =?(t in q) tf(t in d) * idf(t) * getBoost(t.field in d) * lengthNorm(t.field in d) * coord(q,d) * queryNorm(q)

Parameters:

term -

similarity -

Returns:

Throws:

java.io.IOException

getIDF

public static float getIDF(java.lang.String termStr,
                           org.apache.lucene.search.Searcher searcher,
                           org.apache.lucene.search.Similarity similarity)
                    throws java.io.IOException

Throws:

java.io.IOException

getIDFNorm

public static float getIDFNorm(java.lang.String termStr,
                               java.util.Vector<org.apache.lucene.search.TermQuery> terms,
                               org.apache.lucene.search.Searcher searcher,
                               org.apache.lucene.search.Similarity similarity)
                        throws java.io.IOException

Throws:

java.io.IOException

getIDFNorm

public static float getIDFNorm(java.lang.String termStr,
                               java.util.Vector<org.apache.lucene.search.TermQuery> terms,
                               org.apache.lucene.search.Searcher searcher,
                               org.apache.lucene.search.Similarity similarity,
                               boolean cache)
                        throws java.io.IOException

Parameters:

termStr -

terms -

searcher -

similarity -

cache - - indicates if values will be cached

Returns:

Throws:

java.io.IOException

getMaxIDF

private static float getMaxIDF(java.util.Vector<org.apache.lucene.search.TermQuery> terms,
                               org.apache.lucene.search.Searcher searcher,
                               org.apache.lucene.search.Similarity similarity)
                        throws java.io.IOException

Throws:

java.io.IOException

getLengthNorm

private static float getLengthNorm(org.apache.lucene.document.Document doc,
                                   org.apache.lucene.search.Similarity similarity)

Use similarity class instead

getTFNorm

public static float getTFNorm(java.lang.String termStr,
                              org.apache.lucene.document.Document doc,
                              int docId,
                              org.apache.lucene.search.Similarity similarity,
                              org.apache.lucene.index.FilterIndexReader idxReader)
                       throws java.io.IOException

Throws:

java.io.IOException

getTFNorm

public static float getTFNorm(java.lang.String termStr,
                              org.apache.lucene.document.Document doc,
                              int docId,
                              org.apache.lucene.search.Similarity similarity,
                              org.apache.lucene.index.FilterIndexReader idxReader,
                              boolean cache)
                       throws java.io.IOException

Returns:

tf * lengthNorm = [0;1]

Throws:

java.io.IOException

getDocTermCount

public static int getDocTermCount(org.apache.lucene.document.Document doc)

getDocTermCount

public static int getDocTermCount(org.apache.lucene.document.Document doc,
                                  boolean cache)

getTF

public static float getTF(java.lang.String term,
                          int docId,
                          org.apache.lucene.index.FilterIndexReader idxReader)
                   throws java.io.IOException

Throws:

java.io.IOException

coord

public static float coord(java.util.Vector<org.apache.lucene.search.TermQuery> terms,
                          org.apache.lucene.document.Document doc,
                          int docId,
                          org.apache.lucene.search.Similarity similarity,
                          org.apache.lucene.index.FilterIndexReader idxReader)
                   throws java.io.IOException

Throws:

java.io.IOException

getBoostNorm

public static float getBoostNorm(org.apache.lucene.search.TermQuery termQuery,
                                 java.util.Vector<org.apache.lucene.search.TermQuery> terms)

Returns normalized boost factor

Parameters:

termQuery -

terms -

Returns: