You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@lucene.apache.org by dn...@apache.org on 2004/10/10 17:27:16 UTC
cvs commit: jakarta-lucene/src/java/org/apache/lucene/search MultiPhraseQuery.java PhrasePrefixQuery.java
dnaber 2004/10/10 08:27:16
Modified: src/java/org/apache/lucene/search PhrasePrefixQuery.java
Added: src/java/org/apache/lucene/search MultiPhraseQuery.java
Log:
Deprecate PhrasePrefixQuery and copy it to MultiPhraseQuery; also fix toString() in MultiPhraseQuery
Revision Changes Path
1.18 +2 -1 jakarta-lucene/src/java/org/apache/lucene/search/PhrasePrefixQuery.java
Index: PhrasePrefixQuery.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/java/org/apache/lucene/search/PhrasePrefixQuery.java,v
retrieving revision 1.17
retrieving revision 1.18
diff -u -r1.17 -r1.18
--- PhrasePrefixQuery.java 17 Sep 2004 19:24:14 -0000 1.17
+++ PhrasePrefixQuery.java 10 Oct 2004 15:27:15 -0000 1.18
@@ -34,7 +34,8 @@
* add(Term) on the term "Microsoft", then find all terms that has "app" as
* prefix using IndexReader.terms(Term), and use PhrasePrefixQuery.add(Term[]
* terms) to add them to the query.
- *
+ *
+ * @deprecated use {@link org.apache.lucene.search.MultiPhraseQuery} instead
* @author Anders Nielsen
* @version 1.0
*/
1.1 jakarta-lucene/src/java/org/apache/lucene/search/MultiPhraseQuery.java
Index: MultiPhraseQuery.java
===================================================================
package org.apache.lucene.search;
/**
* Copyright 2004 The Apache Software Foundation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.Vector;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.MultipleTermPositions;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermPositions;
import org.apache.lucene.search.Query;
/**
* MultiPhraseQuery is a generalized version of PhraseQuery, with an added
* method {@link #add(Term[])}.
* To use this class, to search for the phrase "Microsoft app*" first use
* add(Term) on the term "Microsoft", then find all terms that have "app" as
* prefix using IndexReader.terms(Term), and use MultiPhraseQuery.add(Term[]
* terms) to add them to the query.
*
* @author Anders Nielsen
* @version 1.0
*/
public class MultiPhraseQuery extends Query {
private String field;
private ArrayList termArrays = new ArrayList();
private Vector positions = new Vector();
private int slop = 0;
/** Sets the phrase slop for this query.
* @see PhraseQuery#setSlop(int)
*/
public void setSlop(int s) { slop = s; }
/** Sets the phrase slop for this query.
* @see PhraseQuery#getSlop()
*/
public int getSlop() { return slop; }
/** Add a single term at the next position in the phrase.
* @see PhraseQuery#add(Term)
*/
public void add(Term term) { add(new Term[]{term}); }
/** Add multiple terms at the next position in the phrase. Any of the terms
* may match.
*
* @see PhraseQuery#add(Term)
*/
public void add(Term[] terms) {
int position = 0;
if (positions.size() > 0)
position = ((Integer) positions.lastElement()).intValue() + 1;
add(terms, position);
}
/**
* Allows to specify the relative position of terms within the phrase.
*
* @see PhraseQuery#add(Term, int)
* @param terms
* @param position
*/
public void add(Term[] terms, int position) {
if (termArrays.size() == 0)
field = terms[0].field();
for (int i = 0; i < terms.length; i++) {
if (terms[i].field() != field) {
throw new IllegalArgumentException(
"All phrase terms must be in the same field (" + field + "): "
+ terms[i]);
}
}
termArrays.add(terms);
positions.addElement(new Integer(position));
}
/**
* Returns the relative positions of terms in this phrase.
*/
public int[] getPositions() {
int[] result = new int[positions.size()];
for (int i = 0; i < positions.size(); i++)
result[i] = ((Integer) positions.elementAt(i)).intValue();
return result;
}
private class MultiPhraseWeight implements Weight {
private Searcher searcher;
private float value;
private float idf;
private float queryNorm;
private float queryWeight;
public MultiPhraseWeight(Searcher searcher) {
this.searcher = searcher;
}
public Query getQuery() { return MultiPhraseQuery.this; }
public float getValue() { return value; }
public float sumOfSquaredWeights() throws IOException {
Iterator i = termArrays.iterator();
while (i.hasNext()) {
Term[] terms = (Term[])i.next();
for (int j=0; j<terms.length; j++)
idf += getSimilarity(searcher).idf(terms[j], searcher);
}
queryWeight = idf * getBoost(); // compute query weight
return queryWeight * queryWeight; // square it
}
public void normalize(float queryNorm) {
this.queryNorm = queryNorm;
queryWeight *= queryNorm; // normalize query weight
value = queryWeight * idf; // idf for document
}
public Scorer scorer(IndexReader reader) throws IOException {
if (termArrays.size() == 0) // optimize zero-term case
return null;
TermPositions[] tps = new TermPositions[termArrays.size()];
for (int i=0; i<tps.length; i++) {
Term[] terms = (Term[])termArrays.get(i);
TermPositions p;
if (terms.length > 1)
p = new MultipleTermPositions(reader, terms);
else
p = reader.termPositions(terms[0]);
if (p == null)
return null;
tps[i] = p;
}
if (slop == 0)
return new ExactPhraseScorer(this, tps, getPositions(), getSimilarity(searcher),
reader.norms(field));
else
return new SloppyPhraseScorer(this, tps, getPositions(), getSimilarity(searcher),
slop, reader.norms(field));
}
public Explanation explain(IndexReader reader, int doc)
throws IOException {
Explanation result = new Explanation();
result.setDescription("weight("+getQuery()+" in "+doc+"), product of:");
Explanation idfExpl = new Explanation(idf, "idf("+getQuery()+")");
// explain query weight
Explanation queryExpl = new Explanation();
queryExpl.setDescription("queryWeight(" + getQuery() + "), product of:");
Explanation boostExpl = new Explanation(getBoost(), "boost");
if (getBoost() != 1.0f)
queryExpl.addDetail(boostExpl);
queryExpl.addDetail(idfExpl);
Explanation queryNormExpl = new Explanation(queryNorm,"queryNorm");
queryExpl.addDetail(queryNormExpl);
queryExpl.setValue(boostExpl.getValue() *
idfExpl.getValue() *
queryNormExpl.getValue());
result.addDetail(queryExpl);
// explain field weight
Explanation fieldExpl = new Explanation();
fieldExpl.setDescription("fieldWeight("+getQuery()+" in "+doc+
"), product of:");
Explanation tfExpl = scorer(reader).explain(doc);
fieldExpl.addDetail(tfExpl);
fieldExpl.addDetail(idfExpl);
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.norms(field);
float fieldNorm =
fieldNorms!=null ? Similarity.decodeNorm(fieldNorms[doc]) : 0.0f;
fieldNormExpl.setValue(fieldNorm);
fieldNormExpl.setDescription("fieldNorm(field="+field+", doc="+doc+")");
fieldExpl.addDetail(fieldNormExpl);
fieldExpl.setValue(tfExpl.getValue() *
idfExpl.getValue() *
fieldNormExpl.getValue());
result.addDetail(fieldExpl);
// combine them
result.setValue(queryExpl.getValue() * fieldExpl.getValue());
if (queryExpl.getValue() == 1.0f)
return fieldExpl;
return result;
}
}
protected Weight createWeight(Searcher searcher) {
if (termArrays.size() == 1) { // optimize one-term case
Term[] terms = (Term[])termArrays.get(0);
BooleanQuery boq = new BooleanQuery();
for (int i=0; i<terms.length; i++) {
boq.add(new TermQuery(terms[i]), BooleanClause.Occur.SHOULD);
}
boq.setBoost(getBoost());
return boq.createWeight(searcher);
}
return new MultiPhraseWeight(searcher);
}
/** Prints a user-readable version of this query. */
public final String toString(String f) {
StringBuffer buffer = new StringBuffer();
if (!field.equals(f)) {
buffer.append(field);
buffer.append(":");
}
buffer.append("\"");
Iterator i = termArrays.iterator();
while (i.hasNext()) {
Term[] terms = (Term[])i.next();
if (terms.length > 1) {
buffer.append("(");
for (int j = 0; j < terms.length; j++) {
buffer.append(terms[j].text());
if (j < terms.length-1)
buffer.append(" ");
}
buffer.append(")");
} else {
buffer.append(terms[0].text());
}
if (i.hasNext())
buffer.append(" ");
}
buffer.append("\"");
if (slop != 0) {
buffer.append("~");
buffer.append(slop);
}
if (getBoost() != 1.0f) {
buffer.append("^");
buffer.append(Float.toString(getBoost()));
}
return buffer.toString();
}
}
---------------------------------------------------------------------
To unsubscribe, e-mail: lucene-dev-unsubscribe@jakarta.apache.org
For additional commands, e-mail: lucene-dev-help@jakarta.apache.org