Index: CHANGES.txt =================================================================== --- CHANGES.txt (revision 806885) +++ CHANGES.txt (working copy) @@ -691,10 +691,10 @@ SpanNearQuery that does not need to use the payloads, you can disable loading them with a new constructor switch. (Mark Miller) -33. LUCENE-1341: Added BoostingNearQuery to enable SpanNearQuery functionality +33. LUCENE-1341: Added PayloadNearQuery to enable SpanNearQuery functionality with payloads (Peter Keegan, Grant Ingersoll, Mark Miller) -34. LUCENE-1790: Added BoostingFunctionTermQuery to enable scoring of payloads +34. LUCENE-1790: Added PayloadTermQuery to enable scoring of payloads based on the maximum payload seen for a document. Slight refactoring of Similarity and other payload queries (Grant Ingersoll) Index: src/java/org/apache/lucene/search/payloads/BoostingFunctionTermQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/BoostingFunctionTermQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/BoostingFunctionTermQuery.java (working copy) @@ -1,205 +0,0 @@ -package org.apache.lucene.search.payloads; -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You 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 org.apache.lucene.index.Term; -import org.apache.lucene.index.IndexReader; -import org.apache.lucene.index.TermPositions; -import org.apache.lucene.search.Searcher; -import org.apache.lucene.search.Scorer; -import org.apache.lucene.search.Weight; -import org.apache.lucene.search.Similarity; -import org.apache.lucene.search.Explanation; -import org.apache.lucene.search.ComplexExplanation; -import org.apache.lucene.search.spans.TermSpans; -import org.apache.lucene.search.spans.SpanTermQuery; -import org.apache.lucene.search.spans.SpanWeight; -import org.apache.lucene.search.spans.SpanScorer; - -import java.io.IOException; - -/** - * This class is very similar to {@link org.apache.lucene.search.spans.SpanTermQuery} - * except that it factors in the value of the payload located at each of the positions - * where the {@link org.apache.lucene.index.Term} occurs. - *

- * In order to take advantage of this, you must override - * {@link org.apache.lucene.search.Similarity#scorePayload(String, byte[],int,int)} - * which returns 1 by default. - *

- * Payload scores are aggregated using a pluggable {@link PayloadFunction}. - **/ -public class BoostingFunctionTermQuery extends SpanTermQuery implements PayloadQuery{ - protected PayloadFunction function; - private boolean includeSpanScore; - - public BoostingFunctionTermQuery(Term term, PayloadFunction function) { - this(term, function, true); - } - - public BoostingFunctionTermQuery(Term term, PayloadFunction function, boolean includeSpanScore) { - super(term); - this.function = function; - this.includeSpanScore = includeSpanScore; - } - - - - public Weight createWeight(Searcher searcher) throws IOException { - return new BoostingFunctionTermWeight(this, searcher); - } - - protected class BoostingFunctionTermWeight extends SpanWeight { - - public BoostingFunctionTermWeight(BoostingFunctionTermQuery query, Searcher searcher) throws IOException { - super(query, searcher); - } - - public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException { - return new BoostingFunctionSpanScorer((TermSpans) query.getSpans(reader), this, - similarity, reader.norms(query.getField())); - } - - protected class BoostingFunctionSpanScorer extends SpanScorer { - //TODO: is this the best way to allocate this? - protected byte[] payload = new byte[256]; - protected TermPositions positions; - protected float payloadScore; - protected int payloadsSeen; - - public BoostingFunctionSpanScorer(TermSpans spans, Weight weight, Similarity similarity, - byte[] norms) throws IOException { - super(spans, weight, similarity, norms); - positions = spans.getPositions(); - } - - protected boolean setFreqCurrentDoc() throws IOException { - if (!more) { - return false; - } - doc = spans.doc(); - freq = 0.0f; - payloadScore = 0; - payloadsSeen = 0; - Similarity similarity1 = getSimilarity(); - while (more && doc == spans.doc()) { - int matchLength = spans.end() - spans.start(); - - freq += similarity1.sloppyFreq(matchLength); - processPayload(similarity1); - - more = spans.next();//this moves positions to the next match in this document - } - return more || (freq != 0); - } - - - protected void processPayload(Similarity similarity) throws IOException { - if (positions.isPayloadAvailable()) { - payload = positions.getPayload(payload, 0); - payloadScore = function.currentScore(doc, term.field(), spans.start(), spans.end(), payloadsSeen, payloadScore, - similarity.scorePayload(doc, term.field(), spans.start(), spans.end(), payload, 0, positions.getPayloadLength())); - payloadsSeen++; - - } else { - //zero out the payload? - } - } - - /** - * - * @return {@link #getSpanScore()} * {@link #getPayloadScore()} - * @throws IOException - */ - public float score() throws IOException { - - return includeSpanScore ? getSpanScore() * getPayloadScore() : getPayloadScore(); - } - - /** - * Returns the SpanScorer score only. - *

- * Should not be overriden without good cause! - * - * @return the score for just the Span part w/o the payload - * @throws IOException - * - * @see #score() - */ - protected float getSpanScore() throws IOException{ - return super.score(); - } - - /** - * The score for the payload - * @return The score, as calculated by {@link PayloadFunction#docScore(int, String, int, float)} - */ - protected float getPayloadScore() { - return function.docScore(doc, term.field(), payloadsSeen, payloadScore); - } - - - public Explanation explain(final int doc) throws IOException { - ComplexExplanation result = new ComplexExplanation(); - Explanation nonPayloadExpl = super.explain(doc); - result.addDetail(nonPayloadExpl); - //QUESTION: Is there a way to avoid this skipTo call? We need to know whether to load the payload or not - Explanation payloadBoost = new Explanation(); - result.addDetail(payloadBoost); - - - float payloadScore = getPayloadScore(); - payloadBoost.setValue(payloadScore); - //GSI: I suppose we could toString the payload, but I don't think that would be a good idea - payloadBoost.setDescription("scorePayload(...)"); - result.setValue(nonPayloadExpl.getValue() * payloadScore); - result.setDescription("btq, product of:"); - result.setMatch(nonPayloadExpl.getValue()==0 ? Boolean.FALSE : Boolean.TRUE); // LUCENE-1303 - return result; - } - - } - } - - public int hashCode() { - final int prime = 31; - int result = super.hashCode(); - result = prime * result + ((function == null) ? 0 : function.hashCode()); - result = prime * result + (includeSpanScore ? 1231 : 1237); - return result; - } - - public boolean equals(Object obj) { - if (this == obj) - return true; - if (!super.equals(obj)) - return false; - if (getClass() != obj.getClass()) - return false; - BoostingFunctionTermQuery other = (BoostingFunctionTermQuery) obj; - if (function == null) { - if (other.function != null) - return false; - } else if (!function.equals(other.function)) - return false; - if (includeSpanScore != other.includeSpanScore) - return false; - return true; - } - - -} Index: src/java/org/apache/lucene/search/payloads/BoostingNearQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/BoostingNearQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/BoostingNearQuery.java (working copy) @@ -1,230 +0,0 @@ -package org.apache.lucene.search.payloads; -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You 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 org.apache.lucene.index.IndexReader; -import org.apache.lucene.search.Explanation; -import org.apache.lucene.search.Scorer; -import org.apache.lucene.search.Searcher; -import org.apache.lucene.search.Similarity; -import org.apache.lucene.search.Weight; -import org.apache.lucene.search.spans.NearSpansOrdered; -import org.apache.lucene.search.spans.NearSpansUnordered; -import org.apache.lucene.search.spans.SpanNearQuery; -import org.apache.lucene.search.spans.SpanQuery; -import org.apache.lucene.search.spans.SpanScorer; -import org.apache.lucene.search.spans.SpanWeight; -import org.apache.lucene.search.spans.Spans; -import org.apache.lucene.util.ToStringUtils; - -import java.io.IOException; -import java.util.Collection; -import java.util.Iterator; - -/** - * This class is very similar to {@link org.apache.lucene.search.spans.SpanNearQuery} except - * that it factors in the value of the payloads located at each of the positions where the - * {@link org.apache.lucene.search.spans.TermSpans} occurs. - *

- * In order to take advantage of this, you must override {@link org.apache.lucene.search.Similarity#scorePayload(String, byte[],int,int)} - * which returns 1 by default. - *

- * Payload scores are aggregated using a pluggable {@link PayloadFunction}. - * - * @see org.apache.lucene.search.Similarity#scorePayload(String, byte[], int, int) - */ - -public class BoostingNearQuery extends SpanNearQuery implements PayloadQuery { - protected String fieldName; - protected PayloadFunction function; - - public BoostingNearQuery(SpanQuery[] clauses, int slop, boolean inOrder) { - this(clauses, slop, inOrder, new AveragePayloadFunction()); - } - - public BoostingNearQuery(SpanQuery[] clauses, int slop, boolean inOrder, PayloadFunction function) { - super(clauses, slop, inOrder); - fieldName = clauses[0].getField(); // all clauses must have same field - this.function = function; - } - - - public Weight createWeight(Searcher searcher) throws IOException { - return new BoostingSpanWeight(this, searcher); - } - - public Object clone() { - int sz = clauses.size(); - SpanQuery[] newClauses = new SpanQuery[sz]; - - for (int i = 0; i < sz; i++) { - SpanQuery clause = (SpanQuery) clauses.get(i); - newClauses[i] = (SpanQuery) clause.clone(); - } - BoostingNearQuery boostingNearQuery = new BoostingNearQuery(newClauses, slop, inOrder); - boostingNearQuery.setBoost(getBoost()); - return boostingNearQuery; - } - - public String toString(String field) { - StringBuffer buffer = new StringBuffer(); - buffer.append("boostingNear(["); - Iterator i = clauses.iterator(); - while (i.hasNext()) { - SpanQuery clause = (SpanQuery)i.next(); - buffer.append(clause.toString(field)); - if (i.hasNext()) { - buffer.append(", "); - } - } - buffer.append("], "); - buffer.append(slop); - buffer.append(", "); - buffer.append(inOrder); - buffer.append(")"); - buffer.append(ToStringUtils.boost(getBoost())); - return buffer.toString(); - } - - //@Override - public int hashCode() { - final int prime = 31; - int result = super.hashCode(); - result = prime * result + ((fieldName == null) ? 0 : fieldName.hashCode()); - result = prime * result + ((function == null) ? 0 : function.hashCode()); - return result; - } - - //@Override - public boolean equals(Object obj) { - if (this == obj) - return true; - if (!super.equals(obj)) - return false; - if (getClass() != obj.getClass()) - return false; - BoostingNearQuery other = (BoostingNearQuery) obj; - if (fieldName == null) { - if (other.fieldName != null) - return false; - } else if (!fieldName.equals(other.fieldName)) - return false; - if (function == null) { - if (other.function != null) - return false; - } else if (!function.equals(other.function)) - return false; - return true; - } - - public class BoostingSpanWeight extends SpanWeight { - public BoostingSpanWeight(SpanQuery query, Searcher searcher) throws IOException { - super(query, searcher); - } - - public Scorer scorer(IndexReader reader) throws IOException { - return new BoostingSpanScorer(query.getSpans(reader), this, - similarity, - reader.norms(query.getField())); - } - - public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException { - return new BoostingSpanScorer(query.getSpans(reader), this, - similarity, - reader.norms(query.getField())); - } - } - - public class BoostingSpanScorer extends SpanScorer { - Spans spans; - - protected float payloadScore; - private int payloadsSeen; - Similarity similarity = getSimilarity(); - - protected BoostingSpanScorer(Spans spans, Weight weight, Similarity similarity, byte[] norms) - throws IOException { - super(spans, weight, similarity, norms); - this.spans = spans; - } - - // Get the payloads associated with all underlying subspans - public void getPayloads(Spans[] subSpans) throws IOException { - for (int i = 0; i < subSpans.length; i++) { - if (subSpans[i] instanceof NearSpansOrdered) { - if (((NearSpansOrdered) subSpans[i]).isPayloadAvailable()) { - processPayloads(((NearSpansOrdered) subSpans[i]).getPayload(), subSpans[i].start(), subSpans[i].end()); - } - getPayloads(((NearSpansOrdered) subSpans[i]).getSubSpans()); - } else if (subSpans[i] instanceof NearSpansUnordered) { - if (((NearSpansUnordered) subSpans[i]).isPayloadAvailable()) { - processPayloads(((NearSpansUnordered) subSpans[i]).getPayload(), subSpans[i].start(), subSpans[i].end()); - } - getPayloads(((NearSpansUnordered) subSpans[i]).getSubSpans()); - } - } - } - - /** - * By default, uses the {@link PayloadFunction} to score the payloads, but can be overridden to do other things. - * - * @param payLoads The payloads - * @param start The start position of the span being scored - * @param end The end position of the span being scored - * - * @see Spans - */ - protected void processPayloads(Collection payLoads, int start, int end) { - for (Iterator iterator = payLoads.iterator(); iterator.hasNext();) { - byte[] thePayload = (byte[]) iterator.next(); - payloadScore = function.currentScore(doc, fieldName, start, end, payloadsSeen, payloadScore, - similarity.scorePayload(doc, fieldName, spans.start(), spans.end(), thePayload, 0, thePayload.length)); - ++payloadsSeen; - } - } - - // - protected boolean setFreqCurrentDoc() throws IOException { - Spans[] spansArr = new Spans[1]; - spansArr[0] = spans; - payloadScore = 0; - payloadsSeen = 0; - getPayloads(spansArr); - return super.setFreqCurrentDoc(); - } - - public float score() throws IOException { - - return super.score() * function.docScore(doc, fieldName, payloadsSeen, payloadScore); - } - - public Explanation explain(int doc) throws IOException { - Explanation result = new Explanation(); - Explanation nonPayloadExpl = super.explain(doc); - result.addDetail(nonPayloadExpl); - Explanation payloadBoost = new Explanation(); - result.addDetail(payloadBoost); - float avgPayloadScore = (payloadsSeen > 0 ? (payloadScore / payloadsSeen) : 1); - payloadBoost.setValue(avgPayloadScore); - payloadBoost.setDescription("scorePayload(...)"); - result.setValue(nonPayloadExpl.getValue() * avgPayloadScore); - result.setDescription("bnq, product of:"); - return result; - } - } - -} Index: src/java/org/apache/lucene/search/payloads/BoostingTermQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/BoostingTermQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/BoostingTermQuery.java (working copy) @@ -37,9 +37,9 @@ * * @see org.apache.lucene.search.Similarity#scorePayload(String, byte[], int, int) * - * @deprecated See {@link org.apache.lucene.search.payloads.BoostingFunctionTermQuery} + * @deprecated See {@link org.apache.lucene.search.payloads.PayloadTermQuery} */ -public class BoostingTermQuery extends BoostingFunctionTermQuery implements PayloadQuery{ +public class BoostingTermQuery extends PayloadTermQuery { public BoostingTermQuery(Term term) { this(term, true); @@ -53,14 +53,14 @@ return new BoostingTermWeight(this, searcher); } - protected class BoostingTermWeight extends BoostingFunctionTermWeight { + protected class BoostingTermWeight extends PayloadTermWeight { public BoostingTermWeight(BoostingTermQuery query, Searcher searcher) throws IOException { super(query, searcher); } public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException { - return new BoostingFunctionSpanScorer((TermSpans) query.getSpans(reader), this, + return new PayloadTermSpanScorer((TermSpans) query.getSpans(reader), this, similarity, reader.norms(query.getField())); } Index: src/java/org/apache/lucene/search/payloads/PayloadFunction.java =================================================================== --- src/java/org/apache/lucene/search/payloads/PayloadFunction.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/PayloadFunction.java (working copy) @@ -20,10 +20,10 @@ /** - * An abstract class that defines a way for Boosting*Query instances + * An abstract class that defines a way for Payload*Query instances * to transform the cumulative effects of payload scores for a document. * - * @see org.apache.lucene.search.payloads.BoostingFunctionTermQuery for more information + * @see org.apache.lucene.search.payloads.PayloadTermQuery for more information * *

* This class and its derivations are experimental and subject to change Index: src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/PayloadNearQuery.java (working copy) @@ -1,4 +1,5 @@ package org.apache.lucene.search.payloads; + /** * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with @@ -36,37 +37,39 @@ import java.util.Iterator; /** - * This class is very similar to {@link org.apache.lucene.search.spans.SpanNearQuery} except - * that it factors in the value of the payloads located at each of the positions where the + * This class is very similar to + * {@link org.apache.lucene.search.spans.SpanNearQuery} except that it factors + * in the value of the payloads located at each of the positions where the * {@link org.apache.lucene.search.spans.TermSpans} occurs. *

- * In order to take advantage of this, you must override {@link org.apache.lucene.search.Similarity#scorePayload(String, byte[],int,int)} + * In order to take advantage of this, you must override + * {@link org.apache.lucene.search.Similarity#scorePayload(String, byte[],int,int)} * which returns 1 by default. *

* Payload scores are aggregated using a pluggable {@link PayloadFunction}. - * - * @see org.apache.lucene.search.Similarity#scorePayload(String, byte[], int, int) + * + * @see org.apache.lucene.search.Similarity#scorePayload(String, byte[], int, + * int) */ - -public class BoostingNearQuery extends SpanNearQuery implements PayloadQuery { +public class PayloadNearQuery extends SpanNearQuery { protected String fieldName; protected PayloadFunction function; - public BoostingNearQuery(SpanQuery[] clauses, int slop, boolean inOrder) { + public PayloadNearQuery(SpanQuery[] clauses, int slop, boolean inOrder) { this(clauses, slop, inOrder, new AveragePayloadFunction()); } - public BoostingNearQuery(SpanQuery[] clauses, int slop, boolean inOrder, PayloadFunction function) { + public PayloadNearQuery(SpanQuery[] clauses, int slop, boolean inOrder, + PayloadFunction function) { super(clauses, slop, inOrder); fieldName = clauses[0].getField(); // all clauses must have same field this.function = function; } - public Weight createWeight(Searcher searcher) throws IOException { - return new BoostingSpanWeight(this, searcher); + return new PayloadNearSpanWeight(this, searcher); } - + public Object clone() { int sz = clauses.size(); SpanQuery[] newClauses = new SpanQuery[sz]; @@ -75,17 +78,18 @@ SpanQuery clause = (SpanQuery) clauses.get(i); newClauses[i] = (SpanQuery) clause.clone(); } - BoostingNearQuery boostingNearQuery = new BoostingNearQuery(newClauses, slop, inOrder); + PayloadNearQuery boostingNearQuery = new PayloadNearQuery(newClauses, slop, + inOrder); boostingNearQuery.setBoost(getBoost()); return boostingNearQuery; } - + public String toString(String field) { StringBuffer buffer = new StringBuffer(); - buffer.append("boostingNear(["); + buffer.append("payloadNear(["); Iterator i = clauses.iterator(); while (i.hasNext()) { - SpanQuery clause = (SpanQuery)i.next(); + SpanQuery clause = (SpanQuery) i.next(); buffer.append(clause.toString(field)); if (i.hasNext()) { buffer.append(", "); @@ -99,8 +103,8 @@ buffer.append(ToStringUtils.boost(getBoost())); return buffer.toString(); } - - //@Override + + // @Override public int hashCode() { final int prime = 31; int result = super.hashCode(); @@ -109,7 +113,7 @@ return result; } - //@Override + // @Override public boolean equals(Object obj) { if (this == obj) return true; @@ -117,7 +121,7 @@ return false; if (getClass() != obj.getClass()) return false; - BoostingNearQuery other = (BoostingNearQuery) obj; + PayloadNearQuery other = (PayloadNearQuery) obj; if (fieldName == null) { if (other.fieldName != null) return false; @@ -131,33 +135,33 @@ return true; } - public class BoostingSpanWeight extends SpanWeight { - public BoostingSpanWeight(SpanQuery query, Searcher searcher) throws IOException { + public class PayloadNearSpanWeight extends SpanWeight { + public PayloadNearSpanWeight(SpanQuery query, Searcher searcher) + throws IOException { super(query, searcher); } public Scorer scorer(IndexReader reader) throws IOException { - return new BoostingSpanScorer(query.getSpans(reader), this, - similarity, - reader.norms(query.getField())); + return new PayloadNearSpanScorer(query.getSpans(reader), this, + similarity, reader.norms(query.getField())); } - public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException { - return new BoostingSpanScorer(query.getSpans(reader), this, - similarity, - reader.norms(query.getField())); + public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, + boolean topScorer) throws IOException { + return new PayloadNearSpanScorer(query.getSpans(reader), this, + similarity, reader.norms(query.getField())); } } - public class BoostingSpanScorer extends SpanScorer { + public class PayloadNearSpanScorer extends SpanScorer { Spans spans; - + protected float payloadScore; private int payloadsSeen; Similarity similarity = getSimilarity(); - protected BoostingSpanScorer(Spans spans, Weight weight, Similarity similarity, byte[] norms) - throws IOException { + protected PayloadNearSpanScorer(Spans spans, Weight weight, + Similarity similarity, byte[] norms) throws IOException { super(spans, weight, similarity, norms); this.spans = spans; } @@ -167,12 +171,14 @@ for (int i = 0; i < subSpans.length; i++) { if (subSpans[i] instanceof NearSpansOrdered) { if (((NearSpansOrdered) subSpans[i]).isPayloadAvailable()) { - processPayloads(((NearSpansOrdered) subSpans[i]).getPayload(), subSpans[i].start(), subSpans[i].end()); + processPayloads(((NearSpansOrdered) subSpans[i]).getPayload(), + subSpans[i].start(), subSpans[i].end()); } getPayloads(((NearSpansOrdered) subSpans[i]).getSubSpans()); } else if (subSpans[i] instanceof NearSpansUnordered) { if (((NearSpansUnordered) subSpans[i]).isPayloadAvailable()) { - processPayloads(((NearSpansUnordered) subSpans[i]).getPayload(), subSpans[i].start(), subSpans[i].end()); + processPayloads(((NearSpansUnordered) subSpans[i]).getPayload(), + subSpans[i].start(), subSpans[i].end()); } getPayloads(((NearSpansUnordered) subSpans[i]).getSubSpans()); } @@ -180,19 +186,21 @@ } /** - * By default, uses the {@link PayloadFunction} to score the payloads, but can be overridden to do other things. - * + * By default, uses the {@link PayloadFunction} to score the payloads, but + * can be overridden to do other things. + * * @param payLoads The payloads * @param start The start position of the span being scored * @param end The end position of the span being scored - * + * * @see Spans */ protected void processPayloads(Collection payLoads, int start, int end) { for (Iterator iterator = payLoads.iterator(); iterator.hasNext();) { byte[] thePayload = (byte[]) iterator.next(); - payloadScore = function.currentScore(doc, fieldName, start, end, payloadsSeen, payloadScore, - similarity.scorePayload(doc, fieldName, spans.start(), spans.end(), thePayload, 0, thePayload.length)); + payloadScore = function.currentScore(doc, fieldName, start, end, + payloadsSeen, payloadScore, similarity.scorePayload(doc, fieldName, + spans.start(), spans.end(), thePayload, 0, thePayload.length)); ++payloadsSeen; } } @@ -209,7 +217,8 @@ public float score() throws IOException { - return super.score() * function.docScore(doc, fieldName, payloadsSeen, payloadScore); + return super.score() + * function.docScore(doc, fieldName, payloadsSeen, payloadScore); } public Explanation explain(int doc) throws IOException { @@ -218,7 +227,8 @@ result.addDetail(nonPayloadExpl); Explanation payloadBoost = new Explanation(); result.addDetail(payloadBoost); - float avgPayloadScore = (payloadsSeen > 0 ? (payloadScore / payloadsSeen) : 1); + float avgPayloadScore = (payloadsSeen > 0 ? (payloadScore / payloadsSeen) + : 1); payloadBoost.setValue(avgPayloadScore); payloadBoost.setDescription("scorePayload(...)"); result.setValue(nonPayloadExpl.getValue() * avgPayloadScore); @@ -226,5 +236,5 @@ return result; } } - + } Index: src/java/org/apache/lucene/search/payloads/PayloadQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/PayloadQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/PayloadQuery.java (working copy) @@ -1,24 +0,0 @@ -package org.apache.lucene.search.payloads; -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You 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. - */ - -/** - * Marker interface indicating this Query is Payload aware. - * - **/ -public interface PayloadQuery { -} Index: src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java =================================================================== --- src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java (revision 806885) +++ src/java/org/apache/lucene/search/payloads/PayloadTermQuery.java (working copy) @@ -1,4 +1,5 @@ package org.apache.lucene.search.payloads; + /** * Licensed to the Apache Software Foundation (ASF) under one or more * contributor license agreements. See the NOTICE file distributed with @@ -33,9 +34,10 @@ import java.io.IOException; /** - * This class is very similar to {@link org.apache.lucene.search.spans.SpanTermQuery} - * except that it factors in the value of the payload located at each of the positions - * where the {@link org.apache.lucene.index.Term} occurs. + * This class is very similar to + * {@link org.apache.lucene.search.spans.SpanTermQuery} except that it factors + * in the value of the payload located at each of the positions where the + * {@link org.apache.lucene.index.Term} occurs. *

* In order to take advantage of this, you must override * {@link org.apache.lucene.search.Similarity#scorePayload(String, byte[],int,int)} @@ -43,46 +45,47 @@ *

* Payload scores are aggregated using a pluggable {@link PayloadFunction}. **/ -public class BoostingFunctionTermQuery extends SpanTermQuery implements PayloadQuery{ +public class PayloadTermQuery extends SpanTermQuery { protected PayloadFunction function; private boolean includeSpanScore; - public BoostingFunctionTermQuery(Term term, PayloadFunction function) { + public PayloadTermQuery(Term term, PayloadFunction function) { this(term, function, true); } - public BoostingFunctionTermQuery(Term term, PayloadFunction function, boolean includeSpanScore) { + public PayloadTermQuery(Term term, PayloadFunction function, + boolean includeSpanScore) { super(term); this.function = function; this.includeSpanScore = includeSpanScore; } - - public Weight createWeight(Searcher searcher) throws IOException { - return new BoostingFunctionTermWeight(this, searcher); + return new PayloadTermWeight(this, searcher); } - protected class BoostingFunctionTermWeight extends SpanWeight { + protected class PayloadTermWeight extends SpanWeight { - public BoostingFunctionTermWeight(BoostingFunctionTermQuery query, Searcher searcher) throws IOException { + public PayloadTermWeight(PayloadTermQuery query, Searcher searcher) + throws IOException { super(query, searcher); } - public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, boolean topScorer) throws IOException { - return new BoostingFunctionSpanScorer((TermSpans) query.getSpans(reader), this, - similarity, reader.norms(query.getField())); + public Scorer scorer(IndexReader reader, boolean scoreDocsInOrder, + boolean topScorer) throws IOException { + return new PayloadTermSpanScorer((TermSpans) query.getSpans(reader), + this, similarity, reader.norms(query.getField())); } - protected class BoostingFunctionSpanScorer extends SpanScorer { - //TODO: is this the best way to allocate this? + protected class PayloadTermSpanScorer extends SpanScorer { + // TODO: is this the best way to allocate this? protected byte[] payload = new byte[256]; protected TermPositions positions; protected float payloadScore; protected int payloadsSeen; - public BoostingFunctionSpanScorer(TermSpans spans, Weight weight, Similarity similarity, - byte[] norms) throws IOException { + public PayloadTermSpanScorer(TermSpans spans, Weight weight, + Similarity similarity, byte[] norms) throws IOException { super(spans, weight, similarity, norms); positions = spans.getPositions(); } @@ -102,73 +105,79 @@ freq += similarity1.sloppyFreq(matchLength); processPayload(similarity1); - more = spans.next();//this moves positions to the next match in this document + more = spans.next();// this moves positions to the next match in this + // document } return more || (freq != 0); } - protected void processPayload(Similarity similarity) throws IOException { if (positions.isPayloadAvailable()) { payload = positions.getPayload(payload, 0); - payloadScore = function.currentScore(doc, term.field(), spans.start(), spans.end(), payloadsSeen, payloadScore, - similarity.scorePayload(doc, term.field(), spans.start(), spans.end(), payload, 0, positions.getPayloadLength())); + payloadScore = function.currentScore(doc, term.field(), + spans.start(), spans.end(), payloadsSeen, payloadScore, + similarity.scorePayload(doc, term.field(), spans.start(), spans + .end(), payload, 0, positions.getPayloadLength())); payloadsSeen++; } else { - //zero out the payload? + // zero out the payload? } } /** - * + * * @return {@link #getSpanScore()} * {@link #getPayloadScore()} * @throws IOException */ public float score() throws IOException { - return includeSpanScore ? getSpanScore() * getPayloadScore() : getPayloadScore(); + return includeSpanScore ? getSpanScore() * getPayloadScore() + : getPayloadScore(); } /** * Returns the SpanScorer score only. *

* Should not be overriden without good cause! - * + * * @return the score for just the Span part w/o the payload * @throws IOException - * + * * @see #score() */ - protected float getSpanScore() throws IOException{ + protected float getSpanScore() throws IOException { return super.score(); } /** * The score for the payload - * @return The score, as calculated by {@link PayloadFunction#docScore(int, String, int, float)} + * + * @return The score, as calculated by + * {@link PayloadFunction#docScore(int, String, int, float)} */ protected float getPayloadScore() { return function.docScore(doc, term.field(), payloadsSeen, payloadScore); } - public Explanation explain(final int doc) throws IOException { ComplexExplanation result = new ComplexExplanation(); Explanation nonPayloadExpl = super.explain(doc); result.addDetail(nonPayloadExpl); - //QUESTION: Is there a way to avoid this skipTo call? We need to know whether to load the payload or not + // QUESTION: Is there a way to avoid this skipTo call? We need to know + // whether to load the payload or not Explanation payloadBoost = new Explanation(); result.addDetail(payloadBoost); - float payloadScore = getPayloadScore(); payloadBoost.setValue(payloadScore); - //GSI: I suppose we could toString the payload, but I don't think that would be a good idea + // GSI: I suppose we could toString the payload, but I don't think that + // would be a good idea payloadBoost.setDescription("scorePayload(...)"); result.setValue(nonPayloadExpl.getValue() * payloadScore); result.setDescription("btq, product of:"); - result.setMatch(nonPayloadExpl.getValue()==0 ? Boolean.FALSE : Boolean.TRUE); // LUCENE-1303 + result.setMatch(nonPayloadExpl.getValue() == 0 ? Boolean.FALSE + : Boolean.TRUE); // LUCENE-1303 return result; } @@ -190,7 +199,7 @@ return false; if (getClass() != obj.getClass()) return false; - BoostingFunctionTermQuery other = (BoostingFunctionTermQuery) obj; + PayloadTermQuery other = (PayloadTermQuery) obj; if (function == null) { if (other.function != null) return false; @@ -201,5 +210,4 @@ return true; } - } Index: src/java/org/apache/lucene/search/payloads/package.html =================================================================== --- src/java/org/apache/lucene/search/payloads/package.html (revision 806885) +++ src/java/org/apache/lucene/search/payloads/package.html (working copy) @@ -26,8 +26,8 @@

    -
  1. BoostingFunctionTermQuery -- Boost a term's score based on the value of the payload located at that term.
    2. -
  2. BoostingNearQuery -- A SpanNearQuery that factors in the value of the payloads located +
  3. PayloadTermQuery -- Boost a term's score based on the value of the payload located at that term.
    4. +
  4. PayloadNearQuery -- A SpanNearQuery that factors in the value of the payloads located at each of the positions where the spans occur.
Index: src/test/org/apache/lucene/search/payloads/BoostingFunctionTermQueryTest.java =================================================================== --- src/test/org/apache/lucene/search/payloads/BoostingFunctionTermQueryTest.java (revision 806885) +++ src/test/org/apache/lucene/search/payloads/BoostingFunctionTermQueryTest.java (working copy) @@ -1,322 +0,0 @@ -package org.apache.lucene.search.payloads; -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You 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 org.apache.lucene.util.LuceneTestCase; -import org.apache.lucene.util.English; -import org.apache.lucene.search.IndexSearcher; -import org.apache.lucene.search.QueryUtils; -import org.apache.lucene.search.TopDocs; -import org.apache.lucene.search.ScoreDoc; -import org.apache.lucene.search.CheckHits; -import org.apache.lucene.search.BooleanClause; -import org.apache.lucene.search.BooleanQuery; -import org.apache.lucene.search.DefaultSimilarity; -import org.apache.lucene.search.spans.SpanTermQuery; -import org.apache.lucene.search.spans.Spans; -import org.apache.lucene.search.spans.TermSpans; -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.LowerCaseTokenizer; -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.tokenattributes.PayloadAttribute; -import org.apache.lucene.index.Payload; -import org.apache.lucene.index.IndexWriter; -import org.apache.lucene.index.Term; -import org.apache.lucene.store.RAMDirectory; -import org.apache.lucene.document.Document; -import org.apache.lucene.document.Field; - -import java.io.Reader; -import java.io.IOException; - - -/** - * - * - **/ -public class BoostingFunctionTermQueryTest extends LuceneTestCase { - private IndexSearcher searcher; - private BoostingSimilarity similarity = new BoostingSimilarity(); - private byte[] payloadField = new byte[]{1}; - private byte[] payloadMultiField1 = new byte[]{2}; - private byte[] payloadMultiField2 = new byte[]{4}; - protected RAMDirectory directory; - - public BoostingFunctionTermQueryTest(String s) { - super(s); - } - - private class PayloadAnalyzer extends Analyzer { - - - public TokenStream tokenStream(String fieldName, Reader reader) { - TokenStream result = new LowerCaseTokenizer(reader); - result = new PayloadFilter(result, fieldName); - return result; - } - } - - private class PayloadFilter extends TokenFilter { - String fieldName; - int numSeen = 0; - - PayloadAttribute payloadAtt; - - public PayloadFilter(TokenStream input, String fieldName) { - super(input); - this.fieldName = fieldName; - payloadAtt = (PayloadAttribute) addAttribute(PayloadAttribute.class); - } - - public boolean incrementToken() throws IOException { - boolean hasNext = input.incrementToken(); - if (hasNext) { - if (fieldName.equals("field")) { - payloadAtt.setPayload(new Payload(payloadField)); - } else if (fieldName.equals("multiField")) { - if (numSeen % 2 == 0) { - payloadAtt.setPayload(new Payload(payloadMultiField1)); - } else { - payloadAtt.setPayload(new Payload(payloadMultiField2)); - } - numSeen++; - } - return true; - } else { - return false; - } - } - } - - protected void setUp() throws Exception { - super.setUp(); - directory = new RAMDirectory(); - PayloadAnalyzer analyzer = new PayloadAnalyzer(); - IndexWriter writer - = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED); - writer.setSimilarity(similarity); - //writer.infoStream = System.out; - for (int i = 0; i < 1000; i++) { - Document doc = new Document(); - Field noPayloadField = new Field(PayloadHelper.NO_PAYLOAD_FIELD, English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED); - //noPayloadField.setBoost(0); - doc.add(noPayloadField); - doc.add(new Field("field", English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED)); - doc.add(new Field("multiField", English.intToEnglish(i) + " " + English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED)); - writer.addDocument(doc); - } - writer.optimize(); - writer.close(); - - searcher = new IndexSearcher(directory, true); - searcher.setSimilarity(similarity); - } - - public void test() throws IOException { - BoostingFunctionTermQuery query = new BoostingFunctionTermQuery(new Term("field", "seventy"), - new MaxPayloadFunction()); - TopDocs hits = searcher.search(query, null, 100); - assertTrue("hits is null and it shouldn't be", hits != null); - assertTrue("hits Size: " + hits.totalHits + " is not: " + 100, hits.totalHits == 100); - - //they should all have the exact same score, because they all contain seventy once, and we set - //all the other similarity factors to be 1 - - assertTrue(hits.getMaxScore() + " does not equal: " + 1, hits.getMaxScore() == 1); - for (int i = 0; i < hits.scoreDocs.length; i++) { - ScoreDoc doc = hits.scoreDocs[i]; - assertTrue(doc.score + " does not equal: " + 1, doc.score == 1); - } - CheckHits.checkExplanations(query, PayloadHelper.FIELD, searcher, true); - Spans spans = query.getSpans(searcher.getIndexReader()); - assertTrue("spans is null and it shouldn't be", spans != null); - assertTrue("spans is not an instanceof " + TermSpans.class, spans instanceof TermSpans); - /*float score = hits.score(0); - for (int i =1; i < hits.length(); i++) - { - assertTrue("scores are not equal and they should be", score == hits.score(i)); - }*/ - - } - - public void testQuery() { - BoostingFunctionTermQuery boostingFuncTermQuery = new BoostingFunctionTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"), - new MaxPayloadFunction()); - QueryUtils.check(boostingFuncTermQuery); - - SpanTermQuery spanTermQuery = new SpanTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy")); - - assertTrue(boostingFuncTermQuery.equals(spanTermQuery) == spanTermQuery.equals(boostingFuncTermQuery)); - - BoostingFunctionTermQuery boostingFuncTermQuery2 = new BoostingFunctionTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"), - new AveragePayloadFunction()); - - QueryUtils.checkUnequal(boostingFuncTermQuery, boostingFuncTermQuery2); - } - - public void testMultipleMatchesPerDoc() throws Exception { - BoostingFunctionTermQuery query = new BoostingFunctionTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"), - new MaxPayloadFunction()); - TopDocs hits = searcher.search(query, null, 100); - assertTrue("hits is null and it shouldn't be", hits != null); - assertTrue("hits Size: " + hits.totalHits + " is not: " + 100, hits.totalHits == 100); - - //they should all have the exact same score, because they all contain seventy once, and we set - //all the other similarity factors to be 1 - - //System.out.println("Hash: " + seventyHash + " Twice Hash: " + 2*seventyHash); - assertTrue(hits.getMaxScore() + " does not equal: " + 4.0, hits.getMaxScore() == 4.0); - //there should be exactly 10 items that score a 4, all the rest should score a 2 - //The 10 items are: 70 + i*100 where i in [0-9] - int numTens = 0; - for (int i = 0; i < hits.scoreDocs.length; i++) { - ScoreDoc doc = hits.scoreDocs[i]; - if (doc.doc % 10 == 0) { - numTens++; - assertTrue(doc.score + " does not equal: " + 4.0, doc.score == 4.0); - } else { - assertTrue(doc.score + " does not equal: " + 2, doc.score == 2); - } - } - assertTrue(numTens + " does not equal: " + 10, numTens == 10); - CheckHits.checkExplanations(query, "field", searcher, true); - Spans spans = query.getSpans(searcher.getIndexReader()); - assertTrue("spans is null and it shouldn't be", spans != null); - assertTrue("spans is not an instanceof " + TermSpans.class, spans instanceof TermSpans); - //should be two matches per document - int count = 0; - //100 hits times 2 matches per hit, we should have 200 in count - while (spans.next()) { - count++; - } - assertTrue(count + " does not equal: " + 200, count == 200); - } - - //Set includeSpanScore to false, in which case just the payload score comes through. - public void testIgnoreSpanScorer() throws Exception { - BoostingFunctionTermQuery query = new BoostingFunctionTermQuery(new Term(PayloadHelper.MULTI_FIELD, "seventy"), - new MaxPayloadFunction(), false); - - IndexSearcher theSearcher = new IndexSearcher(directory, true); - theSearcher.setSimilarity(new FullSimilarity()); - TopDocs hits = searcher.search(query, null, 100); - assertTrue("hits is null and it shouldn't be", hits != null); - assertTrue("hits Size: " + hits.totalHits + " is not: " + 100, hits.totalHits == 100); - - //they should all have the exact same score, because they all contain seventy once, and we set - //all the other similarity factors to be 1 - - //System.out.println("Hash: " + seventyHash + " Twice Hash: " + 2*seventyHash); - assertTrue(hits.getMaxScore() + " does not equal: " + 4.0, hits.getMaxScore() == 4.0); - //there should be exactly 10 items that score a 4, all the rest should score a 2 - //The 10 items are: 70 + i*100 where i in [0-9] - int numTens = 0; - for (int i = 0; i < hits.scoreDocs.length; i++) { - ScoreDoc doc = hits.scoreDocs[i]; - if (doc.doc % 10 == 0) { - numTens++; - assertTrue(doc.score + " does not equal: " + 4.0, doc.score == 4.0); - } else { - assertTrue(doc.score + " does not equal: " + 2, doc.score == 2); - } - } - assertTrue(numTens + " does not equal: " + 10, numTens == 10); - CheckHits.checkExplanations(query, "field", searcher, true); - Spans spans = query.getSpans(searcher.getIndexReader()); - assertTrue("spans is null and it shouldn't be", spans != null); - assertTrue("spans is not an instanceof " + TermSpans.class, spans instanceof TermSpans); - //should be two matches per document - int count = 0; - //100 hits times 2 matches per hit, we should have 200 in count - while (spans.next()) { - count++; - } - } - - public void testNoMatch() throws Exception { - BoostingFunctionTermQuery query = new BoostingFunctionTermQuery(new Term(PayloadHelper.FIELD, "junk"), - new MaxPayloadFunction()); - TopDocs hits = searcher.search(query, null, 100); - assertTrue("hits is null and it shouldn't be", hits != null); - assertTrue("hits Size: " + hits.totalHits + " is not: " + 0, hits.totalHits == 0); - - } - - public void testNoPayload() throws Exception { - BoostingFunctionTermQuery q1 = new BoostingFunctionTermQuery(new Term(PayloadHelper.NO_PAYLOAD_FIELD, "zero"), - new MaxPayloadFunction()); - BoostingFunctionTermQuery q2 = new BoostingFunctionTermQuery(new Term(PayloadHelper.NO_PAYLOAD_FIELD, "foo"), - new MaxPayloadFunction()); - BooleanClause c1 = new BooleanClause(q1, BooleanClause.Occur.MUST); - BooleanClause c2 = new BooleanClause(q2, BooleanClause.Occur.MUST_NOT); - BooleanQuery query = new BooleanQuery(); - query.add(c1); - query.add(c2); - TopDocs hits = searcher.search(query, null, 100); - assertTrue("hits is null and it shouldn't be", hits != null); - assertTrue("hits Size: " + hits.totalHits + " is not: " + 1, hits.totalHits == 1); - int[] results = new int[1]; - results[0] = 0;//hits.scoreDocs[0].doc; - CheckHits.checkHitCollector(query, PayloadHelper.NO_PAYLOAD_FIELD, searcher, results); - } - - // must be static for weight serialization tests - static class BoostingSimilarity extends DefaultSimilarity { - - // TODO: Remove warning after API has been finalized - public float scorePayload(int docId, String fieldName, int start, int end, byte[] payload, int offset, int length) { - //we know it is size 4 here, so ignore the offset/length - return payload[0]; - } - - //!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! - //Make everything else 1 so we see the effect of the payload - //!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!! - public float lengthNorm(String fieldName, int numTerms) { - return 1; - } - - public float queryNorm(float sumOfSquaredWeights) { - return 1; - } - - public float sloppyFreq(int distance) { - return 1; - } - - public float coord(int overlap, int maxOverlap) { - return 1; - } - - public float idf(int docFreq, int numDocs) { - return 1; - } - - public float tf(float freq) { - return freq == 0 ? 0 : 1; - } - } - - static class FullSimilarity extends DefaultSimilarity{ - public float scorePayload(int docId, String fieldName, byte[] payload, int offset, int length) { - //we know it is size 4 here, so ignore the offset/length - return payload[0]; - } - } - -} Index: src/test/org/apache/lucene/search/payloads/TestBoostingNearQuery.java =================================================================== --- src/test/org/apache/lucene/search/payloads/TestBoostingNearQuery.java (revision 806885) +++ src/test/org/apache/lucene/search/payloads/TestBoostingNearQuery.java (working copy) @@ -1,221 +0,0 @@ -package org.apache.lucene.search.payloads; -/** - * Licensed to the Apache Software Foundation (ASF) under one or more - * contributor license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright ownership. - * The ASF licenses this file to You 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.io.Reader; -import java.util.Collection; - -import org.apache.lucene.analysis.Analyzer; -import org.apache.lucene.analysis.LowerCaseTokenizer; -import org.apache.lucene.analysis.Token; -import org.apache.lucene.analysis.TokenFilter; -import org.apache.lucene.analysis.TokenStream; -import org.apache.lucene.analysis.tokenattributes.PayloadAttribute; -import org.apache.lucene.document.Document; -import org.apache.lucene.document.Field; -import org.apache.lucene.index.IndexWriter; -import org.apache.lucene.index.Payload; -import org.apache.lucene.index.Term; -import org.apache.lucene.search.DefaultSimilarity; -import org.apache.lucene.search.IndexSearcher; -import org.apache.lucene.search.QueryUtils; -import org.apache.lucene.search.ScoreDoc; -import org.apache.lucene.search.Searcher; -import org.apache.lucene.search.TopDocs; -import org.apache.lucene.search.spans.SpanQuery; -import org.apache.lucene.store.RAMDirectory; -import org.apache.lucene.util.English; -import org.apache.lucene.util.LuceneTestCase; - - -public class TestBoostingNearQuery extends LuceneTestCase { - private IndexSearcher searcher; - private BoostingSimilarity similarity = new BoostingSimilarity(); - private byte[] payload2 = new byte[]{2}; - private byte[] payload4 = new byte[]{4}; - - public TestBoostingNearQuery(String s) { - super(s); - } - - private class PayloadAnalyzer extends Analyzer { - public TokenStream tokenStream(String fieldName, Reader reader) { - TokenStream result = new LowerCaseTokenizer(reader); - result = new PayloadFilter(result, fieldName); - return result; - } - } - - private class PayloadFilter extends TokenFilter { - String fieldName; - int numSeen = 0; - protected PayloadAttribute payAtt; - - public PayloadFilter(TokenStream input, String fieldName) { - super(input); - this.fieldName = fieldName; - payAtt = (PayloadAttribute) addAttribute(PayloadAttribute.class); - } - - public boolean incrementToken() throws IOException { - boolean result = false; - if (input.incrementToken() == true){ - if (numSeen % 2 == 0) { - payAtt.setPayload(new Payload(payload2)); - } else { - payAtt.setPayload(new Payload(payload4)); - } - numSeen++; - result = true; - } - return result; - } - } - - private BoostingNearQuery newPhraseQuery (String fieldName, String phrase, boolean inOrder) { - int n; - String[] words = phrase.split("[\\s]+"); - SpanQuery clauses[] = new SpanQuery[words.length]; - for (int i=0;i