You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by gs...@apache.org on 2010/10/11 16:37:17 UTC
svn commit: r1021357 - in /lucene/dev/trunk/lucene: ./
src/java/org/apache/lucene/search/spans/ src/java/org/apache/lucene/util/
src/test/org/apache/lucene/analysis/ src/test/org/apache/lucene/search/
src/test/org/apache/lucene/search/spans/
Author: gsingers
Date: Mon Oct 11 14:37:16 2010
New Revision: 1021357
URL: http://svn.apache.org/viewvc?rev=1021357&view=rev
Log:
LUCENE-2692: add some new SpanQuery classes
Added:
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearPayloadCheckQuery.java
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPayloadCheckQuery.java
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionCheckQuery.java
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionRangeQuery.java
lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockPayloadAnalyzer.java
Modified:
lucene/dev/trunk/lucene/CHANGES.txt
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanFirstQuery.java
lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearQuery.java
lucene/dev/trunk/lucene/src/java/org/apache/lucene/util/ToStringUtils.java
lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockAnalyzer.java
lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPositionIncrement.java
lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/spans/TestBasics.java
Modified: lucene/dev/trunk/lucene/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/CHANGES.txt?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/CHANGES.txt (original)
+++ lucene/dev/trunk/lucene/CHANGES.txt Mon Oct 11 14:37:16 2010
@@ -261,6 +261,9 @@ New features
pretend it's an atomic reader. This is a convenience class (you can
use MultiFields static methods directly, instead) if you need to use
the flex APIs directly on a composite reader. (Mike McCandless)
+
+* LUCENE-2692: Added several new SpanQuery classes for positional checking
+ (match is in a range, payload is a specific value) (Grant Ingersoll)
Optimizations
Modified: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanFirstQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanFirstQuery.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanFirstQuery.java (original)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanFirstQuery.java Mon Oct 11 14:37:16 2010
@@ -17,37 +17,30 @@ package org.apache.lucene.search.spans;
* limitations under the License.
*/
-import java.io.IOException;
-
-import java.util.Collection;
-import java.util.Set;
-import java.util.ArrayList;
-
-import org.apache.lucene.index.IndexReader;
-import org.apache.lucene.index.Term;
-import org.apache.lucene.search.Query;
import org.apache.lucene.util.ToStringUtils;
-/** Matches spans near the beginning of a field. */
-public class SpanFirstQuery extends SpanQuery implements Cloneable {
- private SpanQuery match;
- private int end;
+import java.io.IOException;
+
+/** Matches spans near the beginning of a field.
+ * <p/>
+ * This class is a simple extension of {@link SpanPositionRangeQuery} in that it assumes the
+ * start to be zero and only checks the end boundary.
+ *
+ *
+ * */
+public class SpanFirstQuery extends SpanPositionRangeQuery {
/** Construct a SpanFirstQuery matching spans in <code>match</code> whose end
* position is less than or equal to <code>end</code>. */
public SpanFirstQuery(SpanQuery match, int end) {
- this.match = match;
- this.end = end;
+ super(match, 0, end);
}
- /** Return the SpanQuery whose matches are filtered. */
- public SpanQuery getMatch() { return match; }
-
- /** Return the maximum end position permitted in a match. */
- public int getEnd() { return end; }
-
@Override
- public String getField() { return match.getField(); }
+ protected boolean acceptPosition(Spans spans) throws IOException {
+ return spans.end() <= end;
+ }
+
@Override
public String toString(String field) {
@@ -60,89 +53,13 @@ public class SpanFirstQuery extends Span
buffer.append(ToStringUtils.boost(getBoost()));
return buffer.toString();
}
-
+
@Override
public Object clone() {
SpanFirstQuery spanFirstQuery = new SpanFirstQuery((SpanQuery) match.clone(), end);
spanFirstQuery.setBoost(getBoost());
return spanFirstQuery;
}
-
- @Override
- public void extractTerms(Set<Term> terms) {
- match.extractTerms(terms);
- }
-
- @Override
- public Spans getSpans(final IndexReader reader) throws IOException {
- return new Spans() {
- private Spans spans = match.getSpans(reader);
-
- @Override
- public boolean next() throws IOException {
- while (spans.next()) { // scan to next match
- if (end() <= end)
- return true;
- }
- return false;
- }
-
- @Override
- public boolean skipTo(int target) throws IOException {
- if (!spans.skipTo(target))
- return false;
-
- return spans.end() <= end || next();
-
- }
-
- @Override
- public int doc() { return spans.doc(); }
- @Override
- public int start() { return spans.start(); }
- @Override
- public int end() { return spans.end(); }
-
- // TODO: Remove warning after API has been finalized
- @Override
- public Collection<byte[]> getPayload() throws IOException {
- ArrayList<byte[]> result = null;
- if (spans.isPayloadAvailable()) {
- result = new ArrayList<byte[]>(spans.getPayload());
- }
- return result;//TODO: any way to avoid the new construction?
- }
-
- // TODO: Remove warning after API has been finalized
- @Override
- public boolean isPayloadAvailable() {
- return spans.isPayloadAvailable();
- }
-
- @Override
- public String toString() {
- return "spans(" + SpanFirstQuery.this.toString() + ")";
- }
-
- };
- }
-
- @Override
- public Query rewrite(IndexReader reader) throws IOException {
- SpanFirstQuery clone = null;
-
- SpanQuery rewritten = (SpanQuery) match.rewrite(reader);
- if (rewritten != match) {
- clone = (SpanFirstQuery) this.clone();
- clone.match = rewritten;
- }
-
- if (clone != null) {
- return clone; // some clauses rewrote
- } else {
- return this; // no clauses rewrote
- }
- }
@Override
public boolean equals(Object o) {
Added: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearPayloadCheckQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearPayloadCheckQuery.java?rev=1021357&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearPayloadCheckQuery.java (added)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearPayloadCheckQuery.java Mon Oct 11 14:37:16 2010
@@ -0,0 +1,117 @@
+package org.apache.lucene.search.spans;
+/**
+ * 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.ToStringUtils;
+
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.Iterator;
+
+
+/**
+ * Only return those matches that have a specific payload at
+ * the given position.
+ * <p/>
+ *
+ */
+public class SpanNearPayloadCheckQuery extends SpanPositionCheckQuery {
+ protected final Collection<byte[]> payloadToMatch;
+
+ /**
+ * @param match The underlying {@link SpanQuery} to check
+ * @param payloadToMatch The {@link java.util.Collection} of payloads to match
+ */
+ public SpanNearPayloadCheckQuery(SpanNearQuery match, Collection<byte[]> payloadToMatch) {
+ super(match);
+ this.payloadToMatch = payloadToMatch;
+ }
+
+ @Override
+ protected boolean acceptPosition(Spans spans) throws IOException {
+ boolean result = spans.isPayloadAvailable();
+ if (result == true) {
+ Collection<byte[]> candidate = spans.getPayload();
+ if (candidate.size() == payloadToMatch.size()) {
+ //TODO: check the byte arrays are the same
+ //hmm, can't rely on order here
+ int matches = 0;
+ for (byte[] candBytes : candidate) {
+ //Unfortunately, we can't rely on order, so we need to compare all
+ for (byte[] payBytes : payloadToMatch) {
+ if (Arrays.equals(candBytes, payBytes) == true) {
+ matches++;
+ break;
+ }
+ }
+ }
+ if (matches == payloadToMatch.size()){
+ //we've verified all the bytes
+ return true;
+ } else {
+ return false;
+ }
+ } else {
+ return false;
+ }
+ }
+ return false;
+ }
+
+ public String toString(String field) {
+ StringBuilder buffer = new StringBuilder();
+ buffer.append("spanPayCheck(");
+ buffer.append(match.toString(field));
+ buffer.append(", payloadRef: ");
+ for (byte[] bytes : payloadToMatch) {
+ ToStringUtils.byteArray(buffer, bytes);
+ buffer.append(';');
+ }
+ buffer.append(")");
+ buffer.append(ToStringUtils.boost(getBoost()));
+ return buffer.toString();
+ }
+
+ @Override
+ public Object clone() {
+ SpanNearPayloadCheckQuery result = new SpanNearPayloadCheckQuery((SpanNearQuery) match.clone(), payloadToMatch);
+ result.setBoost(getBoost());
+ return result;
+ }
+
+ @Override
+ public boolean equals(Object o) {
+ if (this == o) return true;
+ if (!(o instanceof SpanNearPayloadCheckQuery)) return false;
+
+ SpanNearPayloadCheckQuery other = (SpanNearPayloadCheckQuery) o;
+ return this.payloadToMatch.equals(other.payloadToMatch)
+ && this.match.equals(other.match)
+ && this.getBoost() == other.getBoost();
+ }
+
+ @Override
+ public int hashCode() {
+ int h = match.hashCode();
+ h ^= (h << 8) | (h >>> 25); // reversible
+ //TODO: is this right?
+ h ^= payloadToMatch.hashCode();
+ h ^= Float.floatToRawIntBits(getBoost());
+ return h;
+ }
+}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearQuery.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearQuery.java (original)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanNearQuery.java Mon Oct 11 14:37:16 2010
@@ -45,7 +45,11 @@ public class SpanNearQuery extends SpanQ
/** Construct a SpanNearQuery. Matches spans matching a span from each
* clause, with up to <code>slop</code> total unmatched positions between
* them. * When <code>inOrder</code> is true, the spans from each clause
- * must be * ordered as in <code>clauses</code>. */
+ * must be * ordered as in <code>clauses</code>.
+ * @param clauses the clauses to find near each other
+ * @param slop The slop value
+ * @param inOrder true if order is important
+ * */
public SpanNearQuery(SpanQuery[] clauses, int slop, boolean inOrder) {
this(clauses, slop, inOrder, true);
}
Added: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPayloadCheckQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPayloadCheckQuery.java?rev=1021357&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPayloadCheckQuery.java (added)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPayloadCheckQuery.java Mon Oct 11 14:37:16 2010
@@ -0,0 +1,118 @@
+package org.apache.lucene.search.spans;
+/**
+ * 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.ToStringUtils;
+
+import java.io.IOException;
+import java.util.Arrays;
+import java.util.Collection;
+import java.util.Iterator;
+
+
+/**
+ * Only return those matches that have a specific payload at
+ * the given position.
+ *<p/>
+ * Do not use this with an SpanQuery that contains a {@link org.apache.lucene.search.spans.SpanNearQuery}. Instead, use
+ * {@link SpanNearPayloadCheckQuery} since it properly handles the fact that payloads
+ * aren't ordered by {@link org.apache.lucene.search.spans.SpanNearQuery}.
+ *
+ **/
+public class SpanPayloadCheckQuery extends SpanPositionCheckQuery{
+ protected final Collection<byte[]> payloadToMatch;
+
+ /**
+ *
+ * @param match The underlying {@link org.apache.lucene.search.spans.SpanQuery} to check
+ * @param payloadToMatch The {@link java.util.Collection} of payloads to match
+ */
+ public SpanPayloadCheckQuery(SpanQuery match, Collection<byte[]> payloadToMatch) {
+ super(match);
+ if (match instanceof SpanNearQuery){
+ throw new IllegalArgumentException("SpanNearQuery not allowed");
+ }
+ this.payloadToMatch = payloadToMatch;
+ }
+
+ @Override
+ protected boolean acceptPosition(Spans spans) throws IOException {
+ boolean result = spans.isPayloadAvailable();
+ if (result == true){
+ Collection<byte[]> candidate = spans.getPayload();
+ if (candidate.size() == payloadToMatch.size()){
+ //TODO: check the byte arrays are the same
+ Iterator<byte[]> toMatchIter = payloadToMatch.iterator();
+ //check each of the byte arrays, in order
+ //hmm, can't rely on order here
+ for (byte[] candBytes : candidate) {
+ //if one is a mismatch, then return false
+ if (Arrays.equals(candBytes, toMatchIter.next()) == false){
+ return false;
+ }
+ }
+ //we've verified all the bytes
+ return true;
+ } else {
+ return false;
+ }
+ }
+ return result;
+ }
+
+ public String toString(String field) {
+ StringBuilder buffer = new StringBuilder();
+ buffer.append("spanPayCheck(");
+ buffer.append(match.toString(field));
+ buffer.append(", payloadRef: ");
+ for (byte[] bytes : payloadToMatch) {
+ ToStringUtils.byteArray(buffer, bytes);
+ buffer.append(';');
+ }
+ buffer.append(")");
+ buffer.append(ToStringUtils.boost(getBoost()));
+ return buffer.toString();
+ }
+
+ @Override
+ public Object clone() {
+ SpanPayloadCheckQuery result = new SpanPayloadCheckQuery((SpanQuery) match.clone(), payloadToMatch);
+ result.setBoost(getBoost());
+ return result;
+ }
+
+ @Override
+ public boolean equals(Object o) {
+ if (this == o) return true;
+ if (!(o instanceof SpanPayloadCheckQuery)) return false;
+
+ SpanPayloadCheckQuery other = (SpanPayloadCheckQuery)o;
+ return this.payloadToMatch.equals(other.payloadToMatch)
+ && this.match.equals(other.match)
+ && this.getBoost() == other.getBoost();
+ }
+
+ @Override
+ public int hashCode() {
+ int h = match.hashCode();
+ h ^= (h << 8) | (h >>> 25); // reversible
+ //TODO: is this right?
+ h ^= payloadToMatch.hashCode();
+ h ^= Float.floatToRawIntBits(getBoost()) ;
+ return h;
+ }
+}
\ No newline at end of file
Added: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionCheckQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionCheckQuery.java?rev=1021357&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionCheckQuery.java (added)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionCheckQuery.java Mon Oct 11 14:37:16 2010
@@ -0,0 +1,183 @@
+package org.apache.lucene.search.spans;
+/**
+ * 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.index.Term;
+import org.apache.lucene.search.Query;
+
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Set;
+
+
+/**
+ *
+ *
+ **/
+public abstract class SpanPositionCheckQuery extends SpanQuery implements Cloneable {
+ protected SpanQuery match;
+
+
+ public SpanPositionCheckQuery(SpanQuery match) {
+ this.match = match;
+ }
+
+ /**
+ * @return the SpanQuery whose matches are filtered.
+ *
+ * */
+ public SpanQuery getMatch() { return match; }
+
+
+
+ @Override
+ public String getField() { return match.getField(); }
+
+
+
+ @Override
+ public void extractTerms(Set<Term> terms) {
+ match.extractTerms(terms);
+ }
+
+ /**
+ * Implementing classes are required to return whether the current position is a match for the passed in
+ * "match" {@link org.apache.lucene.search.spans.SpanQuery}.
+ *
+ * This is only called if the underlying {@link org.apache.lucene.search.spans.Spans#next()} for the
+ * match is successful
+ *
+ *
+ * @param spans The {@link org.apache.lucene.search.spans.Spans} instance, positioned at the spot to check
+ * @return true if it is a match, else false.
+ *
+ * @see org.apache.lucene.search.spans.Spans#next()
+ *
+ */
+ protected abstract boolean acceptPosition(Spans spans) throws IOException;
+
+ /**
+ * Implementing classes are required to return whether the position at the target is someplace that
+ * can be skipped to. For instance, the {@link org.apache.lucene.search.spans.SpanFirstQuery} returns
+ * false if the target position is beyond the maximum position allowed or if {@link Spans#next()} is true.
+ * <p/>
+ * Note, this method is only called if the underlying match {@link org.apache.lucene.search.spans.SpanQuery} can
+ * skip to the target.
+ * <p/>
+ * It is safe to assume that the passed in {@link org.apache.lucene.search.spans.Spans} object for the underlying {@link org.apache.lucene.search.spans.SpanQuery} is
+ * positioned at the target.
+ * <p/>
+ * The default implementation is to return true if either {@link #acceptPosition(Spans)} or {@link org.apache.lucene.search.spans.Spans#next()} is true for the
+ * passed in instance of Spans.
+ *<p/>
+ * @param spans The {@link org.apache.lucene.search.spans.Spans} to check
+ * @return true if the instance can skip to this position
+ *
+ * @see Spans#skipTo(int)
+ * @throws java.io.IOException if there is a low-level IO error
+ */
+ protected boolean acceptSkipTo(Spans spans) throws IOException{
+ return acceptPosition(spans) || spans.next();
+ }
+
+ @Override
+ public Spans getSpans(final IndexReader reader) throws IOException {
+ return new PositionCheckSpan(reader);
+ }
+
+
+ @Override
+ public Query rewrite(IndexReader reader) throws IOException {
+ SpanPositionCheckQuery clone = null;
+
+ SpanQuery rewritten = (SpanQuery) match.rewrite(reader);
+ if (rewritten != match) {
+ clone = (SpanPositionCheckQuery) this.clone();
+ clone.match = rewritten;
+ }
+
+ if (clone != null) {
+ return clone; // some clauses rewrote
+ } else {
+ return this; // no clauses rewrote
+ }
+ }
+
+ protected class PositionCheckSpan extends Spans {
+ private Spans spans;
+
+ private final IndexReader reader;
+
+ public PositionCheckSpan(IndexReader reader) throws IOException {
+ this.reader = reader;
+ spans = match.getSpans(reader);
+ }
+
+ @Override
+ public boolean next() throws IOException {
+ //TODO: optimize to skip ahead to start
+ while (spans.next()) { // scan to next match
+ if (acceptPosition(this))
+ return true;
+ }
+ return false;
+ }
+
+ @Override
+ public boolean skipTo(int target) throws IOException {
+ if (!spans.skipTo(target))
+ return false;
+
+ return acceptSkipTo(this);
+
+ }
+
+ @Override
+ public int doc() { return spans.doc(); }
+
+ @Override
+ public int start() { return spans.start(); }
+
+ @Override
+ public int end() { return spans.end(); }
+ // TODO: Remove warning after API has been finalized
+
+ @Override
+ public Collection<byte[]> getPayload() throws IOException {
+ ArrayList<byte[]> result = null;
+ if (spans.isPayloadAvailable()) {
+ result = new ArrayList<byte[]>(spans.getPayload());
+ }
+ return result;//TODO: any way to avoid the new construction?
+ }
+ // TODO: Remove warning after API has been finalized
+
+ @Override
+ public boolean isPayloadAvailable() {
+ return spans.isPayloadAvailable();
+ }
+
+ @Override
+ public String toString() {
+ return "spans(" + SpanPositionCheckQuery.this.toString() + ")";
+ }
+
+ }
+}
\ No newline at end of file
Added: lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionRangeQuery.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionRangeQuery.java?rev=1021357&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionRangeQuery.java (added)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/search/spans/SpanPositionRangeQuery.java Mon Oct 11 14:37:16 2010
@@ -0,0 +1,99 @@
+package org.apache.lucene.search.spans;
+/**
+ * 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.ToStringUtils;
+
+import java.io.IOException;
+
+
+/**
+ * Checks to see if the {@link #getMatch()} lies between a start and end position
+ *
+ * @see org.apache.lucene.search.spans.SpanFirstQuery for a derivation that is optimized for the case where start position is 0
+ */
+public class SpanPositionRangeQuery extends SpanPositionCheckQuery {
+ protected int start = 0;
+ protected int end;
+
+ public SpanPositionRangeQuery(SpanQuery match, int start, int end) {
+ super(match);
+ this.start = start;
+ this.end = end;
+ }
+
+
+ @Override
+ protected boolean acceptPosition(Spans spans) throws IOException {
+ return spans.start() >= start && spans.end() <= end;
+ }
+
+
+ /**
+ * @return The minimum position permitted in a match
+ */
+ public int getStart() {
+ return start;
+ }
+
+ /**
+ * @return the maximum end position permitted in a match.
+ */
+ public int getEnd() {
+ return end;
+ }
+
+ @Override
+ public String toString(String field) {
+ StringBuilder buffer = new StringBuilder();
+ buffer.append("spanPosRange(");
+ buffer.append(match.toString(field));
+ buffer.append(", ").append(start).append(", ");
+ buffer.append(end);
+ buffer.append(")");
+ buffer.append(ToStringUtils.boost(getBoost()));
+ return buffer.toString();
+ }
+
+ @Override
+ public Object clone() {
+ SpanPositionRangeQuery result = new SpanPositionRangeQuery((SpanQuery) match.clone(), start, end);
+ result.setBoost(getBoost());
+ return result;
+ }
+
+ @Override
+ public boolean equals(Object o) {
+ if (this == o) return true;
+ if (!(o instanceof SpanPositionRangeQuery)) return false;
+
+ SpanPositionRangeQuery other = (SpanPositionRangeQuery)o;
+ return this.end == other.end && this.start == other.start
+ && this.match.equals(other.match)
+ && this.getBoost() == other.getBoost();
+ }
+
+ @Override
+ public int hashCode() {
+ int h = match.hashCode();
+ h ^= (h << 8) | (h >>> 25); // reversible
+ h ^= Float.floatToRawIntBits(getBoost()) ^ end ^ start;
+ return h;
+ }
+
+}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/src/java/org/apache/lucene/util/ToStringUtils.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/java/org/apache/lucene/util/ToStringUtils.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/java/org/apache/lucene/util/ToStringUtils.java (original)
+++ lucene/dev/trunk/lucene/src/java/org/apache/lucene/util/ToStringUtils.java Mon Oct 11 14:37:16 2010
@@ -21,11 +21,23 @@ package org.apache.lucene.util;
* Helper methods to ease implementing {@link Object#toString()}.
*/
public class ToStringUtils {
- /** for printing boost only if not 1.0 */
+ /**
+ * for printing boost only if not 1.0
+ */
public static String boost(float boost) {
if (boost != 1.0f) {
return "^" + Float.toString(boost);
} else return "";
}
+ public static void byteArray(StringBuilder buffer, byte[] bytes) {
+ for (int i = 0; i < bytes.length; i++) {
+ buffer.append("b[").append(i).append("]=").append(bytes[i]);
+ if (i < bytes.length - 1) {
+ buffer.append(',');
+ }
+
+ }
+ }
+
}
Modified: lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockAnalyzer.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockAnalyzer.java (original)
+++ lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockAnalyzer.java Mon Oct 11 14:37:16 2010
@@ -20,6 +20,10 @@ package org.apache.lucene.analysis;
import java.io.IOException;
import java.io.Reader;
+import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.index.Payload;
import org.apache.lucene.util.automaton.CharacterRunAutomaton;
/**
@@ -30,8 +34,13 @@ public final class MockAnalyzer extends
private final boolean lowerCase;
private final CharacterRunAutomaton filter;
private final boolean enablePositionIncrements;
+ private final boolean payload;
private int positionIncrementGap;
+ public MockAnalyzer(CharacterRunAutomaton runAutomaton, boolean lowerCase, CharacterRunAutomaton filter, boolean enablePositionIncrements) {
+ this(runAutomaton, lowerCase, filter, enablePositionIncrements, false);
+ }
+
/**
* Creates a new MockAnalyzer.
*
@@ -39,12 +48,14 @@ public final class MockAnalyzer extends
* @param lowerCase true if the tokenizer should lowercase terms
* @param filter DFA describing how terms should be filtered (set of stopwords, etc)
* @param enablePositionIncrements true if position increments should reflect filtered terms.
+ * @param payload if payloads should be added
*/
- public MockAnalyzer(CharacterRunAutomaton runAutomaton, boolean lowerCase, CharacterRunAutomaton filter, boolean enablePositionIncrements) {
+ public MockAnalyzer(CharacterRunAutomaton runAutomaton, boolean lowerCase, CharacterRunAutomaton filter, boolean enablePositionIncrements, boolean payload) {
this.runAutomaton = runAutomaton;
this.lowerCase = lowerCase;
this.filter = filter;
this.enablePositionIncrements = enablePositionIncrements;
+ this.payload = payload;
}
/**
@@ -54,7 +65,11 @@ public final class MockAnalyzer extends
* @param lowerCase true if the tokenizer should lowercase terms
*/
public MockAnalyzer(CharacterRunAutomaton runAutomaton, boolean lowerCase) {
- this(runAutomaton, lowerCase, MockTokenFilter.EMPTY_STOPSET, false);
+ this(runAutomaton, lowerCase, MockTokenFilter.EMPTY_STOPSET, false, false);
+ }
+
+ public MockAnalyzer(CharacterRunAutomaton runAutomaton, boolean lowerCase, boolean payload) {
+ this(runAutomaton, lowerCase, MockTokenFilter.EMPTY_STOPSET, false, payload);
}
/**
@@ -67,12 +82,16 @@ public final class MockAnalyzer extends
@Override
public TokenStream tokenStream(String fieldName, Reader reader) {
MockTokenizer tokenizer = new MockTokenizer(reader, runAutomaton, lowerCase);
- return new MockTokenFilter(tokenizer, filter, enablePositionIncrements);
+ TokenFilter filt = new MockTokenFilter(tokenizer, filter, enablePositionIncrements);
+ if (payload){
+ filt = new SimplePayloadFilter(filt, fieldName);
+ }
+ return filt;
}
private class SavedStreams {
MockTokenizer tokenizer;
- MockTokenFilter filter;
+ TokenFilter filter;
}
@Override
@@ -83,10 +102,14 @@ public final class MockAnalyzer extends
saved = new SavedStreams();
saved.tokenizer = new MockTokenizer(reader, runAutomaton, lowerCase);
saved.filter = new MockTokenFilter(saved.tokenizer, filter, enablePositionIncrements);
+ if (payload){
+ saved.filter = new SimplePayloadFilter(saved.filter, fieldName);
+ }
setPreviousTokenStream(saved);
return saved.filter;
} else {
saved.tokenizer.reset(reader);
+ saved.filter.reset();
return saved.filter;
}
}
@@ -99,4 +122,30 @@ public final class MockAnalyzer extends
public int getPositionIncrementGap(String fieldName){
return positionIncrementGap;
}
+}
+
+final class SimplePayloadFilter extends TokenFilter {
+ String fieldName;
+ int pos;
+ final PayloadAttribute payloadAttr;
+ final CharTermAttribute termAttr;
+
+ public SimplePayloadFilter(TokenStream input, String fieldName) {
+ super(input);
+ this.fieldName = fieldName;
+ pos = 0;
+ payloadAttr = input.addAttribute(PayloadAttribute.class);
+ termAttr = input.addAttribute(CharTermAttribute.class);
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (input.incrementToken()) {
+ payloadAttr.setPayload(new Payload(("pos: " + pos).getBytes()));
+ pos++;
+ return true;
+ } else {
+ return false;
+ }
+ }
}
\ No newline at end of file
Added: lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockPayloadAnalyzer.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockPayloadAnalyzer.java?rev=1021357&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockPayloadAnalyzer.java (added)
+++ lucene/dev/trunk/lucene/src/test/org/apache/lucene/analysis/MockPayloadAnalyzer.java Mon Oct 11 14:37:16 2010
@@ -0,0 +1,93 @@
+package org.apache.lucene.analysis;
+/**
+ * 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.analysis.tokenattributes.CharTermAttribute;
+import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
+import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
+import org.apache.lucene.index.Payload;
+
+import java.io.IOException;
+import java.io.Reader;
+
+
+/**
+ *
+ *
+ **/
+public final class MockPayloadAnalyzer extends Analyzer {
+
+ @Override
+ public TokenStream tokenStream(String fieldName, Reader reader) {
+ TokenStream result = new MockTokenizer(reader, MockTokenizer.WHITESPACE, true);
+ return new MockPayloadFilter(result, fieldName);
+ }
+}
+
+
+/**
+ *
+ *
+ **/
+final class MockPayloadFilter extends TokenFilter {
+ String fieldName;
+
+ int pos;
+
+ int i;
+
+ final PositionIncrementAttribute posIncrAttr;
+ final PayloadAttribute payloadAttr;
+ final CharTermAttribute termAttr;
+
+ public MockPayloadFilter(TokenStream input, String fieldName) {
+ super(input);
+ this.fieldName = fieldName;
+ pos = 0;
+ i = 0;
+ posIncrAttr = input.addAttribute(PositionIncrementAttribute.class);
+ payloadAttr = input.addAttribute(PayloadAttribute.class);
+ termAttr = input.addAttribute(CharTermAttribute.class);
+ }
+
+ @Override
+ public boolean incrementToken() throws IOException {
+ if (input.incrementToken()) {
+ payloadAttr.setPayload(new Payload(("pos: " + pos).getBytes()));
+ int posIncr;
+ if (i % 2 == 1) {
+ posIncr = 1;
+ } else {
+ posIncr = 0;
+ }
+ posIncrAttr.setPositionIncrement(posIncr);
+ pos += posIncr;
+ i++;
+ return true;
+ } else {
+ return false;
+ }
+ }
+
+ @Override
+ public void reset() throws IOException {
+ i = 0;
+ pos = 0;
+ }
+}
+
Modified: lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPositionIncrement.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPositionIncrement.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPositionIncrement.java (original)
+++ lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPositionIncrement.java Mon Oct 11 14:37:16 2010
@@ -18,18 +18,16 @@ package org.apache.lucene.search;
*/
import java.io.Reader;
-import java.io.IOException;
import java.io.StringReader;
import java.util.Collection;
-import java.util.Random;
import org.apache.lucene.analysis.Analyzer;
+import org.apache.lucene.analysis.MockPayloadAnalyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.MockAnalyzer;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute;
-import org.apache.lucene.analysis.tokenattributes.PayloadAttribute;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
@@ -41,8 +39,6 @@ import org.apache.lucene.index.SlowMulti
import org.apache.lucene.index.Term;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.store.Directory;
-import org.apache.lucene.analysis.TokenFilter;
-import org.apache.lucene.index.Payload;
import org.apache.lucene.search.payloads.PayloadSpanUtil;
import org.apache.lucene.search.spans.SpanNearQuery;
import org.apache.lucene.search.spans.SpanQuery;
@@ -200,7 +196,7 @@ public class TestPositionIncrement exten
// should not find "1 2" because there is a gap of 1 in the index
QueryParser qp = new QueryParser(TEST_VERSION_CURRENT, "field",
- new MockAnalyzer(MockTokenizer.WHITESPACE, false, stopStopList, false));
+ new MockAnalyzer(MockTokenizer.WHITESPACE, false, stopStopList, false, false));
q = (PhraseQuery) qp.parse("\"1 2\"");
hits = searcher.search(q, null, 1000).scoreDocs;
assertEquals(0, hits.length);
@@ -224,7 +220,7 @@ public class TestPositionIncrement exten
// when both qp qnd stopFilter propagate increments, we should find the doc.
qp = new QueryParser(TEST_VERSION_CURRENT, "field",
- new MockAnalyzer(MockTokenizer.WHITESPACE, false, stopStopList, true));
+ new MockAnalyzer(MockTokenizer.WHITESPACE, false, stopStopList, true, false));
qp.setEnablePositionIncrements(true);
q = (PhraseQuery) qp.parse("\"1 stop 2\"");
hits = searcher.search(q, null, 1000).scoreDocs;
@@ -241,7 +237,7 @@ public class TestPositionIncrement exten
public void testPayloadsPos0() throws Exception {
Directory dir = newDirectory();
- RandomIndexWriter writer = new RandomIndexWriter(random, dir, new TestPayloadAnalyzer());
+ RandomIndexWriter writer = new RandomIndexWriter(random, dir, new MockPayloadAnalyzer());
Document doc = new Document();
doc.add(new Field("content", new StringReader(
"a a b c d e a f g h i j a b k k")));
@@ -327,57 +323,4 @@ public class TestPositionIncrement exten
is.getIndexReader().close();
dir.close();
}
-}
-
-final class TestPayloadAnalyzer extends Analyzer {
-
- @Override
- public TokenStream tokenStream(String fieldName, Reader reader) {
- TokenStream result = new MockTokenizer(reader, MockTokenizer.WHITESPACE, true);
- return new PayloadFilter(result, fieldName);
- }
-}
-
-final class PayloadFilter extends TokenFilter {
- String fieldName;
-
- int pos;
-
- int i;
-
- final PositionIncrementAttribute posIncrAttr;
- final PayloadAttribute payloadAttr;
- final CharTermAttribute termAttr;
-
- public PayloadFilter(TokenStream input, String fieldName) {
- super(input);
- this.fieldName = fieldName;
- pos = 0;
- i = 0;
- posIncrAttr = input.addAttribute(PositionIncrementAttribute.class);
- payloadAttr = input.addAttribute(PayloadAttribute.class);
- termAttr = input.addAttribute(CharTermAttribute.class);
- }
-
- @Override
- public boolean incrementToken() throws IOException {
- if (input.incrementToken()) {
- payloadAttr.setPayload(new Payload(("pos: " + pos).getBytes()));
- int posIncr;
- if (i % 2 == 1) {
- posIncr = 1;
- } else {
- posIncr = 0;
- }
- posIncrAttr.setPositionIncrement(posIncr);
- pos += posIncr;
- if (TestPositionIncrement.VERBOSE) {
- System.out.println("term=" + termAttr + " pos=" + pos);
- }
- i++;
- return true;
- } else {
- return false;
- }
- }
-}
+}
\ No newline at end of file
Modified: lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/spans/TestBasics.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/spans/TestBasics.java?rev=1021357&r1=1021356&r2=1021357&view=diff
==============================================================================
--- lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/spans/TestBasics.java (original)
+++ lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/spans/TestBasics.java Mon Oct 11 14:37:16 2010
@@ -18,12 +18,18 @@ package org.apache.lucene.search.spans;
*/
import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Collection;
+import java.util.Collections;
+import java.util.List;
import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.MockPayloadAnalyzer;
import org.apache.lucene.analysis.MockTokenizer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.Payload;
import org.apache.lucene.index.RandomIndexWriter;
import org.apache.lucene.index.SlowMultiReaderWrapper;
import org.apache.lucene.index.Term;
@@ -65,11 +71,11 @@ public class TestBasics extends LuceneTe
@BeforeClass
public static void beforeClass() throws Exception {
directory = newDirectory();
- RandomIndexWriter writer = new RandomIndexWriter(random, directory,
- newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(MockTokenizer.SIMPLE, true))
+ RandomIndexWriter writer = new RandomIndexWriter(random, directory,
+ newIndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(MockTokenizer.SIMPLE, true, true))
.setMaxBufferedDocs(_TestUtil.nextInt(random, 50, 1000)));
//writer.infoStream = System.out;
- for (int i = 0; i < 1000; i++) {
+ for (int i = 0; i < 2000; i++) {
Document doc = new Document();
doc.add(newField("field", English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
writer.addDocument(doc);
@@ -94,12 +100,23 @@ public class TestBasics extends LuceneTe
Query query = new TermQuery(new Term("field", "seventy"));
checkHits(query, new int[]
{70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 170, 171, 172, 173, 174, 175,
- 176, 177, 178, 179, 270, 271, 272, 273, 274, 275, 276, 277, 278, 279,
- 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 470, 471, 472, 473,
- 474, 475, 476, 477, 478, 479, 570, 571, 572, 573, 574, 575, 576, 577,
- 578, 579, 670, 671, 672, 673, 674, 675, 676, 677, 678, 679, 770, 771,
- 772, 773, 774, 775, 776, 777, 778, 779, 870, 871, 872, 873, 874, 875,
- 876, 877, 878, 879, 970, 971, 972, 973, 974, 975, 976, 977, 978, 979});
+ 176, 177, 178, 179, 270, 271, 272, 273, 274, 275, 276, 277, 278,
+ 279, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 470, 471,
+ 472, 473, 474, 475, 476, 477, 478, 479, 570, 571, 572, 573, 574,
+ 575, 576, 577, 578, 579, 670, 671, 672, 673, 674, 675, 676, 677,
+ 678, 679, 770, 771, 772, 773, 774, 775, 776, 777, 778, 779, 870,
+ 871, 872, 873, 874, 875, 876, 877, 878, 879, 970, 971, 972, 973,
+ 974, 975, 976, 977, 978, 979, 1070, 1071, 1072, 1073, 1074, 1075,
+ 1076, 1077, 1078, 1079, 1170, 1171, 1172, 1173, 1174, 1175, 1176,
+ 1177, 1178, 1179, 1270, 1271, 1272, 1273, 1274, 1275, 1276, 1277,
+ 1278, 1279, 1370, 1371, 1372, 1373, 1374, 1375, 1376, 1377, 1378,
+ 1379, 1470, 1471, 1472, 1473, 1474, 1475, 1476, 1477, 1478, 1479,
+ 1570, 1571, 1572, 1573, 1574, 1575, 1576, 1577, 1578, 1579, 1670,
+ 1671, 1672, 1673, 1674, 1675, 1676, 1677, 1678, 1679, 1770, 1771,
+ 1772, 1773, 1774, 1775, 1776, 1777, 1778, 1779, 1870, 1871, 1872,
+ 1873, 1874, 1875, 1876, 1877,
+ 1878, 1879, 1970, 1971, 1972, 1973, 1974, 1975, 1976, 1977, 1978,
+ 1979});
}
@Test
@@ -114,7 +131,8 @@ public class TestBasics extends LuceneTe
query.add(new Term("field", "seventy"));
query.add(new Term("field", "seven"));
checkHits(query, new int[]
- {77, 177, 277, 377, 477, 577, 677, 777, 877, 977});
+ {77, 177, 277, 377, 477, 577, 677, 777, 877,
+ 977, 1077, 1177, 1277, 1377, 1477, 1577, 1677, 1777, 1877, 1977});
}
@Test
@@ -131,8 +149,10 @@ public class TestBasics extends LuceneTe
query.add(new TermQuery(new Term("field", "seventy")), BooleanClause.Occur.MUST);
query.add(new TermQuery(new Term("field", "seven")), BooleanClause.Occur.MUST);
checkHits(query, new int[]
- {77, 777, 177, 277, 377, 477, 577, 677, 770, 771, 772, 773, 774, 775,
- 776, 778, 779, 877, 977});
+ {77, 177, 277, 377, 477, 577, 677, 770, 771, 772, 773, 774, 775, 776, 777,
+ 778, 779, 877, 977, 1077, 1177, 1277, 1377, 1477, 1577, 1677,
+ 1770, 1771, 1772, 1773, 1774, 1775, 1776, 1777, 1778, 1779, 1877,
+ 1977});
}
@Test
@@ -150,7 +170,7 @@ public class TestBasics extends LuceneTe
SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {term1, term2},
0, true);
checkHits(query, new int[]
- {77, 177, 277, 377, 477, 577, 677, 777, 877, 977});
+ {77, 177, 277, 377, 477, 577, 677, 777, 877, 977, 1077, 1177, 1277, 1377, 1477, 1577, 1677, 1777, 1877, 1977});
assertTrue(searcher.explain(query, 77).getValue() > 0.0f);
assertTrue(searcher.explain(query, 977).getValue() > 0.0f);
@@ -168,8 +188,10 @@ public class TestBasics extends LuceneTe
4, false);
checkHits(query, new int[]
- {609, 629, 639, 649, 659, 669, 679, 689, 699,
- 906, 926, 936, 946, 956, 966, 976, 986, 996});
+ {609, 629, 639, 649, 659, 669, 679, 689, 699, 906, 926, 936, 946, 956,
+ 966, 976, 986, 996, 1609, 1629, 1639, 1649, 1659, 1669,
+ 1679, 1689, 1699, 1906, 1926, 1936, 1946, 1956, 1966, 1976, 1986,
+ 1996});
}
@Test
@@ -179,7 +201,7 @@ public class TestBasics extends LuceneTe
SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {term1, term2},
4, true);
checkHits(query, new int[]
- {906, 926, 936, 946, 956, 966, 976, 986, 996});
+ {906, 926, 936, 946, 956, 966, 976, 986, 996, 1906, 1926, 1936, 1946, 1956, 1966, 1976, 1986, 1996});
}
@Test
@@ -192,7 +214,7 @@ public class TestBasics extends LuceneTe
SpanNotQuery query = new SpanNotQuery(near, term3);
checkHits(query, new int[]
- {801, 821, 831, 851, 861, 871, 881, 891});
+ {801, 821, 831, 851, 861, 871, 881, 891, 1801, 1821, 1831, 1851, 1861, 1871, 1881, 1891});
assertTrue(searcher.explain(query, 801).getValue() > 0.0f);
assertTrue(searcher.explain(query, 891).getValue() > 0.0f);
@@ -211,7 +233,8 @@ public class TestBasics extends LuceneTe
SpanNotQuery query = new SpanNotQuery(near, or);
checkHits(query, new int[]
- {801, 821, 831, 851, 861, 871, 881, 891});
+ {801, 821, 831, 851, 861, 871, 881, 891,
+ 1801, 1821, 1831, 1851, 1861, 1871, 1881, 1891});
assertTrue(searcher.explain(query, 801).getValue() > 0.0f);
assertTrue(searcher.explain(query, 891).getValue() > 0.0f);
@@ -232,7 +255,7 @@ public class TestBasics extends LuceneTe
SpanNotQuery query = new SpanNotQuery(near, or);
checkHits(query, new int[]
- {801, 821, 831, 851, 871, 891});
+ {801, 821, 831, 851, 871, 891, 1801, 1821, 1831, 1851, 1871, 1891});
assertTrue(searcher.explain(query, 801).getValue() > 0.0f);
assertTrue(searcher.explain(query, 891).getValue() > 0.0f);
@@ -252,7 +275,8 @@ public class TestBasics extends LuceneTe
SpanNotQuery query = new SpanNotQuery(near, exclude);
checkHits(query, new int[]
- {801, 821, 831, 851, 861, 871, 881, 891});
+ {801, 821, 831, 851, 861, 871, 881, 891,
+ 1801, 1821, 1831, 1851, 1861, 1871, 1881, 1891});
assertTrue(searcher.explain(query, 801).getValue() > 0.0f);
assertTrue(searcher.explain(query, 891).getValue() > 0.0f);
@@ -271,8 +295,13 @@ public class TestBasics extends LuceneTe
SpanFirstQuery exclude = new SpanFirstQuery(near, n-1);
SpanNotQuery q = new SpanNotQuery(include, exclude);
- checkHits(q, new int[]{40,41,42,43,44,45,46,47,48,49});
-
+ checkHits(q, new int[]{40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 1040, 1041, 1042, 1043, 1044, 1045, 1046, 1047, 1048,
+ 1049, 1140, 1141, 1142, 1143, 1144, 1145, 1146, 1147, 1148, 1149, 1240, 1241, 1242, 1243, 1244,
+ 1245, 1246, 1247, 1248, 1249, 1340, 1341, 1342, 1343, 1344, 1345, 1346, 1347, 1348, 1349, 1440, 1441, 1442,
+ 1443, 1444, 1445, 1446, 1447, 1448, 1449, 1540, 1541, 1542, 1543, 1544, 1545, 1546, 1547, 1548, 1549, 1640,
+ 1641, 1642, 1643, 1644, 1645, 1646, 1647,
+ 1648, 1649, 1740, 1741, 1742, 1743, 1744, 1745, 1746, 1747, 1748, 1749, 1840, 1841, 1842, 1843, 1844, 1845, 1846,
+ 1847, 1848, 1849, 1940, 1941, 1942, 1943, 1944, 1945, 1946, 1947, 1948, 1949});
}
@Test
@@ -296,6 +325,108 @@ public class TestBasics extends LuceneTe
}
@Test
+ public void testSpanPositionRange() throws Exception {
+ SpanPositionRangeQuery query;
+ SpanTermQuery term1 = new SpanTermQuery(new Term("field", "five"));
+ query = new SpanPositionRangeQuery(term1, 1, 2);
+ checkHits(query, new int[]
+ {25,35, 45, 55, 65, 75, 85, 95});
+ assertTrue(searcher.explain(query, 25).getValue() > 0.0f);
+ assertTrue(searcher.explain(query, 95).getValue() > 0.0f);
+
+ query = new SpanPositionRangeQuery(term1, 0, 1);
+ checkHits(query, new int[]
+ {5, 500, 501, 502, 503, 504, 505, 506, 507, 508, 509, 510, 511, 512,
+ 513, 514, 515, 516, 517, 518, 519, 520, 521, 522, 523, 524, 525,
+ 526, 527, 528, 529, 530, 531, 532, 533, 534, 535, 536, 537, 538,
+ 539, 540, 541, 542, 543, 544, 545, 546, 547, 548, 549, 550, 551,
+ 552, 553, 554, 555, 556, 557, 558, 559, 560, 561, 562, 563, 564,
+ 565, 566, 567, 568, 569, 570, 571, 572, 573, 574, 575, 576, 577,
+ 578, 579, 580, 581, 582, 583, 584,
+ 585, 586, 587, 588, 589, 590, 591, 592, 593, 594, 595, 596, 597,
+ 598, 599});
+
+ query = new SpanPositionRangeQuery(term1, 6, 7);
+ checkHits(query, new int[]{});
+ }
+
+ @Test
+ public void testSpanPayloadCheck() throws Exception {
+ SpanTermQuery term1 = new SpanTermQuery(new Term("field", "five"));
+ Payload pay = new Payload(("pos: " + 5).getBytes());
+ SpanQuery query = new SpanPayloadCheckQuery(term1, Collections.singletonList(pay.getData()));
+ checkHits(query, new int[]
+ {5});
+ assertTrue(searcher.explain(query, 5).getValue() > 0.0f);
+
+ SpanTermQuery term2 = new SpanTermQuery(new Term("field", "hundred"));
+ SpanNearQuery snq;
+ SpanQuery[] clauses;
+ List<byte[]> list;
+ Payload pay2;
+ clauses = new SpanQuery[2];
+ clauses[0] = term1;
+ clauses[1] = term2;
+ snq = new SpanNearQuery(clauses, 0, true);
+ pay = new Payload(("pos: " + 1656).getBytes());
+ pay2 = new Payload(("pos: " + 1657).getBytes());
+ list = new ArrayList<byte[]>();
+ list.add(pay.getData());
+ list.add(pay2.getData());
+ query = new SpanNearPayloadCheckQuery(snq, list);
+ checkHits(query, new int[]
+ {500});
+ clauses = new SpanQuery[3];
+ clauses[0] = term1;
+ clauses[1] = term2;
+ clauses[2] = new SpanTermQuery(new Term("field", "five"));
+ snq = new SpanNearQuery(clauses, 0, true);
+ pay = new Payload(("pos: " + 1670).getBytes());
+ pay2 = new Payload(("pos: " + 1671).getBytes());
+ Payload pay3 = new Payload(("pos: " + 1672).getBytes());
+ list = new ArrayList<byte[]>();
+ list.add(pay.getData());
+ list.add(pay2.getData());
+ list.add(pay3.getData());
+ query = new SpanNearPayloadCheckQuery(snq, list);
+ checkHits(query, new int[]
+ {505});
+ }
+
+ public void testComplexSpanChecks() throws Exception {
+ SpanTermQuery one = new SpanTermQuery(new Term("field", "one"));
+ SpanTermQuery thous = new SpanTermQuery(new Term("field", "thousand"));
+ //should be one position in between
+ SpanTermQuery hundred = new SpanTermQuery(new Term("field", "hundred"));
+ SpanTermQuery three = new SpanTermQuery(new Term("field", "three"));
+
+ SpanNearQuery oneThous = new SpanNearQuery(new SpanQuery[]{one, thous}, 0, true);
+ SpanNearQuery hundredThree = new SpanNearQuery(new SpanQuery[]{hundred, three}, 0, true);
+ SpanNearQuery oneThousHunThree = new SpanNearQuery(new SpanQuery[]{oneThous, hundredThree}, 1, true);
+ SpanQuery query;
+ //this one's too small
+ query = new SpanPositionRangeQuery(oneThousHunThree, 1, 2);
+ checkHits(query, new int[]{});
+ //this one's just right
+ query = new SpanPositionRangeQuery(oneThousHunThree, 0, 6);
+ checkHits(query, new int[]{1103, 1203,1303,1403,1503,1603,1703,1803,1903});
+
+ Collection<byte[]> payloads = new ArrayList<byte[]>();
+ Payload pay = new Payload(("pos: " + 3896).getBytes());
+ Payload pay2 = new Payload(("pos: " + 3897).getBytes());
+ Payload pay3 = new Payload(("pos: " + 3899).getBytes());
+ Payload pay4 = new Payload(("pos: " + 3900).getBytes());
+ payloads.add(pay.getData());
+ payloads.add(pay2.getData());
+ payloads.add(pay3.getData());
+ payloads.add(pay4.getData());
+ query = new SpanNearPayloadCheckQuery(oneThousHunThree, payloads);
+ checkHits(query, new int[]{1103});
+
+ }
+
+
+ @Test
public void testSpanOr() throws Exception {
SpanTermQuery term1 = new SpanTermQuery(new Term("field", "thirty"));
SpanTermQuery term2 = new SpanTermQuery(new Term("field", "three"));
@@ -310,7 +441,8 @@ public class TestBasics extends LuceneTe
checkHits(query, new int[]
{33, 47, 133, 147, 233, 247, 333, 347, 433, 447, 533, 547, 633, 647, 733,
- 747, 833, 847, 933, 947});
+ 747, 833, 847, 933, 947, 1033, 1047, 1133, 1147, 1233, 1247, 1333,
+ 1347, 1433, 1447, 1533, 1547, 1633, 1647, 1733, 1747, 1833, 1847, 1933, 1947});
assertTrue(searcher.explain(query, 33).getValue() > 0.0f);
assertTrue(searcher.explain(query, 947).getValue() > 0.0f);
@@ -330,7 +462,7 @@ public class TestBasics extends LuceneTe
SpanNearQuery query = new SpanNearQuery(new SpanQuery[] {near1, near2},
0, true);
- checkHits(query, new int[] {333});
+ checkHits(query, new int[] {333, 1333});
assertTrue(searcher.explain(query, 333).getValue() > 0.0f);
}
@@ -351,10 +483,13 @@ public class TestBasics extends LuceneTe
10, true);
checkHits(query, new int[]
- {606, 607, 626, 627, 636, 637, 646, 647,
- 656, 657, 666, 667, 676, 677, 686, 687, 696, 697,
- 706, 707, 726, 727, 736, 737, 746, 747,
- 756, 757, 766, 767, 776, 777, 786, 787, 796, 797});
+ {606, 607, 626, 627, 636, 637, 646, 647, 656, 657, 666, 667, 676, 677,
+ 686, 687, 696, 697, 706, 707, 726, 727, 736, 737, 746, 747, 756,
+ 757, 766, 767, 776, 777, 786, 787, 796, 797, 1606, 1607, 1626,
+ 1627, 1636, 1637, 1646, 1647, 1656, 1657, 1666, 1667, 1676, 1677,
+ 1686, 1687, 1696, 1697, 1706, 1707, 1726, 1727, 1736, 1737,
+ 1746, 1747, 1756, 1757, 1766, 1767, 1776, 1777, 1786, 1787, 1796,
+ 1797});
}
@Test
@@ -378,10 +513,12 @@ public class TestBasics extends LuceneTe
100, true);
checkHits(query, new int[]
- {606, 607, 626, 627, 636, 637, 646, 647,
- 656, 657, 666, 667, 676, 677, 686, 687, 696, 697,
- 706, 707, 726, 727, 736, 737, 746, 747,
- 756, 757, 766, 767, 776, 777, 786, 787, 796, 797});
+ {606, 607, 626, 627, 636, 637, 646, 647, 656, 657, 666, 667, 676, 677, 686, 687, 696,
+ 697, 706, 707, 726, 727, 736, 737, 746, 747, 756, 757,
+ 766, 767, 776, 777, 786, 787, 796, 797, 1606, 1607, 1626, 1627, 1636, 1637, 1646,
+ 1647, 1656, 1657,
+ 1666, 1667, 1676, 1677, 1686, 1687, 1696, 1697, 1706, 1707, 1726, 1727, 1736, 1737,
+ 1746, 1747, 1756, 1757, 1766, 1767, 1776, 1777, 1786, 1787, 1796, 1797});
}
@Test