This is invalid until {@link + #next()} is called for the first time.*/ + public abstract int doc(); + + /** Moves to the next docId in the set. Returns true, iff + * there is such a docId. */ + public abstract boolean next() throws IOException; + + /** Skips entries to the first beyond the current whose document number is + * greater than or equal to target.
Returns true iff there is such + * an entry.
Behaves as if written:
+ * boolean skipTo(int target) {
+ * do {
+ * if (!next())
+ * return false;
+ * } while (target > doc());
+ * return true;
+ * }
+ *
+ * Some implementations are considerably more efficient than that.
+ */
+ public abstract boolean skipTo(int target) throws IOException;
+}
Index: src/java/org/apache/lucene/search/Filter.java
===================================================================
--- src/java/org/apache/lucene/search/Filter.java (revision 610038)
+++ src/java/org/apache/lucene/search/Filter.java (working copy)
@@ -20,11 +20,32 @@
import java.util.BitSet;
import java.io.IOException;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.util.DocIdBitSet;
-/** Abstract base class providing a mechanism to restrict searches to a subset
- of an index. */
+/** Abstract base class providing a mechanism to use a subset of an index
+ * for restriction or permission of index search results.
+ *
+ * Note: In Lucene 3.0 {@link #bits(IndexReader)} will be removed
+ * and {@link #getDocIdSet(IndexReader)} will be defined as abstract.
+ * All implementing classes must therefore implement {@link #getDocIdSet(IndexReader)}
+ * in order to work with Lucene 3.0.
+ */
public abstract class Filter implements java.io.Serializable {
- /** Returns a BitSet with true for documents which should be permitted in
- search results, and false for those that should not. */
- public abstract BitSet bits(IndexReader reader) throws IOException;
+ /**
+ * @return A BitSet with true for documents which should be permitted in
+ * search results, and false for those that should not.
+ * @deprecated Use {@link #getDocIdSet(IndexReader)} instead.
+ */
+ public BitSet bits(IndexReader reader) throws IOException {
+ return null;
+ }
+
+ /**
+ * @return a DocIdSet that provides the documents which should be
+ * permitted or prohibited in search results.
+ * @see DocIdBitSet
+ */
+ public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
+ return new DocIdBitSet(bits(reader));
+ }
}
Index: src/java/org/apache/lucene/search/FilteredQuery.java
===================================================================
--- src/java/org/apache/lucene/search/FilteredQuery.java (revision 610038)
+++ src/java/org/apache/lucene/search/FilteredQuery.java (working copy)
@@ -21,7 +21,6 @@
import org.apache.lucene.util.ToStringUtils;
import java.io.IOException;
-import java.util.BitSet;
import java.util.Set;
@@ -47,7 +46,7 @@
/**
* Constructs a new query which applies a filter to the results of the original query.
- * Filter.bits() will be called every time this query is used in a search.
+ * Filter.getDocIdSet() will be called every time this query is used in a search.
* @param query Query to be filtered, cannot be null.
* @param filter Filter to apply to query results, cannot be null.
*/
@@ -86,13 +85,15 @@
inner.addDetail(preBoost);
}
Filter f = FilteredQuery.this.filter;
- BitSet matches = f.bits(ir);
- if (matches.get(i))
+ DocIdSetIterator docIdSetIterator = f.getDocIdSet(ir).iterator();
+ if (docIdSetIterator.skipTo(i) && (docIdSetIterator.doc() == i)) {
return inner;
- Explanation result = new Explanation
- (0.0f, "failure to match filter: " + f.toString());
- result.addDetail(inner);
- return result;
+ } else {
+ Explanation result = new Explanation
+ (0.0f, "failure to match filter: " + f.toString());
+ result.addDetail(inner);
+ return result;
+ }
}
// return this query
@@ -100,50 +101,49 @@
// return a filtering scorer
public Scorer scorer (IndexReader indexReader) throws IOException {
- final Scorer scorer = weight.scorer (indexReader);
- final BitSet bitset = filter.bits (indexReader);
- return new Scorer (similarity) {
+ final Scorer scorer = weight.scorer(indexReader);
+ final DocIdSetIterator docIdSetIterator = filter.getDocIdSet(indexReader).iterator();
- public boolean next() throws IOException {
- do {
- if (! scorer.next()) {
+ return new Scorer(similarity) {
+
+ private boolean advanceToCommon() throws IOException {
+ while (scorer.doc() != docIdSetIterator.doc()) {
+ if (scorer.doc() < docIdSetIterator.doc()) {
+ if (!scorer.skipTo(docIdSetIterator.doc())) {
+ return false;
+ }
+ } else if (!docIdSetIterator.skipTo(scorer.doc())) {
return false;
}
- } while (! bitset.get(scorer.doc()));
- /* When skipTo() is allowed on scorer it should be used here
- * in combination with bitset.nextSetBit(...)
- * See the while loop in skipTo() below.
- */
+ }
return true;
}
+
+ public boolean next() throws IOException {
+ return docIdSetIterator.next() && scorer.next() && advanceToCommon();
+ }
+
public int doc() { return scorer.doc(); }
public boolean skipTo(int i) throws IOException {
- if (! scorer.skipTo(i)) {
- return false;
- }
- while (! bitset.get(scorer.doc())) {
- int nextFiltered = bitset.nextSetBit(scorer.doc() + 1);
- if (nextFiltered == -1) {
- return false;
- } else if (! scorer.skipTo(nextFiltered)) {
- return false;
- }
- }
- return true;
- }
+ return docIdSetIterator.skipTo(i)
+ && scorer.skipTo(docIdSetIterator.doc())
+ && advanceToCommon();
+ }
public float score() throws IOException { return getBoost() * scorer.score(); }
// add an explanation about whether the document was filtered
public Explanation explain (int i) throws IOException {
- Explanation exp = scorer.explain (i);
- exp.setValue(getBoost() * exp.getValue());
+ Explanation exp = scorer.explain(i);
- if (bitset.get(i))
+ if (docIdSetIterator.skipTo(i) && (docIdSetIterator.doc() == i)) {
exp.setDescription ("allowed by filter: "+exp.getDescription());
- else
+ exp.setValue(getBoost() * exp.getValue());
+ } else {
exp.setDescription ("removed by filter: "+exp.getDescription());
+ exp.setValue(0.0f);
+ }
return exp;
}
};
Index: src/java/org/apache/lucene/search/IndexSearcher.java
===================================================================
--- src/java/org/apache/lucene/search/IndexSearcher.java (revision 610038)
+++ src/java/org/apache/lucene/search/IndexSearcher.java (working copy)
@@ -128,22 +128,33 @@
// inherit javadoc
public void search(Weight weight, Filter filter,
final HitCollector results) throws IOException {
- HitCollector collector = results;
- if (filter != null) {
- final BitSet bits = filter.bits(reader);
- collector = new HitCollector() {
- public final void collect(int doc, float score) {
- if (bits.get(doc)) { // skip docs not in bits
- results.collect(doc, score);
- }
- }
- };
- }
Scorer scorer = weight.scorer(reader);
if (scorer == null)
return;
- scorer.score(collector);
+
+ if (filter == null) {
+ scorer.score(results);
+ return;
+ }
+
+ DocIdSetIterator docIdSetIterator = filter.getDocIdSet(reader).iterator(); // CHECKME: use ConjunctionScorer here?
+ boolean more = docIdSetIterator.next();
+ while (more) {
+ int filterDocId = docIdSetIterator.doc();
+ if (! scorer.skipTo(filterDocId)) {
+ more = false;
+ } else {
+ int scorerDocId = scorer.doc();
+ if (scorerDocId == filterDocId) { // permitted by filter
+ results.collect(scorerDocId, scorer.score());
+ more = docIdSetIterator.skipTo(scorerDocId + 1);
+ } else {
+ more = docIdSetIterator.skipTo(scorerDocId);
+ }
+ }
+ }
+
}
public Query rewrite(Query original) throws IOException {
Index: src/java/org/apache/lucene/search/PrefixFilter.java
===================================================================
--- src/java/org/apache/lucene/search/PrefixFilter.java (revision 610038)
+++ src/java/org/apache/lucene/search/PrefixFilter.java (working copy)
@@ -18,6 +18,7 @@
*/
import org.apache.lucene.search.Filter;
+import org.apache.lucene.util.OpenBitSet;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.TermEnum;
@@ -39,6 +40,9 @@
public Term getPrefix() { return prefix; }
+ /**
+ * @deprecated Use {@link #getDocIdSet(IndexReader)} instead.
+ */
public BitSet bits(IndexReader reader) throws IOException {
final BitSet bitSet = new BitSet(reader.maxDoc());
new PrefixGenerator(prefix) {
@@ -48,6 +52,16 @@
}.generate(reader);
return bitSet;
}
+
+ public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
+ final OpenBitSet bitSet = new OpenBitSet(reader.maxDoc());
+ new PrefixGenerator(prefix) {
+ public void handleDoc(int doc) {
+ bitSet.set(doc);
+ }
+ }.generate(reader);
+ return bitSet;
+ }
/** Prints a user-readable version of this query. */
public String toString () {
Index: src/java/org/apache/lucene/search/QueryWrapperFilter.java
===================================================================
--- src/java/org/apache/lucene/search/QueryWrapperFilter.java (revision 610038)
+++ src/java/org/apache/lucene/search/QueryWrapperFilter.java (working copy)
@@ -21,6 +21,7 @@
import java.util.BitSet;
import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.util.OpenBitSet;
/**
* Constrains search results to only match those which also match a provided
@@ -44,6 +45,9 @@
this.query = query;
}
+ /**
+ * @deprecated Use {@link #getDocIdSet(IndexReader)} instead.
+ */
public BitSet bits(IndexReader reader) throws IOException {
final BitSet bits = new BitSet(reader.maxDoc());
@@ -54,7 +58,18 @@
});
return bits;
}
+
+ public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
+ final OpenBitSet bits = new OpenBitSet(reader.maxDoc());
+ new IndexSearcher(reader).search(query, new HitCollector() {
+ public final void collect(int doc, float score) {
+ bits.set(doc); // set bit for hit
+ }
+ });
+ return bits;
+ }
+
public String toString() {
return "QueryWrapperFilter(" + query + ")";
}
Index: src/java/org/apache/lucene/search/RangeFilter.java
===================================================================
--- src/java/org/apache/lucene/search/RangeFilter.java (revision 610038)
+++ src/java/org/apache/lucene/search/RangeFilter.java (working copy)
@@ -21,6 +21,7 @@
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermDocs;
import org.apache.lucene.index.TermEnum;
+import org.apache.lucene.util.OpenBitSet;
import java.io.IOException;
import java.util.BitSet;
@@ -94,6 +95,7 @@
* Returns a BitSet with true for documents which should be
* permitted in search results, and false for those that should
* not.
+ * @deprecated Use {@link #getDocIdSet(IndexReader)} instead.
*/
public BitSet bits(IndexReader reader) throws IOException {
BitSet bits = new BitSet(reader.maxDoc());
@@ -152,6 +154,69 @@
return bits;
}
+ /**
+ * Returns a BitSet with true for documents which should be
+ * permitted in search results, and false for those that should
+ * not.
+ */
+ public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
+ OpenBitSet bits = new OpenBitSet(reader.maxDoc());
+
+ TermEnum enumerator =
+ (null != lowerTerm
+ ? reader.terms(new Term(fieldName, lowerTerm))
+ : reader.terms(new Term(fieldName,"")));
+
+ try {
+
+ if (enumerator.term() == null) {
+ return bits;
+ }
+
+ boolean checkLower = false;
+ if (!includeLower) // make adjustments to set to exclusive
+ checkLower = true;
+
+ TermDocs termDocs = reader.termDocs();
+ try {
+
+ do {
+ Term term = enumerator.term();
+ if (term != null && term.field().equals(fieldName)) {
+ if (!checkLower || null==lowerTerm || term.text().compareTo(lowerTerm) > 0) {
+ checkLower = false;
+ if (upperTerm != null) {
+ int compare = upperTerm.compareTo(term.text());
+ /* if beyond the upper term, or is exclusive and
+ * this is equal to the upper term, break out */
+ if ((compare < 0) ||
+ (!includeUpper && compare==0)) {
+ break;
+ }
+ }
+ /* we have a good term, find the docs */
+
+ termDocs.seek(enumerator.term());
+ while (termDocs.next()) {
+ bits.set(termDocs.doc());
+ }
+ }
+ } else {
+ break;
+ }
+ }
+ while (enumerator.next());
+
+ } finally {
+ termDocs.close();
+ }
+ } finally {
+ enumerator.close();
+ }
+
+ return bits;
+ }
+
public String toString() {
StringBuffer buffer = new StringBuffer();
buffer.append(fieldName);
Index: src/java/org/apache/lucene/search/RemoteCachingWrapperFilter.java
===================================================================
--- src/java/org/apache/lucene/search/RemoteCachingWrapperFilter.java (revision 610038)
+++ src/java/org/apache/lucene/search/RemoteCachingWrapperFilter.java (working copy)
@@ -50,9 +50,21 @@
* searcher side of a remote connection.
* @param reader the index reader for the Filter
* @return the bitset
+ * @deprecated Use {@link #getDocIdSet(IndexReader)} instead.
*/
public BitSet bits(IndexReader reader) throws IOException {
Filter cachedFilter = FilterManager.getInstance().getFilter(filter);
return cachedFilter.bits(reader);
}
+
+ /**
+ * Uses the {@link FilterManager} to keep the cache for a filter on the
+ * searcher side of a remote connection.
+ * @param reader the index reader for the Filter
+ * @return the DocIdSet
+ */
+ public DocIdSet getDocIdSet(IndexReader reader) throws IOException {
+ Filter cachedFilter = FilterManager.getInstance().getFilter(filter);
+ return cachedFilter.getDocIdSet(reader);
+ }
}
Index: src/java/org/apache/lucene/search/Scorer.java
===================================================================
--- src/java/org/apache/lucene/search/Scorer.java (revision 610038)
+++ src/java/org/apache/lucene/search/Scorer.java (working copy)
@@ -33,7 +33,7 @@
*
- * When this method is used the {@link #explain(int)} method should not - * be used. - *
- * - * @return true iff there is another document matching the query. - * @see BooleanQuery#setAllowDocsOutOfOrder - */ - public abstract boolean next() throws IOException; - - /** Returns the current document number matching the query. - * Initially invalid, until {@link #next()} is called the first time. - */ - public abstract int doc(); - /** Returns the score of the current document matching the query. * Initially invalid, until {@link #next()} or {@link #skipTo(int)} * is called the first time. */ public abstract float score() throws IOException; - /** - * Skips to the document matching this Scorer with the lowest doc Id - * greater than or equal to a given target. - * - *- * The behavior of this method is undefined if the target specified is - * less than or equal to the current value of {@link #doc()}. - *
- * Behaves as if written: - *
- * boolean skipTo(int target) {
- * do {
- * if (!next())
- * return false;
- * } while (target > doc());
- * return true;
- * }
- *
- * Most implementations are considerably more efficient than that.
- *
- *
- * - * When this method is used the {@link #explain(int)} method should not - * be used. - *
- * - * @param target The target document number. - * @return true iff there is such a match. - * @see BooleanQuery#setAllowDocsOutOfOrder - */ - public abstract boolean skipTo(int target) throws IOException; - /** Returns an explanation of the score for a document. *