You are viewing a plain text version of this content. The canonical link for it is here.
Posted to java-commits@lucene.apache.org by mi...@apache.org on 2009/11/24 21:26:09 UTC
svn commit: r883852 - in /lucene/java/trunk: ./
contrib/instantiated/src/java/org/apache/lucene/store/instantiated/
contrib/memory/src/java/org/apache/lucene/index/memory/
contrib/misc/src/java/org/apache/lucene/index/
contrib/misc/src/test/org/apache/...
Author: mikemccand
Date: Tue Nov 24 20:26:07 2009
New Revision: 883852
URL: http://svn.apache.org/viewvc?rev=883852&view=rev
Log:
LUCENE-1260: allow Similarity instance to customize how norms are encoded/decoded
Modified:
lucene/java/trunk/CHANGES.txt
lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexWriter.java
lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java
lucene/java/trunk/contrib/misc/src/java/org/apache/lucene/index/FieldNormModifier.java
lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/index/TestFieldNormModifier.java
lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/misc/TestLengthNormModifier.java
lucene/java/trunk/src/java/org/apache/lucene/document/AbstractField.java
lucene/java/trunk/src/java/org/apache/lucene/document/Fieldable.java
lucene/java/trunk/src/java/org/apache/lucene/index/DirectoryReader.java
lucene/java/trunk/src/java/org/apache/lucene/index/IndexReader.java
lucene/java/trunk/src/java/org/apache/lucene/index/MultiReader.java
lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriter.java
lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriterPerField.java
lucene/java/trunk/src/java/org/apache/lucene/index/SegmentReader.java
lucene/java/trunk/src/java/org/apache/lucene/search/MatchAllDocsQuery.java
lucene/java/trunk/src/java/org/apache/lucene/search/MultiPhraseQuery.java
lucene/java/trunk/src/java/org/apache/lucene/search/PhraseQuery.java
lucene/java/trunk/src/java/org/apache/lucene/search/PhraseScorer.java
lucene/java/trunk/src/java/org/apache/lucene/search/Scorer.java
lucene/java/trunk/src/java/org/apache/lucene/search/Similarity.java
lucene/java/trunk/src/java/org/apache/lucene/search/TermQuery.java
lucene/java/trunk/src/java/org/apache/lucene/search/TermScorer.java
lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanScorer.java
lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanWeight.java
lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReader.java
lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderClone.java
lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderCloneNorms.java
lucene/java/trunk/src/test/org/apache/lucene/index/TestNorms.java
lucene/java/trunk/src/test/org/apache/lucene/index/TestSegmentReader.java
Modified: lucene/java/trunk/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/java/trunk/CHANGES.txt?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/CHANGES.txt (original)
+++ lucene/java/trunk/CHANGES.txt Tue Nov 24 20:26:07 2009
@@ -11,6 +11,12 @@
* LUCENE-2076: Rename FSDirectory.getFile -> getDirectory. (George
Aroush via Mike McCandless)
+* LUCENE-1260: Change norm encode (float->byte) and decode
+ (byte->float) to be instance methods not static methods. This way a
+ custom Similarity can alter how norms are encoded, though they must
+ still be encoded as a single byte (Johan Kindgren via Mike
+ McCandless)
+
Bug fixes
* LUCENE-2092: BooleanQuery was ignoring disableCoord in its hashCode
Modified: lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexWriter.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexWriter.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexWriter.java (original)
+++ lucene/java/trunk/contrib/instantiated/src/java/org/apache/lucene/store/instantiated/InstantiatedIndexWriter.java Tue Nov 24 20:26:07 2009
@@ -43,7 +43,6 @@
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.Term;
import org.apache.lucene.index.TermVectorOffsetInfo;
-import org.apache.lucene.search.DefaultSimilarity;
import org.apache.lucene.search.Similarity;
import org.apache.lucene.util.StringHelper;
import org.apache.lucene.util.AttributeImpl;
@@ -202,9 +201,9 @@
byte[] oldNorms = index.getNormsByFieldNameAndDocumentNumber().get(field);
if (oldNorms != null) {
System.arraycopy(oldNorms, 0, norms, 0, oldNorms.length);
- Arrays.fill(norms, oldNorms.length, norms.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(norms, oldNorms.length, norms.length, similarity.encodeNormValue(1.0f));
} else {
- Arrays.fill(norms, 0, norms.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(norms, 0, norms.length, similarity.encodeNormValue(1.0f));
}
normsByFieldNameAndDocumentNumber.put(field, norms);
fieldNames.remove(field);
@@ -212,7 +211,7 @@
for (String field : fieldNames) {
//System.out.println(field);
byte[] norms = new byte[index.getDocumentsByNumber().length + termDocumentInformationFactoryByDocument.size()];
- Arrays.fill(norms, 0, norms.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(norms, 0, norms.length, similarity.encodeNormValue(1.0f));
normsByFieldNameAndDocumentNumber.put(field, norms);
}
fieldNames.clear();
@@ -240,7 +239,7 @@
float norm = eFieldTermDocInfoFactoriesByTermText.getKey().boost;
norm *= document.getDocument().getBoost();
norm *= similarity.lengthNorm(eFieldTermDocInfoFactoriesByTermText.getKey().fieldName, eFieldTermDocInfoFactoriesByTermText.getKey().fieldLength);
- normsByFieldNameAndDocumentNumber.get(eFieldTermDocInfoFactoriesByTermText.getKey().fieldName)[document.getDocumentNumber()] = Similarity.encodeNorm(norm);
+ normsByFieldNameAndDocumentNumber.get(eFieldTermDocInfoFactoriesByTermText.getKey().fieldName)[document.getDocumentNumber()] = similarity.encodeNormValue(norm);
} else {
System.currentTimeMillis();
}
Modified: lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java (original)
+++ lucene/java/trunk/contrib/memory/src/java/org/apache/lucene/index/memory/MemoryIndex.java Tue Nov 24 20:26:07 2009
@@ -50,7 +50,7 @@
import org.apache.lucene.search.Searcher;
import org.apache.lucene.search.Scorer;
import org.apache.lucene.search.Similarity;
-import org.apache.lucene.store.RAMDirectory;
+import org.apache.lucene.store.RAMDirectory; // for javadocs
/**
* High-performance single-document main memory Apache Lucene fulltext search index.
@@ -1102,7 +1102,7 @@
float boost = info != null ? info.getBoost() : 1.0f;
FieldInvertState invertState = new FieldInvertState(0, numTokens, numOverlapTokens, 0, boost);
float n = sim.computeNorm(fieldName, invertState);
- byte norm = Similarity.encodeNorm(n);
+ byte norm = sim.encodeNormValue(n);
norms = new byte[] {norm};
// cache it for future reuse
Modified: lucene/java/trunk/contrib/misc/src/java/org/apache/lucene/index/FieldNormModifier.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/misc/src/java/org/apache/lucene/index/FieldNormModifier.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/contrib/misc/src/java/org/apache/lucene/index/FieldNormModifier.java (original)
+++ lucene/java/trunk/contrib/misc/src/java/org/apache/lucene/index/FieldNormModifier.java Tue Nov 24 20:26:07 2009
@@ -143,7 +143,7 @@
if (sim == null)
reader.setNorm(d, fieldName, Similarity.encodeNorm(1.0f));
else
- reader.setNorm(d, fieldName, Similarity.encodeNorm(sim.lengthNorm(fieldName, termCounts[d])));
+ reader.setNorm(d, fieldName, sim.encodeNormValue(sim.lengthNorm(fieldName, termCounts[d])));
}
}
Modified: lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/index/TestFieldNormModifier.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/index/TestFieldNormModifier.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/index/TestFieldNormModifier.java (original)
+++ lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/index/TestFieldNormModifier.java Tue Nov 24 20:26:07 2009
@@ -44,9 +44,7 @@
public TestFieldNormModifier(String name) {
super(name);
}
-
- public static byte DEFAULT_NORM = Similarity.encodeNorm(1.0f);
-
+
public static int NUM_DOCS = 5;
public Directory store = new RAMDirectory();
Modified: lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/misc/TestLengthNormModifier.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/misc/TestLengthNormModifier.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/misc/TestLengthNormModifier.java (original)
+++ lucene/java/trunk/contrib/misc/src/test/org/apache/lucene/misc/TestLengthNormModifier.java Tue Nov 24 20:26:07 2009
@@ -47,8 +47,6 @@
public TestLengthNormModifier(String name) {
super(name);
}
-
- public static byte DEFAULT_NORM = Similarity.encodeNorm(1.0f);
public static int NUM_DOCS = 5;
Modified: lucene/java/trunk/src/java/org/apache/lucene/document/AbstractField.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/document/AbstractField.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/document/AbstractField.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/document/AbstractField.java Tue Nov 24 20:26:07 2009
@@ -16,7 +16,7 @@
*/
import org.apache.lucene.search.PhraseQuery; // for javadocs
-import org.apache.lucene.search.spans.SpanQuery;
+import org.apache.lucene.search.spans.SpanQuery; // for javadocs
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.util.StringHelper; // for javadocs
@@ -80,13 +80,13 @@
* by the {@link
* org.apache.lucene.search.Similarity#lengthNorm(String,
* int)} and then
- * rounded by {@link org.apache.lucene.search.Similarity#encodeNorm(float)} before it is stored in the
+ * rounded by {@link org.apache.lucene.search.Similarity#encodeNormValue(float)} before it is stored in the
* index. One should attempt to ensure that this product does not overflow
* the range of that encoding.
*
* @see org.apache.lucene.document.Document#setBoost(float)
* @see org.apache.lucene.search.Similarity#computeNorm(String, org.apache.lucene.index.FieldInvertState)
- * @see org.apache.lucene.search.Similarity#encodeNorm(float)
+ * @see org.apache.lucene.search.Similarity#encodeNormValue(float)
*/
public void setBoost(float boost) {
this.boost = boost;
Modified: lucene/java/trunk/src/java/org/apache/lucene/document/Fieldable.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/document/Fieldable.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/document/Fieldable.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/document/Fieldable.java Tue Nov 24 20:26:07 2009
@@ -18,8 +18,8 @@
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.index.FieldInvertState; // for javadocs
-import org.apache.lucene.search.PhraseQuery;
-import org.apache.lucene.search.spans.SpanQuery;
+import org.apache.lucene.search.PhraseQuery; // for javadocs
+import org.apache.lucene.search.spans.SpanQuery; // for javadocs
import java.io.Reader;
import java.io.Serializable;
@@ -48,13 +48,13 @@
* FieldInvertState)} method, the boost value is multiplied
* by the {@link
* org.apache.lucene.search.Similarity#lengthNorm(String,
- * int)} and then rounded by {@link org.apache.lucene.search.Similarity#encodeNorm(float)} before it is stored in the
+ * int)} and then rounded by {@link org.apache.lucene.search.Similarity#encodeNormValue(float)} before it is stored in the
* index. One should attempt to ensure that this product does not overflow
* the range of that encoding.
*
* @see org.apache.lucene.document.Document#setBoost(float)
* @see org.apache.lucene.search.Similarity#computeNorm(String, FieldInvertState)
- * @see org.apache.lucene.search.Similarity#encodeNorm(float)
+ * @see org.apache.lucene.search.Similarity#encodeNormValue(float)
*/
void setBoost(float boost);
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/DirectoryReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/DirectoryReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/DirectoryReader.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/DirectoryReader.java Tue Nov 24 20:26:07 2009
@@ -31,7 +31,7 @@
import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldSelector;
-import org.apache.lucene.search.DefaultSimilarity;
+import org.apache.lucene.search.Similarity;
import org.apache.lucene.store.AlreadyClosedException;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.Lock;
@@ -604,7 +604,7 @@
ensureOpen();
byte[] bytes = normsCache.get(field);
if (bytes==null && !hasNorms(field)) {
- Arrays.fill(result, offset, result.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(result, offset, result.length, Similarity.getDefault().encodeNormValue(1.0f));
} else if (bytes != null) { // cache hit
System.arraycopy(bytes, 0, result, offset, maxDoc());
} else {
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/IndexReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/IndexReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/IndexReader.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/IndexReader.java Tue Nov 24 20:26:07 2009
@@ -730,7 +730,7 @@
* this method call will silently do nothing.
*
* @see #norms(String)
- * @see Similarity#decodeNorm(byte)
+ * @see Similarity#decodeNormValue(byte)
* @throws StaleReaderException if the index has changed
* since this reader was opened
* @throws CorruptIndexException if the index is corrupt
@@ -755,7 +755,7 @@
* document.
*
* @see #norms(String)
- * @see Similarity#decodeNorm(byte)
+ * @see Similarity#decodeNormValue(byte)
*
* @throws StaleReaderException if the index has changed
* since this reader was opened
@@ -768,7 +768,7 @@
public void setNorm(int doc, String field, float value)
throws StaleReaderException, CorruptIndexException, LockObtainFailedException, IOException {
ensureOpen();
- setNorm(doc, field, Similarity.encodeNorm(value));
+ setNorm(doc, field, Similarity.getDefault().encodeNormValue(value));
}
/** Returns an enumeration of all the terms in the index. The
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/MultiReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/MultiReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/MultiReader.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/MultiReader.java Tue Nov 24 20:26:07 2009
@@ -28,7 +28,7 @@
import org.apache.lucene.index.DirectoryReader.MultiTermDocs;
import org.apache.lucene.index.DirectoryReader.MultiTermEnum;
import org.apache.lucene.index.DirectoryReader.MultiTermPositions;
-import org.apache.lucene.search.DefaultSimilarity;
+import org.apache.lucene.search.Similarity;
/** An IndexReader which reads multiple indexes, appending
* their content. */
@@ -316,7 +316,7 @@
subReaders[i].norms(field, result, offset + starts[i]);
if (bytes==null && !hasNorms(field)) {
- Arrays.fill(result, offset, result.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(result, offset, result.length, Similarity.getDefault().encodeNormValue(1.0f));
} else if (bytes != null) { // cache hit
System.arraycopy(bytes, 0, result, offset, maxDoc());
} else {
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriter.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriter.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriter.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriter.java Tue Nov 24 20:26:07 2009
@@ -37,7 +37,7 @@
final class NormsWriter extends InvertedDocEndConsumer {
- private static final byte defaultNorm = Similarity.encodeNorm(1.0f);
+ private static final byte defaultNorm = Similarity.getDefault().encodeNormValue(1.0f);
private FieldInfos fieldInfos;
@Override
public InvertedDocEndConsumerPerThread addThread(DocInverterPerThread docInverterPerThread) {
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriterPerField.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriterPerField.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriterPerField.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/NormsWriterPerField.java Tue Nov 24 20:26:07 2009
@@ -71,7 +71,7 @@
norms = ArrayUtil.grow(norms, 1+upto);
}
final float norm = docState.similarity.computeNorm(fieldInfo.name, fieldState);
- norms[upto] = Similarity.encodeNorm(norm);
+ norms[upto] = Similarity.getDefault().encodeNormValue(norm);
docIDs[upto] = docState.docID;
upto++;
}
Modified: lucene/java/trunk/src/java/org/apache/lucene/index/SegmentReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/index/SegmentReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/index/SegmentReader.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/index/SegmentReader.java Tue Nov 24 20:26:07 2009
@@ -30,7 +30,7 @@
import org.apache.lucene.document.Document;
import org.apache.lucene.document.FieldSelector;
-import org.apache.lucene.search.DefaultSimilarity;
+import org.apache.lucene.search.Similarity;
import org.apache.lucene.store.BufferedIndexInput;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.IndexInput;
@@ -1022,7 +1022,7 @@
ensureOpen();
Norm norm = norms.get(field);
if (norm == null) {
- Arrays.fill(bytes, offset, bytes.length, DefaultSimilarity.encodeNorm(1.0f));
+ Arrays.fill(bytes, offset, bytes.length, Similarity.getDefault().encodeNormValue(1.0f));
return;
}
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/MatchAllDocsQuery.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/MatchAllDocsQuery.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/MatchAllDocsQuery.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/MatchAllDocsQuery.java Tue Nov 24 20:26:07 2009
@@ -70,7 +70,7 @@
@Override
public float score() {
- return norms == null ? score : score * Similarity.decodeNorm(norms[docID()]);
+ return norms == null ? score : score * getSimilarity().decodeNormValue(norms[docID()]);
}
@Override
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/MultiPhraseQuery.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/MultiPhraseQuery.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/MultiPhraseQuery.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/MultiPhraseQuery.java Tue Nov 24 20:26:07 2009
@@ -238,7 +238,7 @@
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.norms(field);
float fieldNorm =
- fieldNorms!=null ? Similarity.decodeNorm(fieldNorms[doc]) : 1.0f;
+ fieldNorms!=null ? similarity.decodeNormValue(fieldNorms[doc]) : 1.0f;
fieldNormExpl.setValue(fieldNorm);
fieldNormExpl.setDescription("fieldNorm(field="+field+", doc="+doc+")");
fieldExpl.addDetail(fieldNormExpl);
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/PhraseQuery.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/PhraseQuery.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/PhraseQuery.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/PhraseQuery.java Tue Nov 24 20:26:07 2009
@@ -108,7 +108,7 @@
}
private class PhraseWeight extends Weight {
- private Similarity similarity;
+ private final Similarity similarity;
private float value;
private float idf;
private float queryNorm;
@@ -232,7 +232,7 @@
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.norms(field);
float fieldNorm =
- fieldNorms!=null ? Similarity.decodeNorm(fieldNorms[doc]) : 1.0f;
+ fieldNorms!=null ? similarity.decodeNormValue(fieldNorms[doc]) : 1.0f;
fieldNormExpl.setValue(fieldNorm);
fieldNormExpl.setDescription("fieldNorm(field="+field+", doc="+doc+")");
fieldExpl.addDetail(fieldNormExpl);
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/PhraseScorer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/PhraseScorer.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/PhraseScorer.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/PhraseScorer.java Tue Nov 24 20:26:07 2009
@@ -110,7 +110,7 @@
public float score() throws IOException {
//System.out.println("scoring " + first.doc);
float raw = getSimilarity().tf(freq) * value; // raw score
- return norms == null ? raw : raw * Similarity.decodeNorm(norms[first.doc]); // normalize
+ return norms == null ? raw : raw * getSimilarity().decodeNormValue(norms[first.doc]); // normalize
}
@Override
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/Scorer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/Scorer.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/Scorer.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/Scorer.java Tue Nov 24 20:26:07 2009
@@ -38,7 +38,7 @@
* with these scores.
*/
public abstract class Scorer extends DocIdSetIterator {
- private Similarity similarity;
+ private final Similarity similarity;
/** Constructs a Scorer.
* @param similarity The <code>Similarity</code> implementation used by this scorer.
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/Similarity.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/Similarity.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/Similarity.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/Similarity.java Tue Nov 24 20:26:07 2009
@@ -26,7 +26,6 @@
import java.io.IOException;
import java.io.Serializable;
import java.util.Collection;
-import java.util.IdentityHashMap;
/**
@@ -498,11 +497,11 @@
* </tr>
* </table>
* <br> <br>
- * However the resulted <i>norm</i> value is {@link #encodeNorm(float) encoded} as a single byte
+ * However the resulted <i>norm</i> value is {@link #encodeNormValue(float) encoded} as a single byte
* before being stored.
* At search time, the norm byte value is read from the index
* {@link org.apache.lucene.store.Directory directory} and
- * {@link #decodeNorm(byte) decoded} back to a float <i>norm</i> value.
+ * {@link #decodeNormValue(byte) decoded} back to a float <i>norm</i> value.
* This encoding/decoding, while reducing index size, comes with the price of
* precision loss - it is not guaranteed that <i>decode(encode(x)) = x</i>.
* For instance, <i>decode(encode(0.89)) = 0.75</i>.
@@ -563,16 +562,30 @@
NORM_TABLE[i] = SmallFloat.byte315ToFloat((byte)i);
}
- /** Decodes a normalization factor stored in an index.
- * @see #encodeNorm(float)
+ /**
+ * Decodes a normalization factor stored in an index.
+ * @see #decodeNormValue(byte)
+ * @deprecated Use {@link #decodeNormValue} instead.
*/
+ @Deprecated
public static float decodeNorm(byte b) {
return NORM_TABLE[b & 0xFF]; // & 0xFF maps negative bytes to positive above 127
}
+ /** Decodes a normalization factor stored in an index.
+ * @see #encodeNormValue(float)
+ */
+ public float decodeNormValue(byte b) {
+ return NORM_TABLE[b & 0xFF]; // & 0xFF maps negative bytes to positive above 127
+ }
+
/** Returns a table for decoding normalization bytes.
- * @see #encodeNorm(float)
+ * @see #encodeNormValue(float)
+ * @see #decodeNormValue(byte)
+ *
+ * @deprecated Use instance methods for encoding/decoding norm values to enable customization.
*/
+ @Deprecated
public static float[] getNormDecoder() {
return NORM_TABLE;
}
@@ -612,7 +625,7 @@
* <p>Note that the return values are computed under
* {@link org.apache.lucene.index.IndexWriter#addDocument(org.apache.lucene.document.Document)}
* and then stored using
- * {@link #encodeNorm(float)}.
+ * {@link #encodeNormValue(float)}.
* Thus they have limited precision, and documents
* must be re-indexed if this method is altered.
*
@@ -654,6 +667,19 @@
* @see org.apache.lucene.document.Field#setBoost(float)
* @see org.apache.lucene.util.SmallFloat
*/
+ public byte encodeNormValue(float f) {
+ return SmallFloat.floatToByte315(f);
+ }
+
+ /**
+ * Static accessor kept for backwards compability reason, use encodeNormValue instead.
+ * @param f norm-value to encode
+ * @return byte representing the given float
+ * @deprecated Use {@link #encodeNormValue} instead.
+ *
+ * @see #encodeNormValue(float)
+ */
+ @Deprecated
public static byte encodeNorm(float f) {
return SmallFloat.floatToByte315(f);
}
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/TermQuery.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/TermQuery.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/TermQuery.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/TermQuery.java Tue Nov 24 20:26:07 2009
@@ -33,7 +33,7 @@
private Term term;
private class TermWeight extends Weight {
- private Similarity similarity;
+ private final Similarity similarity;
private float value;
private float idf;
private float queryNorm;
@@ -135,7 +135,7 @@
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.norms(field);
float fieldNorm =
- fieldNorms!=null ? Similarity.decodeNorm(fieldNorms[doc]) : 1.0f;
+ fieldNorms!=null ? similarity.decodeNormValue(fieldNorms[doc]) : 1.0f;
fieldNormExpl.setValue(fieldNorm);
fieldNormExpl.setDescription("fieldNorm(field="+field+", doc="+doc+")");
fieldExpl.addDetail(fieldNormExpl);
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/TermScorer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/TermScorer.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/TermScorer.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/TermScorer.java Tue Nov 24 20:26:07 2009
@@ -25,8 +25,6 @@
*/
final class TermScorer extends Scorer {
- private static final float[] SIM_NORM_DECODER = Similarity.getNormDecoder();
-
private Weight weight;
private TermDocs termDocs;
private byte[] norms;
@@ -56,6 +54,7 @@
*/
TermScorer(Weight weight, TermDocs td, Similarity similarity, byte[] norms) {
super(similarity);
+
this.weight = weight;
this.termDocs = td;
this.norms = norms;
@@ -127,7 +126,7 @@
? scoreCache[f] // cache hit
: getSimilarity().tf(f)*weightValue; // cache miss
- return norms == null ? raw : raw * SIM_NORM_DECODER[norms[doc] & 0xFF]; // normalize for field
+ return norms == null ? raw : raw * getSimilarity().decodeNormValue(norms[doc]); // normalize for field
}
/**
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanScorer.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanScorer.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanScorer.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanScorer.java Tue Nov 24 20:26:07 2009
@@ -95,7 +95,7 @@
@Override
public float score() throws IOException {
float raw = getSimilarity().tf(freq) * value; // raw score
- return norms == null? raw : raw * Similarity.decodeNorm(norms[doc]); // normalize
+ return norms == null? raw : raw * getSimilarity().decodeNormValue(norms[doc]); // normalize
}
/** This method is no longer an official member of {@link Scorer},
Modified: lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanWeight.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanWeight.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanWeight.java (original)
+++ lucene/java/trunk/src/java/org/apache/lucene/search/spans/SpanWeight.java Tue Nov 24 20:26:07 2009
@@ -118,7 +118,7 @@
Explanation fieldNormExpl = new Explanation();
byte[] fieldNorms = reader.norms(field);
float fieldNorm =
- fieldNorms!=null ? Similarity.decodeNorm(fieldNorms[doc]) : 1.0f;
+ fieldNorms!=null ? similarity.decodeNormValue(fieldNorms[doc]) : 1.0f;
fieldNormExpl.setValue(fieldNorm);
fieldNormExpl.setDescription("fieldNorm(field="+field+", doc="+doc+")");
fieldExpl.addDetail(fieldNormExpl);
Modified: lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReader.java (original)
+++ lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReader.java Tue Nov 24 20:26:07 2009
@@ -511,7 +511,7 @@
// is open against the index:
public void testWritingNorms() throws IOException
{
- String tempDir = System.getProperty("tempDir");
+ String tempDir = "target/test";
if (tempDir == null)
throw new IOException("tempDir undefined, cannot run test");
Modified: lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderClone.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderClone.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderClone.java (original)
+++ lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderClone.java Tue Nov 24 20:26:07 2009
@@ -17,9 +17,6 @@
* limitations under the License.
*/
-import java.io.File;
-import java.io.IOException;
-
import org.apache.lucene.index.SegmentReader.Norm;
import org.apache.lucene.search.Similarity;
import org.apache.lucene.analysis.SimpleAnalyzer;
@@ -28,9 +25,7 @@
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.store.MockRAMDirectory;
-import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.util.LuceneTestCase;
-import org.apache.lucene.store.AlreadyClosedException;
/**
* Tests cloning multiple types of readers, modifying the deletedDocs and norms
@@ -273,13 +268,13 @@
* @throws Exception
*/
private void performDefaultTests(IndexReader r1) throws Exception {
- float norm1 = Similarity.decodeNorm(r1.norms("field1")[4]);
+ float norm1 = Similarity.getDefault().decodeNormValue(r1.norms("field1")[4]);
IndexReader pr1Clone = (IndexReader) r1.clone();
pr1Clone.deleteDocument(10);
pr1Clone.setNorm(4, "field1", 0.5f);
- assertTrue(Similarity.decodeNorm(r1.norms("field1")[4]) == norm1);
- assertTrue(Similarity.decodeNorm(pr1Clone.norms("field1")[4]) != norm1);
+ assertTrue(Similarity.getDefault().decodeNormValue(r1.norms("field1")[4]) == norm1);
+ assertTrue(Similarity.getDefault().decodeNormValue(pr1Clone.norms("field1")[4]) != norm1);
assertTrue(!r1.isDeleted(10));
assertTrue(pr1Clone.isDeleted(10));
@@ -426,7 +421,7 @@
TestIndexReaderReopen.createIndex(dir1, false);
IndexReader orig = IndexReader.open(dir1, false);
orig.setNorm(1, "field1", 17.0f);
- final byte encoded = Similarity.encodeNorm(17.0f);
+ final byte encoded = Similarity.getDefault().encodeNormValue(17.0f);
assertEquals(encoded, orig.norms("field1")[1]);
// the cloned segmentreader should have 2 references, 1 to itself, and 1 to
Modified: lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderCloneNorms.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderCloneNorms.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderCloneNorms.java (original)
+++ lucene/java/trunk/src/test/org/apache/lucene/index/TestIndexReaderCloneNorms.java Tue Nov 24 20:26:07 2009
@@ -216,7 +216,8 @@
}
// norm values should be different
- assertTrue(Similarity.decodeNorm(segmentReader3C.norms("field1")[5]) != Similarity.decodeNorm(segmentReader4C.norms("field1")[5]));
+ assertTrue(Similarity.getDefault().decodeNormValue(segmentReader3C.norms("field1")[5])
+ != Similarity.getDefault().decodeNormValue(segmentReader4C.norms("field1")[5]));
Norm reader4CCNorm = segmentReader4C.norms.get("field1");
assertEquals(3, reader3CCNorm.bytesRef().refCount());
assertEquals(1, reader4CCNorm.bytesRef().refCount());
@@ -283,7 +284,7 @@
assertEquals("number of norms mismatches", numDocNorms, b.length);
ArrayList storedNorms = (i == 1 ? modifiedNorms : norms);
for (int j = 0; j < b.length; j++) {
- float norm = Similarity.decodeNorm(b[j]);
+ float norm = Similarity.getDefault().decodeNormValue(b[j]);
float norm1 = ((Float) storedNorms.get(j)).floatValue();
assertEquals("stored norm value of " + field + " for doc " + j + " is "
+ norm + " - a mismatch!", norm, norm1, 0.000001);
@@ -321,7 +322,8 @@
private float nextNorm() {
float norm = lastNorm + normDelta;
do {
- float norm1 = Similarity.decodeNorm(Similarity.encodeNorm(norm));
+ float norm1 = Similarity.getDefault().decodeNormValue(
+ Similarity.getDefault().encodeNormValue(norm));
if (norm1 > lastNorm) {
// System.out.println(norm1+" > "+lastNorm);
norm = norm1;
Modified: lucene/java/trunk/src/test/org/apache/lucene/index/TestNorms.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/test/org/apache/lucene/index/TestNorms.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/test/org/apache/lucene/index/TestNorms.java (original)
+++ lucene/java/trunk/src/test/org/apache/lucene/index/TestNorms.java Tue Nov 24 20:26:07 2009
@@ -189,7 +189,7 @@
assertEquals("number of norms mismatches",numDocNorms,b.length);
ArrayList storedNorms = (i==1 ? modifiedNorms : norms);
for (int j = 0; j < b.length; j++) {
- float norm = Similarity.decodeNorm(b[j]);
+ float norm = similarityOne.decodeNormValue(b[j]);
float norm1 = ((Float)storedNorms.get(j)).floatValue();
assertEquals("stored norm value of "+field+" for doc "+j+" is "+norm+" - a mismatch!", norm, norm1, 0.000001);
}
@@ -224,7 +224,7 @@
private float nextNorm() {
float norm = lastNorm + normDelta;
do {
- float norm1 = Similarity.decodeNorm(Similarity.encodeNorm(norm));
+ float norm1 = similarityOne.decodeNormValue(similarityOne.encodeNormValue(norm));
if (norm1 > lastNorm) {
//System.out.println(norm1+" > "+lastNorm);
norm = norm1;
Modified: lucene/java/trunk/src/test/org/apache/lucene/index/TestSegmentReader.java
URL: http://svn.apache.org/viewvc/lucene/java/trunk/src/test/org/apache/lucene/index/TestSegmentReader.java?rev=883852&r1=883851&r2=883852&view=diff
==============================================================================
--- lucene/java/trunk/src/test/org/apache/lucene/index/TestSegmentReader.java (original)
+++ lucene/java/trunk/src/test/org/apache/lucene/index/TestSegmentReader.java Tue Nov 24 20:26:07 2009
@@ -26,7 +26,7 @@
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Fieldable;
-import org.apache.lucene.search.DefaultSimilarity;
+import org.apache.lucene.search.Similarity;
import org.apache.lucene.store.RAMDirectory;
public class TestSegmentReader extends LuceneTestCase {
@@ -167,7 +167,7 @@
if (!reader.hasNorms(f.name())) {
// test for fake norms of 1.0 or null depending on the flag
byte [] norms = reader.norms(f.name());
- byte norm1 = DefaultSimilarity.encodeNorm(1.0f);
+ byte norm1 = Similarity.getDefault().encodeNormValue(1.0f);
assertNull(norms);
norms = new byte[reader.maxDoc()];
reader.norms(f.name(),norms, 0);