X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/search/Similarity.java diff --git a/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/search/Similarity.java b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/search/Similarity.java new file mode 100644 index 0000000..5ae94dc --- /dev/null +++ b/lucene-java-3.5.0/lucene/src/java/org/apache/lucene/search/Similarity.java @@ -0,0 +1,921 @@ +package org.apache.lucene.search; + +/** + * 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.FieldInvertState; +import org.apache.lucene.index.Term; +import org.apache.lucene.search.Explanation.IDFExplanation; +import org.apache.lucene.util.SmallFloat; +import org.apache.lucene.util.VirtualMethod; + +import java.io.IOException; +import java.io.Serializable; +import java.util.Collection; + + +/** + * Expert: Scoring API. + * + *
Similarity defines the components of Lucene scoring. + * Overriding computation of these components is a convenient + * way to alter Lucene scoring. + * + *
Suggested reading: + * + * Introduction To Information Retrieval, Chapter 6. + * + *
The following describes how Lucene scoring evolves from + * underlying information retrieval models to (efficient) implementation. + * We first brief on VSM Score, + * then derive from it Lucene's Conceptual Scoring Formula, + * from which, finally, evolves Lucene's Practical Scoring Function + * (the latter is connected directly with Lucene classes and methods). + * + *
Lucene combines + * + * Boolean model (BM) of Information Retrieval + * with + * + * Vector Space Model (VSM) of Information Retrieval - + * documents "approved" by BM are scored by VSM. + * + *
In VSM, documents and queries are represented as + * weighted vectors in a multi-dimensional space, + * where each distinct index term is a dimension, + * and weights are + * Tf-idf values. + * + *
VSM does not require weights to be Tf-idf values, + * but Tf-idf values are believed to produce search results of high quality, + * and so Lucene is using Tf-idf. + * Tf and Idf are described in more detail below, + * but for now, for completion, let's just say that + * for given term t and document (or query) x, + * Tf(t,x) varies with the number of occurrences of term t in x + * (when one increases so does the other) and + * idf(t) similarly varies with the inverse of the + * number of index documents containing term t. + * + *
VSM score of document d for query q is the
+ *
+ * Cosine Similarity
+ * of the weighted query vectors V(q) and V(d):
+ *
+ *
+ *
+ *
| ||||||
+ * |
Note: the above equation can be viewed as the dot product of + * the normalized weighted vectors, in the sense that dividing + * V(q) by its euclidean norm is normalizing it to a unit vector. + * + *
Lucene refines VSM score for both search quality and usability: + *
Under the simplifying assumption of a single field in the index,
+ * we get Lucene's Conceptual scoring formula:
+ *
+ *
+ *
+ *
| |||||||
+ * |
The conceptual formula is a simplification in the sense that (1) terms and documents + * are fielded and (2) boosts are usually per query term rather than per query. + * + *
We now describe how Lucene implements this conceptual scoring formula, and + * derive from it Lucene's Practical Scoring Function. + * + *
For efficient score computation some scoring components + * are computed and aggregated in advance: + * + *
Lucene's Practical Scoring Function is derived from the above. + * The color codes demonstrate how it relates + * to those of the conceptual formula: + * + *
+ *
+ *
| |||||||
+ * |
where + *
+ * {@link org.apache.lucene.search.DefaultSimilarity#tf(float) tf(t in d)} = + * | + *+ * frequency½ + * | + *
+ * {@link org.apache.lucene.search.DefaultSimilarity#idf(int, int) idf(t)} = + * | + *+ * 1 + log ( + * | + *
+ *
|
+ * + * ) + * | + *
+ * queryNorm(q) = + * {@link org.apache.lucene.search.DefaultSimilarity#queryNorm(float) queryNorm(sumOfSquaredWeights)} + * = + * | + *
+ *
|
+ *
+ * {@link org.apache.lucene.search.Weight#sumOfSquaredWeights() sumOfSquaredWeights} = + * {@link org.apache.lucene.search.Query#getBoost() q.getBoost()} 2 + * · + * | + *+ * ∑ + * | + *+ * ( + * idf(t) · + * t.getBoost() + * ) 2 + * | + *
+ * | t in q | + *+ * |
+ * When a document is added to the index, all the above factors are multiplied.
+ * If the document has multiple fields with the same name, all their boosts are multiplied together:
+ *
+ *
+ *
+ * norm(t,d) = + * {@link org.apache.lucene.document.Document#getBoost() doc.getBoost()} + * · + * lengthNorm + * · + * | + *+ * ∏ + * | + *+ * {@link org.apache.lucene.document.Fieldable#getBoost() f.getBoost}() + * | + *
+ * | field f in d named as t | + *+ * |
This is initially an instance of {@link DefaultSimilarity}. + * + * @see Searcher#setSimilarity(Similarity) + * @see org.apache.lucene.index.IndexWriter#setSimilarity(Similarity) + */ + public static Similarity getDefault() { + return Similarity.defaultImpl; + } + + /** Cache of decoded bytes. */ + private static final float[] NORM_TABLE = new float[256]; + + static { + for (int i = 0; i < 256; i++) + NORM_TABLE[i] = SmallFloat.byte315ToFloat((byte)i); + } + + /** + * 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. + *
+ * WARNING: If you override this method, you should change the default + * Similarity to your implementation with {@link Similarity#setDefault(Similarity)}. + * Otherwise, your method may not always be called, especially if you omit norms + * for some fields. + * @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 #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; + } + + /** + * Computes the normalization value for a field, given the accumulated + * state of term processing for this field (see {@link FieldInvertState}). + * + *
Implementations should calculate a float value based on the field + * state and then return that value. + * + *
Matches in longer fields are less precise, so implementations of this
+ * method usually return smaller values when state.getLength()
is large,
+ * and larger values when state.getLength()
is small.
+ *
+ *
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 #encodeNormValue(float)}. + * Thus they have limited precision, and documents + * must be re-indexed if this method is altered. + * + *
For backward compatibility this method by default calls + * {@link #lengthNorm(String, int)} passing + * {@link FieldInvertState#getLength()} as the second argument, and + * then multiplies this value by {@link FieldInvertState#getBoost()}.
+ * + * @lucene.experimental + * + * @param field field name + * @param state current processing state for this field + * @return the calculated float norm + */ + public abstract float computeNorm(String field, FieldInvertState state); + + /** Computes the normalization value for a field given the total number of + * terms contained in a field. These values, together with field boosts, are + * stored in an index and multipled into scores for hits on each field by the + * search code. + * + *Matches in longer fields are less precise, so implementations of this
+ * method usually return smaller values when numTokens
is large,
+ * and larger values when numTokens
is small.
+ *
+ *
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 #encodeNormValue(float)}. + * Thus they have limited precision, and documents + * must be re-indexed if this method is altered. + * + * @param fieldName the name of the field + * @param numTokens the total number of tokens contained in fields named + * fieldName of doc. + * @return a normalization factor for hits on this field of this document + * + * @see org.apache.lucene.document.Field#setBoost(float) + * + * @deprecated Please override computeNorm instead + */ + @Deprecated + public final float lengthNorm(String fieldName, int numTokens) { + throw new UnsupportedOperationException("please use computeNorm instead"); + } + + /** Computes the normalization value for a query given the sum of the squared + * weights of each of the query terms. This value is multiplied into the + * weight of each query term. While the classic query normalization factor is + * computed as 1/sqrt(sumOfSquaredWeights), other implementations might + * completely ignore sumOfSquaredWeights (ie return 1). + * + *
This does not affect ranking, but the default implementation does make scores + * from different queries more comparable than they would be by eliminating the + * magnitude of the Query vector as a factor in the score. + * + * @param sumOfSquaredWeights the sum of the squares of query term weights + * @return a normalization factor for query weights + */ + public abstract float queryNorm(float sumOfSquaredWeights); + + /** Encodes a normalization factor for storage in an index. + * + *
The encoding uses a three-bit mantissa, a five-bit exponent, and + * the zero-exponent point at 15, thus + * representing values from around 7x10^9 to 2x10^-9 with about one + * significant decimal digit of accuracy. Zero is also represented. + * Negative numbers are rounded up to zero. Values too large to represent + * are rounded down to the largest representable value. Positive values too + * small to represent are rounded up to the smallest positive representable + * value. + *
+ * WARNING: If you override this method, you should change the default + * Similarity to your implementation with {@link Similarity#setDefault(Similarity)}. + * Otherwise, your method may not always be called, especially if you omit norms + * for some fields. + * @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); + } + + + /** Computes a score factor based on a term or phrase's frequency in a + * document. This value is multiplied by the {@link #idf(int, int)} + * factor for each term in the query and these products are then summed to + * form the initial score for a document. + * + *
Terms and phrases repeated in a document indicate the topic of the
+ * document, so implementations of this method usually return larger values
+ * when freq
is large, and smaller values when freq
+ * is small.
+ *
+ *
The default implementation calls {@link #tf(float)}. + * + * @param freq the frequency of a term within a document + * @return a score factor based on a term's within-document frequency + */ + public float tf(int freq) { + return tf((float)freq); + } + + /** Computes the amount of a sloppy phrase match, based on an edit distance. + * This value is summed for each sloppy phrase match in a document to form + * the frequency that is passed to {@link #tf(float)}. + * + *
A phrase match with a small edit distance to a document passage more + * closely matches the document, so implementations of this method usually + * return larger values when the edit distance is small and smaller values + * when it is large. + * + * @see PhraseQuery#setSlop(int) + * @param distance the edit distance of this sloppy phrase match + * @return the frequency increment for this match + */ + public abstract float sloppyFreq(int distance); + + /** Computes a score factor based on a term or phrase's frequency in a + * document. This value is multiplied by the {@link #idf(int, int)} + * factor for each term in the query and these products are then summed to + * form the initial score for a document. + * + *
Terms and phrases repeated in a document indicate the topic of the
+ * document, so implementations of this method usually return larger values
+ * when freq
is large, and smaller values when freq
+ * is small.
+ *
+ * @param freq the frequency of a term within a document
+ * @return a score factor based on a term's within-document frequency
+ */
+ public abstract float tf(float freq);
+
+
+ /**
+ * Computes a score factor for a simple term and returns an explanation
+ * for that score factor.
+ *
+ *
+ * The default implementation uses: + * + *
+ * idf(searcher.docFreq(term), searcher.maxDoc()); + *+ * + * Note that {@link Searcher#maxDoc()} is used instead of + * {@link org.apache.lucene.index.IndexReader#numDocs() IndexReader#numDocs()} because also + * {@link Searcher#docFreq(Term)} is used, and when the latter + * is inaccurate, so is {@link Searcher#maxDoc()}, and in the same direction. + * In addition, {@link Searcher#maxDoc()} is more efficient to compute + * + * @param term the term in question + * @param searcher the document collection being searched + * @return an IDFExplain object that includes both an idf score factor + and an explanation for the term. + * @throws IOException + */ + public IDFExplanation idfExplain(final Term term, final Searcher searcher, int docFreq) throws IOException { + + if (!hasIDFExplainWithDocFreqAPI) { + // Fallback to slow impl + return idfExplain(term, searcher); + } + final int df = docFreq; + final int max = searcher.maxDoc(); + final float idf = idf(df, max); + return new IDFExplanation() { + @Override + public String explain() { + return "idf(docFreq=" + df + + ", maxDocs=" + max + ")"; + } + @Override + public float getIdf() { + return idf; + }}; + } + + /** + * This method forwards to {@link + * #idfExplain(Term,Searcher,int)} by passing + *
searcher.docFreq(term)
as the docFreq.
+ *
+ * WARNING: if you subclass Similariary and override this
+ * method then you may hit a peformance hit for certain
+ * queries. Better to override {@link
+ * #idfExplain(Term,Searcher,int)} instead.
+ */
+ public IDFExplanation idfExplain(final Term term, final Searcher searcher) throws IOException {
+ return idfExplain(term, searcher, searcher.docFreq(term));
+ }
+
+ /**
+ * Computes a score factor for a phrase.
+ *
+ *
+ * The default implementation sums the idf factor for
+ * each term in the phrase.
+ *
+ * @param terms the terms in the phrase
+ * @param searcher the document collection being searched
+ * @return an IDFExplain object that includes both an idf
+ * score factor for the phrase and an explanation
+ * for each term.
+ * @throws IOException
+ */
+ public IDFExplanation idfExplain(Collection Terms that occur in fewer documents are better indicators of topic, so
+ * implementations of this method usually return larger values for rare terms,
+ * and smaller values for common terms.
+ *
+ * @param docFreq the number of documents which contain the term
+ * @param numDocs the total number of documents in the collection
+ * @return a score factor based on the term's document frequency
+ */
+ public abstract float idf(int docFreq, int numDocs);
+
+ /** Computes a score factor based on the fraction of all query terms that a
+ * document contains. This value is multiplied into scores.
+ *
+ * The presence of a large portion of the query terms indicates a better
+ * match with the query, so implementations of this method usually return
+ * larger values when the ratio between these parameters is large and smaller
+ * values when the ratio between them is small.
+ *
+ * @param overlap the number of query terms matched in the document
+ * @param maxOverlap the total number of terms in the query
+ * @return a score factor based on term overlap with the query
+ */
+ public abstract float coord(int overlap, int maxOverlap);
+
+ /**
+ * Calculate a scoring factor based on the data in the payload. Overriding implementations
+ * are responsible for interpreting what is in the payload. Lucene makes no assumptions about
+ * what is in the byte array.
+ *
+ * The default implementation returns 1.
+ *
+ * @param docId The docId currently being scored. If this value is {@link #NO_DOC_ID_PROVIDED}, then it should be assumed that the PayloadQuery implementation does not provide document information
+ * @param fieldName The fieldName of the term this payload belongs to
+ * @param start The start position of the payload
+ * @param end The end position of the payload
+ * @param payload The payload byte array to be scored
+ * @param offset The offset into the payload array
+ * @param length The length in the array
+ * @return An implementation dependent float to be used as a scoring factor
+ *
+ */
+ public float scorePayload(int docId, String fieldName, int start, int end, byte [] payload, int offset, int length)
+ {
+ return 1;
+ }
+
+}