X-Git-Url: https://git.mdrn.pl/pylucene.git/blobdiff_plain/a2e61f0c04805cfcb8706176758d1283c7e3a55c..aaeed5504b982cf3545252ab528713250aa33eed:/lucene-java-3.5.0/lucene/contrib/queries/src/java/org/apache/lucene/search/similar/SimilarityQueries.java?ds=inline diff --git a/lucene-java-3.5.0/lucene/contrib/queries/src/java/org/apache/lucene/search/similar/SimilarityQueries.java b/lucene-java-3.5.0/lucene/contrib/queries/src/java/org/apache/lucene/search/similar/SimilarityQueries.java new file mode 100644 index 0000000..30feb3b --- /dev/null +++ b/lucene-java-3.5.0/lucene/contrib/queries/src/java/org/apache/lucene/search/similar/SimilarityQueries.java @@ -0,0 +1,114 @@ +/** + * Copyright 2004 The Apache Software Foundation. + * + * Licensed 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. + */ +package org.apache.lucene.search.similar; + +import java.io.IOException; +import java.io.StringReader; +import java.util.HashSet; +import java.util.Set; + +import org.apache.lucene.analysis.Analyzer; +import org.apache.lucene.analysis.TokenStream; +import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.apache.lucene.index.Term; +import org.apache.lucene.search.BooleanClause; +import org.apache.lucene.search.BooleanQuery; +import org.apache.lucene.search.IndexSearcher; +import org.apache.lucene.search.Query; +import org.apache.lucene.search.TermQuery; + +/** + * Simple similarity measures. + * + * @see MoreLikeThis + */ +public final class SimilarityQueries +{ + /** + * + */ + private SimilarityQueries() + { + } + + /** + * Simple similarity query generators. + * Takes every unique word and forms a boolean query where all words are optional. + * After you get this you'll use to to query your {@link IndexSearcher} for similar docs. + * The only caveat is the first hit returned should be your source document - you'll + * need to then ignore that. + * + *
+ * So, if you have a code fragment like this:
+ *
+ *
+ * Query q = formSimilaryQuery( "I use Lucene to search fast. Fast searchers are good", new StandardAnalyzer(), "contents", null);
+ *
+ *
+ *
+ * The query returned, in string form, will be '(i use lucene to search fast searchers are good')
.
+ *
+ *
+ * The philosophy behind this method is "two documents are similar if they share lots of words". + * Note that behind the scenes, Lucene's scoring algorithm will tend to give two documents a higher similarity score if the share more uncommon words. + * + *
+ * This method is fail-safe in that if a long 'body' is passed in and
+ * {@link BooleanQuery#add BooleanQuery.add()} (used internally)
+ * throws
+ * {@link org.apache.lucene.search.BooleanQuery.TooManyClauses BooleanQuery.TooManyClauses}, the
+ * query as it is will be returned.
+ *
+ * @param body the body of the document you want to find similar documents to
+ * @param a the analyzer to use to parse the body
+ * @param field the field you want to search on, probably something like "contents" or "body"
+ * @param stop optional set of stop words to ignore
+ * @return a query with all unique words in 'body'
+ * @throws IOException this can't happen...
+ */
+ public static Query formSimilarQuery( String body,
+ Analyzer a,
+ String field,
+ Set> stop)
+ throws IOException
+ {
+ TokenStream ts = a.reusableTokenStream( field, new StringReader( body));
+ CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
+
+ BooleanQuery tmp = new BooleanQuery();
+ Set