From 986934c44d25045f148d5ca8fb85fc0440a6af8f Mon Sep 17 00:00:00 2001 From: Daniel Naber Date: Sun, 1 Aug 2004 22:19:59 +0000 Subject: [PATCH] adding a testcase for FuzzyQuery CVS: ---------------------------------------------------------------------- CVS: PR: CVS: If this change addresses a PR in the problem report tracking CVS: database, then enter the PR number(s) here. CVS: Obtained from: CVS: If this change has been taken from another system, such as NCSA, CVS: then name the system in this line, otherwise delete it. CVS: Submitted by: CVS: If this code has been contributed to Apache by someone else; i.e., CVS: they sent us a patch or a new module, then include their name/email CVS: address here. If this is your work then delete this line. CVS: Reviewed by: CVS: If we are doing pre-commit code reviews and someone else has CVS: reviewed your changes, include their name(s) here. CVS: If you have not had it reviewed then delete this line. git-svn-id: https://svn.apache.org/repos/asf/lucene/java/trunk@150378 13f79535-47bb-0310-9956-ffa450edef68 --- .../apache/lucene/search/TestFuzzyQuery.java | 137 ++++++++++++++++++ 1 file changed, 137 insertions(+) create mode 100644 src/test/org/apache/lucene/search/TestFuzzyQuery.java diff --git a/src/test/org/apache/lucene/search/TestFuzzyQuery.java b/src/test/org/apache/lucene/search/TestFuzzyQuery.java new file mode 100644 index 00000000000..9091b24583f --- /dev/null +++ b/src/test/org/apache/lucene/search/TestFuzzyQuery.java @@ -0,0 +1,137 @@ +package org.apache.lucene.search; + +/** + * 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. + */ + +import java.io.IOException; + +import junit.framework.TestCase; +import org.apache.lucene.analysis.WhitespaceAnalyzer; +import org.apache.lucene.document.Document; +import org.apache.lucene.document.Field; +import org.apache.lucene.index.IndexWriter; +import org.apache.lucene.index.Term; +import org.apache.lucene.store.RAMDirectory; + +/** + * Tests {@link FuzzyQuery}. + * + * @author Daniel Naber + */ +public class TestFuzzyQuery extends TestCase { + + public void testDefaultFuzziness() throws Exception { + RAMDirectory directory = new RAMDirectory(); + IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true); + addDoc("aaaaa", writer); + addDoc("aaaab", writer); + addDoc("aaabb", writer); + addDoc("aabbb", writer); + addDoc("abbbb", writer); + addDoc("bbbbb", writer); + addDoc("ddddd", writer); + writer.optimize(); + writer.close(); + IndexSearcher searcher = new IndexSearcher(directory); + + FuzzyQuery query = new FuzzyQuery(new Term("field", "aaaaa")); + Hits hits = searcher.search(query); + assertEquals(3, hits.length()); + + // not similar enough: + query = new FuzzyQuery(new Term("field", "xxxxx")); + hits = searcher.search(query); + assertEquals(0, hits.length()); + query = new FuzzyQuery(new Term("field", "aaccc")); // edit distance to "aaaaa" = 3 + hits = searcher.search(query); + assertEquals(0, hits.length()); + + // query identical to a word in the index: + query = new FuzzyQuery(new Term("field", "aaaaa")); + hits = searcher.search(query); + assertEquals(3, hits.length()); + assertEquals(hits.doc(0).get("field"), ("aaaaa")); + // default allows for up to two edits: + assertEquals(hits.doc(1).get("field"), ("aaaab")); + assertEquals(hits.doc(2).get("field"), ("aaabb")); + + // query similar to a word in the index: + query = new FuzzyQuery(new Term("field", "aaaac")); + hits = searcher.search(query); + assertEquals(3, hits.length()); + assertEquals(hits.doc(0).get("field"), ("aaaaa")); + assertEquals(hits.doc(1).get("field"), ("aaaab")); + assertEquals(hits.doc(2).get("field"), ("aaabb")); + + query = new FuzzyQuery(new Term("field", "ddddX")); + hits = searcher.search(query); + assertEquals(1, hits.length()); + assertEquals(hits.doc(0).get("field"), ("ddddd")); + + // different field = no match: + query = new FuzzyQuery(new Term("anotherfield", "ddddX")); + hits = searcher.search(query); + assertEquals(0, hits.length()); + + searcher.close(); + directory.close(); + } + + public void testDefaultFuzzinessLong() throws Exception { + RAMDirectory directory = new RAMDirectory(); + IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(), true); + addDoc("aaaaaaa", writer); + addDoc("segment", writer); + writer.optimize(); + writer.close(); + IndexSearcher searcher = new IndexSearcher(directory); + + FuzzyQuery query; + // not similar enough: + query = new FuzzyQuery(new Term("field", "xxxxx")); + Hits hits = searcher.search(query); + assertEquals(0, hits.length()); + // edit distance to "aaaaaaa" = 3, this matches because the string is longer than + // in testDefaultFuzziness so a bigger difference is allowed: + query = new FuzzyQuery(new Term("field", "aaaaccc")); + hits = searcher.search(query); + assertEquals(1, hits.length()); + assertEquals(hits.doc(0).get("field"), ("aaaaaaa")); + + // no match, more than half of the characters is wrong: + query = new FuzzyQuery(new Term("field", "aaacccc")); + hits = searcher.search(query); + assertEquals(0, hits.length()); + + // "student" and "stellent" are indeed similar to "segment" by default: + query = new FuzzyQuery(new Term("field", "student")); + hits = searcher.search(query); + assertEquals(1, hits.length()); + query = new FuzzyQuery(new Term("field", "stellent")); + hits = searcher.search(query); + assertEquals(1, hits.length()); + + searcher.close(); + directory.close(); + } + + private void addDoc(String text, IndexWriter writer) throws IOException { + Document doc = new Document(); + doc.add(Field.Text("field", text)); + writer.addDocument(doc); + } + +}