lucene-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From rm...@apache.org
Subject svn commit: r966574 - /lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java
Date Thu, 22 Jul 2010 11:00:48 GMT
Author: rmuir
Date: Thu Jul 22 11:00:48 2010
New Revision: 966574

URL: http://svn.apache.org/viewvc?rev=966574&view=rev
Log:
add random prefixquerytest (hopefully easy to debug preflex issues with)

Added:
    lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java   (with
props)

Added: lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java?rev=966574&view=auto
==============================================================================
--- lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java (added)
+++ lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java Thu Jul
22 11:00:48 2010
@@ -0,0 +1,131 @@
+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 java.io.IOException;
+import java.util.Random;
+
+import org.apache.lucene.analysis.MockAnalyzer;
+import org.apache.lucene.analysis.MockTokenizer;
+import org.apache.lucene.document.Document;
+import org.apache.lucene.document.Field;
+import org.apache.lucene.index.IndexReader;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.index.Term;
+import org.apache.lucene.index.TermsEnum;
+import org.apache.lucene.index.RandomIndexWriter;
+import org.apache.lucene.store.Directory;
+import org.apache.lucene.store.MockRAMDirectory;
+import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.LuceneTestCase;
+import org.apache.lucene.util._TestUtil;
+
+/**
+ * Create an index with random unicode terms
+ * Generates random prefix queries, and validates against a simple impl.
+ */
+public class TestPrefixRandom extends LuceneTestCase {
+  private IndexSearcher searcher;
+  private IndexReader reader;
+  private Directory dir;
+  private Random random;
+  
+  @Override
+  protected void setUp() throws Exception {
+    super.setUp();
+    random = newRandom();
+    dir = new MockRAMDirectory();
+    // TODO: fix mocktokenizer to not extend chartokenizer, so you can have an 'empty' keyword.
+    RandomIndexWriter writer = new RandomIndexWriter(random, dir, 
+        new IndexWriterConfig(TEST_VERSION_CURRENT, new MockAnalyzer(MockTokenizer.KEYWORD,
false)));
+    
+    Document doc = new Document();
+    Field field = new Field("field", "", Field.Store.NO, Field.Index.ANALYZED);
+    doc.add(field);
+
+    for (int i = 0; i < 2000*_TestUtil.getRandomMultiplier(); i++) {
+      field.setValue(_TestUtil.randomUnicodeString(random, 10));
+      writer.addDocument(doc);
+    }
+    reader = writer.getReader();
+    searcher = new IndexSearcher(reader);
+    writer.close();
+  }
+
+  @Override
+  protected void tearDown() throws Exception {
+    reader.close();
+    searcher.close();
+    dir.close();
+    super.tearDown();
+  }
+  
+  /** a stupid prefix query that just blasts thru the terms */
+  private class DumbPrefixQuery extends MultiTermQuery {
+    private final BytesRef prefix;
+    
+    DumbPrefixQuery(Term term) {
+      super(term.field());
+      prefix = term.bytes();
+    }
+    
+    @Override
+    protected TermsEnum getTermsEnum(IndexReader reader) throws IOException {
+      return new SimplePrefixTermsEnum(reader, field, prefix);
+    }
+
+    private class SimplePrefixTermsEnum extends FilteredTermsEnum {
+      private final BytesRef prefix;
+
+      private SimplePrefixTermsEnum(IndexReader reader, 
+          String field, BytesRef prefix) throws IOException {
+        super(reader, field);
+        this.prefix = prefix;
+        setInitialSeekTerm(new BytesRef(""));
+      }
+      
+      @Override
+      protected AcceptStatus accept(BytesRef term) throws IOException {
+        return term.startsWith(prefix) ? AcceptStatus.YES : AcceptStatus.NO;
+      }
+    }
+
+    @Override
+    public String toString(String field) {
+      return field.toString() + ":" + prefix.toString();
+    }
+  }
+  
+  /** test a bunch of random prefixes */
+  public void testPrefixes() throws Exception {
+      for (int i = 0; i < 1000*_TestUtil.getRandomMultiplier(); i++)
+        assertSame(_TestUtil.randomUnicodeString(random, 5));
+  }
+  
+  /** check that the # of hits is the same as from a very
+   * simple prefixquery implementation.
+   */
+  private void assertSame(String prefix) throws IOException {   
+    PrefixQuery smart = new PrefixQuery(new Term("field", prefix));
+    DumbPrefixQuery dumb = new DumbPrefixQuery(new Term("field", prefix));
+    
+    TopDocs smartDocs = searcher.search(smart, 25);
+    TopDocs dumbDocs = searcher.search(dumb, 25);
+    CheckHits.checkEqual(smart, smartDocs.scoreDocs, dumbDocs.scoreDocs);
+  }
+}

Propchange: lucene/dev/trunk/lucene/src/test/org/apache/lucene/search/TestPrefixRandom.java
------------------------------------------------------------------------------
    svn:eol-style = native



Mime
View raw message