You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@lucene.apache.org by ot...@apache.org on 2003/01/04 18:13:40 UTC
cvs commit: jakarta-lucene/src/test/org/apache/lucene/index TestIndexReader.java
otis 2003/01/04 09:13:40
Modified: src/java/org/apache/lucene/index IndexReader.java
SegmentReader.java SegmentsReader.java
Added: src/test/org/apache/lucene/index TestIndexReader.java
Log:
- Applied patches from http://nagoya.apache.org/bugzilla/show_bug.cgi?id=14900
All unit tests still pass.
PR: 14900
Submitted by: Peter Mularien
Reviewed by: Otis
Revision Changes Path
1.12 +10 -0 jakarta-lucene/src/java/org/apache/lucene/index/IndexReader.java
Index: IndexReader.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/java/org/apache/lucene/index/IndexReader.java,v
retrieving revision 1.11
retrieving revision 1.12
diff -u -r1.11 -r1.12
--- IndexReader.java 7 Nov 2002 05:55:39 -0000 1.11
+++ IndexReader.java 4 Jan 2003 17:13:39 -0000 1.12
@@ -56,6 +56,8 @@
import java.io.IOException;
import java.io.File;
+import java.util.Collection;
+
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.Lock;
@@ -301,6 +303,14 @@
writeLock = null;
}
}
+
+ /**
+ * Return a list of all unique field names which exist in the index pointed to by
+ * this IndexReader.
+ * @return Collection of Strings indicating the names of the fields
+ * @throws IOException if there is a problem with accessing the index
+ */
+ public abstract Collection getFieldNames() throws IOException;
/**
* Returns <code>true</code> iff the index in the named directory is
1.7 +20 -7 jakarta-lucene/src/java/org/apache/lucene/index/SegmentReader.java
Index: SegmentReader.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/java/org/apache/lucene/index/SegmentReader.java,v
retrieving revision 1.6
retrieving revision 1.7
diff -u -r1.6 -r1.7
--- SegmentReader.java 7 Nov 2002 05:55:39 -0000 1.6
+++ SegmentReader.java 4 Jan 2003 17:13:39 -0000 1.7
@@ -55,15 +55,17 @@
*/
import java.io.IOException;
-import java.util.Hashtable;
+import java.util.Collection;
import java.util.Enumeration;
+import java.util.HashSet;
+import java.util.Hashtable;
+import java.util.Set;
import java.util.Vector;
-import org.apache.lucene.util.BitVector;
-import org.apache.lucene.store.Directory;
-import org.apache.lucene.store.Lock;
-import org.apache.lucene.store.InputStream;
import org.apache.lucene.document.Document;
+import org.apache.lucene.store.InputStream;
+import org.apache.lucene.store.Lock;
+import org.apache.lucene.util.BitVector;
final class SegmentReader extends IndexReader {
private boolean closeDirectory = false;
@@ -73,7 +75,7 @@
private FieldsReader fieldsReader;
TermInfosReader tis;
-
+
BitVector deletedDocs = null;
private boolean deletedDocsDirty = false;
@@ -113,7 +115,7 @@
proxStream = directory.openFile(segment + ".prx");
openNorms();
}
-
+
final synchronized void doClose() throws IOException {
if (deletedDocsDirty) {
synchronized (directory) { // in- & inter-process sync
@@ -271,4 +273,15 @@
}
}
}
+
+ // javadoc inherited
+ public Collection getFieldNames() throws IOException {
+ // maintain a unique set of field names
+ Set fieldSet = new HashSet();
+ for (int i = 0; i < fieldInfos.size(); i++) {
+ FieldInfo fi = fieldInfos.fieldInfo(i);
+ fieldSet.add(fi.name);
+ }
+ return fieldSet;
+ }
}
1.10 +22 -2 jakarta-lucene/src/java/org/apache/lucene/index/SegmentsReader.java
Index: SegmentsReader.java
===================================================================
RCS file: /home/cvs/jakarta-lucene/src/java/org/apache/lucene/index/SegmentsReader.java,v
retrieving revision 1.9
retrieving revision 1.10
diff -u -r1.9 -r1.10
--- SegmentsReader.java 7 Nov 2002 05:55:39 -0000 1.9
+++ SegmentsReader.java 4 Jan 2003 17:13:39 -0000 1.10
@@ -55,10 +55,14 @@
*/
import java.io.IOException;
+import java.util.Collection;
+import java.util.HashSet;
import java.util.Hashtable;
+import java.util.Iterator;
+import java.util.Set;
-import org.apache.lucene.store.Directory;
import org.apache.lucene.document.Document;
+import org.apache.lucene.store.Directory;
/**
* FIXME: Describe class <code>SegmentsReader</code> here.
@@ -174,6 +178,22 @@
for (int i = 0; i < readers.length; i++)
readers[i].close();
}
+
+ // javadoc inherited
+ public Collection getFieldNames() throws IOException {
+ // maintain a unique set of field names
+ Set fieldSet = new HashSet();
+ for (int i = 0; i < readers.length; i++) {
+ SegmentReader reader = readers[i];
+ Collection names = reader.getFieldNames();
+ // iterate through the field names and add them to the set
+ for (Iterator iterator = names.iterator(); iterator.hasNext();) {
+ String s = (String) iterator.next();
+ fieldSet.add(s);
+ }
+ }
+ return fieldSet;
+ }
}
class SegmentsTermEnum extends TermEnum {
1.1 jakarta-lucene/src/test/org/apache/lucene/index/TestIndexReader.java
Index: TestIndexReader.java
===================================================================
package org.apache.lucene.index;
import junit.framework.TestCase;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import java.util.Collection;
import java.io.IOException;
/* ====================================================================
* The Apache Software License, Version 1.1
*
* Copyright (c) 2003 The Apache Software Foundation. All rights
* reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
*
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
*
* 3. The end-user documentation included with the redistribution,
* if any, must include the following acknowledgment:
* "This product includes software developed by the
* Apache Software Foundation (http://www.apache.org/)."
* Alternately, this acknowledgment may appear in the software itself,
* if and wherever such third-party acknowledgments normally appear.
*
* 4. The names "Apache" and "Apache Software Foundation" and
* "Apache Lucene" must not be used to endorse or promote products
* derived from this software without prior written permission. For
* written permission, please contact apache@apache.org.
*
* 5. Products derived from this software may not be called "Apache",
* "Apache Lucene", nor may "Apache" appear in their name, without
* prior written permission of the Apache Software Foundation.
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
* ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
* USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
* OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
* OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
* ====================================================================
*
* This software consists of voluntary contributions made by many
* individuals on behalf of the Apache Software Foundation. For more
* information on the Apache Software Foundation, please see
* <http://www.apache.org/>.
*/
public class TestIndexReader extends TestCase
{
/**
* Tests the IndexReader.getFieldNames implementation
* @throws Exception on error
*/
public void testGetFieldNames() throws Exception
{
RAMDirectory d = new RAMDirectory();
// set up writer
IndexWriter writer = new IndexWriter(d, new StandardAnalyzer(), true);
addDocumentWithFields(writer);
writer.close();
// set up reader
IndexReader reader = IndexReader.open(d);
Collection fieldNames = reader.getFieldNames();
assertTrue(fieldNames.contains("keyword"));
assertTrue(fieldNames.contains("text"));
assertTrue(fieldNames.contains("unindexed"));
assertTrue(fieldNames.contains("unstored"));
// add more documents
writer = new IndexWriter(d, new StandardAnalyzer(), false);
// want to get some more segments here
for (int i=0;i<5*writer.mergeFactor;i++)
{
addDocumentWithFields(writer);
}
// new fields are in some different segments (we hope)
for (int i=0;i<5*writer.mergeFactor;i++)
{
addDocumentWithDifferentFields(writer);
}
writer.close();
// verify fields again
reader = IndexReader.open(d);
fieldNames = reader.getFieldNames();
assertTrue(fieldNames.contains("keyword"));
assertTrue(fieldNames.contains("text"));
assertTrue(fieldNames.contains("unindexed"));
assertTrue(fieldNames.contains("unstored"));
assertTrue(fieldNames.contains("keyword2"));
assertTrue(fieldNames.contains("text2"));
assertTrue(fieldNames.contains("unindexed2"));
assertTrue(fieldNames.contains("unstored2"));
}
private void addDocumentWithFields(IndexWriter writer) throws IOException
{
Document doc = new Document();
doc.add(Field.Keyword("keyword","test1"));
doc.add(Field.Text("text","test1"));
doc.add(Field.UnIndexed("unindexed","test1"));
doc.add(Field.UnStored("unstored","test1"));
writer.addDocument(doc);
}
private void addDocumentWithDifferentFields(IndexWriter writer) throws IOException
{
Document doc = new Document();
doc.add(Field.Keyword("keyword2","test1"));
doc.add(Field.Text("text2","test1"));
doc.add(Field.UnIndexed("unindexed2","test1"));
doc.add(Field.UnStored("unstored2","test1"));
writer.addDocument(doc);
}
}
--
To unsubscribe, e-mail: <ma...@jakarta.apache.org>
For additional commands, e-mail: <ma...@jakarta.apache.org>