[dna-commits] DNA SVN: r1337 - in trunk/dna-search: src/main/java/org/jboss/dna/search and 1 other directories.
dna-commits at lists.jboss.org
dna-commits at lists.jboss.org
Tue Nov 24 12:43:33 EST 2009
Author: rhauch
Date: 2009-11-24 12:43:33 -0500 (Tue, 24 Nov 2009)
New Revision: 1337
Added:
trunk/dna-search/src/test/java/org/jboss/dna/search/SearchEngineTest.java
Modified:
trunk/dna-search/pom.xml
trunk/dna-search/src/main/java/org/jboss/dna/search/DualIndexSearchProvider.java
Log:
DNA-467 Changed the implementation of the method to delete nodes under a specified branch, and added several test cases to verify that the content can be indexed, re-indexed (multiple times), and searched.
Modified: trunk/dna-search/pom.xml
===================================================================
--- trunk/dna-search/pom.xml 2009-11-24 02:19:50 UTC (rev 1336)
+++ trunk/dna-search/pom.xml 2009-11-24 17:43:33 UTC (rev 1337)
@@ -45,22 +45,22 @@
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-core</artifactId>
- <version>2.9.0</version>
+ <version>2.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-analyzers</artifactId>
- <version>2.9.0</version>
+ <version>2.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-snowball</artifactId>
- <version>2.9.0</version>
+ <version>2.9.1</version>
</dependency>
<dependency>
<groupId>org.apache.lucene</groupId>
<artifactId>lucene-regex</artifactId>
- <version>2.9.0</version>
+ <version>2.9.1</version>
</dependency>
<!--
Testing (note the scope)
Modified: trunk/dna-search/src/main/java/org/jboss/dna/search/DualIndexSearchProvider.java
===================================================================
--- trunk/dna-search/src/main/java/org/jboss/dna/search/DualIndexSearchProvider.java 2009-11-24 02:19:50 UTC (rev 1336)
+++ trunk/dna-search/src/main/java/org/jboss/dna/search/DualIndexSearchProvider.java 2009-11-24 17:43:33 UTC (rev 1337)
@@ -134,7 +134,7 @@
static {
IndexRules.Builder builder = IndexRules.createBuilder();
// Configure the default behavior ...
- builder.defaultTo(IndexRules.INDEX | IndexRules.ANALYZE);
+ builder.defaultTo(IndexRules.INDEX | IndexRules.ANALYZE | IndexRules.FULL_TEXT);
// Configure the UUID properties to be just indexed (not stored, not analyzed, not included in full-text) ...
builder.store(JcrLexicon.UUID, DnaLexicon.UUID);
// Configure the properties that we'll treat as dates ...
@@ -324,7 +324,13 @@
protected IndexWriter getPathsWriter() throws IOException {
assert !readOnly;
if (pathsWriter == null) {
- pathsWriter = new IndexWriter(pathsIndexDirectory, analyzer, overwrite, MaxFieldLength.UNLIMITED);
+ if (overwrite) {
+ // Always overwrite it ...
+ pathsWriter = new IndexWriter(pathsIndexDirectory, analyzer, overwrite, MaxFieldLength.UNLIMITED);
+ } else {
+ // Don't overwrite, but create if missing ...
+ pathsWriter = new IndexWriter(pathsIndexDirectory, analyzer, MaxFieldLength.UNLIMITED);
+ }
}
return pathsWriter;
}
@@ -332,7 +338,13 @@
protected IndexWriter getContentWriter() throws IOException {
assert !readOnly;
if (contentWriter == null) {
- contentWriter = new IndexWriter(contentIndexDirectory, analyzer, overwrite, MaxFieldLength.UNLIMITED);
+ if (overwrite) {
+ // Always overwrite it ...
+ contentWriter = new IndexWriter(contentIndexDirectory, analyzer, overwrite, MaxFieldLength.UNLIMITED);
+ } else {
+ // Don't overwrite, but create if missing ...
+ contentWriter = new IndexWriter(contentIndexDirectory, analyzer, MaxFieldLength.UNLIMITED);
+ }
}
return contentWriter;
}
@@ -492,33 +504,14 @@
*/
public int deleteBelow( Path path ) {
assert !readOnly;
- // Perform a query using the reader to find those nodes at/below the path ...
try {
- IndexReader pathReader = getPathsReader();
- IndexSearcher pathSearcher = new IndexSearcher(pathReader);
- String pathStr = stringFactory.create(path) + "/";
- PrefixQuery query = new PrefixQuery(new Term(PathIndex.PATH, pathStr));
- int numberDeleted = 0;
- while (true) {
- // Execute the query and get the results ...
- TopDocs results = pathSearcher.search(query, SIZE_OF_DELETE_BATCHES);
- int numResultsInBatch = results.scoreDocs.length;
- // Walk the results, delete the doc, and add to the query that we'll use against the content index ...
- IndexReader contentReader = getContentReader();
- for (ScoreDoc result : results.scoreDocs) {
- int docId = result.doc;
- // Find the UUID of the node ...
- Document doc = pathReader.document(docId, UUID_FIELD_SELECTOR);
- String uuid = doc.get(PathIndex.UUID);
- // Delete the document from the paths index ...
- pathReader.deleteDocument(docId);
- // Delete the corresponding document from the content index ...
- contentReader.deleteDocuments(new Term(ContentIndex.UUID, uuid));
- }
- numberDeleted += numResultsInBatch;
- if (numResultsInBatch < SIZE_OF_DELETE_BATCHES) break;
- }
- return numberDeleted;
+ // Create a query to find all the nodes at or below the specified path ...
+ Set<UUID> uuids = getUuidsForDescendantsOf(path, true);
+ Query uuidQuery = findAllNodesWithUuids(uuids);
+ // Now delete the documents from each index using this query, which we can reuse ...
+ getPathsWriter().deleteDocuments(uuidQuery);
+ getContentWriter().deleteDocuments(uuidQuery);
+ return uuids.size();
} catch (FileNotFoundException e) {
// There are no index files yet, so nothing to delete ...
return 0;
@@ -628,42 +621,42 @@
}
}
if (pathsWriter != null) {
+ // try {
+ // pathsWriter.commit();
+ // } catch (IOException e) {
+ // if (ioError == null) ioError = e;
+ // } catch (RuntimeException e) {
+ // if (runtimeError == null) runtimeError = e;
+ // } finally {
try {
- pathsWriter.commit();
+ pathsWriter.close();
} catch (IOException e) {
- ioError = e;
+ if (ioError == null) ioError = e;
} catch (RuntimeException e) {
- runtimeError = e;
+ if (runtimeError == null) runtimeError = e;
} finally {
- try {
- pathsWriter.close();
- } catch (IOException e) {
- ioError = e;
- } catch (RuntimeException e) {
- runtimeError = e;
- } finally {
- pathsWriter = null;
- }
+ pathsWriter = null;
}
+ // }
}
if (contentWriter != null) {
+ // try {
+ // contentWriter.commit();
+ // } catch (IOException e) {
+ // if (ioError == null) ioError = e;
+ // } catch (RuntimeException e) {
+ // if (runtimeError == null) runtimeError = e;
+ // } finally {
try {
- contentWriter.commit();
+ contentWriter.close();
} catch (IOException e) {
if (ioError == null) ioError = e;
} catch (RuntimeException e) {
if (runtimeError == null) runtimeError = e;
} finally {
- try {
- contentWriter.close();
- } catch (IOException e) {
- ioError = e;
- } catch (RuntimeException e) {
- runtimeError = e;
- } finally {
- contentWriter = null;
- }
+ contentWriter = null;
}
+ // }
}
if (ioError != null) {
String msg = SearchI18n.errorWhileCommittingIndexChanges.text(workspaceName, sourceName, ioError.getMessage());
@@ -916,7 +909,7 @@
}
return query;
}
- // Returna query that will always find all of the UUIDs ...
+ // Return a query that will always find all of the UUIDs ...
return new UuidsQuery(ContentIndex.UUID, uuids, getContext().getValueFactories().getUuidFactory());
}
@@ -1515,8 +1508,9 @@
protected static class UuidCollector extends Collector {
private final Set<UUID> uuids = new HashSet<UUID>();
private String[] uuidsByDocId;
- private int baseDocId;
+ // private int baseDocId;
+
protected UuidCollector() {
}
@@ -1555,10 +1549,9 @@
* @see org.apache.lucene.search.Collector#collect(int)
*/
@Override
- public void collect( int doc ) {
- int index = doc - baseDocId;
- assert index >= 0;
- String uuidString = uuidsByDocId[index];
+ public void collect( int docId ) {
+ assert docId >= 0;
+ String uuidString = uuidsByDocId[docId];
assert uuidString != null;
uuids.add(UUID.fromString(uuidString));
}
@@ -1572,7 +1565,7 @@
public void setNextReader( IndexReader reader,
int docBase ) throws IOException {
this.uuidsByDocId = FieldCache.DEFAULT.getStrings(reader, UUID_FIELD);
- this.baseDocId = docBase;
+ // this.baseDocId = docBase;
}
}
}
Added: trunk/dna-search/src/test/java/org/jboss/dna/search/SearchEngineTest.java
===================================================================
--- trunk/dna-search/src/test/java/org/jboss/dna/search/SearchEngineTest.java (rev 0)
+++ trunk/dna-search/src/test/java/org/jboss/dna/search/SearchEngineTest.java 2009-11-24 17:43:33 UTC (rev 1337)
@@ -0,0 +1,193 @@
+/*
+ * JBoss DNA (http://www.jboss.org/dna)
+ * See the COPYRIGHT.txt file distributed with this work for information
+ * regarding copyright ownership. Some portions may be licensed
+ * to Red Hat, Inc. under one or more contributor license agreements.
+ * See the AUTHORS.txt file in the distribution for a full listing of
+ * individual contributors.
+ *
+ * JBoss DNA is free software. Unless otherwise indicated, all code in JBoss DNA
+ * is licensed to you under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * JBoss DNA is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this software; if not, write to the Free
+ * Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
+ * 02110-1301 USA, or see the FSF site: http://www.fsf.org.
+ */
+package org.jboss.dna.search;
+
+import static org.hamcrest.core.Is.is;
+import static org.hamcrest.core.IsNull.notNullValue;
+import static org.junit.Assert.assertThat;
+import java.io.IOException;
+import java.util.List;
+import org.jboss.dna.graph.ExecutionContext;
+import org.jboss.dna.graph.Graph;
+import org.jboss.dna.graph.Location;
+import org.jboss.dna.graph.connector.RepositoryConnection;
+import org.jboss.dna.graph.connector.RepositoryConnectionFactory;
+import org.jboss.dna.graph.connector.RepositorySourceException;
+import org.jboss.dna.graph.connector.inmemory.InMemoryRepositorySource;
+import org.jboss.dna.graph.property.Path;
+import org.jboss.dna.graph.search.SearchEngine;
+import org.jboss.dna.graph.search.SearchProvider;
+import org.junit.Before;
+import org.junit.Test;
+import org.xml.sax.SAXException;
+
+public class SearchEngineTest {
+
+ private SearchEngine engine;
+ private SearchProvider provider;
+ private ExecutionContext context;
+ private String sourceName;
+ private String workspaceName1;
+ private String workspaceName2;
+ private InMemoryRepositorySource source;
+ private RepositoryConnectionFactory connectionFactory;
+ private Graph content;
+
+ @Before
+ public void beforeEach() throws Exception {
+ context = new ExecutionContext();
+ sourceName = "sourceA";
+ workspaceName1 = "workspace1";
+ workspaceName2 = "workspace2";
+
+ // Set up the source and graph instance ...
+ source = new InMemoryRepositorySource();
+ source.setName(sourceName);
+ content = Graph.create(source, context);
+
+ // Create the workspaces ...
+ content.createWorkspace().named(workspaceName1);
+ content.createWorkspace().named(workspaceName2);
+
+ // Set up the connection factory ...
+ connectionFactory = new RepositoryConnectionFactory() {
+ @SuppressWarnings( "synthetic-access" )
+ public RepositoryConnection createConnection( String sourceName ) throws RepositorySourceException {
+ return source.getConnection();
+ }
+ };
+
+ // Set up the provider and the search engine ...
+ IndexRules rules = DualIndexSearchProvider.DEFAULT_RULES;
+ LuceneConfiguration luceneConfig = LuceneConfigurations.inMemory();
+ // LuceneConfiguration luceneConfig = LuceneConfigurations.using(new File("target/testIndexes"));
+ provider = new DualIndexSearchProvider(luceneConfig, rules);
+ engine = new SearchEngine(context, sourceName, connectionFactory, provider);
+ loadContent();
+ }
+
+ protected Path path( String path ) {
+ return context.getValueFactories().getPathFactory().create(path);
+ }
+
+ protected void loadContent() throws IOException, SAXException {
+ // Load the content ...
+ content.useWorkspace(workspaceName1);
+ content.importXmlFrom(getClass().getClassLoader().getResourceAsStream("cars.xml")).into("/");
+ content.useWorkspace(workspaceName2);
+ content.importXmlFrom(getClass().getClassLoader().getResourceAsStream("aircraft.xml")).into("/");
+ }
+
+ @Test
+ public void shouldIndexAllContentInRepositorySource() throws Exception {
+ engine.index(3);
+ }
+
+ @Test
+ public void shouldIndexAllContentInWorkspace() throws Exception {
+ engine.index(workspaceName1, 3);
+ engine.index(workspaceName2, 5);
+ }
+
+ @Test
+ public void shouldIndexAllContentInWorkspaceBelowPath() throws Exception {
+ engine.index(workspaceName1, path("/Cars/Hybrid"), 3);
+ engine.index(workspaceName2, path("/Aircraft/Commercial"), 5);
+ }
+
+ @Test
+ public void shouldReIndexAllContentInWorkspaceBelowPath() throws Exception {
+ for (int i = 0; i != 0; i++) {
+ engine.index(workspaceName1, path("/Cars/Hybrid"), 3);
+ engine.index(workspaceName2, path("/Aircraft/Commercial"), 5);
+ }
+ }
+
+ @Test
+ public void shouldHaveLoadedTestContentIntoRepositorySource() {
+ content.useWorkspace(workspaceName1);
+ assertThat(content.getNodeAt("/Cars/Hybrid/Toyota Prius").getProperty("msrp").getFirstValue(), is((Object)"$21,500"));
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtRootAndUsingDepthOfOne() {
+ engine.index(workspaceName1, path("/"), 1);
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtRootAndUsingDepthOfTwo() {
+ engine.index(workspaceName1, path("/"), 2);
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtRootAndUsingDepthOfThree() {
+ engine.index(workspaceName1, path("/"), 3);
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtRootAndUsingDepthOfFour() {
+ engine.index(workspaceName1, path("/"), 4);
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtRootAndUsingDepthOfTen() {
+ engine.index(workspaceName1, path("/"), 10);
+ }
+
+ @Test
+ public void shouldIndexRepositoryContentStartingAtNonRootNode() {
+ engine.index(workspaceName1, path("/Cars"), 10);
+ }
+
+ @Test
+ public void shouldReIndexRepositoryContentStartingAtNonRootNode() {
+ engine.index(workspaceName1, path("/Cars"), 10);
+ engine.index(workspaceName1, path("/Cars"), 10);
+ engine.index(workspaceName1, path("/Cars"), 10);
+ }
+
+ @Test
+ public void shouldFindNodesByFullTextSearch() {
+ engine.index(workspaceName1, path("/"), 100);
+ List<Location> results = engine.fullTextSearch(context, workspaceName1, "Toyota Prius", 10, 0);
+ assertThat(results, is(notNullValue()));
+ assertThat(results.size(), is(2));
+ assertThat(results.get(0).getPath(), is(path("/Cars/Hybrid/Toyota Prius")));
+ assertThat(results.get(1).getPath(), is(path("/Cars/Hybrid/Toyota Highlander")));
+ }
+
+ @Test
+ public void shouldFindNodesByFullTextSearchWithOffset() {
+ engine.index(workspaceName1, path("/"), 100);
+ List<Location> results = engine.fullTextSearch(context, workspaceName1, "toyota prius", 1, 0);
+ assertThat(results, is(notNullValue()));
+ assertThat(results.size(), is(1));
+ assertThat(results.get(0).getPath(), is(path("/Cars/Hybrid/Toyota Prius")));
+
+ results = engine.fullTextSearch(context, workspaceName1, "+Toyota", 1, 1);
+ assertThat(results, is(notNullValue()));
+ assertThat(results.size(), is(1));
+ assertThat(results.get(0).getPath(), is(path("/Cars/Hybrid/Toyota Highlander")));
+ }
+}
Property changes on: trunk/dna-search/src/test/java/org/jboss/dna/search/SearchEngineTest.java
___________________________________________________________________
Name: svn:keywords
+ Id Revision
Name: svn:eol-style
+ LF
More information about the dna-commits
mailing list