Lucene indexing sample

IndexingTest.java

/**
 * 以下は、Apache Softoware Licence v2.0 の元にで頒布されているコードに一部改変を加えたものです。
 * http://www.apache.org/licenses/LICENSE-2.0.txt
 */

import static org.junit.Assert.*;
import java.io.IOException;

import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.StoredField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;
import org.apache.lucene.util.Version;
import org.junit.Before;
import org.junit.Test;

public class IndexingTest {
  protected String[] ids = { "1", "2" };
	protected String[] unindexed = { "Netherlands", "Italy" };
	protected String[] unstored = { "Amsterdam has lots of bridges",
			"Venice has lots of canals" };
	protected String[] text = { "Amsterdam", "Venice" };
	protected Directory directory;

	@Before
	public void setUp() throws Exception {
		directory = new RAMDirectory();
		IndexWriter writer = getWriter();
		for (int i = 0; i < ids.length; i++) {
			Document doc = new Document();
			doc.add(new StringField("id", ids[i], Store.YES));
			doc.add(new StoredField("country", unindexed[i]));
			doc.add(new TextField("contents", unstored[i], Store.NO));
			doc.add(new StringField("city", text[i], Store.YES));
			writer.addDocument(doc);
		}
		writer.close();
	}

	private IndexWriter getWriter() throws IOException {
		IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40,
				new WhitespaceAnalyzer(Version.LUCENE_40));
		return new IndexWriter(directory, config);
	}
	
	protected int getHitCount(String fieldName, String searchString) throws IOException {
		IndexReader reader = DirectoryReader.open(directory);
		IndexSearcher searcher = new IndexSearcher(reader);
		Term t = new Term(fieldName, searchString);
		Query query = new TermQuery(t);
		int hitCount = searcher.search(query, 1).totalHits;
		reader.close();
		return hitCount;
	}
	
	@Test
	public void testIndexWriter() throws IOException {
		IndexWriter writer = getWriter();
		assertEquals(ids.length, writer.numDocs());
		writer.close();
	}
	
	@Test
	public void testIndexReader() throws IOException {
		IndexReader reader = DirectoryReader.open(directory);
		assertEquals(ids.length, reader.maxDoc());
		assertEquals(ids.length, reader.numDocs());
		reader.close();
	}
	
	@Test
	public void testDelete() throws IOException {
		IndexWriter writer = getWriter();
		assertEquals(2, writer.numDocs());
		writer.deleteDocuments(new Term("id", "1"));
		writer.commit();
		assertTrue(writer.hasDeletions());
		assertEquals(2, writer.maxDoc());
		assertEquals(1, writer.numDocs());
		writer.close();
	}
	
	@Test
	public void testUpdate() throws IOException {
		assertEquals(1, getHitCount("city", "Amsterdam"));
		IndexWriter writer = getWriter();
		Document doc = new Document();
		doc.add(new StringField("id", "1", Store.YES));
		doc.add(new StoredField("country", "Netherlands"));
		doc.add(new TextField("contents", "Den Haag has a lot of museums", Store.NO));
		doc.add(new StringField("city", "Den Haag", Store.YES));
		writer.updateDocument(new Term("id", "1"), doc);
		writer.commit();
		writer.close();
		
		assertEquals(0, getHitCount("city", "Amsterdam"));
		assertEquals(1, getHitCount("city", "Den Haag"));

	}
}