For Lucene 4.7 this code for the indexer:
package tikatest01;
import java.io.File;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.IndexWriter;
import org.apache.tika.Tika;
public class LuceneIndexer {
private final Tika tika;
private final IndexWriter writer;
public LuceneIndexer(Tika tika, IndexWriter writer) {
this.tika = tika;
this.writer = writer;
}
public void indexDocument(File file) throws Exception {
Document document = new Document();
document.add(new TextField(
"filename", file.getName(), Store.YES));
document.add(new TextField(
"fulltext", tika.parseToString(file), Store.NO));
writer.addDocument(document);
}
}
And this code for the main class:
package tikatest01;
import java.io.File;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;
import org.apache.tika.Tika;
public class TikaTest01 {
public static void main(String[] args) throws Exception {
String dirname = "C:\\MyTestDir\\";
File dir = new File(dirname);
IndexWriter writer = new IndexWriter(
new SimpleFSDirectory(dir),
new IndexWriterConfig(
Version.LUCENE_47,
new StandardAnalyzer(Version.LUCENE_47)));
try {
LuceneIndexer indexer = new LuceneIndexer(new Tika(), writer);
indexer.indexDocument(dir);
}
finally {
writer.close();
}
}
}