Java多级多类型全文检索 - 基于Lucene3.3.0

package com.dyhx.archive.lucene; import java.io.File; import java.io.FileReader; import java.io.IOException; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; public class Indexer { private static File indexDir = new File(Constants.INDEX_DIR); private static File dataDir = new File(Constants.DATA_DIR); public static void main(String[] args) throws Exception { int numIndexed = index(); System.out.println("Indexing " + numIndexed + " files..."); } @SuppressWarnings("deprecation") public static int index() throws IOException { if (!dataDir.exists() || !dataDir.isDirectory()) { throw new IOException(dataDir + " does not exist or is not a directory"); } IndexWriter indexWriter = new IndexWriter(FSDirectory.open(indexDir), new StandardAnalyzer(Version.LUCENE_33), true, IndexWriter.MaxFieldLength.LIMITED); indexDirectory(indexWriter, dataDir); int numIndexed = indexWriter.numDocs(); indexWriter.optimize(); indexWriter.close(); return numIndexed; } public static void indexDirectory(IndexWriter writer, File dir) throws IOException { File[] files = dir.listFiles(); for (int i = 0; i < files.length; i++) { File f = files[i]; if (f.isDirectory()) { indexDirectory(writer, f); // directory iterator } else { String[] exts = Constants.EXTS.split(","); for (int j = 0; j < exts.length; j++) { if (f.getName().endsWith("." + exts[j])) { indexFile(writer, f); } } } } } private static void indexFile(IndexWriter writer, File file) throws IOException { if (file.isHidden() || !file.exists() || !file.canRead()) { return; } Document doc = new Document(); doc.add(new Field("name", file.getName().substring(0, file.getName().lastIndexOf(".")), Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("path", file.getCanonicalPath(), Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("parent", file.getParent().substring(file.getParent().lastIndexOf("\\") + 1), Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("content", new FileReader(file))); writer.addDocument(doc); } }