lucene+中文IK分词器 例子

import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.FileNotFoundException; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.URL; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.Field.Index; import org.apache.lucene.document.Field.Store; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.IndexWriterConfig.OpenMode; import org.apache.lucene.store.Directory; import org.apache.lucene.store.LockObtainFailedException; import org.apache.lucene.store.SimpleFSDirectory; import org.apache.lucene.util.Version; import org.wltea.analyzer.lucene.IKAnalyzer; public class FileIndexer { private File baseDir = new File("E:\\dateDir"); private File indexDir2 = new File("E:\\indexDir"); Analyzer luceneAnalyzer = new IKAnalyzer(); Directory indexDir = null ; public FileIndexer() { if (!this.baseDir.exists() || !this.indexDir2.exists()) { return; } } @SuppressWarnings("deprecation") public void createIndex() { try { /* IndexWriter writer = new IndexWriter( FSDirectory.open(indexDir), new IKAnalyzer(false), true, IndexWriter.MaxFieldLength.LIMITED); indexDirectory(writer, baseDir); writer.optimize(); writer.close();*/ IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_35,luceneAnalyzer); indexDir=new SimpleFSDirectory(indexDir2); config.setOpenMode(OpenMode.CREATE); IndexWriter indexWriter = null; indexWriter = new IndexWriter(indexDir,config); Document doc1 = new Document(); doc1.add(new Field("id","1",Store.YES,Index.ANALYZED)); doc1.add(new Field("name","liangge",Store.YES,Index.ANALYZED)); doc1.add(new Field("content","中华人民共和国",Store.YES,Index.ANALYZED)); indexDirectory(indexWriter, baseDir); indexWriter.addDocument(doc1); indexWriter.close(); System.out.println("索引初始化完毕！"); } catch (CorruptIndexException e) { e.printStackTrace(); } catch (LockObtainFailedException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } private void indexDirectory(IndexWriter writer, File dir) { if (!dir.exists() || !dir.isDirectory()) { return; } File[] files = dir.listFiles(); for (File file : files) { if (file.isDirectory()) indexDirectory(writer, file); else indexFile(writer, file); } } private void indexFile(IndexWriter writer, File file) { if (file.isHidden() || !file.exists() || !file.canRead()) { return; } try { //if (file.getCanonicalPath().endsWith(".txt")) { System.out.println("路径" + file.getCanonicalPath()); Document doc = new Document(); doc.add(new Field("content", new InputStreamReader(new FileInputStream(file),"GBK"))); doc.add(new Field("name", file.getCanonicalPath(), Field.Store.YES, Field.Index.ANALYZED)); writer.addDocument(doc); //} } catch (FileNotFoundException e) { e.printStackTrace(); } catch (CorruptIndexException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } } public static void main(String[] args) { FileIndexer lucene = new FileIndexer(); lucene.createIndex(); } }