lucene4.4入门实践

     最近需要用到lucene，使用最新版本4.6的版本，发现比较以前学习的3.0版本有很多的改变，包括各种参数配置，而网上搜索到的大部分都是3.0版本的教程，于是只好自己动手，好在有基础，不难...

     首先创建索引，其实我很久不用lucene了，以前学习的差不多都忘记了，不过我还记得创建索引对象IndexWriter，使用这个对象，根据eclipse的代码提示，差不多就可以完成了

/** * 对目录索引 */ public class Indexer { /** * 索引文件存放文件夹 */ private static String INDEX_DIR = "E:/docData/indexDir"; /** * 被索引目录 */ private static String DATA_DIR = "D:/学习资料"; /** * 测试主函数 * @throws Exception */ public static void main(String[] args) throws Exception { long start =new Date().getTime(); int numIndex=index(new File(INDEX_DIR),new File(DATA_DIR)); long end =new Date().getTime(); System.out.println("indexing:"+numIndex+"times:"+(end-start)); } /** * 索引dataDir下的文件 * * @throws Exception */ private static int index(File indexDir, File dataDir) throws Exception { if (!dataDir.exists() || !dataDir.isDirectory()) { throw new Exception("文件不存在"); } if (!indexDir.exists() || !indexDir.isDirectory()) { indexDir.mkdirs(); } /** * 建立索引 */ Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_44); //指定分词 IndexWriterConfig writerConfig=new IndexWriterConfig(Version.LUCENE_44,analyzer); IndexWriter writer = new IndexWriter(FSDirectory.open(indexDir),writerConfig); indexDirectory(writer, dataDir); int numIndex=writer.numDocs(); //优化索引结果 writer.close(); return numIndex; } /** * 遍历目录下的所有文件 并建立索引 * @param writer * @param dataDir * @throws IOException */ private static void indexDirectory(IndexWriter writer,File dataDir) throws IOException{ File[] files=dataDir.listFiles(); for(int i=0;i<files.length;i++){ File file=files[i]; if(file.isDirectory()){ indexDirectory(writer, file); }else if(file.getName().endsWith(".txt")){ indexFile(writer, file); } } } /** * 对单个文件建立索引 * @param writer * @param dataDir * @throws IOException */ private static void indexFile(IndexWriter writer, File dataDir) throws IOException{ if(dataDir.isHidden()||!dataDir.exists()||!dataDir.canRead()){ return ; } System.out.println("indexing:"+dataDir.getCanonicalPath()); Document document=new Document(); IndexableField field=new TextField("content",new FileReader(dataDir) ); System.out.println(new FileReader(dataDir)+"--"); document.add(field); document.add(new StringField("filename",dataDir.getName(),Field.Store.YES)); document.add(new StringField("path",dataDir.getCanonicalPath(),Field.Store.YES)); writer.addDocument(document); } 对搜索结果进行查询： /** * 对索引结果进行搜索 * * @author madong * */ public class Searcher { /** * 索引所在路径 */ private static String INDEX_DIR = "E:/docData/indexDir"; /** * 关键词 */ private static String KEYWORD = "源码"; /** * 显示前10条记录 */ private static int TOTAL_NUM = 10; /** * 索引查找方法 * * @throws IOException * @throws ParseException */ private static void search(File indexDir, String word) throws IOException, ParseException { /** * 获取读取对象 */ IndexReader reader = DirectoryReader.open(FSDirectory.open(indexDir)); IndexSearcher is = new IndexSearcher(reader); String field = "content"; // 创建查询解析器 QueryParser parser = new QueryParser(Version.LUCENE_44, field, new StandardAnalyzer(Version.LUCENE_44)); Query query = parser.parse(word); /** * 创建结果收集器 */ TopScoreDocCollector collector=TopScoreDocCollector.create(TOTAL_NUM, false); long start =new Date().getTime(); is.search(query, collector); ScoreDoc[] scoreDocs = collector.topDocs().scoreDocs; System.out.println(scoreDocs.length); /** * 可以在此分页 * start 起始位置 * length 记录数 */ for(int i=0;i<scoreDocs.length;i++){ Document doc= is.doc(scoreDocs[i].doc); System.out.println(doc.getField("filename")+" "+scoreDocs[i].toString()); } long end =new Date().getTime(); System.out.println("fund:"+collector.getTotalHits()+" time:"+(end-start)+" query:"+word); } /** * 测试主函数 * @throws Exception */ public static void main(String[] args) throws Exception { File indexDir=new File(INDEX_DIR); if(!indexDir.exists()||!indexDir.isDirectory()){ throw new Exception("目录不存在"); } search(indexDir, KEYWORD); showAnalyzerResult(new StandardAnalyzer(Version.LUCENE_44), KEYWORD); } /** * 查看分词结果 * @throws IOException */ public static void showAnalyzerResult(Analyzer analyzer,String keyword) throws IOException{ StringReader reader=new StringReader(keyword); TokenStream tokenStream= analyzer.tokenStream(keyword, reader); tokenStream.addAttribute(TermToBytesRefAttribute.class); tokenStream.reset();//此句不能少 while(tokenStream.incrementToken()){ TermToBytesRefAttribute cta=tokenStream.getAttribute(TermToBytesRefAttribute.class); System.out.println(cta.toString()); } } }