写了第一个lucene程序（lucene学习笔记）

基本参考了《lucene in action》里面的写法，只是根据Lucene的版本做了小部分变化。网页爬虫爬的数据终于有了用武之地：）

 

Indexer类，主要是建立索引

package com.hudson.lucenestudy; import org.apache.lucene.document.Field; import org.apache.lucene.document.Document; import org.apache.lucene.analysis.standard.StandardAnalyzer; import java.io.FileReader; import java.io.File; import java.io.IOException; import java.util.Date; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; public class Indexer { public static void start(String index, String data) throws Exception { File indexDir = new File(index); File dataDir = new File(data); if (!indexDir.exists()) { indexDir.mkdirs(); } long start = new Date().getTime(); int numIndexed = index(indexDir, dataDir); long end = new Date().getTime(); System.out.println("Indexing " + numIndexed + " files took " + (end - start) + " milliseconds"); } // open an index and start file directory traversal private static int index(File indexDir, File dataDir) throws IOException { if (!dataDir.exists() || !dataDir.isDirectory()) { throw new IOException(dataDir + " does not exist or is not a directory"); } IndexWriter writer = new IndexWriter(FSDirectory.open(indexDir), new StandardAnalyzer(Version.LUCENE_30), true, IndexWriter.MaxFieldLength.LIMITED); writer.setUseCompoundFile(false); indexDirectory(writer, dataDir); int numIndexed = writer.numDocs(); writer.optimize(); writer.close(); return numIndexed; } private 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); } else if (f.getName().endsWith(".txt")) { indexFile(writer, f); } } } private static void indexFile(IndexWriter writer, File f) throws IOException { if (f.isHidden() || !f.exists() || !f.canRead()) { return; } System.out.println("Indexing " + f.getCanonicalPath()); Document doc = new Document(); doc.add(new Field("contents", new FileReader(f))); doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES, Field.Index.ANALYZED));//根据3.0版本稍微改动了一下 writer.addDocument(doc); } }

 

Searcher类主要是进行搜索

package com.hudson.lucenestudy; import java.io.File; import java.io.IOException; import java.util.Date; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.index.IndexReader; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TopScoreDocCollector; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; public class Searcher { public static void start(String index,String q) throws Exception{ File indexDir = new File(index); search(indexDir,q); } private static void search(File indexDir, String q) throws Exception { if (!indexDir.exists() || !indexDir.isDirectory()) { throw new IOException(indexDir + " does not exist or is not a directory"); } Directory fsDir = FSDirectory.open(indexDir); IndexReader reader = IndexReader.open(fsDir); IndexSearcher searcher = new IndexSearcher(reader); Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30); QueryParser parser = new QueryParser(Version.LUCENE_30, "contents", analyzer); Query query = parser.parse(q); TopScoreDocCollector collector = TopScoreDocCollector.create(100, false);//主要设置搜索后显示的条数 long start = new Date().getTime(); searcher.search(query, collector); long end = new Date().getTime(); searcher.close(); ScoreDoc[] hits = collector.topDocs().scoreDocs; System.out.println("About " + collector.getTotalHits() + " results were found in " + (end - start) + " milliseconds/n" + "Results:"); for (ScoreDoc sd : hits) { System.out.println(searcher.doc(sd.doc).get("filenam

 

主程序入口

package com.hudson.lucenestudy; public class IndexAndSearch { /** * @param args */ public static final String INDEX_DIR = "c://lucene//index"; public static final String DATA_DIR = "c://mytest"; public static final String QUERY = "baidu"; public static void main(String[] args) throws Exception{ Indexer.start(INDEX_DIR, DATA_DIR); Searcher.start(INDEX_DIR, QUERY); } }

悲剧刚注册没有上传图片的权限，结果看不到了：（

 

希望大家多提提宝贵的意见谢谢：）