-- 作者:admin
-- 发布时间:2008/5/14 10:52:10
-- [推荐]一个最简单的Lucene程序
1、先到网上下载lucene的jar包
2、设置classpath或者将其放入JDK/jre/lib/ext目录自动发现
3、索引程序功能是将“C:\\\\j2sdk1.4.2_14\\\\docs”目录中的所有文本文件建立索引,并将索引存放在“C:\\\\temp”,这些目录皆可以自己定义: import org.apache.lucene.index.IndexWriter; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field;
import java.io.File; import java.io.IOException; import java.io.FileReader; import java.util.Date;
/** * This code was originally written for * Erik\'s Lucene intro java.net article */ public class Indexer {
public static void main(String[] args) throws Exception { File indexDir = new File("C:\\\\temp"); //Create Lucene index in this directory File dataDir = new File("C:\\\\j2sdk1.4.2_14\\\\docs"); //Index files in this directory
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"); }
public static int index(File indexDir, File dataDir) throws IOException { IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(), true); //indexDir表示索引的存放地点 //new StandardAnalyzer()表示分析器 //true表示如已有索引则覆盖之
writer.setUseCompoundFile(false); //表示生成多文件索引文件(默认为复合索引) indexDirectory(writer, dataDir); int numIndexed = writer.docCount(); 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; if (f.isDirectory()) { indexDirectory(writer, f); // recurse } 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()); //建立索引关键代码 Document doc = new Document(); doc.add(Field.Text("contents", new FileReader(f))); doc.add(Field.Keyword("filename", f.getCanonicalPath())); writer.addDocument(doc); } }
4、搜索程序为: import org.apache.lucene.document.Document; import org.apache.lucene.search.*; import org.apache.lucene.index.*; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.Directory; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.analysis.standard.StandardAnalyzer; import java.io.File; import java.util.Date;
public class SearchExec {
public static void main(String[] args) throws Exception { File indexDir = new File("c:\\\\temp");
Directory fsDir = FSDirectory.getDirectory(indexDir, false);//if true, create, or erase any existing contents //打开索引 IndexSearcher is = new IndexSearcher(fsDir); //解析查询词语 //Query query = new TermQuery(new Term("contents", "java")); //Query query = new TermQuery(new Term("contents", "application")); Query query = QueryParser.parse("java AND NOT application", "contents", new StandardAnalyzer()); //搜索索引 Hits hits = is.search(query); for (int i = 0; i < hits.length(); i++) { Document doc = hits.doc(i); System.out.println(doc.get("filename")); } } }
[此贴子已经被作者于2010-12-14 09:27:29编辑过]
|