lucece 对txt建立索引并且查询的案例

beyondsanli

package case1;import java.io.BufferedReader;import java.io.File;import java.io.FileInputStream;import java.io.IOException;import java.io.InputStreamReader;import java.io.Reader;import org.apache.lucene.analysis.standard.StandardAnalyzer;import org.apache.lucene.document.DateField;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.index.IndexWriter;public class IndexFiles {/** * @param args */public static void main(String[] args) {// TODO 自动生成方法存根File   indexDir = new File("C:\\luceneIndex");try {IndexWriter writer=new IndexWriter(indexDir,new StandardAnalyzer(),true);File files=new File("D:\\chenzk\\lucene");//要对这个文件目录下的所有文件建立索引，保存在indexDir中String [] Fnamelist=files.list();for(int i=0;i<Fnamelist.length;i++){File file=new File(files,Fnamelist[i]);Document doc=new Document();Field fld=Field.Text("path",file.getPath());doc.add(fld);fld=Field.Keyword("modified",DateField.timeToString(file.lastModified()));    doc.add(fld);//下面很重要要将查询的东西保存索引文件中去  文件内容    FileInputStream in = new FileInputStream(file);    Reader reader = new BufferedReader(new InputStreamReader(in));    fld = Field.Text("contents", reader);    doc.add(fld); writer.addDocument(doc);System.out.println("Added:"+doc.get("path"));//索引中有3个字段 文件路径，最后修订时间，文件内容}    writer.optimize();    writer.close();    System.out.println(" Has Added Total "+Fnamelist.length);} catch (IOException e) {// TODO 自动生成 catch 块e.printStackTrace();}}}  以上对文件目录建立索引的过程
 
package case1;import java.io.IOException;import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.standard.StandardAnalyzer;import org.apache.lucene.document.Document;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.Hits;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.Searcher;public class SearchFile {/** * @param args */public static void main(String[] args) {// TODO 自动生成方法存根Analyzer  anlzr=new StandardAnalyzer();     try {Query q=QueryParser.parse("java","contents",anlzr);    System.out.println(" Searching for :"+q.toString("contents")) ;        Searcher serch=new IndexSearcher("C:\\luceneIndex");//索引所在的目录    Hits hts=serch.search(q);    for(int i=0;i<hts.length();i++)    {    Document doc=hts.doc(i);    String path=doc.get("path");    System.out.println("Find "+i+":" +path);    System.out.println("Find :"+doc.get("modified"));    System.out.println("Find: " + doc.get("contents"));        }    System.out.println("Find Total: " + hts.length());} catch (ParseException e) {// TODO 自动生成 catch 块e.printStackTrace();} catch (IOException e) {// TODO 自动生成 catch 块e.printStackTrace();}}} 
以上是对索引中关键字查询的过程
 
下面是将索引放在内存中的案例：
package case2;import java.io.IOException;import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.SimpleAnalyzer;import org.apache.lucene.document.DateField;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.Hits;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.Searcher;import org.apache.lucene.store.Directory;import org.apache.lucene.store.RAMDirectory;public class IndexTest {/** * @param args */public static void main(String[] args) {// TODO 自动生成方法存根try {Directory directory = new RAMDirectory();// 将索引放在内存中Analyzer analyzer = new SimpleAnalyzer();IndexWriter writer = new IndexWriter(directory, analyzer, true);String[] docs = { "a b c d e", "a b c d e a b c d e","a b c d e f g h i j", "a c e", "a c e a c e","a c e a b c" };for (int j = 0; j < docs.length; j++) {Document d = new Document();d.add(Field.Text("contents", docs[j]));writer.addDocument(d);}writer.close();// 以上是生成索引Searcher searcher = new IndexSearcher(directory);String[] queries = { "a ", };Hits hits = null;QueryParser parser = new QueryParser("contents", analyzer);parser.setPhraseSlop(0);for (int j = 0; j < queries.length; j++) {Query query = parser.parse(queries[j]);System.out.println("Query :" + query.toString("contents"));hits = searcher.search(query);// 以上是初始化查询，分析编号1,2System.out.println(hits.length() + " total results");for (int i = 0; i < hits.length() && i < 10; i++) {Document d = hits.doc(i);System.out.println(i + "  " + hits.score(i) + "  " + " "+ d.get("contents"));}}searcher.close();} catch (IOException e) {// TODO 自动生成 catch 块e.printStackTrace();} catch (ParseException e) {// TODO 自动生成 catch 块e.printStackTrace();}}}