lucene实现word，pdf，excel，ppf全文检索源码

创建索引：
  
import java.io.BufferedReader;
import java.io.File;   
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileReader;   
import java.io.IOException;   
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.Reader;
import java.io.StringReader;
import java.text.SimpleDateFormat;
import java.util.Date;   
  
import org.apache.lucene.analysis.standard.StandardAnalyzer;   
import org.apache.lucene.document.DateTools;   
import org.apache.lucene.document.Document;   
import org.apache.lucene.document.Field;   
import org.apache.lucene.index.IndexWriter;   
import org.apache.lucene.store.Directory;   
import org.apache.lucene.store.SimpleFSDirectory;   
import org.apache.lucene.util.Version;   
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.RichTextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFDateUtil;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.poifs.filesystem.DocumentEntry;
import org.apache.poi.poifs.filesystem.DocumentInputStream;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.util.LittleEndian;
/**  
 * 创建索引 Lucene 3.0+  
 * @author Administrator  
 *  
 */  
public class indexer {   
	
    /**  
     * @param args  
     * @throws Exception 
     */  
    public static void main(String[] args) throws Exception {   
        //保存索引文件的地方   
        String indexDir = "data\\test\\indexDir";   
        //将要搜索TXT文件的地方   
        String dateDir = "data\\test\\dateDir";   
        IndexWriter indexWriter = null;   
        //创建Directory对象   
        Directory dir = new SimpleFSDirectory(new File(indexDir));   
        //创建IndexWriter对象,
        //第一个参数是Directory,第二个是分词器,
        //第三个表示是否是创建,如果为false为在此基础上面修改,
        //第四表示表示分词的最大值，比如说new MaxFieldLength(2)，就表示两个字一分，
        //一般用IndexWriter.MaxFieldLength.LIMITED    
        indexWriter = new IndexWriter(dir,new StandardAnalyzer(Version.LUCENE_30),true,
        		IndexWriter.MaxFieldLength.UNLIMITED);   
        File[] files = new File(dateDir).listFiles();   
        for (int i = 0; i 

   
  
import java.io.File;   
import java.io.IOException;   
  
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.IndexSearcher;   
import org.apache.lucene.search.Query;   
import org.apache.lucene.search.ScoreDoc;   
import org.apache.lucene.search.TopDocs;   
import org.apache.lucene.store.Directory;   
import org.apache.lucene.store.SimpleFSDirectory;   
import org.apache.lucene.util.Version;   
/**  
 * 搜索索引 Lucene 3.0+  
 * @author Administrator  
 *  
 */  
public class searcher {   
  
    public static void main(String[] args) throws IOException, ParseException {   
        //保存索引文件的地方      
        String indexDir = "data\\test\\indexDir"; 
        Directory dir = new SimpleFSDirectory(new File(indexDir));   
        //创建 IndexSearcher对象，相比IndexWriter对象，这个参数就要提供一个索引的目录就行了   
        IndexSearcher indexSearch = new IndexSearcher(dir);   
        //创建QueryParser对象,第一个参数表示Lucene的版本,第二个表示搜索Field的字段,第三个表示搜索使用分词器   
        QueryParser queryParser = new QueryParser(Version.LUCENE_30,   
                "contents", new StandardAnalyzer(Version.LUCENE_30));   
        //生成Query对象   
        Query query = queryParser.parse("arcgis");   
        //搜索结果 TopDocs里面有scoreDocs[]数组，里面保存着索引值   
        TopDocs hits = indexSearch.search(query,10);   
        //hits.totalHits表示一共搜到多少个   
        System.out.println("找到了"+hits.totalHits+"个");   
        //循环hits.scoreDocs数据，并使用indexSearch.doc方法把Document还原，再拿出对应的字段的值   
        for (int i = 0; i