lucenepptdocument.java

lucene环境下ppt转txt的源代码,这个代码应该对搜索引擎有一定作用

/*
 * To change this template, choose Tools | Templates
 * and open the template in the editor.
 */
package lucenesearch;

import java.io.*;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.usermodel.SlideShow;

/**
 *
 * @author BileiZhu
 */
public class LucenePPTDocument {

    public static Document getDocument(File doc) {
        String docPath = doc.getAbsolutePath();
        String title = doc.getName();
        FileInputStream inputStream = null;
        Reader contents = null;
        Document document = new Document();

        try {
            inputStream = new FileInputStream(doc);
        } catch (FileNotFoundException e) {
            System.out.println(e);
        }

        StringBuffer sBuff = new StringBuffer("");

        try {
            SlideShow ss = new SlideShow(new HSLFSlideShow(inputStream));
            Slide[] slides = ss.getSlides();

            for (int i = 0; i < slides.length; i++) {
                TextRun[] t = slides[i].getTextRuns();

                for (int j = 0; j < t.length; j++) {
                    sBuff.append(t[j].getText());
                }
            }
        } catch (Exception e) {
            System.out.println(e);
        }

        contents = new StringReader(sBuff.toString());

        document.add(new Field("path", docPath, Field.Store.YES, Field.Index.NO));
        document.add(new Field("title", title, Field.Store.YES, Field.Index.TOKENIZED));
        document.add(new Field("contents", contents));
        document.add(new Field("information", docPath + Long.toString(doc.lastModified()), Field.Store.YES, Field.Index.UN_TOKENIZED));
        return document;
    }
}