lucenepdfdocument.java

来自「在lucene环境下把pdf的文件转换成txt文件的源代码」· Java 代码 · 共 65 行

/*
 * 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.pdfbox.cos.COSDocument;
import org.pdfbox.pdfparser.PDFParser;
import org.pdfbox.util.PDFTextStripper;
import org.pdfbox.pdmodel.PDDocument;

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

    public static Document getDocument(File doc) {
        COSDocument cosDoc = null;
        PDFParser parser = null;
        String docPath = doc.getAbsolutePath();
        String title = doc.getName();
        InputStream inputStream = null;
        Reader contents = null;
        Document document = new Document();

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

        try {
            parser = new PDFParser(inputStream);

            parser.parse();
            cosDoc = parser.getDocument();
            if(cosDoc.isEncrypted()) {
                System.out.println("文件加密，无法索引");
            }
            PDFTextStripper stripper = new PDFTextStripper();
            String docText = stripper.getText(new PDDocument(cosDoc));

            contents = new StringReader(docText);
        } catch (Exception e) {
            System.out.println(e);
        }

        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));
        try {
            cosDoc.close();
        } catch (Exception e) {
            System.out.println(e);
        }

        return document;
    }
}