luceneexceldocument.java

来自「在lucene环境下把excel文件转成txt文件的源代码」· Java 代码 · 共 52 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.apache.poi.poifs.filesystem.POIFSFileSystem;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.extractor.ExcelExtractor;

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

    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);
        }

        try {
            POIFSFileSystem reader = new POIFSFileSystem(inputStream);
            HSSFWorkbook wb = new HSSFWorkbook(reader);
            ExcelExtractor extractor = new ExcelExtractor(wb);

            extractor.setFormulasNotResults(true);
            extractor.setIncludeSheetNames(false);
            String textString = extractor.getText();
            contents = new StringReader(textString);
        } 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));
        return document;
    }
}