Java ExcelExtractor类代码示例

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
private static String microsoftExcelDocumentToString(InputStream inputStream) throws IOException, OpenXML4JException, XmlException {
    StringBuilder sb = new StringBuilder();

    try (InputStream excelStream = new BufferedInputStream(inputStream)) {
        if (POIFSFileSystem.hasPOIFSHeader(excelStream)) { // Before 2007 format files
            POIFSFileSystem excelFS = new POIFSFileSystem(excelStream);
            ExcelExtractor excelExtractor = new ExcelExtractor(excelFS);
            sb.append(excelExtractor.getText());
            excelExtractor.close();
        } else { // New format
            XSSFWorkbook workBook = new XSSFWorkbook(excelStream);
            int numberOfSheets = workBook.getNumberOfSheets();
            for (int i = 0; i < numberOfSheets; i++) {
                XSSFSheet sheet = workBook.getSheetAt(0);
                Iterator<Row> rowIterator = sheet.rowIterator();
                while (rowIterator.hasNext()) {
                    XSSFRow row = (XSSFRow) rowIterator.next();
                    Iterator<Cell> cellIterator = row.cellIterator();
                    while (cellIterator.hasNext()) {
                        XSSFCell cell = (XSSFCell) cellIterator.next();
                        sb.append(cell.toString());
                        sb.append(" ");
                    }
                    sb.append("\n");
                }
                sb.append("\n");
            }
        }
    }

    return sb.toString();
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
/**
 * 利用 POI 提供的工具，提取文件内容为字符串
 *
 * @param excelFile 待提取的 excel 文件
 * @return
 */
public String excelExtractor(File excelFile) {

    try {
        HSSFWorkbook wb = new HSSFWorkbook(new FileInputStream(excelFile));
        ExcelExtractor extractor = new ExcelExtractor(wb);
        extractor.setFormulasNotResults(true);
        extractor.setIncludeSheetNames(true);
        return extractor.getText();
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
        return null;
    }
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
/**
 * {@inheritDoc}
 */
public String extractText(InputStream stream, String type, String encoding) throws IOException {
	try {
		POIFSFileSystem fs = new POIFSFileSystem(stream);
		return new ExcelExtractor(fs).getText();
	} catch (RuntimeException e) {
		logger.warn("Failed to extract Excel text content", e);
		throw new IOException(e.getMessage(), e);
	} finally {
		stream.close();
	}
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
/**
 * Extract text from a power point 97-2003 document.
 * @throws Exception 
 * 
 * @see edu.ur.ir.index.FileTextExtractor#getText(java.io.File)
 */
public String getText(File f) throws Exception {
	String text = null;
	if( isFileTooLarge(f) || f.length() <= 0l )
	{
		return text;
	}
	
	FileInputStream inputStream = null;
	try
	{
		inputStream = new FileInputStream(f);
		HSSFWorkbook workbook = new HSSFWorkbook(inputStream);
		ExcelExtractor excelExtractor = new ExcelExtractor(workbook);
		String myText = excelExtractor.getText();
		if( myText != null && !myText.trim().equals(""))
	    {
	    	text = myText;
	    }
	}
	catch(OutOfMemoryError oome)
	{
		text = null;
		log.error("oome could not extract text", oome);
		throw(oome);
	}
	catch(Exception e)
	{
		text = null;
		log.error("could not get text for power point document " + f.getAbsolutePath(), e);
		throw(e);
	}
	
	finally
	{
		closeInputStream(inputStream);
	}
	return text;

}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
private void extractHeaderFooter(String hf, XHTMLContentHandler xhtml)
    throws SAXException {
  String content = ExcelExtractor
      ._extractHeaderFooter(new HeaderFooterFromString(hf));
  if (content.length() > 0) {
    xhtml.element("p", content);
  }
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
public IndexDocument getIndexedDocument(File2Index fileData)
		throws SolrException {
	try {
		POIFSFileSystem fs = new POIFSFileSystem(new ByteArrayInputStream(fileData.data));
		ExcelExtractor extractor = new ExcelExtractor(fs);
		String excelText = extractor.getText();

		return new IndexDocument(fileData.path, excelText, null);
	} catch (IOException e) {
		String msg = "Failed to write to the index";
		log.error(msg, e);
		throw new SolrException(ErrorCode.SERVER_ERROR, msg);
	}

}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
/**
 * Extract metadata from Office Word
 */
public static OfficeMetadata officeExtractor(InputStream is, String mimeType) throws IOException {
	POIFSFileSystem fs = new POIFSFileSystem(is);
	OfficeMetadata md = new OfficeMetadata();
	SummaryInformation si = null;

	if (MimeTypeConfig.MIME_MS_WORD.equals(mimeType)) {
		si = new WordExtractor(fs).getSummaryInformation();
	} else if (MimeTypeConfig.MIME_MS_EXCEL.equals(mimeType)) {
		si = new ExcelExtractor(fs).getSummaryInformation();
	} else if (MimeTypeConfig.MIME_MS_POWERPOINT.equals(mimeType)) {
		si = new PowerPointExtractor(fs).getSummaryInformation();
	}

	if (si != null) {
		md.setTitle(si.getTitle());
		md.setSubject(si.getSubject());
		md.setAuthor(si.getAuthor());
		md.setLastAuthor(si.getLastAuthor());
		md.setKeywords(si.getKeywords());
		md.setComments(si.getComments());
		md.setTemplate(si.getTemplate());
		md.setRevNumber(si.getRevNumber());
		md.setApplicationName(si.getApplicationName());
		md.setEditTime(si.getEditTime());
		md.setPageCount(si.getPageCount());
		md.setWordCount(si.getWordCount());
		md.setCharCount(si.getCharCount());
		md.setSecurity(si.getSecurity());

		Calendar createDateTime = Calendar.getInstance();
		createDateTime.setTime(si.getCreateDateTime());
		md.setCreateDateTime(createDateTime);

		Calendar lastSaveDateTime = Calendar.getInstance();
		lastSaveDateTime.setTime(si.getLastSaveDateTime());
		md.setLastSaveDateTime(lastSaveDateTime);

		Calendar lastPrinted = Calendar.getInstance();
		lastPrinted.setTime(si.getLastPrinted());
		md.setLastPrinted(lastPrinted);
	}

	log.info("officeExtractor: {}", md);
	return md;
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
public String xls2text(InputStream is) throws IOException {
    ExcelExtractor wd = new ExcelExtractor(new HSSFWorkbook(is));
    String text = wd.getText();
    wd.close();
    return text;
}
 

import org.apache.poi.hssf.extractor.ExcelExtractor; //导入依赖的package包/类
private void extractHeaderFooter(final StringBuilder buffy, final HeaderFooter hf) {
    final String content = ExcelExtractor._extractHeaderFooter(hf);
    if (content.length() > 0) {
        buffy.append(content).append(' ');
    }
}