Java WordExtractor.getText方法代码示例

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
private static String readDoc (String filePath, InputStream is) throws Exception {
    String text= "";
    is = FileMagic.prepareToCheckMagic(is);
    try {
        if (FileMagic.valueOf(is) == FileMagic.OLE2) {
            WordExtractor ex = new WordExtractor(is);
            text = ex.getText();
            ex.close();
        } else if(FileMagic.valueOf(is) == FileMagic.OOXML) {
            XWPFDocument doc = new XWPFDocument(is);
            XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
            text = extractor.getText();
            extractor.close();
        }
    } catch (OfficeXmlFileException e) {
        logger.error(filePath, e);
    } finally {
        if (is != null) {
            is.close();
        }
    }
    return text;
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
private static String microsoftWordDocumentToString(InputStream inputStream) throws IOException {
    String strRet;

    try (InputStream wordStream = new BufferedInputStream(inputStream)) {
        if (POIFSFileSystem.hasPOIFSHeader(wordStream)) {
            WordExtractor wordExtractor = new WordExtractor(wordStream);
            strRet = wordExtractor.getText();
            wordExtractor.close();
        } else {
            XWPFWordExtractor wordXExtractor = new XWPFWordExtractor(new XWPFDocument(wordStream));
            strRet = wordXExtractor.getText();
            wordXExtractor.close();
        }
    }

    return strRet;
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
@Override
public void readContent(ClassifiableContentIF cc, TextHandlerIF handler) {
  try {
    WordExtractor extractor = new WordExtractor(new BufferedInputStream(new ByteArrayInputStream(cc.getContent())));
    String s = extractor.getText();
    char[] c = s.toCharArray();
    handler.startRegion("document");
    handler.text(c, 0, c.length);
    handler.endRegion();
  } catch (Exception e) {
    throw new OntopiaRuntimeException(e);
  }    
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
public IndexDocument getIndexedDocument(File2Index fileData)
		throws SolrException {
	try {
		POIFSFileSystem fs = new POIFSFileSystem(new ByteArrayInputStream(fileData.data));
		WordExtractor extractor = new WordExtractor(fs);
		String wordText = extractor.getText();

		return new IndexDocument(fileData.path, wordText, 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.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
public String doc2text(InputStream is) throws IOException {
    WordExtractor wd = new WordExtractor(is);
    String text = wd.getText();
    wd.close();
    return text;
}
 

import org.apache.poi.hwpf.extractor.WordExtractor; //导入方法依赖的package包/类
/**
 * Extract text from a word 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);
		HWPFDocument wordDocument = new HWPFDocument(inputStream);
		WordExtractor wordExtractor = new WordExtractor(wordDocument);
		

		String myText = wordExtractor.getText();
		if( myText != null && !myText.trim().equals(""))
		{
		    text = myText;
		}
	}
	catch(OutOfMemoryError oome)
	{
		text = null;
		log.error("could not extract text", oome);
		throw(oome);
	}
	catch(Exception e)
	{
		text = null;
		log.error("could not get text for word document " + f.getAbsolutePath(), e);
		throw(e);
	}
	
	finally
	{
		closeInputStream(inputStream);
	}
	return text;
}