Java读取word文档

	public static String readWord(InputStream inputStream,String suffix) throws Exception{

//		File file = new File(filePath);
//		if(file.length()==0) return ""; // 需要操作原因是可能会空文件问题，如果不做处理，在下面读取中会报错
		StringBuffer sb = new StringBuffer();
		String buffer = "";
		try {
			if ("doc".equals(suffix)) {
//				InputStream is = new FileInputStream(file);
				WordExtractor ex = new WordExtractor(inputStream);
				buffer = ex.getText();
				if(buffer.length() > 0){
					//使用回车换行符分割字符串
					String [] arry = buffer.split("\r\n");
					for (String string : arry) {
						sb.append(string.trim());
					}
				}
			} else if ("docx".equals(suffix)) {
				OPCPackage opcPackage = OPCPackage.open(inputStream);
				POIXMLTextExtractor extractor = new XWPFWordExtractor(opcPackage);
				buffer = extractor.getText();
				if(buffer.length() > 0){
					//使用换行符分割字符串
					String [] arry = buffer.split("\n");
					for (String string : arry) {
						sb.append(string.trim());
					}
				}
			} else if("pdf".equals(suffix)){
				RandomAccessBuffer rab = new RandomAccessBuffer(inputStream);
				PDFParser pdfParser = new PDFParser(rab);
				pdfParser.parse();
				PDDocument document = pdfParser.getPDDocument();
				// 获取页码
				int pages = document.getNumberOfPages();
				PDFTextStripper stripper = new PDFTextStripper();
				// 设置按顺序输出
				stripper.setSortByPosition(true);
				stripper.setStartPage(1);
				stripper.setEndPage(pages);
				sb.append(stripper.getText(document));
			}else{
				return null;
			}
			return sb.toString();
		} catch (Exception e) {
			throw e;
		}
	}