org.apache.poi.hwpf.HWPFDocument Java Examples

public static void setDocProperties(String filename) throws IOException {
    System.out.println("filename = [" + filename + "]");
    FileInputStream fis = new FileInputStream(new File(filename));
    HWPFDocument doc = new HWPFDocument(fis);

    SummaryInformation summaryInformation = doc.getSummaryInformation();
    summaryInformation.setAuthor("张鹏");
    summaryInformation.setLastAuthor("张鹏");
    DocumentSummaryInformation documentSummaryInformation = doc.getDocumentSummaryInformation();
    documentSummaryInformation.setCompany("张鹏");
    documentSummaryInformation.setDocumentVersion("1");

    FileOutputStream fos = new FileOutputStream(new File(filename));
    doc.write(fos);

    fos.close();
    doc.close();
    fis.close();
}
 

public static String parseDoc2Html(InputStream input, String charset) throws Exception {
  HWPFDocument wordDocument = new HWPFDocument(input);
  Document doc = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
  WordToHtmlConverter converter = new WordToHtmlConverter(doc);
  converter.processDocument(wordDocument);

  ByteArrayOutputStream output = new ByteArrayOutputStream();
  try {
    DOMSource domSource = new DOMSource(converter.getDocument());
    StreamResult streamResult = new StreamResult(output);
    Transformer serializer = TransformerFactory.newInstance().newTransformer();
    // TODO 有乱码
    serializer.setOutputProperty(OutputKeys.ENCODING, charset);
    serializer.setOutputProperty(OutputKeys.INDENT, "yes");
    serializer.setOutputProperty(OutputKeys.METHOD, "html");
    serializer.transform(domSource, streamResult);
  } finally {
    input.close();
    output.close();
  }

  return new String(output.toByteArray());
}
 

@Test
    public void testDoc() throws IOException {
        HWPFDocument document = new HWPFDocument(new FileInputStream("D:\\Xiaoi\\Items\\2019-07-02 合同智能分析工具\\04_现场数据\\4.25国网北京信通公司110kV半壁店站等63个站点通信蓄电池改造勘察设计合同.doc"));
//        for ( FieldsDocumentPart part : FieldsDocumentPart.values() ) {
//            System.out.println( "=== Document part: " + part + " ===" );
//            for ( Field field : document.getFields().getFields( part ) ) {
//                System.out.println(field.firstSubrange(document.getRange()).getParagraph(0).text());
//            }
//        }

        for (int i=0;i<document.getRange().numParagraphs();i++){
            Paragraph paragraph = document.getRange().getParagraph(i);
            System.out.println(paragraph.text());
            System.out.println("===============================================");
        }

//        for (Field field : document.getFields().getFields(FieldsDocumentPart.MAIN)){
//            System.out.println(field);
//            System.out.println(field.firstSubrange(document.getRange()).getParagraph(0).text());
//        }
//        System.out.println(document.getRange().getParagraph(0).text());
//        System.out.println(document.getMainTextboxRange().getSection(0).text());

    }
 

/**
 * 创建Doc并保存
 *
 * @param templatePath 模板doc路径
 * @param parameters   参数和值
 *                     //* @param imageParameters 书签和图片
 * @param savePath     保存doc的路径
 * @return
 */
public static void CreateDocFromTemplate(String templatePath,
                                         HashMap<String, String> parameters,
                                         //HashMap<String, String> imageParameters,
                                         String savePath)
        throws Exception {
    @Cleanup InputStream is = DocProducer.class.getResourceAsStream(templatePath);
    HWPFDocument doc = new HWPFDocument(is);
    Range range = doc.getRange();

    //把range范围内的${}替换
    for (Map.Entry<String, String> next : parameters.entrySet()) {
        range.replaceText("${" + next.getKey() + "}",
                next.getValue()
        );
    }

    @Cleanup OutputStream os = new FileOutputStream(savePath);
    //把doc输出到输出流中
    doc.write(os);
}
 

/**
 * WORD转HTML
 * 
 * @param docfile
 *            WORD文件全路径
 * @param htmlfile
 *            转换后HTML存放路径
 * @throws Throwable
 * add by duanql	2013-07-17
 */

public void WordConverterHtml(String docfile, String htmlfile){
	try {
	InputStream input = new FileInputStream(docfile);
	HWPFDocument wordDocument = new HWPFDocument(input);
	WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
	wordToHtmlConverter.processDocument(wordDocument);
	Document htmlDocument = wordToHtmlConverter.getDocument();
	ByteArrayOutputStream outStream = new ByteArrayOutputStream();
	DOMSource domSource = new DOMSource(htmlDocument);
	StreamResult streamResult = new StreamResult(outStream);

	TransformerFactory tf = TransformerFactory.newInstance();
	Transformer serializer = tf.newTransformer();
	serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
	serializer.setOutputProperty(OutputKeys.INDENT, "yes");
	serializer.setOutputProperty(OutputKeys.METHOD, "html");
	serializer.transform(domSource, streamResult);
	outStream.close();

	String content = new String(outStream.toByteArray(), "UTF-8");
	stringToFile(content,htmlfile);
	} catch (Exception e) {
		e.printStackTrace();
	}
}
 

/**
 * Get the text from the word file, as an array with one String
 *  per paragraph
 */
public static String[] getWordParagraphText(HWPFDocument doc) {
	String[] ret;
	
	// Extract using the model code
	try {
    	Range r = doc.getRange();

		ret = new String[r.numParagraphs()];
		for(int i=0; i<ret.length; i++) {
			Paragraph p = r.getParagraph(i);
			ret[i] = p.text();
			
			// Fix the line ending
			if(ret[i].endsWith("\r")) {
				ret[i] = ret[i] + "\n";
			}
		}
	}
               catch(Exception e) {
		// Something's up with turning the text pieces into paragraphs
		// Fall back to ripping out the text pieces
		ret = new String[1];
		ret[0] = getWordTextFromPieces(doc);
	}
	
	return ret;
}
 

/**
 * Grab the text, based on the paragraphs. Shouldn't include any crud,
 *  but slightly slower than getTextFromPieces().
 */
public static String getWordTextOld(HWPFDocument doc) {
	StringBuilder ret = new StringBuilder();
	String[] text = getWordParagraphText(doc);
	for(int i=0; i<text.length; i++) {
		ret.append(text[i]);
	}
	return ret.toString();
}
 

/**
 * WORD转HTML
 * 
 * @param docfile
 *            WORD文件全路径
 * @param htmlfile
 *            转换后HTML存放路径
 * @throws Throwable
 * add by duanql	2013-07-17
 */

public void WordConverterHtml(String docfile, String htmlfile){
	try {
	InputStream input = new FileInputStream(docfile);
	HWPFDocument wordDocument = new HWPFDocument(input);
	WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
	wordToHtmlConverter.processDocument(wordDocument);
	Document htmlDocument = wordToHtmlConverter.getDocument();
	ByteArrayOutputStream outStream = new ByteArrayOutputStream();
	DOMSource domSource = new DOMSource(htmlDocument);
	StreamResult streamResult = new StreamResult(outStream);

	TransformerFactory tf = TransformerFactory.newInstance();
	Transformer serializer = tf.newTransformer();
	serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
	serializer.setOutputProperty(OutputKeys.INDENT, "yes");
	serializer.setOutputProperty(OutputKeys.METHOD, "html");
	serializer.transform(domSource, streamResult);
	outStream.close();

	String content = new String(outStream.toByteArray(), "UTF-8");
	stringToFile(content,htmlfile);
	} catch (Exception e) {
		e.printStackTrace();
	}
}
 

/**
 * 向word模板中填充数据，生成新word
 * templePath 是word模板的路径，outPutPath是输出路径
 * 注意模板是doc导出的就是doc，docx导出的是docx，否则会错误，
 *
 * @param mapData    填充的数据
 * @param templePath 模板路径
 * @throws Exception
 */
public static void generateWord(HashMap mapData, String templePath, String outPutPath) throws Exception {
    //因为空格无法输出，过滤一下空格 用-代替
    Iterator<Map.Entry<String, String>> iter = mapData.entrySet().iterator();
    while (iter.hasNext()) {
        Map.Entry entry = iter.next();
        Object key = entry.getKey();
        Object val = entry.getValue();
        if ("".equals(val)) {
            //空格无法输出
            mapData.put(key, "-");
        }
    }

    //先创建文件
    File file = new File(outPutPath);
    if (file.exists()) {
        file.delete();
    }
    file.getParentFile().mkdirs();
    file.createNewFile();

    try {
        //获取文件后缀
        String suffix = getSuffix(templePath);
        if (suffix.equalsIgnoreCase(DOCX_SUFFIX)) {
            XWPFDocument doc = WordExportUtil.exportWord07(templePath, mapData);
            FileOutputStream fos = new FileOutputStream(file);
            doc.write(fos);
            fos.close();
        } else if (suffix.equalsIgnoreCase(DOC_SUFFIX)) {
            HWPFDocument hwpfDocument = new HWPFDocument(new FileInputStream(templePath));
            Range range = hwpfDocument.getRange();
            getRange(range, mapData);
            FileOutputStream stream = new FileOutputStream(file);
            hwpfDocument.write(stream);
            stream.flush();
            stream.close();
        }
    } catch (Exception e) {
        e.printStackTrace();
    }
}
 

private void addWaterMark(Object obj, String watermark, String color) {
	if (obj instanceof XWPFDocument) {
		XWPFDocument doc = (XWPFDocument) obj;
		// create header-footer
		XWPFHeaderFooterPolicy headerFooterPolicy = doc.getHeaderFooterPolicy();
		if (headerFooterPolicy == null) headerFooterPolicy = doc.createHeaderFooterPolicy();
		
		// create default Watermark - fill color black and not rotated
		headerFooterPolicy.createWatermark(watermark);
		
		// get the default header
		// Note: createWatermark also sets FIRST and EVEN headers 
		// but this code does not updating those other headers
		XWPFHeader header = headerFooterPolicy.getHeader(XWPFHeaderFooterPolicy.DEFAULT);
		XWPFParagraph paragraph = header.getParagraphArray(0);
		
		// get com.microsoft.schemas.vml.CTShape where fill color and rotation is set
		XmlObject[] xmlobjects = paragraph.getCTP().getRArray(0).getPictArray(0).selectChildren(new QName("urn:schemas-microsoft-com:vml", "shape"));
		if (xmlobjects.length > 0) {
			com.microsoft.schemas.vml.CTShape ctshape = (com.microsoft.schemas.vml.CTShape)xmlobjects[0];
			// set fill color
			ctshape.setFillcolor(color);
			// set rotation
			ctshape.setStyle(ctshape.getStyle() + ";rotation:315");
		}
	} else if (obj instanceof HWPFDocument) {
		
	}
}
 

public static String getWordTextOld(InputStream is) {
    try {
        return getWordTextOld(new HWPFDocument(is));
    }
    catch(Exception e) {
        e.printStackTrace();
    }
    return null;
}