import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
public static void replaceWordDoc(String inPath, String outPath, Map<String, String> context) {
	Validate.notBlank(inPath);
	Validate.notBlank(outPath);
	Validate.notNull(context);
	try (FileInputStream in = new FileInputStream(new File(inPath));
			FileOutputStream out = new FileOutputStream(outPath, false)) {
		HWPFDocument hdt = new HWPFDocument(in);
		Range range = hdt.getRange();
		for (Map.Entry<String, String> entry : context.entrySet()) {
			range.replaceText(entry.getKey(), entry.getValue());
		}
		hdt.write(out);
	} catch (IOException e) {
		e.printStackTrace();
	}
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * Method to save the file by parameters in doc format
 *
 * @param toSave The file where the information will be saved
 */
private void saveDoc(File toSave) {
  try {
    POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream("down/empty.doc"));
    HWPFDocument doc = new HWPFDocument(fs);
    Range range = doc.getRange();
    Paragraph parContainer = range.insertAfter(new ParagraphProperties(), 0);
    for (String para : paragraphs) {
      parContainer.setSpacingAfter(200);
      parContainer.insertAfter(para);
      parContainer = range.insertAfter(new ParagraphProperties(), 0);
    }
    FileOutputStream fos = new FileOutputStream(toSave);
    doc.write(fos);
    fos.close();
  } catch (Exception e) {
    Logger.getGlobal().log(Level.SEVERE, e.getMessage() + "\n" + Arrays.toString(e.getStackTrace()));
  }
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * 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);
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
@Test
	public void testReadByDoc() throws Exception {
		InputStream is = new FileInputStream("E://video/doc/xiuParty/90Xiu-NEW/oss/90秀--oss与服务器端接口文档.doc");
		POIFSFileSystem pfilesystem = new POIFSFileSystem(is);
		HWPFDocument doc = new HWPFDocument(pfilesystem);
//		// 输出书签信息
//		this.printInfo(doc.getBookmarks());
//		// 输出文本
//		System.out.println(doc.getDocumentText());
		Range range = doc.getRange();
		// this.insertInfo(range);
		this.printInfo(range);
		// 读表格
		this.readTable(range);
		// 读列表
		this.readList(range);
		// 删除range
		Range r = new Range(2, 5, doc);
		r.delete();// 在内存中进行删除，如果需要保存到文件中需要再把它写回文件
		// 把当前HWPFDocument写到输出流中
		doc.write(new FileOutputStream("D:\\test.doc"));
		IOUtils.closeQuietly(is);
	}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * 读表格 每一个回车符代表一个段落，所以对于表格而言，每一个单元格至少包含一个段落，每行结束都是一个段落。
 * 
 * @param range
 */
private void readTable(Range range) {
	// 遍历range范围内的table。
	TableIterator tableIter = new TableIterator(range);
	Table table;
	TableRow row;
	TableCell cell;
	while (tableIter.hasNext()) {
		table = tableIter.next();
		int rowNum = table.numRows();
		for (int j = 0; j < rowNum; j++) {
			row = table.getRow(j);
			int cellNum = row.numCells();
			for (int k = 0; k < cellNum; k++) {
				cell = row.getCell(k);
				// 输出单元格的文本
				System.out.println(cell.text().trim());
			}
		}
	}
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * 输出Range
 * 
 * @param range
 */
private void printInfo(Range range) {
	// 获取段落数
	int paraNum = range.numParagraphs();
	System.out.println(paraNum);
	for (int i = 0; i < paraNum; i++) {
		// this.insertInfo(range.getParagraph(i));
		System.out.println("段落" + (i + 1) + "：" + range.getParagraph(i).text());
		if (i == (paraNum - 1)) {
			this.insertInfo(range.getParagraph(i));
		}
	}
	int secNum = range.numSections();
	System.out.println(secNum);
	Section section;
	for (int i = 0; i < secNum; i++) {
		section = range.getSection(i);
		System.out.println(section.getMarginLeft());
		System.out.println(section.getMarginRight());
		System.out.println(section.getMarginTop());
		System.out.println(section.getMarginBottom());
		System.out.println(section.getPageHeight());
		System.out.println(section.text());
	}
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
private void handleHeaderFooter(Range[] ranges, String type,
    HWPFDocument document, PicturesSource pictures,
    PicturesTable pictureTable, XHTMLContentHandler xhtml)
    throws SAXException, IOException, TikaException {
  if (countParagraphs(ranges) > 0) {
    xhtml.startElement("div", "class", type);
    for (Range r : ranges) {
      if (r != null) {
        for (int i = 0; i < r.numParagraphs(); i++) {
          Paragraph p = r.getParagraph(i);

          String text = p.text();
          if (text.replaceAll("[\\r\\n\\s]+", "").isEmpty()) {
            // Skip empty header or footer paragraphs
          } else {
            i += handleParagraph(p, 0, r, document,
                FieldsDocumentPart.HEADER, pictures, pictureTable, xhtml);
          }
        }
      }
    }
    xhtml.endElement("div");
  }
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
@Override
protected void processBookmarks( HWPFDocumentCore wordDocument,
        Element currentBlock, Range range, int currentTableLevel,
        List<Bookmark> rangeBookmarks )
{
    Element parent = currentBlock;
    for ( Bookmark bookmark : rangeBookmarks )
    {
        Element bookmarkElement = foDocumentFacade.createInline();
        final String idName = "bookmark_" + bookmark.getName();
        // make sure ID used once
        if ( setId( bookmarkElement, idName ) )
        {
            /*
             * if it just empty fo:inline without "id" attribute doesn't
             * making sense to add it to DOM
             */
            parent.appendChild( bookmarkElement );
            parent = bookmarkElement;
        }
    }

    if ( range != null )
        processCharacters( wordDocument, currentTableLevel, range, parent );
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
@Override
protected void processBookmarks( HWPFDocumentCore wordDocument,
        Element currentBlock, Range range, int currentTableLevel,
        List<Bookmark> rangeBookmarks )
{
    Element parent = currentBlock;
    for ( Bookmark bookmark : rangeBookmarks )
    {
        Element bookmarkElement = htmlDocumentFacade
                .createBookmark( bookmark.getName() );
        parent.appendChild( bookmarkElement );
        parent = bookmarkElement;
    }

    if ( range != null )
        processCharacters( wordDocument, currentTableLevel, range, parent );
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
protected void processNote( HWPFDocument wordDocument, Element block,
        Range noteTextRange )
{
    final int noteIndex = noteCounters.getAndIncrement();
    block.appendChild( textDocumentFacade
            .createText( UNICODECHAR_ZERO_WIDTH_SPACE + "[" + noteIndex
                    + "]" + UNICODECHAR_ZERO_WIDTH_SPACE ) );

    if ( notes == null )
        notes = textDocumentFacade.createBlock();

    Element note = textDocumentFacade.createBlock();
    notes.appendChild( note );

    note.appendChild( textDocumentFacade.createText( "^" + noteIndex
            + "\t " ) );
    processCharacters( wordDocument, Integer.MIN_VALUE, noteTextRange, note );
    note.appendChild( textDocumentFacade.createText( "\n" ) );
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
    * Get the text from the word file, as an array with one String
    *  per paragraph
    */
@Deprecated
public String[] getParagraphText() {
    String[] ret;

    // Extract using the model code
    try {
        Range r = doc.getRange();

        ret = WordExtractor.getParagraphText(r);
    } catch (Exception e) {
           // Something's up with turning the text pieces into paragraphs
           // Fall back to ripping out the text pieces
        ret = new String[doc.getTextTable().getTextPieces().size()];
        for(int i=0; i<ret.length; i++) {
            ret[i] = doc.getTextTable().getTextPieces().get(i).getStringBuilder().toString();
            
            // Fix the line endings
            ret[i].replaceAll("\r", "\ufffe");
               ret[i].replaceAll("\ufffe","\r\n");
        }
    }

    return ret;
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * Get the text from the word file, as an array with one String per
 * paragraph
 */
public String[] getParagraphText()
{
    String[] ret;

    // Extract using the model code
    try
    {
        Range r = doc.getRange();

        ret = getParagraphText( r );
    }
    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] = getTextFromPieces();
    }

    return ret;
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
  * Not all documents have all the images concatenated in the data stream
  * although MS claims so. The best approach is to scan all character runs.
  *
  * @return a list of Picture objects found in current document
  */
 public List<Picture> getAllPictures() {
   ArrayList<Picture> pictures = new ArrayList<Picture>();

   Range range = _document.getOverallRange();
   for (int i = 0; i < range.numCharacterRuns(); i++) {
   	CharacterRun run = range.getCharacterRun(i);

       if (run==null) {
           continue;
       }

   	Picture picture = extractPicture(run, false);
   	if (picture != null) {
   		pictures.add(picture);
   	}
}

   searchForPictures(_dgg.getEscherRecords(), pictures);

   return pictures;
 }
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * Processing of text requests.
 * 
 * @param doc word document
 * @param paragraphRef reference to paragraphs
 * @return list of text values as {@code LinkedList<Value>}
 */
private LinkedList<Value> processParagraphRequest(HWPFDocument doc, String paraRef) {
    LinkedList<Value> valList = new LinkedList<Value>();
    Range docRange = doc.getRange();

    setStartEndParagraph(paraRef, "*");
    if (this.startPara == -1 || this.endPara == -1) {
        this.startPara = 0;
        this.endPara = docRange.numParagraphs() - 1;
    }

    // -1 => all paragraphs requested
    if (this.startPara < docRange.numParagraphs()) {
        if (!(this.endPara < docRange.numParagraphs())) {
            this.endPara = docRange.numParagraphs() - 1;
        }

        for (Integer pPos = this.startPara; pPos <= this.endPara; pPos++) {
            Paragraph p = docRange.getParagraph(pPos);
            Integer subURI = pPos + 1;
            valList.add(getParagraph(p, subURI.toString()));
        }
    }

    return valList;
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
public  ArrayList<TableData> read(String path) throws IOException {
		FileInputStream in = new FileInputStream(new File(path));  
        HWPFDocument hwpf = new HWPFDocument(in);  
        Range range = hwpf.getRange();// 得到文档的读取范围  
        TableIterator it = new TableIterator(range);  
        ArrayList<TableData> list=new ArrayList<TableData>();
        int count=0;
        // 迭代文档中的表格  
        while (it.hasNext()) {  
            Table tb = (Table) it.next();  
            TableData data=new TableData();
            // 迭代行，默认从0开始  
            for (int i = 0; i < tb.numRows(); i++) {  
                TableRow tr = tb.getRow(i);  
                // 迭代列，默认从0开始  
                for (int j = 0; j < tr.numCells(); j++) {  
                    TableCell td = tr.getCell(j);// 取得单元格  
                    // 取得单元格的内容  
                    StringBuffer sb=new StringBuffer();
                    for (int k = 0; k < td.numParagraphs(); k++) {  
                        Paragraph para = td.getParagraph(k);  
                        sb.append(para.text());  
                    } 
                    String string=sb.toString().trim();
                    if(i==0&&j==1)
                    {
                    	data.setClazz(string);
                    }
                    else if(i==1&&j==1)
                    {
                    	data.setName(string);
                    }
                    else if(i==2&&j==1)
                    {
                    	data.setLifeCircle(string);
                    }
                    else if(i==2&&j==3)
                    {
                    	data.setTheme(string);
                    }
                    else if(i==3&&j==3)
                    {
                    	data.setForm(string);
                    }
                    else if(i==4&&j==1)
                    {
                    	data.setKeywords(string);
                    }
                    else if(i==9&&j==1)
                    {
                    	data.setContent(string);
                    }
                }  
            }
//            show("第"+count+"条："+data.toString());
            count+=1;
            list.add(data);
        }
		return list;
	}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * 读列表
 * 
 * @param range
 */
private void readList(Range range) {
	int num = range.numParagraphs();
	Paragraph para;
	for (int i = 0; i < num; i++) {
		para = range.getParagraph(i);
		if (para.isInList()) {
			System.out.println("list: " + para.text());
		}
	}
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
private static int countParagraphs(Range... ranges) {
  int count = 0;
  for (Range r : ranges) {
    if (r != null) {
      count += r.numParagraphs();
    }
  }
  return count;
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
public static void main(String[] args) throws Exception
{
	HWPFDocument doc = new HWPFDocument(new FileInputStream(
			"data/document.doc"));

	Range range = doc.getRange();
	String text = range.text();
	
	System.out.println("Range: " + text);
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
public static void main(String[] args) throws Exception
{
	String dataPath = "src/featurescomparison/workingwithranges/accessranges/data/";
	
	HWPFDocument doc = new HWPFDocument(new FileInputStream(
			dataPath + "document.doc"));

	Range range = doc.getRange();
	String text = range.text();
	
	System.out.println("Range: " + text);
}
 

import org.apache.poi.hwpf.usermodel.Range; //导入依赖的package包/类
/**
 * 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;
}