对Word文档中的指定内容进行替换

    不知大家在对Word操作时，有没有遇到需要对指定内容进行替换这种需求。前几天公司有个需求，就是对PDF邀请函的姓名那部分内容进行替换，因为本人以前对Word的书签有过操作，所以思路就是通过将这部分内容设定为书签，对书签的进行替换保存为新的邀请函。

    用到的lib包括，特别强调下，jacob使用时需要给C:/WINDOWS/System32目录下添加jacob对应位数的dll文件：

具体的步骤如下:

    1、首先将PDF转化为WORD文档，替换书签个人感觉WORD操作起来比较方便点，替换后的格式或许有稍许错位，重新编译保存下，将该WORD文档作为邀请函模板;

       

    2、对需要替换的部分添加书签，对邀请人的xx添加书签，暂且命名为xm；

    

    3、替换的内容是以EXCEL存储的单列数据，又引入POI操作EXCEL部分的内容，该类就是POI读取EXCEL内容的公共类，包括XLS以及XLSX；

public class parseExcelFile {
	public static final String OFFICE_EXCEL_2003_POSTFIX = "xls";
	public static final String OFFICE_EXCEL_2010_POSTFIX = "xlsx";
	public static final String EMPTY = "";
	public static final String POINT = ".";
	public static final String NOT_EXCEL_FILE = " : Not the Excel file!";
	public static final String PROCESSING = "Processing...";

	/**
	 * 读Excel文件
	 * 
	 * @param file
	 *            Ecxel文件
	 * @param sheetNum
	 *            第几个sheet 必须大于0或为null（默认1） 否则会报错
	 * @param startLine
	 *            开始行(包含本行) 必须大于0或为null（默认1） 否则会报错
	 * @param endLine
	 *            结束行(包含本行) 必须大于等于开始行或为null（默认最大行） 否则会报错
	 * @param startColumn
	 *            开始列(包含本列) 必须大于0或为null（默认1） 否则会报错
	 * @param endColumn
	 *            结束列(包含本列) 必须大于等于开始列或为null（默认第一行列数） 否则会报错
	 * @return
	 * @throws IOException
	 */
	public Map readExcel(File file, Integer sheetNum, Integer startLine, Integer endLine,
			Integer startColumn, Integer endColumn) throws IOException {
		if (file == null || EMPTY.equals(file)) {
			return null;
		} else {
			String postfix = this.getPostfix(file.getName());
			if (!EMPTY.equals(postfix)) {
				if (OFFICE_EXCEL_2003_POSTFIX.equals(postfix)) {
					return readXls(file, sheetNum, startLine, endLine, startColumn, endColumn);
				} else if (OFFICE_EXCEL_2010_POSTFIX.equals(postfix)) {
					return readXlsx(file, sheetNum, startLine, endLine, startColumn, endColumn);
				}
			} else {
				System.out.println(file + NOT_EXCEL_FILE);
			}
		}
		return null;
	}

	/**
	 * 读2010 xlsx Excel文件
	 * 
	 * @param 文件路径
	 * @param sheetNum
	 *            第几个sheet
	 * @param startLine
	 *            开始行
	 * @param endLine
	 *            结束行
	 * @param startColumn
	 *            开始列
	 * @param endColumn
	 *            结束列
	 * @return
	 * @throws IOException
	 */
	public Map readXlsx(File file, Integer sheetNum, Integer startLine, Integer endLine,
			Integer startColumn, Integer endColumn) throws IOException {
		System.out.println(PROCESSING + file.getName());
		InputStream is = new FileInputStream(file);
		XSSFWorkbook xssfWorkbook = new XSSFWorkbook(is);
		Map map = new HashMap();
		// Read the Sheet
		// for (int numSheet = 0; numSheet < xssfWorkbook.getNumberOfSheets();
		// numSheet++) {
		if (sheetNum == null || sheetNum.equals("")) {
			sheetNum = 1;
			map.put("sheetNum", sheetNum.toString());
		}
		XSSFSheet xssfSheet = xssfWorkbook.getSheetAt(sheetNum - 1);
		if (xssfSheet != null) {
			if (startLine == null || EMPTY.equals(startLine)) {
				startLine = 1;
				map.put("startLine", startLine.toString());
			}
			if (endLine == null || EMPTY.equals(endLine)) {
				endLine = xssfSheet.getLastRowNum() + 1;
				map.put("endLine", endLine.toString());
			}
			if (startColumn == null || EMPTY.equals(startColumn)) {
				startColumn = 1;
				map.put("startColumn", startColumn.toString());
			}
			if (endColumn == null || EMPTY.equals(endColumn)) {
				// 默认获得第一行的列数
				endColumn = xssfSheet.getRow(0).getPhysicalNumberOfCells();
				map.put("endColumn", endColumn.toString());
			}
			// Read the Row
			for (int rowNum = startLine - 1; rowNum < endLine; rowNum++) {
				XSSFRow xssfRow = xssfSheet.getRow(rowNum);
				if (xssfRow != null) {
					for (int i = startColumn - 1; i < endColumn; i++) {
						XSSFCell xc = xssfRow.getCell(i);
						map.put(sheetNum + "-" + rowNum + "-" + i, getValue(xc));
					}
				}
			}
		}
		// }
		return map;
	}

	/**
	 * 读2003 xls Excel文件
	 * 
	 * @param 文件路径
	 * @param startLine
	 *            开始行
	 * @param endLine
	 *            结束行
	 * @param startColumn
	 *            开始列
	 * @param endColumn
	 *            结束列
	 * @return
	 * @throws IOException
	 */
	public Map readXls(File file, Integer sheetNum, Integer startLine, Integer endLine,
			Integer startColumn, Integer endColumn) throws IOException {
		System.out.println(PROCESSING + file.getName());
		InputStream is = new FileInputStream(file);
		POIFSFileSystem fs = new POIFSFileSystem(is);
		HSSFWorkbook hssfWorkbook = new HSSFWorkbook(fs);
		Map map = new HashMap();
		// Read the Sheet
		// for (int numSheet = 0; numSheet < hssfWorkbook.getNumberOfSheets();
		// numSheet++) {
		if (sheetNum == null || sheetNum.equals("")) {
			sheetNum = 1;
			map.put("sheetNum", sheetNum.toString());
		}
		HSSFSheet hssfSheet = hssfWorkbook.getSheetAt(sheetNum - 1);
		if (hssfSheet != null) {

			if (startLine == null || EMPTY.equals(startLine)) {
				startLine = 1;
				map.put("startLine", startLine.toString());
			}
			if (endLine == null || EMPTY.equals(endLine)) {
				endLine = hssfSheet.getLastRowNum() + 1;
				map.put("endLine", endLine.toString());
			}
			if (startColumn == null || EMPTY.equals(startColumn)) {
				startColumn = 1;
				map.put("startColumn", startColumn.toString());
			}
			if (endColumn == null || EMPTY.equals(endColumn)) {
				// 默认获得第一行的列数
				endColumn = hssfSheet.getRow(0).getPhysicalNumberOfCells();
				map.put("endColumn", endColumn.toString());
			}
			// Read the Row
			for (int rowNum = startLine - 1; rowNum < endLine; rowNum++) {
				HSSFRow hssfRow = hssfSheet.getRow(rowNum);
				if (hssfRow != null) {
					for (int i = startColumn - 1; i < endColumn; i++) {
//						HSSFCell xc = hssfRow.getCell(i);
//						System.out.println("xc=" + xc);
						map.put(sheetNum + "-" + rowNum + "-" + i, getValue(hssfRow.getCell(i)));
					}
				}
			}
		}
		// }
		return map;
	}

	/**
	 * 获得后缀名
	 * 
	 * @param path
	 * @return
	 */
	public String getPostfix(String path) {
		if (path == null || EMPTY.equals(path.trim())) {
			return EMPTY;
		}
		if (path.contains(POINT)) {
			return path.substring(path.lastIndexOf(POINT) + 1, path.length());
		}
		return EMPTY;
	}

	@SuppressWarnings("static-access")
	private String getValue(XSSFCell xssfRow) {
		if (xssfRow.getCellType() == xssfRow.CELL_TYPE_BOOLEAN) {
			return String.valueOf(xssfRow.getBooleanCellValue());
		} else if (xssfRow.getCellType() == xssfRow.CELL_TYPE_NUMERIC) {
			if (XSSFDateUtil.isCellDateFormatted(xssfRow)) {
				return XSSFDateUtil.getJavaDate(xssfRow.getNumericCellValue()).toString();
			} else {
				HSSFDataFormatter dateFormatter=new HSSFDataFormatter();
				String xcssfFormatted=dateFormatter.formatCellValue(xssfRow);
				return xcssfFormatted;
			}
		} else {
			return String.valueOf(xssfRow.getStringCellValue());
		}
	}

	@SuppressWarnings("static-access")
	private String getValue(HSSFCell hssfCell) {
		if (hssfCell.getCellType() == hssfCell.CELL_TYPE_BOOLEAN) {
			return String.valueOf(hssfCell.getBooleanCellValue());
		} else if (hssfCell.getCellType() == hssfCell.CELL_TYPE_NUMERIC) {
			if (HSSFDateUtil.isCellDateFormatted(hssfCell)) {
				return HSSFDateUtil.getJavaDate(hssfCell.getNumericCellValue()).toString();
			} else {
				HSSFDataFormatter dateFormatter=new HSSFDataFormatter();
				String ceccFormatted=dateFormatter.formatCellValue(hssfCell);
				return ceccFormatted;
			}
		} else {
			return String.valueOf(hssfCell.getStringCellValue());
		}
	}

	

	/**
	 * 删除文件
	 * 
	 * @param path
	 *            文件路径
	 * @return
	 */
	public String deleteTemporaryFile(String path) {
		if (path != null && !path.equals("")) {
			File file = new File(path);
			if (file.exists()) {
				file.delete();
			}
		}
		return "success";
	}

public class XSSFDateUtil extends DateUtil{
	protected static int absoluteDay(Calendar cal,boolean use1904windowing){
		return DateUtil.absoluteDay(cal, use1904windowing);
	}
}

    数据源内容

   

 

    4、通过jacob操作WORD,读取该书签的内容并进行替换，重新保存为PDF文档，核心代码如下：

 

    

package com.ecservice;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;

import com.jacob.activeX.ActiveXComponent;
import com.jacob.com.ComThread;
import com.jacob.com.Dispatch;
import com.jacob.com.Variant;

public class PDFRead {

	private static final int wdFormatPDF = 17;// word转PDF 格式
	
	
	//Excel数据导入
	private List readNameExcel(String path){
		List NameLists=new ArrayList();
		// 解析存储数据
		parseExcelFile pef = new parseExcelFile();
		try {
			// 获得表数据中数据，
			Integer sheetNum = 1;
			Integer startLine = 0;
			Integer endLine = null;
			Integer startColumn = 1;
			Integer endColumn = 1;
			Map map = pef.readExcel(new File(path.trim()),
					sheetNum, startLine, endLine, startColumn, endColumn);	
			if (map != null) {
				sheetNum = (sheetNum == null ? Integer.parseInt((String) map.get("sheetNum")) : sheetNum);
				startLine = (startLine == null ? Integer.parseInt((String) map.get("startLine")) : startLine);
				endLine = (endLine == null ? Integer.parseInt((String) map.get("endLine")) : endLine);
				startColumn = (startColumn == null ? Integer.parseInt((String) map.get("startColumn")) : startColumn);
				endColumn = (endColumn == null ? Integer.parseInt((String) map.get("endColumn")) : endColumn);
				// 存储数据
				
				for (int i = startLine; i < endLine; i++) {
					for(int j = startColumn-1; j < endColumn; j++){
						String columdata = "";
						if("*".equals(map.get(sheetNum + "-" + i + "-" + j))){
							columdata = "0";
						}else{
							columdata = map.get(sheetNum + "-" + i + "-" + j).trim();
						}
						NameLists.add(columdata);
					}
				}
			}
		} catch (IOException e) {
			e.printStackTrace();
			return null;
		}
		return NameLists;
	}
	

	public static void main(String[] args) {
		ComThread.InitSTA();
		List nameList=new PDFRead().readNameExcel("c://1.xlsx");
		if(nameList!=null){
			for (int k = 0; k < nameList.size(); k++) {
				// 要保存的目标文件
				String tpFile = "";
	
				// 启动word,生成一个ActivexComponent对象
				ActiveXComponent app = new ActiveXComponent("Word.Application");
				// 要转换的word文件
				String inFile = "C://1.doc";
				// 要保存的目标文件
				tpFile = "C://1/" + nameList.get(k) + ".pdf";
				File fileDir=new File("C://1");
				if(!fileDir.exists()){
					fileDir.mkdirs();
					fileDir.setWritable(true);
				}
				app.setProperty("Visible", false);
				Dispatch docs = app.getProperty("Documents").toDispatch();
				Dispatch doc = Dispatch.call(docs, //
						"Open", //
						inFile, // FileName
						false, // ConfirmConversions
						true // ReadOnly
				).toDispatch();
	
				// Dispatch activeDocument=app.getProperty("ActiveDocument").toDispatch();
				Dispatch bookMarks = app.call(doc, "Bookmarks").toDispatch();
				int bCount = Dispatch.get(bookMarks, "Count").getInt(); // 获取书签数
				// 将书签列表存放到list + map 结构中
				for (int i = 1; i <= bCount; i++) {
					// Map bookMark = new HashMap(); //创建Map()
					Dispatch items = Dispatch.call(bookMarks, "Item", i).toDispatch();
					String bookMarkKey = String.valueOf(Dispatch.get(items, "Name").getString()).replaceAll("null", ""); // 读取书签命名
					Dispatch range = Dispatch.get(items, "Range").toDispatch();
					String bookMarkValue = String.valueOf(Dispatch.get(range, "Text").getString()).replaceAll("null", ""); // 读取书签文本
					String MarkKey = bookMarkKey;
					String MarkValue = bookMarkValue;
					// 书签名并替换的内容
					if (MarkKey.equals("xm"))// 书签名为xm
					{
						MarkValue = nameList.get(k); // 该xm书签处插入张三；
					}
	
					Dispatch.put(range, "Text", new Variant(MarkValue));
					// 通过打印查看便于debug
					System.out.println(bookMarkValue);
					System.out.println(MarkValue);
					// 保存文件
					Dispatch.call(doc, //
							"SaveAs", //
							tpFile, // FileName
							wdFormatPDF);
	
				}
				try {
					Variant f = new Variant(false);
					Dispatch.call(doc, "Close", f);
				} catch (Exception e) {
					e.printStackTrace();
				} finally {
					app.invoke("Quit", new Variant[] {});
					ComThread.Release();
				}
	
			}
			System.out.println("转化完成......");
		}else{
			System.out.println("读取excel失败!");
		}

	}
}

    5、测试结果：

    

    邀请函内容就这么愉快的替换掉啦

    

 

   Ending！

 

    PS：写的第一篇博文，有什么不足之处欢迎指正！