POI操作word和PDF

POI根据模板导出word文件

一、制作word模版，${xxxx}是一会要替换的内容，最下面的表格是要插入数据，根据是否以$开头来判断是需要替换还是插入数据。

注意如果是需要插入数据，制作的表格模版需要一行空行，也只能有一行空行，原因可以看代码的逻辑，表格中${header}和${hearder2}是放入需要替换的图片

二、添加poi所需要的jar包文件，我用的maven对jar包进行管理

<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>3.11</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>3.11</version></dependency>

三、由于poi自身bug,会出现图片无法显示问题，这里需要自定义一个类继承XWPFDocument类，接下来使用的都是我们自己创建的这个类来操作word对象，这个类对XWPFDocument进行了继承，所以不用担心会有什么问题

import java.io.InputStream;import org.apache.poi.openxml4j.opc.OPCPackage;import org.apache.poi.xwpf.usermodel.XWPFDocument;import org.apache.poi.xwpf.usermodel.XWPFParagraph;import org.apache.xmlbeans.XmlException;import org.apache.xmlbeans.XmlToken;import org.openxmlformats.schemas.drawingml.x.main.CTNonVisualDrawingProps;import org.openxmlformats.schemas.drawingml.x.main.CTPositiveSize2D;import org.openxmlformats.schemas.drawingml.x.wordprocessingDrawing.CTInline;public class CustomXWPFDocument extends XWPFDocument {public CustomXWPFDocument(InputStream in) throws java.io.IOException {super(in);}public CustomXWPFDocument() {super();}public CustomXWPFDocument(OPCPackage pkg)throws java.io.IOException {super(pkg);}/*** @param id* @param width 宽* @param height 高* @param paragraph 段落*/public void createPicture(int id, int width, int height,XWPFParagraph paragraph) {final int EMU = 9525;width *= EMU;height *= EMU;String blipId = getAllPictures().get(id).getPackageRelationship().getId();CTInline inline = paragraph.createRun().getCTR().addNewDrawing().addNewInline();String picXml = ""+"<a:graphic xmlns:a=\"/drawingml//main\">"+" <a:graphicData uri=\"/drawingml//picture\">"+"<pic:pic xmlns:pic=\"/drawingml//picture\">"+" <pic:nvPicPr>" + " <pic:cNvPr id=\""+ id+"\" name=\"Generated\"/>"+" <pic:cNvPicPr/>"+" </pic:nvPicPr>"+" <pic:blipFill>"+" <a:blip r:embed=\""+ blipId+"\" xmlns:r=\"/officeDocument//relationships\"/>"+" <a:stretch>"+"<a:fillRect/>"+" </a:stretch>"+" </pic:blipFill>"+" <pic:spPr>"+" <a:xfrm>"+"<a:off x=\"0\" y=\"0\"/>"+"<a:ext cx=\""+ width+"\" cy=\""+ height+"\"/>"+" </a:xfrm>"+" <a:prstGeom prst=\"rect\">"+"<a:avLst/>"+" </a:prstGeom>"+" </pic:spPr>"+"</pic:pic>"+" </a:graphicData>" + "</a:graphic>";inline.addNewGraphic().addNewGraphicData();XmlToken xmlToken = null;try{xmlToken = XmlToken.Factory.parse(picXml);}catch(XmlException xe) {xe.printStackTrace();}inline.set(xmlToken);inline.setDistT(0);inline.setDistB(0);inline.setDistL(0);inline.setDistR(0);CTPositiveSize2D extent = inline.addNewExtent();extent.setCx(width);extent.setCy(height);CTNonVisualDrawingProps docPr = inline.addNewDocPr();docPr.setId(id);docPr.setName("图片"+ id);docPr.setDescr("测试");}}

四、接下来就是导出word的工具类了

import java.io.*;import java.util.Iterator;import java.util.List;import java.util.Map;import java.util.regex.Matcher;import java.util.regex.Pattern;import javax.servlet.http.HttpServletResponse;import org.apache.poi.xwpf.usermodel.*;import org.ponent;/******************************************** 通过word模板生成新的word工具类** @Author Administrator* @Date /03/10* @Version V1.0*******************************************/@Componentpublic class WordUtil {/*** 根据模板生成word** @param path* 模板的路径* @param params* 需要替换的参数* @param tableList* 需要插入的参数,里面的list为每个表的数据* @param fileName* 生成word文件的文件名* @return 生成的word的路径*/public String getWord(String path, Map<String, Object> params, List<List<String[]>> tableList, String fileName,String outFileName) throws Exception {File file = new File(path);InputStream is = new FileInputStream(file);CustomXWPFDocument doc = new CustomXWPFDocument(is);this.replaceInPara(doc, params); // 替换文本里面的变量this.replaceInTable(doc, params, tableList); // 替换表格里面的变量// OutputStream os = response.getOutputStream();// response.setContentType("application/x-download");// response.setHeader("Content-disposition", "attachment; filename=" + fileName);// doc.write(os);File newFile = new File(outFileName);OutputStream os = new FileOutputStream(newFile);doc.write(os);this.close(os);this.close(is);return outFileName;}/*** 替换段落里面的变量** @param doc* 要替换的文档* @param params* 参数*/private void replaceInPara(CustomXWPFDocument doc, Map<String, Object> params) {Iterator<XWPFParagraph> iterator = doc.getParagraphsIterator();XWPFParagraph para;while (iterator.hasNext()) {para = iterator.next();this.replaceInPara(para, params, doc);}}/*** 替换段落里面的变量** @param para* 要替换的段落* @param params* 参数*/private void replaceInPara(XWPFParagraph para, Map<String, Object> params, CustomXWPFDocument doc) {List<XWPFRun> runs;Matcher matcher;if (this.matcher(para.getParagraphText()).find()) {runs = para.getRuns();int start = -1;int end = -1;String str = "";for (int i = 0; i < runs.size(); i++) {XWPFRun run = runs.get(i);String runText = run.toString();if ('$' == runText.charAt(0) && '{' == runText.charAt(1)) {start = i;}if ((start != -1)) {str += runText;}if ('}' == runText.charAt(runText.length() - 1)) {if (start != -1) {end = i;break;}}}for (int i = start; i <= end; i++) {para.removeRun(i);i--;end--;}if (params != null) {for (Map.Entry<String, Object> entry : params.entrySet()) {String key = entry.getKey();if (str.indexOf(key) != -1) {Object value = entry.getValue();if (value instanceof String) {str = str.replace(key, value.toString());para.createRun().setText(str, 0);break;} else if (value instanceof Map) {str = str.replace(key, "");Map pic = (Map) value;int width = Integer.parseInt(pic.get("width").toString());int height = Integer.parseInt(pic.get("height").toString());int picType = getPictureType(pic.get("type").toString());byte[] byteArray = (byte[]) pic.get("content");ByteArrayInputStream byteInputStream = new ByteArrayInputStream(byteArray);try {// int ind =// doc.addPicture(byteInputStream,picType);// doc.createPicture(ind, width , height,para);doc.addPictureData(byteInputStream, picType);doc.createPicture(doc.getAllPictures().size() - 1, width, height, para);para.createRun().setText(str, 0);break;} catch (Exception e) {e.printStackTrace();}}}}}}}/*** 为表格插入数据，行数不够添加新行** @param table* 需要插入数据的表格* @param tableList* 插入数据集合*/private static void insertTable(XWPFTable table, List<String[]> tableList) {// 创建行,根据需要插入的数据添加新行，不处理表头for (int i = 0; i < tableList.size(); i++) {XWPFTableRow row = table.createRow();}// 遍历表格插入数据List<XWPFTableRow> rows = table.getRows();int length = table.getRows().size();//i为表格标题行数for (int i = 2; i < length - 1; i++) {XWPFTableRow newRow = table.getRow(i);newRow.setHeight(600); //设置表格行高List<XWPFTableCell> cells = newRow.getTableCells();for (int j = 0; j < cells.size(); j++) {XWPFTableCell cell = cells.get(j);cell.getParagraphs().get(0).setAlignment(ParagraphAlignment.CENTER); //设置单元格居中显示String s = tableList.get(i - 2)[j]; //i减去的数字也为表格行数cell.setText(s);}}}/*** 替换表格里面的变量** @param doc* 要替换的文档* @param params* 参数*/private void replaceInTable(CustomXWPFDocument doc, Map<String, Object> params, List<List<String[]>> tableList) {Iterator<XWPFTable> iterator = doc.getTablesIterator();XWPFTable table;List<XWPFTableRow> rows;List<XWPFTableCell> cells;List<XWPFParagraph> paras;int i = 0;while (iterator.hasNext()) {table = iterator.next();if (table.getRows().size() > 1) {// 判断表格是需要替换还是需要插入，判断逻辑有$为替换，表格无$为插入if (this.matcher(table.getText()).find()) {rows = table.getRows();for (XWPFTableRow row : rows) {cells = row.getTableCells();for (XWPFTableCell cell : cells) {paras = cell.getParagraphs();for (XWPFParagraph para : paras) {this.replaceInPara(para, params, doc);}}}} else {if (tableList != null) {insertTable(table, tableList.get(i)); // 插入数据i++;}}}}}/*** 正则匹配字符串** @param str* @return*/private Matcher matcher(String str) {Pattern pattern = pile("\\$\\{(.+?)\\}", Pattern.CASE_INSENSITIVE);Matcher matcher = pattern.matcher(str);return matcher;}/*** 根据图片类型，取得对应的图片类型代码** @param picType* @return int*/private static int getPictureType(String picType) {int res = CustomXWPFDocument.PICTURE_TYPE_PICT;if (picType != null) {if (picType.equalsIgnoreCase("png")) {res = CustomXWPFDocument.PICTURE_TYPE_PNG;} else if (picType.equalsIgnoreCase("dib")) {res = CustomXWPFDocument.PICTURE_TYPE_DIB;} else if (picType.equalsIgnoreCase("emf")) {res = CustomXWPFDocument.PICTURE_TYPE_EMF;} else if (picType.equalsIgnoreCase("jpg") || picType.equalsIgnoreCase("jpeg")) {res = CustomXWPFDocument.PICTURE_TYPE_JPEG;} else if (picType.equalsIgnoreCase("wmf")) {res = CustomXWPFDocument.PICTURE_TYPE_WMF;}}return res;}/*** 将输入流中的数据写入字节数组** @param in* @return*/public static byte[] inputStream2ByteArray(InputStream in, boolean isClose) {byte[] byteArray = null;try {int total = in.available();byteArray = new byte[total];in.read(byteArray);} catch (IOException e) {e.printStackTrace();} finally {if (isClose) {try {in.close();} catch (Exception e2) {e2.getStackTrace();}}}return byteArray;}/*** 关闭输入流** @param is*/private void close(InputStream is) {if (is != null) {try {is.close();} catch (IOException e) {e.printStackTrace();}}}/*** 关闭输出流** @param os*/private void close(OutputStream os) {if (os != null) {try {os.close();} catch (IOException e) {e.printStackTrace();}}}}

五、最后就是进行测试了，我是用的是ssm框架，这里放出测试代码

@RequestMapping("exportWordData")public void exportWordData(HttpServletRequest request,HttpServletResponse response){WordUtils wordUtil=new WordUtils();Map<String, Object> params = new HashMap<String, Object>();params.put("${position}", "java开发");params.put("${name}", "段然涛");params.put("${sex}", "男");params.put("${national}", "汉族");params.put("${birthday}", "生日");params.put("${address}", "许昌");params.put("${height}", "165cm");params.put("${biYeDate}", "1994-02-03");params.put("${landscape}", "团员");params.put("${zhuanYe}", "社会工作");params.put("${xueLi}", "本科");params.put("${school}", "江西科技师范大学");params.put("${phone}", "177");params.put("${eMail}", "157");try{Map<String,Object> header = new HashMap<String, Object>();header.put("width", 100);header.put("height", 150);header.put("type", "jpg");header.put("content", WordUtils.inputStream2ByteArray(new FileInputStream("C:/Users/Administrator/Desktop/jar包/11.jpg"), true));params.put("${header}",header);Map<String,Object> header2 = new HashMap<String, Object>();header2.put("width", 100);header2.put("height", 150);header2.put("type", "jpg");header2.put("content", WordUtils.inputStream2ByteArray(new FileInputStream("C:/Users/Administrator/Desktop/jar包/22.jpg"), true));params.put("${header2}",header2);List<List<String[]>> list = new ArrayList<List<String[]>>();List<String[]> testList = new ArrayList<String[]>();//一个需要插入的表是一个集合testList.add(new String[]{"1","1AA","1BB","1CC"});testList.add(new String[]{"2","2AA","2BB","2CC"});testList.add(new String[]{"3","3AA","3BB","3CC"});testList.add(new String[]{"4","4AA","4BB","4CC"});list.add(testList);String path="C:/Users/Administrator/Desktop/jar包/mobanFile.docx"; //模板文件位置String fileName= new String("测试文档.docx".getBytes("UTF-8"),"iso-8859-1"); //生成word文件的文件名wordUtil.getWord(path,params,list,fileName,newFilePath);}catch(Exception e){e.printStackTrace();}}

原文链接：/duanrantao/p/8682897.html

word转PDF

WORD转PDF所需jar包：

/ice1jlc

PDF转图片所需jar包：

/ice169c

word转pdf使用的是ASPOSE.word，它的licence需要收费，百度有的文章中有，大家可以自行百度，这里就不放了。调用时传入word的路径和生成后的pdf的路径就行。

注意：在linux下不可以直接FileOutputSteram(path)生成文件，所以需要先new File(path)，如果生成之后的文件中文乱码，可能是服务器没有字库，安装一个就可以了

package com.biolims.report.service;import java.io.FileOutputStream;import java.io.InputStream;import com.aspose.words.Document;import com.aspose.words.License;import com.aspose.words.SaveFormat;/*** * 由于ASPOSE比较吃内存，操作大一点的文件就会堆溢出，所以请先设置好java虚拟机参数：-Xms512m -Xmx512m(参考值)<br>* 如有疑问，请在CSDN下载界面留言,或者联系QQ569925980<br>* * @author Spark**/public class Test {/*** 获取license* * @return*/public static boolean getLicense() {boolean result = false;try {InputStream is = Test.class.getClassLoader().getResourceAsStream("\\license.xml");License aposeLic = new License();aposeLic.setLicense(is);result = true;} catch (Exception e) {e.printStackTrace();}return result;}public static void savedocx(String inPath, String outPath) {if (!getLicense()) {return;}try {long old = System.currentTimeMillis();Document doc = new Document(inPath);// 原始word路径File file = new File(outPath);FileOutputStream fileOS = new FileOutputStream(file );doc.save(fileOS, SaveFormat.PDF);long now = System.currentTimeMillis();System.out.println("共耗时：" + ((now - old) / 1000.0) + "秒");} catch (Exception e) {e.printStackTrace();}}/*** 支持DOC, DOCX, OOXML, RTF, HTML, OpenDocument, PDF, EPUB, XPS, SWF等相互转换<br>* * @param args*/public static void main(String[] args) {// 验证Licenseif (!getLicense()) {return;}try {long old = System.currentTimeMillis();Document doc = new Document("D:\\home\\lims\\报告管理需求 - 0905.docx");// 原始word路径String pdfFile = "D:\\home\\ff.pdf";FileOutputStream fileOS = new FileOutputStream(pdfFile);doc.save(fileOS, SaveFormat.PDF);long now = System.currentTimeMillis();System.out.println("共耗时：" + ((now - old) / 1000.0) + "秒");} catch (Exception e) {e.printStackTrace();}}}

PDF转图片再插入PDF中（防止PDF被修改）

公司大佬说这种防止修改的方法在pdf有多页时可能会出问题，也没测试过，试过的朋友帮忙评论一下

public static String pdf2Image(String PdfFilePath) throws Exception {File file = new File(PdfFilePath);PdfDocument template_writer_pdfdoc = new PdfDocument(new PdfReader(PdfFilePath));Rectangle size=template_writer_pdfdoc.getFirstPage().getPageSize();int pages = template_writer_pdfdoc.getNumberOfPages();PDDocument pdDocument;String pdfPath="";try {String imgPDFPath = file.getParent();int dot = file.getName().lastIndexOf('.');String imagePDFName = file.getName().substring(0, dot); // 获取图片文件名pdDocument = PDDocument.load(file);PDFRenderer renderer = new PDFRenderer(pdDocument);/* dpi越大转换后越清晰，相对转换速度越慢 */StringBuffer imgFilePath = null;List<String> pathList=new ArrayList<String>();for (int i = 0; i < pages; i++) {String imgFilePathPrefix = imgPDFPath + File.separator + imagePDFName;imgFilePath = new StringBuffer();imgFilePath.append(imgFilePathPrefix);imgFilePath.append("_");imgFilePath.append(String.valueOf(i + 1));imgFilePath.append(".jpg");File dstFile = new File(imgFilePath.toString());BufferedImage image = renderer.renderImageWithDPI(i, 300);ImageIO.write(image, "jpg", dstFile);pathList.add(imgFilePath.toString());}template_writer_pdfdoc.close();File file2 = new File(imgPDFPath + File.separator + file.getName());// 第一步：创建一个document对象。com.itextpdf.text.Document document = new com.itextpdf.text.Document();document.setMargins(0, 0, 0, 0);// 第二步：// 创建一个PdfWriter实例，com.itextpdf.text.pdf.PdfWriter.getInstance(document, new FileOutputStream(file2));// 第三步：打开文档。document.open();for(String s:pathList) {com.itextpdf.text.Image img = com.itextpdf.text.Image.getInstance(s);img.setAlignment(com.itextpdf.text.Image.ALIGN_CENTER);img.scaleAbsoluteHeight(size.getHeight());img.scaleAbsoluteWidth(size.getWidth());// 根据图片大小设置页面，一定要先设置页面，再newPage（），否则无效document.setPageSize(new com.itextpdf.text.Rectangle(size.getWidth(), size.getHeight()));document.newPage();document.add(img);}document.close();pdfPath=imgPDFPath + File.separator + file.getName();} catch (IOException e) {e.printStackTrace();}finally {}return pdfPath;}