java生成docx文件、pdf文件、docx转pdf、docx转图片 pdf转图片工具

docx4j生成docx文件、pdf文件、docx转pdf、docx转图片 pdf转图片工具

最近写项目时遇到一些操作数据填充word、pdf以及word转pdf、word转图片的需求。网络搜索资料经整理如下
操作office文档、pdf一般来说有好几种实现方式

1、docx4j+apache.pdfbox

1.1 引入maven

   <!-- pdf 转图片  --><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.25</version></dependency><!--<dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>3.10.1</version></dependency>--><!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/org.apache.poi.xwpf.converter.pdf--><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>org.apache.poi.xwpf.converter.pdf</artifactId><version>1.0.4</version></dependency><!-- pdf 转图片 --><!-- docx4j 创建docx文件、pdf文档、word转pdf文档--><dependency><groupId>org.docx4j</groupId><artifactId>docx4j-JAXB-Internal</artifactId><version>8.2.4</version></dependency><dependency><groupId>org.docx4j</groupId><artifactId>docx4j-export-fo</artifactId><version>8.2.4</version></dependency><!-- docx4j 创建docx文件、pdf文档、word转pdf文档-->

1.2 工具类

package com.sl.utils.office.word;import com.sl.utils.id.IDUtils;
import org.apache.commons.collections4.MapUtils;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.docx4j.Docx4J;
import org.docx4j.TraversalUtil;
import org.docx4j.XmlUtils;
import org.docx4j.dml.wordprocessingDrawing.Inline;
import org.docx4j.finders.RangeFinder;
import org.docx4j.fonts.IdentityPlusMapper;
import org.docx4j.fonts.Mapper;
import org.docx4j.fonts.PhysicalFonts;
import org.docx4j.jaxb.Context;
import org.docx4j.openpackaging.exceptions.Docx4JException;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.openpackaging.parts.WordprocessingML.BinaryPartAbstractImage;
import org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart;
import org.docx4j.wml.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
/*** docx4j生成docx文件、pdf文件、docx转pdf、docx转图片 pdf转图片工具** 有三种方式* 1 通过占位符** <p>* 通过docx文件的书签、占位符替换变量* <p>* 通过占位符替换注意* * 通过占位符替换注意 -----------坑坑坑坑 直接再docx文件中进行修改占位符不一定会连续！！！-----------* ${var}必须是连续的，否则取不到变量。有时候取不到变量的时候可以抓换为xml然后查看你的变量是否是连续的* 可以通过如下方式解决 现在docx文件中写入占位符然后* 把当前docx文件用rar或zip打开，找到其中的 word/document.xml文件，修改占位符连续* <p>* 比如把* <w:r>* <w:t>${na</w:t>* </w:r>* <w:r>* <w:t>me}</w:t>* </w:r>* 修改为* <w:r>* <w:t>${name}</w:t>* </w:r>* 2、全部通过书签* 3、通过域变量*  通过域变量需要重写 docx4居中 XmlUtils 工具类中unmarshallFromTemplate方法 以适配域变量*  具体目录在 org.docx4j* @author gaoxueyong* @create at: 2021/12/28 下午15:02*/
public class DocxAndPdfAndImgUtils {private static final Logger log = LoggerFactory.getLogger(DocxAndPdfAndImgUtils.class);private static WordprocessingMLPackage wordMLPackage;private static ObjectFactory factory;/*** 通过docx模板获取docx模板转换的图片* @param templatePath 模板文件* @param mappings 要匹配的占位符数据* @param fileMapping 书签名称对于的文件* @return*/public static List<byte[]> getPngByDocxTemplate(String templatePath, Map<String, String> mappings, Map<String, byte[]> fileMapping) {return pdfToImg(getPdfFile(templatePath, mappings, fileMapping));}/*** 通过模板获取转换后docx的二进制数组* @param templatePath 模板文件* @param mappings 要匹配的占位符数据* @param fileMapping 书签名称对于的文件* @return*/public static byte[] getDocxByTemplate(String templatePath, Map<String, String> mappings, Map<String, byte[]> fileMapping) {File docxFile = getDocxFile(templatePath, mappings, fileMapping);try {if (null == docxFile) {return null;}byte[] bytes = Files.readAllBytes(docxFile.toPath());if (docxFile.exists()) {docxFile.delete();}return bytes;} catch (IOException e) {log.error("获取文件失败");if (docxFile.exists()) {docxFile.delete();}return null;}}/*** 通过模板获取转换后pdf文件* @param templatePath 模板文件* @param mappings 要匹配的占位符数据* @param fileMapping 书签名称对于的文件* @return*/public static byte[] getPdfFile(String templatePath, Map<String, String> mappings, Map<String, byte[]> fileMapping){try {File docxFile = getDocxFile(templatePath, mappings, fileMapping);if(null == docxFile){return null;}WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.load(docxFile);Path pdf = Files.createTempFile(IDUtils.getPrimaryId(), "pdf");File pdfFile = pdf.toFile();if(null == pdfFile){log.error("创建文件失败");return null;}Docx4J.toPDF(wordMLPackage, new FileOutputStream(pdfFile));if(docxFile.exists()){docxFile.delete();}byte[] bytes = Files.readAllBytes(pdf);if(pdfFile.exists()){pdfFile.delete();}return bytes;} catch (Docx4JException e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;} catch (Exception e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;}}/*** 通过文件输入流获取pdf文档的二进制数组* @param docxInputstream* @return*/public static byte[] getPdfByte(InputStream docxInputstream){try {if(null == docxInputstream){return null;}WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.load(docxInputstream);Path pdf = Files.createTempFile(IDUtils.getPrimaryId(), "pdf");File pdfFile = pdf.toFile();if(null == pdfFile){log.error("创建文件失败");return null;}Docx4J.toPDF(wordMLPackage, new FileOutputStream(pdfFile));byte[] bytes = Files.readAllBytes(pdf);if(pdfFile.exists()){pdfFile.delete();}return bytes;} catch (Docx4JException e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;} catch (Exception e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;}}/*** 通过模板获取转换后docx文件* @param templatePath 模板文件* @param mappings 要匹配的占位符数据* @param fileMapping 书签名称对于的文件* @return*/public static File getDocxFile(String templatePath, Map<String, String> mappings, Map<String, byte[]> fileMapping){try {wordMLPackage = WordprocessingMLPackage.load(new File(templatePath));MainDocumentPart mainDocumentPart = wordMLPackage.getMainDocumentPart();if(MapUtils.isNotEmpty(mappings)){mainDocumentPart.variableReplace(mappings);}factory = Context.getWmlObjectFactory();Document wmlDoc = (Document) mainDocumentPart.getJaxbElement();Body body = wmlDoc.getBody();// 提取正文中所有段落List<Object> paragraphs = body.getContent();// 提取书签并创建书签的游标RangeFinder rt = new RangeFinder("CTBookmark", "CTMarkupRange");new TraversalUtil(paragraphs, rt);// 遍历书签for (CTBookmark bm : rt.getStarts()) {log.info("标签名称:" + bm.getName());if(MapUtils.isEmpty(fileMapping)){break;}if (fileMapping.containsKey(bm.getName())) {addImage(wordMLPackage, bm, fileMapping.get(bm.getName()));}else {if(mappings.containsKey(bm.getName())){replaceText (bm, mappings.get(bm.getName()));}}}wordMLPackage.setFontMapper(getFontMap());Path docx = Files.createTempFile(IDUtils.getPrimaryId(), "docx");File docxFile = docx.toFile();Docx4J.save(wordMLPackage, docxFile);return docxFile;} catch (Docx4JException e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;} catch (Exception e) {log.error("bookReplaceVarText error:Docx4JException ", e);return null;}}/*** 在标签处插入内容* @param bm* @param object* @throws Exception*/public static void replaceText(CTBookmark bm, Object object) throws Exception {if (object == null) {return;}// do we have data for this one?if (bm.getName() == null){return;}String value = object.toString();try {// Can't just remove the object from the parent,// since in the parent, it may be wrapped in a JAXBElementList<Object> theList = null;ParaRPr rpr = null;if (bm.getParent() instanceof P) {PPr pprTemp = ((P) (bm.getParent())).getPPr();if (pprTemp == null) {rpr = null;} else {rpr = ((P) (bm.getParent())).getPPr().getRPr();}theList = ((ContentAccessor) (bm.getParent())).getContent();} else {return;}int rangeStart = -1;int rangeEnd = -1;int i = 0;for (Object ox : theList) {Object listEntry = XmlUtils.unwrap(ox);if (listEntry.equals(bm)) {if (((CTBookmark) listEntry).getName() != null) {rangeStart = i + 1;}} else if (listEntry instanceof CTMarkupRange) {if (((CTMarkupRange) listEntry).getId().equals(bm.getId())) {rangeEnd = i - 1;break;}}i++;}int x = i - 1;// if (rangeStart > 0 && x >= rangeStart) {// Delete the bookmark rangefor (int j = x; j >= rangeStart; j--) {theList.remove(j);}// now add a runR run = factory.createR();Text t = factory.createText();// if (rpr != null)// run.setRPr(paraRPr2RPr(rpr));t.setValue(value);run.getContent().add(t);// t.setValue(value);theList.add(rangeStart, run);// }} catch (ClassCastException cce) {log.error("error", cce);}}/*** 插入图片* @param wPackage* @param bm* @param bytes*/public static void addImage(WordprocessingMLPackage wPackage, CTBookmark bm,byte[] bytes) {//        log.info("addImage :->{},{},{}", wPackage, bm);if(null == bytes){return;}try {// 这儿可以对单个书签进行操作，也可以用一个map对所有的书签进行处理// 获取该书签的父级段落P p = (P) (bm.getParent());// R对象是匿名的复杂类型，然而我并不知道具体啥意思，估计这个要好好去看看ooxml才知道R run = factory.createR();// 读入图片并转化为字节数组，因为docx4j只能字节数组的方式插入图片
//            byte[] bytes = IOUtils.toByteArray(new FileInputStream(file));// InputStream is = new FileInputStream;// byte[] bytes = IOUtils.toByteArray(inputStream);// byte[] bytes = FileUtil.getByteFormBase64DataByImage("");// 开始创建一个行内图片BinaryPartAbstractImage imagePart = BinaryPartAbstractImage.createImagePart(wPackage, bytes);// 最后一个参数是限制图片的宽度，缩放的依据Inline inline = imagePart.createImageInline(null, null, 0, 1, false, 2350);// 获取该书签的父级段落// drawing理解为画布？Drawing drawing = factory.createDrawing();drawing.getAnchorOrInline().add(inline);run.getContent().add(drawing);p.getContent().add(run);} catch (Exception e) {log.error("", e);}}/*** 解决转换后数据显示异常的问题* @return*/private static Mapper getFontMap(){Mapper fontMapper = new IdentityPlusMapper();fontMapper.put("隶书", PhysicalFonts.get("LiSu"));fontMapper.put("宋体", PhysicalFonts.get("SimSun"));fontMapper.put("微软雅黑", PhysicalFonts.get("Microsoft Yahei"));fontMapper.put("黑体", PhysicalFonts.get("SimHei"));fontMapper.put("楷体", PhysicalFonts.get("KaiTi"));fontMapper.put("新宋体", PhysicalFonts.get("NSimSun"));fontMapper.put("华文行楷", PhysicalFonts.get("STXingkai"));fontMapper.put("华文仿宋", PhysicalFonts.get("STFangsong"));fontMapper.put("仿宋", PhysicalFonts.get("FangSong"));fontMapper.put("幼圆", PhysicalFonts.get("YouYuan"));fontMapper.put("华文宋体", PhysicalFonts.get("STSong"));fontMapper.put("华文中宋", PhysicalFonts.get("STZhongsong"));fontMapper.put("等线", PhysicalFonts.get("SimSun"));fontMapper.put("等线 Light", PhysicalFonts.get("SimSun"));fontMapper.put("华文琥珀", PhysicalFonts.get("STHupo"));fontMapper.put("华文隶书", PhysicalFonts.get("STLiti"));fontMapper.put("华文新魏", PhysicalFonts.get("STXinwei"));fontMapper.put("华文彩云", PhysicalFonts.get("STCaiyun"));fontMapper.put("方正姚体", PhysicalFonts.get("FZYaoti"));fontMapper.put("方正舒体", PhysicalFonts.get("FZShuTi"));fontMapper.put("华文细黑", PhysicalFonts.get("STXihei"));fontMapper.put("宋体扩展", PhysicalFonts.get("simsun-extB"));fontMapper.put("仿宋_GB2312", PhysicalFonts.get("FangSong_GB2312"));fontMapper.put("新細明體", PhysicalFonts.get("SimSun"));return fontMapper;}/***  pdf 转图片* @param pdfFile* @return*/public static List<byte[]> pdfToImg(byte[] pdfFile) {PDDocument doc = null;List<byte[]> outFile = new ArrayList<>();try {doc = PDDocument.load(pdfFile);PDFRenderer render = new PDFRenderer(doc);int count = doc.getNumberOfPages();for (int i = 0; i < count; i++) {// 设置图片的分辨率BufferedImage image = render.renderImageWithDPI(i, 296);// 如果是PNG图片想要背景透明的话使用下面这个// BufferedImage image = render.renderImageWithDPI(i, 296,// ImageType.ARGB);Path png = Files.createTempFile(IDUtils.getPrimaryId() + "_" + i, "png");File pngFile = png.toFile();ImageIO.write(image, "PNG", pngFile);outFile.add(Files.readAllBytes(png));pngFile.delete();}} catch (IOException e) {log.error("pdf转换图片失败！");} finally {if (doc != null) {try {doc.close();} catch (IOException e) {log.error("关闭PDDocument失败");}}return outFile;}}
}

1.2.1 重写 XmlUtils以适配域变量

重写 XmlUtils 工具类中unmarshallFromTemplate方法以适配域变量

1.3 关于模板

1.3.1 新建一个docx文档如并添加占位符 (不推荐可以全部都是用标签或域变量)

头像出需要添加书签，书签用以替换图片

1.3.2 修改占位符使其连续

用zip或rar工具打开docx文档并找到word/document.xml文件进行编辑

偷偷的告诉你，其实docx文档也是压缩包，可以修改其后缀直接变成zip文件

打开document.xml文档如下发现刚才的占位符是不连续的，我们要修改使其连续

使用编辑器修改后如下，然后把该文件写会到word问里，或者通过zip工具放进去

现在就可以直接调用工具方法替换数据以及图片了

1.3.2 使用域变量+书签（图片需要使用书签）

注意使用域变量需要重写 docx4居中 XmlUtils 工具类中unmarshallFromTemplate方法以适配域变量

2、xdocreport

2.1 引入maven

        <!-- xdocreport 生成word、pdf --><!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/fr.opensagres.xdocreport.document.docx --><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>fr.opensagres.xdocreport.document.docx</artifactId><version>2.0.2</version></dependency><!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/fr.opensagres.xdocreport.template.freemarker --><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>fr.opensagres.xdocreport.template.freemarker</artifactId><version>2.0.2</version></dependency><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>fr.opensagres.xdocreport.converter.docx.xwpf</artifactId><version>2.0.2</version></dependency><!-- xdocreport 生成word、pdf --><!-- pdf转图片 --><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.25</version></dependency><!-- https://mvnrepository.com/artifact/fr.opensagres.xdocreport/fr.opensagres.poi.xwpf.converter.pdf --><dependency><groupId>fr.opensagres.xdocreport</groupId><artifactId>fr.opensagres.poi.xwpf.converter.pdf</artifactId><version>2.0.2</version></dependency><!-- pdf转图片 --><dependency><groupId>org.projectlombok</groupId><artifactId>lombok</artifactId></dependency>

2.2 模板

注意如果要动态替换图片需要先在模板里插入一张图片，否则无法替换图片

选中头像后的图片

2.3 逻辑代码

      public static void main(String[] args) {Map<String, Object> param = new HashMap<>();param.put("user.username", "小明不怕不怕啦");param.put("user.hobby", "爱玩dota");param.put("name", "sssssssssssssssssssssss");String rootPath = XdocreportUtils.class.getClassLoader().getResource("").getPath();String filePath = String.format("%stemplates/xdocreport/xdocxtemplate.docx", rootPath);Map<String, IImageProvider> imgMap = new HashMap<>();IImageProvider logo = new FileImageProvider(new File("C:\\Users\\Administrator\\Desktop\\2021122211591833953227008.png"), true);logo.setSize(500f, 500f);imgMap.put("logo", logo);IImageProvider pic = new FileImageProvider(new File("C:\\Users\\Administrator\\Desktop\\suoluePic.PNG"), true);pic.setSize(200f, 200f);imgMap.put("pic", pic);exportDocx(param, imgMap, new File(filePath), "C:\\Users\\Administrator\\Desktop\\DocxProjectWithFreemarker_Out.docx");exportPdf(param, imgMap, new File(filePath), "C:\\Users\\Administrator\\Desktop\\DocxProjectWithFreemarker_Out.pdf");}public static void exportDocx(Map<String, Object> param, Map<String, IImageProvider> imgMap, File templateFIle, String outPath) {try {InputStream in = new FileInputStream(templateFIle);//载入模板IXDocReport report = XDocReportRegistry.getRegistry().loadReport(in, TemplateEngineKind.Freemarker);IContext context = report.createContext();//设置要替换的值if (MapUtils.isNotEmpty(param)) {for (Map.Entry<String, Object> entry : param.entrySet()) {context.put(entry.getKey(), entry.getValue());}}FieldsMetadata metadata = report.createFieldsMetadata();report.setFieldsMetadata(metadata);//替换图片if (MapUtils.isNotEmpty(imgMap)) {for (Map.Entry<String, IImageProvider> entry : imgMap.entrySet()) {context.put(entry.getKey(), entry.getValue());metadata.addFieldAsImage(entry.getKey());}}report.setFieldsMetadata(metadata);OutputStream out = new FileOutputStream(new File(outPath));report.process(context, out);out.close();} catch (IOException e) {log.error("导出docx文件出现异常！", e);} catch (XDocReportException e) {log.error("导出docx文件出现异常！", e);}}public static void exportPdf(Map<String, Object> param, Map<String, IImageProvider> imgMap, File templateFIle, String outPath) {try {InputStream in = new FileInputStream(templateFIle);//载入模板IXDocReport report = XDocReportRegistry.getRegistry().loadReport(in, TemplateEngineKind.Freemarker);IContext context = report.createContext();//设置要替换的值if (MapUtils.isNotEmpty(param)) {for (Map.Entry<String, Object> entry : param.entrySet()) {context.put(entry.getKey(), entry.getValue());}}FieldsMetadata metadata = report.createFieldsMetadata();report.setFieldsMetadata(metadata);//替换图片if (MapUtils.isNotEmpty(imgMap)) {for (Map.Entry<String, IImageProvider> entry : imgMap.entrySet()) {context.put(entry.getKey(), entry.getValue());metadata.addFieldAsImage(entry.getKey());}}report.setFieldsMetadata(metadata);OutputStream out = new FileOutputStream(new File(outPath));Options options = Options.getTo(ConverterTypeTo.PDF).via(ConverterTypeVia.XWPF);report.convert(context, options, out);out.close();} catch (IOException e) {log.error("导出pdf文件出现异常！", e);} catch (XDocReportException e) {log.error("导出pdf文件出现异常！", e);}}

2.4 效果

3、冰蓝科技的Spire

3.1 引入maven配置

      <dependency><groupId>e-iceblue</groupId><artifactId>spire.doc.free</artifactId><version>3.9.0</version></dependency><repositories><repository><id>com.e-iceblue</id><url>https://repo.e-iceblue.cn/repository/maven-public/</url></repository></repositories>

3.2 逻辑代码

import com.spire.doc.Document;
import com.spire.doc.FileFormat;
import com.spire.doc.documents.BookmarksNavigator;
import com.spire.doc.documents.Paragraph;
import com.spire.doc.documents.TextBodyPart;
import com.spire.doc.fields.DocPicture;import java.io.IOException;
import java.util.HashMap;
import java.util.Map;public class SpireWordPicTest {public static void main(String[] args) throws IOException {//加载Word文档Document doc = new Document("C:\\Users\\Administrator\\Desktop\\testDocTemplates.docx");Map<String,String> mappings  = new HashMap<>();mappings.put("username","小明");mappings.put("password","123456");/*** https://www.cnblogs.com/Yesi/p/11422349.html* 需要先在模板里设置书签 然后替换**/for(Map.Entry<String,String > entry:mappings.entrySet()){doc.replace(String.format("${%s}",entry.getKey()),entry.getValue(), false, true);}//定位到指定书签位置 设置二维码BookmarksNavigator bookmarksNavigator = new BookmarksNavigator(doc);bookmarksNavigator.moveToBookmark("headerPng", true, true);Paragraph para=  new Paragraph(doc);DocPicture docPicture = para.appendPicture("C:\\Users\\Administrator\\Desktop\\企业微信截图_20211228152622.png");//设置图片宽度docPicture.setWidth(110);//设置图片高度docPicture.setHeight(110);TextBodyPart bodyPart = new TextBodyPart(doc);bodyPart.getBodyItems().add(para);bookmarksNavigator.replaceBookmarkContent(bodyPart);//保存文档doc.saveToFile("C:\\Users\\Administrator\\Desktop\\ReplaceAllMatchedText.docx", FileFormat.Docx_2013);}

冰蓝科技的免费版代码执行效率很低，不知道正式版怎么样
https://www.e-iceblue.cn/spiredocforjava/spire-doc-for-java-program-guide-content.html
样例代码可参考 https://gitee.com/wahnn/SpringBootAll/tree/master/SpringBoot-xdocreportAndDocx4j