java实现word导入导出富文本(含图片)-附完整测试用例

蔚落 2024-03-27 07:29 58阅读 0赞

### 主要有以下几点： ###

1、解决富文本导入导出依赖兼容问题  
2、处理富文本和非富文本内容  
3、解决webp格式通过java下载不了问题，如果要用到富文本导出，将来势必是会碰到的bug，这里提前给提出来并解决，测试用例中有给图片测试。  
4、在原有方法上优化，比如处理等比缩小图片、将图片本地路径，替换为minio或者base64格式

**gitee测试用例：**  
链接: [https://gitee.com/muyangrenOvo/word-import-export][https_gitee.com_muyangrenOvo_word-import-export]

**注意：与文章代码有出入，但思路是一样的。只是获取文件的方式变了，一个是前端调用组件传的，一个是自己new file。**

#### 目录 ####

*   *  主要有以下几点：
     *  1）引入pom.xml依赖
     *  2) word文档导入带样式(含图片)
     *   *  Controller层
         *  service层
         *  HtmlUtil工具类
     *  3) 富文本导出word文档(含图片)
     *   *  Controller层
         *  Service层

### 1）引入pom.xml依赖 ###

<dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi</artifactId>
        <version>4.1.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml-schemas</artifactId>
        <version>4.1.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>4.1.2</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>xdocreport</artifactId>
        <version>2.0.2</version>
    </dependency>
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-scratchpad</artifactId>
        <version>4.1.2</version>
    </dependency>
    <dependency>
    <groupId>io.github.draco1023</groupId>
    <artifactId>poi-tl-ext</artifactId>
    <version>0.4.2</version>
    </dependency>
    <dependency>
        <groupId>org.jsoup</groupId>
        <artifactId>jsoup</artifactId>
        <version>1.15.3</version>
    </dependency>
    
     <dependency>
         <groupId>com.github.nintha</groupId>
         <artifactId>webp-imageio-core</artifactId>
         <version>0.1.0</version>
         
         
         
     </dependency>

### 2) word文档导入带样式(含图片) ###

例如这是word文档，我们要通过波浪线去截取对应内容  
![在这里插入图片描述][87470cb06b4f43a0a27bc0c7b3f09f18.png]

#### Controller层 ####

@ApiLog("导入模板")
        @PostMapping("/importTemplate")
        @ApiOperation(value = "导入模板", notes = "传file")
        public R<CaseInfoVO> importCase(@RequestParam MultipartFile file) {
            return R.data(caseInfoService.importTemplate(file));
        }

#### service层 ####

import com.deepoove.poi.XWPFTemplate;
    import com.deepoove.poi.config.Configure;
    import com.deepoove.poi.config.ConfigureBuilder;
    import fr.opensagres.poi.xwpf.converter.core.FileImageExtractor;
    import fr.opensagres.poi.xwpf.converter.core.FileURIResolver;
    import fr.opensagres.poi.xwpf.converter.core.XWPFConverterException;
    import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;
    import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;
    import org.apache.poi.xwpf.usermodel.XWPFDocument;
    import org.ddr.poi.html.HtmlRenderPolicy;
    
    
    @Override
    public CaseInfoVO importTemplate(MultipartFile file){
            try {
                caseInfoVO = new CaseInfoVO();
                //1、处理非富文本内容基本信息(讲解的是富文本导入,所以该内容略过)
                //List<Map<String, String>> mapList = WordUtil.readWord(file);
                //assert mapList != null;
                //dealWithCaseBasicInfo(caseInfoVO, mapList);
                //2、下载文件到本地
                File destFile = fileDownloadToLocalPath(file);
                //3、处理案例富文本信息
                dealWithCaseInfoRichText(caseInfoVO, destFile);
                //4、替换案例富文本信息中的图片(如果有)路径并删除临时文件和临时图片
                dealWithCaseInfoRichTextToPicture(caseInfoVO);
            } catch (Exception e) {
                e.printStackTrace();
            }
            return caseInfoVO;
        }
    
        private void dealWithCaseInfoRichText(CaseInfoVO caseInfoVO, File destFile) {
            if (!destFile.exists()) {
                throw new ServiceException("导入模板失败,请重新上传！");
            } else {
                //判断是否为docx文件
                if (destFile.getName().endsWith(".docx") || destFile.getName().endsWith(".DOCX")) {
                    // 1)加载word文档生成XWPFDocument对象
                    try (FileInputStream in = new FileInputStream(destFile); XWPFDocument document = new XWPFDocument(in)) {
                        // 2)解析XHTML配置（这里设置IURIResolver来设置图片存放的目录）
                        File imageFolderFile = new File(String.valueOf(destFile.getParentFile()));
                        XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
                        options.setExtractor(new FileImageExtractor(imageFolderFile));
                        options.setIgnoreStylesIfUnused(false);
                        options.setFragment(true);
                        //使用字符数组流获取解析的内容
                        ByteArrayOutputStream baos = new ByteArrayOutputStream();
                        XHTMLConverter.getInstance().convert(document, baos, options);
                      	//带样式的内容(富文本)
                        String conTent = baos.toString();
                      	//通过波浪线分割，然后通过debug去看自己需要的内容的下标位置 然后获取即可(如果不懂，私信)
                        String[] tableSplit = conTent.split("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~</span></p>");
                        int length = tableSplit.length;
                      	//最好是判断下length预期长度，否则模板用于定位的波浪线给破坏了，拿的内容也就变了
                            caseInfoVO.setCriminalBaseInfoSituation(tableSplit[2]);
                            caseInfoVO.setCriminalEducationTransformPlan(tableSplit[4]);
                            caseInfoVO.setCriminalEducationTransformResult(tableSplit[6]);
                        } 
                    } catch (IOException | XWPFConverterException e) {
                        e.printStackTrace();
                    } finally {
                        FileUtil.deleteQuietly(destFile);
                    }
                }
            }
        }
    
      
    
        private String dealWithCaseInfoRichTextToPictureChild(String content, OssBuilder ossBuilder,Set<File> files) {
            List<String> imagesFiles = HtmlUtil.regexMatchPicture(content);
            if (Func.isNotEmpty(imagesFiles)) {
                for (String imagesFile : imagesFiles) {
                    File file = new File(imagesFile);
                    MultipartFile fileItem = createFileItem(file, file.getName());
                    boolean aBoolean = true;
                  	//此处选择循环调用，避免minio上传失败返回空(主要看需求)。
                    while (Boolean.TRUE.equals(aBoolean)) {
                        BladeFile bladeFile = ossBuilder.template().putFile(fileItem);
                        if (Func.isNotEmpty(bladeFile)) {
                            String link = bladeFile.getLink();
                            content = content.replace(imagesFile, link);
                            //删除临时图片(统一删除 如上传同一张图片，第二次会找不到图片)
                            files.add(file);
                            aBoolean = false;
                        }
                    }
                }
            }
            return content;
        }
    
    //最好是定义一个工具类，这里图看起来比较直观，就单独拿出来了
        /**
         * 下载到本地路径
         * @param file
         * @return
         * @throws IOException
         */
        public File fileDownloadToLocalPath(MultipartFile file) {
            File destFile = null;
            try {
                String fileName = file.getOriginalFilename();
                //获取文件后缀
                String pref = fileName.lastIndexOf(".") != -1 ? fileName.substring(fileName.lastIndexOf(".") + 1) : null;
                //临时文件
                //临时文件名避免重复
                String uuidFile = UUID.randomUUID().toString().replace("-", "") + "." + pref;
                destFile = new File(FileChangeUtils.getProjectPath() + uuidFile);
                if (!destFile.getParentFile().exists()) {
                    destFile.getParentFile().mkdirs();
                }
                file.transferTo(destFile);
            } catch (IOException e) {
                e.printStackTrace();
            }
            return destFile;
        }
    
    /**
         * 创建FileItem
         * @param file
         * @param fieldName
         * @return
         */
    	public MultipartFile createFileItem(File file, String fieldName) {
    		FileItemFactory factory = new DiskFileItemFactory(16, null);
    		FileItem item = factory.createItem(fieldName, ContentType.MULTIPART_FORM_DATA.toString(), true, file.getName());
    		int bytesRead = 0;
    		byte[] buffer = new byte[8192];
    		try {
    			FileInputStream fis = new FileInputStream(file);
    			OutputStream os = item.getOutputStream();
    			while ((bytesRead = fis.read(buffer, 0, 8192)) != -1) {
    				os.write(buffer, 0, bytesRead);
    			}
    			os.close();
    			fis.close();
    		} catch (IOException e) {
    			e.printStackTrace();
    		}
    		return new CommonsMultipartFile(item);
    	}

#### HtmlUtil工具类 ####

import java.math.BigDecimal;
    import java.math.RoundingMode;
    import java.util.ArrayList;
    import java.util.HashMap;
    import java.util.List;
    import java.util.regex.Matcher;
    import java.util.regex.Pattern;
    
    /**
     * @author: muyangren
     * @Date: 2022/12/14
     * @Description: 
     * @Version: 1.0
     */
    public class HtmlUtil {
    
        /**
         * 通过正则表达式去获取html中的src
         *
         * @param content
         * @return
         */
        public static List<String> regexMatchPicture(String content) {
            //用来存储获取到的图片地址
            List<String> srcList = new ArrayList<>();
            //匹配字符串中的img标签
            Pattern p = Pattern.compile("<(img|IMG)(.*?)(>|></img>|/>)");
            Matcher matcher = p.matcher(content);
            boolean hasPic = matcher.find();
            //判断是否含有图片
            if (hasPic) {
                //如果含有图片，那么持续进行查找，直到匹配不到
                while (hasPic) {
                    //获取第二个分组的内容，也就是 (.*?)匹配到的
                    String group = matcher.group(2);
                    //匹配图片的地址
                    Pattern srcText = Pattern.compile("(src|SRC)=(\"|\')(.*?)(\"|\')");
                    Matcher matcher2 = srcText.matcher(group);
                    if (matcher2.find()) {
                        //把获取到的图片地址添加到列表中
                        srcList.add(matcher2.group(3));
                    }
                    //判断是否还有img标签
                    hasPic = matcher.find();
                }
            }
            return srcList;
        }
    
        /**
         * 通过正则表达式去获取html中的src中的宽高
         *
         * @param content
         * @return
         */
        public static List<HashMap<String, String>> regexMatchWidthAndHeight(String content) {
            //用来存储获取到的图片地址
            List<HashMap<String, String>> srcList = new ArrayList<>();
            //匹配字符串中的img标签
            Pattern p = Pattern.compile("<(img|IMG)(.*?)(>|></img>|/>)");
            //匹配字符串中的style标签中的宽高
            String regexWidth = "width:(?<width>\\d+([.]\\d+)?)(px|pt)";
            String regexHeight = "height:(?<height>\\d+([.]\\d+)?)(px;|pt;)";
            Matcher matcher = p.matcher(content);
            boolean hasPic = matcher.find();
            //判断是否含有图片
            if (hasPic) {
                //如果含有图片，那么持续进行查找，直到匹配不到
                while (hasPic) {
                    HashMap<String, String> hashMap = new HashMap<>();
                    //获取第二个分组的内容，也就是 (.*?)匹配到的
                    String group = matcher.group(2);
                    hashMap.put("fileUrl", group);
                    //匹配图片的地址
                    Pattern srcText = Pattern.compile(regexWidth);
                    Matcher matcher2 = srcText.matcher(group);
                    String imgWidth = null;
                    String imgHeight = null;
                    if (matcher2.find()) {
                        imgWidth = matcher2.group("width");
                    }
                    srcText = Pattern.compile(regexHeight);
                    matcher2 = srcText.matcher(group);
                    if (matcher2.find()) {
                        imgHeight = matcher2.group("height");
                    }
                    hashMap.put("width", imgWidth);
                    hashMap.put("height", imgHeight);
                    srcList.add(hashMap);
                    //判断是否还有img标签
                    hasPic = matcher.find();
                }
                for (HashMap<String, String> imagesFile : srcList) {
                    String height = imagesFile.get("height");
                    String width = imagesFile.get("width");
                    String fileUrl = imagesFile.get("fileUrl");
                    //1厘米=25px(像素)  17厘米(650px) word最大宽值
                    if (Func.isNotEmpty(width)) {
                        BigDecimal widthDecimal = new BigDecimal(width);
                        BigDecimal maxWidthWord = new BigDecimal("650.0");
                        if (widthDecimal.compareTo(maxWidthWord) > 0) {
                            BigDecimal divide = widthDecimal.divide(maxWidthWord, 2, RoundingMode.HALF_UP);
                            fileUrl = fileUrl.replace("width:" + width, "width:" + maxWidthWord);
                            if (Func.isNotEmpty(height)) {
                                BigDecimal heightDecimal = new BigDecimal(height);
                                BigDecimal divide1 = heightDecimal.divide(divide, 1, RoundingMode.HALF_UP);
                                fileUrl = fileUrl.replace("height:" + height, "height:" + divide1);
                            } else {
                                fileUrl = fileUrl.replace("height:auto", "height:350px");
                            }
                            imagesFile.put("newFileUrl", fileUrl);
                        } else {
                            imagesFile.put("newFileUrl", "");
                        }
                    }
                }
            }
            return srcList;
        }
    }

### 3) 富文本导出word文档(含图片) ###

**参考文献**  
链接: [https://github.com/draco1023/poi-tl-ext][https_github.com_draco1023_poi-tl-ext]  
模板如图所示  
![在这里插入图片描述][50e9be832e004edea13f1e00945e6ab3.png]

#### Controller层 ####

@ApiLog("模板-下载")
        @GetMapping("/downloadTemplate")
        @ApiOperation(value = "模板-下载")
        public void downloadCaseInfo(HttpServletResponse response,CaseInfoDTO caseInfoDTO) {
            caseInfoService.downloadTemplate(response,caseInfoDTO);
        }

#### Service层 ####

@Override
        public void downloadTemplate(HttpServletResponse response, CaseInfoDTO caseInfoDTO) {
            try {
              	//查询需要导入的数据
                List<CaseInfoVO> caseInfoVOS = baseMapper.caseQueryPage(null, null, caseInfoDTO, AuthUtil.getUserId());
               
                CaseInfoVO caseInfoVO = caseInfoVOS.get(0);
                //处理作者名称
                dealWithCaseAuthorName(caseInfoVOS);
                Integer formatType = caseInfoVO.getFormatType();
                org.springframework.core.io.Resource resource;
    
                HtmlRenderPolicy htmlRenderPolicy = new HtmlRenderPolicy();
                ConfigureBuilder builder = Configure.builder();
                Configure config = builder.build();
    
                SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
                Map<String, Object> data = new HashMap(8);
                data.put("caseTitle", caseInfoVO.getCaseTitle());
                data.put("typeName", caseInfoVO.getTypeName());
                    resource = new ClassPathResource("document" + File.separator + "word" + File.separator + "导出模板.docx");
                    config.customPolicy("criminalBaseInfoSituation", htmlRenderPolicy);
                    data.put("criminalBaseInfoSituation", dealWithPictureWidthAndHeight(caseInfoVO.getCriminalBaseInfoSituation()));
              
                //输出到浏览器|下载到本地路径
                StringBuilder stringBuilder = new StringBuilder();
                stringBuilder.append(caseInfoVO.getTenantName()).append("-").append(caseInfoVO.getTypeName()).append("-《").append(caseInfoVO.getCaseTitle()).append("》").append("案例");
                response.setContentType("application/octet-stream");
                response.setHeader("Content-disposition", "attachment;filename=\"" + new String(stringBuilder.toString().getBytes(StandardCharsets.UTF_8), StandardCharsets.ISO_8859_1) + ".docx" + "\"");
                OutputStream out = response.getOutputStream();
                XWPFTemplate.compile(resource.getInputStream(), config).render(data).writeAndClose(out);
                out.flush();
                out.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    
      	//处理图片超过word宽度问题，等比缩小
        private String dealWithPictureWidthAndHeight(String content) {
            List<HashMap<String, String>> imagesFiles = HtmlUtil.regexMatchWidthAndHeight(content);
            if (Func.isNotEmpty(imagesFiles)) {
                for (HashMap<String, String> imagesFile : imagesFiles) {
                    String newFileUrl = imagesFile.get("newFileUrl");
                    String fileUrl = imagesFile.get("fileUrl");
                    if (Func.isNotEmpty(newFileUrl)){
                        content = content.replace(fileUrl, newFileUrl);
                    }
                }
            }
            return content;
        }

如果觉得文章对您有帮助，麻烦点个赞再走哈  
搬运麻烦标注出处

[https_gitee.com_muyangrenOvo_word-import-export]: https://gitee.com/muyangrenOvo/word-import-export
[87470cb06b4f43a0a27bc0c7b3f09f18.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/03/27/5c7d15d1c1644fbcbfe9a5c5ff978b64.png
[https_github.com_draco1023_poi-tl-ext]: https://github.com/draco1023/poi-tl-ext
[50e9be832e004edea13f1e00945e6ab3.png]: https://image.dandelioncloud.cn/pgy_files/images/2024/03/27/0a0ec260d84e428ea1d6be30901b3351.png