SpringBoot word文档转pdf
雨夜归人93 人气:10一.背景
项目中有个需求大体意思是，上传一个word模板，根据word模板合成word文件，再将word文件转为pdf。
二.方案选择
1.Spire.Doc for Java方案
Spire.Doc for Java这个是商用收费的，不过API文档丰富且集成简单，免费版仅支持3页转换。类似的还有ITEXT，这个商用也是受限制的。
2.docx4j方案
开源可商用，仅支持docx格式的word。
3.jodconverter+LibreOffice 方案
开源可商用，调用本地office服务，进行pdf转换，类似的还有jodconverter+openOffice。
4.其他
至于其他的由于不支持跨平台不做考虑。
三.实操
1.docx4j
首先尝试了docx4j，因为docx4j本身支持模板替换的操作，可一次性做替换及文档类型转换，而且仅支持docx类型，对于本次需求问题不大。
1.依赖仅需要一个即可
<dependency> <groupId>org.docx4j</groupId> <artifactId>docx4j-export-fo</artifactId> <version>6.1.0</version> </dependency>
2.主要代码
@Slf4j
public class PdfUtil {
public static <T> void exportByLocalPath(HttpServletResponse response, String fileName, String path, Map<String,String> params){
try (InputStream in = PdfUtil.class.getClassLoader().getResourceAsStream(path)) {
convertDocxToPdf(in, response,fileName,params);
} catch (Exception e) {
log.error("docx文档转换为PDF失败", e.getMessage());
}
}
/**
* docx文档转换为PDF
* @param in
* @param response
* @return
*/
public static void convertDocxToPdf(InputStream in, HttpServletResponse response, String fileName, Map<String,String> params) throws Exception {
response.setContentType("application/pdf");
String fullFileName = new String(fileName.getBytes(), StandardCharsets.ISO_8859_1);
response.setHeader("Content-disposition", "attachment;filename=" + fullFileName + ".pdf");
WordprocessingMLPackage wmlPackage = WordprocessingMLPackage.load(in);
if (params!=null&&!params.isEmpty()) {
MainDocumentPart documentPart = wmlPackage.getMainDocumentPart();
cleanDocumentPart(documentPart);
documentPart.variableReplace(params);
}
setFontMapper(wmlPackage);
Docx4J.toPDF(wmlPackage,response.getOutputStream());
}
/**
* 清除文档空白占位符
* @param documentPart
* @return {@link boolean}
*/
public static boolean cleanDocumentPart(MainDocumentPart documentPart) throws Exception {
if (documentPart == null) {
return false;
}
Document document = documentPart.getContents();
String wmlTemplate =
XmlUtils.marshaltoString(document, true, false, Context.jc);
document = (Document) XmlUtils.unwrap(DocxVariableClearUtil.doCleanDocumentPart(wmlTemplate, Context.jc));
documentPart.setContents(document);
return true;
}
/**
* 设置字体样式
* @param mlPackage
*/
private static void setFontMapper(WordprocessingMLPackage mlPackage) throws Exception {
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("宋体扩展", PhysicalFonts.get("simsun-extB"));
fontMapper.put("仿宋", PhysicalFonts.get("FangSong"));
fontMapper.put("仿宋_GB2312", PhysicalFonts.get("FangSong_GB2312"));
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"));
mlPackage.setFontMapper(fontMapper);
}
}
清除工具类，用于处理占位符替换不生效的问题，这里参考文章
public class DocxVariableClearUtil {
/**
* 去任意XML标签
*/
private static final Pattern XML_PATTERN = Pattern.compile("<[^>]*>");
private DocxVariableClearUtil() {
}
/**
* start符号
*/
private static final char PREFIX = '$';
/**
* 中包含
*/
private static final char LEFT_BRACE = '{';
/**
* 结尾
*/
private static final char RIGHT_BRACE = '}';
/**
* 未开始
*/
private static final int NONE_START = -1;
/**
* 未开始
*/
private static final int NONE_START_INDEX = -1;
/**
* 开始
*/
private static final int PREFIX_STATUS = 1;
/**
* 左括号
*/
private static final int LEFT_BRACE_STATUS = 2;
/**
* 右括号
*/
private static final int RIGHT_BRACE_STATUS = 3;
/**
* doCleanDocumentPart
*
* @param wmlTemplate
* @param jc
* @return
* @throws JAXBException
*/
public static Object doCleanDocumentPart(String wmlTemplate, JAXBContext jc) throws JAXBException {
// 进入变量块位置
int curStatus = NONE_START;
// 开始位置
int keyStartIndex = NONE_START_INDEX;
// 当前位置
int curIndex = 0;
char[] textCharacters = wmlTemplate.toCharArray();
StringBuilder documentBuilder = new StringBuilder(textCharacters.length);
documentBuilder.append(textCharacters);
// 新文档
StringBuilder newDocumentBuilder = new StringBuilder(textCharacters.length);
// 最后一次写位置
int lastWriteIndex = 0;
for (char c : textCharacters) {
switch (c) {
case PREFIX:
// 不管其何状态直接修改指针,这也意味着变量名称里面不能有PREFIX
keyStartIndex = curIndex;
curStatus = PREFIX_STATUS;
break;
case LEFT_BRACE:
if (curStatus == PREFIX_STATUS) {
curStatus = LEFT_BRACE_STATUS;
}
break;
case RIGHT_BRACE:
if (curStatus == LEFT_BRACE_STATUS) {
// 接上之前的字符
newDocumentBuilder.append(documentBuilder.substring(lastWriteIndex, keyStartIndex));
// 结束位置
int keyEndIndex = curIndex + 1;
// 替换
String rawKey = documentBuilder.substring(keyStartIndex, keyEndIndex);
// 干掉多余标签
String mappingKey = XML_PATTERN.matcher(rawKey).replaceAll("");
if (!mappingKey.equals(rawKey)) {
char[] rawKeyChars = rawKey.toCharArray();
// 保留原格式
StringBuilder rawStringBuilder = new StringBuilder(rawKey.length());
// 去掉变量引用字符
for (char rawChar : rawKeyChars) {
if (rawChar == PREFIX || rawChar == LEFT_BRACE || rawChar == RIGHT_BRACE) {
continue;
}
rawStringBuilder.append(rawChar);
}
// 要求变量连在一起
String variable = mappingKey.substring(2, mappingKey.length() - 1);
int variableStart = rawStringBuilder.indexOf(variable);
if (variableStart > 0) {
rawStringBuilder = rawStringBuilder.replace(variableStart, variableStart + variable.length(), mappingKey);
}
newDocumentBuilder.append(rawStringBuilder.toString());
} else {
newDocumentBuilder.append(mappingKey);
}
lastWriteIndex = keyEndIndex;
curStatus = NONE_START;
keyStartIndex = NONE_START_INDEX;
}
default:
break;
}
curIndex++;
}
// 余部
if (lastWriteIndex < documentBuilder.length()) {
newDocumentBuilder.append(documentBuilder.substring(lastWriteIndex));
}
return XmlUtils.unmarshalString(newDocumentBuilder.toString(), jc);
}
}
2.poi-tl+jodconverter+LibreOffice 方案
poi-tl这个是专门用来进行word模板合成的开源库，文档很详细。
LibreOffice 下载最新的稳定版本即可。
1.maven依赖
<!-- word合成 --> <!-- 这里注意版本,1.5版本依赖的poi 3.x的版本 --> <dependency> <groupId>com.deepoove</groupId> <artifactId>poi-tl</artifactId> <version>1.5.1</version> </dependency> <!-- jodconverter word转pdf --> <!-- jodconverter-core这个依赖，理论上不用加的，jodconverter-local已经依赖了，但测试的时候不添加依赖找不到 --> <dependency> <groupId>org.jodconverter</groupId> <artifactId>jodconverter-core</artifactId> <version>4.2.0</version> </dependency> <dependency> <groupId>org.jodconverter</groupId> <artifactId>jodconverter-local</artifactId> <version>4.2.0</version> </dependency> <dependency> <groupId>org.jodconverter</groupId> <artifactId>jodconverter-spring-boot-starter</artifactId> <version>4.2.0</version> </dependency> <!-- 工具类,非必须 --> <dependency> <groupId>cn.hutool</groupId> <artifactId>hutool-all</artifactId> <version>5.4.3</version> </dependency>
2.主要代码
JodConverterConfig配置类
@Configuration
public class JodConverterConfig {
@Autowired
private OfficeManager officeManager;
@Bean
public DocumentConverter documentConverter() {
return LocalConverter.builder()
.officeManager(officeManager)
.build();
}
}
yml配置文件
jodconverter:
local:
enabled: true
office-home: "C:\\Program Files\\LibreOffice"
PdfService合成导出代码
@Slf4j
@Component
public class PdfService {
@Autowired
private DocumentConverter documentConverter;
public void docxToPDF(InputStream inputStream,HttpServletResponse response,String fileName) {
response.setContentType("application/pdf");
try {
String fullFileName = new String(fileName.getBytes(), StandardCharsets.ISO_8859_1);
response.setHeader("Content-disposition","attachment;filename=\\"+fullFileName+".pdf\\");
documentConverter
.convert(inputStream)
.as(DefaultDocumentFormatRegistry.DOCX)
.to(response.getOutputStream())
.as(DefaultDocumentFormatRegistry.PDF)
.execute();
} catch (OfficeException |IOException e) {
log.error("word转pdf失败:{}",e.getMessage());
}
}
public void exportByLocalPath(HttpServletResponse response, String fileName, String path, Object params) throws Exception {
BufferedOutputStream outputStream = null;
BufferedInputStream wordInputStream = null;
try (InputStream in = PdfService.class.getClassLoader().getResourceAsStream(path)) {
// 生成临时文件
String outPutWordPath = System.getProperty("java.io.tmpdir").replaceAll(File.separator + "$", "") + fileName+".docx";
File tempFile = FileUtil.touch(outPutWordPath);
outputStream = FileUtil.getOutputStream(tempFile);
// word模板合成写到临时文件
WordUtil.replaceWord(outputStream, in, params);
// word 转pdf
wordInputStream = FileUtil.getInputStream(tempFile);
docxToPDF(wordInputStream, response,fileName);
// 移除临时文件
FileUtil.del(tempFile);
} catch (Exception e) {
log.error("docx文档转换为PDF失败", e.getMessage());
} finally {
IoUtil.close(outputStream);
IoUtil.close(wordInputStream);
}
}
四.结论
1.docx4j方案
- 依赖少
- 同时支持word合成及格式转换
- 转化效率较差
- 对于含样式及图片转换不友好，容易排版混乱
2.jodconverter+LibreOffice 方案
- 操作稳定
- 转换效率快
- 集成依赖设置较多
- 依赖本地服务
- LibreOffice打开word可能排版样式错乱
- 最后考虑项目需求，最终选择了jodconverter+LibreOffice方案。
以上为个人经验，希望能给大家一个参考，也希望大家多多支持。
加载全部内容