documents4j 文档转换

桃扇骨 2023-10-15 09:01 20阅读 0赞

documents4j 是一个 Java 库，可以将文档转换为另一种文档格式。

[https://github.com/documents4j/documents4j][https_github.com_documents4j_documents4j]

<parent>
        <artifactId>spring-boot-starter-parent</artifactId>
        <groupId>org.springframework.boot</groupId>
        <version>2.6.0</version>
    </parent>
    
    <dependencies>
        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>
        <dependency>
            <groupId>com.documents4j</groupId>
            <artifactId>documents4j-local</artifactId>
            <version>1.1.5</version>
        </dependency>
        <dependency>
            <groupId>com.documents4j</groupId>
            <artifactId>documents4j-transformer-msoffice-word</artifactId>
            <version>1.1.5</version>
        </dependency>
    </dependencies>

@RequestMapping("/to")
    @RestController
    public class PdfController {
        
    
        /**
         * doc文件转pdf
         *
         * @param path 文件路径
         */
        @RequestMapping("/doc2pdf")
        public ResponseEntity<byte[]> doc2pdfFileUpload(String path) throws IOException {
        
            URL url = new URL(path);
            URLConnection conn = url.openConnection();
            InputStream inputStream = conn.getInputStream();
    
            return doc2Pdf(inputStream, ".doc", "fileName.pdf");
        }
    
        /**
         * docx、xlsx、转pdf
         *
         * @param fileType docx、doc、xls、xlsx
         * @param fileName pdf名称
         */
        public ResponseEntity<byte[]> doc2Pdf(InputStream docxInputStream, String fileType, String fileName) throws IOException {
        
            // 转换后的pdf临时路径
            File outputFile = new File("C:/Users/admin002/Desktop/folder/doc/" + fileName);
    
            IConverter converter = LocalConverter.builder().build();
            ResponseEntity<byte[]> fileResult = null;
            try (OutputStream outputStream = Files.newOutputStream(outputFile.toPath());
                 // 导出pdf文件给前端
                 FileInputStream inputStream = new FileInputStream(outputFile);
                 ) {
        
                if (".docx".equals(fileType)) {
        
                    converter.convert(docxInputStream).as(DocumentType.DOCX).to(outputStream).as(DocumentType.PDF).execute();
                } else if (".doc".equals(fileType)) {
        
                    converter.convert(docxInputStream).as(DocumentType.DOC).to(outputStream).as(DocumentType.PDF).execute();
                } else if (".xls".equals(fileType)) {
        
                    converter.convert(docxInputStream).as(DocumentType.XLS).to(outputStream).as(DocumentType.PDF).execute();
                } else if (".xlsx".equals(fileType)) {
        
                    converter.convert(docxInputStream).as(DocumentType.XLSX).to(outputStream).as(DocumentType.PDF).execute();
                }
    
                byte[] bytes = new byte[(int) outputFile.length()];
                inputStream.read(bytes);
    
                HttpHeaders headers = new HttpHeaders();
                // 此处pdf名称需要传入
                headers.set("Content-Disposition", "attachment; filename=\"" + fileName + "\"");
                fileResult = new ResponseEntity(bytes, headers, HttpStatus.OK);
    
            } finally {
        
                docxInputStream.close();
            }
            return fileResult;
        }
    
    }

以上方式依赖于Windows上的MS Word、MS Excel，必须使用Windows。

只有在以下情况下才能运行 `LocalConverter`构建：

*  JVM在MS Windows平台上运行，该平台附带VBS的Microsoft脚本主机。
 *  MS Word 版本必须在2007 或更高版本。安装了 PDF 插件时，才支持 PDF 转换。该插件包含在了Word 2010及更高版本的MS Word中。

未完待续。。。。

[https_github.com_documents4j_documents4j]: https://github.com/documents4j/documents4j