Java实现将Word和PDF转成一张垂直拼接长图的工具类

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>5.2.5</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>5.2.5</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>5.2.5</version> <!-- 如果有 DOCX 相关 -->
</dependency>
<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>3.0.5</version>
</dependency>
<!-- Word转PDF：Docx4J核心 -->
        <dependency>
            <groupId>org.docx4j</groupId>
            <artifactId>docx4j-JAXB-ReferenceImpl</artifactId>
            <version>8.3.10</version>
        </dependency>

        <!-- Word转PDF：FO导出支持（用于PDF渲染） -->
        <dependency>
            <groupId>org.docx4j</groupId>
            <artifactId>docx4j-export-fo</artifactId>
            <version>8.3.10</version>
        </dependency>
        <dependency>
            <groupId>javax.xml.bind</groupId>
            <artifactId>jaxb-api</artifactId>
            <version>2.3.1</version>
        </dependency>
        <dependency>
            <groupId>org.glassfish.jaxb</groupId>
            <artifactId>jaxb-runtime</artifactId>
            <version>2.3.3</version>
        </dependency>
        <!-- 如果 Docx4J 版本旧，还可能需激活模块 -->
        <dependency>
            <groupId>com.sun.activation</groupId>
            <artifactId>javax.activation</artifactId>
            <version>1.2.0</version>
        </dependency>

import lombok.extern.slf4j.Slf4j;
import org.apache.fop.apps.Fop;
import org.apache.fop.apps.FopFactory;
import org.apache.fop.apps.MimeConstants;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.io.RandomAccessReadBuffer;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToFoConverter;
import org.docx4j.Docx4J;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.w3c.dom.Document;

import javax.imageio.ImageIO;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.*;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.sax.SAXResult;
import javax.xml.transform.stream.StreamResult;
import javax.xml.transform.stream.StreamSource;
import java.awt.*;
import java.awt.image.BufferedImage;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/**
 * @Description 文档转长图片工具类
 * 支持Word (doc/docx) 和 PDF 转成一张垂直拼接的长PNG图片
 */

@Slf4j
public class DocumentToImageUtil {

    /**
     * 将文档（Word或PDF）转换为长图片字节数组
     * @param content 文档字节数组
     * @param fileType 文件类型（doc, docx, pdf）
     * @return PNG图片字节数组
     * @throws IOException 转换失败
     */
    public byte[] convertToStitchedImage(byte[] content, String fileType) throws IOException {
        byte[] pdfContent = content;
        if (fileType.toLowerCase().contains("doc") || fileType.toLowerCase().contains("docx")) {
            pdfContent = convertWordToPdf(content, fileType.toLowerCase());
        }
        return convertPdfToStitchedImage(pdfContent);
    }

    /**
     * Word转PDF（支持doc和docx）
     */
    private byte[] convertWordToPdf(byte[] wordContent, String fileType) throws IOException {
        if (fileType.toLowerCase().contains("docx")) {
            // DOCX转PDF使用Docx4J
            try (ByteArrayInputStream bais = new ByteArrayInputStream(wordContent)) {
                WordprocessingMLPackage loadedPackage = WordprocessingMLPackage.load(bais);
                ByteArrayOutputStream baos = new ByteArrayOutputStream();
                Docx4J.toPDF(loadedPackage, baos);
                return baos.toByteArray();
            } catch (Exception e) {
                throw new IOException("DOCX转PDF失败", e);
            }
        } else if (fileType.toLowerCase().contains("doc")) {
            // DOC转PDF使用POI HWPF + Transformer + FOP
            try (ByteArrayInputStream bais = new ByteArrayInputStream(wordContent);
                 HWPFDocument document = new HWPFDocument(bais)) {

                // 1. 使用 WordToFoConverter 生成 FO Document（移除 setFontResolver，使用默认）
                Document foDoc = DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument();
                WordToFoConverter converter = new WordToFoConverter(foDoc);
                // 注意：在 POI 5.2.5 中，setFontResolver 已弃用或移除，使用默认字体解析器
                converter.processDocument(document);

                // 2. Transformer 将 FO Document 序列化为字节流
                ByteArrayOutputStream foBaos = new ByteArrayOutputStream();
                TransformerFactory tf = TransformerFactory.newInstance();
                Transformer serializer = tf.newTransformer();
                serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
                serializer.setOutputProperty(OutputKeys.INDENT, "yes");
                serializer.setOutputProperty(OutputKeys.METHOD, "xml"); // 输出 XML-FO
                serializer.transform(new DOMSource(foDoc), new StreamResult(foBaos));
                byte[] foBytes = foBaos.toByteArray();

                // 3. FOP 将 FO 转 PDF（使用带URI参数的newInstance，避免解析问题）
                FopFactory fopFactory = FopFactory.newInstance(new File(".").toURI()); // 标准方式，设置base URI
                ByteArrayOutputStream pdfBaos = new ByteArrayOutputStream();
                Fop fop = fopFactory.newFop(MimeConstants.MIME_PDF, pdfBaos);
                Transformer transformer = tf.newTransformer(); // 身份转换器
                Source src = new StreamSource(new ByteArrayInputStream(foBytes));
                Result res = new SAXResult(fop.getDefaultHandler());
                transformer.transform(src, res);

                return pdfBaos.toByteArray();
            } catch (Exception e) {
                throw new IOException("DOC转PDF失败", e);
            }
        } else {
            throw new IOException("不支持的文件类型: " + fileType);
        }
    }

    /**
     * PDF转垂直拼接的长图片
     */
    private byte[] convertPdfToStitchedImage(byte[] pdfContent) throws IOException {
        try (ByteArrayInputStream bais = new ByteArrayInputStream(pdfContent);
             RandomAccessReadBuffer buffer = new RandomAccessReadBuffer(bais);
             PDDocument document = Loader.loadPDF(buffer)) {
            PDFRenderer renderer = new PDFRenderer(document);
            int numPages = document.getNumberOfPages();
            if (numPages == 0) {
                return null;
            }

            List<BufferedImage> pageImages = new ArrayList<>();
            int totalHeight = 0;
            int maxWidth = 0;
            for (int i = 0; i < numPages; i++) {
                BufferedImage pageImage = renderer.renderImageWithDPI(i, 150);
                pageImages.add(pageImage);
                totalHeight += pageImage.getHeight();
                maxWidth = Math.max(maxWidth, pageImage.getWidth());
            }

            BufferedImage stitchedImage = new BufferedImage(maxWidth, totalHeight, BufferedImage.TYPE_INT_RGB);
            Graphics2D g2d = stitchedImage.createGraphics();
            g2d.setBackground(java.awt.Color.WHITE);
            g2d.clearRect(0, 0, maxWidth, totalHeight);

            int yOffset = 0;
            for (BufferedImage pageImage : pageImages) {
                g2d.drawImage(pageImage, 0, yOffset, null);
                yOffset += pageImage.getHeight();
            }
            g2d.dispose();

            ByteArrayOutputStream baos = new ByteArrayOutputStream();
            ImageIO.write(stitchedImage, "png", baos);
            return baos.toByteArray();
        } catch (Exception e) {
            throw new IOException("PDF转图片失败", e);
        }
    }
}

byte[] imageBytes = new DocumentToImageUtil().convertToStitchedImage(content, fileType.toLowerCase());