JAVA 实现DOC到DOCX转换(实用篇)

注意1：本文使用了apache的老版本依赖，请斟酌后引用
注意2：这个方法会导致doc文档的表格&图片内容丢失

一：依赖

小工具引入的依赖如下(老版本)

        <!-- POI 核心 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.17</version>
        </dependency>

        <!-- HWPF (Word 97-2003) 支持 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>3.17</version>
        </dependency>

        <!-- XWPF (Word 2007+) 支持 -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.17</version>
        </dependency>

二：正文

依赖不需要过多介绍，直接看代码

1.带上导入的依赖结构是为了让代码可以直接使用，小伙伴们直接cv即可
2.该方法使用 MultipartFile 作为传入传出对象，主要是业务需要，也可以改为流式传输，本文不介绍其他方式

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
import org.springframework.core.io.ByteArrayResource;
import org.springframework.web.multipart.MultipartFile;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.Objects;



public class DocToDocxUtil {

	public static MultipartFile convert(MultipartFile originalFile) throws IOException {
		// 参数校验
		Objects.requireNonNull(originalFile, "Original file cannot be null");

		if (originalFile.isEmpty()) {
			throw new IllegalArgumentException("The provided file is empty.");
		}

		String originalFilename = originalFile.getOriginalFilename();
		if (originalFilename == null) {
			throw new IllegalArgumentException("Original filename cannot be null.");
		}

		if (!originalFilename.toLowerCase().endsWith(".doc")) {
			throw new IllegalArgumentException("The file must have a .doc extension. Received: " + originalFilename);
		}

		HWPFDocument hwpfDocument = null;
		XWPFDocument xwpfDocument = null;
		InputStream inputStream = null;
		ByteArrayOutputStream baos = null;

		try {
			inputStream = originalFile.getInputStream();
			hwpfDocument = new HWPFDocument(inputStream);
			xwpfDocument = new XWPFDocument();
			baos = new ByteArrayOutputStream();

			// 获取文档范围并处理内容
			Range range = hwpfDocument.getRange();
			int paragraphCount = range.numParagraphs();

			// 复制段落内容
			for (int i = 0; i < paragraphCount; i++) {
				Paragraph paragraph = range.getParagraph(i);
				String text = paragraph.text();

				// 清理文本
				text = cleanDocText(text);

				if (!text.isEmpty()) {
					XWPFParagraph xwpfParagraph = xwpfDocument.createParagraph();
					XWPFRun xwpfRun = xwpfParagraph.createRun();
					xwpfRun.setText(text);
				}
			}

			// 写入输出流
			xwpfDocument.write(baos);
			byte[] docxBytes = baos.toByteArray();

			// 创建新的MultipartFile
			return createMultipartFile(originalFile, originalFilename, docxBytes);

		} catch (Exception e) {
			throw new IOException("Failed to convert DOC to DOCX: " + e.getMessage(), e);
		} finally {
			// 手动关闭资源（3.17可能不支持try-with-resources）
			closeQuietly(hwpfDocument);
			closeQuietly(xwpfDocument);
			closeQuietly(inputStream);
			closeQuietly(baos);
		}
	}

	private static String cleanDocText(String text) {
		if (text == null || text.isEmpty()) {
			return "";
		}

		String cleaned = text.trim();

		if (cleaned.endsWith("\r")) {
			cleaned = cleaned.substring(0, cleaned.length() - 1);
		} else if (cleaned.endsWith("\r\n")) {
			cleaned = cleaned.substring(0, cleaned.length() - 2);
		} else if (cleaned.endsWith("\n")) {
			cleaned = cleaned.substring(0, cleaned.length() - 1);
		}

		return cleaned;
	}

	private static MultipartFile createMultipartFile(MultipartFile originalFile,
													 String originalFilename,
													 byte[] content) {

		String newFilename = originalFilename.replaceAll("(?i)\\.doc$", ".docx");

		ByteArrayResource resource = new ByteArrayResource(content) {
			@Override
			public String getFilename() {
				return newFilename;
			}
		};

		return new MultipartFile() {
			@Override
			public String getName() {
				return originalFile.getName();
			}

			@Override
			public String getOriginalFilename() {
				return newFilename;
			}

			@Override
			public String getContentType() {
				return "application/vnd.openxmlformats-officedocument.wordprocessingml.document";
			}

			@Override
			public boolean isEmpty() {
				return content.length == 0;
			}

			@Override
			public long getSize() {
				return content.length;
			}

			@Override
			public byte[] getBytes() {
				return content;
			}

			@Override
			public InputStream getInputStream() {
				return new ByteArrayInputStream(content);
			}

			@Override
			public void transferTo(java.io.File dest) throws IOException {
				try (InputStream is = getInputStream();
					 java.io.FileOutputStream fos = new java.io.FileOutputStream(dest)) {
					byte[] buffer = new byte[8192];
					int bytesRead;
					while ((bytesRead = is.read(buffer)) != -1) {
						fos.write(buffer, 0, bytesRead);
					}
				}
			}
		};
	}

	private static void closeQuietly(AutoCloseable closeable) {
		if (closeable != null) {
			try {
				closeable.close();
			} catch (Exception e) {
				// 安静关闭，忽略异常
			}
		}
	}