JAVA将WORD、EX文档转换为PDF

网上找了很多的方案，最后还是使用Apache POI + itext7适合一些，因为项目要部署在linux环境上，话不多说，直接步入整体。

一、引入相关依赖：

        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi</artifactId>
            <version>3.16</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>3.16</version>
        </dependency>


        <!-- 引入 itext7-core 依赖 -->
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itext7-core</artifactId>
            <version>7.1.16</version>
            <type>pom</type>
        </dependency>

二、上代码：

package com.example.filterandinterceptor.utils;


import com.itextpdf.kernel.font.PdfFont;
import com.itextpdf.kernel.font.PdfFontFactory;
import com.itextpdf.kernel.geom.PageSize;
import com.itextpdf.kernel.pdf.PdfDocument;
import com.itextpdf.kernel.pdf.PdfWriter;
import com.itextpdf.layout.Document;
import com.itextpdf.layout.element.Cell;
import com.itextpdf.layout.element.Paragraph;
import com.itextpdf.layout.element.Table;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.CellType;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.springframework.web.multipart.MultipartFile;

import java.io.IOException;
import java.io.InputStream;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Arrays;
import java.util.List;
import java.util.Objects;

/**
 * @author xiechenyu
 * @Description：
 * @date 2024/5/22 9:27
 */
public class ConvertPdfUtil {
    private final List<String> allowedFileExtensions = Arrays.asList("xls", "xlsx", "doc", "docx");

    private void convertToPdf(MultipartFile file) throws Exception {
        String originalFilename = file.getOriginalFilename();
        if (Objects.isNull(originalFilename)) {
            throw new RuntimeException("请上传正确文件");
        }
        checkFileExtensions(originalFilename);

        // 转换为PDF文件


    }

    private void checkFileExtensions(String originalFilename) {
        String fileExtension = getFileExtension(originalFilename);
        if (!allowedFileExtensions.contains(fileExtension)) {
            throw new RuntimeException("文件格式不正确,支持转换为PDF文件的格式有：xls、xlsx、doc、docx");
        }

    }

    private static String getFileExtension(String filename) {
        if (filename.lastIndexOf('.') != -1 && filename.lastIndexOf('.') != 0) {
            return filename.substring(filename.lastIndexOf('.') + 1);
        } else {
            return "";
        }
    }

    //word文件转pdf，支持doc，docx
    public static void wordToPdf(String inFilePath, String outFilePath) {
        try (PdfDocument pdf = new PdfDocument(new PdfWriter(Files.newOutputStream(Paths.get(outFilePath))));
             Document pdfDocument = new Document(pdf, PageSize.A4.rotate());) {
            //指定pdf的字体样式为STSong-Light，编码方式为UniGB-UCS2-H,不指定编码方式中文乱码
            PdfFont pdfFont = PdfFontFactory.createFont("STSong-Light", "UniGB-UCS2-H");
            // 文件输入流读取文件
            InputStream in = Files.newInputStream(Paths.get(inFilePath));
            // 读取Word文档
            XWPFDocument word = new XWPFDocument(in);
            // 逐段写入PDF
            for (XWPFParagraph paragraph : word.getParagraphs()) {
                pdfDocument.add(new Paragraph(paragraph.getText()).setFont(pdfFont));
            }
        }catch (IOException e){
            throw new RuntimeException(e);
        }
    }


    //excel文件转pdf，支持xsl，xslx
    public static void excelToPdf(String inFilePath, String outFilePath) {
        try (PdfDocument pdf = new PdfDocument(new PdfWriter(Files.newOutputStream(Paths.get(outFilePath))));
             Document document = new Document(pdf, PageSize.A4.rotate());) {

            //指定pdf的字体样式为STSong-Light，编码方式为UniGB-UCS2-H
            PdfFont pdfFont = PdfFontFactory.createFont("STSong-Light", "UniGB-UCS2-H");

            // 文件输入流读取文件
            InputStream in = Files.newInputStream(Paths.get(inFilePath));

            //excel文件类型有xls和xlsx两种，对应的构造器不一样
            String fileExtension = getFileExtension(inFilePath);
            Workbook workbook = Objects.equals(fileExtension, ".xsl") ? new HSSFWorkbook(in) : new XSSFWorkbook(in);

            int numberOfSheets = workbook.getNumberOfSheets();
            for (int k = 0; k < numberOfSheets; k++) {
                Sheet sheet = workbook.getSheetAt(k);
                //获取总列数
                int column = getMaxColumn(sheet);
                //创建一个pdf的table对象，以便在pdf中以表的形式展示，列数和excel列数一致
                Table table = new Table(column);

                for (int i = sheet.getFirstRowNum(); i <= sheet.getLastRowNum(); i++) {
                    for (int j = 0; j < column; j++) {
                        String str = "";
                        //获取excel单元格
                        Row row = sheet.getRow(i);
                        if (Objects.isNull(row)) {
                            continue;
                        }
                        org.apache.poi.ss.usermodel.Cell cell = row.getCell(j);
                        if (Objects.nonNull(cell)) {
                            if (cell.getCellTypeEnum() == CellType.NUMERIC) {
                                str = (int) cell.getNumericCellValue() + "";
                            } else {
                                str = cell.getStringCellValue();
                            }
                        }
                        //将pdf的单元格初始化并添加到pdf中
                        Cell cells = new Cell().setFont(pdfFont).add(new Paragraph(str));
                        table.addCell(cells);
                    }
                }
                //两个table之间增加一个空格
                document.add(new Paragraph(" "));
                document.add(table);
            }


        } catch (IOException e) {
            throw new RuntimeException(e);
        }
    }

    private static int getMaxColumn(Sheet sheet) {
        int maxColumn = 0;
        for (int i = sheet.getFirstRowNum(); i <= sheet.getLastRowNum(); i++) {
            if (Objects.nonNull(sheet.getRow(i))) {
                maxColumn = Math.max(maxColumn, sheet.getRow(i).getLastCellNum());
            }
        }
        return maxColumn;
    }

    public static void main(String[] args) {
//        excelToPdf("D:\\convertfile\\慢查询SQL.xlsx", "D:\\convertfile\\慢查询SQL.pdf");

        wordToPdf("D:\\convertfile\\测试 - 副本.doc", "D:\\convertfile\\测试 - 副本.pdf");
    }


}