java将doc文件转pdf

将doc文件转为pdf

itextpdf+poi 方案，针对doc文件，非docx
缺点，不支持负责的格式，不支持图标，图片等。

需要的依赖

  <!-- https://mvnrepository.com/artifact/com.itextpdf/itextpdf -->
        <dependency>
            <groupId>com.itextpdf</groupId>
            <artifactId>itextpdf</artifactId>
            <version>5.5.13.3</version>
        </dependency>
       <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml</artifactId>
            <version>4.1.2</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-ooxml-schemas -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-ooxml-schemas</artifactId>
            <version>4.1.2</version>
        </dependency>
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>ooxml-schemas</artifactId>
            <version>1.1</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.poi/poi-scratchpad -->
        <dependency>
            <groupId>org.apache.poi</groupId>
            <artifactId>poi-scratchpad</artifactId>
            <version>4.1.2</version>
        </dependency>

java代码

import com.google.common.io.Files;
import com.itextpdf.text.Document;
import com.itextpdf.text.DocumentException;
import com.itextpdf.text.Font;
import com.itextpdf.text.Paragraph;
import com.itextpdf.text.pdf.BaseFont;
import com.itextpdf.text.pdf.PdfWriter;
import lombok.extern.slf4j.Slf4j;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;

import java.io.*;

/**
 * @Description 将doc文件转换为pdf
 */
@Slf4j
public class DocToPdfUtil {

    public static void toPdf(File orgFile, String outputFile) throws IOException {
        File file = new File(outputFile);
        try {
            ByteArrayOutputStream outputStream = toPdf(orgFile);
            Files.write(outputStream.toByteArray(), new File(outputFile));
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static ByteArrayOutputStream toPdf(File file) throws IOException, DocumentException {
        Document pdfDoc = null;
        WordExtractor extractor = null;
        try {
            // 读取DOC文件
            HWPFDocument doc = new HWPFDocument(new FileInputStream(file));
            extractor = new WordExtractor(doc);

            ByteArrayOutputStream outputStream = new ByteArrayOutputStream();
            // 创建PDF文档
            pdfDoc = new Document();
            PdfWriter.getInstance(pdfDoc, outputStream);
            pdfDoc.open();

            // 写入内容
            String[] paragraphs = extractor.getParagraphText();
            // 加载中文字体
            BaseFont baseFont = BaseFont.createFont("STSong-Light", "UniGB-UCS2-H", BaseFont.EMBEDDED);
            Font font = new Font(baseFont, 12);

            for (String text : paragraphs) {
                Paragraph p = new Paragraph(text, font);
                pdfDoc.add(p);
            }
            log.info("==========doc转换pdf成功===============" + file.getAbsolutePath());
            return outputStream;
        } catch (Exception e) {
            log.info("==========doc转换pdf失败===============" + file.getAbsolutePath());
            e.printStackTrace();
            throw e;
        } finally {
            // 关闭资源
            if (null != pdfDoc) {
                pdfDoc.close();
            }
            if (null != extractor) {
                extractor.close();
            }
        }
    }
}

测试用例

 DocToPdfUtil.toPdf(new File("C:\\mydoc\\明朝那点事.doc"), "C:\\mydoc\\明朝那点事" + System.currentTimeMillis() + ".pdf");

遇到的问题

转换的文件不显示中文

原因：字体问题，请设置字体。

// 加载中文字体
            BaseFont baseFont = BaseFont.createFont("STSong-Light", "UniGB-UCS2-H", BaseFont.EMBEDDED);
            Font font = new Font(baseFont, 12);