Java实现PDF批量处理之合并、拆分、加水印的技术方案与实践

<dependency>

<groupId>org.apache.pdfbox</groupId>

<artifactId>pdfbox</artifactId>

<version>2.0.27</version>

</dependency>

import org.apache.pdfbox.multipdf.PDFMergerUtility;

import java.io.*;

import java.util.List;

  


public class PdfMergeService {

  


/**

* 合并多个PDF文件

* @param inputStreams PDF文件输入流列表

* @param outputPath 输出文件路径

*/

public void mergePdf(List<InputStream> inputStreams, String outputPath)

throws IOException {

PDFMergerUtility merger = new PDFMergerUtility();

merger.setDestinationFileName(outputPath);

  


for (InputStream is : inputStreams) {

merger.addSource(is);

}

  


// 执行合并，MemoryUsageSetting可控制内存使用

merger.mergeDocuments(

org.apache.pdfbox.io.MemoryUsageSetting.setupMainMemoryOnly()

);

}

}

import org.apache.pdfbox.multipdf.Splitter;

import org.apache.pdfbox.pdmodel.PDDocument;

  


public class PdfSplitService {

  


/**

* 按页码范围拆分PDF

* @param inputStream 源PDF输入流

* @param startPage 起始页（从1开始）

* @param endPage 结束页

*/

public byte[] splitByPageRange(InputStream inputStream,

int startPage, int endPage) throws IOException {

  


try (PDDocument document = PDDocument.load(inputStream);

PDDocument newDoc = new PDDocument()) {

  


int totalPages = document.getNumberOfPages();

// 参数校验

startPage = Math.max(1, startPage);

endPage = Math.min(totalPages, endPage);

  


for (int i = startPage - 1; i < endPage; i++) {

newDoc.addPage(document.getPage(i));

}

  


ByteArrayOutputStream baos = new ByteArrayOutputStream();

newDoc.save(baos);

return baos.toByteArray();

}

}

}

import org.apache.pdfbox.pdmodel.*;

import org.apache.pdfbox.pdmodel.font.PDType1Font;

import org.apache.pdfbox.pdmodel.graphics.state.PDExtendedGraphicsState;

import org.apache.pdfbox.util.Matrix;

  


public class PdfWatermarkService {

  


public byte[] addTextWatermark(InputStream input, String text,

float opacity, float rotation, float fontSize) throws IOException {

  


try (PDDocument document = PDDocument.load(input)) {

// 遍历每一页添加水印

for (PDPage page : document.getPages()) {

PDPageContentStream cs = new PDPageContentStream(

document, page,

PDPageContentStream.AppendMode.APPEND, true, true

);

  


// 设置透明度

PDExtendedGraphicsState gs = new PDExtendedGraphicsState();

gs.setNonStrokingAlphaConstant(opacity);

cs.setGraphicsStateParameters(gs);

  


// 设置字体和颜色

cs.setFont(PDType1Font.HELVETICA_BOLD, fontSize);

cs.setNonStrokingColor(200, 200, 200); // 浅灰色

  


// 计算页面中心位置

float pageWidth = page.getMediaBox().getWidth();

float pageHeight = page.getMediaBox().getHeight();

float cx = pageWidth / 2;

float cy = pageHeight / 2;

  


// 旋转变换

cs.beginText();

Matrix matrix = Matrix.getRotateInstance(

Math.toRadians(rotation), cx, cy

);

cs.setTextMatrix(matrix);

cs.showText(text);

cs.endText();

cs.close();

}

  


ByteArrayOutputStream baos = new ByteArrayOutputStream();

document.save(baos);

return baos.toByteArray();

}

}

}

// 加载系统中文字体

PDType0Font chineseFont = PDType0Font.load(document,

new FileInputStream("/usr/share/fonts/wqy-microhei/wqy-microhei.ttc"), 0);

cs.setFont(chineseFont, fontSize);

# CentOS/RHEL

sudo yum install -y wqy-microhei-fonts

# Ubuntu/Debian

sudo apt-get install -y fonts-wqy-microhei

@RestController

@RequestMapping("/api/document/pdf")

public class PdfController {

  


@PostMapping("/merge")

public ResponseEntity<?> merge(

@RequestParam("files") MultipartFile[] files) {

// 调用合并服务

}

  


@PostMapping("/split")

public ResponseEntity<?> split(

@RequestParam("file") MultipartFile file,

@RequestParam("startPage") int startPage,

@RequestParam("endPage") int endPage) {

// 调用拆分服务

}

  


@PostMapping("/watermark")

public ResponseEntity<?> watermark(

@RequestParam("file") MultipartFile file,

@RequestParam("text") String text,

@RequestParam(defaultValue = "0.5") float opacity) {

// 调用水印服务

}

}