pdf判断影印件

最新推荐文章于 2024-10-08 23:58:57 发布

changyus

最新推荐文章于 2024-10-08 23:58:57 发布

阅读量240

点赞数

分类专栏： java 文章标签： pdf 开发语言 java

本文链接：https://blog.csdn.net/changyus/article/details/132110459

版权

java 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

文章介绍了如何使用ApachePDFBox库中的PdfImageCounter类来统计PDF文档中图像的数量，以判断PDF文件是否为影印件。PdfUtil类提供了isPhotocopy方法，通过处理每一页并计算图像计数器的值来实现此功能。

摘要由CSDN通过智能技术生成

package com.test.util;

import org.apache.pdfbox.cos.COSBase;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.graphics.PDXObject;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.util.Matrix;


import java.io.IOException;
import java.util.List;

import org.apache.pdfbox.contentstream.PDFStreamEngine;
import org.apache.pdfbox.contentstream.operator.MissingOperandException;
import org.apache.pdfbox.contentstream.operator.Operator;
import org.apache.pdfbox.contentstream.operator.OperatorProcessor;

public class PdfImageCounter extends PDFStreamEngine {
    protected int documentImageCount = 0;

    public int getDocumentImageCount() {
        return documentImageCount;
    }

    public PdfImageCounter() {
        addOperator(new OperatorProcessor() {
            @Override
            public void process(Operator operator, List<COSBase> arguments) throws IOException {
                if (arguments.size() < 1) {
                    throw new MissingOperandException(operator, arguments);
                }
                if (isImage(arguments.get(0))) {
                    documentImageCount++;
                }
            }

            protected Boolean isImage(COSBase base) throws IOException {
               if(!(base instanceof COSName)) {
                  return false;
               }
               
               boolean isImg = context.getResources().isImageXObject((COSName)base);
               
               if(isImg) {
                  Matrix ctmNew = getGraphicsState().getCurrentTransformationMatrix();
                  //
                  if(ctmNew.getTranslateX() == 0.0 && ctmNew.getTranslateY() == 0.0) {
                     return true;
                  }
               }
               
                return false;
            }

            @Override
            public String getName() {
                return "Do";
            }
        });
    }
}

package com.test.util;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;

import java.io.File;

public class PdfUtil {
    /**
     * 判断PDF文件是否为影印件
     *
     * @param path
     * @return boolean
     */
    public static boolean isPhotocopy(String path) {
        try {
            int pageNum = 0;
            int imageCount = 0;
            PDDocument document = PDDocument.load(new File(path));
            PdfImageCounter counter = new PdfImageCounter();

            for (PDPage pdPage : document.getPages()) {
                pageNum++;
                counter.processPage(pdPage);
            }
            imageCount = counter.getDocumentImageCount();
            document.close();
            return pageNum == imageCount;
        } catch (Exception e) {
            return false;
        }
    }
}

public class PdfUtilTest {

    public static void main(String[] args) throws Exception {
        PdfUtilTest test = new PdfUtilTest();
        test.isPhotocopy();

    }

    public void isPhotocopy() throws Exception {
        String filePath = "D:\\opt\\python.pdf";
        boolean a = PdfUtil.isPhotocopy(filePath);
        System.out.println(a);
    }
}