获取 pdf 中某个关键字的位置坐标

前言

  在制作印章的时候 通过后端计算印章位置坐标，需要 提供pdf页面关键字 即可找到此关键字在pdf中的页数以及x,y 坐标

---

一、两个基础配置类

1.KeyWordPositionListener   pdf签名帮助类

代码如下（示例）：

package com.z.boot.core.util.pdf;


import com.itextpdf.awt.geom.Rectangle2D;
import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.parser.ImageRenderInfo;
import com.itextpdf.text.pdf.parser.RenderListener;
import com.itextpdf.text.pdf.parser.TextRenderInfo;
import java.util.ArrayList;
import java.util.List;

/**
 * @ClassName KeyWordPositionListener
 * @Description pdf签名帮助类
 * @Date: 2021/3/17 16:57
 * @Version 1.0
 **/
public class KeyWordPositionListener implements RenderListener{

    private List matches = new ArrayList();
    private List allItems = new ArrayList();
    private Rectangle curPageSize;


    /**
     * 匹配的关键字
     */
    private String keyword;
    /**
     * 匹配的当前页
     */
    private Integer pageNumber;


    public void beginTextBlock() {
        //do nothing
    }


    public void renderText(TextRenderInfo renderInfo) {
        String content = renderInfo.getText();
        content = content.replace("<", "").replace("《", "").replace("(", "").replace("（", "").replace("\"", "").replace("'", "")
                .replace(">", "").replace("》", "").replace(")", "").replace("）", "").replace("、", "").replace(".", "")
                .replace("：", "").replace(":", "").replace(" ", "");
        Rectangle2D.Float boundingRectange  = renderInfo.getBaseline().getBoundingRectange();
        MatchItem item = new MatchItem();
        item.setContent(content);
        item.setPageNum(pageNumber);
        item.setPageWidth(curPageSize.getWidth()); //页面宽度
        item.setPageHeight(curPageSize.getHeight()); //页面高度
        item.setX(boundingRectange.x);
        item.setY(boundingRectange.y);
        item.setRectangeWidth(boundingRectange.getWidth());  //当前块级元素占的宽度
        item.setRectangeHeight(boundingRectange.getHeight()); //当前块级元素占的高度
        if(content!=null && content!=""){
            if(content.equalsIgnoreCase(keyword)) {
                matches.add(item);
            }
        }
        allItems.add(item);//先保存所有的项
    }


    public void endTextBlock() {
        //do nothing
    }


    public void renderImage(ImageRenderInfo renderInfo) {
        //do nothing
    }


    /**
     * 设置需要匹配的当前页
     * @param pageNumber
     */
    public void setPageNumber(Integer pageNumber) {
        this.pageNumber = pageNumber;
    }


    /**
     * 设置需要匹配的关键字，忽略大小写
     * @param keyword
     */
    public void setKeyword(String keyword) {
        this.keyword = keyword;
    }


    /**
     * 返回匹配的结果列表
     * @return
     */
    public List getMatches() {
        return matches;
    }


    void setCurPageSize(Rectangle rect) {
        this.curPageSize = rect;
    }


    public List getAllItems() {
        return allItems;
    }


    public void setAllItems(List allItems) {
        this.allItems = allItems;
    }
}

2.MatchItem 

代码如下（示例）：

package com.z.boot.core.util.pdf;

/**
 * @ClassName MatchItem
 * @Description
 * @Date: 2021/3/17 16:57
 * @Version 1.0
 **/
public class MatchItem {
    private Integer pageNum;
    private Float x;
    private Float y;
    private Float pageWidth;
    private Float pageHeight;
    private String content;
    private double rectangeWidth; //块级元素宽度
    private double rectangeHeight; //块级元素高度


    public Integer getPageNum() {
        return pageNum;
    }
    public void setPageNum(Integer pageNum) {
        this.pageNum = pageNum;
    }
    public Float getX() {
        return x;
    }
    public void setX(Float x) {
        this.x = x;
    }
    public Float getY() {
        return y;
    }
    public void setY(Float y) {
        this.y = y;
    }
    public Float getPageWidth() {
        return pageWidth;
    }
    public void setPageWidth(Float pageWidth) {
        this.pageWidth = pageWidth;
    }
    public Float getPageHeight() {
        return pageHeight;
    }
    public void setPageHeight(Float pageHeight) {
        this.pageHeight = pageHeight;
    }
    public String getContent() {
        return content;
    }
    public void setContent(String content) {
        this.content = content;
    }
    public double getRectangeWidth() {
        return rectangeWidth;
    }
    public void setRectangeWidth(double rectangeWidth) {
        this.rectangeWidth = rectangeWidth;
    }
    public double getRectangeHeight() {
        return rectangeHeight;
    }
    public void setRectangeHeight(double rectangeHeight) {
        this.rectangeHeight = rectangeHeight;
    }

    @Override
    public String toString() {
        return "MatchItem [pageNum=" + pageNum + ", x=" + x + ", y=" + y
                + ", pageWidth=" + pageWidth + ", pageHeight=" + pageHeight
                + ", content=" + content + "]";
    }
}

二、核心计算类

package com.z.boot.core.util.pdf;

import com.itextpdf.text.Rectangle;
import com.itextpdf.text.pdf.PdfReader;
import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
import lombok.extern.slf4j.Slf4j;

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


/**
 * @ClassName QuotationPdf
 * @Description
 * @Date: 2021/3/16 10:44
 * @Version 1.0
 **/
@Slf4j
public class QuotationPdf {

    /**
     * @param filepath
     * @param keyWords
     * @return float[]
     * @Date 2021/3/17 16:57
     * @Description 用于供外部类调用获取关键字所在PDF文件坐标
     * @Version 1.0
     */
    public static MatchItem getKeyWordsByPath(String filepath, String keyWords) throws Exception {
        try {
            PdfReader pdfReader = new PdfReader(filepath);
            int pageCount= pdfReader.getNumberOfPages();
            return matchPage(pdfReader,pageCount, keyWords);
        } catch (IOException e) {
            e.printStackTrace();
            return null;
        }
    }

    /**
     * 在文件中寻找指定的文字内容
     *
     * @param reader
     * @param pageNumber
     * @param keyword
     * @return
     * @throws Exception
     */
    public static MatchItem matchPage(PdfReader reader,
                                      Integer pageNumber, String keyword) throws Exception {
        MatchItem matchItem = null;
        PdfReaderContentParser parse = new PdfReaderContentParser(reader);
        KeyWordPositionListener renderListener = new KeyWordPositionListener();
        renderListener.setKeyword(keyword);
        int page = 0;
        for (page = 1; page <= pageNumber; page++) {
            renderListener.setPageNumber(page);
            Rectangle rectangle = reader.getPageSize(page);
            renderListener.setCurPageSize(rectangle);
            parse.processContent(page, renderListener);
            matchItem = findKeywordItems(renderListener, keyword);
            if(null != matchItem) {
                matchItem.setPageNum(page);
                break;
            }
        }
        reader.close();
        return matchItem;
    }

    /**
     * 找到匹配的关键词块
     *
     * @param renderListener
     * @param keyword
     * @return
     */
    public static MatchItem findKeywordItems(KeyWordPositionListener renderListener,
                                             String keyword) {
        // 先判断本页中是否存在关键词
        List allItems = renderListener.getAllItems();// 所有块LIST
        StringBuilder sbtemp = new StringBuilder("");
        for (int i = 0; i < allItems.size(); i++) {// 将一页中所有的块内容连接起来组成一个字符串。(空格用“正”代替)
            sbtemp.append(((MatchItem) allItems.get(i)).getContent());
        }
        int index  = sbtemp.toString().indexOf(keyword);
        System.out.println(sbtemp.toString());
        if (index == -1) {// 一页组成的字符串没有关键词，直接return
            return null;
        }
        //获取关键词与块内容完全匹配的项
        List matches = renderListener.getMatches();
        if(null == matches || matches.size()<=0){
            //不存在，取本页中连续 拼接块内容 第一个关键字的位置
            //当拼接的长度超过或等于关键字在此页内容中出现的位置，即为找到
            sbtemp = new StringBuilder("");
            for (int i = 0; i < allItems.size(); i++) {
                sbtemp.append(((MatchItem) allItems.get(i)).getContent());
                if(sbtemp.toString().length() >= index+1){
                    matches.add(allItems.get(i));
                    break;
                }
            }
        }
//第二种方式，跟上面是一样的，可以自行研究
//        if(null == matches || matches.size()<=0){
//            //若还为空，第二种情况：多个块内容拼成一个关键词 取连续的几个块内容拼接起来
//            //1.若关键字包含context继续拼接；2.若关键字等于context即找到
//            sbtemp = new StringBuffer("");
//            int ItmeIndex = 0; //块级元素计数器
//            for (int i = 0; i < allItems.size(); i++) {
//                String itemText = ((MatchItem) allItems.get(i)).getContent();
//                sbtemp.append(itemText);
//                if(keyword.contains(sbtemp.toString()) ){
//
//                }else if(keyword.equals(sbtemp.toString())){
//                    matches.add(allItems.get(i));
//                    break;
//                }else if(sbtemp.toString().contains(keyword)){
//                    //被块元素包含
//                    int index1 = itemText.indexOf(keyword);
//                    double rectangeWidth = ((MatchItem) allItems.get(i)).getRectangeWidth(); //块级元素的宽度
//                    double oneWidth = rectangeWidth/itemText.length(); //单个字体的宽度
//                    double finalWidth = (index1+Math.rint(keyword.length()/2) ) * oneWidth + ((MatchItem) allItems.get(i)).getX();
//                    ((MatchItem) allItems.get(i)).setX((float) finalWidth);
//                    matches.add(allItems.get(i));
//                    break;
//                }else{
//                    sbtemp = new StringBuffer("");
//                }
//            }
//        }
        if(null != matches && matches.size()>0){
            return (MatchItem) matches.get(0);
        }else{
            return null;
        }
    }

    /**
     * @param filepath
     * @return float[]
     * @Date 18:24 2020/3/7
     * @Description 用于供外部类获取PDF高度和宽度
     */
    public static float[] getWidthAndHeightByPath(String filepath, int page) {
        float[] coordinate = null;
        try {
            PdfReader pdfReader = new PdfReader(filepath);
            Rectangle pageSize = pdfReader.getPageSize(page);
            float height = pageSize.getHeight();
            float width = pageSize.getWidth();
            System.out.println("width = " + width + ", height = " + height);
            float[] coordinate1 = {width, height};
            pdfReader.close();
            return coordinate1;
//            Document document = new Document(pdfReader.getPageSize(1));
			Document document = new Document(PageSize.A4.rotate(), 0, 0, 30, 0);
//            // 获取页面宽度
//            float widths = document.getPageSize().getWidth();
//            // 获取页面高度
//            float heights = document.getPageSize().getHeight();
//            System.out.println("widths = "+widths+", heights = "+heights);
        } catch (IOException e) {
            e.printStackTrace();
            return coordinate;
        }
    }

    public static void main(String[] args) throws Exception {
        String filePath = "E:\\work\\bin\\wenlinworkspace\\repository\\laboratoryFile\\message\\wordtemp\\2020-12-14\\8ae123961e5d47faa4acee6d066efcf7.pdf";
        MatchItem a = getKeyWordsByPath(filePath, "bm_g_12443_1#_ResultData_32");
        System.out.println("width = " + a.getX()
                + ", height = " + a.getY()
                + ",page = " + a.getPageNum());
//
//        float[] b = getWidthAndHeightByPath(filePath, Integer.parseInt(a.get("page").toString()));
        System.out.println(a.getPageWidth()+"-----"+a.getPageHeight());
        float x = (a.getX() - 35F) / a.getPageWidth();
        float y = (a.getY() - 52.5F) / a.getPageHeight();
        System.out.println("x = " + x + ", y = " + y);
    }

}

三、使用 

public static void main(String[] args) throws Exception {
        String filePath = "E:\\work\\bin\\wenlinworkspace\\repository\\laboratoryFile\\message\\wordtemp\\2020-12-14\\8ae123961e5d47faa4acee6d066efcf7.pdf";
        MatchItem a = getKeyWordsByPath(filePath, "bm_g_12443_1#_ResultData_32");
        System.out.println("width = " + a.getX()
                + ", height = " + a.getY()
                + ",page = " + a.getPageNum());
//
//        float[] b = getWidthAndHeightByPath(filePath, Integer.parseInt(a.get("page").toString()));
        System.out.println(a.getPageWidth()+"-----"+a.getPageHeight());
        float x = (a.getX() - 35F) / a.getPageWidth();
        float y = (a.getY() - 52.5F) / a.getPageHeight();
        System.out.println("x = " + x + ", y = " + y);
    }

MatchItem position = QuotationPdf.getKeyWordsByPath(pdfPath,"合同章_01");
//position  里面包含了 所能用到的所有参数 横纵长度，以及页面长宽
//页面比例 需自行计算