devbox
知新_RL
这个屌丝很懒，什么也没留下！
关注作者
热门标签
热门文章
当前位置:   article > 正文

获取 pdf 中某个关键字的位置坐标_pdf获取坐标

作者：知新_RL | 2024-06-22 00:44:33

赞

踩

pdf获取坐标

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）：

  1. package com.z.boot.core.util.pdf;
  2.  
  3.  
  4. import com.itextpdf.awt.geom.Rectangle2D;
  5. import com.itextpdf.text.Rectangle;
  6. import com.itextpdf.text.pdf.parser.ImageRenderInfo;
  7. import com.itextpdf.text.pdf.parser.RenderListener;
  8. import com.itextpdf.text.pdf.parser.TextRenderInfo;
  9. import java.util.ArrayList;
  10. import java.util.List;
  11.  
  12. /**
  13.  * @ClassName KeyWordPositionListener
  14.  * @Description pdf签名帮助类
  15.  * @Date: 2021/3/17 16:57
  16.  * @Version 1.0
  17.  **/
  18. public class KeyWordPositionListener implements RenderListener{
  19.  
  20.     private List matches = new ArrayList();
  21.     private List allItems = new ArrayList();
  22.     private Rectangle curPageSize;
  23.  
  24.  
  25.     /**
  26.      * 匹配的关键字
  27.      */
  28.     private String keyword;
  29.     /**
  30.      * 匹配的当前页
  31.      */
  32.     private Integer pageNumber;
  33.  
  34.  
  35.     public void beginTextBlock() {
  36.         //do nothing
  37.     }
  38.  
  39.  
  40.     public void renderText(TextRenderInfo renderInfo) {
  41.         String content = renderInfo.getText();
  42.         content = content.replace("<", "").replace("《", "").replace("(", "").replace("（", "").replace("\"", "").replace("'", "")
  43.                 .replace(">", "").replace("》", "").replace(")", "").replace("）", "").replace("、", "").replace(".", "")
  44.                 .replace("：", "").replace(":", "").replace(" ", "");
  45.         Rectangle2D.Float boundingRectange  = renderInfo.getBaseline().getBoundingRectange();
  46.         MatchItem item = new MatchItem();
  47.         item.setContent(content);
  48.         item.setPageNum(pageNumber);
  49.         item.setPageWidth(curPageSize.getWidth()); //页面宽度
  50.         item.setPageHeight(curPageSize.getHeight()); //页面高度
  51.         item.setX(boundingRectange.x);
  52.         item.setY(boundingRectange.y);
  53.         item.setRectangeWidth(boundingRectange.getWidth());  //当前块级元素占的宽度
  54.         item.setRectangeHeight(boundingRectange.getHeight()); //当前块级元素占的高度
  55.         if(content!=null && content!=""){
  56.             if(content.equalsIgnoreCase(keyword)) {
  57.                 matches.add(item);
  58.             }
  59.         }
  60.         allItems.add(item);//先保存所有的项
  61.     }
  62.  
  63.  
  64.     public void endTextBlock() {
  65.         //do nothing
  66.     }
  67.  
  68.  
  69.     public void renderImage(ImageRenderInfo renderInfo) {
  70.         //do nothing
  71.     }
  72.  
  73.  
  74.     /**
  75.      * 设置需要匹配的当前页
  76.      * @param pageNumber
  77.      */
  78.     public void setPageNumber(Integer pageNumber) {
  79.         this.pageNumber = pageNumber;
  80.     }
  81.  
  82.  
  83.     /**
  84.      * 设置需要匹配的关键字，忽略大小写
  85.      * @param keyword
  86.      */
  87.     public void setKeyword(String keyword) {
  88.         this.keyword = keyword;
  89.     }
  90.  
  91.  
  92.     /**
  93.      * 返回匹配的结果列表
  94.      * @return
  95.      */
  96.     public List getMatches() {
  97.         return matches;
  98.     }
  99.  
  100.  
  101.     void setCurPageSize(Rectangle rect) {
  102.         this.curPageSize = rect;
  103.     }
  104.  
  105.  
  106.     public List getAllItems() {
  107.         return allItems;
  108.     }
  109.  
  110.  
  111.     public void setAllItems(List allItems) {
  112.         this.allItems = allItems;
  113.     }
  114. }


2.MatchItem 

代码如下（示例）：

  1. package com.z.boot.core.util.pdf;
  2.  
  3. /**
  4.  * @ClassName MatchItem
  5.  * @Description
  6.  * @Date: 2021/3/17 16:57
  7.  * @Version 1.0
  8.  **/
  9. public class MatchItem {
  10.     private Integer pageNum;
  11.     private Float x;
  12.     private Float y;
  13.     private Float pageWidth;
  14.     private Float pageHeight;
  15.     private String content;
  16.     private double rectangeWidth; //块级元素宽度
  17.     private double rectangeHeight; //块级元素高度
  18.  
  19.  
  20.     public Integer getPageNum() {
  21.         return pageNum;
  22.     }
  23.     public void setPageNum(Integer pageNum) {
  24.         this.pageNum = pageNum;
  25.     }
  26.     public Float getX() {
  27.         return x;
  28.     }
  29.     public void setX(Float x) {
  30.         this.x = x;
  31.     }
  32.     public Float getY() {
  33.         return y;
  34.     }
  35.     public void setY(Float y) {
  36.         this.y = y;
  37.     }
  38.     public Float getPageWidth() {
  39.         return pageWidth;
  40.     }
  41.     public void setPageWidth(Float pageWidth) {
  42.         this.pageWidth = pageWidth;
  43.     }
  44.     public Float getPageHeight() {
  45.         return pageHeight;
  46.     }
  47.     public void setPageHeight(Float pageHeight) {
  48.         this.pageHeight = pageHeight;
  49.     }
  50.     public String getContent() {
  51.         return content;
  52.     }
  53.     public void setContent(String content) {
  54.         this.content = content;
  55.     }
  56.     public double getRectangeWidth() {
  57.         return rectangeWidth;
  58.     }
  59.     public void setRectangeWidth(double rectangeWidth) {
  60.         this.rectangeWidth = rectangeWidth;
  61.     }
  62.     public double getRectangeHeight() {
  63.         return rectangeHeight;
  64.     }
  65.     public void setRectangeHeight(double rectangeHeight) {
  66.         this.rectangeHeight = rectangeHeight;
  67.     }
  68.  
  69.     @Override
  70.     public String toString() {
  71.         return "MatchItem [pageNum=" + pageNum + ", x=" + x + ", y=" + y
  72.                 + ", pageWidth=" + pageWidth + ", pageHeight=" + pageHeight
  73.                 + ", content=" + content + "]";
  74.     }
  75. }

二、核心计算类

  1. package com.z.boot.core.util.pdf;
  2.  
  3. import com.itextpdf.text.Rectangle;
  4. import com.itextpdf.text.pdf.PdfReader;
  5. import com.itextpdf.text.pdf.parser.PdfReaderContentParser;
  6. import lombok.extern.slf4j.Slf4j;
  7.  
  8. import java.io.IOException;
  9. import java.util.List;
  10.  
  11.  
  12. /**
  13.  * @ClassName QuotationPdf
  14.  * @Description
  15.  * @Date: 2021/3/16 10:44
  16.  * @Version 1.0
  17.  **/
  18. @Slf4j
  19. public class QuotationPdf {
  20.  
  21.     /**
  22.      * @param filepath
  23.      * @param keyWords
  24.      * @return float[]
  25.      * @Date 2021/3/17 16:57
  26.      * @Description 用于供外部类调用获取关键字所在PDF文件坐标
  27.      * @Version 1.0
  28.      */
  29.     public static MatchItem getKeyWordsByPath(String filepath, String keyWords) throws Exception {
  30.         try {
  31.             PdfReader pdfReader = new PdfReader(filepath);
  32.             int pageCount= pdfReader.getNumberOfPages();
  33.             return matchPage(pdfReader,pageCount, keyWords);
  34.         } catch (IOException e) {
  35.             e.printStackTrace();
  36.             return null;
  37.         }
  38.     }
  39.  
  40.     /**
  41.      * 在文件中寻找指定的文字内容
  42.      *
  43.      * @param reader
  44.      * @param pageNumber
  45.      * @param keyword
  46.      * @return
  47.      * @throws Exception
  48.      */
  49.     public static MatchItem matchPage(PdfReader reader,
  50.                                       Integer pageNumber, String keyword) throws Exception {
  51.         MatchItem matchItem = null;
  52.         PdfReaderContentParser parse = new PdfReaderContentParser(reader);
  53.         KeyWordPositionListener renderListener = new KeyWordPositionListener();
  54.         renderListener.setKeyword(keyword);
  55.         int page = 0;
  56.         for (page = 1; page <= pageNumber; page++) {
  57.             renderListener.setPageNumber(page);
  58.             Rectangle rectangle = reader.getPageSize(page);
  59.             renderListener.setCurPageSize(rectangle);
  60.             parse.processContent(page, renderListener);
  61.             matchItem = findKeywordItems(renderListener, keyword);
  62.             if(null != matchItem) {
  63.                 matchItem.setPageNum(page);
  64.                 break;
  65.             }
  66.         }
  67.         reader.close();
  68.         return matchItem;
  69.     }
  70.  
  71.     /**
  72.      * 找到匹配的关键词块
  73.      *
  74.      * @param renderListener
  75.      * @param keyword
  76.      * @return
  77.      */
  78.     public static MatchItem findKeywordItems(KeyWordPositionListener renderListener,
  79.                                              String keyword) {
  80.         // 先判断本页中是否存在关键词
  81.         List allItems = renderListener.getAllItems();// 所有块LIST
  82.         StringBuilder sbtemp = new StringBuilder("");
  83.         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)
  84.             sbtemp.append(((MatchItem) allItems.get(i)).getContent());
  85.         }
  86.         int index  = sbtemp.toString().indexOf(keyword);
  87.         System.out.println(sbtemp.toString());
  88.         if (index == -1) {// 一页组成的字符串没有关键词，直接return
  89.             return null;
  90.         }
  91.         //获取关键词与块内容完全匹配的项
  92.         List matches = renderListener.getMatches();
  93.         if(null == matches || matches.size()<=0){
  94.             //不存在，取本页中连续 拼接块内容 第一个关键字的位置
  95.             //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
  96.             sbtemp = new StringBuilder("");
  97.             for (int i = 0; i < allItems.size(); i++) {
  98.                 sbtemp.append(((MatchItem) allItems.get(i)).getContent());
  99.                 if(sbtemp.toString().length() >= index+1){
  100.                     matches.add(allItems.get(i));
  101.                     break;
  102.                 }
  103.             }
  104.         }
  105. //第二种方式，跟上面是一样的，可以自行研究
  106. //        if(null == matches || matches.size()<=0){
  107. //            //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
  108. //            //1.若关键字包含context继续拼接；2.若关键字等于context即找到
  109. //            sbtemp = new StringBuffer("");
  110. //            int ItmeIndex = 0; //块级元素计数器
  111. //            for (int i = 0; i < allItems.size(); i++) {
  112. //                String itemText = ((MatchItem) allItems.get(i)).getContent();
  113. //                sbtemp.append(itemText);
  114. //                if(keyword.contains(sbtemp.toString()) ){
  115. //
  116. //                }else if(keyword.equals(sbtemp.toString())){
  117. //                    matches.add(allItems.get(i));
  118. //                    break;
  119. //                }else if(sbtemp.toString().contains(keyword)){
  120. //                    //被块元素包含
  121. //                    int index1 = itemText.indexOf(keyword);
  122. //                    double rectangeWidth = ((MatchItem) allItems.get(i)).getRectangeWidth(); //块级元素的宽度
  123. //                    double oneWidth = rectangeWidth/itemText.length(); //单个字体的宽度
  124. //                    double finalWidth = (index1+Math.rint(keyword.length()/2) ) * oneWidth + ((MatchItem) allItems.get(i)).getX();
  125. //                    ((MatchItem) allItems.get(i)).setX((float) finalWidth);
  126. //                    matches.add(allItems.get(i));
  127. //                    break;
  128. //                }else{
  129. //                    sbtemp = new StringBuffer("");
  130. //                }
  131. //            }
  132. //        }
  133.         if(null != matches && matches.size()>0){
  134.             return (MatchItem) matches.get(0);
  135.         }else{
  136.             return null;
  137.         }
  138.     }
  139.  
  140.     /**
  141.      * @param filepath
  142.      * @return float[]
  143.      * @Date 18:24 2020/3/7
  144.      * @Description 用于供外部类获取PDF高度和宽度
  145.      */
  146.     public static float[] getWidthAndHeightByPath(String filepath, int page) {
  147.         float[] coordinate = null;
  148.         try {
  149.             PdfReader pdfReader = new PdfReader(filepath);
  150.             Rectangle pageSize = pdfReader.getPageSize(page);
  151.             float height = pageSize.getHeight();
  152.             float width = pageSize.getWidth();
  153.             System.out.println("width = " + width + ", height = " + height);
  154.             float[] coordinate1 = {width, height};
  155.             pdfReader.close();
  156.             return coordinate1;
  157. //            Document document = new Document(pdfReader.getPageSize(1));
  158. 			Document document = new Document(PageSize.A4.rotate(), 0, 0, 30, 0);
  159. //            // 获取页面宽度
  160. //            float widths = document.getPageSize().getWidth();
  161. //            // 获取页面高度
  162. //            float heights = document.getPageSize().getHeight();
  163. //            System.out.println("widths = "+widths+", heights = "+heights);
  164.         } catch (IOException e) {
  165.             e.printStackTrace();
  166.             return coordinate;
  167.         }
  168.     }
  169.  
  170.     public static void main(String[] args) throws Exception {
  171.         String filePath = "E:\\work\\bin\\wenlinworkspace\\repository\\laboratoryFile\\message\\wordtemp\\2020-12-14\\8ae123961e5d47faa4acee6d066efcf7.pdf";
  172.         MatchItem a = getKeyWordsByPath(filePath, "bm_g_12443_1#_ResultData_32");
  173.         System.out.println("width = " + a.getX()
  174.                 + ", height = " + a.getY()
  175.                 + ",page = " + a.getPageNum());
  176. //
  177. //        float[] b = getWidthAndHeightByPath(filePath, Integer.parseInt(a.get("page").toString()));
  178.         System.out.println(a.getPageWidth()+"-----"+a.getPageHeight());
  179.         float x = (a.getX() - 35F) / a.getPageWidth();
  180.         float y = (a.getY() - 52.5F) / a.getPageHeight();
  181.         System.out.println("x = " + x + ", y = " + y);
  182.     }
  183.  
  184. }
  185.

三、使用 

  1. public static void main(String[] args) throws Exception {
  2.         String filePath = "E:\\work\\bin\\wenlinworkspace\\repository\\laboratoryFile\\message\\wordtemp\\2020-12-14\\8ae123961e5d47faa4acee6d066efcf7.pdf";
  3.         MatchItem a = getKeyWordsByPath(filePath, "bm_g_12443_1#_ResultData_32");
  4.         System.out.println("width = " + a.getX()
  5.                 + ", height = " + a.getY()
  6.                 + ",page = " + a.getPageNum());
  7. //
  8. //        float[] b = getWidthAndHeightByPath(filePath, Integer.parseInt(a.get("page").toString()));
  9.         System.out.println(a.getPageWidth()+"-----"+a.getPageHeight());
  10.         float x = (a.getX() - 35F) / a.getPageWidth();
  11.         float y = (a.getY() - 52.5F) / a.getPageHeight();
  12.         System.out.println("x = " + x + ", y = " + y);
  13.     }
  1. MatchItem position = QuotationPdf.getKeyWordsByPath(pdfPath,"合同章_01");
  2. //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
  3. //页面比例 需自行计算

声明：本文内容由网友自发贡献，转载请注明出处：【wpsshop】
推荐阅读
相关标签

Copyright © 2003-2013 www.wpsshop.cn 版权所有，并保留所有权利。

  

闽ICP备14008679号