├── img
    ├── 1.png
    ├── 2.png
    ├── 3.png
    ├── 4.png
    └── 5.png
├── pom.xml
├── src
    └── main
    │   └── java
    │       └── com
    │           └── doccon
    │               └── Tool
    │                   ├── SQLTool.java
    │                   └── pdf2md.java
└── README.md


/img/1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HOUYULIN/DocCon/HEAD/img/1.png


--------------------------------------------------------------------------------
/img/2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HOUYULIN/DocCon/HEAD/img/2.png


--------------------------------------------------------------------------------
/img/3.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HOUYULIN/DocCon/HEAD/img/3.png


--------------------------------------------------------------------------------
/img/4.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HOUYULIN/DocCon/HEAD/img/4.png


--------------------------------------------------------------------------------
/img/5.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/HOUYULIN/DocCon/HEAD/img/5.png


--------------------------------------------------------------------------------
/pom.xml:
--------------------------------------------------------------------------------
 1 | <?xml version="1.0" encoding="UTF-8"?>
 2 | <project xmlns="http://maven.apache.org/POM/4.0.0"
 3 |          xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
 4 |          xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 5 |     <modelVersion>4.0.0</modelVersion>
 6 | 
 7 |     <groupId>org.example</groupId>
 8 |     <artifactId>DocCon</artifactId>
 9 |     <version>1.0-SNAPSHOT</version>
10 | 
11 |     <properties>
12 |         <maven.compiler.source>8</maven.compiler.source>
13 |         <maven.compiler.target>8</maven.compiler.target>
14 |     </properties>
15 | 
16 |     <dependencies>
17 |         <dependency>
18 |             <groupId>org.apache.pdfbox</groupId>
19 |             <artifactId>pdfbox</artifactId>
20 |             <version>2.0.4</version>
21 |         </dependency>
22 |         <dependency>
23 |             <groupId>net.coobird</groupId>
24 |             <artifactId>thumbnailator</artifactId>
25 |             <version>0.4.8</version>
26 |         </dependency>
27 |     </dependencies>
28 | </project>


--------------------------------------------------------------------------------
/src/main/java/com/doccon/Tool/SQLTool.java:
--------------------------------------------------------------------------------
 1 | package com.doccon.Tool;
 2 | 
 3 | import java.util.ArrayList;
 4 | import java.util.List;
 5 | import java.util.Scanner;
 6 | 
 7 | public class SQLTool {
 8 |     public static void main(String[] args) {
 9 |         Scanner sc = new Scanner(System.in);
10 |         String line = "";
11 |         List<String> result = new ArrayList<>();
12 |         System.out.println();
13 |         result.add("CREATE TABLE `author` (");
14 |         while (!"end".equals(line = sc.nextLine())) {
15 |             String s = "";
16 |             String[] split = line.split("\t");
17 |             for (int i =0;i<split.length;i++){
18 |                 if(i==0){
19 |                     s+="`"+split[i]+"` ";
20 |                 }else if(i==1){
21 |                     if(split[0].equals("create_by_id")){
22 |                         s+="bigint(20) unsigned"+split[i];
23 |                     }else {
24 |                         s+=split[i];
25 |                     }
26 | 
27 |                 }else if(i==2){
28 |                     s+=" COMMENT '"+split[i]+"',";
29 |                 }
30 | 
31 |             }
32 |             result.add(s);
33 |         }
34 |         result.add(") ENGINE=InnoDB AUTO_INCREMENT=3 DEFAULT CHARSET=utf8mb4 COMMENT='作者表';");
35 |         for(String str:result){
36 |             System.out.println(str);
37 |         }
38 |     }
39 | }
40 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # DocumentConversion
 2 | 
 3 | # 1.介绍
 4 | 
 5 | java文档转换工具。 
 6 | 
 7 | 目前已实现： pdf转md(pdf转markdown：能够将pdf格式的文件转换成markdown格式的文件，支持同步同时转换图片和文本。)；
 8 | 
 9 | ## 1.1实现功能：pdf转换md
10 | 
11 | ## 1.2存在问题：
12 |     1.图片和文本错位
13 | 
14 |     2.无法处理代码块和表格等。
15 | 
16 | ## 1.3转换D:\pdf\day1.pdf文件的效果：
17 | 
18 | ### 1.3.1转换后的目录结构：
19 | 
20 | ![输入图片说明](https://images.gitee.com/uploads/images/2021/0115/093958_d361d6d2_1012259.png "屏幕截图.png")
21 | 
22 | ### 1.3.2转换后的md文档效果：
23 | 
24 | ![输入图片说明](https://images.gitee.com/uploads/images/2021/0115/094142_46370529_1012259.png "屏幕截图.png")
25 | 
26 | 
27 | # 2.软件架构
28 | 
29 | pom.xml文件
30 | 
31 | 引入pdfbox,thumbnailator文档处理jar包
32 | 
33 | 
34 | # 3.使用说明
35 | 
36 | ## 3.1引入项目
37 | ![输入图片说明](https://images.gitee.com/uploads/images/2021/0115/093309_d80acfc5_1012259.png "屏幕截图.png")
38 | ## 3.2刷新maven
39 | ![输入图片说明](https://images.gitee.com/uploads/images/2021/0115/093239_62a5ddb9_1012259.png "屏幕截图.png")
40 | ## 3.3pdf2md.java文件输入要转换pdf文件路径
41 | ![输入图片说明](https://images.gitee.com/uploads/images/2021/0115/093438_ef46b033_1012259.png "屏幕截图.png")
42 | ## 3.4右键运行
43 | 
44 | 
45 | 
46 | 
47 | 
48 | #### 特技
49 | 
50 | 1.  使用 Readme\_XXX.md 来支持不同的语言，例如 Readme\_en.md, Readme\_zh.md
51 | 2.  Gitee 官方博客 [blog.gitee.com](https://blog.gitee.com)
52 | 3.  你可以 [https://gitee.com/explore](https://gitee.com/explore) 这个地址来了解 Gitee 上的优秀开源项目
53 | 4.  [GVP](https://gitee.com/gvp) 全称是 Gitee 最有价值开源项目，是综合评定出的优秀开源项目
54 | 5.  Gitee 官方提供的使用手册 [https://gitee.com/help](https://gitee.com/help)
55 | 6.  Gitee 封面人物是一档用来展示 Gitee 会员风采的栏目 [https://gitee.com/gitee-stars/](https://gitee.com/gitee-stars/)
56 | 


--------------------------------------------------------------------------------
/src/main/java/com/doccon/Tool/pdf2md.java:
--------------------------------------------------------------------------------
  1 | package com.doccon.Tool;
  2 | 
  3 | import net.coobird.thumbnailator.Thumbnails;
  4 | import org.apache.pdfbox.cos.COSName;
  5 | import org.apache.pdfbox.pdmodel.PDDocument;
  6 | import org.apache.pdfbox.pdmodel.PDPage;
  7 | import org.apache.pdfbox.pdmodel.PDResources;
  8 | import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
  9 | import org.apache.pdfbox.text.PDFTextStripper;
 10 | 
 11 | import java.io.*;
 12 | import java.util.Iterator;
 13 | import java.util.regex.Pattern;
 14 | 
 15 | 
 16 | /**
 17 |  * pdf文件转md
 18 |  */
 19 | public class pdf2md {
 20 | 
 21 | 
 22 | 
 23 |     public static void main(String[] args) throws IOException {
 24 |         //输入要转换的pdf文件
 25 |         String pdfFileName = "D:\\pdf\\day1.pdf";
 26 | 
 27 |         String filename = "";
 28 |         String[] files = pdfFileName.split("\\\\");
 29 |         for (int z=0;z<files.length-1;z++) {
 30 |             filename= filename+files[z]+"\\";
 31 |         }
 32 |         filename=filename+"img";
 33 | 
 34 |         File srcFolder = new File(filename);
 35 |         if(!srcFolder.exists()){//如果文件夹不存在
 36 |             srcFolder.mkdir();//创建文件夹
 37 |         }
 38 |         //转换后的md文件
 39 |         String docFileName = pdfFileName.substring(0, pdfFileName.lastIndexOf(".")) + ".md";
 40 | 
 41 |         //判断是否为空
 42 |         File file = new File(docFileName);
 43 |         if (!file.exists()) {
 44 |             file.createNewFile();
 45 |         }
 46 | 
 47 |         //创建输出流对象,true文档末尾写入，防止覆盖
 48 |         FileOutputStream fos = new FileOutputStream(docFileName, true);
 49 | 
 50 |         //通过PDDocument将pdf文件解析
 51 |         PDDocument pdf = PDDocument.load(new File(pdfFileName));
 52 | 
 53 |         //获取pdf文件的页数
 54 |         int pageNumber = pdf.getNumberOfPages();
 55 | 
 56 |         //提取每一页的图片和文字，添加到 word 中
 57 |         for (int i = 0; i < pageNumber; i++) {
 58 |             //图片处理
 59 |             PDPage page = pdf.getPage(i);
 60 |             PDResources resources = page.getResources();
 61 | 
 62 |             Iterable<COSName> names = resources.getXObjectNames();
 63 | 
 64 |             //迭代器遍历
 65 |             Iterator<COSName> iterator = names.iterator();
 66 |             while (iterator.hasNext()) {
 67 |                 COSName cosName = iterator.next();
 68 | 
 69 | 
 70 | 
 71 | 
 72 |                 if (resources.isImageXObject(cosName)) {
 73 |                     PDImageXObject imageXObject = (PDImageXObject) resources.getXObject(cosName);
 74 | 
 75 |                     //图片路径
 76 |                     String timeimg = "\\"+System.currentTimeMillis() + "";
 77 |                     String img = filename + timeimg + ".jpg";
 78 |                     //创建img文件
 79 |                     File outImgFile = new File(img);
 80 |                     //图片写入img文件
 81 |                     Thumbnails.of(imageXObject.getImage()).scale(0.9).rotate(0).toFile(outImgFile);
 82 | 
 83 |                     //缩放图片
 84 |                     /*BufferedImage bufferedImage = ImageIO.read(outImgFile);
 85 |                     int width = bufferedImage.getWidth();
 86 |                     int height = bufferedImage.getHeight();
 87 |                     if (width > 600) {
 88 |                         double ratio = Math.round((double) width / 550.0);
 89 |                         System.out.println("缩放比ratio：" + ratio);
 90 |                         width = (int) (width / ratio);
 91 |                         height = (int) (height / ratio);
 92 | 
 93 |                     }else{
 94 | 
 95 |                     }
 96 |                      */
 97 | 
 98 | 
 99 |                     //图片写入输入流
100 |                     FileInputStream in = new FileInputStream(outImgFile);
101 |                     byte[] ba = new byte[in.available()];
102 |                     in.read(ba);
103 |                     ByteArrayInputStream byteInputStream = new ByteArrayInputStream(ba);
104 | 
105 |                     //图片路径
106 |                     String url = "![img](img/" + timeimg + ".jpg)";
107 |                     byte[] urlby = url.getBytes();
108 |                     fos.write("\r\n".getBytes());
109 |                     fos.write(urlby);
110 |                 }
111 |             }
112 | 
113 | 
114 |             //pdf文本处理
115 | 
116 |             //创建pdf文档处理对象
117 |             PDFTextStripper stripper = new PDFTextStripper();
118 |             stripper.setSortByPosition(true);
119 |             stripper.setStartPage(i);
120 |             stripper.setEndPage(i);
121 |             //当前页中的文字
122 |             String text = stripper.getText(pdf);
123 |             System.out.println(text);
124 | 
125 |             //将每一行分成string字段
126 |             String[] split = text.split("\\r\\n");
127 |             String dl = "";
128 |             int status = 1;
129 |             //正则判断每一行是否首页字段
130 |             for (int x = 0; x < split.length; x++) {
131 |                 if (Pattern.matches("^[0-9].[0-9].[0-9].[0-9][\\s\\S]*", split[x])) {
132 |                     String[] spl = split[x].split("\\.");
133 |                     dl = "#### " + spl[spl.length-2]+"\\."+ spl[spl.length-1];
134 |                 } else if (Pattern.matches("^[0-9].[0-9].[0-9][\\s\\S]*", split[x])) {
135 |                     String[] spl = split[x].split("\\.");
136 |                     dl = "### " + spl[spl.length-1];
137 |                 } else if (Pattern.matches("^[0-9].[0-9].[\\s\\S]*", split[x])) {
138 |                     dl = "## " + split[x];
139 |                 } else if (Pattern.matches("^[0-9] [\\s\\S]*", split[x])) {
140 |                     dl = "# " + split[x];
141 |                 } else {
142 | 
143 |                     //以：（开头，或者以）结尾，且汉字长度不超过10的行：
144 |                     if(Pattern.matches("[\\s\\S]*[：]$|[\\s\\S]*[：] $|^（[\\s\\S]*|[\\s\\S]*[）]$|[\\s\\S]*[）] $",split[x])&&split[x].length()<=30){
145 |                         split[x]= "\n"+"**"+split[x]+"**"+"\n";
146 |                     }else if(Pattern.matches("[\\s\\S]*[：；]$|[\\s\\S]*[：；] $",split[x])){
147 |                         split[x]= split[x]+"\n\n";
148 |                     }
149 |                     dl = split[x];
150 |                     status = 2;
151 |                 }
152 | 
153 |                 //写入输出流
154 |                 byte[] bytes = dl.getBytes();
155 | 
156 | 
157 |                 //判断是否换行
158 |                 //status:2非标题， 正则表达式最后非以：。结尾
159 |                 if (status == 2 && !Pattern.matches("[\\s\\S]*[。：]$", dl)) {
160 |                     fos.write(bytes);
161 |                 } else {
162 |                     //以[#]开头[:,: ]结尾必须换行^（[\s\S]*|[\s\S]*[）]$
163 |                     if (Pattern.matches("^#[\\s\\S]*", dl) ) {
164 |                         fos.write("\r\n".getBytes());
165 |                         fos.write(bytes);
166 |                         fos.write("\r\n".getBytes());
167 |                     } else {
168 |                         fos.write(bytes);
169 |                         //换行
170 |                         fos.write("\r\n".getBytes());
171 |                         fos.write("\n".getBytes());
172 |                     }
173 | 
174 | 
175 |                 }
176 |                 //重置参数
177 |                 status = 1;
178 | 
179 |             }
180 |         }
181 |         fos.close();
182 |         pdf.close();
183 |         System.out.println("pdf转md转换解析结束！！----");
184 |     }
185 | 
186 | 
187 | }
188 | 


--------------------------------------------------------------------------------