Java implementation of Word/Pdf/TXT to html

Keywords: Java Apache xml encoding

introduction:

Recently, the company is working on an education, training, learning and online examination project. I am mainly engaged in the online course module, mainly doing the course classification, course, courseware creation and online learning and statistical functions, because courseware involves many types, such as video, audio, graphics and text, external links and document types. Among them, there is a problem, that is, the document courseware course is on the web page Display and learning problems, because online statistical learning courses, learning personnel, learning time is long, so we can't download documents to local learning as the traditional method, so it's not under the control of the system, so the final solution is that when uploading document courseware, the corresponding files are converted into HTML files, so that we can browse and learn on the web page

The following is mainly for the conversion of word,pdf and txt text files

1: Java implementation transforms word into html

1: introduce dependency

 1 <dependency>
 2   <groupId>fr.opensagres.xdocreport</groupId>
 3   <artifactId>fr.opensagres.xdocreport.document</artifactId>
 4   <version>1.0.5</version>
 5 </dependency>
 6 <dependency> 
 7   <groupId>fr.opensagres.xdocreport</groupId> 
 8   <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId> 
 9   <version>1.0.5</version> 
10 </dependency>
11   <dependency>
12   <groupId>org.apache.poi</groupId>
13   <artifactId>poi</artifactId>
14   <version>3.12</version>
15 </dependency>
16 <dependency>
17   <groupId>org.apache.poi</groupId>
18   <artifactId>poi-scratchpad</artifactId>
19   <version>3.12</version>
20 </dependency>

2: code demo

 

  1 package com.svse.controller;
  2 
  3 import javax.xml.parsers.DocumentBuilderFactory;
  4 import javax.xml.parsers.ParserConfigurationException;
  5 import javax.xml.transform.OutputKeys;
  6 import javax.xml.transform.Transformer;
  7 import javax.xml.transform.TransformerException;
  8 import javax.xml.transform.TransformerFactory;
  9 import javax.xml.transform.dom.DOMSource;
 10 import javax.xml.transform.stream.StreamResult;
 11 
 12 import org.apache.poi.hwpf.HWPFDocument;
 13 import org.apache.poi.hwpf.converter.PicturesManager;
 14 import org.apache.poi.hwpf.converter.WordToHtmlConverter;
 15 import org.apache.poi.hwpf.usermodel.PictureType;
 16 import org.apache.poi.xwpf.converter.core.BasicURIResolver;
 17 import org.apache.poi.xwpf.converter.core.FileImageExtractor;
 18 import org.apache.poi.xwpf.converter.core.FileURIResolver;
 19 import org.apache.poi.xwpf.converter.core.IURIResolver;
 20 import org.apache.poi.xwpf.converter.core.IXWPFConverter;
 21 import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
 22 import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
 23 import org.apache.poi.xwpf.usermodel.XWPFDocument;
 24 /**
 25  * word Convert to html
 26  */
 27 public class TestWordToHtml {
 28 
 29     public static  final String STORAGEPATH="C://works//files//";
 30     public static  final String IP="192.168.30.222";
 31     public static  final String PORT="8010";
 32     public static void main(String[] args) throws IOException, TransformerException, ParserConfigurationException {
 33         TestWordToHtml wt=new TestWordToHtml();
 34         //wt.Word2003ToHtml("Textual research on Oracle Bone Inscriptions.doc");
 35         wt.Word2007ToHtml("Textual research on Oracle Bone Inscriptions.docx");
 36 
 37     }
 38       
 39      /**
 40      * 2003 Version word to html
 41      * @throws IOException
 42      * @throws TransformerException
 43      * @throws ParserConfigurationException
 44      */
 45     public void Word2003ToHtml(String fileName) throws IOException, TransformerException, ParserConfigurationException {
 46        
 47         final String imagepath = STORAGEPATH+"fileImage/";//When parsing, if doc Pictures in the file will be saved in this path
 48         final String strRanString=getRandomNum();
 49         String filepath =STORAGEPATH;
 50         String htmlName =fileName.substring(0, fileName.indexOf("."))+ "2003.html";
 51         final String file = filepath + fileName;
 52         InputStream input = new FileInputStream(new File(file));
 53         HWPFDocument wordDocument = new HWPFDocument(input);
 54         WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
 55         //Set where pictures are stored
 56         wordToHtmlConverter.setPicturesManager(new PicturesManager() {
 57             public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
 58                 File imgPath = new File(imagepath);
 59                 if(!imgPath.exists()){//Create if picture directory does not exist
 60                     imgPath.mkdirs();
 61                 }
 62                 
 63                 File file = new File(imagepath +strRanString+suggestedName);
 64                 try {
 65                     OutputStream os = new FileOutputStream(file);
 66                     os.write(content);
 67                     os.close();
 68                 } catch (FileNotFoundException e) {
 69                     e.printStackTrace();
 70                 } catch (IOException e) {
 71                     e.printStackTrace();
 72                 }
 73                 
 74                 return  "http://"+IP+":"+PORT+"//uploadFile/fileImage/"+strRanString+suggestedName;
 75                // return imagepath +strRanString+suggestedName;
 76             }
 77         });
 78         
 79         //analysis word file
 80         wordToHtmlConverter.processDocument(wordDocument);
 81         Document htmlDocument = wordToHtmlConverter.getDocument();
 82         
 83         File htmlFile = new File(filepath +strRanString+htmlName);
 84         OutputStream outStream = new FileOutputStream(htmlFile);
 85         
 86 
 87         DOMSource domSource = new DOMSource(htmlDocument);
 88         StreamResult streamResult = new StreamResult(outStream);
 89 
 90         TransformerFactory factory = TransformerFactory.newInstance();
 91         Transformer serializer = factory.newTransformer();
 92         serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
 93         serializer.setOutputProperty(OutputKeys.INDENT, "yes");
 94         serializer.setOutputProperty(OutputKeys.METHOD, "html");
 95         
 96         serializer.transform(domSource, streamResult);
 97         outStream.close();
 98         
 99         System.out.println("generate html File path:"+ "http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
100     }
101 
102     /**
103      * 2007 Version word to html
104      * @throws IOException
105      */
106     public void Word2007ToHtml(String fileName) throws IOException {
107         
108        final String strRanString=getRandomNum();
109         
110         String filepath = STORAGEPATH+strRanString;
111         String htmlName =fileName.substring(0, fileName.indexOf("."))+ "2007.html";
112         File f = new File(STORAGEPATH+fileName);  
113         if (!f.exists()) {  
114             System.out.println("Sorry File does not Exists!");  
115         } else {  
116             if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {  
117                 try {
118                     // 1) load word Document generation XWPFDocument object  
119                     InputStream in = new FileInputStream(f);  
120                     XWPFDocument document = new XWPFDocument(in);  
121       
122                     // 2) analysis XHTML To configure (Set here IURIResolver To set the directory where pictures are stored)  
123                     File imageFolderFile = new File(filepath);  
124                     XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));  
125                     options.setExtractor(new FileImageExtractor(imageFolderFile));  
126                     options.URIResolver(new IURIResolver() {
127                         public String resolve(String uri) {
128                             //http://192.168.30.222:8010//uploadFile/....
129                             return "http://"+IP+":"+PORT+"//uploadFile/"+strRanString +"/"+ uri;
130                         }
131                     });
132                     
133                     options.setIgnoreStylesIfUnused(false);  
134                     options.setFragment(true);  
135                       
136                     // 3) take XWPFDocument convert to XHTML  
137                     OutputStream out = new FileOutputStream(new File(filepath + htmlName));  
138                     IXWPFConverter<XHTMLOptions> converter = XHTMLConverter.getInstance();
139                     converter.convert(document,out, options);
140                     //XHTMLConverter.getInstance().convert(document, out, options);  
141                     System.out.println("html route:"+"http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
142                 } catch (Exception e) {
143                     e.printStackTrace();
144                 }
145             
146             } else {  
147                 System.out.println("Enter only MS Office 2007+ files");  
148             }  
149         }  
150     }  
151 
152      /**
153      *Function Description: generate time stamp
154      *Created by: zsq
155      *Creation time: 2:37:09 PM, December 7, 2019
156      *
157      */
158      public static String getRandomNum(){
159          Date dt = new Date();
160          SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmss");  
161          String str=sdf.format(dt);
162          return str;
163      }
164      
165    } 

2: Java implementation converts Pdf to html

1: introduce dependency

 1 <dependency>
 2             <groupId>net.sf.cssbox</groupId>
 3             <artifactId>pdf2dom</artifactId>
 4             <version>1.7</version>
 5         </dependency> 
 6         <dependency>
 7             <groupId>org.apache.pdfbox</groupId>
 8             <artifactId>pdfbox</artifactId>
 9             <version>2.0.12</version>
10         </dependency>
11         <dependency>
12             <groupId>org.apache.pdfbox</groupId>
13             <artifactId>pdfbox-tools</artifactId>
14             <version>2.0.12</version>
15  </dependency>
16         

2: Code Demo

 1 public class PdfToHtml {
 2 
 3   /*
 4     pdf Transform html
 5      */
 6     public void pdfToHtmlTest(String inPdfPath,String outputHtmlPath)  {
 7        // String outputPath = "C:\\works\\files\\ZSQ Secret knowledge test question bank.html";
 8     9        //try() Written in()It will automatically shut down the flow
10         try{
11             BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputHtmlPath)),"utf-8"));
12             //load PDF file
13             //PDDocument document = PDDocument.load(bytes);
14             PDDocument document = PDDocument.load(new File(inPdfPath));
15             PDFDomTree pdfDomTree = new PDFDomTree();
16             pdfDomTree.writeText(document,out);
17         } catch (Exception e) {
18             e.printStackTrace();
19         }
20     }
21 
22     public static void main(String[] args) throws IOException {
23         PdfToHtml ph=new PdfToHtml();
24         String pdfPath="C:\\works\\files\\Administrative attendance system of Wuhan Research Center.pdf";
25         String outputPath="C:\\works\\files\\Administrative attendance system of Wuhan Research Center.html";
26         ph.pdfToHtmlTest(pdfPath,outputPath);
27   }
28 
29 }

3: Java implementation converts TXT to html

 1  /*
 2      * txt Document to html
 3        filePath:txt Original file path
 4        htmlPosition:html path generated after conversion
 5     */
 6     public static void txtToHtml(String filePath, String htmlPosition) {
 7         try {
 8             //String encoding = "GBK";
 9             File file = new File(filePath);
10             if (file.isFile() && file.exists()) { // Judge whether the file exists
11                 InputStreamReader read = new InputStreamReader(new FileInputStream(file), "GBK");
12                 // Considering the encoding format
13                 BufferedReader bufferedReader = new BufferedReader(read);
14                 // Write file
15                 FileOutputStream fos = new FileOutputStream(new File(htmlPosition));
16                 OutputStreamWriter osw = new OutputStreamWriter(fos, "GBK");
17                 BufferedWriter bw = new BufferedWriter(osw);
18                 String lineTxt = null;
19                 while ((lineTxt = bufferedReader.readLine()) != null) {
20                     bw.write("&nbsp&nbsp&nbsp"+lineTxt + "</br>");
21                 }
22                 bw.close();
23                 osw.close();
24                 fos.close();
25                 read.close();
26             } else {
27                 System.out.println("The specified file could not be found");
28             }
29         } catch (Exception e) {
30             System.out.println("Error reading file content");
31             e.printStackTrace();
32         }
33     }

Posted by brianjw on Mon, 23 Dec 2019 07:17:51 -0800