Linux excel to html

First, use Jacob to transfer Word and Excel to html,pdf to HTML

Recent development encounters the need to upload users to Word, Excel, PDF format documents to achieve preview and download functions, download functions are relatively simple, here we mainly talk about the use of a Middleware — Jacob, through which you can call COM components and Win32 in java applications.
Library. The files in Word and Excel format are converted to HTML, and then displayed to the user for preview.

1. Download Jacob’s jar package first.

When using jacob, put dll under window/system 32, and no registration is required.
2. If the following error occurs
        com.jacob.com.ComFailException: A COM exception has been encountered: 
         At Invoke of: Version 
        Description: An unknown COM error has occured. 
This means that the version of the dll is incorrect, so replace it with the latest version.  
3. If the following error occurs
      no jacob in java.library.path 
      java.lang.UnsatisfiedLinkError: no jacob in java.library.path 
It means that you can put dll under path, set path or put it under window/system 32.

4.PDF to HTML uses a pdf2html.exe program to convert PDF to HTML

 
Links: http://blog.csdn.net/crazypandariy/article/details/17663731

5. There are many examples on the Internet. Here I mainly post the code I use.

package com.commons.yjkh.utils;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;

import  com.jacob.activeX.ActiveXComponent; 
import  com.jacob.com.Dispatch; 
import  com.jacob.com.Variant; 

public class JacobUtil   
{   
    public static final int WORD_HTML = 8;  
    public static final int WORD_TXT = 7;
    public static final int EXCEL_HTML = 44;   
    public static final int PDF_HTML = 17;
  
    /**  
     * WORD Turn HTML  
     * @param docfile WORD File full path  
     * @param htmlfile Transformed HTML Storage Path  
     */  
    public static void wordToHtml(String docfile, String htmlfile)   
    {   
    	// Start word
        ActiveXComponent app = new ActiveXComponent("Word.Application");   
        try  
        { //Setting word invisible
            app.setProperty("Visible", new Variant(false)); 
          Dispatch docs = app.getProperty("Documents").toDispatch();   
          //Open word file
            Dispatch doc = Dispatch.invoke(   
                    docs,   
                    "Open",   
                    Dispatch.Method,   
                    new Object[] { docfile, new Variant(false),   
                            new Variant(true) }, new int[1]).toDispatch();   
          //Save to temporary file as html format
            Dispatch.invoke(doc, "SaveAs", Dispatch.Method, new Object[] {   
                    htmlfile, new Variant(WORD_HTML) }, new int[1]);   
          Variant f = new Variant(false);   
          Dispatch.call(doc, "Close", f);   
        }   
        catch (Exception e)   
        {   
            e.printStackTrace();
        }   
        finally  
        {   
            app.invoke("Quit", new Variant[] {}); 
            html2utf(htmlfile);
            html2utfForJacob(htmlfile);
        }   
    }   
  
    /**  
     * EXCEL Turn HTML  
     * @param xlsfile EXCEL File full path  
     * @param htmlfile Transformed HTML Storage Path  
     */  
    public static void excelToHtml(String xlsfile, String htmlfile)   
    {   
        // Start excel
        ActiveXComponent app = new ActiveXComponent("Excel.Application");    
        try  
        {   
        	//Setting excel invisible
           app.setProperty("Visible", new Variant(false));   
          Dispatch excels = app.getProperty("Workbooks").toDispatch();  
            //Open excel file
            Dispatch excel = Dispatch.invoke(   
                    excels,   
                    "Open",   
                    Dispatch.Method,   
                    new Object[] { xlsfile, new Variant(false),   
                            new Variant(true) }, new int[1]).toDispatch();   
          //Save to temporary file as html format
            Dispatch.invoke(excel, "SaveAs", Dispatch.Method, new Object[] {   
                    htmlfile, new Variant(EXCEL_HTML) }, new int[1]);   
          Variant f = new Variant(false);   
          Dispatch.call(excel, "Close", f);   
        }   
        catch (Exception e)   
        {   
            e.printStackTrace();   
        }   
        finally  
        {   
            app.invoke("Quit", new Variant[] {});   
            html2utf(htmlfile);
            html2utfForJacob(htmlfile);
        }   
    }   
    
    
    /** 
     * PDF Turn HTML
     * Convert PDF file to html file by calling pdf2htmlEX
     * 
     * @param exeFilePath
     *            pdf2htmlEX.exe File path
     * @param pdfFile
     *            pdf File absolute path
     * @param [destDir] Generated html file storage path
     * @param htmlName
     *            Generated html file name
     * @return
     */
    public static boolean pdf2html(String exeFilePath, String pdfFile,
            String destDir, String htmlFileName) {
        if (!(exeFilePath != null && !"".equals(exeFilePath) && pdfFile != null
                && !"".equals(pdfFile) && htmlFileName != null && !""
                    .equals(htmlFileName))) {
            System.out.println("The parameters passed are incorrect!");
            return false;
        }
        Runtime rt = Runtime.getRuntime();
        StringBuilder command = new StringBuilder();
        command.append(exeFilePath).append(" ");
        if (destDir != null && !"".equals(destDir.trim()))// Generate file storage location, need to replace the space in file path
            command.append("--dest-dir ").append(destDir.replace(" ", "" ""))
                    .append(" ");
        command.append("--optimize-text 1 ");// Minimize the number of HTML elements used for text (default: 0)
        command.append("--zoom 1.4 ");
        command.append("--process-outline 0 ");// Display links in html: 0 - false, 1 - true
        command.append("--font-format woff ");// Font suffixes embedded in html (default ttf)
                                                // ttf,otf,woff,svg
        command.append(pdfFile.replace(" ", "" "")).append(" ");// Need to replace spaces in file paths
        if (htmlFileName != null && !"".equals(htmlFileName.trim())) {
            command.append(htmlFileName);
            if (htmlFileName.indexOf(".html") == -1)
                command.append(".html");
        }
        try {
            System.out.println("Command: " + command.toString());
            Process p = rt.exec(command.toString());
            StreamGobbler errorGobbler = new StreamGobbler(p.getErrorStream(),
                    "ERROR");
            // Open screen standard error stream
            errorGobbler.start();
            StreamGobbler outGobbler = new StreamGobbler(p.getInputStream(),
                    "STDOUT");
            // Open screen standard output stream
            outGobbler.start();
            int w = p.waitFor();
            int v = p.exitValue();
            if (w == 0 && v == 0) {
                return true;
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return false;
    }
    
    
    /**
     * linux Down PDF to HTML
     * @param pdfFile
     * @param destDir
     * @param htmlFileName
     * @return
     */
    public static boolean pdf2html_linux(String pdfFile, String destDir,
            String htmlFileName) {
        if (!(pdfFile != null && !"".equals(pdfFile) && htmlFileName != null && !""
                .equals(htmlFileName))) {
            System.out.println("The parameters passed are incorrect!");
            return false;
        }
        Runtime rt = Runtime.getRuntime();
        StringBuilder command = new StringBuilder();
        command.append("pdf2htmlEX").append(" ");
        if (destDir != null && !"".equals(destDir.trim()))// Generate file storage location, need to replace the space in file path
            command.append("--dest-dir ").append(destDir.replace(" ", "" ""))
                    .append(" ");
        command.append("--optimize-text 1 ");// Minimize the number of HTML elements used for text (default: 0)
        command.append("--process-outline 0 ");// Display links in html: 0 - false, 1 - true
        command.append("--font-format woff ");// Font suffixes embedded in html (default ttf)
                                                // ttf,otf,woff,svg
        command.append(pdfFile.replace(" ", "" "")).append(" ");// Need to replace spaces in file paths
        if (htmlFileName != null && !"".equals(htmlFileName.trim())) {
            command.append(htmlFileName);
            if (htmlFileName.indexOf(".html") == -1)
                command.append(".html");
        }
        try {
            System.out.println("Command: " + command.toString());
            Process p = rt.exec(command.toString());
            StreamGobbler errorGobbler = new StreamGobbler(p.getErrorStream(),
                    "ERROR");
            // Open screen standard error stream
            errorGobbler.start();
            StreamGobbler outGobbler = new StreamGobbler(p.getInputStream(),
                    "STDOUT");
            // Open screen standard output stream
            outGobbler.start();
            int w = p.waitFor();
            int v = p.exitValue();
            if (w == 0 && v == 0) {
                return true;
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
        return false;
    }
    
    
    public static void html2utf(String filePath) {
    	try {
	    	String content = "charset=utf-8";
	    	String templateContent = "";
	    	FileInputStream fileinputstream = new FileInputStream(filePath);// Read template files
	    	// The following four lines: Get the length of the input stream, then build an array of that length, read the data in the input stream in bytes into the array, and close the stream.
	    	int lenght = fileinputstream.available();
	    	byte bytes[] = new byte[lenght];
	    	fileinputstream.read(bytes);
	    	fileinputstream.close();
	    	// Construct a new byte array by decoding the specified byte array with the default character set
	
	    	//Because the original html file is in gb2312 format, it should be read in GBK format when converting to string, otherwise it will still be scrambled.
	    	templateContent = new String(bytes, "GBK");
	    	templateContent = templateContent.replaceFirst("charset=gb2312", content);
	    	// Because the string has been replaced, this String is encoded as a byte sequence using the UTF-8 character set, and the result is stored in a new byte array.
	    	byte tag_bytes[] = templateContent.getBytes("UTF-8");
	    	FileOutputStream fileoutputstream = new FileOutputStream(filePath);// Establishing a file output stream
	    	fileoutputstream.write(tag_bytes);
	    	fileoutputstream.close();
    	} catch (Exception e) {
    		System.out.print(e.toString());
    	}
    }
    
    
    public static void html2utfForJacob(String filePath) {
    	
    	filePath = filePath.replace(".html", ".files");
    	File dir = new File(filePath);
        File[] files = dir.listFiles(); // All files in the file directory are placed in an array
        if (files != null) {
            for (int i = 0; i < files.length; i++) {
                String fileName = files[i].getName();
                if (files[i].isDirectory()) { // Determine whether it's a file or a folder
                	html2utfForJacob(files[i].getAbsolutePath()); // Get the absolute path of the file
                } else if (fileName.endsWith("html")) { // Determine whether the filename ends in. html
                    String strFileName = files[i].getAbsolutePath();
                    html2utf(strFileName) ;
                } else {
                    continue;
                }
            }

        }
    }
    
}

package com.commons.yjkh.utils;

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.io.OutputStream;
import java.io.PrintWriter;

public class StreamGobbler extends Thread {
	InputStream is;
    String type;
    OutputStream os;

    public StreamGobbler(InputStream is, String type) {
        this(is, type, null);
    }

    StreamGobbler(InputStream is, String type, OutputStream redirect) {
        this.is = is;
        this.type = type;
        this.os = redirect;
    }

    public void run() {
        InputStreamReader isr = null;
        BufferedReader br = null;
        PrintWriter pw = null;
        try {
            if (os != null)
                pw = new PrintWriter(os);
            isr = new InputStreamReader(is);
            br = new BufferedReader(isr);
            String line = null;
            while ((line = br.readLine()) != null) {
                if (pw != null)
                    pw.println(line);
                System.out.println(type + ">" + line);
            }
            if (pw != null)
                pw.flush();
        } catch (IOException ioe) {
            ioe.printStackTrace();
        } finally {
            try {
                if (pw != null)
                    pw.close();
                if (br != null)
                    br.close();
                if (isr != null)
                    isr.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}