Java:using apache POI how to convert ms word file to pdf?

Question

By using apache POI how to convert ms word file to pdf?

I an using the following code but its not working giving errors I guess I am importing the wrong classes?

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

import org.apache.poi.hslf.record.Document;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;


public class TestCon {

    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub

        POIFSFileSystem fs = null;  
         Document document = new Document(); 

         try {  
             System.out.println("Starting the test");  
             fs = new POIFSFileSystem(new FileInputStream("/document/test2.doc"));  

             HWPFDocument doc = new HWPFDocument(fs);  
             WordExtractor we = new WordExtractor(doc);  

             OutputStream file = new FileOutputStream(new File("/document/test.pdf")); 

             PdfWriter writer = PdfWriter.getInstance(document, file);  

             Range range = doc.getRange();
             document.open();  
             writer.setPageEmpty(true);  
             document.newPage();  
             writer.setPageEmpty(true);  

             String[] paragraphs = we.getParagraphText();  
             for (int i = 0; i < paragraphs.length; i++) {  

                 org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
                // CharacterRun run = pr.getCharacterRun(i);
                // run.setBold(true);
                // run.setCapitalized(true);
                // run.setItalic(true);
                 paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");  
             System.out.println("Length:" + paragraphs[i].length());  
             System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());  

             // add the paragraph to the document  
             document.add(new Paragraph(paragraphs[i]));  
             }  

             System.out.println("Document testing completed");  
         } catch (Exception e) {  
             System.out.println("Exception during test");  
             e.printStackTrace();  
         } finally {  
                         // close the document  
            document.close();  
                     }  
         }  
    }

Answer 1

Got It solved

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

import com.lowagie.text.Document;
import com.lowagie.text.DocumentException;
import com.lowagie.text.Paragraph;
import com.lowagie.text.pdf.PdfWriter;


import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;

import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;


public class TestCon {

    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub

        POIFSFileSystem fs = null;  
        Document document = new Document();

         try {  
             System.out.println("Starting the test");  
             fs = new POIFSFileSystem(new FileInputStream("D:/Resume.doc"));  

             HWPFDocument doc = new HWPFDocument(fs);  
             WordExtractor we = new WordExtractor(doc);  

             OutputStream file = new FileOutputStream(new File("D:/test.pdf")); 

             PdfWriter writer = PdfWriter.getInstance(document, file);  

             Range range = doc.getRange();
             document.open();  
             writer.setPageEmpty(true);  
             document.newPage();  
             writer.setPageEmpty(true);  

             String[] paragraphs = we.getParagraphText();  
             for (int i = 0; i < paragraphs.length; i++) {  

                 org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
                // CharacterRun run = pr.getCharacterRun(i);
                // run.setBold(true);
                // run.setCapitalized(true);
                // run.setItalic(true);
                 paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");  
             System.out.println("Length:" + paragraphs[i].length());  
             System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());  

             // add the paragraph to the document  
             document.add(new Paragraph(paragraphs[i]));  
             }  

             System.out.println("Document testing completed");  
         } catch (Exception e) {  
             System.out.println("Exception during test");  
             e.printStackTrace();  
         } finally {  
                         // close the document  
            document.close();  
                     }  
         }  
    }

Answer 2

This worked For Me:-

Source :- http://www.programcreek.com/java-api-examples/index.php?api=org.apache.poi.xwpf.converter.pdf.PdfConverter

package pdf;

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

import org.apache.poi.xwpf.converter.pdf.PdfConverter;
import org.apache.poi.xwpf.converter.pdf.PdfOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

public class PDF {
    public static void main(String[] args) throws Exception {
          String inputFile="D:/TEST.docx";
          String outputFile="D:/TEST.pdf";
          if (args != null && args.length == 2) {
            inputFile=args[0];
            outputFile=args[1];
          }
          System.out.println("inputFile:" + inputFile + ",outputFile:"+ outputFile);
          FileInputStream in=new FileInputStream(inputFile);
          XWPFDocument document=new XWPFDocument(in);
          File outFile=new File(outputFile);
          OutputStream out=new FileOutputStream(outFile);
          PdfOptions options=null;
          PdfConverter.getInstance().convert(document,out,options);
        }
}

Answer 3

In addition to Kushagra's answer, here the updated maven dependencies:

    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.xdocreport.converter.docx.xwpf</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.xdocreport.converter</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.poi.xwpf.converter.pdf</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
        <version>2.0.1</version>
    </dependency>

Answer 4

The below code worked for me:

Public class DocToPdfConverter{

public static void main(String[] args) {

        String k=null;
        OutputStream fileForPdf =null;
        try {

            String fileName="/document/test2.doc";
            //Below Code is for .doc file 
            if(fileName.endsWith(".doc"))
            {
            HWPFDocument doc = new HWPFDocument(new FileInputStream(
                    fileName));
            WordExtractor we=new WordExtractor(doc);
            k = we.getText();

             fileForPdf = new FileOutputStream(new File(
                        "/document/DocToPdf.pdf")); 
            we.close();
            }

            //Below Code for 

            else if(fileName.endsWith(".docx"))
            {
                XWPFDocument docx = new XWPFDocument(new FileInputStream(
                        fileName));
                // using XWPFWordExtractor Class
                XWPFWordExtractor we = new XWPFWordExtractor(docx);
                 k = we.getText();

                 fileForPdf = new FileOutputStream(new File(
                            "/document/DocxToPdf.pdf"));    
                 we.close();
            }



            Document document = new Document();
            PdfWriter.getInstance(document, fileForPdf);

            document.open();

            document.add(new Paragraph(k));

            document.close();
            fileForPdf.close();



        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

Answer 5

As a side note, it's also possible to read content on-the-fly directly from a Word/Excel content stream instead of reading it from the filesystem and serializing it to disk, for example when retrieving content from CMIS repositories:

e.g.

 //HWPFDocument docx = new HWPFDocument(fs);  
 HWPFDocument docx = new HWPFDocument(doc.getContentStream().getStream()); 

(doc is of type org.apache.chemistry.opencmis.client.api.Document and in this case I adapted your code to retrieve a word file from an Alfresco repository by means of opencmis and transformed it to PDF)

HTH

Answer 6

There are several steps here:

1. Read Word document using POI into a format-agnostic form
2. Convert format-agnostic form into PDF
3. Write PDF

I don't know if POI will do step 2 for you. I'd recommend something else, like iText.

Answer 7

This save my day, i load docx file from an url and convert it to pdf:

pom.xml

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.13</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.13</version>
</dependency>
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
    <version>LATEST</version>
</dependency>

main_class

public String wordToPDFPOI(String url) throws Exception {
    InputStream doc = new URL(url).openStream();
    ByteArrayOutputStream baos = new ByteArrayOutputStream();

    XWPFDocument document = new XWPFDocument(doc);
    PdfOptions options = PdfOptions.create();
    PdfConverter.getInstance().convert(document, baos, options);
    String base64_encoded = Base64.encodeBytes(baos.toByteArray());

    return base64_encoded;
}

Answer 8

All of the answers above will fail if the document has images. I would not suggest you to use apache poi since its library to convert word to pdf have been discontinued now. As of today I don't think that there is any open source library which do the conversion (they require some dependencies like some need MS word to be installed, etc). The best way I could think of (it will only work if you are deploying project on linux machine) is that install Libre Office (open source) in the linux machine and run this :

  String command = "libreoffice --headless --convert-to pdf " + inputPath + " --outdir " + outputPath;
 
 try {
         Runtime.getRuntime().exec(command);
      } catch (IOException e) {
         e.printStackTrace();
      }