Java:Using Apache Poi How to Convert Ms Word File to Pdf

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

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();  
                     }  
         }  
    }

Converting word(.docx) to pdf using Apache POI and itext

You need to install MS Office before running, then:

import com.documents4j.api.DocumentType; 
import com.documents4j.api.IConverter; 
import com.documents4j.job.LocalConverter;
import org.apache.commons.io.output.ByteArrayOutputStream;

import java.io.*; 
import java.util.concurrent.ExecutionException;
import java.util.concurrent.Future; 
import java.util.concurrent.TimeUnit;

public class Converter{
    public static void main(String[] args) throws IOException, ExecutionException, InterruptedException {
        ByteArrayOutputStream bo = new ByteArrayOutputStream();

        InputStream in = new BufferedInputStream(new FileInputStream("d:\\input.docx"));
        IConverter converter = LocalConverter.builder()
                .baseFolder(new File("D:\\input"))
                .workerPool(20, 25, 2, TimeUnit.SECONDS)
                .processTimeout(5, TimeUnit.SECONDS)
                .build();

        Future<Boolean> conversion = converter
                .convert(in).as(DocumentType.MS_WORD)
                .to(bo).as(DocumentType.PDF)
                .prioritizeWith(1000) // optional
                .schedule();
        conversion.get();
        try (OutputStream outputStream = new FileOutputStream("D:\\output.pdf")) {
            bo.writeTo(outputStream);
        } catch (IOException e) {
            e.printStackTrace();
        }
        in.close();
        bo.close();
    }
}

These are the necessary maven dependencies:

<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-api</artifactId>
    <version>0.2.1</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-util-conversion</artifactId>
    <version>0.2.1</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-transformer</artifactId>
    <version>0.2.1</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-util-all</artifactId>
    <version>0.2.1</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-local</artifactId>
    <version>0.2.1</version>
</dependency>
<dependency>
    <groupId>org.slf4j</groupId>
    <artifactId>slf4j-api</artifactId>
    <version>1.8.0-beta2</version>
</dependency>
<dependency>
    <groupId>org.slf4j</groupId>
    <artifactId>slf4j-simple</artifactId>
    <version>1.8.0-beta2</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-util-standalone</artifactId>
    <version>1.0.3</version>
</dependency>
<dependency>
    <groupId>com.documents4j</groupId>
    <artifactId>documents4j-transformer-msoffice-word</artifactId>
    <version>1.0.3</version>
</dependency>
<dependency>
    <groupId>com.google.guava</groupId>
    <artifactId>guava</artifactId>
    <version>23.0</version>
</dependency>

Enjoy!

Related Topics