Examples of org.apache.poi.hwpf.extractor.WordExtractor

org.apache.poi.hwpf.extractor.WordExtractor
Class to extract the text from a Word Document. You should use either getParagraphText() or getText() unless you have a strong reason otherwise. @author Nick Burch (nick at torchbox dot com)

     * Bug 45473 - HWPF cannot read file after save
     */
    public void test45473()
    {
        HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile( "Bug45473.doc" );
        String text1 = new WordExtractor( doc1 ).getText().trim();


        HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack( doc1 );
        String text2 = new WordExtractor( doc2 ).getText().trim();


        // the text in the saved document has some differences in line
        // separators but we tolerate that
        assertEquals( text1.replaceAll( "\n", "" ), text2.replaceAll( "\n", "" ) );
    }

View Full Code Here

     * missing
     */
    public void test46817()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug46817.doc" );
        WordExtractor extractor = new WordExtractor( doc );
        String text = extractor.getText().trim();


        assertTrue( text.contains( "Nazwa wykonawcy" ) );
        assertTrue( text.contains( "kujawsko-pomorskie" ) );
        assertTrue( text.contains( "ekomel@ekomel.com.pl" ) );
    }

View Full Code Here

     * @throws IOException
     */
    public void test47286() throws IOException
    {
        HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile( "Bug47286.doc" );
        String text1 = new WordExtractor( doc1 ).getText().trim();


        HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack( doc1 );
        String text2 = new WordExtractor( doc2 ).getText().trim();


        // the text in the saved document has some differences in line
        // separators but we tolerate that
        assertEquals( text1.replaceAll( "\n", "" ), text2.replaceAll( "\n", "" ) );

View Full Code Here

     * some website as an embedded object
     */
    public void test47731() throws Exception
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug47731.doc" );
        String foundText = new WordExtractor( doc ).getText();


        assertTrue( foundText
                .contains( "Soak the rice in water for three to four hours" ) );
    }

View Full Code Here

    public void test47742() throws Exception
    {


        // (1) extract text from MS Word document via POI
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug47742.doc" );
        String foundText = new WordExtractor( doc ).getText();


        // (2) read text from text document (retrieved by saving the word
        // document as text file using encoding UTF-8)
        InputStream is = POIDataSamples.getDocumentInstance()
                .openResourceAsStream( "Bug47742-text.txt" );

View Full Code Here

        // TODO: refactor into something nicer!
        if(System.getProperty("poi.test.remote") != null) {
            String href = "http://domex.nps.edu/corp/files/govdocs1/007/007488.doc";
            HWPFDocument hwpfDocument = HWPFTestDataSamples.openRemoteFile( href );


            WordExtractor wordExtractor = new WordExtractor( hwpfDocument );
            wordExtractor.getText();
        }


    }

View Full Code Here

        
        // Create a document for this file
        HWPFDocument doc = new HWPFDocument(fs);


        // Create a WordExtractor to read the text of the word document
        WordExtractor we = new WordExtractor(doc);


        // Extract all paragraphs in the document as strings
        text = we.getText();


        // Output the document
        if(logger.isInfoEnabled())
          logger.info("Word Document has " + text.length() + " chars\n\n" + text);
      }

View Full Code Here

      
      if(entry.getName().equals("Workbook")) {
        return new ExcelExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("WordDocument")) {
        return new WordExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("PowerPoint Document")) {
        return new PowerPointExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("VisioDocument")) {

View Full Code Here

0 1 2 3 4 5 6 7 8

TOP

Related Classes of org.apache.poi.hwpf.extractor.WordExtractor

com.gentics.cr.lucene.indexer.transformer.doc.DOCContentTransformer

com.google.code.ftspc.lector.parsers.POI.DocParser

net.yacy.document.parser.docParser

org.apache.jackrabbit.extractor.MsWordTextExtractor

org.apache.poi.extractor.ExtractorFactory

org.apache.poi.hwpf.converter.WordToTextConverter

org.apache.poi.hwpf.HWPFDocument

org.apache.poi.hwpf.model.TextPiece

org.apache.poi.hwpf.usermodel.HeaderStories

org.apache.poi.hwpf.usermodel.Paragraph

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.