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)

        }


        if (poifsDir.hasEntry("WordDocument")) {
            // Old or new style word document?
            try {
                return new WordExtractor(poifsDir);
            } catch (OldWordFileFormatException e) {
                return new Word6Extractor(poifsDir);
            }
        }

View Full Code Here

     * Bug 33519 - HWPF fails to read a file
     */
    public void test33519()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug33519.doc" );
        WordExtractor extractor = new WordExtractor( doc );
        extractor.getText();
    }

View Full Code Here

     * Bug 34898 - WordExtractor doesn't read the whole string from the file
     */
    public void test34898()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug34898.doc" );
        WordExtractor extractor = new WordExtractor( doc );
        assertEquals( "\u30c7\u30a3\u30ec\u30af\u30c8\u30ea", extractor
                .getText().trim() );
    }

View Full Code Here

     * Bug 44331 - HWPFDocument.write destroys fields
     */
    public void test44431()
    {
        HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile( "Bug44431.doc" );
        WordExtractor extractor1 = new WordExtractor( doc1 );


        HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack( doc1 );
        WordExtractor extractor2 = new WordExtractor( doc2 );


        assertEquals( extractor1.getFooterText(), extractor2.getFooterText() );
        assertEquals( extractor1.getHeaderText(), extractor2.getHeaderText() );
        assertEquals( Arrays.toString( extractor1.getParagraphText() ),
                Arrays.toString( extractor2.getParagraphText() ) );


        assertEquals( extractor1.getText(), extractor2.getText() );
    }

View Full Code Here

     * Bug 44331 - HWPFDocument.write destroys fields
     */
    public void test44431_2()
    {
        HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile( "Bug44431.doc" );
        WordExtractor extractor1 = new WordExtractor( doc1 );


        assertEquals( "File name=FieldsTest.doc\n" + 
            "\n" + 
            "\n" + 
            "STYLEREF test\n" + 
            "\n" + 
            "\n" + 
            "\n" + 
            "TEST TABLE OF CONTENTS\n" + 
            "\n" + 
            "Heading paragraph in next page\t2\n" + 
            "Another heading paragraph in further page\t3\n" + 
            "Another heading paragraph in further page\t3\n" + 
            "\n" + 
            "\n" + 
            "Heading paragraph in next page\n" + 
            "Another heading paragraph in further page\n" + 
            "\n" + 
            "\n" + 
            "\n" + 
            "Page 3 of 3", extractor1.getText() );
    }

View Full Code Here

     * 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

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.