Examples of org.apache.poi.hwpf.model.PicturesTable

org.apache.poi.hwpf.model.PicturesTable
Holds information about all pictures embedded in Word Document either via "Insert -> Picture -> From File" or via clipboard. Responsible for images extraction and determining whether some document�s piece contains embedded image. Analyzes raw data bytestream �Data� (where Word stores all embedded objects) provided by HWPFDocument. Word stores images as is within so called "Data stream" - the stream within a Word docfile containing various data that hang off of characters in the main stream. For example, binary data describing in-line pictures and/or formfields an also embedded objects-native data. Word picture structures are concatenated one after the other in the data stream if the document contains pictures. Data stream is easily reachable via HWPFDocument._dataStream property. A picture is represented in the document text stream as a special character, an Unicode \u0001 whose CharacterRun.isSpecial() returns true. The file location of the picture in the Word binary file is accessed via CharacterRun.getPicOffset(). The CharacterRun.getPicOffset() is a byte offset into the data stream. Beginning at the position recorded in picOffset, a header data structure, will be stored. @author Dmitry Romanov

    }


    public void testEquation()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "equation.doc" );
        PicturesTable pictures = doc.getPicturesTable();


        final List<Picture> allPictures = pictures.getAllPictures();
        assertEquals( 1, allPictures.size() );


        Picture picture = allPictures.get( 0 );
        assertNotNull( picture );
        assertEquals( PictureType.EMF, picture.suggestPictureType() );

View Full Code Here

     *  \u0001 which has the offset. More than one can
     *  reference the same \u0001
     */
    public void testFloatingPictures() throws Exception {
       HWPFDocument doc = HWPFTestDataSamples.openSampleFile("FloatingPictures.doc");
       PicturesTable pictures = doc.getPicturesTable();
       
       // There are 19 images in the picture, but some are
       //  duplicate floating ones
       assertEquals(17, pictures.getAllPictures().size());
       
       int plain8s = 0;
       int escher8s = 0;
       int image1s = 0;
       
       Range r = doc.getRange();
       for(int np=0; np < r.numParagraphs(); np++) {
          Paragraph p = r.getParagraph(np);
          for(int nc=0; nc < p.numCharacterRuns(); nc++) {
             CharacterRun cr = p.getCharacterRun(nc);
             if(pictures.hasPicture(cr)) {
                image1s++;
             } else if(pictures.hasEscherPicture(cr)) {
                escher8s++;
             } else if(cr.text().startsWith("\u0008")) {
                plain8s++;
             }
          }

View Full Code Here

        assertEquals(0, pic2.getDyaCropBottom());
    }


    public void testPictureDetectionWithPNG() throws Exception {
        HWPFDocument document = HWPFTestDataSamples.openSampleFile("PngPicture.doc");
        PicturesTable pictureTable = document.getPicturesTable();
        
        assertEquals(1, pictureTable.getAllPictures().size());
        
        Picture p = pictureTable.getAllPictures().get(0);
        assertEquals(PictureType.PNG, p.suggestPictureType());
        assertEquals("png", p.suggestFileExtension());
    }

View Full Code Here

        addTextIfAny(xhtml, "header", wordExtractor.getHeaderText());


        // Grab the list of pictures. As far as we can tell,
        //  the pictures should be in order, and may be directly
        //  placed or referenced from an anchor
        PicturesTable pictureTable = document.getPicturesTable();
        PicturesSource pictures = new PicturesSource(document);
        
        // Do the main paragraph text
        Range r = document.getRange();
        for(int i=0; i<r.numParagraphs(); i++) {

View Full Code Here

        addTextIfAny(xhtml, "header", wordExtractor.getHeaderText());


        // Grab the list of pictures. As far as we can tell,
        //  the pictures should be in order, and may be directly
        //  placed or referenced from an anchor
        PicturesTable pictureTable = document.getPicturesTable();
        PicturesSource pictures = new PicturesSource(document);
        
        // Do the main paragraph text
        Range r = document.getRange();
        for(int i=0; i<r.numParagraphs(); i++) {

View Full Code Here

    HWPFDocument docB = new HWPFDocument(new FileInputStream(docBFile));
    
    assertNotNull(docA.getPicturesTable());
    assertNotNull(docB.getPicturesTable());
    
    PicturesTable picA = docA.getPicturesTable();
    PicturesTable picB = docB.getPicturesTable();
    
    List picturesA = picA.getAllPictures();
    List picturesB = picB.getAllPictures();
    
    assertEquals(7, picturesA.size());
    assertEquals(2, picturesB.size());
  }

View Full Code Here

  /**
   * Test that we have the right images in at least one file
   */
  public void testImageData() throws Exception {
    HWPFDocument docB = new HWPFDocument(new FileInputStream(docBFile));
    PicturesTable picB = docB.getPicturesTable();
    List picturesB = picB.getAllPictures();
    
    assertEquals(2, picturesB.size());
    
    Picture pic1 = (Picture)picturesB.get(0);
    Picture pic2 = (Picture)picturesB.get(1);

View Full Code Here

  /**
   * Test that compressed image data is correctly returned.
   */
  public void testCompressedImageData() throws Exception {
    HWPFDocument docC = new HWPFDocument(new FileInputStream(docCFile));
    PicturesTable picC = docC.getPicturesTable();
    List picturesC = picC.getAllPictures();
    
    assertEquals(1, picturesC.size());
    
    Picture pic = (Picture)picturesC.get(0);
    assertNotNull(pic);

View Full Code Here

       //   file and an embeded word file, in that order
       HWPFDocument doc = HWPFTestDataSamples.openSampleFile("word_with_embeded.doc");
       
       // Check we don't break loading the pictures
       doc.getPicturesTable().getAllPictures();
       PicturesTable pictureTable = doc.getPicturesTable();
       
       // Check the text, and its embeded images
       Paragraph p;
       Range r = doc.getRange();
       assertEquals(1, r.numSections());
       assertEquals(5, r.numParagraphs());
       
       p = r.getParagraph(0);
       assertEquals(2, p.numCharacterRuns());
       assertEquals("I have lots of embedded files in me\r", p.text());
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(0)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(1)));
       
       p = r.getParagraph(1);
       assertEquals(5, p.numCharacterRuns());
       assertEquals("\u0013 EMBED Excel.Sheet.8  \u0014\u0001\u0015\r", p.text());
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(0)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(1)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(2)));
       assertEquals(true,  pictureTable.hasPicture(p.getCharacterRun(3)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(4)));
       
       p = r.getParagraph(2);
       assertEquals(6, p.numCharacterRuns());
       assertEquals("\u0013 EMBED Excel.Sheet.8  \u0014\u0001\u0015\r", p.text());
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(0)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(1)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(2)));
       assertEquals(true,  pictureTable.hasPicture(p.getCharacterRun(3)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(4)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(5)));
       
       p = r.getParagraph(3);
       assertEquals(6, p.numCharacterRuns());
       assertEquals("\u0013 EMBED PowerPoint.Show.8  \u0014\u0001\u0015\r", p.text());
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(0)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(1)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(2)));
       assertEquals(true,  pictureTable.hasPicture(p.getCharacterRun(3)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(4)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(5)));
       
       p = r.getParagraph(4);
       assertEquals(6, p.numCharacterRuns());
       assertEquals("\u0013 EMBED Word.Document.8 \\s \u0014\u0001\u0015\r", p.text());
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(0)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(1)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(2)));
       assertEquals(true,  pictureTable.hasPicture(p.getCharacterRun(3)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(4)));
       assertEquals(false, pictureTable.hasPicture(p.getCharacterRun(5)));


       // Look at the pictures table
       List<Picture> pictures = pictureTable.getAllPictures();
       assertEquals(4, pictures.size());


        Picture picture = pictures.get( 0 );
        assertEquals( "emf", picture.suggestFileExtension() );
        assertEquals( "0.emf", picture.suggestFullFileName() );

View Full Code Here

    }


    public void testEquation()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "equation.doc" );
        PicturesTable pictures = doc.getPicturesTable();


        final List<Picture> allPictures = pictures.getAllPictures();
        assertEquals( 1, allPictures.size() );


        Picture picture = allPictures.get( 0 );
        assertNotNull( picture );
        assertEquals( PictureType.EMF, picture.suggestPictureType() );

View Full Code Here

0 1 2 3 4 5

TOP

Related Classes of org.apache.poi.hwpf.model.PicturesTable

org.apache.poi.ddf.DefaultEscherRecordFactory

org.apache.poi.ddf.EscherBlipRecord

org.apache.poi.ddf.EscherBSERecord

org.apache.poi.ddf.EscherRecord

org.apache.poi.ddf.EscherRecordFactory

org.apache.poi.hwpf.HWPFDocument

org.apache.poi.hwpf.TestHWPFPictures

org.apache.poi.hwpf.usermodel.CharacterRun

org.apache.poi.hwpf.usermodel.Picture

org.apache.poi.hwpf.usermodel.Range

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.