Examples with DirectoryNode org.apache.poi.poifs.filesystem.DirectoryNode used on opensource projects

Example 6 with DirectoryNode

use of org.apache.poi.poifs.filesystem.DirectoryNode in project poi by apache.

the class POIFSChunkParser method parse.

public static ChunkGroup[] parse(DirectoryNode node) throws IOException {
    Chunks mainChunks = new Chunks();
    ArrayList<ChunkGroup> groups = new ArrayList<ChunkGroup>();
    groups.add(mainChunks);
    //  there doesn't seem to be any use of that in Outlook
    for (Entry entry : node) {
        if (entry instanceof DirectoryNode) {
            DirectoryNode dir = (DirectoryNode) entry;
            ChunkGroup group = null;
            // Do we know what to do with it?
            if (dir.getName().startsWith(AttachmentChunks.PREFIX)) {
                group = new AttachmentChunks(dir.getName());
            }
            if (dir.getName().startsWith(NameIdChunks.NAME)) {
                group = new NameIdChunks();
            }
            if (dir.getName().startsWith(RecipientChunks.PREFIX)) {
                group = new RecipientChunks(dir.getName());
            }
            if (group != null) {
                processChunks(dir, group);
                groups.add(group);
            } else {
            // Unknown directory, skip silently
            }
        }
    }
    // Now do the top level chunks
    processChunks(node, mainChunks);
    // match up variable-length properties and their chunks
    for (ChunkGroup group : groups) {
        group.chunksComplete();
    }
    // Finish
    return groups.toArray(new ChunkGroup[groups.size()]);
}

Example 7 with DirectoryNode

use of org.apache.poi.poifs.filesystem.DirectoryNode in project poi by apache.

the class TestExtractor method testExtractFromEmbeded.

@Test
public void testExtractFromEmbeded() throws IOException {
    InputStream is = POIDataSamples.getSpreadSheetInstance().openResourceAsStream("excel_with_embeded.xls");
    POIFSFileSystem fs = new POIFSFileSystem(is);
    DirectoryNode root = fs.getRoot();
    PowerPointExtractor ppe1 = assertExtractFromEmbedded(root, "MBD0000A3B6", "Sample PowerPoint file\nThis is the 1st file\nNot much too it\n");
    PowerPointExtractor ppe2 = assertExtractFromEmbedded(root, "MBD0000A3B3", "Sample PowerPoint file\nThis is the 2nd file\nNot much too it either\n");
    ppe2.close();
    ppe1.close();
    fs.close();
}

Example 8 with DirectoryNode

use of org.apache.poi.poifs.filesystem.DirectoryNode in project poi by apache.

the class TestTextRunReWrite method testWritesOutTheSameNonRich.

@Test
public void testWritesOutTheSameNonRich() throws IOException {
    // Ensure the text lengths are as we'd expect to start with
    assertEquals(1, ss.getSlides().size());
    assertEquals(2, ss.getSlides().get(0).getTextParagraphs().size());
    // Grab the first text run on the first sheet
    List<HSLFTextParagraph> tr1 = ss.getSlides().get(0).getTextParagraphs().get(0);
    List<HSLFTextParagraph> tr2 = ss.getSlides().get(0).getTextParagraphs().get(1);
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(179, HSLFTextParagraph.getRawText(tr2).length());
    assertEquals(1, tr1.size());
    assertEquals(30, HSLFTextParagraph.getText(tr1).length());
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(31, tr1.get(0).getTextRuns().get(0).getCharacterStyle().getCharactersCovered());
    assertEquals(31, tr1.get(0).getParagraphStyle().getCharactersCovered());
    // Set the text to be as it is now
    HSLFTextParagraph.setText(tr1, HSLFTextParagraph.getRawText(tr1));
    tr1 = ss.getSlides().get(0).getTextParagraphs().get(0);
    // Check the text lengths are still right
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(179, HSLFTextParagraph.getRawText(tr2).length());
    assertEquals(1, tr1.size());
    assertEquals(30, HSLFTextParagraph.getText(tr1).length());
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(31, tr1.get(0).getTextRuns().get(0).getCharacterStyle().getCharactersCovered());
    assertEquals(31, tr1.get(0).getParagraphStyle().getCharactersCovered());
    // Write the slideshow out to a byte array
    ByteArrayOutputStream baos = new ByteArrayOutputStream();
    ss.write(baos);
    // Build an input stream of it
    ByteArrayInputStream bais = new ByteArrayInputStream(baos.toByteArray());
    // Use POIFS to query that lot
    POIFSFileSystem npfs = new POIFSFileSystem(bais);
    // Check that the "PowerPoint Document" sections have the same size
    DirectoryNode oDir = ss.getSlideShowImpl().getDirectory();
    DocumentEntry oProps = (DocumentEntry) oDir.getEntry(HSLFSlideShow.POWERPOINT_DOCUMENT);
    DocumentEntry nProps = (DocumentEntry) npfs.getRoot().getEntry(HSLFSlideShow.POWERPOINT_DOCUMENT);
    assertEquals(oProps.getSize(), nProps.getSize());
    // Check that they contain the same data
    byte[] _oData = new byte[oProps.getSize()];
    byte[] _nData = new byte[nProps.getSize()];
    oDir.createDocumentInputStream(HSLFSlideShow.POWERPOINT_DOCUMENT).read(_oData);
    npfs.createDocumentInputStream(HSLFSlideShow.POWERPOINT_DOCUMENT).read(_nData);
    assertArrayEquals(_oData, _nData);
    npfs.close();
}

Example 9 with DirectoryNode

use of org.apache.poi.poifs.filesystem.DirectoryNode in project poi by apache.

the class TestTextRunReWrite method testWritesOutTheSameRich.

@Test
public void testWritesOutTheSameRich() throws IOException {
    // Grab the first text run on the first sheet
    List<HSLFTextParagraph> tr1 = ss.getSlides().get(0).getTextParagraphs().get(0);
    // Get the first rich text run
    HSLFTextRun rtr1 = tr1.get(0).getTextRuns().get(0);
    // Check that the text sizes are as expected
    assertEquals(1, tr1.get(0).getTextRuns().size());
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(30, rtr1.getLength());
    assertEquals(30, rtr1.getRawText().length());
    assertEquals(31, rtr1.getCharacterStyle().getCharactersCovered());
    assertEquals(31, tr1.get(0).getParagraphStyle().getCharactersCovered());
    // Set the text to be as it is now
    rtr1.setText(rtr1.getRawText());
    rtr1 = tr1.get(0).getTextRuns().get(0);
    // Check that the text sizes are still as expected
    assertEquals(1, tr1.get(0).getTextRuns().size());
    assertEquals(30, HSLFTextParagraph.getRawText(tr1).length());
    assertEquals(30, tr1.get(0).getTextRuns().get(0).getRawText().length());
    assertEquals(30, rtr1.getLength());
    assertEquals(30, rtr1.getRawText().length());
    assertEquals(31, rtr1.getCharacterStyle().getCharactersCovered());
    assertEquals(31, tr1.get(0).getParagraphStyle().getCharactersCovered());
    // Write the slideshow out to a byte array
    ByteArrayOutputStream baos = new ByteArrayOutputStream();
    ss.write(baos);
    // Build an input stream of it
    ByteArrayInputStream bais = new ByteArrayInputStream(baos.toByteArray());
    // Use POIFS to query that lot
    POIFSFileSystem npfs = new POIFSFileSystem(bais);
    // Check that the "PowerPoint Document" sections have the same size
    DirectoryNode oDir = ss.getSlideShowImpl().getDirectory();
    DocumentEntry oProps = (DocumentEntry) oDir.getEntry(HSLFSlideShow.POWERPOINT_DOCUMENT);
    DocumentEntry nProps = (DocumentEntry) npfs.getRoot().getEntry(HSLFSlideShow.POWERPOINT_DOCUMENT);
    assertEquals(oProps.getSize(), nProps.getSize());
    // Check that they contain the same data
    byte[] _oData = new byte[oProps.getSize()];
    byte[] _nData = new byte[nProps.getSize()];
    oDir.createDocumentInputStream(HSLFSlideShow.POWERPOINT_DOCUMENT).read(_oData);
    npfs.createDocumentInputStream(HSLFSlideShow.POWERPOINT_DOCUMENT).read(_nData);
    assertArrayEquals(_oData, _nData);
    npfs.close();
}

Example 10 with DirectoryNode

use of org.apache.poi.poifs.filesystem.DirectoryNode in project poi by apache.

the class EmbeddedObjects method main.

@SuppressWarnings("unused")
public static void main(String[] args) throws Exception {
    POIFSFileSystem fs = new POIFSFileSystem(new FileInputStream(args[0]));
    HSSFWorkbook workbook = new HSSFWorkbook(fs);
    for (HSSFObjectData obj : workbook.getAllEmbeddedObjects()) {
        //the OLE2 Class Name of the object
        String oleName = obj.getOLE2ClassName();
        DirectoryNode dn = (obj.hasDirectoryEntry()) ? (DirectoryNode) obj.getDirectory() : null;
        Closeable document = null;
        if (oleName.equals("Worksheet")) {
            document = new HSSFWorkbook(dn, fs, false);
        } else if (oleName.equals("Document")) {
            document = new HWPFDocument(dn);
        } else if (oleName.equals("Presentation")) {
            document = new HSLFSlideShow(dn);
        } else {
            if (dn != null) {
                // The DirectoryEntry is a DocumentNode. Examine its entries to find out what it is
                for (Entry entry : dn) {
                    String name = entry.getName();
                }
            } else {
                // There is no DirectoryEntry
                // Recover the object's data from the HSSFObjectData instance.
                byte[] objectData = obj.getObjectData();
            }
        }
        if (document != null) {
            document.close();
        }
    }
    workbook.close();
}