Examples of org.apache.poi.poifs.filesystem.Entry

org.apache.poi.poifs.filesystem.Entry
This interface provides access to an object managed by a Filesystem instance. Entry objects are further divided into DocumentEntry and DirectoryEntry instances. @author Marc Johnson (mjohnson at apache dot org)

    try {
      bis = new BufferedInputStream(leaf.getInputStream());
      POIFSFileSystem filesystem = new POIFSFileSystem(bis);
      Iterator<?> entries = filesystem.getRoot().getEntries();
      while (entries.hasNext()) {
        Entry entry = (Entry) entries.next();
        String name = entry.getName();
        if (!(entry instanceof DocumentEntry)) {
          // Skip directory entries
        } else if ("WordDocument".equals(name)) {
          collectWordDocument(filesystem, sb);
        }

View Full Code Here

    throws WritingNotSupportedException, IOException
    {
        /* If there is already an entry with the same name, remove it. */
        try
        {
            final Entry e = dir.getEntry(name);
            e.delete();
        }
        catch (FileNotFoundException ex)
        {
            /* Entry not found, no need to remove it. */
        }

View Full Code Here


        // Parse remaining document entries
        boolean outlookExtracted = false;
        Iterator<?> entries = filesystem.getRoot().getEntries();
        while (entries.hasNext()) {
            Entry entry = (Entry) entries.next();
            String name = entry.getName();
            if (!(entry instanceof DocumentEntry)) {
                // Skip directory entries
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);

View Full Code Here

  }
  public static POIOLE2TextExtractor createExtractor(DirectoryNode poifsDir, POIFSFileSystem fs) throws IOException {
    // Look for certain entries in the stream, to figure it
    //  out from
    for(Iterator entries = poifsDir.getEntries(); entries.hasNext(); ) {
      Entry entry = (Entry)entries.next();
      
      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")) {
        return new VisioTextExtractor(poifsDir, fs);
      }
    }
    throw new IllegalArgumentException("No supported documents found in the OLE2 stream");
  }

View Full Code Here

    
    if(ext instanceof ExcelExtractor) {
      // These are in MBD... under the root
      Iterator it = fs.getRoot().getEntries();
      while(it.hasNext()) {
        Entry entry = (Entry)it.next();
        if(entry.getName().startsWith("MBD")) {
          dirs.add(entry);
        }
      }
    } else if(ext instanceof WordExtractor) {
      // These are in ObjectPool -> _... under the root
      try {
        DirectoryEntry op = (DirectoryEntry)
          fs.getRoot().getEntry("ObjectPool");
        Iterator it = op.getEntries();
        while(it.hasNext()) {
          Entry entry = (Entry)it.next();
          if(entry.getName().startsWith("_")) {
            dirs.add(entry);
          }
        }
      } catch(FileNotFoundException e) {}
    } else if(ext instanceof PowerPointExtractor) {

View Full Code Here

      DirectoryEntry newRoot = target.getRoot();


      Iterator entries = root.getEntries();
       
      while (entries.hasNext()) {
         Entry entry = (Entry)entries.next();
         if (!isInList(entry.getName(), excepts)) {
             copyNodeRecursively(entry,newRoot);
         }
      } 
   }

View Full Code Here

    {
        boolean equal = true;
        /* Iterate over d1 and compare each entry with its counterpart in d2. */
        for (final Iterator i = d1.getEntries(); equal && i.hasNext();)
        {
            final Entry e1 = (Entry) i.next();
            final String n1 = e1.getName();
            Entry e2 = null;
            try
            {
                e2 = d2.getEntry(n1);
            }
            catch (FileNotFoundException ex)
            {
                msg.append("Document \"" + e1 + "\" exists, document \"" +
                           e2 + "\" does not.\n");
                equal = false;
                break;
            }


            if (e1.isDirectoryEntry() && e2.isDirectoryEntry())
                equal = equal((DirectoryEntry) e1, (DirectoryEntry) e2, msg);
            else if (e1.isDocumentEntry() && e2.isDocumentEntry())
                equal = equal((DocumentEntry) e1, (DocumentEntry) e2, msg);
            else
            {
                msg.append("One of \"" + e1 + "\" and \"" + e2 + "\" is a " +
                           "document while the other one is a directory.\n");
                equal = false;
            }
        }


        /* Iterate over d2 just to make sure that there are no entries in d2
         * that are not in d1. */
        for (final Iterator i = d2.getEntries(); equal && i.hasNext();)
        {
            final Entry e2 = (Entry) i.next();
            final String n2 = e2.getName();
            Entry e1 = null;
            try
            {
                e1 = d1.getEntry(n2);
            }
            catch (FileNotFoundException ex)

View Full Code Here


        // Parse remaining document entries
        boolean outlookExtracted = false;
        Iterator<?> entries = filesystem.getRoot().getEntries();
        while (entries.hasNext()) {
            Entry entry = (Entry) entries.next();
            String name = entry.getName();
            if (entry instanceof DirectoryEntry) {
               if ("Quill".equals(name)) {
                  setType(metadata, "application/x-mspublisher");
                  PublisherTextExtractor extractor =
                      new PublisherTextExtractor(filesystem);

View Full Code Here

     *  (older) Works?
     * If not, it's likely an embedded resource
     */
    private static MediaType processCompObjFormatType(DirectoryEntry root) {
        try {
            Entry e = root.getEntry("\u0001CompObj");
            if (e != null && e.isDocumentEntry()) {
                DocumentNode dn = (DocumentNode)e;
                DocumentInputStream stream = new DocumentInputStream(dn);
                byte [] bytes = IOUtils.toByteArray(stream);
                /*
                 * This array contains a string with a normal ASCII name of the

View Full Code Here

  }
  public static POIOLE2TextExtractor createExtractor(DirectoryNode poifsDir, POIFSFileSystem fs) throws IOException {
    // Look for certain entries in the stream, to figure it
    //  out from
    for(Iterator entries = poifsDir.getEntries(); entries.hasNext(); ) {
      Entry entry = (Entry)entries.next();
      
      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")) {
        return new VisioTextExtractor(poifsDir, fs);
      }
    }
    throw new IllegalArgumentException("No supported documents found in the OLE2 stream");
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.poi.poifs.filesystem.Entry

net.sf.mpxj.sample.MppDump

nz.govt.natlib.adapter.excel.ExcelAdapter

nz.govt.natlib.adapter.powerpoint.PowerPointAdapter

nz.govt.natlib.adapter.works.DocAdapter

org.apache.poi.extractor.ExtractorFactory

org.apache.poi.hpsf.examples.CopyCompare

org.apache.poi.hpsf.MutablePropertySet

org.apache.poi.hssf.usermodel.examples.EmeddedObjects

org.apache.poi.hssf.usermodel.HSSFObjectData

org.apache.poi.hssf.usermodel.HSSFWorkbook

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.