/**
  * Is this one of the kinds of formats which uses CompObj to store all of their data, eg Star
  * Draw, Star Impress or (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
        * application used to create this file. We want to search for that
        * name.
        */
       if (arrayContains(bytes, MS_GRAPH_CHART_BYTES)) {
         return MS_GRAPH_CHART;
       } else if (arrayContains(bytes, STAR_DRAW)) {
         return SDA;
       } else if (arrayContains(bytes, STAR_IMPRESS)) {
         return SDD;
       } else if (arrayContains(bytes, WORKS_QUILL96)) {
         return WPS;
       }
     }
   } catch (Exception e) {
     /*
      * "root.getEntry" can throw FileNotFoundException. The code inside
      * "if" can throw IOExceptions. Theoretically. Practically no
      * exceptions will likely ever appear.
      *
      * Swallow all of them. If any occur, we just assume that we can't
      * distinguish between Draw and Impress and return something safe:
      * x-tika-msoffice
      */
   }
   return OLE;
 }
 private static Set<String> getTopLevelNames(DirectoryNode root) {
   Set<String> names = new HashSet<String>();
   for (Entry entry : root) {
     names.add(entry.getName());
   }
   return names;
 }
Exemple #3
0
 protected void copy(DirectoryEntry sourceDir, DirectoryEntry destDir) throws IOException {
   for (org.apache.poi.poifs.filesystem.Entry entry : sourceDir) {
     if (entry instanceof DirectoryEntry) {
       // Need to recurse
       DirectoryEntry newDir = destDir.createDirectory(entry.getName());
       copy((DirectoryEntry) entry, newDir);
     } else {
       // Copy entry
       InputStream contents = new DocumentInputStream((DocumentEntry) entry);
       try {
         destDir.createDocument(entry.getName(), contents);
       } finally {
         contents.close();
       }
     }
   }
 }
Exemple #4
0
  /**
   * Compares two {@link DirectoryEntry} instances of a POI file system. The directories must
   * contain the same streams with the same names and contents.
   *
   * @param d1 The first directory.
   * @param d2 The second directory.
   * @param msg The method may append human-readable comparison messages to this string buffer.
   * @return <code>true</code> if the directories are equal, else <code>false</code>.
   * @exception MarkUnsupportedException if a POI document stream does not support the mark()
   *     operation.
   * @exception NoPropertySetStreamException if the application tries to create a property set from
   *     a POI document stream that is not a property set stream.
   * @throws UnsupportedEncodingException
   * @exception IOException if any I/O exception occurs.
   */
  private static boolean equal(
      final DirectoryEntry d1, final DirectoryEntry d2, final StringBuffer msg)
      throws NoPropertySetStreamException, MarkUnsupportedException, UnsupportedEncodingException,
          IOException {
    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) {
        msg.append("Document \"" + e2 + "\" exitsts, document \"" + e1 + "\" does not.\n");
        equal = false;
        break;
      }
    }
    return equal;
  }
Exemple #5
0
  /**
   * Writes out the word file that is represented by an instance of this class.
   *
   * @param out The OutputStream to write to.
   * @throws IOException If there is an unexpected IOException from the passed in OutputStream.
   */
  public void write(OutputStream out) throws IOException {
    // initialize our streams for writing.
    HWPFFileSystem docSys = new HWPFFileSystem();
    HWPFOutputStream wordDocumentStream = docSys.getStream(STREAM_WORD_DOCUMENT);
    HWPFOutputStream tableStream = docSys.getStream(STREAM_TABLE_1);
    // HWPFOutputStream dataStream = docSys.getStream("Data");
    int tableOffset = 0;

    // FileInformationBlock fib = (FileInformationBlock)_fib.clone();
    // clear the offsets and sizes in our FileInformationBlock.
    _fib.clearOffsetsSizes();

    // determine the FileInformationBLock size
    int fibSize = _fib.getSize();
    fibSize +=
        POIFSConstants.SMALLER_BIG_BLOCK_SIZE - (fibSize % POIFSConstants.SMALLER_BIG_BLOCK_SIZE);

    // preserve space for the FileInformationBlock because we will be writing
    // it after we write everything else.
    byte[] placeHolder = new byte[fibSize];
    wordDocumentStream.write(placeHolder);
    int mainOffset = wordDocumentStream.getOffset();

    // write out the StyleSheet.
    _fib.setFcStshf(tableOffset);
    _ss.writeTo(tableStream);
    _fib.setLcbStshf(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    // get fcMin and fcMac because we will be writing the actual text with the
    // complex table.
    int fcMin = mainOffset;

    /*
     * clx (encoding of the sprm lists for a complex file and piece table
     * for a any file) Written immediately after the end of the previously
     * recorded structure. This is recorded in all Word documents
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 23 of 210
     */

    // write out the Complex table, includes text.
    _fib.setFcClx(tableOffset);
    _cft.writeTo(wordDocumentStream, tableStream);
    _fib.setLcbClx(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();
    int fcMac = wordDocumentStream.getOffset();

    /*
     * dop (document properties record) Written immediately after the end of
     * the previously recorded structure. This is recorded in all Word
     * documents
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 23 of 210
     */

    // write out the DocumentProperties.
    _fib.setFcDop(tableOffset);
    _dop.writeTo(tableStream);
    _fib.setLcbDop(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    /*
     * plcfBkmkf (table recording beginning CPs of bookmarks) Written
     * immediately after the sttbfBkmk, if the document contains bookmarks.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */
    if (_bookmarksTables != null) {
      _bookmarksTables.writePlcfBkmkf(_fib, tableStream);
      tableOffset = tableStream.getOffset();
    }

    /*
     * plcfBkmkl (table recording limit CPs of bookmarks) Written
     * immediately after the plcfBkmkf, if the document contains bookmarks.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */
    if (_bookmarksTables != null) {
      _bookmarksTables.writePlcfBkmkl(_fib, tableStream);
      tableOffset = tableStream.getOffset();
    }

    /*
     * plcfbteChpx (bin table for CHP FKPs) Written immediately after the
     * previously recorded table. This is recorded in all Word documents.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */

    // write out the CHPBinTable.
    _fib.setFcPlcfbteChpx(tableOffset);
    _cbt.writeTo(wordDocumentStream, tableStream, fcMin, _cft.getTextPieceTable());
    _fib.setLcbPlcfbteChpx(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    /*
     * plcfbtePapx (bin table for PAP FKPs) Written immediately after the
     * plcfbteChpx. This is recorded in all Word documents.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */

    // write out the PAPBinTable.
    _fib.setFcPlcfbtePapx(tableOffset);
    _pbt.writeTo(wordDocumentStream, tableStream, _cft.getTextPieceTable());
    _fib.setLcbPlcfbtePapx(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    /*
     * plcfendRef (endnote reference position table) Written immediately
     * after the previously recorded table if the document contains endnotes
     *
     * plcfendTxt (endnote text position table) Written immediately after
     * the plcfendRef if the document contains endnotes
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */
    _endnotesTables.writeRef(_fib, tableStream);
    _endnotesTables.writeTxt(_fib, tableStream);
    tableOffset = tableStream.getOffset();

    /*
     * plcffld*** (table of field positions and statuses for annotation
     * subdocument) Written immediately after the previously recorded table,
     * if the ******* subdocument contains fields.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */

    if (_fieldsTables != null) {
      _fieldsTables.write(_fib, tableStream);
      tableOffset = tableStream.getOffset();
    }

    /*
     * plcffndRef (footnote reference position table) Written immediately
     * after the stsh if the document contains footnotes
     *
     * plcffndTxt (footnote text position table) Written immediately after
     * the plcffndRef if the document contains footnotes
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 24 of 210
     */
    _footnotesTables.writeRef(_fib, tableStream);
    _footnotesTables.writeTxt(_fib, tableStream);
    tableOffset = tableStream.getOffset();

    /*
     * plcfsed (section table) Written immediately after the previously
     * recorded table. Recorded in all Word documents
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 25 of 210
     */

    // write out the SectionTable.
    _fib.setFcPlcfsed(tableOffset);
    _st.writeTo(wordDocumentStream, tableStream);
    _fib.setLcbPlcfsed(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    // write out the list tables
    if (_lt != null) {
      /*
       * plcflst (list formats) Written immediately after the end of the
       * previously recorded, if there are any lists defined in the
       * document. This begins with a short count of LSTF structures
       * followed by those LSTF structures. This is immediately followed
       * by the allocated data hanging off the LSTFs. This data consists
       * of the array of LVLs for each LSTF. (Each LVL consists of an LVLF
       * followed by two grpprls and an XST.)
       *
       * Microsoft Office Word 97-2007 Binary File Format (.doc)
       * Specification; Page 25 of 210
       */
      _lt.writeListDataTo(_fib, tableStream);
      tableOffset = tableStream.getOffset();

      /*
       * plflfo (more list formats) Written immediately after the end of
       * the plcflst and its accompanying data, if there are any lists
       * defined in the document. This consists first of a PL of LFO
       * records, followed by the allocated data (if any) hanging off the
       * LFOs. The allocated data consists of the array of LFOLVLFs for
       * each LFO (and each LFOLVLF is immediately followed by some LVLs).
       *
       * Microsoft Office Word 97-2007 Binary File Format (.doc)
       * Specification; Page 26 of 210
       */
      _fib.setFcPlfLfo(tableStream.getOffset());
      _lt.writeListOverridesTo(tableStream);
      _fib.setLcbPlfLfo(tableStream.getOffset() - tableOffset);
      tableOffset = tableStream.getOffset();
    }

    /*
     * sttbfBkmk (table of bookmark name strings) Written immediately after
     * the previously recorded table, if the document contains bookmarks.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 27 of 210
     */
    if (_bookmarksTables != null) {
      _bookmarksTables.writeSttbfBkmk(_fib, tableStream);
      tableOffset = tableStream.getOffset();
    }

    /*
     * sttbSavedBy (last saved by string table) Written immediately after
     * the previously recorded table.
     *
     * Microsoft Office Word 97-2007 Binary File Format (.doc)
     * Specification; Page 27 of 210
     */

    // write out the saved-by table.
    if (_sbt != null) {
      _fib.setFcSttbSavedBy(tableOffset);
      _sbt.writeTo(tableStream);
      _fib.setLcbSttbSavedBy(tableStream.getOffset() - tableOffset);

      tableOffset = tableStream.getOffset();
    }

    // write out the revision mark authors table.
    if (_rmat != null) {
      _fib.setFcSttbfRMark(tableOffset);
      _rmat.writeTo(tableStream);
      _fib.setLcbSttbfRMark(tableStream.getOffset() - tableOffset);

      tableOffset = tableStream.getOffset();
    }

    // write out the FontTable.
    _fib.setFcSttbfffn(tableOffset);
    _ft.writeTo(tableStream);
    _fib.setLcbSttbfffn(tableStream.getOffset() - tableOffset);
    tableOffset = tableStream.getOffset();

    // set some variables in the FileInformationBlock.
    _fib.getFibBase().setFcMin(fcMin);
    _fib.getFibBase().setFcMac(fcMac);
    _fib.setCbMac(wordDocumentStream.getOffset());

    // make sure that the table, doc and data streams use big blocks.
    byte[] mainBuf = wordDocumentStream.toByteArray();
    if (mainBuf.length < 4096) {
      byte[] tempBuf = new byte[4096];
      System.arraycopy(mainBuf, 0, tempBuf, 0, mainBuf.length);
      mainBuf = tempBuf;
    }

    // Table1 stream will be used
    _fib.getFibBase().setFWhichTblStm(true);

    // write out the FileInformationBlock.
    // _fib.serialize(mainBuf, 0);
    _fib.writeTo(mainBuf, tableStream);

    byte[] tableBuf = tableStream.toByteArray();
    if (tableBuf.length < 4096) {
      byte[] tempBuf = new byte[4096];
      System.arraycopy(tableBuf, 0, tempBuf, 0, tableBuf.length);
      tableBuf = tempBuf;
    }

    byte[] dataBuf = _dataStream;
    if (dataBuf == null) {
      dataBuf = new byte[4096];
    }
    if (dataBuf.length < 4096) {
      byte[] tempBuf = new byte[4096];
      System.arraycopy(dataBuf, 0, tempBuf, 0, dataBuf.length);
      dataBuf = tempBuf;
    }

    // create new document preserving order of entries
    POIFSFileSystem pfs = new POIFSFileSystem();
    boolean docWritten = false;
    boolean dataWritten = false;
    boolean objectPoolWritten = false;
    boolean tableWritten = false;
    boolean propertiesWritten = false;
    for (Iterator<Entry> iter = directory.getEntries(); iter.hasNext(); ) {
      Entry entry = iter.next();
      if (entry.getName().equals(STREAM_WORD_DOCUMENT)) {
        if (!docWritten) {
          pfs.createDocument(new ByteArrayInputStream(mainBuf), STREAM_WORD_DOCUMENT);
          docWritten = true;
        }
      } else if (entry.getName().equals(STREAM_OBJECT_POOL)) {
        if (!objectPoolWritten) {
          _objectPool.writeTo(pfs.getRoot());
          objectPoolWritten = true;
        }
      } else if (entry.getName().equals(STREAM_TABLE_0) || entry.getName().equals(STREAM_TABLE_1)) {
        if (!tableWritten) {
          pfs.createDocument(new ByteArrayInputStream(tableBuf), STREAM_TABLE_1);
          tableWritten = true;
        }
      } else if (entry.getName().equals(SummaryInformation.DEFAULT_STREAM_NAME)
          || entry.getName().equals(DocumentSummaryInformation.DEFAULT_STREAM_NAME)) {
        if (!propertiesWritten) {
          writeProperties(pfs);
          propertiesWritten = true;
        }
      } else if (entry.getName().equals(STREAM_DATA)) {
        if (!dataWritten) {
          pfs.createDocument(new ByteArrayInputStream(dataBuf), STREAM_DATA);
          dataWritten = true;
        }
      } else {
        EntryUtils.copyNodeRecursively(entry, pfs.getRoot());
      }
    }

    if (!docWritten) pfs.createDocument(new ByteArrayInputStream(mainBuf), STREAM_WORD_DOCUMENT);
    if (!tableWritten) pfs.createDocument(new ByteArrayInputStream(tableBuf), STREAM_TABLE_1);
    if (!propertiesWritten) writeProperties(pfs);
    if (!dataWritten) pfs.createDocument(new ByteArrayInputStream(dataBuf), STREAM_DATA);
    if (!objectPoolWritten) _objectPool.writeTo(pfs.getRoot());

    pfs.writeFilesystem(out);
    this.directory = pfs.getRoot();

    /*
     * since we updated all references in FIB and etc, using new arrays to
     * access data
     */
    this.directory = pfs.getRoot();
    this._tableStream = tableStream.toByteArray();
    this._dataStream = dataBuf;
  }