Example usage for org.apache.poi.poifs.filesystem DocumentEntry getSize

List of usage examples for org.apache.poi.poifs.filesystem DocumentEntry getSize

  1. HOME
  2. Java
  3. org.apache.poi
  4. org.apache.poi.poifs.filesystem.*
  5. DocumentEntry
  6. getSize

Introduction

In this page you can find the example usage for org.apache.poi.poifs.filesystem DocumentEntry getSize.

Prototype


public int getSize();

Source Link

Document

get the zize of the document, in bytes

Usage

From source file:ReadOLE2Entry.java

License:Open Source License

public static double[] ReadDouble(DocumentEntry document) throws IOException {
    DocumentInputStream stream = new DocumentInputStream(document);
    int len = document.getSize();
    byte[] buf = new byte[len];
    double[] bufDbl = new double[len / 8];
    try {/*ww w  . j  a  va2 s  .  co m*/
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    ByteBuffer.wrap(buf).order(ByteOrder.LITTLE_ENDIAN).asDoubleBuffer().get(bufDbl);
    return bufDbl;
}

From source file:ReadOLE2Entry.java

License:Open Source License

public static int[] ReadInt(DocumentEntry document) throws IOException {
    DocumentInputStream stream = new DocumentInputStream(document);
    int len = document.getSize();
    byte[] buf = new byte[len];
    int[] bufInt = new int[len / 4];
    try {/*from   w w  w .j  a  v  a2s.c om*/
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    ByteBuffer.wrap(buf).order(ByteOrder.LITTLE_ENDIAN).asIntBuffer().get(bufInt);
    return bufInt;
}

From source file:ReadOLE2Entry.java

License:Open Source License

public static short[] ReadShort(DocumentEntry document) throws IOException {
    DocumentInputStream stream = new DocumentInputStream(document);
    int len = document.getSize();
    byte[] buf = new byte[len];
    short[] bufShort = new short[len / 2];
    try {//from  w w w  .j  a va2s  . c  o m
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    ByteBuffer.wrap(buf).order(ByteOrder.LITTLE_ENDIAN).asShortBuffer().get(bufShort);
    return bufShort;
}

From source file:ReadOLE2Entry.java

License:Open Source License

public static byte[] ReadBytes(DocumentEntry document) throws IOException {
    DocumentInputStream stream = new DocumentInputStream(document);
    int len = document.getSize();
    byte[] buf = new byte[len];
    try {//from   ww  w. j av a  2s .c  o  m
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    return buf;
}

From source file:ReadOLE2Entry.java

License:Open Source License

public static String ReadString(DocumentEntry document) throws IOException {
    DocumentInputStream stream = new DocumentInputStream(document);
    int len = document.getSize();
    byte[] buf = new byte[len];
    try {/* ww w.  j a  va2 s  .c  o  m*/
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    String str = new String(buf);
    return str;
}

From source file:com.ezdi.rtf.testRTFParser.RTFObjDataParser.java

License:Apache License

private byte[] handleEmbeddedPOIFS(InputStream is, Metadata metadata, AtomicInteger unknownFilenameCount)
        throws IOException {

    byte[] ret = null;
    try (NPOIFSFileSystem fs = new NPOIFSFileSystem(is)) {

        DirectoryNode root = fs.getRoot();

        if (root == null) {
            return ret;
        }//w  w  w. j  av  a  2  s  .  co  m

        if (root.hasEntry("Package")) {
            Entry ooxml = root.getEntry("Package");
            TikaInputStream stream = TikaInputStream.get(new DocumentInputStream((DocumentEntry) ooxml));

            ByteArrayOutputStream out = new ByteArrayOutputStream();

            IOUtils.copy(stream, out);
            ret = out.toByteArray();
        } else {
            // try poifs
            POIFSDocumentType type = POIFSDocumentType.detectType(root);
            if (type == POIFSDocumentType.OLE10_NATIVE) {
                try {
                    // Try to un-wrap the OLE10Native record:
                    Ole10Native ole = Ole10Native.createFromEmbeddedOleObject(root);
                    ret = ole.getDataBuffer();
                } catch (Ole10NativeException ex) {
                    // Not a valid OLE10Native record, skip it
                }
            } else if (type == POIFSDocumentType.COMP_OBJ) {

                DocumentEntry contentsEntry;
                try {
                    contentsEntry = (DocumentEntry) root.getEntry("CONTENTS");
                } catch (FileNotFoundException ioe) {
                    contentsEntry = (DocumentEntry) root.getEntry("Contents");
                }

                try (DocumentInputStream inp = new DocumentInputStream(contentsEntry)) {
                    ret = new byte[contentsEntry.getSize()];
                    inp.readFully(ret);
                }
            } else {

                ByteArrayOutputStream out = new ByteArrayOutputStream();
                is.reset();
                IOUtils.copy(is, out);
                ret = out.toByteArray();
                metadata.set(Metadata.RESOURCE_NAME_KEY,
                        "file_" + unknownFilenameCount.getAndIncrement() + "." + type.getExtension());
                metadata.set(Metadata.CONTENT_TYPE, type.getType().toString());
            }
        }
    }
    return ret;
}

From source file:com.healthmarketscience.jackcess.util.OleBlobTest.java

License:Apache License

private static void checkCompoundStorage(OleBlob.CompoundContent cc, Attachment attach) throws Exception {
    File tmpData = File.createTempFile("attach_", ".dat");

    try {//  w w  w  .j  a v  a  2s  . co m
        FileOutputStream fout = new FileOutputStream(tmpData);
        fout.write(attach.getFileData());
        fout.close();

        POIFSFileSystem attachFs = new POIFSFileSystem(tmpData, true);

        for (OleBlob.CompoundContent.Entry e : cc) {
            DocumentEntry attachE = null;
            try {
                attachE = CompoundOleUtil.getDocumentEntry(e.getName(), attachFs.getRoot());
            } catch (FileNotFoundException fnfe) {
                // ignored, the ole data has extra entries
                continue;
            }

            byte[] attachEBytes = toByteArray(new DocumentInputStream(attachE), attachE.getSize());
            byte[] entryBytes = toByteArray(e.getStream(), e.length());

            assertTrue(Arrays.equals(attachEBytes, entryBytes));
        }

        ByteUtil.closeQuietly(attachFs);

    } finally {
        tmpData.delete();
    }
}

From source file:com.krawler.esp.fileparser.word.ExtractWordFile.java

License:Open Source License

public String extractText(String filepath) throws FastSavedException, IOException {
    InputStream iStream = new BufferedInputStream(new FileInputStream(filepath));
    POIFSFileSystem fsys = new POIFSFileSystem(iStream);

    // load our POIFS document streams.
    DocumentEntry headerProps = (DocumentEntry) fsys.getRoot().getEntry("WordDocument");
    DocumentInputStream din = fsys.createDocumentInputStream("WordDocument");
    byte[] header = new byte[headerProps.getSize()];

    din.read(header);/*from   w w w.j  a  v  a  2 s  . c o  m*/
    din.close();

    int info = LittleEndian.getShort(header, 0xa);
    if ((info & 0x4) != 0) {
        throw new FastSavedException("Fast-saved files are unsupported at this time");
    }
    if ((info & 0x100) != 0) {
        System.out.println("This document is password protected");
    }

    // determine the version of Word this document came from.
    int nFib = LittleEndian.getShort(header, 0x2);
    switch (nFib) {
    case 101:
    case 102:
    case 103:
    case 104:
        // this is a Word 6.0 doc send it to the extractor for that version.
        Word6Extractor oldExtractor = new Word6Extractor();
        return oldExtractor.extractText(header);
    }

    // Get the information we need from the header
    boolean useTable1 = (info & 0x200) != 0;

    // get the location of the piece table
    int complexOffset = LittleEndian.getInt(header, 0x1a2);

    // determine which table stream we must use.
    String tableName = null;
    if (useTable1) {
        tableName = "1Table";
    } else {
        tableName = "0Table";
    }

    DocumentEntry table = (DocumentEntry) fsys.getRoot().getEntry(tableName);
    byte[] tableStream = new byte[table.getSize()];

    din = fsys.createDocumentInputStream(tableName);

    din.read(tableStream);
    din.close();

    int chpOffset = LittleEndian.getInt(header, 0xfa);
    int chpSize = LittleEndian.getInt(header, 0xfe);
    int fcMin = LittleEndian.getInt(header, 0x18);

    // load our text pieces and our character runs
    ComplexFileTable cft = new ComplexFileTable(header, tableStream, complexOffset, fcMin);
    TextPieceTable tpt = cft.getTextPieceTable();
    List textPieces = tpt.getTextPieces();

    CHPBinTable cbt = new CHPBinTable(header, tableStream, chpOffset, chpSize, fcMin, tpt);

    // make the POIFS objects available for garbage collection
    din = null;
    fsys = null;
    table = null;
    headerProps = null;

    List textRuns = cbt.getTextRuns();
    Iterator runIt = textRuns.iterator();
    Iterator textIt = textPieces.iterator();

    TextPiece currentPiece = (TextPiece) textIt.next();
    int currentTextStart = currentPiece.getStart();
    int currentTextEnd = currentPiece.getEnd();

    WordTextBuffer finalTextBuf = new WordTextBuffer();

    // iterate through all text runs extract the text only if they haven't
    // been
    // deleted
    while (runIt.hasNext()) {
        CHPX chpx = (CHPX) runIt.next();
        boolean deleted = isDeleted(chpx.getGrpprl());
        if (deleted) {
            continue;
        }

        int runStart = chpx.getStart();
        int runEnd = chpx.getEnd();

        while (runStart >= currentTextEnd) {
            currentPiece = (TextPiece) textIt.next();
            currentTextStart = currentPiece.getStart();
            currentTextEnd = currentPiece.getEnd();
        }

        if (runEnd < currentTextEnd) {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else if (runEnd > currentTextEnd) {
            while (runEnd > currentTextEnd) {
                String str = currentPiece.substring(runStart - currentTextStart,
                        currentTextEnd - currentTextStart);
                finalTextBuf.append(str);
                if (textIt.hasNext()) {
                    currentPiece = (TextPiece) textIt.next();
                    currentTextStart = currentPiece.getStart();
                    runStart = currentTextStart;
                    currentTextEnd = currentPiece.getEnd();
                } else {
                    return finalTextBuf.toString();
                }
            }
            String str = currentPiece.substring(0, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            if (textIt.hasNext()) {
                currentPiece = (TextPiece) textIt.next();
                currentTextStart = currentPiece.getStart();
                currentTextEnd = currentPiece.getEnd();
            }
            finalTextBuf.append(str);
        }
    }
    return finalTextBuf.toString();
}

From source file:com.krawler.esp.fileparser.wordparser.ExtractWordFile.java

License:Open Source License

public String extractText(String filepath) throws FastSavedException, IOException {
    InputStream iStream = new BufferedInputStream(new FileInputStream(filepath));

    ArrayList text = new ArrayList();
    POIFSFileSystem fsys = new POIFSFileSystem(iStream);

    // load our POIFS document streams.
    DocumentEntry headerProps = (DocumentEntry) fsys.getRoot().getEntry("WordDocument");
    DocumentInputStream din = fsys.createDocumentInputStream("WordDocument");
    byte[] header = new byte[headerProps.getSize()];

    din.read(header);//from  w w w. ja  v  a 2s  .  c  o  m
    din.close();

    int info = LittleEndian.getShort(header, 0xa);
    if ((info & 0x4) != 0) {
        throw new FastSavedException("Fast-saved files are unsupported at this time");
    }
    if ((info & 0x100) != 0) {
        System.out.println("This document is password protected");
    }

    // determine the version of Word this document came from.
    int nFib = LittleEndian.getShort(header, 0x2);
    // Get the information we need from the header
    boolean useTable1 = (info & 0x200) != 0;

    // get the location of the piece table
    int complexOffset = LittleEndian.getInt(header, 0x1a2);

    // determine which table stream we must use.
    String tableName = null;
    if (useTable1) {
        tableName = "1Table";
    } else {
        tableName = "0Table";
    }

    DocumentEntry table = (DocumentEntry) fsys.getRoot().getEntry(tableName);
    byte[] tableStream = new byte[table.getSize()];

    din = fsys.createDocumentInputStream(tableName);

    din.read(tableStream);
    din.close();

    int chpOffset = LittleEndian.getInt(header, 0xfa);
    int chpSize = LittleEndian.getInt(header, 0xfe);
    int fcMin = LittleEndian.getInt(header, 0x18);

    ComplexFileTable cft = new ComplexFileTable(header, tableStream, complexOffset, fcMin);
    TextPieceTable tpt = cft.getTextPieceTable();
    switch (nFib) {
    case 101:
    case 102:
    case 103:
    case 104:
        // this is a Word 6.0 doc send it to the extractor for that version.
        Word6Extractor oldExtractor = new Word6Extractor();
        return oldExtractor.extractText(header, tpt);
    }
    CHPBinTable cbt = new CHPBinTable(header, tableStream, chpOffset, chpSize, fcMin, tpt);
    // load our text pieces and our character runs

    List textPieces = tpt.getTextPieces();

    // make the POIFS objects available for garbage collection
    din = null;
    fsys = null;
    table = null;
    headerProps = null;

    List textRuns = cbt.getTextRuns();
    Iterator runIt = textRuns.iterator();
    Iterator textIt = textPieces.iterator();

    TextPiece currentPiece = (TextPiece) textIt.next();
    int currentTextStart = currentPiece.getStart();
    int currentTextEnd = currentPiece.getEnd();

    WordTextBuffer finalTextBuf = new WordTextBuffer();

    // iterate through all text runs extract the text only if they haven't
    // been
    // deleted
    while (runIt.hasNext()) {
        CHPX chpx = (CHPX) runIt.next();
        boolean deleted = isDeleted(chpx.getGrpprl());
        if (deleted) {
            continue;
        }

        int runStart = chpx.getStart();
        int runEnd = chpx.getEnd();

        while (runStart >= currentTextEnd) {
            currentPiece = (TextPiece) textIt.next();
            currentTextStart = currentPiece.getStart();
            currentTextEnd = currentPiece.getEnd();
        }

        if (runEnd < currentTextEnd) {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else if (runEnd > currentTextEnd) {
            while (runEnd > currentTextEnd) {
                String str = currentPiece.substring(runStart - currentTextStart,
                        currentTextEnd - currentTextStart);
                finalTextBuf.append(str);
                if (textIt.hasNext()) {
                    currentPiece = (TextPiece) textIt.next();
                    currentTextStart = currentPiece.getStart();
                    runStart = currentTextStart;
                    currentTextEnd = currentPiece.getEnd();
                } else {
                    return finalTextBuf.toString();
                }
            }
            String str = currentPiece.substring(0, runEnd - currentTextStart);
            finalTextBuf.append(str);
        } else {
            String str = currentPiece.substring(runStart - currentTextStart, runEnd - currentTextStart);
            if (textIt.hasNext()) {
                currentPiece = (TextPiece) textIt.next();
                currentTextStart = currentPiece.getStart();
                currentTextEnd = currentPiece.getEnd();
            }
            finalTextBuf.append(str);
        }
    }
    return finalTextBuf.toString();
}

From source file:com.pnf.plugin.ole.parser.streams.OleProcessor.java

License:Apache License

private void addAll(ContainerStream parent, DirectoryEntry root) throws IOException {
    // Iterate through all entries in the current fs directory
    for (Entry e : root) {
        // If it's another directory entry, recurse deeper
        if (e instanceof DirectoryEntry) {
            // Recurse and parse files, if any, within the current directory
            DirectoryEntry d = (DirectoryEntry) e;
            ClassID id = d.getStorageClsid();

            if (Stream.isVbaStorage(d.getName())) {
                VbaContainerStream vba = new VbaContainerStream(parent, id, d.getName());
                addAll(vba, d);//from   w  w w.  ja  v a 2s .c om
            } else {
                ContainerStream currDir = new ContainerStream(parent, id, d.getName());
                addAll(currDir, d);
            }
        } else if (e instanceof DocumentEntry) {
            // Retrieve chained representation of files in image
            DocumentEntry doc = (DocumentEntry) e;

            // Create byte array around contents of file.
            byte[] data = new byte[doc.getSize()];

            // Read data from image file into buffer
            boolean error = false;
            try (DocumentInputStream stream = new DocumentInputStream(doc)) {
                try {
                    stream.readFully(data);
                } catch (IndexOutOfBoundsException i) {
                    error = true;
                }
            } catch (IOException e1) {
                error = true;
            }

            ByteBuffer buff = ByteBuffer.wrap(data);
            new DocumentStream(parent, e.getName(), buff, error); // constructor takes care of notifying parent of a new child
        }
    }
}