Example usage for org.apache.poi.poifs.filesystem DocumentInputStream close

Introduction

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

Prototype

@Override
    public void close() 

Source Link

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 {//from   ww w  .  j  av a2s .  c om
        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 ww w .j a  v  a 2 s  .  c  o m
        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 {/*  w w w .ja  v a  2s . 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 .  ja va2  s  . 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 .java  2s  .c o m
        stream.readFully(buf, 0, len);
    } finally {
        stream.close();
    }
    String str = new String(buf);
    return str;
}

---

From source file:com.argo.hwp.v5.HwpTextExtractorV5.java

License:Open Source License

/**
 * HWP? FileHeader /*  ww  w .  j a v a 2s  . c om*/
 * 
 * @param fs
 * @return
 * @throws IOException
 */
private static FileHeader getHeader(NPOIFSFileSystem fs) throws IOException {
    DirectoryNode root = fs.getRoot();

    // ??? p.18

    // FileHeader  
    Entry headerEntry = root.getEntry("FileHeader");
    if (!headerEntry.isDocumentEntry())
        return null;

    //  ?
    byte[] header = new byte[256]; // FileHeader ? 256
    DocumentInputStream headerStream = new DocumentInputStream((DocumentEntry) headerEntry);
    try {
        int read = headerStream.read(header);
        if (read != 256
                || !Arrays.equals(HWP_V5_SIGNATURE, Arrays.copyOfRange(header, 0, HWP_V5_SIGNATURE.length)))
            return null;
    } finally {
        headerStream.close();
    }

    FileHeader fileHeader = new FileHeader();

    // . debug
    fileHeader.version = HwpVersion.parseVersion(LittleEndian.getUInt(header, 32));
    long flags = LittleEndian.getUInt(header, 36);
    log.debug("Flags={}", Long.toBinaryString(flags).replace(' ', '0'));

    fileHeader.compressed = (flags & 0x01) == 0x01;
    fileHeader.encrypted = (flags & 0x02) == 0x02;
    fileHeader.viewtext = (flags & 0x04) == 0x04;

    return fileHeader;
}

---

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  www.  j a  va 2  s  .com
    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.  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);
    // 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.oneis.graphics.ThumbnailFinder.java

License:Mozilla Public License

/**
 * Try and get a thumbnail from an old Microsoft Office document
 *//*from w ww  .  j av a 2 s .  c om*/
private void findFromOldMSOffice() {
    try {
        File poiFilesystem = new File(inFilename);

        // Open the POI filesystem.
        InputStream is = new FileInputStream(poiFilesystem);
        POIFSFileSystem poifs = new POIFSFileSystem(is);
        is.close();

        // Read the summary information.
        DirectoryEntry dir = poifs.getRoot();
        DocumentEntry siEntry = (DocumentEntry) dir.getEntry(SummaryInformation.DEFAULT_STREAM_NAME);
        DocumentInputStream dis = new DocumentInputStream(siEntry);
        PropertySet ps = new PropertySet(dis);
        dis.close();
        SummaryInformation si = new SummaryInformation(ps);
        if (si != null) {
            byte[] thumbnailData = si.getThumbnail();
            if (thumbnailData != null) {
                Thumbnail thumbnail = new Thumbnail(thumbnailData);
                byte[] wmf = thumbnail.getThumbnailAsWMF();
                // Got something!
                thumbnailDimensions = tryWMFFormat(new ByteArrayInputStream(wmf), outFilename, outFormat,
                        maxDimension);
            }
        }
    } catch (Exception e) {
        logIgnoredException("ThumbnailFinder Apache POI file reading failed", e);
    }
}

---

From source file:com.progdan.doc2txt.WordExtractor.java

License:Apache License

/**
 * Gets the text from a Word document.//from w w w  .  j ava 2 s  .  c  o m
 *
 * @param in The InputStream representing the Word file.
 */
public String extractText(InputStream in) throws Exception {
    ArrayList text = new ArrayList();
    POIFSFileSystem fsys = new POIFSFileSystem(in);

    // 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);
    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) {
        throw new PasswordProtectedException("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);
    CHPBinTable cbt = new CHPBinTable(header, tableStream, chpOffset, chpSize, fcMin);

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

---

• «
• 1
• 2
• 3
• 4
• »