Example usage for org.apache.poi.util LittleEndian getShort

Introduction

In this page you can find the example usage for org.apache.poi.util LittleEndian getShort.

Prototype

public static short getShort(byte[] data) 

Source Link

Document

get a short value from the beginning of a byte array

Usage

From source file:com.krawler.esp.fileparser.word.Word6CHPBinTable.java

License:Open Source License

/**
 * Constructor used to read a binTable in from a Word document.
 * //  ww  w .j  a va  2 s . c o  m
 * @param documentStream
 *            The POIFS "WordDocument" stream from a Word document
 * @param offset
 *            The offset of the Chp bin table in the main stream.
 * @param size
 *            The size of the Chp bin table in the main stream.
 * @param fcMin
 *            The start of text in the main stream.
 */
public Word6CHPBinTable(byte[] documentStream, int offset, int size, int fcMin) {
    PlexOfCps binTable = new PlexOfCps(documentStream, offset, size, 2);

    int length = binTable.length();
    for (int x = 0; x < length; x++) {
        GenericPropertyNode node = binTable.getProperty(x);

        int pageNum = LittleEndian.getShort((byte[]) node.getBytes());
        int pageOffset = POIFSConstants.LARGER_BIG_BLOCK_SIZE * pageNum;
        byte[] tableStream = null;
        int size1 = 0;
        TextPieceTable tpttemp = new TextPieceTable(documentStream, tableStream, pageOffset, size1, fcMin);
        CHPFormattedDiskPage cfkp = new CHPFormattedDiskPage(documentStream, pageOffset, fcMin, tpttemp);

        int fkpSize = cfkp.size();

        for (int y = 0; y < fkpSize; y++) {
            _textRuns.add(cfkp.getCHPX(y));
        }
    }
}

---

From source file:com.krawler.esp.fileparser.word.Word6CHPBinTable.java

License:Open Source License

public Word6CHPBinTable(byte[] documentStream, int offset, int size, int fcMin, TextPieceTable tpt) {
    PlexOfCps binTable = new PlexOfCps(documentStream, offset, size, 2);

    int length = binTable.length();
    for (int x = 0; x < length; x++) {
        GenericPropertyNode node = binTable.getProperty(x);

        int pageNum = LittleEndian.getShort((byte[]) node.getBytes());
        int pageOffset = POIFSConstants.LARGER_BIG_BLOCK_SIZE * pageNum;

        CHPFormattedDiskPage cfkp = new CHPFormattedDiskPage(documentStream, pageOffset, fcMin, tpt);

        int fkpSize = cfkp.size();

        for (int y = 0; y < fkpSize; y++) {
            _textRuns.add(cfkp.getCHPX(y));
        }/*from w w w . j  a  v  a 2  s .  c o  m*/
    }
}

---

From source file:com.krawler.esp.fileparser.wordparser.Word6CHPBinTable.java

License:Open Source License

/**
 * Constructor used to read a binTable in from a Word document.
 *
 * @param documentStream/*from  w  ww  .  j a v a 2s .  c om*/
 *            The POIFS "WordDocument" stream from a Word document
 * @param offset
 *            The offset of the Chp bin table in the main stream.
 * @param size
 *            The size of the Chp bin table in the main stream.
 * @param fcMin
 *            The start of text in the main stream.
 */
public Word6CHPBinTable(byte[] documentStream, int offset, int size, int fcMin)
        throws UnsupportedEncodingException {
    PlexOfCps binTable = new PlexOfCps(documentStream, offset, size, 2);

    int length = binTable.length();
    for (int x = 0; x < length; x++) {
        GenericPropertyNode node = binTable.getProperty(x);

        int pageNum = LittleEndian.getShort((byte[]) node.getBytes());
        int pageOffset = POIFSConstants.LARGER_BIG_BLOCK_SIZE * pageNum;
        byte[] tableStream = null;
        int size1 = 0;
        TextPieceTable tpttemp = new TextPieceTable(documentStream, tableStream, pageOffset, size1, fcMin);
        CHPFormattedDiskPage cfkp = new CHPFormattedDiskPage(documentStream, pageOffset, fcMin, tpttemp);

        int fkpSize = cfkp.size();

        for (int y = 0; y < fkpSize; y++) {
            _textRuns.add(cfkp.getCHPX(y));
        }
    }
}

---

From source file:com.progdan.doc2txt.chp.Word6CHPBinTable.java

License:Apache License

/**
 * Constructor used to read a binTable in from a Word document.
 *
 * @param documentStream The POIFS "WordDocument" stream from a Word document
 * @param offset The offset of the Chp bin table in the main stream.
 * @param size The size of the Chp bin table in the main stream.
 * @param fcMin The start of text in the main stream.
 *///from  w  ww  . j  a va2s.  co  m
public Word6CHPBinTable(byte[] documentStream, int offset, int size, int fcMin) {
    PlexOfCps binTable = new PlexOfCps(documentStream, offset, size, 2);

    int length = binTable.length();
    for (int x = 0; x < length; x++) {
        GenericPropertyNode node = binTable.getProperty(x);

        int pageNum = LittleEndian.getShort((byte[]) node.getBytes());
        int pageOffset = POIFSConstants.BIG_BLOCK_SIZE * pageNum;

        CHPFormattedDiskPage cfkp = new CHPFormattedDiskPage(documentStream, pageOffset, fcMin);

        int fkpSize = cfkp.size();

        for (int y = 0; y < fkpSize; y++) {
            _textRuns.add(cfkp.getCHPX(y));
        }
    }
}

---

From source file:org.textmining.extraction.word.chp.Word6CHPBinTable.java

License:Open Source License

/**
 * Constructor used to read a binTable in from a Word document.
 *
 * @param documentStream The POIFS "WordDocument" stream from a Word document
 * @param offset The offset of the Chp bin table in the main stream.
 * @param size The size of the Chp bin table in the main stream.
 * @param fcMin The start of text in the main stream.
 *///w  ww . j  a v a  2  s  .c  o m
public Word6CHPBinTable(byte[] documentStream, int offset, int size, int fcMin, NodeHelper helper) {
    PlexOfCps binTable = new PlexOfCps(documentStream, offset, size, 2);

    int length = binTable.length();
    for (int x = 0; x < length; x++) {
        GenericPropertyNode node = binTable.getProperty(x);

        int pageNum = LittleEndian.getShort((byte[]) node.getBytes());
        int pageOffset = POIFSConstants.SMALLER_BIG_BLOCK_SIZE * pageNum;

        //TODO fix this
        CHPFormattedDiskPage cfkp = new CHPFormattedDiskPage(documentStream, pageOffset, fcMin, helper);

        int fkpSize = cfkp.size();

        for (int y = 0; y < fkpSize; y++) {
            _textRuns.add(cfkp.getCHPX(y));
        }
    }
    helper.sortNodes(_textRuns, false);
}

---