Example usage for org.apache.poi.hwpf.model TextPiece getRawBytes

Introduction

In this page you can find the example usage for org.apache.poi.hwpf.model TextPiece getRawBytes.

Prototype

public byte[] getRawBytes() 

Source Link

Usage

From source file:com.xx.platform.util.tools.ms.WordExtractor.java

License:Apache License

/**
 * Grab the text out of the text pieces. Might also include various
 *  bits of crud, but will work in cases where the text piece -> paragraph
 *  mapping is broken. Fast too./*from w  w  w.  j a  va2s.c  o m*/
 */
public String getTextFromPieces() {
    StringBuffer textBuf = new StringBuffer();

    Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
    while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();

        String encoding = "Cp1252";
        if (piece.isUnicode()) {
            encoding = "UTF-16LE";
        }
        try {
            String text = new String(piece.getRawBytes(), encoding);
            textBuf.append(text);
        } catch (UnsupportedEncodingException e) {
            throw new InternalError("Standard Encoding " + encoding + " not found, JVM broken");
        }
    }

    String text = textBuf.toString();

    // Fix line endings (Note - won't get all of them
    text = text.replaceAll("\r\r\r", "\r\n\r\n\r\n");
    text = text.replaceAll("\r\r", "\r\n\r\n");

    if (text.endsWith("\r")) {
        text += "\n";
    }

    return text;
}

---

From source file:org.opencrx.kernel.text.WordToText.java

License:BSD License

/**
 * Grab the text out of the text pieces. Might also include various
 * bits of crud, but will work in cases where the text piece -> paragraph
 * mapping is broken. Fast too.//w  ww.java2s  .c  om
 */
public String getTextFromPieces(HWPFDocument doc) {
    StringBuffer textBuf = new StringBuffer();
    Iterator<TextPiece> textPieces = doc.getTextTable().getTextPieces().iterator();
    while (textPieces.hasNext()) {
        TextPiece piece = textPieces.next();
        String encoding = "Cp1252";
        if (piece.isUnicode()) {
            encoding = "UTF-16LE";
        }
        try {
            String text = new String(piece.getRawBytes(), encoding);
            textBuf.append(text);
        } catch (UnsupportedEncodingException e) {
        }
    }
    String text = textBuf.toString();
    // Fix line endings (Note - won't get all of them
    text = text.replaceAll("\r\r\r", "\r\n\r\n\r\n");
    text = text.replaceAll("\r\r", "\r\n\r\n");
    if (text.endsWith("\r")) {
        text += "\n";
    }
    return text;
}

---

From source file:org.wandora.utils.MSOfficeBox.java

License:Open Source License

/**
 * Grab the text out of the text pieces. Might also include various
 *  bits of crud, but will work in cases where the text piece -> paragraph
 *  mapping is broken. Fast too./*from w w w . ja v a2 s.  c  om*/
 */
public static String getWordTextFromPieces(HWPFDocument doc) {
    StringBuilder textBuf = new StringBuilder();

    Iterator textPieces = doc.getTextTable().getTextPieces().iterator();
    while (textPieces.hasNext()) {
        TextPiece piece = (TextPiece) textPieces.next();

        String encoding = "Cp1252";
        if (piece.isUnicode()) {
            encoding = "UTF-16LE";
        }
        try {
            String text = new String(piece.getRawBytes(), encoding);
            textBuf.append(text);
        } catch (UnsupportedEncodingException e) {
            throw new InternalError("Standard Encoding " + encoding + " not found, JVM broken");
        }
    }

    String text = textBuf.toString();

    // Fix line endings (Note - won't get all of them
    text = text.replaceAll("\r\r\r", "\r\n\r\n\r\n");
    text = text.replaceAll("\r\r", "\r\n\r\n");

    if (text.endsWith("\r")) {
        text += "\n";
    }

    return text;
}

---