Java Code Examples for org.apache.pdfbox.util.Vector#getY()

The following examples show how to use org.apache.pdfbox.util.Vector#getY() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: PDFVisibleTextStripper.java    From testarea-pdfbox2 with Apache License 2.0 5 votes vote down vote up
@Override
protected void processTextPosition(TextPosition text) {
    Matrix textMatrix = text.getTextMatrix();
    Vector start = textMatrix.transform(new Vector(0, 0));
    Vector end = new Vector(start.getX() + text.getWidth(), start.getY());

    PDGraphicsState gs = getGraphicsState();
    Area area = gs.getCurrentClippingPath();
    if (area == null ||
            (contains(area, lowerLeftX + start.getX(), lowerLeftY + start.getY()) &&
                    ((!checkEndPointToo) || contains(area, lowerLeftX + end.getX(), lowerLeftY + end.getY()))))
        super.processTextPosition(text);
    else if (dropStream != null)
        dropStream.printf("Clipped '%s' at %s,%s\n", text.getUnicode(), lowerLeftX + start.getX(), lowerLeftY + start.getY());
}
 
Example 2
Source File: PDFVisibleTextStripper.java    From testarea-pdfbox2 with Apache License 2.0 5 votes vote down vote up
void deleteCharsInPath() {
    for (List<TextPosition> list : charactersByArticle) {
        List<TextPosition> toRemove = new ArrayList<>();
        for (TextPosition text : list) {
            Matrix textMatrix = text.getTextMatrix();
            Vector start = textMatrix.transform(new Vector(0, 0));
            Vector end = new Vector(start.getX() + text.getWidth(), start.getY());
            if (linePath.contains(lowerLeftX + start.getX(), lowerLeftY + start.getY()) ||
                    (checkEndPointToo && linePath.contains(lowerLeftX + end.getX(), lowerLeftY + end.getY()))) {
                toRemove.add(text);
            }
        }
        if (toRemove.size() != 0) {
            System.out.println(toRemove.size());
            list.removeAll(toRemove);
        }
    }
}
 
Example 3
Source File: PDFStreamEngine.java    From gcs with Mozilla Public License 2.0 4 votes vote down vote up
/**
 * Process text from the PDF Stream. You should override this method if you want to
 * perform an action when encoded text is being processed.
 *
 * @param string the encoded text
 * @throws IOException if there is an error processing the string
 */
protected void showText(byte[] string) throws IOException
{
    PDGraphicsState state = getGraphicsState();
    PDTextState textState = state.getTextState();

    // get the current font
    PDFont font = textState.getFont();
    if (font == null)
    {
        LOG.warn("No current font, will use default");
        font = PDFontFactory.createDefaultFont();
    }

    float fontSize = textState.getFontSize();
    float horizontalScaling = textState.getHorizontalScaling() / 100f;
    float charSpacing = textState.getCharacterSpacing();

    // put the text state parameters into matrix form
    Matrix parameters = new Matrix(
            fontSize * horizontalScaling, 0, // 0
            0, fontSize,                     // 0
            0, textState.getRise());         // 1

    // read the stream until it is empty
    InputStream in = new ByteArrayInputStream(string);
    while (in.available() > 0)
    {
        // decode a character
        int before = in.available();
        int code = font.readCode(in);
        int codeLength = before - in.available();
        String unicode = font.toUnicode(code);

        // Word spacing shall be applied to every occurrence of the single-byte character code
        // 32 in a string when using a simple font or a composite font that defines code 32 as
        // a single-byte code.
        float wordSpacing = 0;
        if (codeLength == 1 && code == 32)
        {
            wordSpacing += textState.getWordSpacing();
        }

        // text rendering matrix (text space -> device space)
        Matrix ctm = state.getCurrentTransformationMatrix();
        Matrix textRenderingMatrix = parameters.multiply(textMatrix).multiply(ctm);

        // get glyph's position vector if this is vertical text
        // changes to vertical text should be tested with PDFBOX-2294 and PDFBOX-1422
        if (font.isVertical())
        {
            // position vector, in text space
            Vector v = font.getPositionVector(code);

            // apply the position vector to the horizontal origin to get the vertical origin
            textRenderingMatrix.translate(v);
        }

        // get glyph's horizontal and vertical displacements, in text space
        Vector w = font.getDisplacement(code);

        // process the decoded glyph
        saveGraphicsState();
        Matrix textMatrixOld = textMatrix;
        Matrix textLineMatrixOld = textLineMatrix;
        showGlyph(textRenderingMatrix, font, code, unicode, w);
        textMatrix = textMatrixOld;
        textLineMatrix = textLineMatrixOld;
        restoreGraphicsState();

        // calculate the combined displacements
        float tx;
        float ty;
        if (font.isVertical())
        {
            tx = 0;
            ty = w.getY() * fontSize + charSpacing + wordSpacing;
        }
        else
        {
            tx = (w.getX() * fontSize + charSpacing + wordSpacing) * horizontalScaling;
            ty = 0;
        }

        // update the text matrix
        textMatrix.concatenate(Matrix.getTranslateInstance(tx, ty));
    }
}