Java TextPosition.getHeightDir方法代码示例

import org.apache.pdfbox.text.TextPosition; //导入方法依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/46080131/text-coordinates-when-stripping-from-pdfbox">
 * Text coordinates when stripping from PDFBox
 * </a>
 * <br/>
 * <a href="https://download-a.akamaihd.net/files/media_mwb/b7/mwb_I_201711.pdf">
 * mwb_I_201711.pdf
 * </a>
 * <p>
 * This test applies the OP's code to his example PDF file and indeed, there is an offset!
 * This is due to the <code>LegacyPDFStreamEngine</code> method <code>showGlyph</code>
 * which manipulates the text rendering matrix to make the lower left corner of the
 * crop box the origin. In the current version of this test, that offset is corrected,
 * see below. 
 * </p>
 */
@Test
public void testCoverTextByRectanglesMwbI201711() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("mwb_I_201711.pdf")  ) {
        PDDocument doc = PDDocument.load(resource);

        myStripper stripper = new myStripper();

        stripper.setStartPage(1); // fix it to first page just to test it
        stripper.setEndPage(1);
        stripper.getText(doc);

        TextLine line = stripper.lines.get(1); // the line i want to paint on

        float minx = -1;
        float maxx = -1;

        for (TextPosition pos: line.textPositions)
        {
            if (pos == null)
                continue;

            if (minx == -1 || pos.getTextMatrix().getTranslateX() < minx) {
                minx = pos.getTextMatrix().getTranslateX();
            }
            if (maxx == -1 || pos.getTextMatrix().getTranslateX() > maxx) {
                maxx = pos.getTextMatrix().getTranslateX();
            }
        }

        TextPosition firstPosition = line.textPositions.get(0);
        TextPosition lastPosition = line.textPositions.get(line.textPositions.size() - 1);

        // corrected x and y
        PDRectangle cropBox = doc.getPage(0).getCropBox();

        float x = minx + cropBox.getLowerLeftX();
        float y = firstPosition.getTextMatrix().getTranslateY() + cropBox.getLowerLeftY();
        float w = (maxx - minx) + lastPosition.getWidth();
        float h = lastPosition.getHeightDir();

        PDPageContentStream contentStream = new PDPageContentStream(doc, doc.getPage(0), PDPageContentStream.AppendMode.APPEND, false, true);

        contentStream.setNonStrokingColor(Color.RED);
        contentStream.addRect(x, y, w, h);
        contentStream.fill();
        contentStream.close();

        File fileout = new File(RESULT_FOLDER, "mwb_I_201711-withRectangles.pdf");
        doc.save(fileout);
        doc.close();
    }
}
 

import org.apache.pdfbox.text.TextPosition; //导入方法依赖的package包/类
@Override
protected void writeString(String string, List<TextPosition> textPositions) throws IOException
{
    for (TextPosition textPosition: textPositions)
    {
        if (textPosition == null) {
            continue;
        }

        String c = textPosition.getUnicode();

        // if c not printable, return
        if (!isPrintable(c)) {
            continue;
        }

        Float h = textPosition.getHeightDir();

        if (c.equals(NBSP)) { // replace non-breaking space for space
            c = " ";
        }

        float wos = textPosition.getWidthOfSpace();

        TextElement te = new TextElement(Utils.round(textPosition.getYDirAdj() - h, 2),
                Utils.round(textPosition.getXDirAdj(), 2), Utils.round(textPosition.getWidthDirAdj(), 2),
                Utils.round(textPosition.getHeightDir(), 2), textPosition.getFont(), textPosition.getFontSize(), c,
                // workaround a possible bug in PDFBox:
                // https://issues.apache.org/jira/browse/PDFBOX-1755
                wos, textPosition.getDir());

        this.minCharWidth = (float) Math.min(this.minCharWidth, te.getWidth());
        this.minCharHeight = (float) Math.min(this.minCharHeight, te.getHeight());

        this.spatialIndex.add(te);
        this.textElements.add(te);
    }
}
 

import org.apache.pdfbox.text.TextPosition; //导入方法依赖的package包/类
/**
 * <a href="https://stackoverflow.com/questions/46080131/text-coordinates-when-stripping-from-pdfbox">
 * Text coordinates when stripping from PDFBox
 * </a>
 * <p>
 * This test applies the OP's code to an arbitrary PDF file and it did work properly
 * (well, it did only cover the text from the baseline upwards but that is to be expected).
 * </p>
 */
@Test
public void testCoverTextByRectanglesInput() throws IOException {
    try (   InputStream resource = getClass().getResourceAsStream("input.pdf")  ) {
        PDDocument doc = PDDocument.load(resource);

        myStripper stripper = new myStripper();

        stripper.setStartPage(1); // fix it to first page just to test it
        stripper.setEndPage(1);
        stripper.getText(doc);

        TextLine line = stripper.lines.get(1); // the line i want to paint on

        float minx = -1;
        float maxx = -1;

        for (TextPosition pos: line.textPositions)
        {
            if (pos == null)
                continue;

            if (minx == -1 || pos.getTextMatrix().getTranslateX() < minx) {
                minx = pos.getTextMatrix().getTranslateX();
            }
            if (maxx == -1 || pos.getTextMatrix().getTranslateX() > maxx) {
                maxx = pos.getTextMatrix().getTranslateX();
            }
        }

        TextPosition firstPosition = line.textPositions.get(0);
        TextPosition lastPosition = line.textPositions.get(line.textPositions.size() - 1);

        float x = minx;
        float y = firstPosition.getTextMatrix().getTranslateY();
        float w = (maxx - minx) + lastPosition.getWidth();
        float h = lastPosition.getHeightDir();

        PDPageContentStream contentStream = new PDPageContentStream(doc, doc.getPage(0), PDPageContentStream.AppendMode.APPEND, false);

        contentStream.setNonStrokingColor(Color.RED);
        contentStream.addRect(x, y, w, h);
        contentStream.fill();
        contentStream.close();

        File fileout = new File(RESULT_FOLDER, "input-withRectangles.pdf");
        doc.save(fileout);
        doc.close();
    }
}
 

import org.apache.pdfbox.text.TextPosition; //导入方法依赖的package包/类
private void addRect(TextPosition tp, List<Rectangle> rects) {
	Rectangle rect = new Rectangle();
	float xdelta = tp.getWidthDirAdj() * .2F;
	float ydelta = tp.getHeightDir() * .2F;
	rect.x = (int) ((tp.getXDirAdj() - xdelta) * xFactor);
	rect.y = (int) ((tp.getYDirAdj() - (tp.getHeightDir() + ydelta)) * yFactor);
	rect.width = (int) ((tp.getWidthDirAdj() + xdelta * 2) * xFactor);
	rect.height = (int) ((tp.getHeightDir() + ydelta * 2) * yFactor);
	rects.add(rect);
}