gpt4 book ai didi

java - 提取和打印文本位置

转载 作者:行者123 更新时间:2023-12-02 03:57:39 24 4
gpt4 key购买 nike

我一直在对 pdfbox 进行一些实验,目前遇到一个问题,我怀疑该问题与坐标系有关。
我正在扩展 PDFTextStripper 以获取 pdf 页面中每个字符的 X 和 Y。
最初,我使用 ImageIO 创建一个图像,在我收到的位置打印文本,并在我想要的每个引用的底部放置一个小标记(不同颜色的矩形),一切看起来都很好。但现在为了避免丢失 pdf 的样式,我只想覆盖 pdf 并添加之前的语音标记,但我得到的坐标在 PDPageContentStream 中不匹配。
关于将我从 PDFTextStripper -> processTextPosition 获得的 pdf 坐标与视觉坐标相匹配的任何帮助

使用版本1.8.11

最佳答案

正如评论中所讨论的,这是 DrawPrintTextLocations 工具的 1.8 版本,它是 2.0 版本示例集合的一部分,并且基于更知名的 PrintTextLocations 示例。与 2.0 版本不同,这个版本不显示字体边界框,只显示文本提取大小,大约是一个小字形(a、e 等)的高度。它用作文本提取的启发式工具。这就是此处“我得到的文本位置减半”效果的原因。如果您需要边界框,最好使用 2.0(可能太大)。要获得精确的大小,您必须计算每个字形的路径并获取该字形的边界,同样,您需要该字形的 2.0 版本。

public class DrawPrintTextLocations extends PDFTextStripper
{
private BufferedImage image;
private final String filename;
static final int SCALE = 4;
private Graphics2D g2d;
private final PDDocument document;

/**
* Instantiate a new PDFTextStripper object.
*
* @param document
* @param filename
* @throws IOException If there is an error loading the properties.
*/
public DrawPrintTextLocations(PDDocument document, String filename) throws IOException
{
this.document = document;
this.filename = filename;
}

/**
* This will print the documents data.
*
* @param args The command line arguments.
*
* @throws IOException If there is an error parsing the document.
*/
public static void main(String[] args) throws IOException
{
if (args.length != 1)
{
usage();
}
else
{
PDDocument document = null;
try
{
document = PDDocument.load(new File(args[0]));

DrawPrintTextLocations stripper = new DrawPrintTextLocations(document, args[0]);
stripper.setSortByPosition(true);

for (int page = 0; page < document.getNumberOfPages(); ++page)
{
stripper.stripPage(page);
}
}
finally
{
if (document != null)
{
document.close();
}
}
}
}

private void stripPage(int page) throws IOException
{
PDPage pdPage = (PDPage) document.getDocumentCatalog().getAllPages().get(page);
image = pdPage.convertToImage(BufferedImage.TYPE_INT_RGB, 72 * SCALE);
PDRectangle cropBox = pdPage.getCropBox();

g2d = image.createGraphics();
g2d.setStroke(new BasicStroke(0.1f));
g2d.scale(SCALE, SCALE);

setStartPage(page + 1);
setEndPage(page + 1);

Writer dummy = new OutputStreamWriter(new ByteArrayOutputStream());
writeText(document, dummy);

// beads in green
g2d.setStroke(new BasicStroke(0.4f));
List<PDThreadBead> pageArticles = pdPage.getThreadBeads();
for (PDThreadBead bead : pageArticles)
{
PDRectangle r = bead.getRectangle();
GeneralPath p = transform(r, Matrix.getTranslatingInstance(-cropBox.getLowerLeftX(), cropBox.getLowerLeftY()));
AffineTransform flip = new AffineTransform();
flip.translate(0, pdPage.findCropBox().getHeight());
flip.scale(1, -1);
Shape s = flip.createTransformedShape(p);
g2d.setColor(Color.green);
g2d.draw(s);
}

g2d.dispose();

String imageFilename = filename;
int pt = imageFilename.lastIndexOf('.');
imageFilename = imageFilename.substring(0, pt) + "-marked-" + (page + 1) + ".png";
ImageIO.write(image, "png", new File(imageFilename));
}

/**
* Override the default functionality of PDFTextStripper.
*/
@Override
protected void writeString(String string, List<TextPosition> textPositions) throws IOException
{
for (TextPosition text : textPositions)
{
System.out.println("String[" + text.getXDirAdj() + ","
+ text.getYDirAdj() + " fs=" + text.getFontSize() + " xscale="
+ text.getXScale() + " height=" + text.getHeightDir() + " space="
+ text.getWidthOfSpace() + " width="
+ text.getWidthDirAdj() + "]" + text.getCharacter());

// in red:
// show rectangles with the "height" (not a real height, but used for text extraction
// heuristics, it is 1/2 of the bounding box height and starts at y=0)
Rectangle2D.Float rect = new Rectangle2D.Float(
text.getXDirAdj(),
(text.getYDirAdj() - text.getHeightDir()),
text.getWidthDirAdj(),
text.getHeightDir());
g2d.setColor(Color.red);
g2d.draw(rect);
}
}

/**
* This will print the usage for this document.
*/
private static void usage()
{
System.err.println("Usage: java " + DrawPrintTextLocations.class.getName() + " <input-pdf>");
}


/**
* Transforms the given point by this matrix.
*
* @param x x-coordinate
* @param y y-coordinate
*/
private Point2D.Float transformPoint(Matrix m, float x, float y)
{
float[][] values = m.getValues();
float a = values[0][0];
float b = values[0][1];
float c = values[1][0];
float d = values[1][1];
float e = values[2][0];
float f = values[2][2];
return new Point2D.Float(x * a + y * c + e, x * b + y * d + f);
}

/**
* Returns a path which represents this rectangle having been transformed by the given matrix.
* Note that the resulting path need not be rectangular.
*/
private GeneralPath transform(PDRectangle r, Matrix matrix)
{
float x1 = r.getLowerLeftX();
float y1 = r.getLowerLeftY();
float x2 = r.getUpperRightX();
float y2 = r.getUpperRightY();

Point2D.Float p0 = transformPoint(matrix, x1, y1);
Point2D.Float p1 = transformPoint(matrix, x2, y1);
Point2D.Float p2 = transformPoint(matrix, x2, y2);
Point2D.Float p3 = transformPoint(matrix, x1, y2);

GeneralPath path = new GeneralPath();
path.moveTo((float) p0.getX(), (float) p0.getY());
path.lineTo((float) p1.getX(), (float) p1.getY());
path.lineTo((float) p2.getX(), (float) p2.getY());
path.lineTo((float) p3.getX(), (float) p3.getY());
path.closePath();
return path;
}

}

关于java - 提取和打印文本位置,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/35274448/

24 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com