PDFBox - 线/矩形提取
PDFBox - Line / Rectangle extraction
我正在尝试从 PDF 中提取文本坐标和线（或矩形）坐标。
TextPosition class 有 getXDirAdj() 和 getYDirAdj() 方法，它们根据相应 TextPosition 对象表示的文本片段的方向转换坐标（根据评论更正来自@mkl)
无论页面旋转如何，最终输出都是一致的。
输出所需的坐标为 X0,Y0（页面左上角）
这是对@Tilman Hausherr 解决方案的轻微修改。 y 坐标被反转（高度 - y），以使其与文本提取过程中的坐标保持一致，输出也被写入 csv。
public class LineCatcher extends PDFGraphicsStreamEngine
{
private static final GeneralPath linePath = new GeneralPath();
private static ArrayList<Rectangle2D> rectList= new ArrayList<Rectangle2D>();
private int clipWindingRule = -1;
private static String headerRecord = "Text|Page|x|y|width|height|space|font";
public LineCatcher(PDPage page)
{
super(page);
}
public static void main(String[] args) throws IOException
{
if( args.length != 4 )
{
usage();
}
else
{
PDDocument document = null;
FileOutputStream fop = null;
File file;
Writer osw = null;
int numPages;
double page_height;
try
{
document = PDDocument.load( new File(args[0], args[1]) );
numPages = document.getNumberOfPages();
file = new File(args[2], args[3]);
fop = new FileOutputStream(file);
// if file doesnt exists, then create it
if (!file.exists()) {
file.createNewFile();
}
osw = new OutputStreamWriter(fop, "UTF8");
osw.write(headerRecord + System.lineSeparator());
System.out.println("Line Processing numPages:" + numPages);
for (int n = 0; n < numPages; n++) {
System.out.println("Line Processing page:" + n);
rectList = new ArrayList<Rectangle2D>();
PDPage page = document.getPage(n);
page_height = page.getCropBox().getUpperRightY();
LineCatcher lineCatcher = new LineCatcher(page);
lineCatcher.processPage(page);
try{
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x = Double.toString(rect.getX());
String y = Double.toString(page_height - rect.getY()) ;
String w = Double.toString(rect.getWidth());
String h = Double.toString(rect.getHeight());
writeToFile(pageNum, x, y, w, h, osw);
}
rectList = null;
page = null;
lineCatcher = null;
}
catch(IOException io){
throw new IOException("Failed to Parse document for line processing. Incorrect document format. Page:" + n);
}
};
}
catch(IOException io){
throw new IOException("Failed to Parse document for line processing. Incorrect document format.");
}
finally
{
if ( osw != null ){
osw.close();
}
if( document != null )
{
document.close();
}
}
}
}
private static void writeToFile(String pageNum, String x, String y, String w, String h, Writer osw) throws IOException {
String c = "^" + "|" +
pageNum + "|" +
x + "|" +
y + "|" +
w + "|" +
h + "|" +
"999" + "|" +
"marker-only";
osw.write(c + System.lineSeparator());
}
@Override
public void appendRectangle(Point2D p0, Point2D p1, Point2D p2, Point2D p3) throws IOException
{
// to ensure that the path is created in the right direction, we have to create
// it by combining single lines instead of creating a simple rectangle
linePath.moveTo((float) p0.getX(), (float) p0.getY());
linePath.lineTo((float) p1.getX(), (float) p1.getY());
linePath.lineTo((float) p2.getX(), (float) p2.getY());
linePath.lineTo((float) p3.getX(), (float) p3.getY());
// close the subpath instead of adding the last line so that a possible set line
// cap style isn't taken into account at the "beginning" of the rectangle
linePath.closePath();
}
@Override
public void drawImage(PDImage pdi) throws IOException
{
}
@Override
public void clip(int windingRule) throws IOException
{
// the clipping path will not be updated until the succeeding painting operator is called
clipWindingRule = windingRule;
}
@Override
public void moveTo(float x, float y) throws IOException
{
linePath.moveTo(x, y);
}
@Override
public void lineTo(float x, float y) throws IOException
{
linePath.lineTo(x, y);
}
@Override
public void curveTo(float x1, float y1, float x2, float y2, float x3, float y3) throws IOException
{
linePath.curveTo(x1, y1, x2, y2, x3, y3);
}
@Override
public Point2D getCurrentPoint() throws IOException
{
return linePath.getCurrentPoint();
}
@Override
public void closePath() throws IOException
{
linePath.closePath();
}
@Override
public void endPath() throws IOException
{
if (clipWindingRule != -1)
{
linePath.setWindingRule(clipWindingRule);
getGraphicsState().intersectClippingPath(linePath);
clipWindingRule = -1;
}
linePath.reset();
}
@Override
public void strokePath() throws IOException
{
rectList.add(linePath.getBounds2D());
linePath.reset();
}
@Override
public void fillPath(int windingRule) throws IOException
{
linePath.reset();
}
@Override
public void fillAndStrokePath(int windingRule) throws IOException
{
linePath.reset();
}
@Override
public void shadingFill(COSName cosn) throws IOException
{
}
/**
* This will print the usage for this document.
*/
private static void usage()
{
System.err.println( "Usage: java " + LineCatcher.class.getName() + " <input-pdf>" + " <output-file>");
}
}
正在使用 PDFGraphicsStreamEngine class 提取直线和矩形坐标。线条和矩形的坐标与文本坐标不对齐
绿色：文本
红色：按原样获得的线坐标
黑色：预期坐标（对输出应用变换后获得）
尝试了 setRotation() 方法来纠正 运行 行提取之前的旋转。然而结果并不一致。
使用 PDFBox 获得旋转并获得一致的线/矩形坐标输出的可能选项有哪些？
据我了解这里的需求，OP在可见页面左上角的原点坐标系中工作（考虑页面旋转），x坐标向右递增，y坐标向下递增，单位为PDF默认用户space单位（通常为1/72英寸).
在这个坐标系中他需要以
的形式提取（水平或垂直）线
- 左/上端点坐标和
- 宽度/高度。
转换 LineCatcher 结果
另一方面，他从 Tilman 那里得到的助手 class LineCatcher 没有 考虑页面旋转。此外，它 return 是垂直线的 底部 端点，而不是顶端端点。因此，必须对 LineCatcher 结果应用坐标变换。
为此只需替换
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x = Double.toString(rect.getX());
String y = Double.toString(page_height - rect.getY()) ;
String w = Double.toString(rect.getWidth());
String h = Double.toString(rect.getHeight());
writeToFile(pageNum, x, y, w, h, osw);
}
来自
int pageRotation = page.getRotation();
PDRectangle pageCropBox = page.getCropBox();
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x, y, w, h;
switch(pageRotation) {
case 0:
x = Double.toString(rect.getX() - pageCropBox.getLowerLeftX());
y = Double.toString(pageCropBox.getUpperRightY() - rect.getY() + rect.getHeight());
w = Double.toString(rect.getWidth());
h = Double.toString(rect.getHeight());
break;
case 90:
x = Double.toString(rect.getY() - pageCropBox.getLowerLeftY());
y = Double.toString(rect.getX() - pageCropBox.getLowerLeftX());
w = Double.toString(rect.getHeight());
h = Double.toString(rect.getWidth());
break;
case 180:
x = Double.toString(pageCropBox.getUpperRightX() - rect.getX() - rect.getWidth());
y = Double.toString(rect.getY() - pageCropBox.getLowerLeftY());
w = Double.toString(rect.getWidth());
h = Double.toString(rect.getHeight());
break;
case 270:
x = Double.toString(pageCropBox.getUpperRightY() - rect.getY() + rect.getHeight());
y = Double.toString(pageCropBox.getUpperRightX() - rect.getX() - rect.getWidth());
w = Double.toString(rect.getHeight());
h = Double.toString(rect.getWidth());
break;
default:
throw new IOException(String.format("Unsupported page rotation %d on page %d.", pageRotation, page));
}
writeToFile(pageNum, x, y, w, h, osw);
}
(ExtractLinesWithDir 测试 testExtractLineRotationTestWithDir)
与 TextPosition.get?DirAdj() 坐标的关系
OP描述坐标参考TextPosition class方法getXDirAdj()和getYDirAdj()。实际上，这些方法 return 在坐标系中坐标系，原点在页面左上角， y 坐标在旋转页面后向下 增加，以便文本竖直绘制.
在示例文档的情况下，所有文本都被绘制为在应用页面旋转后直立。我对上面写的需求的理解由此推导出来。
使用 TextPosition.get?DirAdj() 值作为全局坐标的问题在于，在包含以不同方向绘制文本的页面的文档中，收集的文本坐标突然与不同的坐标系相关。因此，一个通用的解决方案不应该像那样疯狂地收集坐标。相反，它应该首先确定页面方向（例如页面旋转给出的方向或大部分文本共享的方向）并使用该方向给出的固定坐标系中的坐标加上文本书写方向的指示有问题的作品。
我正在尝试从 PDF 中提取文本坐标和线（或矩形）坐标。
TextPosition class 有 getXDirAdj() 和 getYDirAdj() 方法，它们根据相应 TextPosition 对象表示的文本片段的方向转换坐标（根据评论更正来自@mkl)
无论页面旋转如何，最终输出都是一致的。
输出所需的坐标为 X0,Y0（页面左上角）
这是对@Tilman Hausherr 解决方案的轻微修改。 y 坐标被反转（高度 - y），以使其与文本提取过程中的坐标保持一致，输出也被写入 csv。
public class LineCatcher extends PDFGraphicsStreamEngine
{
private static final GeneralPath linePath = new GeneralPath();
private static ArrayList<Rectangle2D> rectList= new ArrayList<Rectangle2D>();
private int clipWindingRule = -1;
private static String headerRecord = "Text|Page|x|y|width|height|space|font";
public LineCatcher(PDPage page)
{
super(page);
}
public static void main(String[] args) throws IOException
{
if( args.length != 4 )
{
usage();
}
else
{
PDDocument document = null;
FileOutputStream fop = null;
File file;
Writer osw = null;
int numPages;
double page_height;
try
{
document = PDDocument.load( new File(args[0], args[1]) );
numPages = document.getNumberOfPages();
file = new File(args[2], args[3]);
fop = new FileOutputStream(file);
// if file doesnt exists, then create it
if (!file.exists()) {
file.createNewFile();
}
osw = new OutputStreamWriter(fop, "UTF8");
osw.write(headerRecord + System.lineSeparator());
System.out.println("Line Processing numPages:" + numPages);
for (int n = 0; n < numPages; n++) {
System.out.println("Line Processing page:" + n);
rectList = new ArrayList<Rectangle2D>();
PDPage page = document.getPage(n);
page_height = page.getCropBox().getUpperRightY();
LineCatcher lineCatcher = new LineCatcher(page);
lineCatcher.processPage(page);
try{
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x = Double.toString(rect.getX());
String y = Double.toString(page_height - rect.getY()) ;
String w = Double.toString(rect.getWidth());
String h = Double.toString(rect.getHeight());
writeToFile(pageNum, x, y, w, h, osw);
}
rectList = null;
page = null;
lineCatcher = null;
}
catch(IOException io){
throw new IOException("Failed to Parse document for line processing. Incorrect document format. Page:" + n);
}
};
}
catch(IOException io){
throw new IOException("Failed to Parse document for line processing. Incorrect document format.");
}
finally
{
if ( osw != null ){
osw.close();
}
if( document != null )
{
document.close();
}
}
}
}
private static void writeToFile(String pageNum, String x, String y, String w, String h, Writer osw) throws IOException {
String c = "^" + "|" +
pageNum + "|" +
x + "|" +
y + "|" +
w + "|" +
h + "|" +
"999" + "|" +
"marker-only";
osw.write(c + System.lineSeparator());
}
@Override
public void appendRectangle(Point2D p0, Point2D p1, Point2D p2, Point2D p3) throws IOException
{
// to ensure that the path is created in the right direction, we have to create
// it by combining single lines instead of creating a simple rectangle
linePath.moveTo((float) p0.getX(), (float) p0.getY());
linePath.lineTo((float) p1.getX(), (float) p1.getY());
linePath.lineTo((float) p2.getX(), (float) p2.getY());
linePath.lineTo((float) p3.getX(), (float) p3.getY());
// close the subpath instead of adding the last line so that a possible set line
// cap style isn't taken into account at the "beginning" of the rectangle
linePath.closePath();
}
@Override
public void drawImage(PDImage pdi) throws IOException
{
}
@Override
public void clip(int windingRule) throws IOException
{
// the clipping path will not be updated until the succeeding painting operator is called
clipWindingRule = windingRule;
}
@Override
public void moveTo(float x, float y) throws IOException
{
linePath.moveTo(x, y);
}
@Override
public void lineTo(float x, float y) throws IOException
{
linePath.lineTo(x, y);
}
@Override
public void curveTo(float x1, float y1, float x2, float y2, float x3, float y3) throws IOException
{
linePath.curveTo(x1, y1, x2, y2, x3, y3);
}
@Override
public Point2D getCurrentPoint() throws IOException
{
return linePath.getCurrentPoint();
}
@Override
public void closePath() throws IOException
{
linePath.closePath();
}
@Override
public void endPath() throws IOException
{
if (clipWindingRule != -1)
{
linePath.setWindingRule(clipWindingRule);
getGraphicsState().intersectClippingPath(linePath);
clipWindingRule = -1;
}
linePath.reset();
}
@Override
public void strokePath() throws IOException
{
rectList.add(linePath.getBounds2D());
linePath.reset();
}
@Override
public void fillPath(int windingRule) throws IOException
{
linePath.reset();
}
@Override
public void fillAndStrokePath(int windingRule) throws IOException
{
linePath.reset();
}
@Override
public void shadingFill(COSName cosn) throws IOException
{
}
/**
* This will print the usage for this document.
*/
private static void usage()
{
System.err.println( "Usage: java " + LineCatcher.class.getName() + " <input-pdf>" + " <output-file>");
}
}
正在使用 PDFGraphicsStreamEngine class 提取直线和矩形坐标。线条和矩形的坐标与文本坐标不对齐
绿色：文本 红色：按原样获得的线坐标 黑色：预期坐标（对输出应用变换后获得）
尝试了 setRotation() 方法来纠正 运行 行提取之前的旋转。然而结果并不一致。
使用 PDFBox 获得旋转并获得一致的线/矩形坐标输出的可能选项有哪些？
据我了解这里的需求，OP在可见页面左上角的原点坐标系中工作（考虑页面旋转），x坐标向右递增，y坐标向下递增，单位为PDF默认用户space单位（通常为1/72英寸).
在这个坐标系中他需要以
的形式提取（水平或垂直）线- 左/上端点坐标和
- 宽度/高度。
转换 LineCatcher 结果
另一方面，他从 Tilman 那里得到的助手 class LineCatcher 没有 考虑页面旋转。此外，它 return 是垂直线的 底部 端点，而不是顶端端点。因此，必须对 LineCatcher 结果应用坐标变换。
为此只需替换
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x = Double.toString(rect.getX());
String y = Double.toString(page_height - rect.getY()) ;
String w = Double.toString(rect.getWidth());
String h = Double.toString(rect.getHeight());
writeToFile(pageNum, x, y, w, h, osw);
}
来自
int pageRotation = page.getRotation();
PDRectangle pageCropBox = page.getCropBox();
for(Rectangle2D rect:rectList) {
String pageNum = Integer.toString(n + 1);
String x, y, w, h;
switch(pageRotation) {
case 0:
x = Double.toString(rect.getX() - pageCropBox.getLowerLeftX());
y = Double.toString(pageCropBox.getUpperRightY() - rect.getY() + rect.getHeight());
w = Double.toString(rect.getWidth());
h = Double.toString(rect.getHeight());
break;
case 90:
x = Double.toString(rect.getY() - pageCropBox.getLowerLeftY());
y = Double.toString(rect.getX() - pageCropBox.getLowerLeftX());
w = Double.toString(rect.getHeight());
h = Double.toString(rect.getWidth());
break;
case 180:
x = Double.toString(pageCropBox.getUpperRightX() - rect.getX() - rect.getWidth());
y = Double.toString(rect.getY() - pageCropBox.getLowerLeftY());
w = Double.toString(rect.getWidth());
h = Double.toString(rect.getHeight());
break;
case 270:
x = Double.toString(pageCropBox.getUpperRightY() - rect.getY() + rect.getHeight());
y = Double.toString(pageCropBox.getUpperRightX() - rect.getX() - rect.getWidth());
w = Double.toString(rect.getHeight());
h = Double.toString(rect.getWidth());
break;
default:
throw new IOException(String.format("Unsupported page rotation %d on page %d.", pageRotation, page));
}
writeToFile(pageNum, x, y, w, h, osw);
}
(ExtractLinesWithDir 测试 testExtractLineRotationTestWithDir)
与 TextPosition.get?DirAdj() 坐标的关系
OP描述坐标参考TextPosition class方法getXDirAdj()和getYDirAdj()。实际上，这些方法 return 在坐标系中坐标系，原点在页面左上角， y 坐标在旋转页面后向下 增加，以便文本竖直绘制.
在示例文档的情况下，所有文本都被绘制为在应用页面旋转后直立。我对上面写的需求的理解由此推导出来。
使用 TextPosition.get?DirAdj() 值作为全局坐标的问题在于，在包含以不同方向绘制文本的页面的文档中，收集的文本坐标突然与不同的坐标系相关。因此，一个通用的解决方案不应该像那样疯狂地收集坐标。相反，它应该首先确定页面方向（例如页面旋转给出的方向或大部分文本共享的方向）并使用该方向给出的固定坐标系中的坐标加上文本书写方向的指示有问题的作品。