use of org.apache.pdfbox.pdmodel.font.PDType3Font in project pdfbox by apache.
the class LegacyPDFStreamEngine method showGlyph.
/**
* This method was originally written by Ben Litchfield for PDFStreamEngine.
*/
@Override
protected void showGlyph(Matrix textRenderingMatrix, PDFont font, int code, String unicode, Vector displacement) throws IOException {
//
// legacy calculations which were previously in PDFStreamEngine
//
// DO NOT USE THIS CODE UNLESS YOU ARE WORKING WITH PDFTextStripper.
// THIS CODE IS DELIBERATELY INCORRECT
//
PDGraphicsState state = getGraphicsState();
Matrix ctm = state.getCurrentTransformationMatrix();
float fontSize = state.getTextState().getFontSize();
float horizontalScaling = state.getTextState().getHorizontalScaling() / 100f;
Matrix textMatrix = getTextMatrix();
BoundingBox bbox = font.getBoundingBox();
if (bbox.getLowerLeftY() < Short.MIN_VALUE) {
// PDFBOX-2158 and PDFBOX-3130
// files by Salmat eSolutions / ClibPDF Library
bbox.setLowerLeftY(-(bbox.getLowerLeftY() + 65536));
}
// 1/2 the bbox is used as the height todo: why?
float glyphHeight = bbox.getHeight() / 2;
// sometimes the bbox has very high values, but CapHeight is OK
PDFontDescriptor fontDescriptor = font.getFontDescriptor();
if (fontDescriptor != null) {
float capHeight = fontDescriptor.getCapHeight();
if (Float.compare(capHeight, 0) != 0 && (capHeight < glyphHeight || Float.compare(glyphHeight, 0) == 0)) {
glyphHeight = capHeight;
}
}
// transformPoint from glyph space -> text space
float height;
if (font instanceof PDType3Font) {
height = font.getFontMatrix().transformPoint(0, glyphHeight).y;
} else {
height = glyphHeight / 1000;
}
float displacementX = displacement.getX();
// calculate our own
if (font.isVertical()) {
displacementX = font.getWidth(code) / 1000;
// there may be an additional scaling factor for true type fonts
TrueTypeFont ttf = null;
if (font instanceof PDTrueTypeFont) {
ttf = ((PDTrueTypeFont) font).getTrueTypeFont();
} else if (font instanceof PDType0Font) {
PDCIDFont cidFont = ((PDType0Font) font).getDescendantFont();
if (cidFont instanceof PDCIDFontType2) {
ttf = ((PDCIDFontType2) cidFont).getTrueTypeFont();
}
}
if (ttf != null && ttf.getUnitsPerEm() != 1000) {
displacementX *= 1000f / ttf.getUnitsPerEm();
}
}
//
// legacy calculations which were previously in PDFStreamEngine
//
// DO NOT USE THIS CODE UNLESS YOU ARE WORKING WITH PDFTextStripper.
// THIS CODE IS DELIBERATELY INCORRECT
//
// (modified) combined displacement, this is calculated *without* taking the character
// spacing and word spacing into account, due to legacy code in TextStripper
float tx = displacementX * fontSize * horizontalScaling;
float ty = displacement.getY() * fontSize;
// (modified) combined displacement matrix
Matrix td = Matrix.getTranslateInstance(tx, ty);
// (modified) text rendering matrix
// text space -> device space
Matrix nextTextRenderingMatrix = td.multiply(textMatrix).multiply(ctm);
float nextX = nextTextRenderingMatrix.getTranslateX();
float nextY = nextTextRenderingMatrix.getTranslateY();
// (modified) width and height calculations
float dxDisplay = nextX - textRenderingMatrix.getTranslateX();
float dyDisplay = height * textRenderingMatrix.getScalingFactorY();
//
// start of the original method
//
// Note on variable names. There are three different units being used in this code.
// Character sizes are given in glyph units, text locations are initially given in text
// units, and we want to save the data in display units. The variable names should end with
// Text or Disp to represent if the values are in text or disp units (no glyph units are
// saved).
float glyphSpaceToTextSpaceFactor = 1 / 1000f;
if (font instanceof PDType3Font) {
glyphSpaceToTextSpaceFactor = font.getFontMatrix().getScaleX();
}
float spaceWidthText = 0;
try {
// to avoid crash as described in PDFBOX-614, see what the space displacement should be
spaceWidthText = font.getSpaceWidth() * glyphSpaceToTextSpaceFactor;
} catch (Exception exception) {
LOG.warn(exception, exception);
}
if (Float.compare(spaceWidthText, 0) == 0) {
spaceWidthText = font.getAverageFontWidth() * glyphSpaceToTextSpaceFactor;
// the average space width appears to be higher than necessary so make it smaller
spaceWidthText *= .80f;
}
if (Float.compare(spaceWidthText, 0) == 0) {
// if could not find font, use a generic value
spaceWidthText = 1.0f;
}
// the space width has to be transformed into display units
float spaceWidthDisplay = spaceWidthText * textRenderingMatrix.getScalingFactorX();
// use our additional glyph list for Unicode mapping
unicode = font.toUnicode(code, glyphList);
// this, which is why we leave it until this point in PDFTextStreamEngine.
if (unicode == null) {
if (font instanceof PDSimpleFont) {
char c = (char) code;
unicode = new String(new char[] { c });
} else {
// skips them. See the "allah2.pdf" TestTextStripper file.
return;
}
}
// adjust for cropbox if needed
Matrix translatedTextRenderingMatrix;
if (translateMatrix == null) {
translatedTextRenderingMatrix = textRenderingMatrix;
} else {
translatedTextRenderingMatrix = Matrix.concatenate(translateMatrix, textRenderingMatrix);
nextX -= pageSize.getLowerLeftX();
nextY -= pageSize.getLowerLeftY();
}
processTextPosition(new TextPosition(pageRotation, pageSize.getWidth(), pageSize.getHeight(), translatedTextRenderingMatrix, nextX, nextY, Math.abs(dyDisplay), dxDisplay, Math.abs(spaceWidthDisplay), unicode, new int[] { code }, font, fontSize, (int) (fontSize * textMatrix.getScalingFactorX())));
}
use of org.apache.pdfbox.pdmodel.font.PDType3Font in project pdfbox by apache.
the class DrawPrintTextLocations method writeString.
/**
* 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.getUnicode());
// glyph space -> user space
// note: text.getTextMatrix() is *not* the Text Matrix, it's the Text Rendering Matrix
AffineTransform at = text.getTextMatrix().createAffineTransform();
// 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(0, 0, text.getWidthDirAdj() / text.getTextMatrix().getScalingFactorX(), text.getHeightDir() / text.getTextMatrix().getScalingFactorY());
Shape s = at.createTransformedShape(rect);
s = flipAT.createTransformedShape(s);
s = rotateAT.createTransformedShape(s);
g2d.setColor(Color.red);
g2d.draw(s);
// in blue:
// show rectangle with the real vertical bounds, based on the font bounding box y values
// usually, the height is identical to what you see when marking text in Adobe Reader
PDFont font = text.getFont();
BoundingBox bbox = font.getBoundingBox();
// advance width, bbox height (glyph space)
// todo: should iterate all chars
float xadvance = font.getWidth(text.getCharacterCodes()[0]);
rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), xadvance, bbox.getHeight());
if (font instanceof PDType3Font) {
// bbox and font matrix are unscaled
at.concatenate(font.getFontMatrix().createAffineTransform());
} else {
// bbox and font matrix are already scaled to 1000
at.scale(1 / 1000f, 1 / 1000f);
}
s = at.createTransformedShape(rect);
s = flipAT.createTransformedShape(s);
s = rotateAT.createTransformedShape(s);
g2d.setColor(Color.blue);
g2d.draw(s);
}
}
use of org.apache.pdfbox.pdmodel.font.PDType3Font in project pdfbox by apache.
the class DebugPageDrawer method showGlyph.
/**
* Glyph bounding boxes.
*/
@Override
protected void showGlyph(Matrix textRenderingMatrix, PDFont font, int code, String unicode, Vector displacement) throws IOException {
// draw glyph
super.showGlyph(textRenderingMatrix, font, code, unicode, displacement);
if (showGlyphBounds) {
Shape bbox;
// compute visual bounds
if (font instanceof PDType3Font) {
// todo: implement me
return;
} else {
AffineTransform at = textRenderingMatrix.createAffineTransform();
at.concatenate(font.getFontMatrix().createAffineTransform());
// get the path
PDVectorFont vectorFont = (PDVectorFont) font;
GeneralPath path = vectorFont.getNormalizedPath(code);
if (path == null) {
return;
}
// stretch non-embedded glyph if it does not match the width contained in the PDF
if (!font.isEmbedded() && !font.isVertical() && !font.isStandard14() && font.hasExplicitWidth(code)) {
float fontWidth = font.getWidthFromFont(code);
if (// ignore spaces
fontWidth > 0 && Math.abs(fontWidth - displacement.getX() * 1000) > 0.0001) {
float pdfWidth = displacement.getX() * 1000;
at.scale(pdfWidth / fontWidth, 1);
}
}
Shape glyph = at.createTransformedShape(path);
bbox = glyph.getBounds2D();
}
// save
Graphics2D graphics = getGraphics();
Color color = graphics.getColor();
Stroke stroke = graphics.getStroke();
Shape clip = graphics.getClip();
// draw
graphics.setClip(graphics.getDeviceConfiguration().getBounds());
graphics.setColor(Color.cyan);
graphics.setStroke(new BasicStroke(.5f));
graphics.draw(bbox);
// restore
graphics.setStroke(stroke);
graphics.setColor(color);
graphics.setClip(clip);
}
}
use of org.apache.pdfbox.pdmodel.font.PDType3Font in project pdfbox by apache.
the class DrawPrintTextLocations method calculateGlyphBounds.
// this calculates the real (except for type 3 fonts) individual glyph bounds
private Shape calculateGlyphBounds(Matrix textRenderingMatrix, PDFont font, int code) throws IOException {
GeneralPath path = null;
AffineTransform at = textRenderingMatrix.createAffineTransform();
at.concatenate(font.getFontMatrix().createAffineTransform());
if (font instanceof PDType3Font) {
// It is difficult to calculate the real individual glyph bounds for type 3 fonts
// because these are not vector fonts, the content stream could contain almost anything
// that is found in page content streams.
PDType3Font t3Font = (PDType3Font) font;
PDType3CharProc charProc = t3Font.getCharProc(code);
if (charProc != null) {
BoundingBox fontBBox = t3Font.getBoundingBox();
PDRectangle glyphBBox = charProc.getGlyphBBox();
if (glyphBBox != null) {
// PDFBOX-3850: glyph bbox could be larger than the font bbox
glyphBBox.setLowerLeftX(Math.max(fontBBox.getLowerLeftX(), glyphBBox.getLowerLeftX()));
glyphBBox.setLowerLeftY(Math.max(fontBBox.getLowerLeftY(), glyphBBox.getLowerLeftY()));
glyphBBox.setUpperRightX(Math.min(fontBBox.getUpperRightX(), glyphBBox.getUpperRightX()));
glyphBBox.setUpperRightY(Math.min(fontBBox.getUpperRightY(), glyphBBox.getUpperRightY()));
path = glyphBBox.toGeneralPath();
}
}
} else if (font instanceof PDVectorFont) {
PDVectorFont vectorFont = (PDVectorFont) font;
path = vectorFont.getPath(code);
if (font instanceof PDTrueTypeFont) {
PDTrueTypeFont ttFont = (PDTrueTypeFont) font;
int unitsPerEm = ttFont.getTrueTypeFont().getHeader().getUnitsPerEm();
at.scale(1000d / unitsPerEm, 1000d / unitsPerEm);
}
if (font instanceof PDType0Font) {
PDType0Font t0font = (PDType0Font) font;
if (t0font.getDescendantFont() instanceof PDCIDFontType2) {
int unitsPerEm = ((PDCIDFontType2) t0font.getDescendantFont()).getTrueTypeFont().getHeader().getUnitsPerEm();
at.scale(1000d / unitsPerEm, 1000d / unitsPerEm);
}
}
} else if (font instanceof PDSimpleFont) {
PDSimpleFont simpleFont = (PDSimpleFont) font;
// these two lines do not always work, e.g. for the TT fonts in file 032431.pdf
// which is why PDVectorFont is tried first.
String name = simpleFont.getEncoding().getName(code);
path = simpleFont.getPath(name);
} else {
// shouldn't happen, please open issue in JIRA
System.out.println("Unknown font class: " + font.getClass());
}
if (path == null) {
return null;
}
return at.createTransformedShape(path.getBounds2D());
}
Aggregations