List of usage examples for org.apache.pdfbox.util Matrix getTranslateY
public float getTranslateY()
From source file:com.fngry.monk.biz.demo.pdf.pdfbox.PrintImageLocations.java
License:Apache License
/** * This is used to handle an operation./*from w w w .j av a 2s. c om*/ * * @param operator The operation to perform. * @param operands The list of arguments. * * @throws IOException If there is an error processing the operation. */ @Override protected void processOperator(Operator operator, List<COSBase> operands) throws IOException { String operation = operator.getName(); if ("Do".equals(operation)) { COSName objectName = (COSName) operands.get(0); PDXObject xobject = getResources().getXObject(objectName); if (xobject instanceof PDImageXObject) { PDImageXObject image = (PDImageXObject) xobject; if ("png".equals(image.getSuffix())) { return; } int imageWidth = image.getWidth(); int imageHeight = image.getHeight(); // System.out.println("Found image [" + objectName.getName() + "]"); Matrix ctmNew = getGraphicsState().getCurrentTransformationMatrix(); float imageXScale = ctmNew.getScalingFactorX(); float imageYScale = ctmNew.getScalingFactorY(); // position in user space units. 1 unit = 1/72 inch at 72 dpi // System.out.println("position in PDF = " + ctmNew.getTranslateX() + ", " + ctmNew.getTranslateY() + " in user space units"); // // raw size in pixels // System.out.println("raw image size = " + imageWidth + ", " + imageHeight + " in pixels"); // // displayed size in user space units // System.out.println("displayed size = " + imageXScale + ", " + imageYScale + " in user space units"); // displayed size in inches at 72 dpi rendering // imageXScale /= 72; // imageYScale /= 72; // System.out.println("displayed size = " + imageXScale + ", " + imageYScale + " in inches at 72 dpi rendering"); // // displayed size in millimeters at 72 dpi rendering // imageXScale *= 25.4; // imageYScale *= 25.4; // System.out.println("displayed size = " + imageXScale + ", " + imageYScale + " in millimeters at 72 dpi rendering"); System.out.println(); // BufferedImage bufferImage = image.getImage(); // ByteArrayOutputStream os = new ByteArrayOutputStream(); // ImageIO.write(bufferImage, image.getSuffix(), os); // // String fileName = this.pageName + "_" + objectName.getName() + "." + image.getSuffix(); // Path outputFile = new File("/Users/gaorongyu/Downloads/temp/" // + this.pageName + "_" + objectName.getName() + "." + image.getSuffix()).toPath(); ImageInfo imageInfo = new ImageInfo((int) ctmNew.getTranslateX(), (int) ctmNew.getTranslateY(), (int) imageXScale, (int) imageYScale); imageInfo.setImage(image); imageInfo.setObjectName(objectName); imageInfoList.add(imageInfo); // java.nio.file.Files.copy(new ByteArrayInputStream(os.toByteArray()), outputFile); } else if (xobject instanceof PDFormXObject) { PDFormXObject form = (PDFormXObject) xobject; showForm(form); } } else { super.processOperator(operator, operands); } }
From source file:com.repeatability.pdf.PDFTextStreamEngine.java
License:Apache License
/** * This method was originally written by Ben Litchfield for PDFStreamEngine. */// ww w .jav a 2s . c o m @Override protected void showGlyph(Matrix textRenderingMatrix, PDFont font, int code, String unicode, Vector displacement) throws IOException { // // legacy calculations which were previously in PDFStreamEngine // 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 (capHeight != 0 && capHeight < glyphHeight) { 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(); // the sorting algorithm is based on the width of the character. As the displacement // for vertical characters doesn't provide any suitable value for it, we have to // 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(); } } // (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 Matrix nextTextRenderingMatrix = td.multiply(textMatrix).multiply(ctm); // text space -> device space 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 (Throwable exception) { LOG.warn(exception, exception); } if (spaceWidthText == 0) { spaceWidthText = font.getAverageFontWidth() * glyphSpaceToTextSpaceFactor; // the average space width appears to be higher than necessary so make it smaller spaceWidthText *= .80f; } if (spaceWidthText == 0) { spaceWidthText = 1.0f; // if could not find font, use a generic value } // 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); // when there is no Unicode mapping available, Acrobat simply coerces the character code // into Unicode, so we do the same. Subclasses of PDFStreamEngine don't necessarily want // 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 { // Acrobat doesn't seem to coerce composite font's character codes, instead it // 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, dyDisplay, dxDisplay, spaceWidthDisplay, unicode, new int[] { code }, font, fontSize, (int) (fontSize * textMatrix.getScalingFactorX()))); }
From source file:helper.pdfpreprocessing.pdf.TextHighlight.java
License:Apache License
/** * Computes a series of bounding boxes (PDRectangle) from a list of TextPositions. It will create a new bounding box * if the vertical tolerance is exceeded * * @param positions// w w w . j a v a 2 s.c om * @throws IOException */ public List<PDRectangle> getTextBoundingBoxes(final List<TextPosition> positions) { final List<PDRectangle> boundingBoxes = new ArrayList<>(); float lowerLeftX = -1, lowerLeftY = -1, upperRightX = -1, upperRightY = -1; boolean first = true; for (final TextPosition position : positions) { if (position == null) { continue; } final Matrix textPos = position.getTextMatrix(); final float height = position.getHeight() * getHeightModifier(); if (first) { lowerLeftX = textPos.getTranslateX(); upperRightX = lowerLeftX + position.getWidth(); lowerLeftY = textPos.getTranslateY(); upperRightY = lowerLeftY + height; first = false; continue; } // we are still on the same line if (Math.abs(textPos.getTranslateY() - lowerLeftY) <= getVerticalTolerance()) { upperRightX = textPos.getTranslateX() + position.getWidth(); upperRightY = textPos.getTranslateY() + height; } else { final PDRectangle boundingBox = boundingBox(lowerLeftX, lowerLeftY, upperRightX, upperRightY); boundingBoxes.add(boundingBox); // new line lowerLeftX = textPos.getTranslateX(); upperRightX = lowerLeftX + position.getWidth(); lowerLeftY = textPos.getTranslateY(); upperRightY = lowerLeftY + height; } } if (!(lowerLeftX == -1 && lowerLeftY == -1 && upperRightX == -1 && upperRightY == -1)) { final PDRectangle boundingBox = boundingBox(lowerLeftX, lowerLeftY, upperRightX, upperRightY); boundingBoxes.add(boundingBox); } return boundingBoxes; }