Java PDType3Font类代码示例

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
/**
 * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
 * Render Type3 font character as image using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
 * 4700198773.pdf
 * </a>
 * from
 * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
 * extract text with custom font result non readble
 * </a>
 * <p>
 * This test shows how one can render individual Type 3 font glyphs as bitmaps.
 * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
 * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
 * with the glyph in question and render that page.   
 * </p>
 * <p>
 * As the OP did not provide a sample PDF, we simply use one from another
 * stackoverflow question. There obviously might remain issues with the
 * OP's files.
 * </p>
 */
@Test
public void testRenderSdnList() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("sdnlist.pdf"))
    {
        PDDocument document = PDDocument.load(resource);

        PDPage page = document.getPage(1);
        PDResources pageResources = page.getResources();
        COSName f1Name = COSName.getPDFName("R144");
        PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
        Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

        COSDictionary charProcsDictionary = fontF1.getCharProcs();
        for (COSName key : charProcsDictionary.keySet())
        {
            COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
            PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
            PDRectangle bbox = charProc.getGlyphBBox();
            if (bbox == null)
                bbox = charProc.getBBox();
            Integer code = f1NameToCode.get(key.getName());

            if (code != null)
            {
                PDDocument charDocument = new PDDocument();
                PDPage charPage = new PDPage(bbox);
                charDocument.addPage(charPage);
                charPage.setResources(pageResources);
                PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                charContentStream.beginText();
                charContentStream.setFont(fontF1, bbox.getHeight());
                charContentStream.getOutput().write(String.format("<%2X> Tj\n", code).getBytes());
                charContentStream.endText();
                charContentStream.close();

                File result = new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.png", key.getName(), code));
                PDFRenderer renderer = new PDFRenderer(charDocument);
                BufferedImage image = renderer.renderImageWithDPI(0, 96);
                ImageIO.write(image, "PNG", result);
                charDocument.save(new File(RESULT_FOLDER, String.format("sdnlist-%s-%s.pdf", key.getName(), code)));
                charDocument.close();
            }
        }
    }
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
/**
 * <a href="http://stackoverflow.com/questions/42032729/render-type3-font-character-as-image-using-pdfbox">
 * Render Type3 font character as image using PDFBox
 * </a>
 * <br/>
 * <a href="https://drive.google.com/file/d/0B0f6X4SAMh2KRDJTbm4tb3E1a1U/view">
 * 4700198773.pdf
 * </a>
 * from
 * <a href="http://stackoverflow.com/questions/37754112/extract-text-with-custom-font-result-non-readble">
 * extract text with custom font result non readble
 * </a>
 * <p>
 * This test shows how one can render individual Type 3 font glyphs as bitmaps.
 * Unfortunately PDFBox out-of-the-box does not provide a class to render contents
 * of arbitrary XObjects, merely for rendering pages; thus, we simply create a page
 * with the glyph in question and render that page.   
 * </p>
 * <p>
 * As the OP did not provide a sample PDF, we simply use one from another
 * stackoverflow question. There obviously might remain issues with the
 * OP's files.
 * </p>
 */
@Test
public void testRender4700198773() throws IOException
{
    try (   InputStream resource = getClass().getResourceAsStream("4700198773.pdf"))
    {
        PDDocument document = PDDocument.load(resource);

        PDPage page = document.getPage(0);
        PDResources pageResources = page.getResources();
        COSName f1Name = COSName.getPDFName("F1");
        PDType3Font fontF1 = (PDType3Font) pageResources.getFont(f1Name);
        Map<String, Integer> f1NameToCode = fontF1.getEncoding().getNameToCodeMap();

        COSDictionary charProcsDictionary = fontF1.getCharProcs();
        for (COSName key : charProcsDictionary.keySet())
        {
            COSStream stream = (COSStream) charProcsDictionary.getDictionaryObject(key);
            PDType3CharProc charProc = new PDType3CharProc(fontF1, stream);
            PDRectangle bbox = charProc.getGlyphBBox();
            if (bbox == null)
                bbox = charProc.getBBox();
            Integer code = f1NameToCode.get(key.getName());

            if (code != null)
            {
                PDDocument charDocument = new PDDocument();
                PDPage charPage = new PDPage(bbox);
                charDocument.addPage(charPage);
                charPage.setResources(pageResources);
                PDPageContentStream charContentStream = new PDPageContentStream(charDocument, charPage);
                charContentStream.beginText();
                charContentStream.setFont(fontF1, bbox.getHeight());
                charContentStream.getOutput().write(String.format("<%2X> Tj\n", code).getBytes());
                charContentStream.endText();
                charContentStream.close();

                File result = new File(RESULT_FOLDER, String.format("4700198773-%s-%s.png", key.getName(), code));
                PDFRenderer renderer = new PDFRenderer(charDocument);
                BufferedImage image = renderer.renderImageWithDPI(0, 96);
                ImageIO.write(image, "PNG", result);
                charDocument.save(new File(RESULT_FOLDER, String.format("4700198773-%s-%s.pdf", key.getName(), code)));
                charDocument.close();
            }
        }
    }
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
/**
 * Computes the normalized fontname of the font. This is a string with only
 * the fontname and no additional style informations (like "bold" or
 * "italic").
 * 
 * @param font
 *          the font to analyze.
 * @return the derived font name.
 */
public static String computeBasename(PDFont font) {
  // Terminate all whitespaces, commas and hyphens
  String fontname = null;
  
  if (font != null) {
    if (font instanceof PDType3Font) {
      fontname = "type3";
    } else {
      fontname = font.getName().toLowerCase();
      
      // Terminate trailing characters up to the "+".
      // As far as I know, these characters are used in names of embedded
      // fonts. If the embedded font can't be read, we'll try to find it here.
      if (fontname.indexOf("+") > -1) {
        fontname = fontname.substring(fontname.indexOf("+") + 1);
      }
    }
  }

  return fontname;
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
/**
 * Computes the normalized fontname of the font. This is a string with only
 * the fontname and no additional style informations (like "bold" or
 * "italic").
 * 
 * @param font
 *          the font to analyze.
 * @return the derived font name.
 */
public static String computeBasename(PDFont font) {
  // Terminate all whitespaces, commas and hyphens
  String fontname;
  if (font instanceof PDType3Font) {
    fontname = "type3";
  } else {
    fontname = font.getName().toLowerCase();

    // Terminate trailing characters up to the "+".
    // As far as I know, these characters are used in names of embedded fonts
    // If the embedded font can't be read, we'll try to find it here
    if (fontname.indexOf("+") > -1) {
      fontname = fontname.substring(fontname.indexOf("+") + 1);
    }
  }

  return fontname;
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
@Override
protected void writeString(String text, List<TextPosition> textPositions) throws IOException {
    text = text.toLowerCase();
    int index = text.indexOf(mTextToHighlight);
    if (index != -1) {
        PDPage currentPage = getCurrentPage();
        PDRectangle pageBoundingBox = currentPage.getBBox();
        AffineTransform flip = new AffineTransform();
        flip.translate(0, pageBoundingBox.getHeight());
        flip.scale(1, -1);
        PDRectangle mediaBox = currentPage.getMediaBox();
        float mediaHeight = mediaBox.getHeight();
        float mediaWidth = mediaBox.getWidth();
        int size = textPositions.size();
        while (index != -1) {
            int last = index + mTextToHighlight.length() - 1;
            for (int i = index; i <= last; i++) {
                TextPosition pos = textPositions.get(i);
                PDFont font = pos.getFont();
                BoundingBox bbox = font.getBoundingBox();
                Rectangle2D.Float rect = new Rectangle2D.Float(0, bbox.getLowerLeftY(), font.getWidth(pos.getCharacterCodes()[0]), bbox.getHeight());
                AffineTransform at = pos.getTextMatrix().createAffineTransform();
                if (font instanceof PDType3Font) {
                    at.concatenate(font.getFontMatrix().createAffineTransform());
                } else {
                    at.scale(1 / 1000f, 1 / 1000f);
                }
                Shape shape = flip.createTransformedShape(at.createTransformedShape(rect));
                AffineTransform transform = mGC.getTransform();
                int rotation = currentPage.getRotation();
                if (rotation != 0) {
                    switch (rotation) {
                        case 90:
                            mGC.translate(mediaHeight, 0);
                            break;
                        case 270:
                            mGC.translate(0, mediaWidth);
                            break;
                        case 180:
                            mGC.translate(mediaWidth, mediaHeight);
                            break;
                        default:
                            break;
                    }
                    mGC.rotate(Math.toRadians(rotation));
                }
                mGC.fill(shape);
                if (rotation != 0) {
                    mGC.setTransform(transform);
                }
            }
            index = last < size - 1 ? text.indexOf(mTextToHighlight, last + 1) : -1;
        }
    }
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
/**
 * The default constructor.
 */
protected PdfBoxFont(PDFont font) {
  this();
  this.font = font;
  
  this.name = font.getName();
  this.basename = computeBasename(font);
  this.isType3Font = font instanceof PDType3Font;
  // pdfFont.isSymbolicFont = font.isSymbolicFont(); TODO
  
  // Normalize all kinds of fonttypes. There are several possible version
  // which have to be normalized e.g. Arial,Bold Arial-BoldMT
  // Helvetica-oblique ...
  this.basename = this.basename.replaceAll(" ", "")
      .replaceAll(",", "")
      .replaceAll("-", "");
  
  int length1 = this.basename.length();
  this.basename = this.basename.replaceAll("extrabold", "")
      .replaceAll("bold", "")
      .replaceAll("black", "");
  int length2 = this.basename.length();
  this.isBold = length2 < length1;
  
  this.basename = this.basename.replaceAll("italic", "")
      .replaceAll("oblique", "");
  length1 = this.basename.length();
  this.isItalic = length1 < length2;
  
  this.basename = this.basename
      .replaceAll("condensed", "")
      .replaceAll("medium", "")
      .replaceAll("regular", "")
      .replaceAll("light", "");
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
@Override
public boolean isType3Font() {
  return font instanceof PDType3Font;
}
 

import org.apache.pdfbox.pdmodel.font.PDType3Font; //导入依赖的package包/类
@Override
public void showLigature(String[] unicodes, int code, PDFont font, 
    Matrix trm) throws IOException {
  super.showLigature(unicodes, code, font, trm);
  
  float size = getGraphicsState().getTextState().getFontSize();
  PDColor nonStrokingColor = getGraphicsState().getNonStrokingColor();
  PdfBoxColor color = PdfBoxColor.create(nonStrokingColor);
  PdfBoxFont pdfFont = PdfBoxFont.create(font);

  Rectangle boundingBox = null;
  if (font instanceof PDType3Font) {
    processType3Stream(((PDType3Font) font).getCharProc(code), trm);
    boundingBox = getCurrentType3GlyphBoundingBox();
  } else {
    boundingBox = getFontGlyphBoundingBox(code, font, trm);
  }

  if (boundingBox == null) {
    boundingBox = getDefaultBoundingBox(code, font, trm);
  } else {
    Rectangle defaultBoundingBox = getDefaultBoundingBox(code, font, trm);
    boundingBox.setMinX(defaultBoundingBox.getMinX());
    boundingBox.setMaxX(defaultBoundingBox.getMaxX());
  }

  float widthPerUnicode = boundingBox.getWidth() / (float) unicodes.length;

  for (int i = 0; i < unicodes.length; i++) {
    float minX = boundingBox.getMinX() + i * widthPerUnicode;
    float maxX = minX + widthPerUnicode;
    float minY = boundingBox.getMinY();
    float maxY = boundingBox.getMaxY();
    Rectangle newBoundBox = new SimpleRectangle(minX, minY, maxX, maxY);

    PdfBoxCharacter character = new PdfBoxCharacter(currentPage, unicodes[i]);
    character.setCharCode(code);
    character.setRectangle(newBoundBox);
    character.setTextRenderingMatrix(trm);
    character.setFont(pdfFont);
    character.setFontsize(size);
    character.setColor(color);
   
    showPdfTextCharacter(character);
  }
}