Method GetPDFTextObjects

deps/tesseract/api/pdfrenderer.cpp:334–504

}

char* TessPDFRenderer::GetPDFTextObjects(TessBaseAPI* api,
                                         double width, double height) {
  STRING pdf_str("");
  double ppi = api->GetSourceYResolution();

  // These initial conditions are all arbitrary and will be overwritten
  double old_x = 0.0, old_y = 0.0;
  int old_fontsize = 0;
  tesseract::WritingDirection old_writing_direction =
      WRITING_DIRECTION_LEFT_TO_RIGHT;
  bool new_block = true;
  int fontsize = 0;
  double a = 1;
  double b = 0;
  double c = 0;
  double d = 1;

  // TODO(jbreiden) This marries the text and image together.
  // Slightly cleaner from an abstraction standpoint if this were to
  // live inside a separate text object.
  pdf_str += "q ";
  pdf_str.add_str_double("", prec(width));
  pdf_str += " 0 0 ";
  pdf_str.add_str_double("", prec(height));
  pdf_str += " 0 0 cm";
  if (!textonly_) {
    pdf_str += " /Im1 Do";
  }
  pdf_str += " Q\n";

  int line_x1 = 0;
  int line_y1 = 0;
  int line_x2 = 0;
  int line_y2 = 0;

  ResultIterator *res_it = api->GetIterator();
  while (!res_it->Empty(RIL_BLOCK)) {
    if (res_it->IsAtBeginningOf(RIL_BLOCK)) {
      pdf_str += "BT\n3 Tr";     // Begin text object, use invisible ink
      old_fontsize = 0;          // Every block will declare its fontsize
      new_block = true;          // Every block will declare its affine matrix
    }

    if (res_it->IsAtBeginningOf(RIL_TEXTLINE)) {
      int x1, y1, x2, y2;
      res_it->Baseline(RIL_TEXTLINE, &x1, &y1, &x2, &y2);
      ClipBaseline(ppi, x1, y1, x2, y2, &line_x1, &line_y1, &line_x2, &line_y2);
    }

    if (res_it->Empty(RIL_WORD)) {
      res_it->Next(RIL_WORD);
      continue;
    }

    // Writing direction changes at a per-word granularity
    tesseract::WritingDirection writing_direction;
    {
      tesseract::Orientation orientation;