hocrpdf.py 文件源码

def process_pdf(self, image_data, hocr_data, pdf_filename):
        """Utility function if you'd rather get the PDF data back instead of save it automatically."""
        pdf = Canvas(pdf_filename, pageCompression=1)
        pdf.setCreator('hocr-tools')
        pdf.setPageSize((self.width, self.height))
        pdf.drawImage(image_data, 0, 0, width=self.width, height=self.height)
        pdf = self.add_text_layer(pdf, hocr_data)
        pdf_data = pdf.getpdfdata()
        return pdf_data