I’m working on a Python script to generate PowerPoint slides from a JSON file. The script reads slide content from the JSON file, converts MathML to OMML for mathematical equations, and then inserts the content into a PowerPoint template. However, when I try to open the generated output.pptx file, PowerPoint displays an error:

PowerPoint found a problem with content in output.pptx
PowerPoint can attempt to repair the presentation. If you trust the source of this presentation, click Repair.

When I click “Repair,” PowerPoint attempts to fix the presentation, but the formatting is often broken, and some content is lost.

Here is the relevant part of my code:

def convert_mathml_to_omml(mathml):
    try:
        tree = etree.fromstring(mathml)
        xslt = etree.parse(r'D:MOMLPMOMLPstaticMML2OMML.XSL')
        transform = etree.XSLT(xslt)
        new_dom = transform(tree)
        return new_dom
    except etree.XMLSyntaxError as xml_err:
        print(f"XML Syntax Error: {xml_err}")
    except etree.XSLTParseError as xslt_err:
        print(f"XSLT Parse Error: {xslt_err}")
    except etree.XSLTApplyError as apply_err:
        print(f"XSLT Apply Error: {apply_err}")
    except Exception as err:
        print(f"General Error: {err}")
    return None

def add_slide(prs, title, subtitle=None, content=None):
    try:
        slide_layout = prs.slide_layouts[6]
        slide = prs.slides.add_slide(slide_layout)

        title_placeholder = slide.shapes.title
        content_placeholder = slide.placeholders[1]

        title_placeholder.left = Inches(0.5)
        title_placeholder.top = Inches(0.5)
        title_placeholder.width = Inches(9)
        title_placeholder.height = Inches(1.5)

        title_placeholder.text = title
        if subtitle:
            title_placeholder.text += f"n{subtitle}"

        for paragraph in title_placeholder.text_frame.paragraphs:
            for run in paragraph.runs:
                run.font.size = Pt(15)
                run.font.bold = True

        content_text = []
        mathml_items = []
        if content:
            for item in content:
                if isinstance(item, str):
                    content_text.append(item)
                elif isinstance(item, dict) and 'mathml' in item:
                    mathml_items.append(item['mathml'])

        content_text.append("")

        content_placeholder.left = Inches(1.5)
        content_placeholder.top = Inches(2.0)
        content_placeholder.width = Inches(9)
        content_placeholder.height = Inches(5.5)

        if content_text:
            combined_text = 'n'.join(content_text)
            content_placeholder.text = combined_text

            if mathml_items:
                nsmap = {
                    'a14': "http://schemas.microsoft.com/office/drawing/2010/main",
                    'm': "http://schemas.openxmlformats.org/officeDocument/2006/math"
                }
                wrapper = etree.Element(
                    '{http://schemas.microsoft.com/office/drawing/2010/main}m',
                    nsmap=nsmap
                )
                omml_para = etree.SubElement(
                    wrapper,
                    '{http://schemas.openxmlformats.org/officeDocument/2006/math}oMathPara'
                )

                for mathml in mathml_items:
                    omml = convert_mathml_to_omml(mathml)
                    if omml is not None:
                        omml_para.append(omml.getroot())

                p = content_placeholder.text_frame.add_paragraph()
                p._element.append(wrapper)
                p = content_placeholder.text_frame.add_paragraph()  

            p = content_placeholder.text_frame.add_paragraph()

        for paragraph in content_placeholder.text_frame.paragraphs:
            for run in paragraph.runs:
                run.font.size = Pt(15)
                run.font.name = 'Calibri'
                run.font.bold = False
    except Exception as err:
        print(f"Error adding slide: {err}")

def main(json_file, template_pptx, output_pptx):
    try:
        prs = Presentation(template_pptx)
        
        with open(json_file, 'r') as file:
            slides = json.load(file)

        for i, slide in enumerate(slides):
            title = slide.get('title', '')
            subtitle = slide.get('subtitle', None)
            content = slide.get('content', [])
            add_slide(prs, title, subtitle, content)
            
            if i == 0:
                title_slide = prs.slides[0]
                title_shape = title_slide.shapes.title
                title_shape.text = title
        
        prs.save(output_pptx)
    except Exception as err:
        print(err)
    

Details:

• PowerPoint Template: I’m using a custom PowerPoint template (template.pptx).
• MathML to OMML Conversion: I’m converting MathML to OMML using an XSLT file (MML2OMML.XSL).
• JSON Input: The script reads content from a JSON file and generates slides based on the data.
• Error Handling: The script includes error handling, but the generated PPTX still seems to have some corruption issues.

Problem:

Despite the error handling and the content being generated correctly as far as I can tell, PowerPoint reports an issue with the file when attempting to open it. I suspect it might be related to the way I’m embedding the OMML content, but I’m not sure.

1. What could be causing PowerPoint to throw this error?
2. Is there a better way to embed MathML/OMML in PowerPoint using Python?
3. How can I debug or validate the PowerPoint XML to identify the specific issue?

Any help or insights would be greatly appreciated!