Function readPptxFile

tool/office_ppt_read.go:68–109

── goppt helpers ───────────────────────────────────────────────────────────── readPptxFile opens a .pptx file and returns its text content formatted as one section per slide.

(path string)

// readPptxFile opens a .pptx file and returns its text content formatted
// as one section per slide.
func readPptxFile(path string) (string, error) {
	reader := &ppt.PPTXReader{}
	pres, err := reader.Read(path)
	if err != nil {
		return "", err
	}

	slideCount := pres.GetSlideCount()
	if slideCount == 0 {
		return "", fmt.Errorf("the PowerPoint file contains no slides")
	}

	var sb strings.Builder
	fmt.Fprintf(&sb, "Total slides: %d\n", slideCount)

	for i := 0; i < slideCount; i++ {
		slide, err := pres.GetSlide(i)
		if err != nil {
			continue
		}

		name := slide.GetName()
		if name == "" {
			name = fmt.Sprintf("Slide %d", i+1)
		}
		fmt.Fprintf(&sb, "\n=== %s ===\n", name)

		for _, shape := range slide.GetShapes() {
			text := extractShapeText(shape)
			text = strings.TrimSpace(text)
			if text != "" {
				sb.WriteString(text)
				sb.WriteByte('\n')
			}
		}

		if notes := strings.TrimSpace(slide.GetNotes()); notes != "" {
			fmt.Fprintf(&sb, "[Notes] %s\n", notes)
		}
	}
	return sb.String(), nil
}

// extractShapeText recursively extracts all text from a Shape.
func extractShapeText(shape ppt.Shape) string {