Add generated PPTX slides and improved converter script

scripts/convert_slides_to_pptx.py

@@ -1,128 +1,419 @@
 #!/usr/bin/env python3
 """
-Convert markdown slides to PowerPoint (PPTX) format
-Requires: python-pptx
+Convert session markdown slides to styled PowerPoint presentations.
 
-Install: pip install python-pptx
+Run from the infy/ directory:
+    python3 scripts/convert_slides_to_pptx.py
+
+Requires: pip install python-pptx
 """
 
+import re
 from pptx import Presentation
 from pptx.util import Inches, Pt
-from pptx.enum.text import PP_ALIGN
 from pptx.dml.color import RGBColor
-import re
-import sys
+from pptx.enum.text import PP_ALIGN
 
-def markdown_to_pptx(md_file, pptx_file):
-    """Convert markdown slides to PPTX format."""
-    
-    # Read markdown file
-    with open(md_file, 'r') as f:
-        content = f.read()
-    
-    # Split by slide delimiter (---)
-    slides_text = content.split('\n---\n')
-    
-    # Create presentation
-    prs = Presentation()
-    prs.slide_width = Inches(10)
-    prs.slide_height = Inches(7.5)
-    
-    # Define color scheme
-    TITLE_COLOR = RGBColor(0, 102, 204)  # Blue
-    TEXT_COLOR = RGBColor(50, 50, 50)    # Dark gray
-    
-    for slide_content in slides_text:
-        slide_content = slide_content.strip()
-        if not slide_content:
+# ── Brand colours ───────────────────────────────────────────────────────────
+HF_ORANGE   = RGBColor(0xFF, 0x6B, 0x35)   # Hugging Face orange
+HF_DARK     = RGBColor(0x1C, 0x1C, 0x1C)   # Near-black
+HF_BLUE     = RGBColor(0x00, 0x62, 0xCC)   # Accent blue
+CODE_BG     = RGBColor(0xF0, 0xF0, 0xF0)   # Light grey (code bg)
+CODE_FG     = RGBColor(0x2D, 0x2D, 0x2D)   # Dark (code text)
+SUBHEAD_CLR = RGBColor(0x00, 0x62, 0xCC)   # Blue subheadings
+TEXT_CLR    = RGBColor(0x33, 0x33, 0x33)   # Body text
+WHITE       = RGBColor(0xFF, 0xFF, 0xFF)
+INLINE_CODE = RGBColor(0xC7, 0x26, 0x3B)   # Red-ish for inline code
+QUOTE_BG    = RGBColor(0xFF, 0xF3, 0xED)   # Light orange (blockquote bg)
+TABLE_HDR   = RGBColor(0xFF, 0x6B, 0x35)   # Header row colour
+BORDER_CLR  = RGBColor(0xCC, 0xCC, 0xCC)   # Light grey border
+
+# ── Slide dimensions (widescreen 16:9) ──────────────────────────────────────
+SW          = Inches(13.33)
+SH          = Inches(7.5)
+MARGIN      = Inches(0.5)
+TITLE_H     = Inches(1.2)
+BODY_TOP    = Inches(1.45)
+BODY_BOTTOM = Inches(7.2)
+BODY_W      = SW - 2 * MARGIN
+
+# ── Low-level helpers ────────────────────────────────────────────────────────
+
+def _set_bg(slide, rgb: RGBColor):
+    f = slide.background.fill
+    f.solid()
+    f.fore_color.rgb = rgb
+
+
+def _add_rect(slide, x, y, w, h, rgb: RGBColor, border_rgb=None):
+    shape = slide.shapes.add_shape(1, x, y, w, h)   # 1 = rectangle
+    shape.fill.solid()
+    shape.fill.fore_color.rgb = rgb
+    if border_rgb:
+        shape.line.color.rgb = border_rgb
+        shape.line.width = Pt(0.5)
+    else:
+        shape.line.color.rgb = rgb   # same colour as fill → invisible border
+    return shape
+
+
+def _add_runs(para, text: str, base_size, base_color: RGBColor, base_bold=False):
+    """Append inline-formatted runs (**bold** and `code`) to an existing paragraph."""
+    parts = re.split(r'(\*\*[^*]+?\*\*|`[^`]+?`|\*[^*]+?\*)', text)
+    for part in parts:
+        if not part:
             continue
-        
-        # Add blank slide
-        blank_slide_layout = prs.slide_layouts[6]
-        slide = prs.slides.add_slide(blank_slide_layout)
-        
-        # Add background
-        background = slide.background
-        fill = background.fill
-        fill.solid()
-        fill.fore_color.rgb = RGBColor(255, 255, 255)
-        
-        # Parse slide content
-        lines = slide_content.split('\n')
-        
-        # Add title (first line with #)
-        title_found = False
-        current_y = Inches(0.5)
-        
-        for line in lines:
-            if line.startswith('# '):
-                title_box = slide.shapes.add_textbox(Inches(0.5), current_y, Inches(9), Inches(1))
-                title_frame = title_box.text_frame
-                title_frame.word_wrap = True
-                p = title_frame.paragraphs[0]
-                p.text = line.replace('# ', '')
-                p.font.size = Pt(44)
-                p.font.bold = True
-                p.font.color.rgb = TITLE_COLOR
-                current_y += Inches(1.2)
-                title_found = True
-                break
-            elif line.startswith('## '):
-                title_box = slide.shapes.add_textbox(Inches(0.5), current_y, Inches(9), Inches(1))
-                title_frame = title_box.text_frame
-                title_frame.word_wrap = True
-                p = title_frame.paragraphs[0]
-                p.text = line.replace('## ', '')
-                p.font.size = Pt(36)
-                p.font.bold = True
-                p.font.color.rgb = TITLE_COLOR
-                current_y += Inches(0.8)
+        run = para.add_run()
+        if part.startswith('**') and part.endswith('**'):
+            run.text = part[2:-2]
+            run.font.bold = True
+            run.font.size = base_size
+            run.font.color.rgb = base_color
+        elif part.startswith('`') and part.endswith('`'):
+            run.text = part[1:-1]
+            run.font.name = 'Courier New'
+            run.font.size = Pt(max(base_size.pt - 2, 10))
+            run.font.color.rgb = INLINE_CODE
+        elif part.startswith('*') and part.endswith('*'):
+            run.text = part[1:-1]
+            run.font.italic = True
+            run.font.size = base_size
+            run.font.color.rgb = base_color
+        else:
+            run.text = part
+            run.font.bold = base_bold
+            run.font.size = base_size
+            run.font.color.rgb = base_color
+
+
+# ── Markdown parser ──────────────────────────────────────────────────────────
+
+def parse_slides(content: str):
+    """
+    Split content into a list of (title, items[]) tuples, one per slide.
+
+    A new slide begins whenever a `---`-separated block starts with a #/##
+    heading.  Continuation blocks (no heading) are merged into the previous
+    slide so that e.g. presenter details on a title slide don't become a
+    separate slide.
+    """
+    raw_blocks = re.split(r'\n---\n', content)
+    merged = []
+    current = None
+    for block in raw_blocks:
+        block = block.strip()
+        if not block:
+            continue
+        if re.match(r'^#{1,2} ', block):
+            if current is not None:
+                merged.append(current)
+            current = block
+        else:
+            if current is not None:
+                current += '\n' + block
+            else:
+                current = block
+    if current:
+        merged.append(current)
+
+    return [_parse_one_slide(s) for s in merged]
+
+
+def _parse_one_slide(raw: str):
+    """
+    Parse one slide's text into (title, items[]).
+
+    Item shapes:
+      {'type': 'subheading', 'text': str}
+      {'type': 'bullet',     'text': str, 'level': int}
+      {'type': 'code',       'lines': list[str]}
+      {'type': 'quote',      'text': str}
+      {'type': 'table_row',  'cells': list[str], 'header': bool}
+      {'type': 'text',       'text': str}
+      {'type': 'separator'}
+    """
+    lines = raw.strip().split('\n')
+    title = ''
+    items = []
+    title_found = False
+    in_code = False
+    code_buf = []
+    table_next_header = True
+
+    for line in lines:
+        # ── Code fence ──
+        if line.strip().startswith('```'):
+            if in_code:
+                items.append({'type': 'code', 'lines': list(code_buf)})
+                code_buf.clear()
+                in_code = False
+            else:
+                in_code = True
+            continue
+        if in_code:
+            code_buf.append(line)
+            continue
+
+        # ── Slide title (first # or ## heading) ──
+        if not title_found:
+            if line.startswith('## ') or line.startswith('# '):
+                raw_title = re.sub(r'^#{1,2} ', '', line).strip()
+                title = re.sub(r'^Slide \d+[\.:]\s*', '', raw_title)
                 title_found = True
-                break
-        
-        # Add content (remaining lines)
-        if title_found:
-            lines = lines[1:]
-        
-        content_text = '\n'.join(lines).strip()
-        if content_text:
-            # Remove markdown formatting
-            content_text = re.sub(r'\*\*(.*?)\*\*', r'\1', content_text)  # Bold
-            content_text = re.sub(r'\*(.*?)\*', r'\1', content_text)      # Italic
-            content_text = re.sub(r'`(.*?)`', r'\1', content_text)        # Code
-            
-            content_box = slide.shapes.add_textbox(Inches(0.5), current_y, Inches(9), Inches(5.5))
-            text_frame = content_box.text_frame
-            text_frame.word_wrap = True
-            
-            p = text_frame.paragraphs[0]
-            p.text = content_text
-            p.font.size = Pt(18)
-            p.font.color.rgb = TEXT_COLOR
-            p.level = 0
-    
-    # Save presentation
+                continue
+
+        # ── Decorative separator inside a slide ──
+        if line.strip() in ('---', '***'):
+            items.append({'type': 'separator'})
+            continue
+
+        # ── ### subheading ──
+        if line.startswith('### '):
+            items.append({'type': 'subheading', 'text': line[4:].strip()})
+            table_next_header = True
+            continue
+
+        # ── Blockquote ──
+        if line.startswith('> '):
+            items.append({'type': 'quote', 'text': line[2:].strip()})
+            continue
+
+        # ── Table row ──
+        if line.strip().startswith('|'):
+            if re.match(r'^\|[\-\s\|:]+\|$', line.strip()):
+                table_next_header = False
+                continue   # separator row
+            cells = [c.strip() for c in line.strip().strip('|').split('|')]
+            items.append({'type': 'table_row', 'cells': cells,
+                          'header': table_next_header})
+            table_next_header = False
+            continue
+
+        # ── Bullet / numbered list ──
+        m = re.match(r'^(\s*)([-*•]|\d+\.)\s+(.+)$', line)
+        if m:
+            level = len(m.group(1)) // 2
+            items.append({'type': 'bullet', 'text': m.group(3), 'level': level})
+            table_next_header = True
+            continue
+
+        # ── Empty line ──
+        if not line.strip():
+            continue
+
+        # ── Plain / bold text ──
+        items.append({'type': 'text', 'text': line.strip()})
+        table_next_header = True
+
+    return title, items
+
+
+# ── Slide renderer ───────────────────────────────────────────────────────────
+
+def _get_blank_layout(prs):
+    for layout in prs.slide_layouts:
+        if 'blank' in layout.name.lower():
+            return layout
+    return prs.slide_layouts[6]
+
+
+def render_slide(prs: Presentation, title: str, items: list):
+    """Add one fully-styled slide to the presentation."""
+    slide = prs.slides.add_slide(_get_blank_layout(prs))
+    _set_bg(slide, WHITE)
+
+    # ─ Orange title bar ─
+    _add_rect(slide, 0, 0, SW, TITLE_H, HF_ORANGE)
+    _add_rect(slide, 0, TITLE_H, SW, Inches(0.045), HF_DARK)
+
+    # ─ Title text ─
+    tb = slide.shapes.add_textbox(MARGIN, Inches(0.22), BODY_W, Inches(0.92))
+    tf = tb.text_frame
+    tf.word_wrap = True
+    p = tf.paragraphs[0]
+    run = p.add_run()
+    run.text = title or 'Slide'
+    run.font.size = Pt(30)
+    run.font.bold = True
+    run.font.color.rgb = WHITE
+
+    # ─ Body ─
+    y = BODY_TOP
+    table_rows = []
+
+    def flush_table():
+        nonlocal y
+        if not table_rows:
+            return
+        row_h = Inches(0.32)
+        h = row_h * len(table_rows) + Inches(0.15)
+        if y + h > BODY_BOTTOM:
+            table_rows.clear()
+            return
+        _add_rect(slide, MARGIN, y, BODY_W, h,
+                  RGBColor(0xF8, 0xF8, 0xF8), border_rgb=BORDER_CLR)
+        ttb = slide.shapes.add_textbox(
+            MARGIN + Inches(0.12), y + Inches(0.06),
+            BODY_W - Inches(0.24), h - Inches(0.1))
+        ttf = ttb.text_frame
+        ttf.word_wrap = True
+        for i, row_item in enumerate(table_rows):
+            tp = ttf.paragraphs[0] if i == 0 else ttf.add_paragraph()
+            is_hdr = row_item.get('header', False)
+            run = tp.add_run()
+            run.text = '  │  '.join(row_item['cells'])
+            run.font.size = Pt(12)
+            run.font.name = 'Courier New'
+            run.font.bold = is_hdr
+            run.font.color.rgb = TABLE_HDR if is_hdr else HF_DARK
+        y += h + Inches(0.1)
+        table_rows.clear()
+
+    for item in items:
+        # flush pending table if moving to a non-table item
+        if item['type'] != 'table_row' and table_rows:
+            flush_table()
+
+        itype = item['type']
+
+        # ── Code block ──────────────────────────────────────────────────────
+        if itype == 'code':
+            code_lines = item['lines']
+            n = len(code_lines)
+            if n == 0:
+                continue
+            h = Inches(0.26) * n + Inches(0.22)
+            h = min(h, BODY_BOTTOM - y)
+            if y + Inches(0.4) > BODY_BOTTOM:
+                continue
+            _add_rect(slide, MARGIN, y, BODY_W, h, CODE_BG, border_rgb=BORDER_CLR)
+            ctb = slide.shapes.add_textbox(
+                MARGIN + Inches(0.15), y + Inches(0.1),
+                BODY_W - Inches(0.3), h - Inches(0.15))
+            ctf = ctb.text_frame
+            ctf.word_wrap = False
+            visible = max(1, int((h - Inches(0.15)) / Inches(0.26)))
+            for i, cl in enumerate(code_lines[:visible]):
+                cp = ctf.paragraphs[0] if i == 0 else ctf.add_paragraph()
+                run = cp.add_run()
+                run.text = cl
+                run.font.name = 'Courier New'
+                run.font.size = Pt(11)
+                run.font.color.rgb = CODE_FG
+            y += h + Inches(0.12)
+
+        # ── Table row ───────────────────────────────────────────────────────
+        elif itype == 'table_row':
+            table_rows.append(item)
+
+        # ── ### Subheading ──────────────────────────────────────────────────
+        elif itype == 'subheading':
+            h = Inches(0.44)
+            if y + h > BODY_BOTTOM:
+                continue
+            stb = slide.shapes.add_textbox(MARGIN, y, BODY_W, h)
+            stf = stb.text_frame
+            stf.word_wrap = True
+            p = stf.paragraphs[0]
+            _add_runs(p, item['text'], Pt(19), SUBHEAD_CLR, base_bold=True)
+            y += h
+
+        # ── Blockquote ──────────────────────────────────────────────────────
+        elif itype == 'quote':
+            h = Inches(0.5)
+            if y + h > BODY_BOTTOM:
+                continue
+            _add_rect(slide, MARGIN, y, Inches(0.08), h, HF_ORANGE)
+            _add_rect(slide, MARGIN + Inches(0.08), y,
+                      BODY_W - Inches(0.08), h, QUOTE_BG)
+            qtb = slide.shapes.add_textbox(
+                MARGIN + Inches(0.22), y + Inches(0.07),
+                BODY_W - Inches(0.3), h - Inches(0.1))
+            qtf = qtb.text_frame
+            qtf.word_wrap = True
+            qp = qtf.paragraphs[0]
+            _add_runs(qp, item['text'], Pt(17), HF_DARK, base_bold=True)
+            y += h + Inches(0.06)
+
+        # ── Bullet ──────────────────────────────────────────────────────────
+        elif itype == 'bullet':
+            level = item.get('level', 0)
+            indent = Inches(0.36 * (level + 1))
+            h = Inches(0.34)
+            if y + h > BODY_BOTTOM:
+                continue
+            dot = '▸ ' if level == 0 else '◦ '
+            btb = slide.shapes.add_textbox(
+                MARGIN + indent, y, BODY_W - indent, h)
+            btf = btb.text_frame
+            btf.word_wrap = True
+            bp = btf.paragraphs[0]
+            mr = bp.add_run()
+            mr.text = dot
+            mr.font.size = Pt(15)
+            mr.font.color.rgb = HF_ORANGE
+            mr.font.bold = True
+            _add_runs(bp, item['text'], Pt(15), TEXT_CLR)
+            y += h
+
+        # ── Separator ───────────────────────────────────────────────────────
+        elif itype == 'separator':
+            if y + Inches(0.15) <= BODY_BOTTOM:
+                _add_rect(slide, MARGIN, y + Inches(0.06),
+                          BODY_W, Inches(0.02), BORDER_CLR)
+                y += Inches(0.2)
+
+        # ── Plain / bold text ───────────────────────────────────────────────
+        elif itype == 'text':
+            text = item['text']
+            h = Inches(0.36)
+            if y + h > BODY_BOTTOM:
+                continue
+            txtb = slide.shapes.add_textbox(MARGIN, y, BODY_W, h)
+            txtf = txtb.text_frame
+            txtf.word_wrap = True
+            p = txtf.paragraphs[0]
+            _add_runs(p, text, Pt(15), TEXT_CLR)
+            y += h
+
+    # flush any remaining table
+    if table_rows:
+        flush_table()
+
+
+# ── Main ─────────────────────────────────────────────────────────────────────
+
+def markdown_to_pptx(md_file: str, pptx_file: str):
+    with open(md_file, 'r', encoding='utf-8') as f:
+        content = f.read()
+
+    parsed = parse_slides(content)
+    prs = Presentation()
+    prs.slide_width = SW
+    prs.slide_height = SH
+
+    for title, items in parsed:
+        render_slide(prs, title, items)
+
     prs.save(pptx_file)
-    print(f"✅ Converted: {md_file} → {pptx_file}")
-
-if __name__ == "__main__":
-    # Convert both sessions
-    print("=" * 60)
-    print("📊 Converting Markdown Slides to PowerPoint")
-    print("=" * 60 + "\n")
-    
+    print(f'✅  {md_file}  →  {pptx_file}  ({len(parsed)} slides)')
+
+
+if __name__ == '__main__':
+    print('=' * 60)
+    print('📊  Converting Markdown Slides → PowerPoint')
+    print('=' * 60 + '\n')
+
     try:
-        markdown_to_pptx("slides/SESSION1_SLIDES.md", "slides/SESSION1_SLIDES.pptx")
-        markdown_to_pptx("slides/SESSION2_SLIDES.md", "slides/SESSION2_SLIDES.pptx")
-        
-        print("\n" + "=" * 60)
-        print("✅ Conversion complete!")
-        print("=" * 60)
-        print("\n📁 Generated files:")
-        print("  - slides/SESSION1_SLIDES.pptx")
-        print("  - slides/SESSION2_SLIDES.pptx")
-        print("\n💡 Tip: Open in PowerPoint/LibreOffice and adjust formatting as needed")
+        markdown_to_pptx('slides/SESSION1_SLIDES.md', 'slides/SESSION1_SLIDES.pptx')
+        markdown_to_pptx('slides/SESSION2_SLIDES.md', 'slides/SESSION2_SLIDES.pptx')
+        print('\n✅  All done!')
+        print('   slides/SESSION1_SLIDES.pptx')
+        print('   slides/SESSION2_SLIDES.pptx')
+    except ImportError as e:
+        print(f'❌  Missing dependency: {e}')
+        print('\n   Install with:  pip3 install python-pptx')
     except Exception as e:
-        print(f"❌ Error: {str(e)}")
-        print("\n💡 Make sure you have python-pptx installed:")
-        print("   pip install python-pptx")
+        import traceback
+        traceback.print_exc()
+        print(f'\n❌  Error: {e}')