Upload app.py

app.py

@@ -0,0 +1,609 @@
+"""
+Design System Extractor v2 — Main Application
+==============================================
+
+Flow:
+1. User enters URL
+2. Agent 1 discovers pages → User confirms
+3. Agent 1 extracts tokens (Desktop + Mobile)
+4. Agent 2 normalizes tokens
+5. Stage 1 UI: User reviews tokens (accept/reject, Desktop↔Mobile toggle)
+6. Agent 3 proposes upgrades
+7. Stage 2 UI: User selects options with live preview
+8. Agent 4 generates JSON
+9. Stage 3 UI: User exports
+"""
+
+import os
+import asyncio
+import json
+import gradio as gr
+from datetime import datetime
+from typing import Optional
+
+# Get HF token from environment
+HF_TOKEN_FROM_ENV = os.getenv("HF_TOKEN", "")
+
+# =============================================================================
+# GLOBAL STATE
+# =============================================================================
+
+class AppState:
+    """Global application state."""
+    def __init__(self):
+        self.reset()
+    
+    def reset(self):
+        self.discovered_pages = []
+        self.base_url = ""
+        self.desktop_raw = None  # ExtractedTokens
+        self.mobile_raw = None   # ExtractedTokens
+        self.desktop_normalized = None  # NormalizedTokens
+        self.mobile_normalized = None   # NormalizedTokens
+        self.logs = []
+    
+    def log(self, message: str):
+        timestamp = datetime.now().strftime("%H:%M:%S")
+        self.logs.append(f"[{timestamp}] {message}")
+        if len(self.logs) > 100:
+            self.logs.pop(0)
+    
+    def get_logs(self) -> str:
+        return "\n".join(self.logs)
+
+state = AppState()
+
+
+# =============================================================================
+# LAZY IMPORTS
+# =============================================================================
+
+def get_crawler():
+    import agents.crawler
+    return agents.crawler
+
+def get_extractor():
+    import agents.extractor
+    return agents.extractor
+
+def get_normalizer():
+    import agents.normalizer
+    return agents.normalizer
+
+def get_schema():
+    import core.token_schema
+    return core.token_schema
+
+
+# =============================================================================
+# PHASE 1: DISCOVER PAGES
+# =============================================================================
+
+async def discover_pages(url: str, progress=gr.Progress()):
+    """Discover pages from URL."""
+    state.reset()
+    
+    if not url or not url.startswith(("http://", "https://")):
+        return "❌ Please enter a valid URL", "", None
+    
+    state.log(f"🚀 Starting discovery for: {url}")
+    progress(0.1, desc="🔍 Discovering pages...")
+    
+    try:
+        crawler = get_crawler()
+        discoverer = crawler.PageDiscoverer()
+        
+        pages = await discoverer.discover(url)
+        
+        state.discovered_pages = pages
+        state.base_url = url
+        
+        state.log(f"✅ Found {len(pages)} pages")
+        
+        # Format for display
+        pages_data = []
+        for page in pages:
+            pages_data.append([
+                True,  # Selected by default
+                page.url,
+                page.title if page.title else "(No title)",
+                page.page_type.value,
+                "✓" if not page.error else f"⚠ {page.error}"
+            ])
+        
+        progress(1.0, desc="✅ Discovery complete!")
+        
+        status = f"✅ Found {len(pages)} pages. Review and click 'Extract Tokens' to continue."
+        
+        return status, state.get_logs(), pages_data
+        
+    except Exception as e:
+        import traceback
+        state.log(f"❌ Error: {str(e)}")
+        return f"❌ Error: {str(e)}", state.get_logs(), None
+
+
+# =============================================================================
+# PHASE 2: EXTRACT TOKENS
+# =============================================================================
+
+async def extract_tokens(pages_data, progress=gr.Progress()):
+    """Extract tokens from selected pages (both viewports)."""
+    
+    state.log(f"📥 Received pages_data type: {type(pages_data)}")
+    
+    if pages_data is None:
+        return "❌ Please discover pages first", state.get_logs(), None, None
+    
+    # Get selected URLs - handle pandas DataFrame
+    selected_urls = []
+    
+    try:
+        # Check if it's a pandas DataFrame
+        if hasattr(pages_data, 'iterrows'):
+            state.log(f"📥 DataFrame with {len(pages_data)} rows, columns: {list(pages_data.columns)}")
+            
+            for idx, row in pages_data.iterrows():
+                # Get values by column name or position
+                try:
+                    # Try column names first
+                    is_selected = row.get('Select', row.iloc[0] if len(row) > 0 else False)
+                    url = row.get('URL', row.iloc[1] if len(row) > 1 else '')
+                except:
+                    # Fallback to positional
+                    is_selected = row.iloc[0] if len(row) > 0 else False
+                    url = row.iloc[1] if len(row) > 1 else ''
+                
+                if is_selected and url:
+                    selected_urls.append(url)
+        
+        # If it's a dict (Gradio sometimes sends this)
+        elif isinstance(pages_data, dict):
+            state.log(f"📥 Dict with keys: {list(pages_data.keys())}")
+            data = pages_data.get('data', [])
+            for row in data:
+                if isinstance(row, (list, tuple)) and len(row) >= 2 and row[0]:
+                    selected_urls.append(row[1])
+        
+        # If it's a list
+        elif isinstance(pages_data, (list, tuple)):
+            state.log(f"📥 List with {len(pages_data)} items")
+            for row in pages_data:
+                if isinstance(row, (list, tuple)) and len(row) >= 2 and row[0]:
+                    selected_urls.append(row[1])
+                    
+    except Exception as e:
+        state.log(f"❌ Error parsing pages_data: {str(e)}")
+        import traceback
+        state.log(traceback.format_exc())
+    
+    state.log(f"📋 Found {len(selected_urls)} selected URLs")
+    
+    # If still no URLs, try using stored discovered pages
+    if not selected_urls and state.discovered_pages:
+        state.log("⚠️ No URLs from table, using all discovered pages")
+        selected_urls = [p.url for p in state.discovered_pages if not p.error][:10]
+    
+    if not selected_urls:
+        return "❌ No pages selected. Please select pages or rediscover.", state.get_logs(), None, None
+    
+    # Limit to 10 pages for performance
+    selected_urls = selected_urls[:10]
+    
+    state.log(f"📋 Extracting from {len(selected_urls)} pages:")
+    for url in selected_urls[:3]:
+        state.log(f"   • {url}")
+    if len(selected_urls) > 3:
+        state.log(f"   ... and {len(selected_urls) - 3} more")
+    
+    progress(0.05, desc="🚀 Starting extraction...")
+    
+    try:
+        schema = get_schema()
+        extractor_mod = get_extractor()
+        normalizer_mod = get_normalizer()
+        
+        # === DESKTOP EXTRACTION ===
+        state.log("")
+        state.log("🖥️ DESKTOP EXTRACTION (1440px)")
+        progress(0.1, desc="🖥️ Extracting desktop tokens...")
+        
+        desktop_extractor = extractor_mod.TokenExtractor(viewport=schema.Viewport.DESKTOP)
+        
+        def desktop_progress(p):
+            progress(0.1 + (p * 0.35), desc=f"🖥️ Desktop... {int(p*100)}%")
+        
+        state.desktop_raw = await desktop_extractor.extract(selected_urls, progress_callback=desktop_progress)
+        
+        state.log(f"   Raw: {len(state.desktop_raw.colors)} colors, {len(state.desktop_raw.typography)} typography, {len(state.desktop_raw.spacing)} spacing")
+        
+        # Normalize desktop
+        state.log("   Normalizing...")
+        state.desktop_normalized = normalizer_mod.normalize_tokens(state.desktop_raw)
+        state.log(f"   Normalized: {len(state.desktop_normalized.colors)} colors, {len(state.desktop_normalized.typography)} typography, {len(state.desktop_normalized.spacing)} spacing")
+        
+        # === MOBILE EXTRACTION ===
+        state.log("")
+        state.log("📱 MOBILE EXTRACTION (375px)")
+        progress(0.5, desc="📱 Extracting mobile tokens...")
+        
+        mobile_extractor = extractor_mod.TokenExtractor(viewport=schema.Viewport.MOBILE)
+        
+        def mobile_progress(p):
+            progress(0.5 + (p * 0.35), desc=f"📱 Mobile... {int(p*100)}%")
+        
+        state.mobile_raw = await mobile_extractor.extract(selected_urls, progress_callback=mobile_progress)
+        
+        state.log(f"   Raw: {len(state.mobile_raw.colors)} colors, {len(state.mobile_raw.typography)} typography, {len(state.mobile_raw.spacing)} spacing")
+        
+        # Normalize mobile
+        state.log("   Normalizing...")
+        state.mobile_normalized = normalizer_mod.normalize_tokens(state.mobile_raw)
+        state.log(f"   Normalized: {len(state.mobile_normalized.colors)} colors, {len(state.mobile_normalized.typography)} typography, {len(state.mobile_normalized.spacing)} spacing")
+        
+        progress(0.95, desc="📊 Preparing results...")
+        
+        # Format results for Stage 1 UI
+        desktop_data = format_tokens_for_display(state.desktop_normalized)
+        mobile_data = format_tokens_for_display(state.mobile_normalized)
+        
+        state.log("")
+        state.log("=" * 50)
+        state.log("✅ EXTRACTION COMPLETE!")
+        state.log("=" * 50)
+        
+        progress(1.0, desc="✅ Complete!")
+        
+        status = f"""## ✅ Extraction Complete!
+
+| Viewport | Colors | Typography | Spacing |
+|----------|--------|------------|---------|
+| Desktop | {len(state.desktop_normalized.colors)} | {len(state.desktop_normalized.typography)} | {len(state.desktop_normalized.spacing)} |
+| Mobile | {len(state.mobile_normalized.colors)} | {len(state.mobile_normalized.typography)} | {len(state.mobile_normalized.spacing)} |
+
+**Next:** Review the tokens below. Accept or reject, then proceed to Stage 2.
+"""
+        
+        return status, state.get_logs(), desktop_data, mobile_data
+        
+    except Exception as e:
+        import traceback
+        state.log(f"❌ Error: {str(e)}")
+        state.log(traceback.format_exc())
+        return f"❌ Error: {str(e)}", state.get_logs(), None, None
+
+
+def format_tokens_for_display(normalized) -> dict:
+    """Format normalized tokens for Gradio display."""
+    if normalized is None:
+        return {"colors": [], "typography": [], "spacing": []}
+    
+    # Colors are now a dict
+    colors = []
+    color_items = list(normalized.colors.values()) if isinstance(normalized.colors, dict) else normalized.colors
+    for c in sorted(color_items, key=lambda x: -x.frequency)[:50]:
+        colors.append([
+            True,  # Accept checkbox
+            c.value,
+            c.suggested_name or "",
+            c.frequency,
+            c.confidence.value if c.confidence else "medium",
+            f"{c.contrast_white:.1f}:1" if c.contrast_white else "N/A",
+            "✓" if c.wcag_aa_small_text else "✗",
+            ", ".join(c.contexts[:2]) if c.contexts else "",
+        ])
+    
+    # Typography
+    typography = []
+    typo_items = list(normalized.typography.values()) if isinstance(normalized.typography, dict) else normalized.typography
+    for t in sorted(typo_items, key=lambda x: -x.frequency)[:30]:
+        typography.append([
+            True,  # Accept checkbox
+            t.font_family,
+            t.font_size,
+            str(t.font_weight),
+            t.line_height or "",
+            t.suggested_name or "",
+            t.frequency,
+            t.confidence.value if t.confidence else "medium",
+        ])
+    
+    # Spacing
+    spacing = []
+    spacing_items = list(normalized.spacing.values()) if isinstance(normalized.spacing, dict) else normalized.spacing
+    for s in sorted(spacing_items, key=lambda x: x.value_px)[:20]:
+        spacing.append([
+            True,  # Accept checkbox
+            s.value,
+            f"{s.value_px}px",
+            s.suggested_name or "",
+            s.frequency,
+            "✓" if s.fits_base_8 else "",
+            s.confidence.value if s.confidence else "medium",
+        ])
+    
+    return {
+        "colors": colors,
+        "typography": typography,
+        "spacing": spacing,
+    }
+
+
+def switch_viewport(viewport: str):
+    """Switch between desktop and mobile view."""
+    if viewport == "Desktop (1440px)":
+        data = format_tokens_for_display(state.desktop_normalized)
+    else:
+        data = format_tokens_for_display(state.mobile_normalized)
+    
+    return data["colors"], data["typography"], data["spacing"]
+
+
+# =============================================================================
+# STAGE 3: EXPORT
+# =============================================================================
+
+def export_tokens_json():
+    """Export tokens to JSON."""
+    result = {
+        "metadata": {
+            "source_url": state.base_url,
+            "extracted_at": datetime.now().isoformat(),
+            "version": "v1-extracted",
+        },
+        "desktop": None,
+        "mobile": None,
+    }
+    
+    if state.desktop_normalized:
+        result["desktop"] = {
+            "colors": [
+                {"value": c.value, "name": c.suggested_name, "frequency": c.frequency, 
+                 "confidence": c.confidence.value if c.confidence else "medium"}
+                for c in state.desktop_normalized.colors
+            ],
+            "typography": [
+                {"font_family": t.font_family, "font_size": t.font_size, 
+                 "font_weight": t.font_weight, "line_height": t.line_height,
+                 "name": t.suggested_name, "frequency": t.frequency}
+                for t in state.desktop_normalized.typography
+            ],
+            "spacing": [
+                {"value": s.value, "value_px": s.value_px, "name": s.suggested_name,
+                 "frequency": s.frequency, "fits_base_8": s.fits_base_8}
+                for s in state.desktop_normalized.spacing
+            ],
+        }
+    
+    if state.mobile_normalized:
+        result["mobile"] = {
+            "colors": [
+                {"value": c.value, "name": c.suggested_name, "frequency": c.frequency,
+                 "confidence": c.confidence.value if c.confidence else "medium"}
+                for c in state.mobile_normalized.colors
+            ],
+            "typography": [
+                {"font_family": t.font_family, "font_size": t.font_size,
+                 "font_weight": t.font_weight, "line_height": t.line_height,
+                 "name": t.suggested_name, "frequency": t.frequency}
+                for t in state.mobile_normalized.typography
+            ],
+            "spacing": [
+                {"value": s.value, "value_px": s.value_px, "name": s.suggested_name,
+                 "frequency": s.frequency, "fits_base_8": s.fits_base_8}
+                for s in state.mobile_normalized.spacing
+            ],
+        }
+    
+    return json.dumps(result, indent=2, default=str)
+
+
+# =============================================================================
+# UI BUILDING
+# =============================================================================
+
+def create_ui():
+    """Create the Gradio interface."""
+    
+    with gr.Blocks(
+        title="Design System Extractor v2",
+        theme=gr.themes.Soft(),
+        css="""
+        .color-swatch { display: inline-block; width: 24px; height: 24px; border-radius: 4px; margin-right: 8px; vertical-align: middle; }
+        """
+    ) as app:
+        
+        gr.Markdown("""
+        # 🎨 Design System Extractor v2
+        
+        **Reverse-engineer design systems from live websites.**
+        
+        A semi-automated, human-in-the-loop system that extracts, normalizes, and upgrades design tokens.
+        
+        ---
+        """)
+        
+        # =================================================================
+        # CONFIGURATION
+        # =================================================================
+        
+        with gr.Accordion("⚙️ Configuration", open=not bool(HF_TOKEN_FROM_ENV)):
+            gr.Markdown("**HuggingFace Token** — Required for Stage 2 (AI upgrades)")
+            with gr.Row():
+                hf_token_input = gr.Textbox(
+                    label="HF Token", placeholder="hf_xxxx", type="password",
+                    scale=4, value=HF_TOKEN_FROM_ENV,
+                )
+                save_token_btn = gr.Button("💾 Save", scale=1)
+            token_status = gr.Markdown("✅ Token loaded" if HF_TOKEN_FROM_ENV else "⏳ Enter token")
+            
+            def save_token(token):
+                if token and len(token) > 10:
+                    os.environ["HF_TOKEN"] = token.strip()
+                    return "✅ Token saved!"
+                return "❌ Invalid token"
+            
+            save_token_btn.click(save_token, [hf_token_input], [token_status])
+        
+        # =================================================================
+        # URL INPUT & PAGE DISCOVERY
+        # =================================================================
+        
+        with gr.Accordion("🔍 Step 1: Discover Pages", open=True):
+            gr.Markdown("Enter your website URL to discover pages for extraction.")
+            
+            with gr.Row():
+                url_input = gr.Textbox(label="Website URL", placeholder="https://example.com", scale=4)
+                discover_btn = gr.Button("🔍 Discover Pages", variant="primary", scale=1)
+            
+            discover_status = gr.Markdown("")
+            
+            with gr.Row():
+                log_output = gr.Textbox(label="📋 Log", lines=8, interactive=False)
+            
+            pages_table = gr.Dataframe(
+                headers=["Select", "URL", "Title", "Type", "Status"],
+                datatype=["bool", "str", "str", "str", "str"],
+                label="Discovered Pages",
+                interactive=True,
+                visible=False,
+            )
+            
+            extract_btn = gr.Button("🚀 Extract Tokens (Desktop + Mobile)", variant="primary", visible=False)
+        
+        # =================================================================
+        # STAGE 1: EXTRACTION REVIEW
+        # =================================================================
+        
+        with gr.Accordion("📊 Stage 1: Review Extracted Tokens", open=False) as stage1_accordion:
+            
+            extraction_status = gr.Markdown("")
+            
+            gr.Markdown("""
+            **Review the extracted tokens.** Toggle between Desktop and Mobile viewports.
+            Accept or reject tokens, then proceed to Stage 2 for AI-powered upgrades.
+            """)
+            
+            viewport_toggle = gr.Radio(
+                choices=["Desktop (1440px)", "Mobile (375px)"],
+                value="Desktop (1440px)",
+                label="Viewport",
+            )
+            
+            with gr.Tabs():
+                with gr.Tab("🎨 Colors"):
+                    colors_table = gr.Dataframe(
+                        headers=["Accept", "Color", "Suggested Name", "Frequency", "Confidence", "Contrast", "AA", "Context"],
+                        datatype=["bool", "str", "str", "number", "str", "str", "str", "str"],
+                        label="Colors",
+                        interactive=True,
+                    )
+                
+                with gr.Tab("📝 Typography"):
+                    typography_table = gr.Dataframe(
+                        headers=["Accept", "Font", "Size", "Weight", "Line Height", "Suggested Name", "Frequency", "Confidence"],
+                        datatype=["bool", "str", "str", "str", "str", "str", "number", "str"],
+                        label="Typography",
+                        interactive=True,
+                    )
+                
+                with gr.Tab("📏 Spacing"):
+                    spacing_table = gr.Dataframe(
+                        headers=["Accept", "Value", "Pixels", "Suggested Name", "Frequency", "Base 8", "Confidence"],
+                        datatype=["bool", "str", "str", "str", "number", "str", "str"],
+                        label="Spacing",
+                        interactive=True,
+                    )
+            
+            proceed_stage2_btn = gr.Button("➡️ Proceed to Stage 2: AI Upgrades", variant="primary")
+        
+        # =================================================================
+        # STAGE 2: AI UPGRADES (Placeholder)
+        # =================================================================
+        
+        with gr.Accordion("🧠 Stage 2: AI-Powered Upgrades (Coming Soon)", open=False):
+            gr.Markdown("""
+            **Agent 3 (Design System Advisor)** will analyze your tokens and propose:
+            
+            - **Type Scale Options:** Choose from A/B/C (1.25, 1.333, 1.414 ratios)
+            - **Color Ramp Generation:** AA-compliant tints and shades
+            - **Spacing System:** Aligned to 8px base grid
+            - **Naming Conventions:** Semantic token names
+            
+            Each option will show a **live preview** so you can see the changes before accepting.
+            
+            *Requires HuggingFace token for LLM inference.*
+            """)
+        
+        # =================================================================
+        # STAGE 3: EXPORT
+        # =================================================================
+        
+        with gr.Accordion("📦 Stage 3: Export", open=False):
+            gr.Markdown("Export your design tokens to JSON (compatible with Figma Tokens Studio).")
+            
+            export_btn = gr.Button("📥 Export JSON", variant="secondary")
+            export_output = gr.Code(label="Tokens JSON", language="json", lines=20)
+            
+            export_btn.click(export_tokens_json, outputs=[export_output])
+        
+        # =================================================================
+        # EVENT HANDLERS
+        # =================================================================
+        
+        # Store data for viewport toggle
+        desktop_data = gr.State({})
+        mobile_data = gr.State({})
+        
+        # Discover pages
+        discover_btn.click(
+            fn=discover_pages,
+            inputs=[url_input],
+            outputs=[discover_status, log_output, pages_table],
+        ).then(
+            fn=lambda: (gr.update(visible=True), gr.update(visible=True)),
+            outputs=[pages_table, extract_btn],
+        )
+        
+        # Extract tokens
+        extract_btn.click(
+            fn=extract_tokens,
+            inputs=[pages_table],
+            outputs=[extraction_status, log_output, desktop_data, mobile_data],
+        ).then(
+            fn=lambda d: (d.get("colors", []), d.get("typography", []), d.get("spacing", [])),
+            inputs=[desktop_data],
+            outputs=[colors_table, typography_table, spacing_table],
+        ).then(
+            fn=lambda: gr.update(open=True),
+            outputs=[stage1_accordion],
+        )
+        
+        # Viewport toggle
+        viewport_toggle.change(
+            fn=switch_viewport,
+            inputs=[viewport_toggle],
+            outputs=[colors_table, typography_table, spacing_table],
+        )
+        
+        # =================================================================
+        # FOOTER
+        # =================================================================
+        
+        gr.Markdown("""
+        ---
+        **Design System Extractor v2** | Built with Playwright + Gradio + LangGraph + HuggingFace
+        
+        *A semi-automated co-pilot for design system recovery and modernization.*
+        """)
+    
+    return app
+
+
+# =============================================================================
+# MAIN
+# =============================================================================
+
+if __name__ == "__main__":
+    app = create_ui()
+    app.launch(server_name="0.0.0.0", server_port=7860)