SuperCharged-Claude-Code-Upgrade/skills/design-pattern-learner/scripts/analyze.py

#!/usr/bin/env python3
"""
Design Pattern Analyzer
Fetches and analyzes design patterns from external sources
"""

import sys
import json
import re
import os
from urllib.parse import urlparse
from datetime import datetime
import subprocess

class DesignPatternAnalyzer:
    def __init__(self, source_url):
        self.source_url = source_url
        self.patterns = {
            "source": source_url,
            "timestamp": datetime.now().isoformat(),
            "design_tokens": {},
            "components": [],
            "layouts": [],
            "animations": []
        }

    def fetch_source(self):
        """Fetch content from URL/gist/repo"""
        print(f"📥 Fetching source: {self.source_url}")

        # Detect source type
        if "gist.github.com" in self.source_url:
            return self._fetch_gist()
        elif "github.com" in self.source_url:
            return self._fetch_github_repo()
        else:
            return self._fetch_webpage()

    def _fetch_gist(self):
        """Fetch gist content using git"""
        print("🔍 Detected: GitHub Gist")

        # Extract gist ID
        gist_match = re.search(r'gist\.github\.com/[^/]+/([a-f0-9]+)', self.source_url)
        if not gist_match:
            gist_match = re.search(r'gist\.github\.com/([a-f0-9]+)', self.source_url)

        if gist_match:
            gist_id = gist_match.group(1)
            gist_url = f"https://gist.github.com/{gist_id}"

            # Use curl to fetch
            result = subprocess.run(
                ['curl', '-s', gist_url],
                capture_output=True,
                text=True
            )

            if result.returncode == 0:
                return self._parse_gist_html(result.stdout)
            else:
                print(f"❌ Failed to fetch gist: {result.stderr}")
                return None
        else:
            print("❌ Could not extract gist ID")
            return None

    def _fetch_github_repo(self):
        """Fetch GitHub repository"""
        print("🔍 Detected: GitHub Repository")
        print("⚠️  Repo analysis requires cloning - will analyze README and structure")

        # For now, analyze the main page
        result = subprocess.run(
            ['curl', '-s', self.source_url],
            capture_output=True,
            text=True
        )

        if result.returncode == 0:
            return self._parse_github_page(result.stdout)
        else:
            print(f"❌ Failed to fetch repo: {result.stderr}")
            return None

    def _fetch_webpage(self):
        """Fetch regular webpage"""
        print("🔍 Detected: Webpage")

        result = subprocess.run(
            ['curl', '-s', '-L', self.source_url],
            capture_output=True,
            text=True
        )

        if result.returncode == 0:
            return result.stdout
        else:
            print(f"❌ Failed to fetch webpage: {result.stderr}")
            return None

    def _parse_gist_html(self, html):
        """Parse gist HTML to extract code"""
        print("📄 Parsing gist content...")

        # Look for file content in gist HTML
        # Extract from <div class="highlight"> or similar
        file_pattern = r'<div class="[^"]*highlight[^"]*"[^>]*>(.*?)</div>'
        files = re.findall(file_pattern, html, re.DOTALL)

        if files:
            # Clean up HTML entities and tags
            content = []
            for file_html in files:
                # Remove HTML tags but keep code
                clean_code = re.sub(r'<[^>]+>', '\n', file_html)
                clean_code = re.sub(r'&lt;', '<', clean_code)
                clean_code = re.sub(r'&gt;', '>', clean_code)
                clean_code = re.sub(r'&amp;', '&', clean_code)
                clean_code = re.sub(r'\n\s*\n', '\n', clean_code)
                content.append(clean_code.strip())

            return '\n\n'.join(content)
        else:
            print("⚠️  Could not extract gist files")
            return html

    def _parse_github_page(self, html):
        """Parse GitHub repo page"""
        print("📄 Parsing repository page...")
        return html

    def analyze_design_tokens(self, content):
        """Extract design tokens from content"""
        print("\n🎨 Extracting Design Tokens...")

        tokens = {}

        # Colors
        colors = self._extract_colors(content)
        if colors:
            tokens['colors'] = colors
            print(f"  ✓ Found {len(colors)} color patterns")

        # Typography
        typography = self._extract_typography(content)
        if typography:
            tokens['typography'] = typography
            print(f"  ✓ Found {len(typography.get('fonts', []))} font patterns")

        # Spacing
        spacing = self._extract_spacing(content)
        if spacing:
            tokens['spacing'] = spacing
            print(f"  ✓ Found spacing patterns")

        # Effects
        effects = self._extract_effects(content)
        if effects:
            tokens['effects'] = effects
            print(f"  ✓ Found {len(effects.get('shadows', []))} shadow patterns")

        self.patterns['design_tokens'] = tokens
        return tokens

    def _extract_colors(self, content):
        """Extract color patterns"""
        colors = {}

        # Hex colors
        hex_colors = re.findall(r'#[0-9a-fA-F]{3,6}', content)
        if hex_colors:
            colors['hex'] = list(set(hex_colors))[:20]  # Limit to 20 unique

        # Tailwind color classes
        tailwind_colors = re.findall(r'\b(bg|text|border)-([a-z]+)-(\d+)\b', content)
        if tailwind_colors:
            colors['tailwind'] = [
                f"{prefix}-{color}-{shade}"
                for prefix, color, shade in tailwind_colors
            ][:20]

        # CSS color names
        css_colors = re.findall(r'\b(black|white|gray|red|blue|green|yellow|purple|pink|indigo)\b', content, re.I)
        if css_colors:
            colors['css'] = list(set(css_colors))

        return colors if colors else None

    def _extract_typography(self, content):
        """Extract typography patterns"""
        typo = {}

        # Font families
        fonts = re.findall(r'font-family:\s*([^;]+)', content, re.I)
        if fonts:
            typo['fonts'] = list(set(fonts))

        # Font sizes
        sizes = re.findall(r'(text-|font-)?size:\s*([^;]+)', content, re.I)
        if sizes:
            typo['sizes'] = list(set([s[1] for s in sizes]))

        # Tailwind text classes
        tailwind_text = re.findall(r'\b(text|font)-(xl|lg|md|sm|xs|\d)\b', content)
        if tailwind_text:
            typo['tailwind'] = [f"{prefix}-{size}" for prefix, size in tailwind_text]

        return typo if typo else None

    def _extract_spacing(self, content):
        """Extract spacing patterns"""
        spacing = {}

        # Tailwind spacing
        tailwind_spacing = re.findall(r'\b(p|m|px|py|pt|pb|pl|pr)-(\\d+)\b', content)
        if tailwind_spacing:
            spacing['tailwind'] = list(set([f"{prefix}-{size}" for prefix, size in tailwind_spacing]))

        # CSS spacing
        css_spacing = re.findall(r'(padding|margin):\s*([^;]+)', content, re.I)
        if css_spacing:
            spacing['css'] = list(set([f"{prop}: {val}" for prop, val in css_spacing]))

        return spacing if spacing else None

    def _extract_effects(self, content):
        """Extract visual effects"""
        effects = {}

        # Shadows
        shadows = re.findall(r'box-shadow:\s*([^;]+)', content, re.I)
        if shadows:
            effects['shadows'] = list(set(shadows))

        # Tailwind shadows
        tailwind_shadows = re.findall(r'\bshadow-(xl|lg|md|sm|none)\b', content)
        if tailwind_shadows:
            effects['tailwind_shadows'] = [f"shadow-{s}" for s in tailwind_shadows]

        # Border radius
        radius = re.findall(r'border-radius:\s*([^;]+)', content, re.I)
        if radius:
            effects['radius'] = list(set(radius))

        return effects if effects else None

    def analyze_components(self, content):
        """Extract UI components"""
        print("\n🧩 Identifying Components...")

        components = []

        # Look for common component patterns
        component_patterns = {
            'button': r'<button[^>]*>.*?</button>|class="[^"]*button[^"]*"',
            'card': r'class="[^"]*card[^"]*"',
            'modal': r'class="[^"]*modal[^"]*"',
            'nav': r'<nav[^>]*>.*?</nav>|class="[^"]*nav[^"]*"',
            'form': r'<form[^>]*>.*?</form>|class="[^"]*form[^"]*"',
            'input': r'<input[^>]*/?>|class="[^"]*input[^"]*"',
            'hero': r'class="[^"]*hero[^"]*"',
            'footer': r'<footer[^>]*>.*?</footer>',
            'header': r'<header[^>]*>.*?</header>',
        }

        for comp_name, pattern in component_patterns.items():
            matches = re.findall(pattern, content, re.DOTALL | re.IGNORECASE)
            if matches:
                components.append({
                    'type': comp_name,
                    'count': len(matches),
                    'examples': matches[:3]  # First 3 examples
                })
                print(f"  ✓ Found {len(matches)} {comp_name} component(s)")

        self.patterns['components'] = components
        return components

    def analyze_layouts(self, content):
        """Extract layout patterns"""
        print("\n📐 Analyzing Layouts...")

        layouts = []

        # Grid layouts
        grids = re.findall(r'grid-cols-\\d+', content)
        if grids:
            layouts.append({
                'type': 'grid',
                'variants': list(set(grids))
            })
            print(f"  ✓ Found grid layouts: {list(set(grids))}")

        # Flexbox
        flex_patterns = re.findall(r'flex-(row|col|wrap|nowrap)', content)
        if flex_patterns:
            layouts.append({
                'type': 'flexbox',
                'patterns': list(set(flex_patterns))
            })
            print(f"  ✓ Found flexbox patterns: {list(set(flex_patterns))}")

        # Containers
        containers = re.findall(r'class="[^"]*container[^"]*"', content)
        if containers:
            layouts.append({
                'type': 'container',
                'count': len(containers)
            })
            print(f"  ✓ Found {len(containers)} container(s)")

        self.patterns['layouts'] = layouts
        return layouts

    def analyze_animations(self, content):
        """Extract animation patterns"""
        print("\n✨ Analyzing Animations...")

        animations = []

        # Transitions
        transitions = re.findall(r'transition(?:-[^:]*)?:\\s*([^;]+)', content, re.I)
        if transitions:
            animations.append({
                'type': 'transition',
                'patterns': list(set(transitions))[:10]
            })
            print(f"  ✓ Found transitions: {len(set(transitions))}")

        # Transforms
        transforms = re.findall(r'transform:\\s*([^;]+)', content, re.I)
        if transforms:
            animations.append({
                'type': 'transform',
                'patterns': list(set(transforms))
            })
            print(f"  ✓ Found transforms: {len(set(transforms))}")

        # Keyframes
        keyframes = re.findall(r'@keyframes\\s+(\\w+)', content)
        if keyframes:
            animations.append({
                'type': 'keyframe',
                'names': list(set(keyframes))
            })
            print(f"  ✓ Found keyframes: {list(set(keyframes))}")

        self.patterns['animations'] = animations
        return animations

    def save_patterns(self):
        """Save extracted patterns to file"""
        # Create data directory if needed
        data_dir = os.path.expanduser('~/.claude/skills/design-pattern-learner/data/patterns')
        os.makedirs(data_dir, exist_ok=True)

        # Generate filename from URL
        safe_name = re.sub(r'[^a-zA-Z0-9]', '_', self.source_url)[:50]
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        filename = f"{safe_name}_{timestamp}.json"
        filepath = os.path.join(data_dir, filename)

        # Save patterns
        with open(filepath, 'w') as f:
            json.dump(self.patterns, f, indent=2)

        print(f"\n💾 Patterns saved to: {filepath}")

        # Also save to learning history
        history_file = os.path.expanduser('~/.claude/skills/design-pattern-learner/learning-history.jsonl')
        with open(history_file, 'a') as f:
            f.write(json.dumps({
                'timestamp': datetime.now().isoformat(),
                'source': self.source_url,
                'file': filename,
                'patterns_count': len(self.patterns['components']),
                'success': True
            }) + '\n')

        return filepath

    def generate_summary(self):
        """Generate human-readable summary"""
        print("\n" + "="*60)
        print("📊 DESIGN PATTERN ANALYSIS SUMMARY")
        print("="*60)

        print(f"\n📍 Source: {self.source_url}")
        print(f"🕐 Analyzed: {self.patterns['timestamp']}")

        # Design tokens
        if self.patterns['design_tokens']:
            print("\n🎨 Design Tokens:")
            for category, values in self.patterns['design_tokens'].items():
                print(f"  • {category}: {len(values)} patterns")

        # Components
        if self.patterns['components']:
            print(f"\n🧩 Components Found: {len(self.patterns['components'])}")
            for comp in self.patterns['components']:
                print(f"  • {comp['type']}: {comp['count']} instance(s)")

        # Layouts
        if self.patterns['layouts']:
            print(f"\n📐 Layout Patterns: {len(self.patterns['layouts'])}")
            for layout in self.patterns['layouts']:
                print(f"  • {layout['type']}")

        # Animations
        if self.patterns['animations']:
            print(f"\n✨ Animations: {len(self.patterns['animations'])}")
            for anim in self.patterns['animations']:
                print(f"  • {anim['type']}")

        print("\n" + "="*60)
        print("✅ Analysis Complete!")
        print("="*60)

def main():
    if len(sys.argv) < 2:
        print("Usage: python3 analyze.py <URL>")
        print("Example: python3 analyze.py https://gist.github.com/user/id")
        sys.exit(1)

    url = sys.argv[1]

    analyzer = DesignPatternAnalyzer(url)

    # Fetch content
    content = analyzer.fetch_source()
    if not content:
        print("❌ Failed to fetch content")
        sys.exit(1)

    # Analyze patterns
    analyzer.analyze_design_tokens(content)
    analyzer.analyze_components(content)
    analyzer.analyze_layouts(content)
    analyzer.analyze_animations(content)

    # Save results
    filepath = analyzer.save_patterns()

    # Show summary
    analyzer.generate_summary()

    print(f"\n💡 Next steps:")
    print(f"  • View patterns: cat {filepath}")
    print(f"  • Generate implementation: python3 generate.py --source {filepath}")

if __name__ == '__main__':
    main()