1#!/usr/bin/env python3
2# -*- coding: utf-8 -*-
3"""
4UI/UX Pro Max Core - BM25 search engine for UI/UX style guides
5"""
6 
7import csv
8import re
9from pathlib import Path
10from math import log
11from collections import defaultdict
12 
13# ============ CONFIGURATION ============
14DATA_DIR = Path(__file__).parent.parent / "data"
15MAX_RESULTS = 3
16 
17CSV_CONFIG = {
18    "style": {
19        "file": "styles.csv",
20        "search_cols": ["Style Category", "Keywords", "Best For", "Type", "AI Prompt Keywords"],
21        "output_cols": ["Style Category", "Type", "Keywords", "Primary Colors", "Effects & Animation", "Best For", "Light Mode ✓", "Dark Mode ✓", "Performance", "Accessibility", "Framework Compatibility", "Complexity", "AI Prompt Keywords", "CSS/Technical Keywords", "Implementation Checklist", "Design System Variables"]
22    },
23    "color": {
24        "file": "colors.csv",
25        "search_cols": ["Product Type", "Notes"],
26        "output_cols": ["Product Type", "Primary", "On Primary", "Secondary", "On Secondary", "Accent", "On Accent", "Background", "Foreground", "Card", "Card Foreground", "Muted", "Muted Foreground", "Border", "Destructive", "On Destructive", "Ring", "Notes"]
27    },
28    "chart": {
29        "file": "charts.csv",
30        "search_cols": ["Data Type", "Keywords", "Best Chart Type", "When to Use", "When NOT to Use", "Accessibility Notes"],
31        "output_cols": ["Data Type", "Keywords", "Best Chart Type", "Secondary Options", "When to Use", "When NOT to Use", "Data Volume Threshold", "Color Guidance", "Accessibility Grade", "Accessibility Notes", "A11y Fallback", "Library Recommendation", "Interactive Level"]
32    },
33    "landing": {
34        "file": "landing.csv",
35        "search_cols": ["Pattern Name", "Keywords", "Conversion Optimization", "Section Order"],
36        "output_cols": ["Pattern Name", "Keywords", "Section Order", "Primary CTA Placement", "Color Strategy", "Conversion Optimization"]
37    },
38    "product": {
39        "file": "products.csv",
40        "search_cols": ["Product Type", "Keywords", "Primary Style Recommendation", "Key Considerations"],
41        "output_cols": ["Product Type", "Keywords", "Primary Style Recommendation", "Secondary Styles", "Landing Page Pattern", "Dashboard Style (if applicable)", "Color Palette Focus"]
42    },
43    "ux": {
44        "file": "ux-guidelines.csv",
45        "search_cols": ["Category", "Issue", "Description", "Platform"],
46        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
47    },
48    "typography": {
49        "file": "typography.csv",
50        "search_cols": ["Font Pairing Name", "Category", "Mood/Style Keywords", "Best For", "Heading Font", "Body Font"],
51        "output_cols": ["Font Pairing Name", "Category", "Heading Font", "Body Font", "Mood/Style Keywords", "Best For", "Google Fonts URL", "CSS Import", "Tailwind Config", "Notes"]
52    },
53    "icons": {
54        "file": "icons.csv",
55        "search_cols": ["Category", "Icon Name", "Keywords", "Best For"],
56        "output_cols": ["Category", "Icon Name", "Keywords", "Library", "Import Code", "Usage", "Best For", "Style"]
57    },
58    "react": {
59        "file": "react-performance.csv",
60        "search_cols": ["Category", "Issue", "Keywords", "Description"],
61        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
62    },
63    "web": {
64        "file": "app-interface.csv",
65        "search_cols": ["Category", "Issue", "Keywords", "Description"],
66        "output_cols": ["Category", "Issue", "Platform", "Description", "Do", "Don't", "Code Example Good", "Code Example Bad", "Severity"]
67    },
68    "google-fonts": {
69        "file": "google-fonts.csv",
70        "search_cols": ["Family", "Category", "Stroke", "Classifications", "Keywords", "Subsets", "Designers"],
71        "output_cols": ["Family", "Category", "Stroke", "Classifications", "Styles", "Variable Axes", "Subsets", "Designers", "Popularity Rank", "Google Fonts URL"]
72    }
73}
74 
75STACK_CONFIG = {
76    "react":            {"file": "stacks/react.csv"},
77    "nextjs":           {"file": "stacks/nextjs.csv"},
78    "vue":              {"file": "stacks/vue.csv"},
79    "svelte":           {"file": "stacks/svelte.csv"},
80    "astro":            {"file": "stacks/astro.csv"},
81    "swiftui":          {"file": "stacks/swiftui.csv"},
82    "react-native":     {"file": "stacks/react-native.csv"},
83    "flutter":          {"file": "stacks/flutter.csv"},
84    "nuxtjs":           {"file": "stacks/nuxtjs.csv"},
85    "nuxt-ui":          {"file": "stacks/nuxt-ui.csv"},
86    "html-tailwind":    {"file": "stacks/html-tailwind.csv"},
87    "shadcn":           {"file": "stacks/shadcn.csv"},
88    "jetpack-compose":  {"file": "stacks/jetpack-compose.csv"},
89    "threejs":          {"file": "stacks/threejs.csv"},
90    "angular":          {"file": "stacks/angular.csv"},
91    "laravel":          {"file": "stacks/laravel.csv"},
92}
93 
94# Common columns for all stacks
95_STACK_COLS = {
96    "search_cols": ["Category", "Guideline", "Description", "Do", "Don't"],
97    "output_cols": ["Category", "Guideline", "Description", "Do", "Don't", "Code Good", "Code Bad", "Severity", "Docs URL"]
98}
99 
100AVAILABLE_STACKS = list(STACK_CONFIG.keys())
101 
102 
103# ============ BM25 IMPLEMENTATION ============
104class BM25:
105    """BM25 ranking algorithm for text search"""
106 
107    def __init__(self, k1=1.5, b=0.75):
108        self.k1 = k1
109        self.b = b
110        self.corpus = []
111        self.doc_lengths = []
112        self.avgdl = 0
113        self.idf = {}
114        self.doc_freqs = defaultdict(int)
115        self.N = 0
116 
117    def tokenize(self, text):
118        """Lowercase, split, remove punctuation, filter short words"""
119        text = re.sub(r'[^\w\s]', ' ', str(text).lower())
120        return [w for w in text.split() if len(w) > 2]
121 
122    def fit(self, documents):
123        """Build BM25 index from documents"""
124        self.corpus = [self.tokenize(doc) for doc in documents]
125        self.N = len(self.corpus)
126        if self.N == 0:
127            return
128        self.doc_lengths = [len(doc) for doc in self.corpus]
129        self.avgdl = sum(self.doc_lengths) / self.N
130 
131        for doc in self.corpus:
132            seen = set()
133            for word in doc:
134                if word not in seen:
135                    self.doc_freqs[word] += 1
136                    seen.add(word)
137 
138        for word, freq in self.doc_freqs.items():
139            self.idf[word] = log((self.N - freq + 0.5) / (freq + 0.5) + 1)
140 
141    def score(self, query):
142        """Score all documents against query"""
143        query_tokens = self.tokenize(query)
144        scores = []
145 
146        for idx, doc in enumerate(self.corpus):
147            score = 0
148            doc_len = self.doc_lengths[idx]
149            term_freqs = defaultdict(int)
150            for word in doc:
151                term_freqs[word] += 1
152 
153            for token in query_tokens:
154                if token in self.idf:
155                    tf = term_freqs[token]
156                    idf = self.idf[token]
157                    numerator = tf * (self.k1 + 1)
158                    denominator = tf + self.k1 * (1 - self.b + self.b * doc_len / self.avgdl)
159                    score += idf * numerator / denominator
160 
161            scores.append((idx, score))
162 
163        return sorted(scores, key=lambda x: x[1], reverse=True)
164 
165 
166# ============ SEARCH FUNCTIONS ============
167def _load_csv(filepath):
168    """Load CSV and return list of dicts"""
169    with open(filepath, 'r', encoding='utf-8') as f:
170        return list(csv.DictReader(f))
171 
172 
173def _search_csv(filepath, search_cols, output_cols, query, max_results):
174    """Core search function using BM25"""
175    if not filepath.exists():
176        return []
177 
178    data = _load_csv(filepath)
179 
180    # Build documents from search columns
181    documents = [" ".join(str(row.get(col, "")) for col in search_cols) for row in data]
182 
183    # BM25 search
184    bm25 = BM25()
185    bm25.fit(documents)
186    ranked = bm25.score(query)
187 
188    # Get top results with score > 0
189    results = []
190    for idx, score in ranked[:max_results]:
191        if score > 0:
192            row = data[idx]
193            results.append({col: row.get(col, "") for col in output_cols if col in row})
194 
195    return results
196 
197 
198def detect_domain(query):
199    """Auto-detect the most relevant domain from query"""
200    query_lower = query.lower()
201 
202    domain_keywords = {
203        "color": ["color", "palette", "hex", "#", "rgb", "token", "semantic", "accent", "destructive", "muted", "foreground"],
204        "chart": ["chart", "graph", "visualization", "trend", "bar", "pie", "scatter", "heatmap", "funnel"],
205        "landing": ["landing", "page", "cta", "conversion", "hero", "testimonial", "pricing", "section"],
206        "product": ["saas", "ecommerce", "e-commerce", "fintech", "healthcare", "gaming", "portfolio", "crypto", "dashboard", "fitness", "restaurant", "hotel", "travel", "music", "education", "learning", "legal", "insurance", "medical", "beauty", "pharmacy", "dental", "pet", "dating", "wedding", "recipe", "delivery", "ride", "booking", "calendar", "timer", "tracker", "diary", "note", "chat", "messenger", "crm", "invoice", "parking", "transit", "vpn", "alarm", "weather", "sleep", "meditation", "fasting", "habit", "grocery", "meme", "wardrobe", "plant care", "reading", "flashcard", "puzzle", "trivia", "arcade", "photography", "streaming", "podcast", "newsletter", "marketplace", "freelancer", "coworking", "airline", "museum", "theater", "church", "non-profit", "charity", "kindergarten", "daycare", "senior care", "veterinary", "florist", "bakery", "brewery", "construction", "automotive", "real estate", "logistics", "agriculture", "coding bootcamp"],
207        "style": ["style", "design", "ui", "minimalism", "glassmorphism", "neumorphism", "brutalism", "dark mode", "flat", "aurora", "prompt", "css", "implementation", "variable", "checklist", "tailwind"],
208        "ux": ["ux", "usability", "accessibility", "wcag", "touch", "scroll", "animation", "keyboard", "navigation", "mobile"],
209        "typography": ["font pairing", "typography pairing", "heading font", "body font"],
210        "google-fonts": ["google font", "font family", "font weight", "font style", "variable font", "noto", "font for", "find font", "font subset", "font language", "monospace font", "serif font", "sans serif font", "display font", "handwriting font", "font", "typography", "serif", "sans"],
211        "icons": ["icon", "icons", "lucide", "heroicons", "symbol", "glyph", "pictogram", "svg icon"],
212        "react": ["react", "next.js", "nextjs", "suspense", "memo", "usecallback", "useeffect", "rerender", "bundle", "waterfall", "barrel", "dynamic import", "rsc", "server component"],
213        "web": ["aria", "focus", "outline", "semantic", "virtualize", "autocomplete", "form", "input type", "preconnect"]
214    }
215 
216    scores = {domain: sum(1 for kw in keywords if re.search(r'\b' + re.escape(kw) + r'\b', query_lower)) for domain, keywords in domain_keywords.items()}
217    best = max(scores, key=scores.get)
218    return best if scores[best] > 0 else "style"
219 
220 
221def search(query, domain=None, max_results=MAX_RESULTS):
222    """Main search function with auto-domain detection"""
223    if domain is None:
224        domain = detect_domain(query)
225 
226    config = CSV_CONFIG.get(domain, CSV_CONFIG["style"])
227    filepath = DATA_DIR / config["file"]
228 
229    if not filepath.exists():
230        return {"error": f"File not found: {filepath}", "domain": domain}
231 
232    results = _search_csv(filepath, config["search_cols"], config["output_cols"], query, max_results)
233 
234    return {
235        "domain": domain,
236        "query": query,
237        "file": config["file"],
238        "count": len(results),
239        "results": results
240    }
241 
242 
243def search_stack(query, stack, max_results=MAX_RESULTS):
244    """Search stack-specific guidelines"""
245    if stack not in STACK_CONFIG:
246        return {"error": f"Unknown stack: {stack}. Available: {', '.join(AVAILABLE_STACKS)}"}
247 
248    filepath = DATA_DIR / STACK_CONFIG[stack]["file"]
249 
250    if not filepath.exists():
251        return {"error": f"Stack file not found: {filepath}", "stack": stack}
252 
253    results = _search_csv(filepath, _STACK_COLS["search_cols"], _STACK_COLS["output_cols"], query, max_results)
254 
255    return {
256        "domain": "stack",
257        "stack": stack,
258        "query": query,
259        "file": STACK_CONFIG[stack]["file"],
260        "count": len(results),
261        "results": results
262    }
263