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", "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-native": {"file": "stacks/react-native.csv"},
77}
78 
79# Common columns for all stacks
80_STACK_COLS = {
81    "search_cols": ["Category", "Guideline", "Description", "Do", "Don't"],
82    "output_cols": ["Category", "Guideline", "Description", "Do", "Don't", "Code Good", "Code Bad", "Severity", "Docs URL"]
83}
84 
85AVAILABLE_STACKS = list(STACK_CONFIG.keys())
86 
87 
88# ============ BM25 IMPLEMENTATION ============
89class BM25:
90    """BM25 ranking algorithm for text search"""
91 
92    def __init__(self, k1=1.5, b=0.75):
93        self.k1 = k1
94        self.b = b
95        self.corpus = []
96        self.doc_lengths = []
97        self.avgdl = 0
98        self.idf = {}
99        self.doc_freqs = defaultdict(int)
100        self.N = 0
101 
102    def tokenize(self, text):
103        """Lowercase, split, remove punctuation, filter short words"""
104        text = re.sub(r'[^\w\s]', ' ', str(text).lower())
105        return [w for w in text.split() if len(w) > 2]
106 
107    def fit(self, documents):
108        """Build BM25 index from documents"""
109        self.corpus = [self.tokenize(doc) for doc in documents]
110        self.N = len(self.corpus)
111        if self.N == 0:
112            return
113        self.doc_lengths = [len(doc) for doc in self.corpus]
114        self.avgdl = sum(self.doc_lengths) / self.N
115 
116        for doc in self.corpus:
117            seen = set()
118            for word in doc:
119                if word not in seen:
120                    self.doc_freqs[word] += 1
121                    seen.add(word)
122 
123        for word, freq in self.doc_freqs.items():
124            self.idf[word] = log((self.N - freq + 0.5) / (freq + 0.5) + 1)
125 
126    def score(self, query):
127        """Score all documents against query"""
128        query_tokens = self.tokenize(query)
129        scores = []
130 
131        for idx, doc in enumerate(self.corpus):
132            score = 0
133            doc_len = self.doc_lengths[idx]
134            term_freqs = defaultdict(int)
135            for word in doc:
136                term_freqs[word] += 1
137 
138            for token in query_tokens:
139                if token in self.idf:
140                    tf = term_freqs[token]
141                    idf = self.idf[token]
142                    numerator = tf * (self.k1 + 1)
143                    denominator = tf + self.k1 * (1 - self.b + self.b * doc_len / self.avgdl)
144                    score += idf * numerator / denominator
145 
146            scores.append((idx, score))
147 
148        return sorted(scores, key=lambda x: x[1], reverse=True)
149 
150 
151# ============ SEARCH FUNCTIONS ============
152def _load_csv(filepath):
153    """Load CSV and return list of dicts"""
154    with open(filepath, 'r', encoding='utf-8') as f:
155        return list(csv.DictReader(f))
156 
157 
158def _search_csv(filepath, search_cols, output_cols, query, max_results):
159    """Core search function using BM25"""
160    if not filepath.exists():
161        return []
162 
163    data = _load_csv(filepath)
164 
165    # Build documents from search columns
166    documents = [" ".join(str(row.get(col, "")) for col in search_cols) for row in data]
167 
168    # BM25 search
169    bm25 = BM25()
170    bm25.fit(documents)
171    ranked = bm25.score(query)
172 
173    # Get top results with score > 0
174    results = []
175    for idx, score in ranked[:max_results]:
176        if score > 0:
177            row = data[idx]
178            results.append({col: row.get(col, "") for col in output_cols if col in row})
179 
180    return results
181 
182 
183def detect_domain(query):
184    """Auto-detect the most relevant domain from query"""
185    query_lower = query.lower()
186 
187    domain_keywords = {
188        "color": ["color", "palette", "hex", "#", "rgb", "token", "semantic", "accent", "destructive", "muted", "foreground"],
189        "chart": ["chart", "graph", "visualization", "trend", "bar", "pie", "scatter", "heatmap", "funnel"],
190        "landing": ["landing", "page", "cta", "conversion", "hero", "testimonial", "pricing", "section"],
191        "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"],
192        "style": ["style", "design", "ui", "minimalism", "glassmorphism", "neumorphism", "brutalism", "dark mode", "flat", "aurora", "prompt", "css", "implementation", "variable", "checklist", "tailwind"],
193        "ux": ["ux", "usability", "accessibility", "wcag", "touch", "scroll", "animation", "keyboard", "navigation", "mobile"],
194        "typography": ["font pairing", "typography pairing", "heading font", "body font"],
195        "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"],
196        "icons": ["icon", "icons", "lucide", "heroicons", "symbol", "glyph", "pictogram", "svg icon"],
197        "react": ["react", "next.js", "nextjs", "suspense", "memo", "usecallback", "useeffect", "rerender", "bundle", "waterfall", "barrel", "dynamic import", "rsc", "server component"],
198        "web": ["aria", "focus", "outline", "semantic", "virtualize", "autocomplete", "form", "input type", "preconnect"]
199    }
200 
201    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()}
202    best = max(scores, key=scores.get)
203    return best if scores[best] > 0 else "style"
204 
205 
206def search(query, domain=None, max_results=MAX_RESULTS):
207    """Main search function with auto-domain detection"""
208    if domain is None:
209        domain = detect_domain(query)
210 
211    config = CSV_CONFIG.get(domain, CSV_CONFIG["style"])
212    filepath = DATA_DIR / config["file"]
213 
214    if not filepath.exists():
215        return {"error": f"File not found: {filepath}", "domain": domain}
216 
217    results = _search_csv(filepath, config["search_cols"], config["output_cols"], query, max_results)
218 
219    return {
220        "domain": domain,
221        "query": query,
222        "file": config["file"],
223        "count": len(results),
224        "results": results
225    }
226 
227 
228def search_stack(query, stack, max_results=MAX_RESULTS):
229    """Search stack-specific guidelines"""
230    if stack not in STACK_CONFIG:
231        return {"error": f"Unknown stack: {stack}. Available: {', '.join(AVAILABLE_STACKS)}"}
232 
233    filepath = DATA_DIR / STACK_CONFIG[stack]["file"]
234 
235    if not filepath.exists():
236        return {"error": f"Stack file not found: {filepath}", "stack": stack}
237 
238    results = _search_csv(filepath, _STACK_COLS["search_cols"], _STACK_COLS["output_cols"], query, max_results)
239 
240    return {
241        "domain": "stack",
242        "stack": stack,
243        "query": query,
244        "file": STACK_CONFIG[stack]["file"],
245        "count": len(results),
246        "results": results
247    }
248