thuban 0.3.3 → 0.4.0

package/packages/scanner/codebase-passport.js

@@ -1,299 +0,0 @@
-/**
- * Thuban Codebase Passport Generator
- *
- * @purpose Generate a single JSON identity file for the entire codebase
- * @module thuban
- * @layer scanner
- * @exports-to cli
- * @critical-for Onboarding — new devs understand the codebase in minutes not weeks
- */
-
-const fs = require('fs');
-const path = require('path');
-const crypto = require('crypto');
-
-class CodebasePassport {
-  constructor(opts = {}) {
-    this.rootPath = opts.rootPath || process.cwd();
-  }
-
-  /**
-   * Generate the passport from scan results
-   */
-  generate(files, opts = {}) {
-    const startTime = Date.now();
-    const fileMap = [];
-    const dependencies = {};
-    const exports = {};
-    const entryPoints = [];
-    const sacredFiles = [];
-    const riskAreas = [];
-    let totalLines = 0;
-    const languages = {};
-    const frameworks = new Set();
-
-    for (const file of files) {
-      let content;
-      try {
-        const stat = fs.statSync(file);
-        if (stat.size > 1024 * 1024) continue;
-        content = fs.readFileSync(file, 'utf-8');
-      } catch (e) {
-        continue;
-      }
-
-      const relPath = path.relative(this.rootPath, file);
-      const lines = content.split('\n');
-      totalLines += lines.length;
-
-      // Detect language
-      const ext = path.extname(file);
-      languages[ext] = (languages[ext] || 0) + lines.length;
-
-      // Detect frameworks
-      this._detectFrameworks(content, frameworks);
-
-      // Map imports and exports
-      const fileDeps = this._extractDependencies(content, relPath);
-      const fileExports = this._extractExports(content, relPath);
-
-      dependencies[relPath] = fileDeps;
-      if (fileExports.length > 0) exports[relPath] = fileExports;
-
-      // Detect entry points
-      if (this._isEntryPoint(relPath, content)) {
-        entryPoints.push(relPath);
-      }
-
-      // Detect sacred files (high dependency count = risky to change)
-      const importedByCount = files.filter(f => {
-        try {
-          const c = fs.readFileSync(f, 'utf-8');
-          return c.includes(relPath.replace(/\\/g, '/')) || c.includes(relPath.replace(/\//g, '\\'));
-        } catch (e) { return false; }
-      }).length;
-
-      if (importedByCount > 5) {
-        sacredFiles.push({
-          file: relPath,
-          importedBy: importedByCount,
-          risk: importedByCount > 10 ? 'critical' : 'high',
-          note: `Changing this file affects ${importedByCount} other files. Proceed with caution.`,
-        });
-      }
-
-      // File purpose summary
-      const purpose = this._detectPurpose(relPath, content);
-      fileMap.push({
-        path: relPath,
-        lines: lines.length,
-        purpose,
-        imports: fileDeps.length,
-        exports: fileExports.length,
-      });
-    }
-
-    // Build dependency graph summary
-    const depChains = this._findCriticalPaths(dependencies);
-
-    // Detect architecture pattern
-    const architecture = this._detectArchitecture(fileMap);
-
-    const passport = {
-      _version: '1.0.0',
-      _generated: new Date().toISOString(),
-      _generator: 'thuban',
-
-      project: {
-        name: path.basename(this.rootPath),
-        rootPath: this.rootPath,
-        totalFiles: files.length,
-        totalLines,
-        languages: Object.entries(languages)
-          .sort((a, b) => b[1] - a[1])
-          .map(([ext, lines]) => ({ extension: ext, lines, percentage: Math.round((lines / totalLines) * 100) })),
-        frameworks: [...frameworks],
-        architecture,
-        entryPoints,
-      },
-
-      files: fileMap
-        .sort((a, b) => b.imports - a.imports)
-        .slice(0, 200), // Cap to prevent huge passports
-
-      sacred: sacredFiles
-        .sort((a, b) => b.importedBy - a.importedBy),
-
-      dependencies: {
-        totalChains: Object.keys(dependencies).length,
-        criticalPaths: depChains.slice(0, 20),
-        circularRisks: this._findCircularRisks(dependencies),
-      },
-
-      onboarding: {
-        estimatedReadTimeMinutes: Math.ceil(totalLines / 200), // ~200 lines/min for scanning
-        startHere: entryPoints.slice(0, 5),
-        keyFiles: sacredFiles.slice(0, 10).map(s => s.file),
-        doNotTouch: sacredFiles.filter(s => s.risk === 'critical').map(s => s.file),
-        quickSummary: this._generateQuickSummary(fileMap, frameworks, architecture),
-      },
-
-      generatedIn: Date.now() - startTime + 'ms',
-    };
-
-    return passport;
-  }
-
-  /**
-   * Save passport to file
-   */
-  save(passport, outputPath) {
-    const filePath = outputPath || path.join(this.rootPath, '.thuban-passport.json');
-    fs.writeFileSync(filePath, JSON.stringify(passport, null, 2), 'utf-8');
-    return filePath;
-  }
-
-  // ─── Private ─────────────────────────────────────────────
-
-  _extractDependencies(content, filePath) {
-    const deps = [];
-    const patterns = [
-      /require\s*\(\s*['"]([^'"]+)['"]\s*\)/g,
-      /import\s+.*?from\s+['"]([^'"]+)['"]/g,
-      /import\s*\(\s*['"]([^'"]+)['"]\s*\)/g,
-    ];
-
-    for (const pattern of patterns) {
-      let match;
-      while ((match = pattern.exec(content)) !== null) {
-        deps.push(match[1]);
-      }
-    }
-
-    return [...new Set(deps)];
-  }
-
-  _extractExports(content, filePath) {
-    const exports = [];
-
-    // module.exports
-    const moduleExports = content.match(/module\.exports\s*=\s*(\{[\s\S]*?\}|[a-zA-Z_$]\w*)/);
-    if (moduleExports) exports.push('module.exports');
-
-    // Named exports
-    const namedExports = content.match(/exports\.([a-zA-Z_$]\w*)\s*=/g);
-    if (namedExports) {
-      namedExports.forEach(e => exports.push(e.replace(/\s*=\s*$/, '')));
-    }
-
-    // ES6 exports
-    const es6Exports = content.match(/export\s+(?:default\s+)?(?:const|let|var|function|class)\s+([a-zA-Z_$]\w*)/g);
-    if (es6Exports) {
-      es6Exports.forEach(e => exports.push(e));
-    }
-
-    return exports;
-  }
-
-  _isEntryPoint(relPath, content) {
-    const entryNames = ['index.', 'main.', 'app.', 'server.', 'cli.', 'bin/'];
-    if (entryNames.some(n => relPath.includes(n))) return true;
-    if (content.includes('#!/usr/bin/env')) return true;
-    if (content.includes('createServer') || content.includes('.listen(')) return true;
-    return false;
-  }
-
-  _detectPurpose(relPath, content) {
-    const lower = relPath.toLowerCase();
-    if (/route/i.test(lower)) return 'routing';
-    if (/middleware/i.test(lower)) return 'middleware';
-    if (/model/i.test(lower)) return 'data model';
-    if (/controller/i.test(lower)) return 'controller';
-    if (/service/i.test(lower)) return 'service';
-    if (/util|helper|lib/i.test(lower)) return 'utility';
-    if (/config/i.test(lower)) return 'configuration';
-    if (/test|spec/i.test(lower)) return 'test';
-    if (/component/i.test(lower)) return 'UI component';
-    if (/hook/i.test(lower)) return 'React hook';
-    if (/store|redux|state/i.test(lower)) return 'state management';
-    if (/api/i.test(lower)) return 'API layer';
-    if (/db|database|migration/i.test(lower)) return 'database';
-    if (/auth/i.test(lower)) return 'authentication';
-    if (/cli|command/i.test(lower)) return 'CLI';
-
-    // Check content for clues
-    if (content.includes('app.get(') || content.includes('router.')) return 'routing';
-    if (content.includes('mongoose.model') || content.includes('Schema')) return 'data model';
-    if (content.includes('React') || content.includes('jsx')) return 'React component';
-
-    return 'application logic';
-  }
-
-  _detectFrameworks(content, frameworks) {
-    if (content.includes('require(\'express\'') || content.includes('from \'express\'')) frameworks.add('Express');
-    if (content.includes('require(\'react\'') || content.includes('from \'react\'')) frameworks.add('React');
-    if (content.includes('require(\'next\'') || content.includes('from \'next\'')) frameworks.add('Next.js');
-    if (content.includes('require(\'mongoose\'') || content.includes('from \'mongoose\'')) frameworks.add('Mongoose');
-    if (content.includes('require(\'fastify\'') || content.includes('from \'fastify\'')) frameworks.add('Fastify');
-    if (content.includes('require(\'vue\'') || content.includes('from \'vue\'')) frameworks.add('Vue');
-    if (content.includes('require(\'stripe\'') || content.includes('from \'stripe\'')) frameworks.add('Stripe');
-    if (content.includes('@angular')) frameworks.add('Angular');
-  }
-
-  _detectArchitecture(fileMap) {
-    const paths = fileMap.map(f => f.path.toLowerCase());
-    if (paths.some(p => p.includes('controller')) && paths.some(p => p.includes('model'))) return 'MVC';
-    if (paths.some(p => p.includes('service')) && paths.some(p => p.includes('repository'))) return 'Service-Repository';
-    if (paths.some(p => p.includes('component')) && paths.some(p => p.includes('store'))) return 'Component-Store (SPA)';
-    if (paths.some(p => p.includes('pages/')) && paths.some(p => p.includes('api/'))) return 'Next.js (Pages Router)';
-    if (paths.some(p => p.includes('app/')) && paths.some(p => p.includes('route'))) return 'App Router';
-    if (paths.some(p => p.includes('packages/'))) return 'Monorepo';
-    return 'Flat';
-  }
-
-  _findCriticalPaths(dependencies) {
-    return Object.entries(dependencies)
-      .filter(([, deps]) => deps.length > 3)
-      .map(([file, deps]) => ({
-        file,
-        dependsOn: deps.length,
-        topDeps: deps.slice(0, 5),
-      }))
-      .sort((a, b) => b.dependsOn - a.dependsOn)
-      .slice(0, 20);
-  }
-
-  _findCircularRisks(dependencies) {
-    const risks = [];
-    for (const [fileA, depsA] of Object.entries(dependencies)) {
-      for (const dep of depsA) {
-        const resolved = this._resolveRelative(fileA, dep);
-        if (resolved && dependencies[resolved]) {
-          const depsB = dependencies[resolved];
-          if (depsB.some(d => this._resolveRelative(resolved, d) === fileA)) {
-            risks.push({ fileA, fileB: resolved, risk: 'circular dependency' });
-          }
-        }
-      }
-    }
-    return risks.slice(0, 10);
-  }
-
-  _resolveRelative(from, dep) {
-    if (dep.startsWith('.')) {
-      const dir = path.dirname(from);
-      let resolved = path.join(dir, dep).replace(/\\/g, '/');
-      if (!resolved.match(/\.\w+$/)) resolved += '.js';
-      return resolved;
-    }
-    return null;
-  }
-
-  _generateQuickSummary(fileMap, frameworks, architecture) {
-    const totalFiles = fileMap.length;
-    const fw = [...frameworks].join(', ') || 'vanilla';
-    return `${totalFiles}-file ${architecture} project using ${fw}. Start with entry points listed above.`;
-  }
-}
-
-module.exports = CodebasePassport;

package/packages/scanner/copy-paste-detector.js

@@ -1,276 +0,0 @@
-/**
- * Thuban Copy-Paste Drift Detector
- *
- * @purpose Find similar code blocks pasted in multiple files with slight variations
- * @module thuban
- * @layer scanner
- * @exports-to cli
- * @critical-for Code quality — AI generates similar solutions everywhere
- */
-
-const fs = require('fs');
-const path = require('path');
-const crypto = require('crypto');
-
-class CopyPasteDriftDetector {
-  constructor(opts = {}) {
-    this.rootPath = opts.rootPath || process.cwd();
-    this.minLines = opts.minLines || 5;          // Minimum function size to consider
-    this.similarityThreshold = opts.similarity || 0.7; // 70% similarity = likely copy-paste
-  }
-
-  /**
-   * Scan files for copy-paste clusters
-   */
-  scan(files) {
-    const functions = [];
-
-    // Extract all functions with their normalized bodies
-    for (const file of files) {
-      let content;
-      try {
-        const stat = fs.statSync(file);
-        if (stat.size > 512 * 1024) continue;
-        content = fs.readFileSync(file, 'utf-8');
-      } catch (e) {
-        continue;
-      }
-
-      const relPath = path.relative(this.rootPath, file);
-      if (this._isSkippable(relPath)) continue;
-
-      const fileFunctions = this._extractFunctions(content, relPath);
-      functions.push(...fileFunctions);
-    }
-
-    // Compare all functions to find clusters
-    const clusters = this._findClusters(functions);
-
-    const totalDuplicateLines = clusters.reduce((sum, c) =>
-      sum + c.members.reduce((s, m) => s + m.lineCount, 0) - c.members[0].lineCount, 0);
-
-    return {
-      clusters,
-      totalClusters: clusters.length,
-      totalDuplicateInstances: clusters.reduce((sum, c) => sum + c.members.length, 0),
-      totalDuplicateLines,
-      recommendation: clusters.length > 0
-        ? `Extract ${clusters.length} shared utilities to eliminate ${totalDuplicateLines} duplicate lines.`
-        : 'No copy-paste drift detected.',
-    };
-  }
-
-  // ─── Private ─────────────────────────────────────────────
-
-  _extractFunctions(content, filePath) {
-    const lines = content.split('\n');
-    const functions = [];
-
-    for (let i = 0; i < lines.length; i++) {
-      const fn = this._detectFunction(lines[i]);
-      if (!fn) continue;
-
-      const endLine = this._findFunctionEnd(lines, i);
-      const body = lines.slice(i, endLine + 1).join('\n');
-      const lineCount = endLine - i + 1;
-
-      if (lineCount < this.minLines) continue;
-
-      const normalized = this._normalize(body);
-      const hash = crypto.createHash('md5').update(normalized).digest('hex');
-      const tokens = this._tokenize(normalized);
-
-      functions.push({
-        file: filePath,
-        name: fn.name,
-        line: i + 1,
-        lineCount,
-        hash,
-        tokens,
-        normalized,
-      });
-
-      i = endLine;
-    }
-
-    return functions;
-  }
-
-  _findClusters(functions) {
-    const visited = new Set();
-    const clusters = [];
-
-    for (let i = 0; i < functions.length; i++) {
-      if (visited.has(i)) continue;
-
-      const cluster = [functions[i]];
-      visited.add(i);
-
-      for (let j = i + 1; j < functions.length; j++) {
-        if (visited.has(j)) continue;
-
-        // Quick hash check for exact duplicates
-        if (functions[i].hash === functions[j].hash) {
-          cluster.push(functions[j]);
-          visited.add(j);
-          continue;
-        }
-
-        // Token-level similarity check
-        const similarity = this._tokenSimilarity(functions[i].tokens, functions[j].tokens);
-        if (similarity >= this.similarityThreshold) {
-          cluster.push({ ...functions[j], similarity: Math.round(similarity * 100) });
-          visited.add(j);
-        }
-      }
-
-      if (cluster.length >= 2) {
-        // Find the differences between cluster members
-        const diffs = this._findDiffs(cluster);
-
-        clusters.push({
-          pattern: cluster[0].name,
-          members: cluster.map(m => ({
-            file: m.file,
-            name: m.name,
-            line: m.line,
-            lineCount: m.lineCount,
-            similarity: m.similarity || 100,
-          })),
-          totalInstances: cluster.length,
-          differences: diffs,
-          severity: cluster.length >= 4 ? 'high' : cluster.length >= 3 ? 'medium' : 'low',
-          recommendation: `Extract to shared utility. ${cluster.length} functions → 1.`,
-        });
-      }
-    }
-
-    return clusters.sort((a, b) => b.totalInstances - a.totalInstances);
-  }
-
-  _normalize(code) {
-    // Two-pass normalization:
-    // Pass 1: collect all declared variable names
-    const declaredNames = [];
-    const declPattern = /(?:const|let|var|function)\s+([a-zA-Z_$][a-zA-Z0-9_$]*)/g;
-    let m;
-    while ((m = declPattern.exec(code)) !== null) {
-      if (!declaredNames.includes(m[1])) declaredNames.push(m[1]);
-    }
-
-    let normalized = code
-      // Remove comments
-      .replace(/\/\/.*$/gm, '')
-      .replace(/\/\*[\s\S]*?\*\//g, '')
-      // Normalize string literals
-      .replace(/'[^']*'/g, 'STR')
-      .replace(/"[^"]*"/g, 'STR')
-      .replace(/`[^`]*`/g, 'STR')
-      // Normalize numbers
-      .replace(/\b\d+\.?\d*\b/g, 'NUM');
-
-    // Pass 2: replace ALL occurrences of each declared name with VAR_N
-    declaredNames.forEach((name, idx) => {
-      const nameRegex = new RegExp(`\\b${name.replace(/[.*+?^${}()|[\]\\]/g, '\\$&')}\\b`, 'g');
-      normalized = normalized.replace(nameRegex, `VAR_${idx}`);
-    });
-
-    // Normalize whitespace
-    return normalized.replace(/\s+/g, ' ').trim();
-  }
-
-  _tokenize(normalized) {
-    return normalized
-      .split(/[\s{}()\[\];,=+\-*/<>!&|?:.]+/)
-      .filter(t => t.length > 0);
-  }
-
-  _tokenSimilarity(tokens1, tokens2) {
-    if (tokens1.length === 0 && tokens2.length === 0) return 1;
-    if (tokens1.length === 0 || tokens2.length === 0) return 0;
-
-    const set1 = new Set(tokens1);
-    const set2 = new Set(tokens2);
-    const intersection = [...set1].filter(t => set2.has(t)).length;
-    const union = new Set([...tokens1, ...tokens2]).size;
-
-    // Jaccard similarity
-    const jaccard = union > 0 ? intersection / union : 0;
-
-    // Also consider length similarity
-    const lengthRatio = Math.min(tokens1.length, tokens2.length) / Math.max(tokens1.length, tokens2.length);
-
-    return (jaccard * 0.7) + (lengthRatio * 0.3);
-  }
-
-  _findDiffs(cluster) {
-    if (cluster.length < 2) return [];
-
-    const diffs = [];
-    const base = cluster[0].normalized;
-
-    for (let i = 1; i < cluster.length; i++) {
-      const other = cluster[i].normalized;
-      if (base !== other) {
-        const baseTokens = new Set(this._tokenize(base));
-        const otherTokens = new Set(this._tokenize(other));
-        const onlyInOther = [...otherTokens].filter(t => !baseTokens.has(t));
-        const onlyInBase = [...baseTokens].filter(t => !otherTokens.has(t));
-        if (onlyInOther.length > 0 || onlyInBase.length > 0) {
-          diffs.push({
-            file: cluster[i].file,
-            addedTokens: onlyInOther.slice(0, 5),
-            removedTokens: onlyInBase.slice(0, 5),
-          });
-        }
-      }
-    }
-
-    return diffs;
-  }
-
-  _detectFunction(line) {
-    const trimmed = line.trim();
-    // JavaScript/TypeScript: function/const/let/var
-    let match = trimmed.match(/^(?:export\s+)?(?:async\s+)?function\s+([a-zA-Z_$][a-zA-Z0-9_$]*)/);
-    if (match) return { name: match[1] };
-    match = trimmed.match(/^(?:export\s+)?(?:const|let|var)\s+([a-zA-Z_$][a-zA-Z0-9_$]*)\s*=\s*(?:async\s+)?(?:function|\()/);
-    if (match) return { name: match[1] };
-    // Kotlin: fun
-    match = trimmed.match(/^(?:private\s+|public\s+|internal\s+|protected\s+)?(?:suspend\s+)?fun\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*[(<]/);
-    if (match) return { name: match[1] };
-    // Rust: fn
-    match = trimmed.match(/^(?:pub(?:\([^)]*\))?\s+)?(?:async\s+)?fn\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*[(<]/);
-    if (match) return { name: match[1] };
-    // PHP: function
-    match = trimmed.match(/^(?:(?:public|private|protected|static)\s+)*function\s+([a-zA-Z_][a-zA-Z0-9_]*)\s*\(/);
-    if (match) return { name: match[1] };
-    // Ruby: def
-    match = trimmed.match(/^def\s+(?:self\.)?([a-zA-Z_][a-zA-Z0-9_?!]*)\s*[(\s]?/);
-    if (match) return { name: match[1] };
-    return null;
-  }
-
-  _findFunctionEnd(lines, startLine) {
-    let depth = 0;
-    let started = false;
-    for (let i = startLine; i < lines.length && i < startLine + 200; i++) {
-      for (const ch of lines[i]) {
-        if (ch === '{') { depth++; started = true; }
-        if (ch === '}') depth--;
-      }
-      if (started && depth <= 0) return i;
-    }
-    return Math.min(startLine + 20, lines.length - 1);
-  }
-
-  _isSkippable(relPath) {
-    const skip = [
-      /\.test\./i, /\.spec\./i, /test[\/\\]/i, /node_modules/i,
-      /\.min\./i, /\.d\.ts$/, /\.config\./i,
-    ];
-    return skip.some(r => r.test(relPath));
-  }
-}
-
-module.exports = CopyPasteDriftDetector;