@aiready/pattern-detect 0.16.18 → 0.16.20

package/dist/detector-entry.mjs

@@ -0,0 +1,7 @@
+import {
+  detectDuplicatePatterns
+} from "./chunk-VGMM3L3O.mjs";
+import "./chunk-I6ETJC7L.mjs";
+export {
+  detectDuplicatePatterns
+};

package/dist/index.d.mts

@@ -1,242 +1,14 @@
-import { ToolProvider, Severity, FileContent, ScanOptions, AnalysisResult, CostConfig, ToolScoringOutput } from '@aiready/core';
+import { ToolProvider } from '@aiready/core';
 export { Severity } from '@aiready/core';
+export { D as DuplicateGroup, P as PatternDetectOptions, a as PatternSummary, R as RefactorCluster, b as analyzePatterns, c as createRefactorClusters, f as filterClustersByImpact, g as generateSummary, d as getSmartDefaults, e as groupDuplicatesByFilePair } from './analyzer-entry-BVz-HnZd.mjs';
+export { detectDuplicatePatterns } from './detector-entry.mjs';
+export { calculatePatternScore } from './scoring-entry.mjs';
+export { C as CONTEXT_RULES, a as ContextRule, c as calculateSeverity, f as filterBySeverity, g as getSeverityLabel, b as getSeverityThreshold } from './context-rules-entry-y2uJSngh.mjs';
+export { D as DuplicatePattern, P as PatternType } from './types-DU2mmhwb.mjs';
 
 /**
  * Pattern Detection Tool Provider
  */
 declare const PatternDetectProvider: ToolProvider;
 
-type PatternType = 'api-handler' | 'validator' | 'utility' | 'class-method' | 'component' | 'function' | 'unknown';
-interface DuplicatePattern {
-    file1: string;
-    line1: number;
-    endLine1: number;
-    file2: string;
-    line2: number;
-    endLine2: number;
-    code1: string;
-    code2: string;
-    similarity: number;
-    confidence: number;
-    patternType: PatternType;
-    tokenCost: number;
-    severity: Severity;
-    reason?: string;
-    suggestion?: string;
-    matchedRule?: string;
-}
-interface DetectionOptions {
-    minSimilarity: number;
-    minLines: number;
-    batchSize: number;
-    approx: boolean;
-    minSharedTokens: number;
-    maxCandidatesPerBlock: number;
-    streamResults: boolean;
-    excludePatterns?: string[];
-    confidenceThreshold?: number;
-    ignoreWhitelist?: string[];
-    onProgress?: (processed: number, total: number, message: string) => void;
-}
-
-/**
- * Detect duplicate patterns across files
- *
- * @param fileContents - Array of file contents to analyze.
- * @param options - Configuration for duplicate detection (thresholds, progress, etc).
- * @returns Promise resolving to an array of detected duplicate patterns sorted by similarity.
- */
-declare function detectDuplicatePatterns(fileContents: FileContent[], options: DetectionOptions): Promise<DuplicatePattern[]>;
-
-interface DuplicateGroup {
-    filePair: string;
-    severity: Severity;
-    occurrences: number;
-    totalTokenCost: number;
-    averageSimilarity: number;
-    patternTypes: Set<PatternType>;
-    lineRanges: Array<{
-        file1: {
-            start: number;
-            end: number;
-        };
-        file2: {
-            start: number;
-            end: number;
-        };
-    }>;
-}
-interface RefactorCluster {
-    id: string;
-    name: string;
-    files: string[];
-    severity: Severity;
-    duplicateCount: number;
-    totalTokenCost: number;
-    averageSimilarity: number;
-    reason?: string;
-    suggestion?: string;
-}
-/**
- * Group raw duplicates by file pairs to reduce noise
- */
-declare function groupDuplicatesByFilePair(duplicates: DuplicatePattern[]): DuplicateGroup[];
-/**
- * Create clusters of highly related files (refactor targets)
- * Uses a simple connected components algorithm
- * @param duplicates - Array of duplicate patterns to cluster
- * @returns Array of refactor clusters
- */
-declare function createRefactorClusters(duplicates: DuplicatePattern[]): RefactorCluster[];
-/**
- * Filter clusters by impact threshold
- * @param clusters - Array of refactor clusters to filter
- * @param minTokenCost - Minimum token cost threshold (default: 1000)
- * @param minFiles - Minimum number of files in cluster (default: 3)
- * @returns Filtered array of refactor clusters
- */
-declare function filterClustersByImpact(clusters: RefactorCluster[], minTokenCost?: number, minFiles?: number): RefactorCluster[];
-
-interface PatternDetectOptions extends ScanOptions {
-    minSimilarity?: number;
-    minLines?: number;
-    batchSize?: number;
-    approx?: boolean;
-    minSharedTokens?: number;
-    maxCandidatesPerBlock?: number;
-    streamResults?: boolean;
-    severity?: string;
-    includeTests?: boolean;
-    useSmartDefaults?: boolean;
-    groupByFilePair?: boolean;
-    createClusters?: boolean;
-    minClusterTokenCost?: number;
-    minClusterFiles?: number;
-    excludePatterns?: string[];
-    confidenceThreshold?: number;
-    ignoreWhitelist?: string[];
-    onProgress?: (processed: number, total: number, message: string) => void;
-}
-interface PatternSummary {
-    totalPatterns: number;
-    totalTokenCost: number;
-    patternsByType: Record<PatternType, number>;
-    topDuplicates: Array<{
-        files: Array<{
-            path: string;
-            startLine: number;
-            endLine: number;
-        }>;
-        similarity: number;
-        patternType: PatternType;
-        tokenCost: number;
-    }>;
-}
-/**
- * Determine smart defaults based on repository size estimation.
- *
- * @param directory - The directory to analyze for size.
- * @param userOptions - User-provided option overrides.
- * @returns Promise resolving to optimal detection options.
- */
-declare function getSmartDefaults(directory: string, userOptions: Partial<PatternDetectOptions>): Promise<PatternDetectOptions>;
-/**
- * Main entry point for pattern detection analysis.
- *
- * @param options - Configuration including rootDir and detection parameters.
- * @returns Promise resolving to the comprehensive pattern detect report.
- * @lastUpdated 2026-03-18
- */
-declare function analyzePatterns(options: PatternDetectOptions): Promise<{
-    results: AnalysisResult[];
-    duplicates: DuplicatePattern[];
-    files: string[];
-    groups?: DuplicateGroup[];
-    clusters?: RefactorCluster[];
-    config: PatternDetectOptions;
-}>;
-/**
- * Generate a summary of pattern detection results.
- *
- * @param results - Array of file-level analysis results.
- * @returns Consolidated pattern summary object.
- */
-declare function generateSummary(results: AnalysisResult[]): PatternSummary;
-
-/**
- * Calculate AI Readiness Score for pattern duplication (0-100)
- *
- * Based on:
- * - Number of duplicates per file
- * - Token waste per file
- * - High-impact duplicates (>1000 tokens or >70% similarity)
- *
- * Includes business value metrics:
- * - Estimated monthly cost of token waste
- * - Estimated developer hours to fix
- *
- * @param duplicates - Array of detected duplicate patterns.
- * @param totalFilesAnalyzed - Total count of files scanned.
- * @param costConfig - Optional configuration for business value calculations.
- * @returns Standardized scoring output for pattern detection.
- */
-declare function calculatePatternScore(duplicates: DuplicatePattern[], totalFilesAnalyzed: number, costConfig?: Partial<CostConfig>): ToolScoringOutput;
-
-/**
- * Context-aware severity detection for duplicate patterns
- * Identifies intentional duplication patterns and adjusts severity accordingly
- */
-interface ContextRule {
-    name: string;
-    detect: (file: string, code: string) => boolean;
-    severity: Severity;
-    reason: string;
-    suggestion?: string;
-}
-/**
- * Context rules for detecting intentional or acceptable duplication patterns
- * Rules are checked in order - first match wins
- */
-declare const CONTEXT_RULES: ContextRule[];
-/**
- * Calculate severity based on context rules and code characteristics
- *
- * @param file1 - First file path in the duplicate pair.
- * @param file2 - Second file path in the duplicate pair.
- * @param code - Snippet of the duplicated code.
- * @param similarity - The calculated similarity score (0-1).
- * @param linesOfCode - Number of lines in the duplicated block.
- * @returns An object containing the severity level and reasoning.
- */
-declare function calculateSeverity(file1: string, file2: string, code: string, similarity: number, linesOfCode: number): {
-    severity: Severity;
-    reason?: string;
-    suggestion?: string;
-    matchedRule?: string;
-};
-/**
- * Get a human-readable severity label with emoji
- *
- * @param severity - The severity level to label.
- * @returns Formatted label string for UI display.
- */
-declare function getSeverityLabel(severity: Severity): string;
-/**
- * Filter duplicates by minimum severity threshold
- *
- * @param duplicates - List of items with a severity property.
- * @param minSeverity - Minimum threshold for inclusion.
- * @returns Filtered list of items.
- */
-declare function filterBySeverity<T extends {
-    severity: Severity;
-}>(duplicates: T[], minSeverity: Severity): T[];
-/**
- * Get numerical similarity threshold associated with a severity level
- *
- * @param severity - The severity level to look up.
- * @returns Minimum similarity value for this severity.
- */
-declare function getSeverityThreshold(severity: Severity): number;
-
-export { CONTEXT_RULES, type ContextRule, type DuplicateGroup, type DuplicatePattern, type PatternDetectOptions, PatternDetectProvider, type PatternSummary, type PatternType, type RefactorCluster, analyzePatterns, calculatePatternScore, calculateSeverity, createRefactorClusters, detectDuplicatePatterns, filterBySeverity, filterClustersByImpact, generateSummary, getSeverityLabel, getSeverityThreshold, getSmartDefaults, groupDuplicatesByFilePair };
+export { PatternDetectProvider };

package/dist/index.d.ts

@@ -1,242 +1,14 @@
-import { ToolProvider, Severity, FileContent, ScanOptions, AnalysisResult, CostConfig, ToolScoringOutput } from '@aiready/core';
+import { ToolProvider } from '@aiready/core';
 export { Severity } from '@aiready/core';
+export { D as DuplicateGroup, P as PatternDetectOptions, a as PatternSummary, R as RefactorCluster, b as analyzePatterns, c as createRefactorClusters, f as filterClustersByImpact, g as generateSummary, d as getSmartDefaults, e as groupDuplicatesByFilePair } from './analyzer-entry-BwuoiCNm.js';
+export { detectDuplicatePatterns } from './detector-entry.js';
+export { calculatePatternScore } from './scoring-entry.js';
+export { C as CONTEXT_RULES, a as ContextRule, c as calculateSeverity, f as filterBySeverity, g as getSeverityLabel, b as getSeverityThreshold } from './context-rules-entry-y2uJSngh.js';
+export { D as DuplicatePattern, P as PatternType } from './types-DU2mmhwb.js';
 
 /**
  * Pattern Detection Tool Provider
  */
 declare const PatternDetectProvider: ToolProvider;
 
-type PatternType = 'api-handler' | 'validator' | 'utility' | 'class-method' | 'component' | 'function' | 'unknown';
-interface DuplicatePattern {
-    file1: string;
-    line1: number;
-    endLine1: number;
-    file2: string;
-    line2: number;
-    endLine2: number;
-    code1: string;
-    code2: string;
-    similarity: number;
-    confidence: number;
-    patternType: PatternType;
-    tokenCost: number;
-    severity: Severity;
-    reason?: string;
-    suggestion?: string;
-    matchedRule?: string;
-}
-interface DetectionOptions {
-    minSimilarity: number;
-    minLines: number;
-    batchSize: number;
-    approx: boolean;
-    minSharedTokens: number;
-    maxCandidatesPerBlock: number;
-    streamResults: boolean;
-    excludePatterns?: string[];
-    confidenceThreshold?: number;
-    ignoreWhitelist?: string[];
-    onProgress?: (processed: number, total: number, message: string) => void;
-}
-
-/**
- * Detect duplicate patterns across files
- *
- * @param fileContents - Array of file contents to analyze.
- * @param options - Configuration for duplicate detection (thresholds, progress, etc).
- * @returns Promise resolving to an array of detected duplicate patterns sorted by similarity.
- */
-declare function detectDuplicatePatterns(fileContents: FileContent[], options: DetectionOptions): Promise<DuplicatePattern[]>;
-
-interface DuplicateGroup {
-    filePair: string;
-    severity: Severity;
-    occurrences: number;
-    totalTokenCost: number;
-    averageSimilarity: number;
-    patternTypes: Set<PatternType>;
-    lineRanges: Array<{
-        file1: {
-            start: number;
-            end: number;
-        };
-        file2: {
-            start: number;
-            end: number;
-        };
-    }>;
-}
-interface RefactorCluster {
-    id: string;
-    name: string;
-    files: string[];
-    severity: Severity;
-    duplicateCount: number;
-    totalTokenCost: number;
-    averageSimilarity: number;
-    reason?: string;
-    suggestion?: string;
-}
-/**
- * Group raw duplicates by file pairs to reduce noise
- */
-declare function groupDuplicatesByFilePair(duplicates: DuplicatePattern[]): DuplicateGroup[];
-/**
- * Create clusters of highly related files (refactor targets)
- * Uses a simple connected components algorithm
- * @param duplicates - Array of duplicate patterns to cluster
- * @returns Array of refactor clusters
- */
-declare function createRefactorClusters(duplicates: DuplicatePattern[]): RefactorCluster[];
-/**
- * Filter clusters by impact threshold
- * @param clusters - Array of refactor clusters to filter
- * @param minTokenCost - Minimum token cost threshold (default: 1000)
- * @param minFiles - Minimum number of files in cluster (default: 3)
- * @returns Filtered array of refactor clusters
- */
-declare function filterClustersByImpact(clusters: RefactorCluster[], minTokenCost?: number, minFiles?: number): RefactorCluster[];
-
-interface PatternDetectOptions extends ScanOptions {
-    minSimilarity?: number;
-    minLines?: number;
-    batchSize?: number;
-    approx?: boolean;
-    minSharedTokens?: number;
-    maxCandidatesPerBlock?: number;
-    streamResults?: boolean;
-    severity?: string;
-    includeTests?: boolean;
-    useSmartDefaults?: boolean;
-    groupByFilePair?: boolean;
-    createClusters?: boolean;
-    minClusterTokenCost?: number;
-    minClusterFiles?: number;
-    excludePatterns?: string[];
-    confidenceThreshold?: number;
-    ignoreWhitelist?: string[];
-    onProgress?: (processed: number, total: number, message: string) => void;
-}
-interface PatternSummary {
-    totalPatterns: number;
-    totalTokenCost: number;
-    patternsByType: Record<PatternType, number>;
-    topDuplicates: Array<{
-        files: Array<{
-            path: string;
-            startLine: number;
-            endLine: number;
-        }>;
-        similarity: number;
-        patternType: PatternType;
-        tokenCost: number;
-    }>;
-}
-/**
- * Determine smart defaults based on repository size estimation.
- *
- * @param directory - The directory to analyze for size.
- * @param userOptions - User-provided option overrides.
- * @returns Promise resolving to optimal detection options.
- */
-declare function getSmartDefaults(directory: string, userOptions: Partial<PatternDetectOptions>): Promise<PatternDetectOptions>;
-/**
- * Main entry point for pattern detection analysis.
- *
- * @param options - Configuration including rootDir and detection parameters.
- * @returns Promise resolving to the comprehensive pattern detect report.
- * @lastUpdated 2026-03-18
- */
-declare function analyzePatterns(options: PatternDetectOptions): Promise<{
-    results: AnalysisResult[];
-    duplicates: DuplicatePattern[];
-    files: string[];
-    groups?: DuplicateGroup[];
-    clusters?: RefactorCluster[];
-    config: PatternDetectOptions;
-}>;
-/**
- * Generate a summary of pattern detection results.
- *
- * @param results - Array of file-level analysis results.
- * @returns Consolidated pattern summary object.
- */
-declare function generateSummary(results: AnalysisResult[]): PatternSummary;
-
-/**
- * Calculate AI Readiness Score for pattern duplication (0-100)
- *
- * Based on:
- * - Number of duplicates per file
- * - Token waste per file
- * - High-impact duplicates (>1000 tokens or >70% similarity)
- *
- * Includes business value metrics:
- * - Estimated monthly cost of token waste
- * - Estimated developer hours to fix
- *
- * @param duplicates - Array of detected duplicate patterns.
- * @param totalFilesAnalyzed - Total count of files scanned.
- * @param costConfig - Optional configuration for business value calculations.
- * @returns Standardized scoring output for pattern detection.
- */
-declare function calculatePatternScore(duplicates: DuplicatePattern[], totalFilesAnalyzed: number, costConfig?: Partial<CostConfig>): ToolScoringOutput;
-
-/**
- * Context-aware severity detection for duplicate patterns
- * Identifies intentional duplication patterns and adjusts severity accordingly
- */
-interface ContextRule {
-    name: string;
-    detect: (file: string, code: string) => boolean;
-    severity: Severity;
-    reason: string;
-    suggestion?: string;
-}
-/**
- * Context rules for detecting intentional or acceptable duplication patterns
- * Rules are checked in order - first match wins
- */
-declare const CONTEXT_RULES: ContextRule[];
-/**
- * Calculate severity based on context rules and code characteristics
- *
- * @param file1 - First file path in the duplicate pair.
- * @param file2 - Second file path in the duplicate pair.
- * @param code - Snippet of the duplicated code.
- * @param similarity - The calculated similarity score (0-1).
- * @param linesOfCode - Number of lines in the duplicated block.
- * @returns An object containing the severity level and reasoning.
- */
-declare function calculateSeverity(file1: string, file2: string, code: string, similarity: number, linesOfCode: number): {
-    severity: Severity;
-    reason?: string;
-    suggestion?: string;
-    matchedRule?: string;
-};
-/**
- * Get a human-readable severity label with emoji
- *
- * @param severity - The severity level to label.
- * @returns Formatted label string for UI display.
- */
-declare function getSeverityLabel(severity: Severity): string;
-/**
- * Filter duplicates by minimum severity threshold
- *
- * @param duplicates - List of items with a severity property.
- * @param minSeverity - Minimum threshold for inclusion.
- * @returns Filtered list of items.
- */
-declare function filterBySeverity<T extends {
-    severity: Severity;
-}>(duplicates: T[], minSeverity: Severity): T[];
-/**
- * Get numerical similarity threshold associated with a severity level
- *
- * @param severity - The severity level to look up.
- * @returns Minimum similarity value for this severity.
- */
-declare function getSeverityThreshold(severity: Severity): number;
-
-export { CONTEXT_RULES, type ContextRule, type DuplicateGroup, type DuplicatePattern, type PatternDetectOptions, PatternDetectProvider, type PatternSummary, type PatternType, type RefactorCluster, analyzePatterns, calculatePatternScore, calculateSeverity, createRefactorClusters, detectDuplicatePatterns, filterBySeverity, filterClustersByImpact, generateSummary, getSeverityLabel, getSeverityThreshold, getSmartDefaults, groupDuplicatesByFilePair };
+export { PatternDetectProvider };

package/dist/index.js

@@ -230,144 +230,27 @@ function getSeverityThreshold(severity) {
   return thresholds[severity] || 0;
 }
 
-// src/detector.ts
+// src/core/normalizer.ts
 function normalizeCode(code, isPython = false) {
+  if (!code) return "";
   let normalized = code;
   if (isPython) {
     normalized = normalized.replace(/#.*/g, "");
   } else {
-    normalized = normalized.replace(/\/\/.*/g, "").replace(/\/\*[\s\S]*?\*\//g, "");
+    normalized = normalized.replace(/\/\/.*$/gm, "").replace(/\/\*[\s\S]*?\*\//g, "");
   }
-  return normalized.replace(/['"`]/g, '"').replace(/\s+/g, " ").trim().toLowerCase();
+  return normalized.replace(/"[^"]*"/g, '"STR"').replace(/'[^']*'/g, "'STR'").replace(/`[^`]*`/g, "`STR`").replace(/\b\d+\b/g, "NUM").replace(/\s+/g, " ").trim().toLowerCase();
 }
+
+// src/detector.ts
 function extractBlocks(file, content) {
-  const isPython = file.toLowerCase().endsWith(".py");
-  if (isPython) {
-    return extractBlocksPython(file, content);
-  }
-  const blocks = [];
-  const lines = content.split("\n");
-  const blockRegex = /^\s*(?:export\s+)?(?:async\s+)?(?:public\s+|private\s+|protected\s+|internal\s+|static\s+|readonly\s+|virtual\s+|abstract\s+|override\s+)*(function|class|interface|type|enum|record|struct|void|func|[a-zA-Z0-9_<>[]]+)\s+([a-zA-Z0-9_]+)(?:\s*\(|(?:\s+extends|\s+implements|\s+where)?\s*\{)|^\s*(?:export\s+)?const\s+([a-zA-Z0-9_]+)\s*=\s*[a-zA-Z0-9_.]+\.object\(|^\s*(app\.(?:get|post|put|delete|patch|use))\(/gm;
-  let match;
-  while ((match = blockRegex.exec(content)) !== null) {
-    const startLine = content.substring(0, match.index).split("\n").length;
-    let type;
-    let name;
-    if (match[1]) {
-      type = match[1];
-      name = match[2];
-    } else if (match[3]) {
-      type = "const";
-      name = match[3];
-    } else {
-      type = "handler";
-      name = match[4];
-    }
-    let endLine = -1;
-    let openBraces = 0;
-    let foundStart = false;
-    for (let i = match.index; i < content.length; i++) {
-      if (content[i] === "{") {
-        openBraces++;
-        foundStart = true;
-      } else if (content[i] === "}") {
-        openBraces--;
-      }
-      if (foundStart && openBraces === 0) {
-        endLine = content.substring(0, i + 1).split("\n").length;
-        break;
-      }
-    }
-    if (endLine === -1) {
-      const remaining = content.slice(match.index);
-      const nextLineMatch = remaining.indexOf("\n");
-      if (nextLineMatch !== -1) {
-        endLine = startLine;
-      } else {
-        endLine = lines.length;
-      }
-    }
-    endLine = Math.max(startLine, endLine);
-    const blockCode = lines.slice(startLine - 1, endLine).join("\n");
-    const tokens = (0, import_core2.estimateTokens)(blockCode);
-    blocks.push({
-      file,
-      startLine,
-      endLine,
-      code: blockCode,
-      tokens,
-      patternType: inferPatternType(type, name)
-    });
-  }
-  return blocks;
-}
-function extractBlocksPython(file, content) {
-  const blocks = [];
-  const lines = content.split("\n");
-  const blockRegex = /^\s*(?:async\s+)?(def|class)\s+([a-zA-Z0-9_]+)/gm;
-  let match;
-  while ((match = blockRegex.exec(content)) !== null) {
-    const startLinePos = content.substring(0, match.index).split("\n").length;
-    const startLineIdx = startLinePos - 1;
-    const initialIndent = lines[startLineIdx].search(/\S/);
-    let endLineIdx = startLineIdx;
-    for (let i = startLineIdx + 1; i < lines.length; i++) {
-      const line = lines[i];
-      if (line.trim().length === 0) {
-        endLineIdx = i;
-        continue;
-      }
-      const currentIndent = line.search(/\S/);
-      if (currentIndent <= initialIndent) {
-        break;
-      }
-      endLineIdx = i;
-    }
-    while (endLineIdx > startLineIdx && lines[endLineIdx].trim().length === 0) {
-      endLineIdx--;
-    }
-    const blockCode = lines.slice(startLineIdx, endLineIdx + 1).join("\n");
-    const tokens = (0, import_core2.estimateTokens)(blockCode);
-    blocks.push({
-      file,
-      startLine: startLinePos,
-      endLine: endLineIdx + 1,
-      code: blockCode,
-      tokens,
-      patternType: inferPatternType(match[1], match[2])
-    });
-  }
-  return blocks;
-}
-function inferPatternType(keyword, name) {
-  const n = name.toLowerCase();
-  if (keyword === "handler" || n.includes("handler") || n.includes("controller") || n.startsWith("app.")) {
-    return "api-handler";
-  }
-  if (n.includes("validate") || n.includes("schema")) return "validator";
-  if (n.includes("util") || n.includes("helper")) return "utility";
-  if (keyword === "class") return "class-method";
-  if (n.match(/^[A-Z]/)) return "component";
-  if (keyword === "function") return "function";
-  return "unknown";
+  return (0, import_core2.extractCodeBlocks)(file, content);
 }
 function calculateSimilarity(a, b) {
-  if (a === b) return 1;
-  const tokensA = a.split(/[^a-zA-Z0-9]+/).filter((t) => t.length > 0);
-  const tokensB = b.split(/[^a-zA-Z0-9]+/).filter((t) => t.length > 0);
-  if (tokensA.length === 0 || tokensB.length === 0) return 0;
-  const setA = new Set(tokensA);
-  const setB = new Set(tokensB);
-  const intersection = new Set([...setA].filter((x) => setB.has(x)));
-  const union = /* @__PURE__ */ new Set([...setA, ...setB]);
-  return intersection.size / union.size;
+  return (0, import_core2.calculateStringSimilarity)(a, b);
 }
 function calculateConfidence(similarity, tokens, lines) {
-  let confidence = similarity;
-  if (lines > 20) confidence += 0.05;
-  if (tokens > 200) confidence += 0.05;
-  if (lines < 5) confidence -= 0.1;
-  return Math.max(0, Math.min(1, confidence));
+  return (0, import_core2.calculateHeuristicConfidence)(similarity, tokens, lines);
 }
 async function detectDuplicatePatterns(fileContents, options) {
   const {

package/dist/index.mjs

@@ -1,20 +1,28 @@
 import {
-  CONTEXT_RULES,
   PatternDetectProvider,
-  Severity,
+  Severity
+} from "./chunk-6JTVOBJX.mjs";
+import {
   analyzePatterns,
-  calculatePatternScore,
-  calculateSeverity,
   createRefactorClusters,
-  detectDuplicatePatterns,
-  filterBySeverity,
   filterClustersByImpact,
   generateSummary,
-  getSeverityLabel,
-  getSeverityThreshold,
   getSmartDefaults,
   groupDuplicatesByFilePair
-} from "./chunk-BUBQ3W6W.mjs";
+} from "./chunk-DNZS4ESD.mjs";
+import {
+  detectDuplicatePatterns
+} from "./chunk-VGMM3L3O.mjs";
+import {
+  CONTEXT_RULES,
+  calculateSeverity,
+  filterBySeverity,
+  getSeverityLabel,
+  getSeverityThreshold
+} from "./chunk-I6ETJC7L.mjs";
+import {
+  calculatePatternScore
+} from "./chunk-WBBO35SC.mjs";
 export {
   CONTEXT_RULES,
   PatternDetectProvider,