@aiready/pattern-detect 0.16.6 → 0.16.7

package/dist/cli.js

@@ -312,14 +312,33 @@ function calculateSimilarity(a, b) {
   const union = /* @__PURE__ */ new Set([...setA, ...setB]);
   return intersection.size / union.size;
 }
+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));
+}
 async function detectDuplicatePatterns(fileContents, options) {
-  const { minSimilarity, minLines, streamResults, onProgress } = options;
+  const {
+    minSimilarity,
+    minLines,
+    streamResults,
+    onProgress,
+    excludePatterns = [],
+    confidenceThreshold = 0,
+    ignoreWhitelist = []
+  } = options;
   const allBlocks = [];
+  const excludeRegexes = excludePatterns.map((p) => new RegExp(p, "i"));
   for (const { file, content } of fileContents) {
     const blocks = extractBlocks(file, content);
-    allBlocks.push(
-      ...blocks.filter((b) => b.endLine - b.startLine + 1 >= minLines)
-    );
+    for (const b of blocks) {
+      if (b.endLine - b.startLine + 1 < minLines) continue;
+      const isExcluded = excludeRegexes.some((regex) => regex.test(b.code));
+      if (isExcluded) continue;
+      allBlocks.push(b);
+    }
   }
   const duplicates = [];
   const totalBlocks = allBlocks.length;
@@ -350,10 +369,20 @@ async function detectDuplicatePatterns(fileContents, options) {
       comparisons++;
       const b2 = allBlocks[j];
       if (b1.file === b2.file) continue;
+      const isWhitelisted = ignoreWhitelist.some((pattern) => {
+        return b1.file.includes(pattern) && b2.file.includes(pattern) || pattern === `${b1.file}::${b2.file}` || pattern === `${b2.file}::${b1.file}`;
+      });
+      if (isWhitelisted) continue;
       const isPython2 = b2.file.toLowerCase().endsWith(".py");
       const norm2 = normalizeCode(b2.code, isPython2);
       const sim = calculateSimilarity(norm1, norm2);
       if (sim >= minSimilarity) {
+        const confidence = calculateConfidence(
+          sim,
+          b1.tokens,
+          b1.endLine - b1.startLine + 1
+        );
+        if (confidence < confidenceThreshold) continue;
         const { severity, reason, suggestion, matchedRule } = calculateSeverity(
           b1.file,
           b2.file,
@@ -371,6 +400,7 @@ async function detectDuplicatePatterns(fileContents, options) {
           code1: b1.code,
           code2: b2.code,
           similarity: sim,
+          confidence,
           patternType: b1.patternType,
           tokenCost: b1.tokens + b2.tokens,
           severity,
@@ -381,7 +411,7 @@ async function detectDuplicatePatterns(fileContents, options) {
         duplicates.push(dup);
         if (streamResults)
           console.log(
-            `[DUPLICATE] ${dup.file1}:${dup.line1} <-> ${dup.file2}:${dup.line2} (${Math.round(sim * 100)}%)`
+            `[DUPLICATE] ${dup.file1}:${dup.line1} <-> ${dup.file2}:${dup.line2} (${Math.round(sim * 100)}%, conf: ${Math.round(confidence * 100)}%)`
           );
       }
     }
@@ -595,6 +625,17 @@ function logConfiguration(config, estimatedBlocks) {
   console.log(`   Min shared tokens: ${config.minSharedTokens}`);
   console.log(`   Severity filter: ${config.severity}`);
   console.log(`   Include tests: ${config.includeTests}`);
+  if (config.excludePatterns && config.excludePatterns.length > 0) {
+    console.log(`   Exclude patterns: ${config.excludePatterns.length} active`);
+  }
+  if (config.confidenceThreshold && config.confidenceThreshold > 0) {
+    console.log(`   Confidence threshold: ${config.confidenceThreshold}`);
+  }
+  if (config.ignoreWhitelist && config.ignoreWhitelist.length > 0) {
+    console.log(
+      `   Ignore whitelist: ${config.ignoreWhitelist.length} entries`
+    );
+  }
   console.log("");
 }
 async function analyzePatterns(options) {
@@ -613,6 +654,9 @@ async function analyzePatterns(options) {
     createClusters = true,
     minClusterTokenCost = 1e3,
     minClusterFiles = 3,
+    excludePatterns = [],
+    confidenceThreshold = 0,
+    ignoreWhitelist = [],
     ...scanOptions
   } = finalOptions;
   const files = await (0, import_core4.scanFiles)(scanOptions);
@@ -639,6 +683,9 @@ async function analyzePatterns(options) {
     minSharedTokens,
     maxCandidatesPerBlock,
     streamResults,
+    excludePatterns,
+    confidenceThreshold,
+    ignoreWhitelist,
     onProgress: options.onProgress
   });
   for (const file of files) {
@@ -740,6 +787,8 @@ function generateSummary(results) {
         }
       ],
       similarity: similarityMatch ? parseInt(similarityMatch[1]) / 100 : 0,
+      confidence: similarityMatch ? parseInt(similarityMatch[1]) / 100 : 0,
+      // Fallback for summary
       patternType: typeMatch?.[1] || "unknown",
       tokenCost: tokenMatch ? parseInt(tokenMatch[1]) : 0
     };
@@ -901,7 +950,7 @@ var PatternDetectProvider = {
 // src/index.ts
 import_core7.ToolRegistry.register(PatternDetectProvider);
 
-// src/cli.ts
+// src/cli-action.ts
 var import_chalk = __toESM(require("chalk"));
 var import_fs = require("fs");
 var import_path2 = require("path");
@@ -1006,80 +1055,61 @@ function generateHTMLReport(results, summary) {
 </html>`;
 }
 
-// src/cli.ts
-var program = new import_commander.Command();
-program.name("aiready-patterns").description("Detect duplicate patterns in your codebase").version("0.1.0").addHelpText(
-  "after",
-  "\nCONFIGURATION:\n  Supports config files: aiready.json, aiready.config.json, .aiready.json, .aireadyrc.json, aiready.config.js, .aireadyrc.js\n  CLI options override config file settings\n\nPARAMETER TUNING:\n  If you get too few results: decrease --similarity, --min-lines, or --min-shared-tokens\n  If analysis is too slow: increase --min-lines, --min-shared-tokens, or decrease --max-candidates\n  If you get too many false positives: increase --similarity or --min-lines\n\nEXAMPLES:\n  aiready-patterns .                                    # Basic analysis with smart defaults\n  aiready-patterns . --similarity 0.3 --min-lines 3     # More sensitive detection\n  aiready-patterns . --max-candidates 50 --no-approx    # Slower but more thorough\n  aiready-patterns . --output json > report.json       # JSON export"
-).argument("<directory>", "Directory to analyze").option(
-  "-s, --similarity <number>",
-  "Minimum similarity score (0-1). Lower = more results, higher = fewer but more accurate. Default: 0.4"
-).option(
-  "-l, --min-lines <number>",
-  "Minimum lines to consider. Lower = more results, higher = faster analysis. Default: 5"
-).option(
-  "--batch-size <number>",
-  "Batch size for comparisons. Higher = faster but more memory. Default: 100"
-).option(
-  "--no-approx",
-  "Disable approximate candidate selection. Slower but more thorough on small repos"
-).option(
-  "--min-shared-tokens <number>",
-  "Minimum shared tokens to consider a candidate. Higher = faster, fewer results. Default: 8"
-).option(
-  "--max-candidates <number>",
-  "Maximum candidates per block. Higher = more thorough but slower. Default: 100"
-).option(
-  "--no-stream-results",
-  "Disable incremental output (default: enabled)"
-).option("--include <patterns>", "File patterns to include (comma-separated)").option("--exclude <patterns>", "File patterns to exclude (comma-separated)").option(
-  "--min-severity <level>",
-  "Minimum severity to show: critical|major|minor|info. Default: minor"
-).option(
-  "--exclude-test-fixtures",
-  "Exclude test fixture duplication (beforeAll/afterAll)"
-).option("--exclude-templates", "Exclude template file duplication").option(
-  "--include-tests",
-  "Include test files in analysis (excluded by default)"
-).option(
-  "--max-results <number>",
-  "Maximum number of results to show in console output. Default: 10"
-).option("--no-group-by-file-pair", "Disable grouping duplicates by file pair").option("--no-create-clusters", "Disable creating refactor clusters").option(
-  "--min-cluster-tokens <number>",
-  "Minimum token cost for cluster reporting. Default: 1000"
-).option(
-  "--min-cluster-files <number>",
-  "Minimum files for cluster reporting. Default: 3"
-).option(
-  "--show-raw-duplicates",
-  "Show raw duplicates instead of grouped view"
-).option(
-  "-o, --output <format>",
-  "Output format: console, json, html",
-  "console"
-).option("--output-file <path>", "Output file path (for json/html)").action(async (directory, options) => {
+// src/constants.ts
+var DEFAULT_MIN_SIMILARITY = 0.4;
+var DEFAULT_MIN_LINES = 5;
+var DEFAULT_BATCH_SIZE = 100;
+var DEFAULT_MIN_SHARED_TOKENS = 8;
+var DEFAULT_MAX_CANDIDATES_PER_BLOCK = 100;
+var DEFAULT_MAX_RESULTS = 10;
+var DEFAULT_MIN_CLUSTER_TOKEN_COST = 1e3;
+var DEFAULT_MIN_CLUSTER_FILES = 3;
+var COMMAND_NAME = "aiready-patterns";
+var COMMAND_VERSION = "0.1.0";
+var DEFAULT_OUTPUT_FORMAT = "console";
+var HELP_TEXT_AFTER = `
+CONFIGURATION:
+  Supports config files: aiready.json, aiready.config.json, .aiready.json, .aireadyrc.json, aiready.config.js, .aireadyrc.js
+  CLI options override config file settings
+
+PARAMETER TUNING:
+  If you get too few results: decrease --similarity, --min-lines, or --min-shared-tokens
+  If analysis is too slow: increase --min-lines, --min-shared-tokens, or decrease --max-candidates
+  If you get too many false positives: increase --similarity or --min-lines
+
+EXAMPLES:
+  aiready-patterns .                                    # Basic analysis with smart defaults
+  aiready-patterns . --similarity 0.3 --min-lines 3     # More sensitive detection
+  aiready-patterns . --max-candidates 50 --no-approx    # Slower but more thorough
+  aiready-patterns . --output json > report.json       # JSON export`;
+
+// src/cli-action.ts
+async function patternActionHandler(directory, options) {
   console.log(import_chalk.default.blue("\u{1F50D} Analyzing patterns...\n"));
   const startTime = Date.now();
   const config = await (0, import_core9.loadConfig)(directory);
   const defaults = {
-    minSimilarity: 0.4,
-    minLines: 5,
-    batchSize: 100,
+    minSimilarity: DEFAULT_MIN_SIMILARITY,
+    minLines: DEFAULT_MIN_LINES,
+    batchSize: DEFAULT_BATCH_SIZE,
     approx: true,
-    minSharedTokens: 8,
-    maxCandidatesPerBlock: 100,
+    minSharedTokens: DEFAULT_MIN_SHARED_TOKENS,
+    maxCandidatesPerBlock: DEFAULT_MAX_CANDIDATES_PER_BLOCK,
     streamResults: true,
     include: void 0,
     exclude: void 0,
+    excludePatterns: void 0,
+    confidenceThreshold: 0,
+    ignoreWhitelist: void 0,
     minSeverity: import_core9.Severity.Minor,
     excludeTestFixtures: false,
     excludeTemplates: false,
     includeTests: false,
-    maxResults: 10,
+    maxResults: DEFAULT_MAX_RESULTS,
     groupByFilePair: true,
     createClusters: true,
-    minClusterTokenCost: 1e3,
-    minClusterFiles: 3,
+    minClusterTokenCost: DEFAULT_MIN_CLUSTER_TOKEN_COST,
+    minClusterFiles: DEFAULT_MIN_CLUSTER_FILES,
     showRawDuplicates: false
   };
   const mergedConfig = (0, import_core9.mergeConfigWithDefaults)(config, defaults);
@@ -1095,15 +1125,18 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
     streamResults: options.streamResults !== false && mergedConfig.streamResults,
     include: options.include?.split(",") || mergedConfig.include,
     exclude: options.exclude?.split(",") || mergedConfig.exclude,
+    excludePatterns: options.excludePatterns?.split(",") || mergedConfig.excludePatterns,
+    confidenceThreshold: options.confidenceThreshold ? parseFloat(options.confidenceThreshold) : mergedConfig.confidenceThreshold,
+    ignoreWhitelist: options.ignoreWhitelist?.split(",") || mergedConfig.ignoreWhitelist,
     minSeverity: options.minSeverity || mergedConfig.minSeverity,
     excludeTestFixtures: options.excludeTestFixtures || mergedConfig.excludeTestFixtures,
     excludeTemplates: options.excludeTemplates || mergedConfig.excludeTemplates,
     includeTests: options.includeTests || mergedConfig.includeTests,
     maxResults: options.maxResults ? parseInt(options.maxResults) : mergedConfig.maxResults,
-    groupByFilePair: options.groupBy_file_pair !== false && mergedConfig.groupByFilePair,
-    createClusters: options.create_clusters !== false && mergedConfig.createClusters,
-    minClusterTokenCost: options.min_cluster_tokens ? parseInt(options.min_cluster_tokens) : mergedConfig.minClusterTokenCost,
-    minClusterFiles: options.min_cluster_files ? parseInt(options.min_cluster_files) : mergedConfig.minClusterFiles,
+    groupByFilePair: options.groupByFilePair !== false && mergedConfig.groupByFilePair,
+    createClusters: options.createClusters !== false && mergedConfig.createClusters,
+    minClusterTokenCost: options.minClusterTokens ? parseInt(options.minClusterTokens) : mergedConfig.minClusterTokenCost,
+    minClusterFiles: options.minClusterFiles ? parseInt(options.minClusterFiles) : mergedConfig.minClusterFiles,
     showRawDuplicates: options.showRawDuplicates || mergedConfig.showRawDuplicates
   };
   if (finalOptions.includeTests && finalOptions.exclude) {
@@ -1189,9 +1222,7 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
   console.log(import_chalk.default.cyan(divider));
   console.log(import_chalk.default.bold.white("  PATTERN ANALYSIS SUMMARY"));
   console.log(import_chalk.default.cyan(divider) + "\n");
-  console.log(
-    import_chalk.default.white(`\u{1F4C1} Files analyzed: ${import_chalk.default.bold(results.length)}`)
-  );
+  console.log(import_chalk.default.white(`\u{1F4C1} Files analyzed: ${import_chalk.default.bold(results.length)}`));
   console.log(
     import_chalk.default.yellow(
       `\u26A0  AI confusion patterns detected: ${import_chalk.default.bold(totalIssues)}`
@@ -1202,9 +1233,7 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
       `\u{1F4B0} Token cost (wasted): ${import_chalk.default.bold(summary.totalTokenCost.toLocaleString())}`
     )
   );
-  console.log(
-    import_chalk.default.gray(`\u23F1  Analysis time: ${import_chalk.default.bold(elapsedTime + "s")}`)
-  );
+  console.log(import_chalk.default.gray(`\u23F1  Analysis time: ${import_chalk.default.bold(elapsedTime + "s")}`));
   const sortedTypes = Object.entries(summary.patternsByType).filter(([, count]) => count > 0).sort(([, a], [, b]) => b - a);
   if (sortedTypes.length > 0) {
     console.log(import_chalk.default.cyan("\n" + divider));
@@ -1270,9 +1299,7 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
     console.log(import_chalk.default.cyan(divider) + "\n");
     clusters.sort((a, b) => b.totalTokenCost - a.totalTokenCost).forEach((cluster, idx) => {
       const severityBadge = (0, import_core9.getSeverityBadge)(cluster.severity);
-      console.log(
-        `${idx + 1}. ${severityBadge} ${import_chalk.default.bold(cluster.name)}`
-      );
+      console.log(`${idx + 1}. ${severityBadge} ${import_chalk.default.bold(cluster.name)}`);
       console.log(
         `   Total tokens: ${import_chalk.default.bold(cluster.totalTokenCost.toLocaleString())} | Avg similarity: ${import_chalk.default.bold(Math.round(cluster.averageSimilarity * 100) + "%")} | Duplicates: ${import_chalk.default.bold(cluster.duplicateCount)}`
       );
@@ -1354,10 +1381,8 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
         import_chalk.default.red("\u25CF ") + import_chalk.default.white(`${issue.file}:${issue.location.line}`)
       );
       console.log(`  ${import_chalk.default.dim(issue.message)}`);
-      console.log(
-        `  ${import_chalk.default.green("\u2192")} ${import_chalk.default.italic(issue.suggestion)}
-`
-      );
+      console.log(`  ${import_chalk.default.green("\u2192")} ${import_chalk.default.italic(issue.suggestion)}
+`);
     });
   }
   if (totalIssues === 0) {
@@ -1367,9 +1392,7 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
         "\u{1F4A1} If you expected to find duplicates, try adjusting parameters:"
       )
     );
-    console.log(
-      import_chalk.default.dim("   \u2022 Lower similarity threshold: --similarity 0.3")
-    );
+    console.log(import_chalk.default.dim("   \u2022 Lower similarity threshold: --similarity 0.3"));
     console.log(import_chalk.default.dim("   \u2022 Reduce minimum lines: --min-lines 3"));
     console.log(import_chalk.default.dim("   \u2022 Include test files: --include-tests"));
     console.log(
@@ -1381,9 +1404,7 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
     console.log(
       import_chalk.default.yellow("\n\u{1F4A1} Few results found. To find more duplicates, try:")
     );
-    console.log(
-      import_chalk.default.dim("   \u2022 Lower similarity threshold: --similarity 0.3")
-    );
+    console.log(import_chalk.default.dim("   \u2022 Lower similarity threshold: --similarity 0.3"));
     console.log(import_chalk.default.dim("   \u2022 Reduce minimum lines: --min-lines 3"));
     console.log(import_chalk.default.dim("   \u2022 Include test files: --include-tests"));
     console.log(
@@ -1410,5 +1431,64 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
       "\u{1F41B} Found a bug? Report it: https://github.com/caopengau/aiready-pattern-detect/issues\n"
     )
   );
-});
+}
+
+// src/cli.ts
+var program = new import_commander.Command();
+program.name(COMMAND_NAME).description("Detect duplicate patterns in your codebase").version(COMMAND_VERSION).addHelpText("after", HELP_TEXT_AFTER).argument("<directory>", "Directory to analyze").option(
+  "-s, --similarity <number>",
+  `Minimum similarity score (0-1). Default: ${DEFAULT_MIN_SIMILARITY}`
+).option(
+  "-l, --min-lines <number>",
+  `Minimum lines to consider. Default: ${DEFAULT_MIN_LINES}`
+).option(
+  "--batch-size <number>",
+  `Batch size for comparisons. Default: ${DEFAULT_BATCH_SIZE}`
+).option(
+  "--no-approx",
+  "Disable approximate candidate selection. Slower but more thorough on small repos"
+).option(
+  "--min-shared-tokens <number>",
+  `Minimum shared tokens to consider a candidate. Default: ${DEFAULT_MIN_SHARED_TOKENS}`
+).option(
+  "--max-candidates <number>",
+  `Maximum candidates per block. Default: ${DEFAULT_MAX_CANDIDATES_PER_BLOCK}`
+).option(
+  "--no-stream-results",
+  "Disable incremental output (default: enabled)"
+).option("--include <patterns>", "File patterns to include (comma-separated)").option("--exclude <patterns>", "File patterns to exclude (comma-separated)").option(
+  "--exclude-patterns <regexes>",
+  "Regex patterns to exclude specific code content (comma-separated)"
+).option(
+  "--confidence-threshold <number>",
+  "Minimum confidence score (0-1). Default: 0"
+).option(
+  "--ignore-whitelist <patterns>",
+  "List of file pairs or patterns to ignore (comma-separated)"
+).option(
+  "--min-severity <level>",
+  "Minimum severity to show: critical|major|minor|info. Default: minor"
+).option(
+  "--exclude-test-fixtures",
+  "Exclude test fixture duplication (beforeAll/afterAll)"
+).option("--exclude-templates", "Exclude template file duplication").option(
+  "--include-tests",
+  "Include test files in analysis (excluded by default)"
+).option(
+  "--max-results <number>",
+  `Maximum number of results to show in console output. Default: ${DEFAULT_MAX_RESULTS}`
+).option("--no-group-by-file-pair", "Disable grouping duplicates by file pair").option("--no-create-clusters", "Disable creating refactor clusters").option(
+  "--min-cluster-tokens <number>",
+  `Minimum token cost for cluster reporting. Default: ${DEFAULT_MIN_CLUSTER_TOKEN_COST}`
+).option(
+  "--min-cluster-files <number>",
+  `Minimum files for cluster reporting. Default: ${DEFAULT_MIN_CLUSTER_FILES}`
+).option(
+  "--show-raw-duplicates",
+  "Show raw duplicates instead of grouped view"
+).option(
+  "-o, --output <format>",
+  "Output format: console, json, html",
+  DEFAULT_OUTPUT_FORMAT
+).option("--output-file <path>", "Output file path (for json/html)").action(patternActionHandler);
 program.parse();