@aiready/pattern-detect 0.16.19 → 0.16.20

package/dist/cli.mjs

@@ -1,10 +1,10 @@
 #!/usr/bin/env node
-import "./chunk-UB3CGOQ7.mjs";
+import "./chunk-6JTVOBJX.mjs";
 import {
   analyzePatterns,
   generateSummary
-} from "./chunk-WMOGJFME.mjs";
-import "./chunk-THF4RW63.mjs";
+} from "./chunk-DNZS4ESD.mjs";
+import "./chunk-VGMM3L3O.mjs";
 import {
   filterBySeverity
 } from "./chunk-I6ETJC7L.mjs";
@@ -23,7 +23,9 @@ import {
   resolveOutputPath,
   Severity,
   getSeverityBadge as getSeverityBadge2,
-  getSeverityValue as getSeverityValue2
+  getSeverityValue as getSeverityValue2,
+  printTerminalHeader,
+  getTerminalDivider
 } from "@aiready/core";
 
 // src/cli-output.ts
@@ -32,6 +34,7 @@ import {
   getSeverityValue,
   generateReportHead,
   generateStatCards,
+  generateScoreCard,
   generateTable,
   generateReportFooter
 } from "@aiready/core";
@@ -52,10 +55,14 @@ function generateHTMLReport(results, summary) {
   const { metadata } = data;
   const s = data.summary;
   const head = generateReportHead("AIReady - Pattern Detection Report");
-  const scoreCard = `<div class="stat-card" style="margin-bottom: 2rem;">
-    <div class="stat-label">AI Ready Score (Deduplication)</div>
-    <div class="stat-value">${Math.max(0, 100 - Math.round((s.duplicates?.length || 0) / (s.totalFiles || 1) * 20))}%</div>
-  </div>`;
+  const score = Math.max(
+    0,
+    100 - Math.round((s.duplicates?.length || 0) / (s.totalFiles || 1) * 20)
+  );
+  const scoreCard = generateScoreCard(
+    `${score}%`,
+    "AI Ready Score (Deduplication)"
+  );
   const stats = generateStatCards([
     { value: s.totalFiles, label: "Files Analyzed" },
     { value: s.duplicates?.length || 0, label: "Duplicate Clusters" },
@@ -254,12 +261,7 @@ async function patternActionHandler(directory, options) {
 \u2713 HTML report saved to ${outputPath}`));
     return;
   }
-  const terminalWidth = process.stdout.columns || 80;
-  const dividerWidth = Math.min(60, terminalWidth - 2);
-  const divider = "\u2501".repeat(dividerWidth);
-  console.log(chalk.cyan(divider));
-  console.log(chalk.bold.white("  PATTERN ANALYSIS SUMMARY"));
-  console.log(chalk.cyan(divider) + "\n");
+  printTerminalHeader("PATTERN ANALYSIS SUMMARY");
   console.log(chalk.white(`\u{1F4C1} Files analyzed: ${chalk.bold(results.length)}`));
   console.log(
     chalk.yellow(
@@ -274,9 +276,9 @@ async function patternActionHandler(directory, options) {
   console.log(chalk.gray(`\u23F1  Analysis time: ${chalk.bold(elapsedTime + "s")}`));
   const sortedTypes = Object.entries(summary.patternsByType).filter(([, count]) => count > 0).sort(([, a], [, b]) => b - a);
   if (sortedTypes.length > 0) {
-    console.log(chalk.cyan("\n" + divider));
+    console.log("\n" + getTerminalDivider());
     console.log(chalk.bold.white("  PATTERNS BY TYPE"));
-    console.log(chalk.cyan(divider) + "\n");
+    console.log(getTerminalDivider() + "\n");
     sortedTypes.forEach(([type, count]) => {
       const icon = getPatternIcon(type);
       console.log(
@@ -285,11 +287,11 @@ async function patternActionHandler(directory, options) {
     });
   }
   if (!finalOptions.showRawDuplicates && groups && groups.length > 0) {
-    console.log(chalk.cyan("\n" + divider));
+    console.log("\n" + getTerminalDivider());
     console.log(
       chalk.bold.white(`  \u{1F4E6} DUPLICATE GROUPS (${groups.length} file pairs)`)
     );
-    console.log(chalk.cyan(divider) + "\n");
+    console.log(getTerminalDivider() + "\n");
     const topGroups = groups.sort((a, b) => {
       const bVal = getSeverityValue2(b.severity);
       const aVal = getSeverityValue2(a.severity);
@@ -330,11 +332,11 @@ async function patternActionHandler(directory, options) {
     }
   }
   if (!finalOptions.showRawDuplicates && clusters && clusters.length > 0) {
-    console.log(chalk.cyan("\n" + divider));
+    console.log("\n" + getTerminalDivider());
     console.log(
       chalk.bold.white(`  \u{1F3AF} REFACTOR CLUSTERS (${clusters.length} patterns)`)
     );
-    console.log(chalk.cyan(divider) + "\n");
+    console.log(getTerminalDivider() + "\n");
     clusters.sort((a, b) => b.totalTokenCost - a.totalTokenCost).forEach((cluster, idx) => {
       const severityBadge = getSeverityBadge2(cluster.severity);
       console.log(`${idx + 1}. ${severityBadge} ${chalk.bold(cluster.name)}`);
@@ -362,9 +364,9 @@ async function patternActionHandler(directory, options) {
     });
   }
   if (totalIssues > 0 && (finalOptions.showRawDuplicates || !groups || groups.length === 0)) {
-    console.log(chalk.cyan("\n" + divider));
+    console.log("\n" + getTerminalDivider());
     console.log(chalk.bold.white("  TOP DUPLICATE PATTERNS"));
-    console.log(chalk.cyan(divider) + "\n");
+    console.log(getTerminalDivider() + "\n");
     const topDuplicates = filteredDuplicates.sort((a, b) => {
       const bVal = getSeverityValue2(b.severity);
       const aVal = getSeverityValue2(a.severity);
@@ -411,9 +413,9 @@ async function patternActionHandler(directory, options) {
     (issue) => getSeverityValue2(issue.severity) === 4
   );
   if (criticalIssues.length > 0) {
-    console.log(chalk.cyan(divider));
+    console.log(getTerminalDivider());
     console.log(chalk.bold.white("  CRITICAL ISSUES (>95% similar)"));
-    console.log(chalk.cyan(divider) + "\n");
+    console.log(getTerminalDivider() + "\n");
     criticalIssues.slice(0, 5).forEach((issue) => {
       console.log(
         chalk.red("\u25CF ") + chalk.white(`${issue.file}:${issue.location.line}`)
@@ -450,7 +452,7 @@ async function patternActionHandler(directory, options) {
     );
     console.log("");
   }
-  console.log(chalk.cyan(divider));
+  console.log(getTerminalDivider());
   if (totalIssues > 0) {
     console.log(
       chalk.white(

package/dist/detector-entry.js

@@ -167,144 +167,27 @@ function calculateSeverity(file1, file2, code, similarity, linesOfCode) {
   }
 }
 
-// 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/detector-entry.mjs

@@ -1,6 +1,6 @@
 import {
   detectDuplicatePatterns
-} from "./chunk-THF4RW63.mjs";
+} from "./chunk-VGMM3L3O.mjs";
 import "./chunk-I6ETJC7L.mjs";
 export {
   detectDuplicatePatterns

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

@@ -1,7 +1,7 @@
 import {
   PatternDetectProvider,
   Severity
-} from "./chunk-UB3CGOQ7.mjs";
+} from "./chunk-6JTVOBJX.mjs";
 import {
   analyzePatterns,
   createRefactorClusters,
@@ -9,10 +9,10 @@ import {
   generateSummary,
   getSmartDefaults,
   groupDuplicatesByFilePair
-} from "./chunk-WMOGJFME.mjs";
+} from "./chunk-DNZS4ESD.mjs";
 import {
   detectDuplicatePatterns
-} from "./chunk-THF4RW63.mjs";
+} from "./chunk-VGMM3L3O.mjs";
 import {
   CONTEXT_RULES,
   calculateSeverity,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@aiready/pattern-detect",
-  "version": "0.16.19",
+  "version": "0.16.20",
   "description": "Semantic duplicate pattern detection for AI-generated code - finds similar implementations that waste AI context tokens",
   "main": "./dist/index.js",
   "module": "./dist/index.mjs",
@@ -65,7 +65,7 @@
   "dependencies": {
     "commander": "^14.0.0",
     "chalk": "^5.3.0",
-    "@aiready/core": "0.23.20"
+    "@aiready/core": "0.23.21"
   },
   "devDependencies": {
     "tsup": "^8.3.5",