@aiready/pattern-detect 0.1.3 → 0.2.0

package/dist/{chunk-4CZGZIDL.mjs → chunk-QE4E3F7C.mjs}

@@ -2,7 +2,7 @@
 import { scanFiles, readFileContent } from "@aiready/core";
 
 // src/detector.ts
-import { similarityScore, estimateTokens } from "@aiready/core";
+import { estimateTokens } from "@aiready/core";
 function categorizePattern(code) {
   const lower = code.toLowerCase();
   if (lower.includes("request") && lower.includes("response") || lower.includes("router.") || lower.includes("app.get") || lower.includes("app.post") || lower.includes("express") || lower.includes("ctx.body")) {
@@ -80,15 +80,6 @@ function jaccardSimilarity(tokens1, tokens2) {
   const union = set1.size + set2.size - intersection;
   return union === 0 ? 0 : intersection / union;
 }
-function calculateSimilarity(block1, block2) {
-  const norm1 = normalizeCode(block1);
-  const norm2 = normalizeCode(block2);
-  const baseSimilarity = similarityScore(norm1, norm2);
-  const tokens1 = norm1.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokens2 = norm2.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokenSimilarity = similarityScore(tokens1.join(" "), tokens2.join(" "));
-  return baseSimilarity * 0.4 + tokenSimilarity * 0.6;
-}
 async function detectDuplicatePatterns(files, options) {
   const {
     minSimilarity,
@@ -98,7 +89,6 @@ async function detectDuplicatePatterns(files, options) {
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
     maxComparisons = 5e4,
     // Cap at 50K comparisons by default
     streamResults = false
@@ -213,7 +203,7 @@ async function detectDuplicatePatterns(files, options) {
         if (maxComparisons && comparisonsProcessed >= maxComparisons) break;
         comparisonsProcessed++;
         const block2 = allBlocks[j];
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
@@ -243,7 +233,7 @@ async function detectDuplicatePatterns(files, options) {
         comparisonsProcessed++;
         const block2 = allBlocks[j];
         if (block1.file === block2.file) continue;
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
@@ -293,15 +283,14 @@ function getRefactoringSuggestion(patternType, similarity) {
 }
 async function analyzePatterns(options) {
   const {
-    minSimilarity = 0.65,
-    // Lower default for fast Jaccard mode (Levenshtein would be 0.85+)
+    minSimilarity = 0.4,
+    // Jaccard similarity default (40% threshold)
     minLines = 5,
     maxBlocks = 500,
     batchSize = 100,
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
     maxComparisons = 5e4,
     streamResults = false,
     ...scanOptions
@@ -322,7 +311,6 @@ async function analyzePatterns(options) {
     approx,
     minSharedTokens,
     maxCandidatesPerBlock,
-    fastMode,
     maxComparisons,
     streamResults
   });
@@ -387,8 +375,21 @@ function generateSummary(results) {
     const typeMatch = issue.message.match(/^(\S+(?:-\S+)*) pattern/);
     const fileMatch = issue.message.match(/similar to (.+?) \(/);
     return {
-      file1: issue.location.file,
-      file2: fileMatch?.[1] || "unknown",
+      files: [
+        {
+          path: issue.location.file,
+          startLine: issue.location.line,
+          endLine: 0
+          // Not available from Issue
+        },
+        {
+          path: fileMatch?.[1] || "unknown",
+          startLine: 0,
+          // Not available from Issue
+          endLine: 0
+          // Not available from Issue
+        }
+      ],
       similarity: similarityMatch ? parseInt(similarityMatch[1]) / 100 : 0,
       patternType: typeMatch?.[1] || "unknown",
       tokenCost: tokenMatch ? parseInt(tokenMatch[1]) : 0

package/dist/{chunk-ZNZ5O435.mjs → chunk-TXWPOVYU.mjs}

@@ -2,7 +2,7 @@
 import { scanFiles, readFileContent } from "@aiready/core";
 
 // src/detector.ts
-import { similarityScore, estimateTokens } from "@aiready/core";
+import { estimateTokens } from "@aiready/core";
 function categorizePattern(code) {
   const lower = code.toLowerCase();
   if (lower.includes("request") && lower.includes("response") || lower.includes("router.") || lower.includes("app.get") || lower.includes("app.post") || lower.includes("express") || lower.includes("ctx.body")) {
@@ -54,6 +54,7 @@ function extractCodeBlocks(content, minLines) {
       blocks.push({
         content: blockContent,
         startLine: blockStart + 1,
+        endLine: i + 1,
         patternType: categorizePattern(blockContent),
         linesOfCode
       });
@@ -79,44 +80,32 @@ function jaccardSimilarity(tokens1, tokens2) {
   const union = set1.size + set2.size - intersection;
   return union === 0 ? 0 : intersection / union;
 }
-function calculateSimilarity(block1, block2) {
-  const norm1 = normalizeCode(block1);
-  const norm2 = normalizeCode(block2);
-  const baseSimilarity = similarityScore(norm1, norm2);
-  const tokens1 = norm1.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokens2 = norm2.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokenSimilarity = similarityScore(tokens1.join(" "), tokens2.join(" "));
-  return baseSimilarity * 0.4 + tokenSimilarity * 0.6;
-}
 async function detectDuplicatePatterns(files, options) {
   const {
     minSimilarity,
     minLines,
-    maxBlocks = 500,
     batchSize = 100,
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
-    maxComparisons = 5e4,
-    // Cap at 50K comparisons by default
+    maxComparisons = 1e5,
+    // Cap at 100K comparisons by default
     streamResults = false
   } = options;
   const duplicates = [];
-  let allBlocks = files.flatMap(
+  const allBlocks = files.flatMap(
     (file) => extractCodeBlocks(file.content, minLines).map((block) => ({
-      ...block,
+      content: block.content,
+      startLine: block.startLine,
+      endLine: block.endLine,
       file: file.file,
       normalized: normalizeCode(block.content),
-      tokenCost: estimateTokens(block.content)
+      patternType: block.patternType,
+      tokenCost: estimateTokens(block.content),
+      linesOfCode: block.linesOfCode
     }))
   );
   console.log(`Extracted ${allBlocks.length} code blocks for analysis`);
-  if (allBlocks.length > maxBlocks) {
-    console.log(`\u26A0\uFE0F  Limiting to ${maxBlocks} blocks (sorted by size) to prevent memory issues`);
-    console.log(`   Use --max-blocks to increase limit or --min-lines to filter smaller blocks`);
-    allBlocks = allBlocks.sort((a, b) => b.linesOfCode - a.linesOfCode).slice(0, maxBlocks);
-  }
   const stopwords = /* @__PURE__ */ new Set([
     "return",
     "const",
@@ -208,13 +197,15 @@ async function detectDuplicatePatterns(files, options) {
         if (maxComparisons && comparisonsProcessed >= maxComparisons) break;
         comparisonsProcessed++;
         const block2 = allBlocks[j];
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
             file2: block2.file,
             line1: block1.startLine,
             line2: block2.startLine,
+            endLine1: block1.endLine,
+            endLine2: block2.endLine,
             similarity,
             snippet: block1.content.split("\n").slice(0, 5).join("\n") + "\n...",
             patternType: block1.patternType,
@@ -225,7 +216,7 @@ async function detectDuplicatePatterns(files, options) {
           if (streamResults) {
             console.log(`
    \u2705 Found: ${duplicate.patternType} ${Math.round(similarity * 100)}% similar`);
-            console.log(`      ${duplicate.file1}:${duplicate.line1} \u21D4 ${duplicate.file2}:${duplicate.line2}`);
+            console.log(`      ${duplicate.file1}:${duplicate.line1}-${duplicate.endLine1} \u21D4 ${duplicate.file2}:${duplicate.line2}-${duplicate.endLine2}`);
             console.log(`      Token cost: ${duplicate.tokenCost.toLocaleString()}`);
           }
         }
@@ -236,13 +227,15 @@ async function detectDuplicatePatterns(files, options) {
         comparisonsProcessed++;
         const block2 = allBlocks[j];
         if (block1.file === block2.file) continue;
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
             file2: block2.file,
             line1: block1.startLine,
             line2: block2.startLine,
+            endLine1: block1.endLine,
+            endLine2: block2.endLine,
             similarity,
             snippet: block1.content.split("\n").slice(0, 5).join("\n") + "\n...",
             patternType: block1.patternType,
@@ -253,7 +246,7 @@ async function detectDuplicatePatterns(files, options) {
           if (streamResults) {
             console.log(`
    \u2705 Found: ${duplicate.patternType} ${Math.round(similarity * 100)}% similar`);
-            console.log(`      ${duplicate.file1}:${duplicate.line1} \u21D4 ${duplicate.file2}:${duplicate.line2}`);
+            console.log(`      ${duplicate.file1}:${duplicate.line1}-${duplicate.endLine1} \u21D4 ${duplicate.file2}:${duplicate.line2}-${duplicate.endLine2}`);
             console.log(`      Token cost: ${duplicate.tokenCost.toLocaleString()}`);
           }
         }
@@ -284,16 +277,14 @@ function getRefactoringSuggestion(patternType, similarity) {
 }
 async function analyzePatterns(options) {
   const {
-    minSimilarity = 0.7,
-    // Lower default for fast Jaccard mode (was 0.85 for Levenshtein)
+    minSimilarity = 0.4,
+    // Jaccard similarity default (40% threshold)
     minLines = 5,
-    maxBlocks = 500,
     batchSize = 100,
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
-    maxComparisons = 5e4,
+    maxComparisons = 1e5,
     streamResults = false,
     ...scanOptions
   } = options;
@@ -308,12 +299,10 @@ async function analyzePatterns(options) {
   const duplicates = await detectDuplicatePatterns(fileContents, {
     minSimilarity,
     minLines,
-    maxBlocks,
     batchSize,
     approx,
     minSharedTokens,
     maxCandidatesPerBlock,
-    fastMode,
     maxComparisons,
     streamResults
   });
@@ -378,8 +367,21 @@ function generateSummary(results) {
     const typeMatch = issue.message.match(/^(\S+(?:-\S+)*) pattern/);
     const fileMatch = issue.message.match(/similar to (.+?) \(/);
     return {
-      file1: issue.location.file,
-      file2: fileMatch?.[1] || "unknown",
+      files: [
+        {
+          path: issue.location.file,
+          startLine: issue.location.line,
+          endLine: 0
+          // Not available from Issue
+        },
+        {
+          path: fileMatch?.[1] || "unknown",
+          startLine: 0,
+          // Not available from Issue
+          endLine: 0
+          // Not available from Issue
+        }
+      ],
       similarity: similarityMatch ? parseInt(similarityMatch[1]) / 100 : 0,
       patternType: typeMatch?.[1] || "unknown",
       tokenCost: tokenMatch ? parseInt(tokenMatch[1]) : 0

package/dist/cli.js

@@ -108,31 +108,19 @@ function jaccardSimilarity(tokens1, tokens2) {
   const union = set1.size + set2.size - intersection;
   return union === 0 ? 0 : intersection / union;
 }
-function calculateSimilarity(block1, block2) {
-  const norm1 = normalizeCode(block1);
-  const norm2 = normalizeCode(block2);
-  const baseSimilarity = (0, import_core.similarityScore)(norm1, norm2);
-  const tokens1 = norm1.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokens2 = norm2.split(/[\s(){}[\];,]+/).filter(Boolean);
-  const tokenSimilarity = (0, import_core.similarityScore)(tokens1.join(" "), tokens2.join(" "));
-  return baseSimilarity * 0.4 + tokenSimilarity * 0.6;
-}
 async function detectDuplicatePatterns(files, options) {
   const {
     minSimilarity,
     minLines,
-    maxBlocks = 500,
     batchSize = 100,
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
-    maxComparisons = 5e4,
-    // Cap at 50K comparisons by default
     streamResults = false
   } = options;
   const duplicates = [];
-  let allBlocks = files.flatMap(
+  const maxComparisons = approx ? Infinity : 5e5;
+  const allBlocks = files.flatMap(
     (file) => extractCodeBlocks(file.content, minLines).map((block) => ({
       content: block.content,
       startLine: block.startLine,
@@ -145,10 +133,9 @@ async function detectDuplicatePatterns(files, options) {
     }))
   );
   console.log(`Extracted ${allBlocks.length} code blocks for analysis`);
-  if (allBlocks.length > maxBlocks) {
-    console.log(`\u26A0\uFE0F  Limiting to ${maxBlocks} blocks (sorted by size) to prevent memory issues`);
-    console.log(`   Use --max-blocks to increase limit or --min-lines to filter smaller blocks`);
-    allBlocks = allBlocks.sort((a, b) => b.linesOfCode - a.linesOfCode).slice(0, maxBlocks);
+  if (!approx && allBlocks.length > 500) {
+    console.log(`\u26A0\uFE0F  Using --no-approx mode with ${allBlocks.length} blocks may be slow (O(B\xB2) complexity).`);
+    console.log(`   Consider using approximate mode (default) for better performance.`);
   }
   const stopwords = /* @__PURE__ */ new Set([
     "return",
@@ -238,10 +225,14 @@ async function detectDuplicatePatterns(files, options) {
     }
     if (approx && candidates) {
       for (const { j } of candidates) {
-        if (maxComparisons && comparisonsProcessed >= maxComparisons) break;
+        if (!approx && maxComparisons !== Infinity && comparisonsProcessed >= maxComparisons) {
+          console.log(`\u26A0\uFE0F  Comparison safety limit reached (${maxComparisons.toLocaleString()} comparisons in --no-approx mode).`);
+          console.log(`   This prevents excessive runtime on large repos. Consider using approximate mode (default) or --min-lines to reduce blocks.`);
+          break;
+        }
         comparisonsProcessed++;
         const block2 = allBlocks[j];
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
@@ -271,7 +262,7 @@ async function detectDuplicatePatterns(files, options) {
         comparisonsProcessed++;
         const block2 = allBlocks[j];
         if (block1.file === block2.file) continue;
-        const similarity = fastMode ? jaccardSimilarity(blockTokens[i], blockTokens[j]) : calculateSimilarity(block1.content, block2.content);
+        const similarity = jaccardSimilarity(blockTokens[i], blockTokens[j]);
         if (similarity >= minSimilarity) {
           const duplicate = {
             file1: block1.file,
@@ -321,16 +312,13 @@ function getRefactoringSuggestion(patternType, similarity) {
 }
 async function analyzePatterns(options) {
   const {
-    minSimilarity = 0.65,
-    // Lower default for fast Jaccard mode (Levenshtein would be 0.85+)
+    minSimilarity = 0.4,
+    // Jaccard similarity default (40% threshold)
     minLines = 5,
-    maxBlocks = 500,
     batchSize = 100,
     approx = true,
     minSharedTokens = 8,
     maxCandidatesPerBlock = 100,
-    fastMode = true,
-    maxComparisons = 5e4,
     streamResults = false,
     ...scanOptions
   } = options;
@@ -345,13 +333,10 @@ async function analyzePatterns(options) {
   const duplicates = await detectDuplicatePatterns(fileContents, {
     minSimilarity,
     minLines,
-    maxBlocks,
     batchSize,
     approx,
     minSharedTokens,
     maxCandidatesPerBlock,
-    fastMode,
-    maxComparisons,
     streamResults
   });
   for (const file of files) {
@@ -415,15 +400,21 @@ function generateSummary(results) {
     const typeMatch = issue.message.match(/^(\S+(?:-\S+)*) pattern/);
     const fileMatch = issue.message.match(/similar to (.+?) \(/);
     return {
-      file1: issue.location.file,
-      file2: fileMatch?.[1] || "unknown",
-      line1: issue.location.line,
-      line2: 0,
-      // Not available from Issue
-      endLine1: 0,
-      // Not available from Issue
-      endLine2: 0,
-      // Not available from Issue
+      files: [
+        {
+          path: issue.location.file,
+          startLine: issue.location.line,
+          endLine: 0
+          // Not available from Issue
+        },
+        {
+          path: fileMatch?.[1] || "unknown",
+          startLine: 0,
+          // Not available from Issue
+          endLine: 0
+          // Not available from Issue
+        }
+      ],
       similarity: similarityMatch ? parseInt(similarityMatch[1]) / 100 : 0,
       patternType: typeMatch?.[1] || "unknown",
       tokenCost: tokenMatch ? parseInt(tokenMatch[1]) : 0
@@ -442,30 +433,28 @@ var import_chalk = __toESM(require("chalk"));
 var import_fs = require("fs");
 var import_path = require("path");
 var program = new import_commander.Command();
-program.name("aiready-patterns").description("Detect duplicate patterns in your codebase").version("0.1.0").argument("<directory>", "Directory to analyze").option("-s, --similarity <number>", "Minimum similarity score (0-1)", "0.40").option("-l, --min-lines <number>", "Minimum lines to consider", "5").option("--max-blocks <number>", "Maximum blocks to analyze (prevents OOM)", "500").option("--batch-size <number>", "Batch size for comparisons", "100").option("--no-approx", "Disable approximate candidate selection (faster on small repos, slower on large)").option("--min-shared-tokens <number>", "Minimum shared tokens to consider a candidate", "8").option("--max-candidates <number>", "Maximum candidates per block", "100").option("--no-fast-mode", "Use slower but more accurate Levenshtein distance (default: fast Jaccard)").option("--max-comparisons <number>", "Maximum total comparisons budget", "50000").option("--stream-results", "Output duplicates incrementally as found (useful for slow analysis)").option("--include <patterns>", "File patterns to include (comma-separated)").option("--exclude <patterns>", "File patterns to exclude (comma-separated)").option(
+program.name("aiready-patterns").description("Detect duplicate patterns in your codebase").version("0.1.0").argument("<directory>", "Directory to analyze").option("-s, --similarity <number>", "Minimum similarity score (0-1)", "0.40").option("-l, --min-lines <number>", "Minimum lines to consider", "5").option("--batch-size <number>", "Batch size for comparisons", "100").option("--no-approx", "Disable approximate candidate selection (faster on small repos, slower on large)").option("--min-shared-tokens <number>", "Minimum shared tokens to consider a candidate", "8").option("--max-candidates <number>", "Maximum candidates per block", "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(
   "-o, --output <format>",
   "Output format: console, json, html",
   "console"
 ).option("--output-file <path>", "Output file path (for json/html)").action(async (directory, options) => {
   console.log(import_chalk.default.blue("\u{1F50D} Analyzing patterns...\n"));
+  const startTime = Date.now();
   const results = await analyzePatterns({
     rootDir: directory,
     minSimilarity: parseFloat(options.similarity),
     minLines: parseInt(options.minLines),
-    maxBlocks: parseInt(options.maxBlocks),
     batchSize: parseInt(options.batchSize),
     approx: options.approx !== false,
     // default true; --no-approx sets to false
     minSharedTokens: parseInt(options.minSharedTokens),
     maxCandidatesPerBlock: parseInt(options.maxCandidates),
-    fastMode: options.fastMode !== false,
-    // default true; --no-fast-mode sets to false
-    maxComparisons: parseInt(options.maxComparisons),
-    streamResults: options.streamResults === true,
-    // default false; --stream-results sets to true
+    streamResults: options.streamResults !== false,
+    // default true; --no-stream-results sets to false
     include: options.include?.split(","),
     exclude: options.exclude?.split(",")
   });
+  const elapsedTime = ((Date.now() - startTime) / 1e3).toFixed(2);
   const summary = generateSummary(results);
   const totalIssues = results.reduce((sum, r) => sum + r.issues.length, 0);
   if (options.output === "json") {
@@ -508,6 +497,9 @@ 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: ${import_chalk.default.bold(elapsedTime + "s")}`)
+  );
   const sortedTypes = Object.entries(summary.patternsByType).filter(([, count]) => count > 0).sort(([, a], [, b]) => b - a);
   if (sortedTypes.length > 0) {
     console.log(import_chalk.default.cyan("\n" + divider));
@@ -529,12 +521,12 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
           `${Math.round(dup.similarity * 100)}%`
         )} ${getPatternIcon(dup.patternType)} ${import_chalk.default.white(dup.patternType)}`
       );
-      console.log(
-        `   ${import_chalk.default.dim(dup.file1)}:${import_chalk.default.cyan(dup.line1)}-${import_chalk.default.cyan(dup.endLine1)}`
-      );
-      console.log(
-        `   ${import_chalk.default.dim("\u2194")} ${import_chalk.default.dim(dup.file2)}:${import_chalk.default.cyan(dup.line2)}-${import_chalk.default.cyan(dup.endLine2)}`
-      );
+      dup.files.forEach((file, fileIdx) => {
+        const prefix = fileIdx === 0 ? "   " : "   \u2194 ";
+        console.log(
+          `${import_chalk.default.dim(prefix)}${import_chalk.default.dim(file.path)}:${import_chalk.default.cyan(file.startLine)}-${import_chalk.default.cyan(file.endLine)}`
+        );
+      });
       console.log(
         `   ${import_chalk.default.red(`${dup.tokenCost.toLocaleString()} tokens wasted`)}
 `
@@ -631,8 +623,7 @@ function generateHTMLReport(summary, results) {
         <tr>
           <th>Similarity</th>
           <th>Type</th>
-          <th>File 1</th>
-          <th>File 2</th>
+          <th>Files</th>
           <th>Token Cost</th>
         </tr>
       </thead>
@@ -642,8 +633,7 @@ function generateHTMLReport(summary, results) {
           <tr>
             <td class="${dup.similarity > 0.95 ? "critical" : dup.similarity > 0.9 ? "major" : "minor"}">${Math.round(dup.similarity * 100)}%</td>
             <td>${dup.patternType}</td>
-            <td><code>${dup.file1}</code></td>
-            <td><code>${dup.file2}</code></td>
+            <td>${dup.files.map((f) => `<code>${f.path}:${f.startLine}-${f.endLine}</code>`).join("<br>\u2194<br>")}</td>
             <td>${dup.tokenCost.toLocaleString()}</td>
           </tr>
         `

package/dist/cli.mjs

@@ -2,7 +2,7 @@
 import {
   analyzePatterns,
   generateSummary
-} from "./chunk-N5DE7IYX.mjs";
+} from "./chunk-JKVKOXYR.mjs";
 
 // src/cli.ts
 import { Command } from "commander";
@@ -10,30 +10,28 @@ import chalk from "chalk";
 import { writeFileSync } from "fs";
 import { join } from "path";
 var program = new Command();
-program.name("aiready-patterns").description("Detect duplicate patterns in your codebase").version("0.1.0").argument("<directory>", "Directory to analyze").option("-s, --similarity <number>", "Minimum similarity score (0-1)", "0.40").option("-l, --min-lines <number>", "Minimum lines to consider", "5").option("--max-blocks <number>", "Maximum blocks to analyze (prevents OOM)", "500").option("--batch-size <number>", "Batch size for comparisons", "100").option("--no-approx", "Disable approximate candidate selection (faster on small repos, slower on large)").option("--min-shared-tokens <number>", "Minimum shared tokens to consider a candidate", "8").option("--max-candidates <number>", "Maximum candidates per block", "100").option("--no-fast-mode", "Use slower but more accurate Levenshtein distance (default: fast Jaccard)").option("--max-comparisons <number>", "Maximum total comparisons budget", "50000").option("--stream-results", "Output duplicates incrementally as found (useful for slow analysis)").option("--include <patterns>", "File patterns to include (comma-separated)").option("--exclude <patterns>", "File patterns to exclude (comma-separated)").option(
+program.name("aiready-patterns").description("Detect duplicate patterns in your codebase").version("0.1.0").argument("<directory>", "Directory to analyze").option("-s, --similarity <number>", "Minimum similarity score (0-1)", "0.40").option("-l, --min-lines <number>", "Minimum lines to consider", "5").option("--batch-size <number>", "Batch size for comparisons", "100").option("--no-approx", "Disable approximate candidate selection (faster on small repos, slower on large)").option("--min-shared-tokens <number>", "Minimum shared tokens to consider a candidate", "8").option("--max-candidates <number>", "Maximum candidates per block", "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(
   "-o, --output <format>",
   "Output format: console, json, html",
   "console"
 ).option("--output-file <path>", "Output file path (for json/html)").action(async (directory, options) => {
   console.log(chalk.blue("\u{1F50D} Analyzing patterns...\n"));
+  const startTime = Date.now();
   const results = await analyzePatterns({
     rootDir: directory,
     minSimilarity: parseFloat(options.similarity),
     minLines: parseInt(options.minLines),
-    maxBlocks: parseInt(options.maxBlocks),
     batchSize: parseInt(options.batchSize),
     approx: options.approx !== false,
     // default true; --no-approx sets to false
     minSharedTokens: parseInt(options.minSharedTokens),
     maxCandidatesPerBlock: parseInt(options.maxCandidates),
-    fastMode: options.fastMode !== false,
-    // default true; --no-fast-mode sets to false
-    maxComparisons: parseInt(options.maxComparisons),
-    streamResults: options.streamResults === true,
-    // default false; --stream-results sets to true
+    streamResults: options.streamResults !== false,
+    // default true; --no-stream-results sets to false
     include: options.include?.split(","),
     exclude: options.exclude?.split(",")
   });
+  const elapsedTime = ((Date.now() - startTime) / 1e3).toFixed(2);
   const summary = generateSummary(results);
   const totalIssues = results.reduce((sum, r) => sum + r.issues.length, 0);
   if (options.output === "json") {
@@ -76,6 +74,9 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
       `\u{1F4B0} Token cost (wasted): ${chalk.bold(summary.totalTokenCost.toLocaleString())}`
     )
   );
+  console.log(
+    chalk.gray(`\u23F1  Analysis time: ${chalk.bold(elapsedTime + "s")}`)
+  );
   const sortedTypes = Object.entries(summary.patternsByType).filter(([, count]) => count > 0).sort(([, a], [, b]) => b - a);
   if (sortedTypes.length > 0) {
     console.log(chalk.cyan("\n" + divider));
@@ -97,12 +98,12 @@ program.name("aiready-patterns").description("Detect duplicate patterns in your
           `${Math.round(dup.similarity * 100)}%`
         )} ${getPatternIcon(dup.patternType)} ${chalk.white(dup.patternType)}`
       );
-      console.log(
-        `   ${chalk.dim(dup.file1)}:${chalk.cyan(dup.line1)}-${chalk.cyan(dup.endLine1)}`
-      );
-      console.log(
-        `   ${chalk.dim("\u2194")} ${chalk.dim(dup.file2)}:${chalk.cyan(dup.line2)}-${chalk.cyan(dup.endLine2)}`
-      );
+      dup.files.forEach((file, fileIdx) => {
+        const prefix = fileIdx === 0 ? "   " : "   \u2194 ";
+        console.log(
+          `${chalk.dim(prefix)}${chalk.dim(file.path)}:${chalk.cyan(file.startLine)}-${chalk.cyan(file.endLine)}`
+        );
+      });
       console.log(
         `   ${chalk.red(`${dup.tokenCost.toLocaleString()} tokens wasted`)}
 `
@@ -199,8 +200,7 @@ function generateHTMLReport(summary, results) {
         <tr>
           <th>Similarity</th>
           <th>Type</th>
-          <th>File 1</th>
-          <th>File 2</th>
+          <th>Files</th>
           <th>Token Cost</th>
         </tr>
       </thead>
@@ -210,8 +210,7 @@ function generateHTMLReport(summary, results) {
           <tr>
             <td class="${dup.similarity > 0.95 ? "critical" : dup.similarity > 0.9 ? "major" : "minor"}">${Math.round(dup.similarity * 100)}%</td>
             <td>${dup.patternType}</td>
-            <td><code>${dup.file1}</code></td>
-            <td><code>${dup.file2}</code></td>
+            <td>${dup.files.map((f) => `<code>${f.path}:${f.startLine}-${f.endLine}</code>`).join("<br>\u2194<br>")}</td>
             <td>${dup.tokenCost.toLocaleString()}</td>
           </tr>
         `

package/dist/index.d.mts

@@ -26,7 +26,6 @@ interface DetectionOptions {
     approx?: boolean;
     minSharedTokens?: number;
     maxCandidatesPerBlock?: number;
-    fastMode?: boolean;
     maxComparisons?: number;
     streamResults?: boolean;
 }
@@ -38,13 +37,10 @@ declare function detectDuplicatePatterns(files: FileContent[], options: Detectio
 interface PatternDetectOptions extends ScanOptions {
     minSimilarity?: number;
     minLines?: number;
-    maxBlocks?: number;
     batchSize?: number;
     approx?: boolean;
     minSharedTokens?: number;
     maxCandidatesPerBlock?: number;
-    fastMode?: boolean;
-    maxComparisons?: number;
     streamResults?: boolean;
 }
 interface PatternSummary {
@@ -52,12 +48,11 @@ interface PatternSummary {
     totalTokenCost: number;
     patternsByType: Record<PatternType, number>;
     topDuplicates: Array<{
-        file1: string;
-        file2: string;
-        line1: number;
-        line2: number;
-        endLine1: number;
-        endLine2: number;
+        files: Array<{
+            path: string;
+            startLine: number;
+            endLine: number;
+        }>;
         similarity: number;
         patternType: PatternType;
         tokenCost: number;