@aiready/pattern-detect 0.17.8 → 0.17.12

package/dist/chunk-JKVKOXYR.mjs

@@ -1,407 +0,0 @@
-// src/index.ts
-import { scanFiles, readFileContent } from "@aiready/core";
-
-// src/detector.ts
-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")) {
-    return "api-handler";
-  }
-  if (lower.includes("validate") || lower.includes("schema") || lower.includes("zod") || lower.includes("yup") || lower.includes("if") && lower.includes("throw")) {
-    return "validator";
-  }
-  if (lower.includes("return (") || lower.includes("jsx") || lower.includes("component") || lower.includes("props")) {
-    return "component";
-  }
-  if (lower.includes("class ") || lower.includes("this.")) {
-    return "class-method";
-  }
-  if (lower.includes("return ") && !lower.includes("this") && !lower.includes("new ")) {
-    return "utility";
-  }
-  if (lower.includes("function") || lower.includes("=>")) {
-    return "function";
-  }
-  return "unknown";
-}
-function extractCodeBlocks(content, minLines) {
-  const lines = content.split("\n");
-  const blocks = [];
-  let currentBlock = [];
-  let blockStart = 0;
-  let braceDepth = 0;
-  let inFunction = false;
-  for (let i = 0; i < lines.length; i++) {
-    const line = lines[i];
-    const trimmed = line.trim();
-    if (!inFunction && (trimmed.includes("function ") || trimmed.includes("=>") || trimmed.includes("async ") || /^(export\s+)?(async\s+)?function\s+/.test(trimmed) || /^(export\s+)?const\s+\w+\s*=\s*(async\s*)?\(/.test(trimmed))) {
-      inFunction = true;
-      blockStart = i;
-    }
-    for (const char of line) {
-      if (char === "{") braceDepth++;
-      if (char === "}") braceDepth--;
-    }
-    if (inFunction) {
-      currentBlock.push(line);
-    }
-    if (inFunction && braceDepth === 0 && currentBlock.length >= minLines) {
-      const blockContent = currentBlock.join("\n");
-      const linesOfCode = currentBlock.filter(
-        (l) => l.trim() && !l.trim().startsWith("//")
-      ).length;
-      blocks.push({
-        content: blockContent,
-        startLine: blockStart + 1,
-        endLine: i + 1,
-        patternType: categorizePattern(blockContent),
-        linesOfCode
-      });
-      currentBlock = [];
-      inFunction = false;
-    } else if (inFunction && braceDepth === 0) {
-      currentBlock = [];
-      inFunction = false;
-    }
-  }
-  return blocks;
-}
-function normalizeCode(code) {
-  return code.replace(/\/\/.*$/gm, "").replace(/\/\*[\s\S]*?\*\//g, "").replace(/"[^"]*"/g, '"STR"').replace(/'[^']*'/g, "'STR'").replace(/`[^`]*`/g, "`STR`").replace(/\b\d+\b/g, "NUM").replace(/\s+/g, " ").trim();
-}
-function jaccardSimilarity(tokens1, tokens2) {
-  const set1 = new Set(tokens1);
-  const set2 = new Set(tokens2);
-  let intersection = 0;
-  for (const token of set1) {
-    if (set2.has(token)) intersection++;
-  }
-  const union = set1.size + set2.size - intersection;
-  return union === 0 ? 0 : intersection / union;
-}
-async function detectDuplicatePatterns(files, options) {
-  const {
-    minSimilarity,
-    minLines,
-    batchSize = 100,
-    approx = true,
-    minSharedTokens = 8,
-    maxCandidatesPerBlock = 100,
-    streamResults = false
-  } = options;
-  const duplicates = [];
-  const maxComparisons = approx ? Infinity : 5e5;
-  const allBlocks = files.flatMap(
-    (file) => extractCodeBlocks(file.content, minLines).map((block) => ({
-      content: block.content,
-      startLine: block.startLine,
-      endLine: block.endLine,
-      file: file.file,
-      normalized: normalizeCode(block.content),
-      patternType: block.patternType,
-      tokenCost: estimateTokens(block.content),
-      linesOfCode: block.linesOfCode
-    }))
-  );
-  console.log(`Extracted ${allBlocks.length} code blocks for analysis`);
-  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",
-    "const",
-    "let",
-    "var",
-    "function",
-    "class",
-    "new",
-    "if",
-    "else",
-    "for",
-    "while",
-    "async",
-    "await",
-    "try",
-    "catch",
-    "switch",
-    "case",
-    "default",
-    "import",
-    "export",
-    "from",
-    "true",
-    "false",
-    "null",
-    "undefined",
-    "this"
-  ]);
-  const tokenize = (norm) => norm.split(/[\s(){}\[\];,\.]+/).filter((t) => t && t.length >= 3 && !stopwords.has(t.toLowerCase()));
-  const blockTokens = allBlocks.map((b) => tokenize(b.normalized));
-  const invertedIndex = /* @__PURE__ */ new Map();
-  if (approx) {
-    for (let i = 0; i < blockTokens.length; i++) {
-      for (const tok of blockTokens[i]) {
-        let arr = invertedIndex.get(tok);
-        if (!arr) {
-          arr = [];
-          invertedIndex.set(tok, arr);
-        }
-        arr.push(i);
-      }
-    }
-  }
-  const totalComparisons = approx ? void 0 : allBlocks.length * (allBlocks.length - 1) / 2;
-  if (totalComparisons !== void 0) {
-    console.log(`Processing ${totalComparisons.toLocaleString()} comparisons in batches...`);
-  } else {
-    console.log(`Using approximate candidate selection to reduce comparisons...`);
-  }
-  let comparisonsProcessed = 0;
-  let comparisonsBudgetExhausted = false;
-  const startTime = Date.now();
-  for (let i = 0; i < allBlocks.length; i++) {
-    if (maxComparisons && comparisonsProcessed >= maxComparisons) {
-      comparisonsBudgetExhausted = true;
-      break;
-    }
-    if (i % batchSize === 0 && i > 0) {
-      const elapsed = ((Date.now() - startTime) / 1e3).toFixed(1);
-      const duplicatesFound = duplicates.length;
-      if (totalComparisons !== void 0) {
-        const progress = (comparisonsProcessed / totalComparisons * 100).toFixed(1);
-        const remaining = totalComparisons - comparisonsProcessed;
-        const rate = comparisonsProcessed / parseFloat(elapsed);
-        const eta = remaining > 0 ? (remaining / rate).toFixed(0) : 0;
-        console.log(`   ${progress}% (${comparisonsProcessed.toLocaleString()}/${totalComparisons.toLocaleString()} comparisons, ${elapsed}s elapsed, ~${eta}s remaining, ${duplicatesFound} duplicates)`);
-      } else {
-        console.log(`   Processed ${i.toLocaleString()}/${allBlocks.length} blocks (${elapsed}s elapsed, ${duplicatesFound} duplicates)`);
-      }
-      await new Promise((resolve) => setImmediate(resolve));
-    }
-    const block1 = allBlocks[i];
-    let candidates = null;
-    if (approx) {
-      const counts = /* @__PURE__ */ new Map();
-      for (const tok of blockTokens[i]) {
-        const ids = invertedIndex.get(tok);
-        if (!ids) continue;
-        for (const j of ids) {
-          if (j <= i) continue;
-          if (allBlocks[j].file === block1.file) continue;
-          counts.set(j, (counts.get(j) || 0) + 1);
-        }
-      }
-      candidates = Array.from(counts.entries()).filter(([, shared]) => shared >= minSharedTokens).sort((a, b) => b[1] - a[1]).slice(0, maxCandidatesPerBlock).map(([j, shared]) => ({ j, shared }));
-    }
-    if (approx && candidates) {
-      for (const { j } of candidates) {
-        if (!approx && maxComparisons !== Infinity && comparisonsProcessed >= maxComparisons) {
-          console.log(`\u26A0\uFE0F  Comparison safety limit reached (${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 = 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,
-            tokenCost: block1.tokenCost + block2.tokenCost,
-            linesOfCode: block1.linesOfCode
-          };
-          duplicates.push(duplicate);
-          if (streamResults) {
-            console.log(`
-   \u2705 Found: ${duplicate.patternType} ${Math.round(similarity * 100)}% similar`);
-            console.log(`      ${duplicate.file1}:${duplicate.line1}-${duplicate.endLine1} \u21D4 ${duplicate.file2}:${duplicate.line2}-${duplicate.endLine2}`);
-            console.log(`      Token cost: ${duplicate.tokenCost.toLocaleString()}`);
-          }
-        }
-      }
-    } else {
-      for (let j = i + 1; j < allBlocks.length; j++) {
-        if (maxComparisons && comparisonsProcessed >= maxComparisons) break;
-        comparisonsProcessed++;
-        const block2 = allBlocks[j];
-        if (block1.file === block2.file) continue;
-        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,
-            tokenCost: block1.tokenCost + block2.tokenCost,
-            linesOfCode: block1.linesOfCode
-          };
-          duplicates.push(duplicate);
-          if (streamResults) {
-            console.log(`
-   \u2705 Found: ${duplicate.patternType} ${Math.round(similarity * 100)}% similar`);
-            console.log(`      ${duplicate.file1}:${duplicate.line1}-${duplicate.endLine1} \u21D4 ${duplicate.file2}:${duplicate.line2}-${duplicate.endLine2}`);
-            console.log(`      Token cost: ${duplicate.tokenCost.toLocaleString()}`);
-          }
-        }
-      }
-    }
-  }
-  if (comparisonsBudgetExhausted) {
-    console.log(`\u26A0\uFE0F  Comparison budget exhausted (${maxComparisons.toLocaleString()} comparisons). Use --max-comparisons to increase.`);
-  }
-  return duplicates.sort(
-    (a, b) => b.similarity - a.similarity || b.tokenCost - a.tokenCost
-  );
-}
-
-// src/index.ts
-function getRefactoringSuggestion(patternType, similarity) {
-  const baseMessages = {
-    "api-handler": "Extract common middleware or create a base handler class",
-    validator: "Consolidate validation logic into shared schema validators (Zod/Yup)",
-    utility: "Move to a shared utilities file and reuse across modules",
-    "class-method": "Consider inheritance or composition to share behavior",
-    component: "Extract shared logic into a custom hook or HOC",
-    function: "Extract into a shared helper function",
-    unknown: "Extract common logic into a reusable module"
-  };
-  const urgency = similarity > 0.95 ? " (CRITICAL: Nearly identical code)" : similarity > 0.9 ? " (HIGH: Very similar, refactor soon)" : "";
-  return baseMessages[patternType] + urgency;
-}
-async function analyzePatterns(options) {
-  const {
-    minSimilarity = 0.4,
-    // Jaccard similarity default (40% threshold)
-    minLines = 5,
-    batchSize = 100,
-    approx = true,
-    minSharedTokens = 8,
-    maxCandidatesPerBlock = 100,
-    streamResults = false,
-    ...scanOptions
-  } = options;
-  const files = await scanFiles(scanOptions);
-  const results = [];
-  const fileContents = await Promise.all(
-    files.map(async (file) => ({
-      file,
-      content: await readFileContent(file)
-    }))
-  );
-  const duplicates = await detectDuplicatePatterns(fileContents, {
-    minSimilarity,
-    minLines,
-    batchSize,
-    approx,
-    minSharedTokens,
-    maxCandidatesPerBlock,
-    streamResults
-  });
-  for (const file of files) {
-    const fileDuplicates = duplicates.filter(
-      (dup) => dup.file1 === file || dup.file2 === file
-    );
-    const issues = fileDuplicates.map((dup) => {
-      const otherFile = dup.file1 === file ? dup.file2 : dup.file1;
-      const severity = dup.similarity > 0.95 ? "critical" : dup.similarity > 0.9 ? "major" : "minor";
-      return {
-        type: "duplicate-pattern",
-        severity,
-        message: `${dup.patternType} pattern ${Math.round(dup.similarity * 100)}% similar to ${otherFile} (${dup.tokenCost} tokens wasted)`,
-        location: {
-          file,
-          line: dup.file1 === file ? dup.line1 : dup.line2
-        },
-        suggestion: getRefactoringSuggestion(dup.patternType, dup.similarity)
-      };
-    });
-    const totalTokenCost = fileDuplicates.reduce(
-      (sum, dup) => sum + dup.tokenCost,
-      0
-    );
-    results.push({
-      fileName: file,
-      issues,
-      metrics: {
-        tokenCost: totalTokenCost,
-        consistencyScore: Math.max(0, 1 - fileDuplicates.length * 0.1)
-      }
-    });
-  }
-  return results;
-}
-function generateSummary(results) {
-  const allIssues = results.flatMap((r) => r.issues);
-  const totalTokenCost = results.reduce(
-    (sum, r) => sum + (r.metrics.tokenCost || 0),
-    0
-  );
-  const patternsByType = {
-    "api-handler": 0,
-    validator: 0,
-    utility: 0,
-    "class-method": 0,
-    component: 0,
-    function: 0,
-    unknown: 0
-  };
-  allIssues.forEach((issue) => {
-    const match = issue.message.match(/^(\S+(?:-\S+)*) pattern/);
-    if (match) {
-      const type = match[1];
-      patternsByType[type] = (patternsByType[type] || 0) + 1;
-    }
-  });
-  const topDuplicates = allIssues.slice(0, 10).map((issue) => {
-    const similarityMatch = issue.message.match(/(\d+)% similar/);
-    const tokenMatch = issue.message.match(/\((\d+) tokens/);
-    const typeMatch = issue.message.match(/^(\S+(?:-\S+)*) pattern/);
-    const fileMatch = issue.message.match(/similar to (.+?) \(/);
-    return {
-      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
-    };
-  });
-  return {
-    totalPatterns: allIssues.length,
-    totalTokenCost,
-    patternsByType,
-    topDuplicates
-  };
-}
-
-export {
-  detectDuplicatePatterns,
-  analyzePatterns,
-  generateSummary
-};