Merge pull request #426 from ShunsukeHayashi/fix/no-git-folder-384

gitnexus/src/cli/analyze.ts

@@ -15,7 +15,7 @@ import { initLbug, loadGraphToLbug, getLbugStats, executeQuery, executeWithReuse
 // versions whose ABI is not yet supported by the native binary (#89).
 // disposeEmbedder intentionally not called — ONNX Runtime segfaults on cleanup (see #38)
 import { getStoragePaths, saveMeta, loadMeta, addToGitignore, registerRepo, getGlobalRegistryPath, cleanupOldKuzuFiles } from '../storage/repo-manager.js';
-import { getCurrentCommit, isGitRepo, getGitRoot } from '../storage/git.js';
+import { getCurrentCommit, getGitRoot, hasGitDir } from '../storage/git.js';
 import { generateAIContextFiles } from './ai-context.js';
 import { generateSkillFiles, type GeneratedSkillInfo } from './skill-gen.js';
 import fs from 'fs/promises';
@@ -48,6 +48,8 @@ export interface AnalyzeOptions {
   embeddings?: boolean;
   skills?: boolean;
   verbose?: boolean;
+  /** Index the folder even when no .git directory is present. */
+  skipGit?: boolean;
 }
 
 /** Threshold: auto-skip embeddings for repos with more nodes than this */
@@ -87,18 +89,27 @@ export const analyzeCommand = async (
   } else {
     const gitRoot = getGitRoot(process.cwd());
     if (!gitRoot) {
-      console.log('  Not inside a git repository\n');
-      process.exitCode = 1;
-      return;
+      if (!options?.skipGit) {
+        console.log('  Not inside a git repository.\n  Tip: pass --skip-git to index any folder without a .git directory.\n');
+        process.exitCode = 1;
+        return;
+      }
+      // --skip-git: fall back to cwd as the root
+      repoPath = path.resolve(process.cwd());
+    } else {
+      repoPath = gitRoot;
     }
-    repoPath = gitRoot;
   }
 
-  if (!isGitRepo(repoPath)) {
-    console.log('  Not a git repository\n');
+  const repoHasGit = hasGitDir(repoPath);
+  if (!repoHasGit && !options?.skipGit) {
+    console.log('  Not a git repository.\n  Tip: pass --skip-git to index any folder without a .git directory.\n');
     process.exitCode = 1;
     return;
   }
+  if (!repoHasGit) {
+    console.log('  Warning: no .git directory found \u2014 commit-tracking and incremental updates disabled.\n');
+  }
 
   const { storagePath, lbugPath } = getStoragePaths(repoPath);
 
@@ -109,12 +120,15 @@ export const analyzeCommand = async (
     console.log('  Migrating from KuzuDB to LadybugDB — rebuilding index...\n');
   }
 
-  const currentCommit = getCurrentCommit(repoPath);
+  const currentCommit = repoHasGit ? getCurrentCommit(repoPath) : '';
   const existingMeta = await loadMeta(storagePath);
 
   if (existingMeta && !options?.force && !options?.skills && existingMeta.lastCommit === currentCommit) {
-    console.log('  Already up to date\n');
-    return;
+    // Non-git folders have currentCommit = '' — always rebuild since we can't detect changes
+    if (currentCommit !== '') {
+      console.log('  Already up to date\n');
+      return;
+    }
   }
 
   if (process.env.GITNEXUS_NO_GITIGNORE) {
@@ -317,7 +331,12 @@ export const analyzeCommand = async (
   };
   await saveMeta(storagePath, meta);
   await registerRepo(repoPath, meta);
-  await addToGitignore(repoPath);
+  // Only attempt to update .gitignore when a .git directory is present.
+  // Use hasGitDir (filesystem check) rather than git CLI subprocess
+  // so we skip correctly for --skip-git folders even if git CLI is available.
+  if (hasGitDir(repoPath)) {
+    await addToGitignore(repoPath);
+  }
 
   const projectName = path.basename(repoPath);
   let aggregatedClusterCount = 0;

gitnexus/src/cli/index.ts

@@ -28,6 +28,7 @@ program
   .option('-f, --force', 'Force full re-index even if up to date')
   .option('--embeddings', 'Enable embedding generation for semantic search (off by default)')
   .option('--skills', 'Generate repo-specific skill files from detected communities')
+  .option('--skip-git', 'Index a folder without requiring a .git directory')
    .option('-v, --verbose', 'Enable verbose ingestion warnings (default: false)')
    .addHelpText('after', '\nEnvironment variables:\n  GITNEXUS_NO_GITIGNORE=1  Skip .gitignore parsing (still reads .gitnexusignore)')
    .action(createLazyAction(() => import('./analyze.js'), 'analyzeCommand'));

gitnexus/src/storage/git.ts

@@ -1,4 +1,5 @@
 import { execSync } from 'child_process';
+import { statSync } from 'fs';
 import path from 'path';
 
 // Git utilities for repository detection, commit tracking, and diff analysis
@@ -34,3 +35,22 @@ export const getGitRoot = (fromPath: string): string | null => {
     return null;
   }
 };
+/**
+ * Check whether a directory contains a .git entry (file or folder).
+ *
+ * This is intentionally a simple filesystem check rather than running
+ * `git rev-parse`, so it works even when git is not installed or when
+ * the directory is a git-worktree root (which has a .git file, not a
+ * directory).  Use `isGitRepo` for a definitive git answer.
+ *
+ * @param dirPath - Absolute path to the directory to inspect.
+ * @returns `true` when `.git` is present, `false` otherwise.
+ */
+export const hasGitDir = (dirPath: string): boolean => {
+  try {
+    statSync(path.join(dirPath, '.git'));
+    return true;
+  } catch {
+    return false;
+  }
+};

gitnexus/test/unit/git-utils.test.ts

@@ -0,0 +1,113 @@
+/**
+ * Unit Tests: git utility helpers (storage/git.ts)
+ *
+ * Tests isGitRepo, getCurrentCommit, getGitRoot, and the newly added
+ * hasGitDir helper introduced for issue #384 (indexing non-git folders).
+ */
+import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+import path from 'path';
+import os from 'os';
+import fs from 'fs';
+
+// ─── hasGitDir ────────────────────────────────────────────────────────────
+//
+// hasGitDir is a synchronous fs.statSync check — we test it by actually
+// creating temporary directories rather than mocking the fs module,
+// because the implementation is a simple one-liner and real disk I/O is
+// fast and deterministic for this purpose.
+
+describe('hasGitDir', () => {
+  // Import after test setup to ensure module resolution is correct
+  const getHasGitDir = async () => {
+    const mod = await import('../../src/storage/git.js');
+    return mod.hasGitDir;
+  };
+
+  it('returns true when .git directory exists', async () => {
+    const hasGitDir = await getHasGitDir();
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      fs.mkdirSync(path.join(tmpDir, '.git'));
+      expect(hasGitDir(tmpDir)).toBe(true);
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+
+  it('returns true when .git is a file (git worktree)', async () => {
+    const hasGitDir = await getHasGitDir();
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      fs.writeFileSync(path.join(tmpDir, '.git'), 'gitdir: /some/other/.git\n');
+      expect(hasGitDir(tmpDir)).toBe(true);
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+
+  it('returns false when .git entry is absent', async () => {
+    const hasGitDir = await getHasGitDir();
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      // No .git here — plain directory
+      expect(hasGitDir(tmpDir)).toBe(false);
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+
+  it('returns false for a non-existent path', async () => {
+    const hasGitDir = await getHasGitDir();
+    expect(hasGitDir('/tmp/__gitnexus_nonexistent_path__')).toBe(false);
+  });
+});
+
+// ─── isGitRepo ────────────────────────────────────────────────────────────
+//
+// isGitRepo shells out to `git rev-parse` — we verify it returns false
+// for a plain temp directory without running git init.
+
+describe('isGitRepo', () => {
+  it('returns false for a plain (non-git) directory', async () => {
+    const { isGitRepo } = await import('../../src/storage/git.js');
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      expect(isGitRepo(tmpDir)).toBe(false);
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+
+  it('returns false for a non-existent path', async () => {
+    const { isGitRepo } = await import('../../src/storage/git.js');
+    expect(isGitRepo('/tmp/__gitnexus_nonexistent__')).toBe(false);
+  });
+});
+
+// ─── getCurrentCommit ─────────────────────────────────────────────────────
+
+describe('getCurrentCommit', () => {
+  it('returns empty string for a non-git directory', async () => {
+    const { getCurrentCommit } = await import('../../src/storage/git.js');
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      expect(getCurrentCommit(tmpDir)).toBe('');
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+});
+
+// ─── getGitRoot ───────────────────────────────────────────────────────────
+
+describe('getGitRoot', () => {
+  it('returns null for a plain temp directory', async () => {
+    const { getGitRoot } = await import('../../src/storage/git.js');
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gitnexus-test-'));
+    try {
+      expect(getGitRoot(tmpDir)).toBeNull();
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+});

gitnexus/test/unit/skip-git-cli.test.ts

@@ -0,0 +1,38 @@
+import { describe, it, expect } from 'vitest';
+import { execSync } from 'child_process';
+import path from 'path';
+import os from 'os';
+import fs from 'fs';
+
+describe('--skip-git CLI flag', () => {
+  it('Commander maps --skip-git to options.skipGit (not --no-git inversion)', () => {
+    // Verify the CLI defines --skip-git, not --no-git
+    const helpOutput = execSync('node dist/cli/index.js analyze --help', {
+      cwd: path.resolve(__dirname, '../..'),
+      encoding: 'utf8',
+      timeout: 10000,
+    });
+
+    expect(helpOutput).toContain('--skip-git');
+    expect(helpOutput).not.toContain('--no-git');
+  });
+
+  it('rejects non-git folder without --skip-git', () => {
+    const tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gn-no-git-'));
+    fs.writeFileSync(path.join(tmpDir, 'test.ts'), 'export const x = 1;');
+
+    try {
+      execSync(`node dist/cli/index.js analyze "${tmpDir}"`, {
+        cwd: path.resolve(__dirname, '../..'),
+        encoding: 'utf8',
+        timeout: 10000,
+      });
+      // Should not reach here
+      expect.unreachable('Should have exited with non-zero');
+    } catch (err: any) {
+      expect(err.stdout || err.stderr || '').toContain('--skip-git');
+    } finally {
+      fs.rmSync(tmpDir, { recursive: true, force: true });
+    }
+  });
+});