feat: initial CodeBoard monorepo scaffold

Turborepo monorepo with npm workspaces: - apps/web: Next.js 14 frontend with Tailwind v4, SSE progress, doc viewer - apps/worker: BullMQ job processor (clone → parse → LLM generate) - packages/shared: TypeScript types - packages/parser: Babel-based AST parser (JS/TS) + regex (Python) - packages/llm: OpenAI/Anthropic provider abstraction + prompt pipeline - packages/diagrams: Mermaid architecture & dependency graph generators - packages/database: Prisma schema (PostgreSQL) - Docker multi-stage build (web + worker targets) All packages compile successfully with tsc and next build.
2026-02-09 15:22:50 +00:00
parent efdc282da5
commit 79dad6124f
72 changed files with 10132 additions and 136 deletions
--- a/packages/parser/src/file-walker.ts
+++ b/packages/parser/src/file-walker.ts
@@ -0,0 +1,121 @@
+import { readdir, stat, readFile } from "node:fs/promises";
+import { join, relative, extname, basename } from "node:path";
+
+const IGNORED_DIRS = new Set([
+  "node_modules",
+  ".git",
+  "dist",
+  "build",
+  "vendor",
+  "__pycache__",
+  ".next",
+  ".turbo",
+  "coverage",
+  ".venv",
+  "venv",
+  ".tox",
+  "target",
+  ".cache",
+  ".idea",
+  ".vscode",
+]);
+
+const LANGUAGE_MAP: Record<string, string> = {
+  ".ts": "typescript",
+  ".tsx": "typescript",
+  ".js": "javascript",
+  ".jsx": "javascript",
+  ".mjs": "javascript",
+  ".cjs": "javascript",
+  ".py": "python",
+  ".go": "go",
+  ".rs": "rust",
+  ".java": "java",
+  ".rb": "ruby",
+  ".php": "php",
+  ".cs": "csharp",
+  ".cpp": "cpp",
+  ".c": "c",
+  ".h": "c",
+  ".hpp": "cpp",
+  ".swift": "swift",
+  ".kt": "kotlin",
+};
+
+const ENTRY_POINT_NAMES = new Set([
+  "index",
+  "main",
+  "app",
+  "server",
+  "mod",
+  "lib",
+  "__init__",
+  "manage",
+]);
+
+export interface WalkedFile {
+  absolutePath: string;
+  relativePath: string;
+  language: string;
+  size: number;
+  isEntryPoint: boolean;
+}
+
+async function walkDir(
+  dir: string,
+  rootDir: string,
+  results: WalkedFile[]
+): Promise<void> {
+  const entries = await readdir(dir, { withFileTypes: true });
+
+  for (const entry of entries) {
+    if (IGNORED_DIRS.has(entry.name)) continue;
+    if (entry.name.startsWith(".")) continue;
+
+    const fullPath = join(dir, entry.name);
+
+    if (entry.isDirectory()) {
+      await walkDir(fullPath, rootDir, results);
+      continue;
+    }
+
+    const ext = extname(entry.name);
+    const language = LANGUAGE_MAP[ext];
+    if (!language) continue;
+
+    const fileStat = await stat(fullPath);
+    if (fileStat.size > 500_000) continue;
+
+    const nameWithoutExt = basename(entry.name, ext);
+    const isEntryPoint = ENTRY_POINT_NAMES.has(nameWithoutExt);
+
+    results.push({
+      absolutePath: fullPath,
+      relativePath: relative(rootDir, fullPath),
+      language,
+      size: fileStat.size,
+      isEntryPoint,
+    });
+  }
+}
+
+export async function walkFiles(repoPath: string): Promise<WalkedFile[]> {
+  const results: WalkedFile[] = [];
+  await walkDir(repoPath, repoPath, results);
+
+  results.sort((a, b) => {
+    if (a.isEntryPoint && !b.isEntryPoint) return -1;
+    if (!a.isEntryPoint && b.isEntryPoint) return 1;
+    return a.relativePath.localeCompare(b.relativePath);
+  });
+
+  return results;
+}
+
+export async function readFileContent(filePath: string): Promise<string> {
+  return readFile(filePath, "utf-8");
+}
+
+export function detectLanguage(filePath: string): string | null {
+  return LANGUAGE_MAP[extname(filePath)] ?? null;
+}