c0py: initial scaffolding for website registry tool

packages/c0py-core/src/registry/analyzer.ts

@@ -0,0 +1,39 @@
+import type { Page } from "@siax/c0py-types";
+
+export interface AnalysisResult {
+  totalPages: number;
+  uniqueDomains: number;
+  avgStatusCode: number;
+  statusCodes: Record<number, number>;
+  contentTypes: Record<string, number>;
+  hasBrokenLinks: boolean;
+  brokenLinks: number;
+}
+
+export function analyzePages(pages: Page[]): AnalysisResult {
+  const statusCodes: Record<number, number> = {};
+  const contentTypes: Record<string, number> = {};
+  let brokenLinks = 0;
+
+  for (const page of pages) {
+    statusCodes[page.statusCode] = (statusCodes[page.statusCode] ?? 0) + 1;
+    const ct = page.contentType?.split(";")[0].trim() ?? "unknown";
+    contentTypes[ct] = (contentTypes[ct] ?? 0) + 1;
+    if (page.statusCode >= 400) brokenLinks++;
+  }
+
+  const avgStatusCode =
+    pages.length > 0
+      ? pages.reduce((sum, p) => sum + p.statusCode, 0) / pages.length
+      : 0;
+
+  return {
+    totalPages: pages.length,
+    uniqueDomains: new Set(pages.map((p) => new URL(p.url).host)).size,
+    avgStatusCode: Math.round(avgStatusCode * 100) / 100,
+    statusCodes,
+    contentTypes,
+    hasBrokenLinks: brokenLinks > 0,
+    brokenLinks,
+  };
+}

packages/c0py-core/src/registry/registry.ts

@@ -0,0 +1,31 @@
+import type { Page, Registry, ScanRun } from "@siax/c0py-types";
+import type { CrawledPage } from "./types";
+
+export function assembleRegistry(
+  url: string,
+  name: string,
+  crawled: CrawledPage[]
+): { registry: Registry; pages: Page[] } {
+  const registry: Registry = {
+    id: crypto.randomUUID(),
+    url,
+    name,
+    createdAt: new Date(),
+    updatedAt: new Date(),
+  };
+
+  const pages: Page[] = crawled.map((c) => ({
+    id: crypto.randomUUID(),
+    registryId: registry.id,
+    url: c.url,
+    path: c.path,
+    title: c.title,
+    description: c.description,
+    statusCode: c.statusCode,
+    contentType: c.contentType,
+    discoveredAt: new Date(),
+    analysis: null,
+  }));
+
+  return { registry, pages };
+}

packages/c0py-core/src/registry/types.ts

@@ -0,0 +1,15 @@
+export interface CrawlOptions {
+  url: string;
+  maxPages: number;
+  timeoutMs: number;
+}
+
+export interface CrawledPage {
+  url: string;
+  path: string;
+  title: string | null;
+  description: string | null;
+  statusCode: number;
+  contentType: string | null;
+  links: string[];
+}