c0py: initial scaffolding for website registry tool

packages/c0py-core/tests/analyzer.test.ts

@@ -0,0 +1,65 @@
+import { describe, it, expect } from "vitest";
+import { analyzePages } from "../src/registry/analyzer";
+import type { Page } from "@siax/c0py-types";
+
+const pages: Page[] = [
+  {
+    id: "1",
+    registryId: "r1",
+    url: "https://example.com/",
+    path: "/",
+    title: "Home",
+    description: null,
+    statusCode: 200,
+    contentType: "text/html",
+    discoveredAt: new Date(),
+    analysis: null,
+  },
+  {
+    id: "2",
+    registryId: "r1",
+    url: "https://example.com/about",
+    path: "/about",
+    title: "About",
+    description: null,
+    statusCode: 200,
+    contentType: "text/html",
+    discoveredAt: new Date(),
+    analysis: null,
+  },
+  {
+    id: "3",
+    registryId: "r1",
+    url: "https://example.com/missing",
+    path: "/missing",
+    title: null,
+    description: null,
+    statusCode: 404,
+    contentType: "text/html",
+    discoveredAt: new Date(),
+    analysis: null,
+  },
+];
+
+describe("analyzePages", () => {
+  it("counts pages correctly", () => {
+    const result = analyzePages(pages);
+    expect(result.totalPages).toBe(3);
+    expect(result.brokenLinks).toBe(1);
+    expect(result.hasBrokenLinks).toBe(true);
+    expect(result.uniqueDomains).toBe(1);
+  });
+
+  it("aggregates status codes", () => {
+    const result = analyzePages(pages);
+    expect(result.statusCodes[200]).toBe(2);
+    expect(result.statusCodes[404]).toBe(1);
+  });
+
+  it("handles empty input", () => {
+    const result = analyzePages([]);
+    expect(result.totalPages).toBe(0);
+    expect(result.avgStatusCode).toBe(0);
+    expect(result.hasBrokenLinks).toBe(false);
+  });
+});

packages/c0py-core/tests/crawler.test.ts

@@ -0,0 +1,16 @@
+import { describe, it, expect } from "vitest";
+import { Crawler } from "../src/crawler/crawler";
+
+describe("Crawler", () => {
+  it("instantiates with options", () => {
+    const c = new Crawler({ maxPages: 10, timeoutMs: 5000 });
+    expect(c).toBeDefined();
+  });
+
+  it("crawls a real page", async () => {
+    const c = new Crawler({ maxPages: 1, timeoutMs: 10000 });
+    const pages = await c.crawl("https://example.com");
+    expect(pages.length).toBeGreaterThanOrEqual(1);
+    expect(pages[0].statusCode).toBe(200);
+  }, 15000);
+});

packages/c0py-core/tests/registry.test.ts

@@ -0,0 +1,24 @@
+import { describe, it, expect } from "vitest";
+import { assembleRegistry } from "../src/registry/registry";
+
+describe("assembleRegistry", () => {
+  it("creates a registry with pages", () => {
+    const result = assembleRegistry("https://example.com", "Example", [
+      {
+        url: "https://example.com/",
+        path: "/",
+        title: "Home",
+        description: null,
+        statusCode: 200,
+        contentType: "text/html",
+        links: [],
+      },
+    ]);
+
+    expect(result.registry.url).toBe("https://example.com");
+    expect(result.registry.name).toBe("Example");
+    expect(result.pages).toHaveLength(1);
+    expect(result.pages[0].id).toBeDefined();
+    expect(result.pages[0].registryId).toBe(result.registry.id);
+  });
+});

packages/c0py-core/tests/setup.ts

@@ -0,0 +1 @@
+testTimeout: 10000,