/**
 * WorthDoing.ai
 * Author: Simon-Pierre Boucher
 * Contact: contact@spboucher.ai
 * File: tests/canonical-url.test.ts
 * Description: URL canonicalization + content hashing tests (deduplication layer).
 */
import { describe, it, expect } from "vitest";
import { canonicalizeUrl, sha256 } from "@/lib/firecrawl/url";

describe("canonicalizeUrl", () => {
  it("strips www, fragments, and trailing slashes", () => {
    expect(canonicalizeUrl("https://www.Example.com/path/#section")).toBe("https://example.com/path");
  });

  it("removes tracking parameters but keeps meaningful ones", () => {
    expect(canonicalizeUrl("https://example.com/a?utm_source=x&page=2&fbclid=abc")).toBe(
      "https://example.com/a?page=2",
    );
  });

  it("sorts query parameters for stable comparison", () => {
    expect(canonicalizeUrl("https://example.com/a?b=2&a=1")).toBe(canonicalizeUrl("https://example.com/a?a=1&b=2"));
  });

  it("normalizes equivalent URLs to the same canonical form", () => {
    const variants = [
      "https://www.example.com/post/",
      "https://example.com/post",
      "https://example.com/post#comments",
      "https://example.com/post?utm_campaign=news",
    ];
    const canon = new Set(variants.map(canonicalizeUrl));
    expect(canon.size).toBe(1);
  });

  it("keeps the root path as /", () => {
    expect(canonicalizeUrl("https://example.com")).toBe("https://example.com/");
  });
});

describe("sha256", () => {
  it("is deterministic and collision-distinct for different content", () => {
    expect(sha256("hello")).toBe(sha256("hello"));
    expect(sha256("hello")).not.toBe(sha256("hello!"));
    expect(sha256("hello")).toHaveLength(64);
  });
});