Skip to content

test: add error handling test for extractLinks #18

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
saurabhsharma2u merged 1 commit into from
Feb 25, 2026
Merged

test: add error handling test for extractLinks #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 53 additions & 0 deletions plugins/core/tests/extract.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,53 @@
import { extractLinks } from '../src/crawler/extract.js';
import { test, expect, describe, vi, afterEach } from 'vitest';
import * as cheerio from 'cheerio';

vi.mock('cheerio', async (importOriginal) => {
const mod = await importOriginal<any>();
return {
...mod,
load: vi.fn((...args: any[]) => mod.load(...args))
};
});

describe('extractLinks', () => {
afterEach(() => {
vi.restoreAllMocks();
});

test('should extract links correctly', () => {
const html = `
<html>
<body>
<a href="/foo">Foo</a>
<a href="bar">Bar</a>
<a href="https://other.com/baz">Baz</a>
<a href="#top">Top</a>
</body>
</html>
`;
const links = extractLinks(html, 'https://example.com/page/');
expect(links).toContain('https://example.com/foo');
expect(links).toContain('https://example.com/page/bar');
expect(links).toContain('https://other.com/baz');
expect(links).not.toContain('https://example.com/page/#top');
expect(links).toContain('https://example.com/page/');
});

test('should handle cheerio errors gracefully', () => {
const consoleSpy = vi.spyOn(console, 'error').mockImplementation(() => { });
const error = new Error('Cheerio error');

vi.mocked(cheerio.load).mockImplementationOnce(() => {
throw error;
});

const links = extractLinks('<html></html>', 'https://example.com');

expect(links).toEqual([]);
expect(consoleSpy).toHaveBeenCalledWith(
expect.stringContaining('Error extracting links from https://example.com'),
error
);
});
});
19 changes: 0 additions & 19 deletions plugins/core/tests/normalize.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
import { normalizeUrl } from '../src/crawler/normalize.js';
import { extractLinks } from '../src/crawler/extract.js';
import { test, expect } from 'vitest';

test('normalizeUrl', () => {
Expand All @@ -11,24 +10,6 @@ test('normalizeUrl', () => {
expect(normalizeUrl('https://example.com/', '')).toBe('https://example.com/');
});

test('extractLinks', () => {
const html = `
<html>
<body>
<a href="/foo">Foo</a>
<a href="bar">Bar</a>
<a href="https://other.com/baz">Baz</a>
<a href="#top">Top</a>
</body>
</html>
`;
const links = extractLinks(html, 'https://example.com/page/');
expect(links).toContain('https://example.com/foo');
expect(links).toContain('https://example.com/page/bar');
expect(links).toContain('https://other.com/baz');
expect(links).not.toContain('https://example.com/page/#top');
expect(links).toContain('https://example.com/page/'); // #top resolves to base url without fragment
});
test('normalizeUrl: absolute resolution', () => {
expect(normalizeUrl('/foo', 'https://example.com')).toBe('https://example.com/foo');
expect(normalizeUrl('bar', 'https://example.com/baz/')).toBe('https://example.com/baz/bar');
Expand Down
Loading