import { extractUrls, htmlToText, decodeEntities, fetchUrlDirect } from '../src/features/web/webFetch';
describe('webFetch.extractUrls', () => {
it('extracts http(s) URLs and strips trailing punctuation', () => {
const urls = extractUrls('https://koritips.com 가서 내용 분석해줘.');
expect(urls).toEqual(['https://koritips.com']);
});
it('handles multiple URLs with dedupe and max cap', () => {
const text = 'A: https://a.com/x, B: https://b.com/y 그리고 다시 https://a.com/x 또 https://c.com';
const urls = extractUrls(text, 2);
expect(urls).toEqual(['https://a.com/x', 'https://b.com/y']);
});
it('ignores slash commands and empty input', () => {
expect(extractUrls('/wikify https://a.com')).toEqual([]);
expect(extractUrls('')).toEqual([]);
expect(extractUrls('URL 없는 문장')).toEqual([]);
});
it('strips Korean closing punctuation contamination', () => {
expect(extractUrls('링크(https://a.com/page)를 봐줘')).toEqual(['https://a.com/page']);
expect(extractUrls('「https://b.com」 분석')).toEqual(['https://b.com']);
});
it('recognizes bare domains without scheme and prepends https://', () => {
expect(extractUrls('koritips.com 가서 내용 분석해줘')).toEqual(['https://koritips.com']);
expect(extractUrls('www.example.net/path/page 확인')).toEqual(['https://www.example.net/path/page']);
expect(extractUrls('naver.co.kr 어때?')).toEqual(['https://naver.co.kr']);
});
it('does not mistake filenames or emails for bare domains', () => {
expect(extractUrls('utils.ts 와 package.json 수정해줘')).toEqual([]);
expect(extractUrls('메일은 user@gmail.com 입니다')).toEqual([]);
});
it('does not double-count a scheme URL as a bare domain', () => {
expect(extractUrls('https://koritips.com 그리고 koritips.com')).toEqual(['https://koritips.com']);
});
});
describe('webFetch.htmlToText', () => {
it('strips scripts, styles, and tags while preserving block structure', () => {
const html = `
제목입니다
첫 문단.
둘째 문단.
`;
const text = htmlToText(html);
expect(text).not.toContain('alert');
expect(text).not.toContain('color:red');
expect(text).toContain('제목입니다');
expect(text).toMatch(/첫 문단\.\n/);
});
it('decodes common entities', () => {
expect(decodeEntities('A & B <tag> "q" 's' ')).toBe(`A & B "q" 's' `);
expect(decodeEntities('김')).toBe('김');
});
it('collapses excessive whitespace', () => {
const text = htmlToText('a
\n\n\n\nb
');
expect(text).not.toMatch(/\n{3,}/);
});
});
describe('webFetch.fetchUrlDirect (no network)', () => {
it('rejects non-http schemes without throwing', async () => {
const r = await fetchUrlDirect('ftp://example.com');
expect(r.ok).toBe(false);
expect(r.error).toContain('http');
});
it('returns honest failure for unreachable host (no throw)', async () => {
const r = await fetchUrlDirect('http://127.0.0.1:1', { timeoutMs: 1500 });
expect(r.ok).toBe(false);
expect(typeof r.error).toBe('string');
}, 10_000);
});