@link-assistant/web-capture 1.12.0 → 2.0.1

package/tests/unit/github.test.js

@@ -1,156 +0,0 @@
-import nock from '../helpers/nock.js';
-import {
-  fetchGithubRepositorySnapshot,
-  formatGithubRepositoryMarkdown,
-  formatGithubRepositoryText,
-  getGithubRepositoryTextFilename,
-  isGithubRepositoryUrl,
-  parseGithubRepositoryUrl,
-} from '../../src/github.js';
-
-const SNAPSHOT = {
-  sourceUrl: 'https://github.com/octocat/Hello-World',
-  defaultBranch: 'master',
-  repository: {
-    full_name: 'octocat/Hello-World',
-    description: 'A friendly test repository',
-    html_url: 'https://github.com/octocat/Hello-World',
-    default_branch: 'master',
-    language: 'JavaScript',
-    stargazers_count: 42,
-    forks_count: 7,
-    open_issues_count: 3,
-    license: { spdx_id: 'MIT' },
-    topics: ['demo', 'capture'],
-  },
-  tree: [
-    {
-      name: 'src',
-      path: 'src',
-      type: 'dir',
-      html_url: 'https://github.com/octocat/Hello-World/tree/master/src',
-    },
-    {
-      name: 'README.md',
-      path: 'README.md',
-      type: 'file',
-      size: 37,
-      html_url: 'https://github.com/octocat/Hello-World/blob/master/README.md',
-    },
-  ],
-  readme: {
-    path: 'README.md',
-    content: '# Hello World\n\nThis is the README.',
-  },
-};
-
-afterEach(() => {
-  nock.cleanAll();
-});
-
-describe('GitHub repository URLs', () => {
-  it('detects plain GitHub repository pages', () => {
-    expect(
-      parseGithubRepositoryUrl('https://github.com/octocat/Hello-World')
-    ).toEqual({
-      owner: 'octocat',
-      repo: 'Hello-World',
-      fullName: 'octocat/Hello-World',
-      htmlUrl: 'https://github.com/octocat/Hello-World',
-    });
-    expect(
-      isGithubRepositoryUrl('https://github.com/octocat/Hello-World')
-    ).toBe(true);
-    expect(
-      isGithubRepositoryUrl('https://github.com/octocat/Hello-World/issues')
-    ).toBe(false);
-    expect(
-      isGithubRepositoryUrl('https://example.com/octocat/Hello-World')
-    ).toBe(false);
-  });
-
-  it('derives repository text filenames', () => {
-    expect(
-      getGithubRepositoryTextFilename('https://github.com/octocat/Hello-World')
-    ).toBe('octocat-Hello-World.txt');
-  });
-});
-
-describe('GitHub repository snapshot fetching', () => {
-  it('requests identity encoding from GitHub JSON and raw README fetches', async () => {
-    const owner = 'octocat';
-    const repo = 'Hello-World';
-    const readme = '# Hello World\n\nRaw README content.';
-
-    const githubApi = nock('https://api.github.com', {
-      reqheaders: {
-        'accept-encoding': 'identity',
-      },
-    })
-      .get(`/repos/${owner}/${repo}`)
-      .reply(200, {
-        full_name: `${owner}/${repo}`,
-        html_url: `https://github.com/${owner}/${repo}`,
-        default_branch: 'master',
-      })
-      .get(`/repos/${owner}/${repo}/readme`)
-      .query({ ref: 'master' })
-      .reply(200, {
-        name: 'README.md',
-        path: 'README.md',
-        download_url: `https://raw.githubusercontent.com/${owner}/${repo}/master/README.md`,
-      })
-      .get(`/repos/${owner}/${repo}/contents`)
-      .query({ ref: 'master' })
-      .reply(200, [
-        {
-          name: 'README.md',
-          path: 'README.md',
-          type: 'file',
-          size: readme.length,
-        },
-      ]);
-
-    const rawGithub = nock('https://raw.githubusercontent.com', {
-      reqheaders: {
-        'accept-encoding': 'identity',
-      },
-    })
-      .get(`/${owner}/${repo}/master/README.md`)
-      .reply(200, readme);
-
-    const snapshot = await fetchGithubRepositorySnapshot(
-      `https://github.com/${owner}/${repo}`
-    );
-
-    expect(snapshot.readme.content).toBe(readme);
-    expect(githubApi.isDone()).toBe(true);
-    expect(rawGithub.isDone()).toBe(true);
-  });
-});
-
-describe('GitHub repository snapshot formatting', () => {
-  it('formats a compact markdown snapshot with metadata, file tree, and README', () => {
-    const markdown = formatGithubRepositoryMarkdown(SNAPSHOT);
-
-    expect(markdown).toContain('# octocat/Hello-World');
-    expect(markdown).toContain('> A friendly test repository');
-    expect(markdown).toContain('- Default branch: `master`');
-    expect(markdown).toContain('- [src/](');
-    expect(markdown).toContain('- [README.md](');
-    expect(markdown).toContain('## README.md');
-    expect(markdown).toContain('# Hello World');
-  });
-
-  it('formats a compact plain-text snapshot with metadata, file tree, and README', () => {
-    const text = formatGithubRepositoryText(SNAPSHOT);
-
-    expect(text).toContain('Repository: octocat/Hello-World');
-    expect(text).toContain('Description: A friendly test repository');
-    expect(text).toContain('Files:');
-    expect(text).toContain('- src/');
-    expect(text).toContain('- README.md');
-    expect(text).toContain('README.md:');
-    expect(text).toContain('This is the README.');
-  });
-});

package/tests/unit/heading-image.test.js

@@ -1,49 +0,0 @@
-import { convertHtmlToMarkdown } from '../../src/lib.js';
-import { extractBase64Images } from '../../src/gdocs.js';
-
-const PNG_B64 =
-  'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNgYAAAAAMAASsJTYQAAAAASUVORK5CYII=';
-
-const IMG_REF_PATTERN = /!\[[^\]]*\]\([^)]*images\/[^)]+\)/g;
-
-describe('heading image parity', () => {
-  it('<img> inside <h1> survives Turndown and stays in sync with extraction', () => {
-    const html = `<html><body><h1>Title <img src="data:image/png;base64,${PNG_B64}" alt="x"></h1><p>Body</p></body></html>`;
-
-    const { html: localHtml, images } = extractBase64Images(html);
-    const md = convertHtmlToMarkdown(localHtml);
-    const mdImgCount = (md.match(IMG_REF_PATTERN) || []).length;
-
-    expect(images).toHaveLength(1);
-    expect(mdImgCount).toBe(images.length);
-  });
-
-  it('<img> inside all heading levels is preserved', () => {
-    for (let level = 1; level <= 6; level++) {
-      const tag = `h${level}`;
-      const html = `<html><body><${tag}><img src="data:image/png;base64,${PNG_B64}" alt="icon"> Heading</${tag}></body></html>`;
-
-      const { html: localHtml, images } = extractBase64Images(html);
-      const md = convertHtmlToMarkdown(localHtml);
-      const refs = (md.match(IMG_REF_PATTERN) || []).length;
-
-      expect(refs).toBe(images.length);
-    }
-  });
-
-  it('image count parity across full pipeline', () => {
-    const html = `<html><body>
-<h1><img src="data:image/png;base64,${PNG_B64}" alt="h1"> Chapter</h1>
-<p>Text <img src="data:image/png;base64,${PNG_B64}" alt="p1"> here.</p>
-<h2><img src="data:image/png;base64,${PNG_B64}" alt="h2"> Section</h2>
-<p><img src="data:image/png;base64,${PNG_B64}" alt="p2"></p>
-</body></html>`;
-
-    const { html: localHtml, images } = extractBase64Images(html);
-    const md = convertHtmlToMarkdown(localHtml);
-    const mdRefCount = (md.match(IMG_REF_PATTERN) || []).length;
-
-    expect(images).toHaveLength(4);
-    expect(mdRefCount).toBe(images.length);
-  });
-});

package/tests/unit/heading-numbering.test.js

@@ -1,28 +0,0 @@
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-import { convertHtmlToMarkdown } from '../../src/lib.js';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-const HTML = fs.readFileSync(
-  path.join(__dirname, '..', 'fixtures', 'heading-numbering.html'),
-  'utf8'
-);
-
-it('preserves hierarchical heading numbering (13, 13.1, 13.2, 13.3)', () => {
-  const md = convertHtmlToMarkdown(HTML);
-
-  // Parent number 13 must survive — either as Markdown heading or as numbered-list item.
-  expect(md).toMatch(/(^|\n)#{1,6}\s+13\.|(^|\n)13\.\s/);
-
-  // Sub-numbers 13.1, 13.2, 13.3 must each appear in heading-like context (line start, not buried mid-paragraph).
-  for (const sub of ['13.1', '13.2', '13.3']) {
-    expect(md).toMatch(
-      new RegExp(`(^|\\n)\\s*\\*{0,3}\\s*${sub.replace('.', '\\.')}`, 'm')
-    );
-  }
-
-  // Subsections must NOT be wrapped in markdown blockquotes — there is no <blockquote> in the fixture.
-  expect(md).not.toMatch(/^>\s+\*{1,3}13\.\d/m);
-});

package/tests/unit/html2md-br-in-list-item.test.js

@@ -1,23 +0,0 @@
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-import { convertHtmlToMarkdown } from '../../src/lib.js';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-const HTML = fs.readFileSync(
-  path.join(__dirname, '..', 'fixtures', 'list-item-with-br.html'),
-  'utf8'
-);
-
-it('preserves <br> as a line separator inside list items', () => {
-  const md = convertHtmlToMarkdown(HTML);
-  for (const tag of ['TAG1', 'TAG2', 'TAG3']) {
-    expect(md).toMatch(
-      new RegExp(`(^|\\n)\\s*\\*{0,2}${tag}\\*{0,2}\\s*–`, 'm')
-    );
-  }
-  // Definitions must not be glued on the same line (no <br> dropped).
-  expect(md).not.toMatch(/Definition one\.[ \t]*\*{0,2}TAG2/);
-  expect(md).not.toMatch(/Definition two\.[ \t]*\*{0,2}TAG3/);
-});

package/tests/unit/html2md-ol-numbering.test.js

@@ -1,20 +0,0 @@
-import fs from 'fs';
-import path from 'path';
-import { fileURLToPath } from 'url';
-import { convertHtmlToMarkdown } from '../../src/lib.js';
-
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-const HTML = fs.readFileSync(
-  path.join(__dirname, '..', 'fixtures', 'ol-continuous-numbering.html'),
-  'utf8'
-);
-
-it('numbers consecutive top-level ordered lists continuously', () => {
-  const md = convertHtmlToMarkdown(HTML);
-  expect(md).toMatch(/^\s*1\.\s+\*\*First\*\*/m);
-  expect(md).toMatch(/^\s*2\.\s+\*\*Second\*\*/m);
-  expect(md).toMatch(/^\s*3\.\s+\*\*Third\*\*/m);
-  expect(md).toMatch(/^\s*4\.\s+\*\*Fourth\*\*/m);
-  expect(md).toMatch(/^\s*13\.\s+\*\*Top-level/m);
-});