Reimplement as a tokenizer with GFM parity

This commit is contained in:
gsb
2026-04-30 07:09:19 +00:00
parent 005db2f431
commit d41716c8b2
28 changed files with 4798 additions and 1398 deletions
+390 -5
View File
@@ -1,7 +1,7 @@
import { ribbit } from './setup';
const r = ribbit();
const hopdown = new r.HopDown();
const lib = ribbit();
const hopdown = new lib.HopDown();
const H = (md: string) => hopdown.toHTML(md);
const M = (html: string) => hopdown.toMarkdown(html);
const rt = (md: string) => M(H(md));
@@ -18,9 +18,9 @@ describe('Markdown → HTML', () => {
});
describe('headings', () => {
it.each([1,2,3,4,5,6])('h%i', (n) => {
const prefix = '#'.repeat(n);
expect(H(`${prefix} Sub`)).toContain(`<h${n}`);
it.each([1, 2, 3, 4, 5, 6])('h%i', (level) => {
const prefix = '#'.repeat(level);
expect(H(`${prefix} Sub`)).toContain(`<h${level}`);
});
it('heading id', () => expect(H('## Hello World')).toContain("id='HelloWorld'"));
it('heading inline md', () => expect(H('## **Bold** text')).toContain('<strong>Bold</strong>'));
@@ -149,3 +149,388 @@ describe('Tables with nested markdown', () => {
it('td bold rt', () => expect(rt('| h |\n|---|\n| **b** |')).toBe('| h |\n| --- |\n| **b** |'));
it('multi-cell rt', () => expect(rt('| **a** | *b* |\n|---|---|\n| `c` | [d](e) |')).toBe('| **a** | *b* |\n| --- | --- |\n| `c` | [d](e) |'));
});
describe('Backslash escapes', () => {
it('escaped asterisk', () => expect(H('\\*not italic\\*')).toBe('<p>*not italic*</p>'));
it('escaped backslash', () => expect(H('a \\\\ b')).toBe('<p>a \\ b</p>'));
it('escaped backtick', () => expect(H('\\`not code\\`')).toBe('<p>`not code`</p>'));
it('round-trip preserves escape', () => {
const html = H('\\*literal\\*');
expect(html).toContain('*literal*');
expect(html).not.toContain('<em>');
});
});
describe('Strikethrough', () => {
it('md→html', () => expect(H('~~deleted~~')).toBe('<p><del>deleted</del></p>'));
it('html→md', () => expect(M('<p><del>gone</del></p>')).toBe('~~gone~~'));
it('round-trip', () => expect(rt('~~struck~~')).toBe('~~struck~~'));
it('mixed with bold', () => expect(H('**bold** and ~~struck~~')).toContain('<del>struck</del>'));
});
describe('Link titles', () => {
it('link with title', () => expect(H('[t](http://x "My Title")')).toBe('<p><a href="http://x" title="My Title">t</a></p>'));
it('title round-trip', () => expect(rt('[t](http://x "My Title")')).toBe('[t](http://x "My Title")'));
});
describe('Reference links', () => {
it('basic reference', () => expect(H('[text][ref]\n\n[ref]: http://x')).toContain('<a href="http://x">text</a>'));
it('shortcut reference', () => expect(H('[ref][]\n\n[ref]: http://x')).toContain('<a href="http://x">ref</a>'));
it('reference with title', () => expect(H('[t][r]\n\n[r]: http://x "T"')).toContain('title="T"'));
it('case insensitive', () => expect(H('[t][REF]\n\n[ref]: http://x')).toContain('<a href="http://x">'));
it('undefined reference passes through', () => expect(H('[t][missing]')).toContain('[t][missing]'));
it('definition not rendered', () => expect(H('[ref]: http://x\n\ntext')).toBe('<p>text</p>'));
});
describe('HTML passthrough', () => {
it('inline html preserved', () => expect(H('a <span class="x">b</span> c')).toContain('<span class="x">b</span>'));
it('self-closing tag', () => expect(H('a <br/> b')).toContain('<br/>'));
it('html not double-escaped', () => expect(H('<em>hi</em>')).not.toContain('&lt;'));
});
describe('Autolinks', () => {
it('angle bracket autolink', () => expect(H('<https://example.com>')).toContain('<a href="https://example.com">'));
it('bare URL', () => expect(H('visit https://example.com today')).toContain('<a href="https://example.com">'));
it('URL not matched inside link', () => {
const html = H('[text](https://example.com)');
// Should have exactly one <a> tag, not nested
const anchorPattern = /<a /g;
const count = (html.match(anchorPattern) || []).length;
expect(count).toBe(1);
});
});
describe('Alternate syntax (parse-only, canonical output)', () => {
describe('underscore emphasis', () => {
it('_italic_ → *italic*', () => {
expect(H('_italic_')).toBe('<p><em>italic</em></p>');
expect(rt('_italic_')).toBe('*italic*');
});
it('__bold__ → **bold**', () => {
expect(H('__bold__')).toBe('<p><strong>bold</strong></p>');
expect(rt('__bold__')).toBe('**bold**');
});
it('___both___ → ***both***', () => {
expect(H('___both___')).toContain('<em><strong>both</strong></em>');
expect(rt('___both___')).toBe('***both***');
});
it('mid-word _ not converted', () => {
expect(H('foo_bar_baz')).toBe('<p>foo_bar_baz</p>');
});
});
describe('setext headings', () => {
it('=== underline → h1', () => {
expect(H('Title\n=====')).toContain('<h1');
expect(H('Title\n=====')).toContain('Title');
});
it('--- underline → h2', () => {
expect(H('Sub\n---')).toContain('<h2');
});
it('round-trips to ATX', () => {
expect(rt('Title\n=====')).toBe('# Title');
expect(rt('Sub\n---')).toBe('## Sub');
});
});
describe('ATX closing hashes', () => {
it('## Title ## → h2', () => {
expect(H('## Title ##')).toContain('<h2');
expect(H('## Title ##')).toContain('Title');
});
it('round-trips without closing', () => {
expect(rt('## Title ##')).toBe('## Title');
});
});
describe('tilde fenced code', () => {
it('~~~ fence accepted', () => {
expect(H('~~~\ncode\n~~~')).toContain('<code>code</code>');
});
it('round-trips to backtick', () => {
expect(rt('~~~\ncode\n~~~')).toContain('```');
});
});
describe('plus list marker', () => {
it('+ item accepted', () => {
expect(H('+ item')).toContain('<li>');
});
it('round-trips to -', () => {
expect(rt('+ item')).toContain('- item');
});
});
});
describe('HopDown delimiter matching API', () => {
describe('findCompletePair', () => {
it('finds bold pair', () => {
const result = hopdown.findCompletePair('hello **world** end');
expect(result).not.toBeNull();
expect(result!.htmlTag).toBe('strong');
expect(result!.content).toBe('world');
expect(result!.delimiter).toBe('**');
});
it('finds italic pair', () => {
const result = hopdown.findCompletePair('hello *world* end');
expect(result).not.toBeNull();
expect(result!.htmlTag).toBe('em');
});
it('finds strikethrough pair', () => {
const result = hopdown.findCompletePair('hello ~~gone~~ end');
expect(result).not.toBeNull();
expect(result!.htmlTag).toBe('del');
});
it('returns null when no pair exists', () => {
expect(hopdown.findCompletePair('hello world')).toBeNull();
});
it('skips sentinel-wrapped content', () => {
expect(hopdown.findCompletePair('hello \x01<strong>world</strong>\x02 end')).toBeNull();
});
it('respects precedence (boldItalic before bold)', () => {
const result = hopdown.findCompletePair('***both***');
expect(result).not.toBeNull();
expect(result!.htmlTag).toBe('em');
expect(result!.tag.name).toBe('boldItalic');
});
});
describe('findUnmatchedOpener', () => {
it('finds unclosed bold', () => {
const result = hopdown.findUnmatchedOpener('hello **world');
expect(result).not.toBeNull();
expect(result!.htmlTag).toBe('strong');
expect(result!.content).toBe('world');
});
it('returns null when no opener exists', () => {
expect(hopdown.findUnmatchedOpener('hello world end')).toBeNull();
});
it('returns null for plain text', () => {
expect(hopdown.findUnmatchedOpener('hello world')).toBeNull();
});
});
describe('getTagForElement', () => {
it('returns tag for strong element', () => {
const element = document.createElement('strong');
const tag = hopdown.getTagForElement(element);
expect(tag).not.toBeNull();
expect(tag!.name).toBe('bold');
expect(tag!.delimiter).toBe('**');
});
it('returns tag for em element', () => {
const element = document.createElement('em');
const tag = hopdown.getTagForElement(element);
expect(tag).not.toBeNull();
expect(tag!.name).toBe('italic');
});
it('returns null for div element', () => {
const element = document.createElement('div');
expect(hopdown.getTagForElement(element)).toBeNull();
});
});
describe('getEditableSelector', () => {
it('returns a non-empty string', () => {
const selector = hopdown.getEditableSelector();
expect(selector.length).toBeGreaterThan(0);
});
it('includes inline tag selectors', () => {
const selector = hopdown.getEditableSelector();
expect(selector).toContain('strong');
expect(selector).toContain('em');
expect(selector).toContain('code');
});
it('includes block tag selectors', () => {
const selector = hopdown.getEditableSelector();
expect(selector).toContain('pre');
expect(selector).toContain('blockquote');
});
});
});
describe('Hard line breaks', () => {
it('trailing two spaces', () => {
expect(H('line one \nline two')).toContain('<br>');
});
it('trailing backslash', () => {
expect(H('line one\\\nline two')).toContain('<br>');
});
it('single space does not break', () => {
expect(H('line one \nline two')).not.toContain('<br>');
});
it('round-trip', () => {
const html = H('line one \nline two');
const markdown = M(html);
expect(markdown).toContain(' \n');
});
});
describe('Link nesting prevention', () => {
it('nested brackets prevent link match', () => {
const html = H('[outer [inner](http://b)](http://a)');
// The outer [ prevents matching as a single link — the inner
// link matches instead, and the outer brackets are literal text
expect(html).toContain('<a href="http://b">inner</a>');
});
it('preserves inner link text', () => {
const html = H('[outer [inner](http://b)](http://a)');
expect(html).toContain('inner');
});
it('autolink inside link is stripped', () => {
const html = H('[see <https://b.com>](http://a)');
const anchorPattern = /<a /g;
const linkCount = (html.match(anchorPattern) || []).length;
expect(linkCount).toBe(1);
});
});
describe('Multiple-of-3 emphasis rule', () => {
it('***foo*** is bold-italic', () => {
expect(H('***foo***')).toContain('<em><strong>foo</strong></em>');
});
it('**foo** is bold', () => {
expect(H('**foo**')).toBe('<p><strong>foo</strong></p>');
});
it('*foo* is italic', () => {
expect(H('*foo*')).toBe('<p><em>foo</em></p>');
});
it('*foo** does not match (1+2=3, rule applies)', () => {
const html = H('*foo**');
expect(html).not.toContain('<em>');
expect(html).not.toContain('<strong>');
});
it('**foo* does not match (2+1=3, rule applies)', () => {
const html = H('**foo*');
expect(html).not.toContain('<em>');
expect(html).not.toContain('<strong>');
});
});
describe('HTML entity resolution', () => {
it('&amp; resolves to &', () => {
expect(H('a &amp; b')).toBe('<p>a &amp; b</p>');
});
it('&lt; resolves to <', () => {
expect(H('a &lt; b')).toBe('<p>a &lt; b</p>');
});
it('&gt; resolves to >', () => {
expect(H('a &gt; b')).toBe('<p>a &gt; b</p>');
});
it('&#123; resolves to {', () => {
expect(H('&#123;')).toBe('<p>{</p>');
});
it('&#x7B; resolves to {', () => {
expect(H('&#x7B;')).toBe('<p>{</p>');
});
it('unknown entity passes through', () => {
expect(H('&unknown;')).toContain('&amp;unknown;');
});
});
describe('Nested inline scenarios', () => {
describe('markdown → HTML nesting', () => {
it('strikethrough wraps bold', () => {
expect(H('~~**bold** struck~~')).toBe('<p><del><strong>bold</strong> struck</del></p>');
});
it('bold wraps strikethrough', () => {
expect(H('**~~struck~~ bold**')).toBe('<p><strong><del>struck</del> bold</strong></p>');
});
it('italic wraps link', () => {
expect(H('*[text](http://x)*')).toContain('<em><a href="http://x">text</a></em>');
});
it('code inside strikethrough', () => {
expect(H('~~`code` struck~~')).toContain('<del><code>code</code> struck</del>');
});
it('adjacent bold and italic', () => {
const html = H('**bold***italic*');
expect(html).toContain('<strong>bold</strong>');
expect(html).toContain('<em>italic</em>');
});
});
describe('HTML → markdown → HTML round-trip nesting', () => {
it('bold wraps italic', () => {
const html = '<p><strong>a <em>b</em> c</strong></p>';
expect(H(M(html))).toBe(html);
});
it('italic wraps bold', () => {
const html = '<p><em>a <strong>b</strong> c</em></p>';
expect(H(M(html))).toBe(html);
});
it('bold wraps code', () => {
const html = '<p><strong>a <code>b</code> c</strong></p>';
expect(H(M(html))).toBe(html);
});
it('bold wraps link', () => {
const html = '<p><strong><a href="http://x">t</a></strong></p>';
expect(H(M(html))).toBe(html);
});
it('strikethrough wraps bold', () => {
const html = '<p><del><strong>bold</strong> struck</del></p>';
expect(H(M(html))).toBe(html);
});
it('italic wraps link', () => {
const html = '<p><em><a href="http://x">t</a></em></p>';
expect(H(M(html))).toBe(html);
});
});
describe('literal delimiters in text round-trip', () => {
it('literal * in bold', () => {
const html = '<p><strong>a * b</strong></p>';
expect(H(M(html))).toBe(html);
});
it('literal ~ in strikethrough', () => {
const html = '<p><del>a ~ b</del></p>';
expect(H(M(html))).toBe(html);
});
it('literal ` adjacent to code', () => {
const html = '<p>a ` b <code>c</code></p>';
expect(H(M(html))).toBe(html);
});
it('literal * in plain text', () => {
const html = '<p>hello * world</p>';
expect(H(M(html))).toBe(html);
});
it('literal ** in plain text', () => {
const html = '<p>hello ** world</p>';
expect(H(M(html))).toBe(html);
});
it('literal _ in plain text', () => {
const html = '<p>hello _ world</p>';
expect(H(M(html))).toBe(html);
});
});
});
describe('Backslash-escaped HTML tags', () => {
it('\\<em> does not produce a real em element', () => {
const html = H('\\<em>text');
expect(html).not.toContain('<em>');
expect(html).toContain('&lt;em&gt;');
});
it('\\<b> does not produce a real b element', () => {
const html = H('\\<b>text');
expect(html).not.toContain('<b>');
});
it('round-trip of escaped HTML tag in text', () => {
const html = '<p>~~\\<em>---\\<b></em></p>';
const markdown = M(html);
const rehtml = H(markdown);
const markdown2 = M(rehtml);
const rehtml2 = H(markdown2);
expect(rehtml).toBe(rehtml2);
});
});