feat(parser): v0.1.15 — parser short+medium term improvements
Short-term fixes: - Fix ***bold italic*** / ___bold italic___ triple emphasis - Fix link text inline formatting (recursive renderInline on [**bold**](url)) - Fix backtick inline code nesting (CommonMark-compliant extractInlineCodes) - Fix tab indentation stripping in indented code blocks Medium-term improvements: - parseTokens() / renderTokens() separation API for token-level transform - registerBlockHandler() table-driven block handler registry - Backslash escape support (\* \_ \) Also: - Add 48 new test cases (583 total, 7 suites, all passing) - Parser coverage: 95.43% stmts / 91.38% branches / 100% funcs / 98.25% lines - Update README.md, site/, package.json to v0.1.15
This commit is contained in:
+422
-1
@@ -3,7 +3,7 @@
|
||||
* 覆盖 Markdown 解析器的所有语法分支与安全特性
|
||||
*/
|
||||
|
||||
import { parseMarkdown, safeUrl, slugify } from '../src/parser.js';
|
||||
import { parseMarkdown, parseTokens, renderTokens, safeUrl, slugify, clearRenderCache, registerBlockHandler } from '../src/parser.js';
|
||||
|
||||
describe('parseMarkdown - 基础', () => {
|
||||
test('空输入返回空字符串', () => {
|
||||
@@ -697,3 +697,424 @@ describe('parseMarkdown - v0.1.4 代码块语言扩展', () => {
|
||||
expect(html).toContain('language-file.txt');
|
||||
});
|
||||
});
|
||||
|
||||
// ============ v0.1.15 新增测试 ============
|
||||
|
||||
describe('parseMarkdown - v0.1.15 三重强调', () => {
|
||||
test('***bold italic*** 渲染为 <em><strong>', () => {
|
||||
const html = parseMarkdown('***bold italic***');
|
||||
expect(html).toContain('<em><strong>bold italic</strong></em>');
|
||||
});
|
||||
|
||||
test('___bold italic___ 渲染为 <em><strong>', () => {
|
||||
const html = parseMarkdown('___bold italic___');
|
||||
expect(html).toContain('<em><strong>bold italic</strong></em>');
|
||||
});
|
||||
|
||||
test('段落中混用 *** 和普通格式', () => {
|
||||
const html = parseMarkdown('a ***nested*** b');
|
||||
expect(html).toContain('<em><strong>nested</strong></em>');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 链接文本内格式', () => {
|
||||
test('链接文本支持粗体', () => {
|
||||
const html = parseMarkdown('[**bold link**](https://example.com)');
|
||||
expect(html).toContain('<a href="https://example.com"');
|
||||
expect(html).toContain('<strong>bold link</strong>');
|
||||
});
|
||||
|
||||
test('链接文本支持斜体', () => {
|
||||
const html = parseMarkdown('[*italic*](https://example.com)');
|
||||
expect(html).toContain('<em>italic</em>');
|
||||
});
|
||||
|
||||
test('链接文本支持行内代码', () => {
|
||||
const html = parseMarkdown('[`code` link](https://example.com)');
|
||||
expect(html).toContain('<code>code</code>');
|
||||
});
|
||||
|
||||
test('链接文本支持混合格式', () => {
|
||||
const html = parseMarkdown('[**bold** and *italic*](https://example.com)');
|
||||
expect(html).toContain('<strong>bold</strong>');
|
||||
expect(html).toContain('<em>italic</em>');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 反引号精确嵌套', () => {
|
||||
test('双反引号包裹单反引号', () => {
|
||||
const html = parseMarkdown('`` ` ``');
|
||||
expect(html).toContain('<code>');
|
||||
// 内容应为单个反引号
|
||||
expect(html).not.toContain('``');
|
||||
});
|
||||
|
||||
test('三反引号包裹反引号代码', () => {
|
||||
const html = parseMarkdown('``` `code` ```');
|
||||
expect(html).toContain('<code>');
|
||||
expect(html).toContain('`code`');
|
||||
});
|
||||
|
||||
test('普通反引号代码正常', () => {
|
||||
const html = parseMarkdown('`normal code`');
|
||||
expect(html).toContain('<code>normal code</code>');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 缩进代码块 Tab', () => {
|
||||
test('Tab 缩进代码块剥离 Tab', () => {
|
||||
const html = parseMarkdown('\tcode line');
|
||||
expect(html).toContain('<pre><code>');
|
||||
expect(html).toContain('code line');
|
||||
// Tab 应被剥离
|
||||
expect(html).not.toContain('\t');
|
||||
});
|
||||
|
||||
test('4 空格缩进代码块正常', () => {
|
||||
const html = parseMarkdown(' code line');
|
||||
expect(html).toContain('<pre><code>');
|
||||
expect(html).toContain('code line');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 反斜杠转义', () => {
|
||||
test('\\* 转义星号', () => {
|
||||
const html = parseMarkdown('a \\* b');
|
||||
expect(html).toContain('a * b');
|
||||
expect(html).not.toContain('<em>');
|
||||
});
|
||||
|
||||
test('\\_ 转义下划线', () => {
|
||||
const html = parseMarkdown('a \\_ b');
|
||||
expect(html).toContain('a _ b');
|
||||
expect(html).not.toContain('<em>');
|
||||
});
|
||||
|
||||
test('\\\\ 转义反斜杠本身', () => {
|
||||
const html = parseMarkdown('a \\\\ b');
|
||||
expect(html).toContain('a \\ b');
|
||||
});
|
||||
|
||||
test('非标点字符不转义', () => {
|
||||
const html = parseMarkdown('\\a');
|
||||
expect(html).toContain('\\a');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 parseTokens / renderTokens', () => {
|
||||
test('parseTokens 返回 token 数组和 footnotes', () => {
|
||||
const { tokens, footnotes } = parseTokens('# Hello\n\nworld');
|
||||
expect(Array.isArray(tokens)).toBe(true);
|
||||
expect(tokens.length).toBe(2);
|
||||
expect(tokens[0].type).toBe('heading');
|
||||
expect(tokens[0].level).toBe(1);
|
||||
expect(tokens[0].text).toBe('Hello');
|
||||
expect(tokens[1].type).toBe('paragraph');
|
||||
expect(tokens[1].text).toBe('world');
|
||||
expect(typeof footnotes).toBe('object');
|
||||
});
|
||||
|
||||
test('parseTokens 提取脚注', () => {
|
||||
const { tokens, footnotes } = parseTokens('text[^1]\n\n[^1]: note');
|
||||
expect(footnotes['1']).toBe('note');
|
||||
});
|
||||
|
||||
test('renderTokens 从 token 渲染 HTML', () => {
|
||||
const { tokens, footnotes } = parseTokens('# Title\n\n**bold**');
|
||||
const html = renderTokens(tokens, {}, footnotes);
|
||||
expect(html).toContain('<h1');
|
||||
expect(html).toContain('Title');
|
||||
expect(html).toContain('<strong>bold</strong>');
|
||||
});
|
||||
|
||||
test('renderTokens 渲染脚注区', () => {
|
||||
const { tokens, footnotes } = parseTokens('text[^fn]\n\n[^fn]: footnote content');
|
||||
const html = renderTokens(tokens, {}, footnotes);
|
||||
expect(html).toContain('me-footnotes');
|
||||
expect(html).toContain('footnote content');
|
||||
});
|
||||
|
||||
test('parseTokens 空输入返回空', () => {
|
||||
const { tokens } = parseTokens('');
|
||||
expect(tokens.length).toBe(0);
|
||||
const { tokens: t2 } = parseTokens(null);
|
||||
expect(t2.length).toBe(0);
|
||||
});
|
||||
|
||||
test('parseTokens 处理所有块级类型', () => {
|
||||
const md = [
|
||||
'# Heading',
|
||||
'',
|
||||
'paragraph text',
|
||||
'',
|
||||
'> quote',
|
||||
'',
|
||||
'- list item',
|
||||
'',
|
||||
'```',
|
||||
'code',
|
||||
'```',
|
||||
'',
|
||||
'---',
|
||||
'',
|
||||
'| a | b |',
|
||||
'| --- | --- |',
|
||||
'| 1 | 2 |',
|
||||
].join('\n');
|
||||
const { tokens } = parseTokens(md);
|
||||
const types = tokens.map((t) => t.type);
|
||||
expect(types).toContain('heading');
|
||||
expect(types).toContain('paragraph');
|
||||
expect(types).toContain('quote');
|
||||
expect(types).toContain('ul');
|
||||
expect(types).toContain('code');
|
||||
expect(types).toContain('hr');
|
||||
expect(types).toContain('table');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - v0.1.15 registerBlockHandler', () => {
|
||||
test('注册自定义块级处理器', () => {
|
||||
registerBlockHandler({
|
||||
name: 'customAlert',
|
||||
priority: 8.5,
|
||||
test: (line) => {
|
||||
const m = line.match(/^:::(\w+)/);
|
||||
return m ? m : null;
|
||||
},
|
||||
parse: (lines, i, match) => {
|
||||
const type = match[1];
|
||||
const content = [];
|
||||
let j = i + 1;
|
||||
while (j < lines.length && !lines[j].startsWith(':::')) {
|
||||
content.push(lines[j]);
|
||||
j++;
|
||||
}
|
||||
if (j < lines.length) j++; // skip closing :::
|
||||
return { token: { type: 'alert', alertType: type, content: content.join('\n') }, newIndex: j };
|
||||
},
|
||||
});
|
||||
|
||||
// 需要在 renderToken 中处理 alert 类型，这里只验证 token 生成
|
||||
const { tokens } = parseTokens(':::info\nThis is a note\n:::');
|
||||
const alertToken = tokens.find((t) => t.type === 'alert');
|
||||
expect(alertToken).toBeDefined();
|
||||
expect(alertToken.alertType).toBe('info');
|
||||
expect(alertToken.content).toBe('This is a note');
|
||||
});
|
||||
});
|
||||
|
||||
// ============ v0.1.15 覆盖率补齐测试 ============
|
||||
|
||||
describe('parseMarkdown - 覆盖率：渲染缓存淘汰', () => {
|
||||
test('缓存超过上限触发 FIFO 淘汰', () => {
|
||||
// MAX_CACHE_SIZE = 300，填充 301 个不同文本触发淘汰
|
||||
for (let i = 0; i < 301; i++) {
|
||||
const text = `text ${i} **bold**`;
|
||||
parseMarkdown(text);
|
||||
}
|
||||
// 不应抛错，且至少有一次淘汰发生
|
||||
expect(true).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：缩进代码块空行回退', () => {
|
||||
test('缩进检测匹配但无有效代码行时返回 null token', () => {
|
||||
// 4空格后无内容的行不属于代码块
|
||||
const { tokens } = parseTokens(' ');
|
||||
// 空行可能被空白处理器跳过，验证不生成 code token
|
||||
const codeTokens = tokens.filter((t) => t.type === 'code');
|
||||
expect(codeTokens.length).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：Setext 标题拒绝非段落', () => {
|
||||
test('列表项不被识别为 Setext 标题', () => {
|
||||
const html = parseMarkdown('- item\n===');
|
||||
expect(html).toContain('<ul>');
|
||||
expect(html).not.toContain('<h1');
|
||||
});
|
||||
|
||||
test('引用行不被识别为 Setext 标题', () => {
|
||||
const html = parseMarkdown('> quote\n===');
|
||||
expect(html).toContain('<blockquote>');
|
||||
expect(html).not.toContain('<h1');
|
||||
});
|
||||
|
||||
test('代码围栏不被识别为 Setext h2', () => {
|
||||
const html = parseMarkdown('```\n---');
|
||||
expect(html).toContain('<pre><code>');
|
||||
expect(html).not.toContain('<h2');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：段落收集边界', () => {
|
||||
test('段落遇到 Setext 分隔行终止', () => {
|
||||
const { tokens } = parseTokens('text\n===');
|
||||
expect(tokens.length).toBe(1);
|
||||
expect(tokens[0].type).toBe('heading');
|
||||
expect(tokens[0].level).toBe(1);
|
||||
});
|
||||
|
||||
test('段落遇到表格分隔行终止', () => {
|
||||
const { tokens } = parseTokens('| a | b |\n| --- | --- |');
|
||||
// 表格处理器先于段落，生成 table token
|
||||
expect(tokens.length).toBe(1);
|
||||
expect(tokens[0].type).toBe('table');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：列表项空行续行', () => {
|
||||
test('列表项后跟空行再跟缩进续行', () => {
|
||||
const html = parseMarkdown('- item start\n\n continued');
|
||||
expect(html).toContain('<ul>');
|
||||
expect(html).toContain('item start');
|
||||
expect(html).toContain('continued');
|
||||
});
|
||||
|
||||
test('列表项续行缩进与非缩进', () => {
|
||||
const html = parseMarkdown('- item line\n indent continuation\nno-indent');
|
||||
// no-indent 行在 item line 中一起显示（非独立项）
|
||||
expect(html).toContain('<ul>');
|
||||
expect(html).toContain('item line');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：任务列表子项', () => {
|
||||
test('任务列表嵌套子列表', () => {
|
||||
const html = parseMarkdown('- [x] done\n - sub item');
|
||||
expect(html).toContain('me-task-item');
|
||||
expect(html).toContain('checked');
|
||||
expect(html).toContain('sub item');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：脚注多行续行', () => {
|
||||
test('脚注定义跨多行', () => {
|
||||
const html = parseMarkdown('text[^multi]\n\n[^multi]: line one\n line two\nmore text');
|
||||
expect(html).toContain('me-footnotes');
|
||||
expect(html).toContain('line one');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：未闭合反引号', () => {
|
||||
test('未闭合的反引号原样保留', () => {
|
||||
const html = parseMarkdown('text `code');
|
||||
expect(html).toContain('`');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：图片引用链接', () => {
|
||||
test('图片引用 ![alt][ref]', () => {
|
||||
const html = parseMarkdown('![logo][img-ref]');
|
||||
expect(html).toContain('<img');
|
||||
expect(html).toContain('alt="logo"');
|
||||
expect(html).toContain('me-img-ref');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：链接引用回退', () => {
|
||||
test('链接引用 [text][ref] 保留原文', () => {
|
||||
const html = parseMarkdown('[click][myref]');
|
||||
expect(html).toContain('[click][myref]');
|
||||
expect(html).not.toContain('<a');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：自定义 token default 渲染', () => {
|
||||
test('未识别 token type 返回空字符串', () => {
|
||||
const tokens = [{ type: 'unknownType', text: 'whatever' }];
|
||||
const html = renderTokens(tokens);
|
||||
expect(html).toBe('');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：clearRenderCache', () => {
|
||||
test('clearRenderCache 清除缓存', () => {
|
||||
// 先使用缓存
|
||||
parseMarkdown('cached text');
|
||||
// 清除后不抛错
|
||||
expect(() => clearRenderCache()).not.toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：有 title 的链接', () => {
|
||||
test('链接带 title 属性', () => {
|
||||
const html = parseMarkdown('[text](https://example.com "my title")');
|
||||
expect(html).toContain('title="my title"');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：图片带 title', () => {
|
||||
test('图片带 title 属性', () => {
|
||||
const html = parseMarkdown('');
|
||||
expect(html).toContain('title="photo title"');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 覆盖率：无 match 的图片链接回退', () => {
|
||||
test('不完整的图片语法被保留', () => {
|
||||
const html = parseMarkdown('![broken');
|
||||
// 不完整的 ![... 不作为图片
|
||||
expect(html).toContain('![broken');
|
||||
});
|
||||
});
|
||||
|
||||
// ============ 额外分支补齐（目标 95%+ Stmts） ============
|
||||
|
||||
describe('parseMarkdown - 分支：缩进代码块空行', () => {
|
||||
test('仅有缩进空格无内容的行不产生代码块', () => {
|
||||
// 通过 parseTokens 检查，空白处理器先捕获空行
|
||||
const { tokens } = parseTokens(' \nparagraph');
|
||||
const codeTokens = tokens.filter((t) => t.type === 'code' && t.indent);
|
||||
expect(codeTokens.length).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 分支：Setext H2 拒绝列表行', () => {
|
||||
test('有序列表行后跟 --- 不形成 Setext h2', () => {
|
||||
const html = parseMarkdown('1. item\n---');
|
||||
expect(html).toContain('<ol');
|
||||
// --- 应被解析为水平线，而非 Setext 标题
|
||||
expect(html).toContain('<hr');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 分支：段落遇到 Setext 标题终止', () => {
|
||||
test('段落收集在 Setext 分隔行前停止', () => {
|
||||
const html = parseMarkdown('Some text\n=======');
|
||||
expect(html).toContain('<h1');
|
||||
expect(html).toContain('Some text');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 分支：段落遇到表格终止', () => {
|
||||
test('段落遇到表格行终止并生成表格', () => {
|
||||
const html = parseMarkdown('| Name | Age |\n| --- | --- |\n| Tom | 25 |');
|
||||
expect(html).toContain('<table>');
|
||||
expect(html).toContain('Name');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 分支：列表空行续行', () => {
|
||||
test('列表项内部空行后继续', () => {
|
||||
const html = parseMarkdown('- item start\n\n still item\n- next item');
|
||||
expect(html).toContain('<ul>');
|
||||
expect(html).toContain('item start');
|
||||
expect(html).toContain('still item');
|
||||
expect(html).toContain('next item');
|
||||
});
|
||||
});
|
||||
|
||||
describe('parseMarkdown - 分支：嵌套列表子项渲染', () => {
|
||||
test('嵌套列表通过 subTokens 正确渲染', () => {
|
||||
const html = parseMarkdown('- parent\n - child\n - child2');
|
||||
expect(html).toContain('<ul>');
|
||||
expect(html).toContain('parent');
|
||||
expect(html).toContain('child');
|
||||
expect(html).toContain('child2');
|
||||
// 验证内层 ul 存在
|
||||
const innerUlCount = (html.match(/<ul>/g) || []).length;
|
||||
expect(innerUlCount).toBeGreaterThanOrEqual(2);
|
||||
});
|
||||
});
|
||||
|
||||
Reference in New Issue
Block a user