new-markdown/tests/chunk-load.test.ts

// 分片载入（docs/20）：切分安全性 + 分片解析拼接与整篇解析的序列化等价。
import { describe, it, expect, afterEach } from 'vitest'
import type { Editor } from '@milkdown/kit/core'
import { createMarkdownEditor, getMarkdown } from '../src/editor/editor'
import { splitMarkdownChunks, prepareChunkLoad } from '../src/editor/chunkLoader'

let editors: Editor[] = []
afterEach(async () => {
  for (const e of editors) { try { await e.destroy() } catch { /* ignore */ } }
  editors = []
  document.body.innerHTML = ''
})

async function load(md: string): Promise<Editor> {
  const root = document.createElement('div')
  document.body.appendChild(root)
  const editor = createMarkdownEditor(root, md)
  editors.push(editor)
  await editor.create()
  return editor
}

/** 生成超过阈值的富结构文档：多标题、宽松列表、任务、表格、公式、Mermaid、含空行围栏 */
function bigDoc(): string {
  const parts: string[] = []
  for (let s = 1; s <= 20; s++) {
    parts.push(`## 第 ${s} 节`)
    parts.push('')
    parts.push(`第 ${s} 节的正文段落，包含**加粗**、*斜体*与行内公式 $a_${s}+b$，以及足够长的中文填充文本。`.repeat(60))
    parts.push('')
    parts.push('- 条目甲')
    parts.push('')
    parts.push('- [ ] 任务乙')
    parts.push('')
    parts.push('| 列一 | 列二 |')
    parts.push('| --- | --- |')
    parts.push(`| 值 ${s} | ${s} |`)
    parts.push('')
    parts.push('```text')
    parts.push(`code ${s} 第一行`)
    parts.push('')
    parts.push('# 这行在围栏里不是标题')
    parts.push('')
    parts.push('```')
    parts.push('')
    parts.push('> 引用第一段')
    parts.push('>')
    parts.push('> 引用第二段')
    parts.push('')
    parts.push('```mermaid')
    parts.push('graph TD')
    parts.push('  A-->B')
    parts.push('```')
    parts.push('')
    parts.push(`$$\nE_${s} = mc^2\n$$`)
    parts.push('')
    parts.push('---')
    parts.push('')
  }
  return parts.join('\n')
}

describe('splitMarkdownChunks', () => {
  it('拼接回去与原文逐字相同，片数 > 1', () => {
    const md = bigDoc()
    expect(md.length).toBeGreaterThan(60_000)
    const chunks = splitMarkdownChunks(md)
    expect(chunks.length).toBeGreaterThan(1)
    expect(chunks.join('')).toBe(md)
  })

  it('围栏内的空行与 # 行不触发切分', () => {
    const md = `# 顶\n\n\`\`\`text\n第一行\n\n# 假标题\n\n\`\`\`\n\n正文 ${'填充'.repeat(40)}`
    const chunks = splitMarkdownChunks(md)
    expect(chunks.join('')).toBe(md)
    // 没有合法切点时整篇一片（小文档本来也一片）
    expect(chunks.length).toBe(1)
  })

  it('含链接引用定义时整篇一片（定义可能在文末被前文引用）', () => {
    const md = `${bigDoc()}\n\n[ref1]: https://example.com\n`
    expect(splitMarkdownChunks(md).length).toBe(1)
    expect(prepareChunkLoad(md)).toBeNull()
  })

  it('小文档不走分片', () => {
    expect(prepareChunkLoad('# 小\n\n正文')).toBeNull()
  })
})

describe('分片载入与整篇解析等价', () => {
  it('逐片追加后的序列化 == 整篇解析的序列化', async () => {
    const md = bigDoc()
    const whole = getMarkdown(await load(md))
    const handle = prepareChunkLoad(md)
    expect(handle).not.toBeNull()
    if (!handle) return
    const editor = await load(handle.firstChunk)
    const progress: number[] = []
    await handle.appendRest(editor, (done) => { progress.push(done) }, () => false)
    expect(progress[progress.length - 1]).toBe(handle.totalChunks)
    const chunked = getMarkdown(editor)
    expect(chunked).toBe(whole)
  }, 60_000)
})

describe('列表内嵌围栏不被切开（docs/29）', () => {
  it('分片序列化与整篇逐字相等', async () => {
    const parts: string[] = []
    for (let s = 1; s <= 30; s++) {
      parts.push(`## 小节 ${s}`)
      parts.push('')
      parts.push('正文填充。'.repeat(420))
      parts.push('')
      parts.push('- 列表项，内含缩进围栏代码：')
      parts.push('')
      parts.push('  ```js')
      parts.push(`  const v${s} = ${s}`)
      parts.push('  ```')
      parts.push('')
      parts.push('- 下一项')
      parts.push('')
    }
    const md = parts.join('\n')
    expect(md.length).toBeGreaterThan(60_000)
    const whole = getMarkdown(await load(md))
    const handle = prepareChunkLoad(md)
    expect(handle).not.toBeNull()
    const editor = await load(handle!.firstChunk)
    await handle!.appendRest(editor, () => undefined, () => false)
    expect(getMarkdown(editor)).toBe(whole)
  }, 60000)
})