feat(export): 交付 Markdown → HTML 导出服务

实现 Export Service 完整生命周期：mistune AST → Document AST → HtmlExporter 渲染完整 HTML5，异步任务注册表 + 取消 + 24h 产物过期。新增 5 个 /api/exports 端点与 15 项测试；pdf/docx 与函数图像静态渲染留待后续 PR。
2026-09-04 09:02:33 +08:00
parent 2e496462a9
commit 5c2441464d
18 changed files with 1358 additions and 17 deletions
@@ -0,0 +1,303 @@
+"""Export Service 的单元与端到端测试。
+
+沿用 conftest 隔离机制：APP_DATA_DIR / DB / Vault / exports 目录都落在临时目录，
+不读写真实数据。导出采用「创建即 queued + 后台 Task 执行」的异步模型，测试在同一
+事件循环内创建并等待后台任务结束，得到终态 ExportJob 后再断言。
+"""
+
+from __future__ import annotations
+
+import asyncio
+from datetime import datetime, timedelta, timezone
+
+import pytest
+from pydantic import ValidationError
+
+from app.config import get_settings
+from app.contracts import (
+    ExportFormat,
+    ExportOptions,
+    ExportRequest,
+    ExportSource,
+    ExportSourceType,
+    ExportStatus,
+)
+from app.errors import ApiError
+from app.export import service as export_service
+from app.export.exporters.html import HtmlExporter
+from app.export.markdown import parse_document
+
+MD = """# 进程调度
+
+一些 **加粗** 和 *斜体*，[链接](https://a.b) 与 `code`。
+
+- 项目一
+- 项目二
+
+```python
+print(1)
+```
+
+```mermaid
+graph LR
+```
+
+```function_plot
+y = x
+```
+
+| a | b |
+|---|---|
+| 1 | 2 |
+
+行内 $x^2$ 与块级
+$$
+y = mx + b
+$$
+"""
+
+
+@pytest.fixture(autouse=True)
+def _reset_export_state():
+    """清空内存注册表，避免跨用例的任务/取消标志互相污染。"""
+    export_service._jobs.clear()
+    export_service._tasks.clear()
+    export_service._cancel_flags.clear()
+    yield
+    export_service._jobs.clear()
+    export_service._tasks.clear()
+    export_service._cancel_flags.clear()
+
+
+def _create_and_wait(request: ExportRequest) -> object:
+    """创建导出并在同一事件循环内等待后台任务结束，返回终态 ExportJob。"""
+
+    async def _execute():
+        job = await export_service.create_export(request)
+        return await export_service.wait_for_export(job.job_id)
+
+    return asyncio.run(_execute())
+
+
+# --------------------------------------------------------------------------- #
+# markdown → Document AST
+# --------------------------------------------------------------------------- #
+def _types(nodes) -> list[str]:
+    return [n.type for n in nodes]
+
+
+def test_parse_document_heading_and_inline() -> None:
+    doc = parse_document("# 标题\n\n一段 **加粗** 和 [链接](https://a.b)。")
+
+    assert doc.type == "document"
+    heading = doc.children[0]
+    assert heading.type == "heading"
+    assert heading.attributes["level"] == 1
+
+    para = doc.children[1]
+    assert para.type == "paragraph"
+    kinds = _types(para.children)
+    assert "text" in kinds
+    assert "strong" in kinds
+    assert "link" in kinds
+
+    link = next(c for c in para.children if c.type == "link")
+    assert link.attributes["href"] == "https://a.b"
+
+
+def test_parse_document_list_and_code_fencing() -> None:
+    doc = parse_document("- a\n- b\n\n```mermaid\ngraph LR\n```\n\n```function_plot\ny=x\n```\n\n```python\nx\n```")
+
+    kinds = [c.type for c in doc.children]
+    assert kinds[0] == "list"
+    assert kinds[1] == "mermaid"
+    assert kinds[2] == "function_plot"
+    assert kinds[3] == "code_block"
+
+    code = doc.children[3]
+    assert code.attributes["language"] == "python"
+    assert code.text == "x"
+
+
+def test_parse_document_table_and_math() -> None:
+    doc = parse_document("| a | b |\n|---|---|\n| 1 | 2 |\n\n$x^2$\n\n$$\ny=mx\n$$")
+
+    table = doc.children[0]
+    assert table.type == "table"
+    assert table.children[0].type == "table_row"
+    assert table.children[0].children[0].attributes["head"] is True
+
+    # 表格后是「行内数学所在段落」与「块级数学」
+    kinds = [c.type for c in doc.children[1:]]
+    assert "paragraph" in kinds
+    assert "math_block" in kinds
+
+
+# --------------------------------------------------------------------------- #
+# HtmlExporter
+# --------------------------------------------------------------------------- #
+async def _render(markdown: str, *, title: str = "") -> str:
+    doc = parse_document(markdown)
+    doc.attributes["title"] = title
+    result = await HtmlExporter().export(doc, ExportOptions())
+    return result.content.decode("utf-8")
+
+
+def test_html_exporter_renders_basic_nodes_and_escapes() -> None:
+    html = asyncio.run(_render("# 标题\n\n**加粗** [链接](https://a.b) 与 <b>原始</b>。"))
+
+    assert "<h1>标题</h1>" in html
+    assert "<strong>加粗</strong>" in html
+    assert '<a href="https://a.b">链接</a>' in html
+    # 原始 HTML 必须被转义，不能注入文档
+    assert "&lt;b&gt;原始&lt;/b&gt;" in html
+    assert "<b>原始</b>" not in html
+
+
+def test_html_exporter_marks_mermaid_and_function_plot() -> None:
+    result = asyncio.run(HtmlExporter().export(parse_document("```mermaid\ngraph LR\n```"), ExportOptions()))
+
+    html = result.content.decode("utf-8")
+    assert '<pre class="mermaid">graph LR</pre>' in html
+    assert any("mermaid" in w for w in result.warnings)
+
+
+def test_html_exporter_include_title_and_metadata() -> None:
+    doc = parse_document("正文")
+    doc.attributes["title"] = "操作系统复习"
+    doc.attributes["metadata"] = {"tags": ["os", "复习"]}
+
+    opts = ExportOptions(include_title=True, include_metadata=True)
+    result = asyncio.run(HtmlExporter().export(doc, opts))
+    html = result.content.decode("utf-8")
+
+    assert '<h1 class="title">操作系统复习</h1>' in html
+    assert "os, 复习" in html
+
+
+# --------------------------------------------------------------------------- #
+# ExportService
+# --------------------------------------------------------------------------- #
+def _markdown_request(markdown: str, *, format: ExportFormat = ExportFormat.html) -> ExportRequest:
+    return ExportRequest(
+        source=ExportSource(type=ExportSourceType.markdown, markdown=markdown),
+        format=format,
+    )
+
+
+def test_export_markdown_source_completes_and_writes_file() -> None:
+    finished = _create_and_wait(_markdown_request(MD))
+
+    assert finished.status == ExportStatus.completed
+    assert finished.file is not None
+    assert finished.file.mime_type == "text/html"
+    assert finished.file.size > 0
+    assert len(finished.file.sha256) == 64
+
+    path = get_settings().exports_path / f"{finished.job_id}.html"
+    assert path.exists()
+    content = path.read_text(encoding="utf-8")
+    assert "进程调度" in content
+
+
+def test_export_note_source_resolves_title_and_metadata() -> None:
+    from app.services import note_service
+
+    async def _go():
+        note = await note_service.create_note(
+            title="操作系统复习", markdown="# 进程调度\n\n内容。", folder="导出", tags=["os"]
+        )
+        request = ExportRequest(
+            source=ExportSource(type=ExportSourceType.note, note_id=note.note_id),
+            format=ExportFormat.html,
+            options=ExportOptions(include_metadata=True),
+        )
+        job = await export_service.create_export(request)
+        return await export_service.wait_for_export(job.job_id)
+
+    finished = asyncio.run(_go())
+    assert finished.status == ExportStatus.completed
+    assert finished.file is not None
+    assert finished.file.file_name == "操作系统复习.html"
+    content = (get_settings().exports_path / f"{finished.job_id}.html").read_text(encoding="utf-8")
+    assert "操作系统复习" in content
+    assert "进程调度" in content
+
+
+def test_export_pdf_unsupported() -> None:
+    with pytest.raises(ApiError) as exc:
+        asyncio.run(
+            export_service.create_export(_markdown_request("# x", format=ExportFormat.pdf))
+        )
+    assert exc.value.status_code == 400
+    assert exc.value.code == "EXPORT_FORMAT_UNSUPPORTED"
+
+
+def test_export_unknown_note_404() -> None:
+    request = ExportRequest(
+        source=ExportSource(type=ExportSourceType.note, note_id="note_missing"),
+        format=ExportFormat.html,
+    )
+    with pytest.raises(ApiError) as exc:
+        asyncio.run(export_service.create_export(request))
+    assert exc.value.status_code == 404
+    assert exc.value.code == "EXPORT_SOURCE_NOT_FOUND"
+
+
+def test_export_empty_markdown_invalid() -> None:
+    with pytest.raises(ApiError) as exc:
+        asyncio.run(export_service.create_export(_markdown_request("   ")))
+    assert exc.value.status_code == 400
+    assert exc.value.code == "EXPORT_OPTIONS_INVALID"
+
+
+def test_export_cancel_queued_job() -> None:
+    async def _go():
+        job = await export_service.create_export(_markdown_request("# x"))
+        cancelled = export_service.cancel_export(job.job_id)
+        assert cancelled is not None
+        return await export_service.wait_for_export(job.job_id)
+
+    finished = asyncio.run(_go())
+    assert finished.status == ExportStatus.cancelled
+    assert finished.file is None
+
+
+def test_export_file_expired_410() -> None:
+    async def _go():
+        job = await export_service.create_export(_markdown_request("# x"))
+        finished = await export_service.wait_for_export(job.job_id)
+        past = datetime.now(timezone.utc) - timedelta(hours=1)
+        export_service._jobs[job.job_id] = finished.model_copy(
+            update={"file": finished.file.model_copy(update={"expires_at": past})}
+        )
+        return job.job_id
+
+    job_id = asyncio.run(_go())
+    with pytest.raises(ApiError) as exc:
+        export_service.get_export_file(job_id)
+    assert exc.value.status_code == 410
+    assert exc.value.code == "EXPORT_FILE_EXPIRED"
+
+
+def test_export_list_and_get() -> None:
+    finished = _create_and_wait(_markdown_request("# 列表测试"))
+
+    items, total = export_service.list_exports(limit=50, offset=0)
+    assert total == 1
+    assert items[0].job_id == finished.job_id
+
+    got = export_service.get_export(finished.job_id)
+    assert got is not None and got.status == ExportStatus.completed
+
+    assert export_service.get_export("export_missing") is None
+
+
+# --------------------------------------------------------------------------- #
+# 契约校验
+# --------------------------------------------------------------------------- #
+def test_export_source_requires_matching_field() -> None:
+    with pytest.raises(ValidationError):
+        ExportSource(type=ExportSourceType.note, note_id=None)
+    with pytest.raises(ValidationError):
+        ExportSource(type=ExportSourceType.markdown, markdown=None)