backend/app/export/exporters/html.py

@@ -8,12 +8,28 @@ from __future__ import annotations
 
 import html
 from datetime import datetime
+from urllib.parse import urlparse
 
 from app.contracts import ExportOptions
 from app.export.document import Document, DocumentNode, ExportResult
 
 _MERMAID_WARNING = "mermaid 需前端渲染，已保留为占位代码块"
 _FUNCTION_PLOT_WARNING = "函数图像渲染将在后续版本提供，已保留为占位代码块"
+_RAW_HTML_WARNING = "原始 HTML 已按纯文本转义保留"
+
+# 链接/图片地址允许的协议；无 scheme 的相对地址视为安全，其余协议一律降级
+_ALLOWED_URL_SCHEMES = frozenset({"http", "https", "mailto"})
+
+
+def _safe_url(url: str) -> str | None:
+    """校验 URL 协议；安全返回原串，不安全返回 None。"""
+    url = url.strip()
+    if not url:
+        return None
+    scheme = urlparse(url).scheme.lower()
+    if scheme and scheme not in _ALLOWED_URL_SCHEMES:
+        return None
+    return url
 
 _BASE_CSS = """
 body { margin: 0; background: #f6f7f9; color: #1f2328; font: 15px/1.7 -apple-system, 'Segoe UI', 'Microsoft YaHei', sans-serif; }
@@ -46,7 +62,8 @@ hr { border: none; border-top: 1px solid #d0d7de; margin: 1.4em 0; }
 class HtmlExporter:
     """实现 DocumentExporter：递归渲染 Document AST 为完整 HTML5 文档。"""
 
-    async def export(self, document: Document, options: ExportOptions) -> ExportResult:
+    def render(self, document: Document, options: ExportOptions) -> ExportResult:
+        """同步渲染；CPU 密集，调用方应放入线程执行，避免阻塞事件循环。"""
         self._options = options
         warnings: list[str] = []
         body = self._render_children(document.children, warnings)
@@ -55,6 +72,10 @@ class HtmlExporter:
             content=content.encode("utf-8"), mime_type="text/html", warnings=warnings
         )
 
+    async def export(self, document: Document, options: ExportOptions) -> ExportResult:
+        """契约要求的 async 接口；渲染本身同步，直接转发到 render。"""
+        return self.render(document, options)
+
     def _assemble(
         self, document: Document, options: ExportOptions, body: str, warnings: list[str]
     ) -> str:
@@ -179,6 +200,11 @@ class HtmlExporter:
     def _render_math_block(self, node: DocumentNode, warnings: list[str]) -> str:
         return f'<div class="math-block">$${html.escape(node.text)}$$</div>'
 
+    def _render_html_block(self, node: DocumentNode, warnings: list[str]) -> str:
+        # 原始 HTML 不可信，转义为纯文本展示，保证正文不丢且无注入风险
+        warnings.append(_RAW_HTML_WARNING)
+        return f'<div class="raw-html">{html.escape(node.text)}</div>'
+
     # --- 行内 ---
     def _render_text(self, node: DocumentNode, warnings: list[str]) -> str:
         return html.escape(node.text)
@@ -190,21 +216,32 @@ class HtmlExporter:
         return f"<strong>{self._render_children(node.children, warnings)}</strong>"
 
     def _render_link(self, node: DocumentNode, warnings: list[str]) -> str:
-        href = html.escape(str(node.attributes.get("href") or ""))
+        inner = self._render_children(node.children, warnings)
+        href = str(node.attributes.get("href") or "")
+        safe_href = _safe_url(href)
+        if safe_href is None:
+            # 危险协议（如 javascript:）降级为纯文本，不输出可点击链接
+            warnings.append(f"链接协议不安全，已降级为纯文本：{href!r}")
+            return inner
         title = str(node.attributes.get("title") or "")
-        attrs = [f'href="{href}"']
+        attrs = [f'href="{html.escape(safe_href)}"']
         if title:
             attrs.append(f'title="{html.escape(title)}"')
-        return f"<a {' '.join(attrs)}>{self._render_children(node.children, warnings)}</a>"
+        return f"<a {' '.join(attrs)}>{inner}</a>"
 
     def _render_codespan(self, node: DocumentNode, warnings: list[str]) -> str:
         return f"<code>{html.escape(node.text)}</code>"
 
     def _render_image(self, node: DocumentNode, warnings: list[str]) -> str:
-        src = html.escape(str(node.attributes.get("src") or ""))
+        src = str(node.attributes.get("src") or "")
-        alt = html.escape(str(node.attributes.get("alt") or ""))
+        alt = str(node.attributes.get("alt") or "")
+        safe_src = _safe_url(src)
+        if safe_src is None:
+            # 危险协议（如 data:/javascript:）跳过图片，仅输出 alt 文本
+            warnings.append(f"图片地址不安全，已跳过：{src!r}")
+            return html.escape(alt) if alt else ""
         title = str(node.attributes.get("title") or "")
-        attrs = [f'src="{src}"', f'alt="{alt}"']
+        attrs = [f'src="{html.escape(safe_src)}"', f'alt="{html.escape(alt)}"']
         if title:
             attrs.append(f'title="{html.escape(title)}"')
         return f"<img {' '.join(attrs)}>"

backend/app/export/markdown.py

@@ -15,7 +15,7 @@ _PLUGINS = ["table", "math", "url", "task_lists"]
 
 # fenced code 语言分流：命中则转为专用节点，其余按普通代码块
 _MERMAID_LANG = "mermaid"
-_FUNCTION_PLOT_LANGS = {"function_plot", "functionplot"}
+_FUNCTION_PLOT_LANGS = {"function-plot", "function_plot", "functionplot"}
 
 
 def parse_document(markdown: str) -> Document:
@@ -85,10 +85,19 @@ class _AstMapper:
             return DocumentNode(type="thematic_break", node_id=self.next_id())
         if kind == "blank_line":
             return None
-        # 未知块级 token（如 block_html）保守保留原文，避免静默丢失
+        if kind == "block_html":
+            # 原始 HTML 块降级为纯文本节点，由 HtmlExporter 转义并记 warning，避免静默丢失正文
+            return DocumentNode(
+                type="html_block", node_id=self.next_id(), text=token.get("raw", "")
+            )
+        # 未知块级 token 保守保留原文；映射为带 text 子节点的 paragraph，避免被渲染层丢弃
         raw = token.get("raw", "")
         if raw:
-            return DocumentNode(type="paragraph", node_id=self.next_id(), text=raw)
+            return DocumentNode(
+                type="paragraph",
+                node_id=self.next_id(),
+                children=[DocumentNode(type="text", node_id=self.next_id(), text=raw)],
+            )
         return None
 
     def map_list_item(self, token: dict) -> DocumentNode:
@@ -144,10 +153,16 @@ class _AstMapper:
         if kind == "codespan":
             return DocumentNode(type="codespan", node_id=self.next_id(), text=token.get("raw", ""))
         if kind == "image":
+            # mistune 图片 token：src 在 attrs.url，alt 来自 children 的文本，title 在 attrs.title
             attrs = token.get("attrs", {})
-            attributes = {"src": attrs.get("src", "")}
+            alt = "".join(
-            if attrs.get("alt"):
+                child.get("raw", "")
-                attributes["alt"] = attrs["alt"]
+                for child in token.get("children", [])
+                if child.get("type") == "text"
+            )
+            attributes = {"src": attrs.get("url", "")}
+            if alt:
+                attributes["alt"] = alt
             if attrs.get("title"):
                 attributes["title"] = attrs["title"]
             return DocumentNode(type="image", node_id=self.next_id(), attributes=attributes)

backend/app/export/service.py

@@ -28,7 +28,7 @@ from app.contracts import (
     ExportStatus,
 )
 from app.errors import ApiError
-from app.export.document import Document
+from app.export.document import Document, ExportResult
 from app.export.exporters.html import HtmlExporter
 from app.export.markdown import parse_document
 from app.services import note_service
@@ -61,10 +61,44 @@ def _safe_download_name(title: str) -> str:
     return name[:80]
 
 
+def _export_path(job_id: str) -> Path:
+    return get_settings().exports_path / f"{job_id}.html"
+
+
+def _delete_file(job_id: str) -> None:
+    """删除导出产物文件；文件不存在时忽略。"""
+    try:
+        _export_path(job_id).unlink(missing_ok=True)
+    except OSError:
+        logger.warning("Failed to delete export file: %s", job_id)
+
+
+def cleanup_orphan_files() -> int:
+    """清理 exports 目录下无对应内存任务的孤立产物（服务重启后调用）。"""
+    exports_dir = get_settings().exports_path
+    if not exports_dir.is_dir():
+        return 0
+    removed = 0
+    for path in exports_dir.glob("*.html"):
+        if path.stem not in _jobs:
+            try:
+                path.unlink()
+                removed += 1
+            except OSError:
+                logger.warning("Failed to delete orphan export file: %s", path)
+    return removed
+
+
+def _render_document(document: Document, options: ExportOptions) -> ExportResult:
+    """同步渲染辅助，供 asyncio.to_thread 调用；每次新建实例避免跨线程复用。"""
+    return HtmlExporter().render(document, options)
+
+
 def _forget(job_id: str) -> None:
     _jobs.pop(job_id, None)
     _tasks.pop(job_id, None)
     _cancel_flags.pop(job_id, None)
+    _delete_file(job_id)
 
 
 def _evict_terminal() -> bool:
@@ -166,19 +200,20 @@ async def _execute(
         if cancel_event.is_set():
             raise ExportCancelled()
 
-        document = parse_document(markdown)
+        # 解析与渲染都是 CPU 密集的同步工作，放入线程执行避免阻塞事件循环，
+        # 使运行中的取消能在渲染边界生效；写文件前再次检查取消。
+        document = await asyncio.to_thread(parse_document, markdown)
         document.attributes["title"] = title
         if metadata:
             document.attributes["metadata"] = metadata
 
-        exporter = HtmlExporter()
+        result = await asyncio.to_thread(_render_document, document, options)
-        result = await exporter.export(document, options)
         if cancel_event.is_set():
             raise ExportCancelled()
 
         out_dir = get_settings().exports_path
         out_dir.mkdir(parents=True, exist_ok=True)
-        path = out_dir / f"{job_id}.html"
+        path = _export_path(job_id)
         path.write_bytes(result.content)
 
         completed_at = _now()
@@ -260,8 +295,9 @@ def get_export_file(job_id: str) -> Path:
             404, "EXPORT_JOB_NOT_FOUND", "export file not ready", {"job_id": job_id}
         )
     if job.file.expires_at <= _now():
+        _forget(job_id)  # 过期即清理内存记录与产物文件
         raise ApiError(410, "EXPORT_FILE_EXPIRED", "export file has expired", {"job_id": job_id})
-    return get_settings().exports_path / f"{job_id}.html"
+    return _export_path(job_id)
 
 
 async def wait_for_export(job_id: str) -> ExportJob | None:

backend/app/main.py

@@ -8,6 +8,7 @@ from starlette.exceptions import HTTPException as StarletteHttpException
 from app.config import get_settings
 from app.container import container
 from app.errors import ApiError, api_error_handler, http_error_handler, validation_error_handler
+from app.export import service as export_service
 from app.routes import router as api_router
 from app.schemas import HealthResponse, ServiceStatusResponse
 
@@ -16,6 +17,8 @@ settings = get_settings()
 
 @asynccontextmanager
 async def lifespan(_: FastAPI):
+    # 重启后内存注册表为空，清理上一次运行遗留的导出产物，避免磁盘垃圾堆积。
+    export_service.cleanup_orphan_files()
     yield
     # 第三方 MCP Server 必须跟随 AI Core 退出，不能遗留孤儿进程。
     container.plugins.shutdown()

backend/tests/test_export.py

@@ -16,6 +16,7 @@ from pydantic import ValidationError
 from app.config import get_settings
 from app.contracts import (
     ExportFormat,
+    ExportJob,
     ExportOptions,
     ExportRequest,
     ExportSource,
@@ -133,6 +134,21 @@ def test_parse_document_table_and_math() -> None:
     assert "math_block" in kinds
 
 
+def test_parse_document_image_maps_src_alt_title() -> None:
+    doc = parse_document('![替代文本](https://a.b/img.png "标题")')
+    img = doc.children[0].children[0]
+    assert img.type == "image"
+    assert img.attributes["src"] == "https://a.b/img.png"
+    assert img.attributes["alt"] == "替代文本"
+    assert img.attributes["title"] == "标题"
+
+
+def test_parse_document_function_plot_dash_alias() -> None:
+    doc = parse_document("```function-plot\ny = x^2\n```")
+    assert doc.children[0].type == "function_plot"
+    assert doc.children[0].text == "y = x^2"
+
+
 # --------------------------------------------------------------------------- #
 # HtmlExporter
 # --------------------------------------------------------------------------- #
@@ -162,6 +178,38 @@ def test_html_exporter_marks_mermaid_and_function_plot() -> None:
     assert any("mermaid" in w for w in result.warnings)
 
 
+def test_html_exporter_rejects_unsafe_link_protocol() -> None:
+    result = asyncio.run(
+        HtmlExporter().export(parse_document("[点我](javascript:alert(1))"), ExportOptions())
+    )
+    html = result.content.decode("utf-8")
+    assert "javascript:" not in html
+    assert "点我" in html
+    assert any("不安全" in w for w in result.warnings)
+
+
+def test_html_exporter_rejects_unsafe_image_protocol() -> None:
+    result = asyncio.run(
+        HtmlExporter().export(parse_document("![alt](data:text/html,<script>)"), ExportOptions())
+    )
+    html = result.content.decode("utf-8")
+    assert "data:" not in html
+    assert "<img" not in html
+    assert "alt" in html
+    assert any("不安全" in w for w in result.warnings)
+
+
+def test_html_exporter_preserves_raw_html_block() -> None:
+    result = asyncio.run(
+        HtmlExporter().export(parse_document("<div>重要正文</div>"), ExportOptions())
+    )
+    html = result.content.decode("utf-8")
+    assert "重要正文" in html
+    assert "<div>" not in html
+    assert "&lt;div&gt;重要正文&lt;/div&gt;" in html
+    assert any("原始 HTML" 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"
@@ -274,10 +322,73 @@ def test_export_file_expired_410() -> None:
         return job.job_id
 
     job_id = asyncio.run(_go())
+    path = get_settings().exports_path / f"{job_id}.html"
     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"
+    assert not path.exists()  # 过期即清理产物文件
+    assert export_service.get_export(job_id) is None  # 内存记录一并清理
+
+
+def test_export_eviction_deletes_file() -> None:
+    finished = _create_and_wait(_markdown_request("# 淘汰"))
+    victim_path = get_settings().exports_path / f"{finished.job_id}.html"
+    assert victim_path.exists()
+
+    # 塞满 MAX_JOBS 个终态任务，下一次 create 会淘汰最旧的终态（finished 最先插入）
+    for i in range(export_service.MAX_JOBS):
+        export_service._jobs[f"export_fake_{i}"] = ExportJob(
+            job_id=f"export_fake_{i}",
+            status=ExportStatus.completed,
+            format=ExportFormat.html,
+            created_at=datetime.now(timezone.utc),
+        )
+    _create_and_wait(_markdown_request("# 触发淘汰"))
+    assert not victim_path.exists()
+
+
+def test_cleanup_orphan_files() -> None:
+    exports_dir = get_settings().exports_path
+    exports_dir.mkdir(parents=True, exist_ok=True)
+    orphan = exports_dir / "export_orphan.html"
+    orphan.write_text("stale", encoding="utf-8")
+
+    finished = _create_and_wait(_markdown_request("# 保留"))
+    keep_path = exports_dir / f"{finished.job_id}.html"
+    assert keep_path.exists()
+
+    removed = export_service.cleanup_orphan_files()
+    assert removed >= 1
+    assert not orphan.exists()
+    assert keep_path.exists()  # 仍在注册表中的任务文件保留
+
+
+def test_export_cancel_during_running(monkeypatch) -> None:
+    import threading
+    import time
+
+    real_parse = parse_document
+    started = threading.Event()
+
+    def slow_parse(markdown: str):
+        started.set()
+        time.sleep(0.1)
+        return real_parse(markdown)
+
+    monkeypatch.setattr(export_service, "parse_document", slow_parse)
+
+    async def _go():
+        job = await export_service.create_export(_markdown_request("# 运行中取消"))
+        while not started.is_set():
+            await asyncio.sleep(0)
+        export_service.cancel_export(job.job_id)
+        return await export_service.wait_for_export(job.job_id)
+
+    finished = asyncio.run(_go())
+    assert finished.status == ExportStatus.cancelled
+    assert finished.file is None
+    assert not (get_settings().exports_path / f"{finished.job_id}.html").exists()
 
 
 def test_export_list_and_get() -> None: