fix(export): 为函数图像与导出产物增加资源上限
针对 PR 审阅「函数数量没有限制,可能生成数百 MB 的 SVG」: - parser: 单块 function-plot 表达式上限 _MAX_EXPRESSIONS=16,超限整块回退 - html: 单篇文档函数图像上限 _MAX_FUNCTION_PLOTS=16,超出回退源码占位 - service: 输入源 MAX_MARKDOWN_CHARS、产物 MAX_EXPORT_BYTES,超限分别 拒绝创建或标记 failed(EXPORT_OUTPUT_TOO_LARGE) - 补充 4 条回归测试与文档说明 Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
@@ -22,6 +22,9 @@ _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"})
|
||||
|
||||
# 单篇文档允许的函数图像数量上限,超出部分回退占位,防止多图块并发采样耗尽内存/线程
|
||||
_MAX_FUNCTION_PLOTS = 16
|
||||
|
||||
|
||||
def _safe_url(url: str) -> str | None:
|
||||
"""校验 URL 协议;安全返回原串,不安全返回 None。"""
|
||||
@@ -69,6 +72,7 @@ class HtmlExporter:
|
||||
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
|
||||
self._plot_count = 0
|
||||
warnings: list[str] = []
|
||||
body = self._render_children(document.children, warnings)
|
||||
content = self._assemble(document, options, body, warnings)
|
||||
@@ -203,6 +207,13 @@ class HtmlExporter:
|
||||
return f"函数图像:{diag.message}{loc}"
|
||||
|
||||
def _render_function_plot(self, node: DocumentNode, warnings: list[str]) -> str:
|
||||
# 文档级数量上限:超出部分直接回退占位,不解析不采样,防止海量图像耗尽资源
|
||||
self._plot_count += 1
|
||||
if self._plot_count > _MAX_FUNCTION_PLOTS:
|
||||
warnings.append(
|
||||
f"函数图像:文档内函数图像数量超过上限 {_MAX_FUNCTION_PLOTS},已回退为源码占位"
|
||||
)
|
||||
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
|
||||
# 解析与渲染共同纳入局部异常回退:单个图像失败只回退占位 + warning,
|
||||
# 绝不阻断整篇导出(含复杂表达式触发的 RecursionError 等异常)。
|
||||
try:
|
||||
|
||||
@@ -39,8 +39,10 @@ _jobs: dict[str, ExportJob] = {}
|
||||
_tasks: dict[str, asyncio.Task] = {}
|
||||
_cancel_flags: dict[str, asyncio.Event] = {}
|
||||
MAX_JOBS = 100
|
||||
# markdown 源大小上限,防止未保存预览塞爆内存/产物
|
||||
# 输入源(note / markdown)统一大小上限,防止未保存预览或超长笔记塞爆内存/产物
|
||||
MAX_MARKDOWN_CHARS = 200_000
|
||||
# 最终导出产物大小上限,防止超大 HTML 耗尽内存/磁盘
|
||||
MAX_EXPORT_BYTES = 20 * 1024 * 1024 # 20 MB
|
||||
# 产物有效期
|
||||
FILE_TTL = timedelta(hours=24)
|
||||
|
||||
@@ -51,6 +53,10 @@ class ExportCancelled(Exception):
|
||||
"""导出在渲染前被取消时抛出,用于标记 cancelled。"""
|
||||
|
||||
|
||||
class ExportTooLarge(Exception):
|
||||
"""导出产物超过大小上限时抛出,用于标记 failed 并携带专用错误码。"""
|
||||
|
||||
|
||||
def _now() -> datetime:
|
||||
return datetime.now(timezone.utc)
|
||||
|
||||
@@ -123,6 +129,13 @@ async def _resolve_source(source: ExportSource) -> tuple[str, str, dict | None]:
|
||||
"note not found",
|
||||
{"note_id": source.note_id},
|
||||
)
|
||||
if len(note.markdown) > MAX_MARKDOWN_CHARS:
|
||||
raise ApiError(
|
||||
400,
|
||||
"EXPORT_OPTIONS_INVALID",
|
||||
f"note source exceeds {MAX_MARKDOWN_CHARS} characters",
|
||||
{"size": len(note.markdown), "limit": MAX_MARKDOWN_CHARS},
|
||||
)
|
||||
metadata = {
|
||||
"file_path": note.file_path,
|
||||
"tags": note.tags,
|
||||
@@ -210,6 +223,8 @@ async def _execute(
|
||||
result = await asyncio.to_thread(_render_document, document, options)
|
||||
if cancel_event.is_set():
|
||||
raise ExportCancelled()
|
||||
if len(result.content) > MAX_EXPORT_BYTES:
|
||||
raise ExportTooLarge()
|
||||
|
||||
out_dir = get_settings().exports_path
|
||||
out_dir.mkdir(parents=True, exist_ok=True)
|
||||
@@ -241,6 +256,15 @@ async def _execute(
|
||||
"completed_at": _now(),
|
||||
}
|
||||
)
|
||||
except ExportTooLarge:
|
||||
_jobs[job_id] = _jobs[job_id].model_copy(
|
||||
update={
|
||||
"status": ExportStatus.failed,
|
||||
"error": "Export output exceeds size limit.",
|
||||
"error_code": "EXPORT_OUTPUT_TOO_LARGE",
|
||||
"completed_at": _now(),
|
||||
}
|
||||
)
|
||||
except Exception as exc: # 渲染失败不拖垮服务,只记日志与项目错误码
|
||||
logger.exception("Export failed: job_id=%s", job_id)
|
||||
_jobs[job_id] = _jobs[job_id].model_copy(
|
||||
|
||||
@@ -51,6 +51,8 @@ _NUMBER_RE = re.compile(r"^(\d+\.?\d*|\.\d+)([eE][+-]?\d+)?$")
|
||||
# 用白名单校验提前拦截,保证失败走正常诊断路径而不是异常逃逸出导出链路。
|
||||
_MAX_AST_DEPTH = 200
|
||||
_MAX_AST_NODES = 1000
|
||||
# 单块 function-plot 允许的表达式数量上限,防止海量表达式导致超大 SVG 与海量采样求值
|
||||
_MAX_EXPRESSIONS = 16
|
||||
|
||||
|
||||
class PlotParseError(Exception):
|
||||
@@ -368,6 +370,16 @@ def parse_source(source: str) -> FunctionPlotParseResult:
|
||||
has_error = True
|
||||
continue
|
||||
expressions.append(FunctionPlotExpression(expression=expr_text))
|
||||
# 表达式数量超限:整块回退并提前终止,避免对海量表达式做采样求值
|
||||
if len(expressions) > _MAX_EXPRESSIONS:
|
||||
diagnostics.append(
|
||||
PlotDiagnostic(
|
||||
severity="error",
|
||||
code="FUNCTION_PLOT_TOO_MANY_EXPRESSIONS",
|
||||
message=f"表达式数量超过上限 {_MAX_EXPRESSIONS},已回退为源码占位",
|
||||
)
|
||||
)
|
||||
return FunctionPlotParseResult(plot=None, diagnostics=diagnostics)
|
||||
|
||||
if has_error:
|
||||
return FunctionPlotParseResult(plot=None, diagnostics=diagnostics)
|
||||
|
||||
Reference in New Issue
Block a user