feat(export): 多格式后台导出、主题与警告框渲染 #43

Merged
Kronecker merged 21 commits from feat/export-service into main 2026-09-07 01:38:36 +08:00
7 changed files with 130 additions and 41 deletions
Showing only changes of commit c9c5f81d49 - Show all commits
+11
View File
@@ -24,6 +24,9 @@ _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
# 单篇文档允许的函数图像累计 AST 节点预算,超出部分回退占位,防止组合复杂度(多图块
# × 多表达式 × 深表达式)在采样求值时长时间占满 CPU
_MAX_TOTAL_PLOT_NODES = 8000
def _safe_url(url: str) -> str | None:
@@ -73,6 +76,7 @@ class HtmlExporter:
"""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
self._plot_nodes = 0
warnings: list[str] = []
body = self._render_children(document.children, warnings)
content = self._assemble(document, options, body, warnings)
@@ -222,6 +226,13 @@ class HtmlExporter:
warnings.append(self._format_plot_diagnostic(diag))
if parsed.plot is None:
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
# 文档级累计复杂度预算:超出后回退占位,不再采样求值
if self._plot_nodes + parsed.plot.node_count > _MAX_TOTAL_PLOT_NODES:
warnings.append(
f"函数图像:文档内函数图像累计复杂度超过上限 {_MAX_TOTAL_PLOT_NODES} 节点,已回退为源码占位"
)
return f'<pre class="function-plot">{html.escape(node.text)}</pre>'
self._plot_nodes += parsed.plot.node_count
rendered = render_svg(parsed.plot)
except Exception as exc:
warnings.append(f"函数图像:解析或渲染失败,已回退占位({exc}")
+44 -37
View File
@@ -43,6 +43,10 @@ MAX_JOBS = 100
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
# 并发渲染上限:解析/渲染是 CPU 密集的同步工作,限制同时执行的任务数,
# 防止大量任务同时占满工作线程与内存
MAX_CONCURRENT_RENDERS = 2
_render_slots = asyncio.Semaphore(MAX_CONCURRENT_RENDERS)
# 产物有效期
FILE_TTL = timedelta(hours=24)
@@ -208,47 +212,50 @@ async def _execute(
}
)
try:
# 让出一次,使「创建后立即取消」的 queued 任务能及时进入 cancelled
await asyncio.sleep(0)
if cancel_event.is_set():
raise ExportCancelled()
# 并发渲染限额:解析/渲染是 CPU 密集的同步工作,用信号量限制同时执行的任务数,
# 超出限额的任务在此排队等待,避免大量任务同时占满工作线程与内存
async with _render_slots:
# 让出一次,使「创建后立即取消」的 queued 任务能及时进入 cancelled
await asyncio.sleep(0)
if cancel_event.is_set():
raise ExportCancelled()
# 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
# 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
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()
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)
path = _export_path(job_id)
path.write_bytes(result.content)
out_dir = get_settings().exports_path
out_dir.mkdir(parents=True, exist_ok=True)
path = _export_path(job_id)
path.write_bytes(result.content)
completed_at = _now()
_jobs[job_id] = _jobs[job_id].model_copy(
update={
"status": ExportStatus.completed,
"progress": ExportProgress(
phase="completed", current=1, total=1, percent=1.0
),
"file": ExportFile(
file_name=f"{_safe_download_name(title)}.html",
mime_type=result.mime_type,
size=len(result.content),
sha256=hashlib.sha256(result.content).hexdigest(),
expires_at=completed_at + FILE_TTL,
),
"warnings": result.warnings,
"completed_at": completed_at,
}
)
completed_at = _now()
_jobs[job_id] = _jobs[job_id].model_copy(
update={
"status": ExportStatus.completed,
"progress": ExportProgress(
phase="completed", current=1, total=1, percent=1.0
),
"file": ExportFile(
file_name=f"{_safe_download_name(title)}.html",
mime_type=result.mime_type,
size=len(result.content),
sha256=hashlib.sha256(result.content).hexdigest(),
expires_at=completed_at + FILE_TTL,
),
"warnings": result.warnings,
"completed_at": completed_at,
}
)
except ExportCancelled:
_jobs[job_id] = _jobs[job_id].model_copy(
update={
+2
View File
@@ -31,6 +31,8 @@ class FunctionPlot(BaseModel):
domain: tuple[float, float] = (-10.0, 10.0)
range: tuple[float, float] | None = None
axes: PlotAxes = Field(default_factory=PlotAxes)
# 该块所有表达式 AST 节点数之和,供导出器做文档级累计复杂度预算
node_count: int = 0
class PlotDiagnostic(BaseModel):
+11 -1
View File
@@ -215,6 +215,13 @@ def parse_expression(expr: str) -> ast.Expression:
return tree
def _count_nodes(node: ast.AST) -> int:
"""统计已通过校验的表达式 AST 节点数,供文档级累计复杂度预算使用。"""
counter = [0]
_check_node(node, counter=counter)
return counter[0]
def evaluate(expr_ast: ast.Expression, x: float) -> float:
"""递归解释已校验 AST 得到数值,全程不编译/执行代码。"""
return _eval_node(expr_ast.body, x)
@@ -282,6 +289,7 @@ def parse_source(source: str) -> FunctionPlotParseResult:
ylabel: str | None = None
grid: bool = True
has_error = False
total_nodes = 0
for lineno, raw_line in enumerate(source.splitlines(), start=1):
line = raw_line.strip()
@@ -363,12 +371,13 @@ def parse_source(source: str) -> FunctionPlotParseResult:
continue
try:
parse_expression(expr_text)
tree = parse_expression(expr_text)
except PlotParseError as exc:
exc.diagnostic.line = lineno
diagnostics.append(exc.diagnostic)
has_error = True
continue
total_nodes += _count_nodes(tree.body)
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:
@@ -398,5 +407,6 @@ def parse_source(source: str) -> FunctionPlotParseResult:
domain=domain,
range=range_,
axes=PlotAxes(xlabel=xlabel, ylabel=ylabel, grid=grid),
node_count=total_nodes,
)
return FunctionPlotParseResult(plot=plot, diagnostics=diagnostics)
+34
View File
@@ -449,3 +449,37 @@ def test_export_output_too_large(monkeypatch) -> None:
assert finished.error_code == "EXPORT_OUTPUT_TOO_LARGE"
assert finished.file is None
assert not (get_settings().exports_path / f"{finished.job_id}.html").exists()
def test_export_limits_concurrent_rendering(monkeypatch) -> None:
# P1:并发渲染受 MAX_CONCURRENT_RENDERS 限制,大量任务不会同时占满工作线程
import threading
import time
real_render = export_service._render_document
active = 0
peak = 0
lock = threading.Lock()
def slow_render(document, options):
nonlocal active, peak
with lock:
active += 1
peak = max(peak, active)
time.sleep(0.05)
with lock:
active -= 1
return real_render(document, options)
monkeypatch.setattr(export_service, "_render_document", slow_render)
async def _go():
jobs = [
await export_service.create_export(_markdown_request(f"# t{i}"))
for i in range(6)
]
return [await export_service.wait_for_export(j.job_id) for j in jobs]
finished = asyncio.run(_go())
assert all(j.status == ExportStatus.completed for j in finished)
assert peak <= export_service.MAX_CONCURRENT_RENDERS
+14
View File
@@ -269,3 +269,17 @@ def test_html_exporter_limits_function_plot_count() -> None:
assert html.count('<figure class="function-plot">') == 16
assert html.count('<pre class="function-plot">') == 4
assert any("函数图像数量超过上限" in w for w in result.warnings)
def test_html_exporter_limits_total_plot_nodes(monkeypatch) -> None:
# P1:文档级累计 AST 节点预算超限后,后续图像回退占位,防止组合复杂度耗尽 CPU
import app.export.exporters.html as html_mod
monkeypatch.setattr(html_mod, "_MAX_TOTAL_PLOT_NODES", 5)
# 第一个图块 y=x(1 节点)在预算内;第二个图块 y=x+x+x+x(7 节点)累计超限
md = "```function-plot\ny = x\n```\n\n```function-plot\ny = x + x + x + x\n```"
result = asyncio.run(HtmlExporter().export(parse_document(md), ExportOptions()))
html = result.content.decode("utf-8")
assert html.count('<figure class="function-plot">') == 1
assert html.count('<pre class="function-plot">') == 1
assert any("累计复杂度" in w for w in result.warnings)
+14 -3
View File
@@ -63,20 +63,31 @@ fenced code 按语言分流:`mermaid` → `mermaid` 节点、`function_plot`/`
- 输入源(`note``markdown`)统一限制 `MAX_MARKDOWN_CHARS = 200_000` 字符,超限返回 `EXPORT_OPTIONS_INVALID`
- 单个 `function-plot` 图块最多 16 条表达式,超限整块回退占位并记结构化诊断 `FUNCTION_PLOT_TOO_MANY_EXPRESSIONS`
- 单篇文档最多 16 个函数图像,超出部分回退占位并记 warning。
- 单篇文档累计函数图像 AST 节点预算 `_MAX_TOTAL_PLOT_NODES = 8000`,超出部分回退占位并记 warning,防止多图块 × 多表达式 × 深表达式组合在采样求值时长时间占满 CPU。
- 并发渲染上限 `MAX_CONCURRENT_RENDERS = 2`,解析/渲染是 CPU 密集工作,超出限额的任务在内存中排队等待渲染槽位,避免大量任务同时占满工作线程与内存。
- 最终产物大小上限 `MAX_EXPORT_BYTES = 20 MB`,超限任务标记 failed 并返回 `EXPORT_OUTPUT_TOO_LARGE`
## 错误码
错误分两类:**同步错误**在创建/查询请求的 HTTP 响应里直接返回对应状态码;**异步任务错误**在创建时已返回 `202`,后续轮询 `GET /api/exports/{job_id}` 仍返回 `200`,错误通过任务状态与 `error_code` 字段暴露,**不映射 HTTP 状态码**。
同步错误:
```text
EXPORT_SOURCE_NOT_FOUND 404
EXPORT_FORMAT_UNSUPPORTED 400
EXPORT_OPTIONS_INVALID 400
EXPORT_RENDER_FAILED 500
EXPORT_UNSUPPORTED_CONTENT 422
EXPORT_UNSUPPORTED_CONTENT 422(预留)
EXPORT_JOB_NOT_FOUND 404
EXPORT_FILE_EXPIRED 410
EXPORT_CAPACITY_EXCEEDED 429
EXPORT_OUTPUT_TOO_LARGE 413
```
异步任务错误(轮询返回 `200`,字段形如 `{"status": "failed", "error_code": "..."}`):
```text
EXPORT_RENDER_FAILED
EXPORT_OUTPUT_TOO_LARGE
```
## 测试