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。
This commit is contained in:
yxx
2026-09-04 09:02:33 +08:00
parent 2e496462a9
commit 5c2441464d
18 changed files with 1358 additions and 17 deletions
+272
View File
@@ -0,0 +1,272 @@
"""Export 服务:任务注册表、后台渲染、取消与产物生命周期。
与 Benchmark 一致采用「创建即返回 queued、后台 Task 异步执行」的内存模型:任务与产物
暂存内存与 exports 目录,不持久化到 SQLite。导出是单阶段渲染,无 SSE 事件流,取消主要
在渲染前/后让出执行权的边界生效;产物带 24h 过期时间,过期后不可下载。
"""
from __future__ import annotations
import asyncio
import hashlib
import logging
import re
from datetime import datetime, timedelta, timezone
from pathlib import Path
from uuid import uuid4
from app.config import get_settings
from app.contracts import (
ExportFile,
ExportFormat,
ExportJob,
ExportOptions,
ExportProgress,
ExportRequest,
ExportSource,
ExportSourceType,
ExportStatus,
)
from app.errors import ApiError
from app.export.document import Document
from app.export.exporters.html import HtmlExporter
from app.export.markdown import parse_document
from app.services import note_service
logger = logging.getLogger(__name__)
_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
MAX_MARKDOWN_CHARS = 200_000
# 产物有效期
FILE_TTL = timedelta(hours=24)
_INVALID_FILE_CHARS = re.compile(r'[\\/:*?"<>|]')
class ExportCancelled(Exception):
"""导出在渲染前被取消时抛出,用于标记 cancelled。"""
def _now() -> datetime:
return datetime.now(timezone.utc)
def _safe_download_name(title: str) -> str:
"""清洗标题得到安全的下载文件名;空标题回退到 export。"""
name = _INVALID_FILE_CHARS.sub("_", title).strip() or "export"
return name[:80]
def _forget(job_id: str) -> None:
_jobs.pop(job_id, None)
_tasks.pop(job_id, None)
_cancel_flags.pop(job_id, None)
def _evict_terminal() -> bool:
"""超过容量时淘汰最旧的终态任务;全为活动任务无法淘汰时返回 False。"""
terminal = (ExportStatus.completed, ExportStatus.failed, ExportStatus.cancelled)
while len(_jobs) >= MAX_JOBS:
victim = next((jid for jid, job in _jobs.items() if job.status in terminal), None)
if victim is None:
return False
_forget(victim)
return True
async def _resolve_source(source: ExportSource) -> tuple[str, str, dict | None]:
"""把导出源解析为 (markdown, title, metadata)metadata 仅 note 源提供。"""
if source.type == ExportSourceType.note:
note = await note_service.get_note(source.note_id)
if note is None:
raise ApiError(
404,
"EXPORT_SOURCE_NOT_FOUND",
"note not found",
{"note_id": source.note_id},
)
metadata = {
"file_path": note.file_path,
"tags": note.tags,
"created_at": note.created_at,
"updated_at": note.updated_at,
}
return note.markdown, note.title, metadata
markdown = source.markdown or ""
if not markdown.strip():
raise ApiError(400, "EXPORT_OPTIONS_INVALID", "markdown source must not be empty")
if len(markdown) > MAX_MARKDOWN_CHARS:
raise ApiError(
400,
"EXPORT_OPTIONS_INVALID",
f"markdown source exceeds {MAX_MARKDOWN_CHARS} characters",
{"size": len(markdown), "limit": MAX_MARKDOWN_CHARS},
)
return markdown, "", None
async def create_export(request: ExportRequest) -> ExportJob:
"""创建导出任务,立即返回 queued 的 ExportJob,由后台 Task 渲染。"""
if request.format != ExportFormat.html:
raise ApiError(
400,
"EXPORT_FORMAT_UNSUPPORTED",
"PDF/DOCX 暂未实现,当前仅支持 HTML",
{"format": request.format.value},
)
markdown, title, metadata = await _resolve_source(request.source)
if not _evict_terminal():
raise ApiError(
429,
"EXPORT_CAPACITY_EXCEEDED",
"Export capacity exceeded; wait for active jobs to finish.",
{},
)
job_id = "export_" + uuid4().hex[:12]
job = ExportJob(
job_id=job_id,
status=ExportStatus.queued,
format=request.format,
created_at=_now(),
)
_jobs[job_id] = job
_cancel_flags[job_id] = asyncio.Event()
_tasks[job_id] = asyncio.create_task(
_execute(job_id, markdown, title, metadata, request.options)
)
return job
async def _execute(
job_id: str,
markdown: str,
title: str,
metadata: dict | None,
options: ExportOptions,
) -> None:
"""后台渲染:解析 → 导出 → 写文件 → 挂载产物元信息。"""
cancel_event = _cancel_flags[job_id]
_jobs[job_id] = _jobs[job_id].model_copy(
update={
"status": ExportStatus.running,
"started_at": _now(),
"progress": ExportProgress(phase="rendering", current=0, total=1, percent=0.0),
}
)
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()
document = parse_document(markdown)
document.attributes["title"] = title
if metadata:
document.attributes["metadata"] = metadata
exporter = HtmlExporter()
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.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,
}
)
except ExportCancelled:
_jobs[job_id] = _jobs[job_id].model_copy(
update={
"status": ExportStatus.cancelled,
"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(
update={
"status": ExportStatus.failed,
"error": "Export render failed.",
"error_code": "EXPORT_RENDER_FAILED",
"completed_at": _now(),
}
)
finally:
_cancel_flags.pop(job_id, None)
def list_exports(
status: ExportStatus | None = None,
format: ExportFormat | None = None,
limit: int = 50,
offset: int = 0,
) -> tuple[list[ExportJob], int]:
jobs = list(_jobs.values())
if status is not None:
jobs = [j for j in jobs if j.status == status]
if format is not None:
jobs = [j for j in jobs if j.format == format]
jobs.sort(key=lambda j: j.created_at, reverse=True)
total = len(jobs)
return jobs[offset : offset + limit], total
def get_export(job_id: str) -> ExportJob | None:
return _jobs.get(job_id)
def cancel_export(job_id: str) -> ExportJob | None:
"""取消导出:仅 queued/running 可取消,后台 Task 在让出边界标记 cancelled。"""
job = _jobs.get(job_id)
if job is None:
return None
if job.status in (ExportStatus.queued, ExportStatus.running):
_cancel_flags[job_id].set()
return job
def get_export_file(job_id: str) -> Path:
"""返回可下载产物的存储路径;未完成返回 404、过期返回 410。"""
job = _jobs.get(job_id)
if job is None:
raise ApiError(404, "EXPORT_JOB_NOT_FOUND", "export job not found", {"job_id": job_id})
if job.status != ExportStatus.completed or job.file is None:
raise ApiError(
404, "EXPORT_JOB_NOT_FOUND", "export file not ready", {"job_id": job_id}
)
if job.file.expires_at <= _now():
raise ApiError(410, "EXPORT_FILE_EXPIRED", "export file has expired", {"job_id": job_id})
return get_settings().exports_path / f"{job_id}.html"
async def wait_for_export(job_id: str) -> ExportJob | None:
"""等待后台任务结束(测试/轮询用);无任务时直接返回当前状态。"""
task = _tasks.get(job_id)
if task is not None:
await task
return _jobs.get(job_id)