JiriUhlirandClaude Opus 5
156289fe2d
Sluzba prijme adresu HTML dokumentu nebo HTML v tele requestu a vrati PDF. Navrzena pro dokumenty o stovkach az tisicich stranek. Rendering: - WeasyPrint jako vychozi engine, spravne CSS Paged Media, nizka pametova narocnost, bez JavaScriptu - Chromium pres Playwright pro dokumenty dokreslovane skripty - rezim auto s detekci skriptu a fallbackem pri selhani WeasyPrintu Velke dokumenty: - deleni na casti na strukturalnich hranicich, rez nikdy uvnitr tabulky nebo odstavce - dvoupruchodovy render obsahu se skutecnymi cisly stranek, pozice nadpisu se ctou z kotev hlasenych u kazde stranky - cislovani stranek bud pres CSS countery, nebo pres cislovaci vrstvu nastampovanou na hotove PDF, rozmer stranky se cte z vysledneho souboru - Chromium se restartuje po N jobech, nikdy vsak behem beziciho renderu API: - POST /convert synchronne, POST /jobs asynchronne se sledovanim stavu, stahovanim vysledku, rusenim a volitelnym callbackem - GET /health s overenim dostupnosti obou enginu a stavem fronty - OpenAPI respektuje prefix reverse proxy pres root_path Bezpecnost a provoz: - SSRF kontrola po DNS resolvu, na kazdem presmerovani a u vsech pozadavku prohlizece - nedostupne assety render nezastavi, ale hlasi se v odpovedi i v logu - fronta s omezenym poctem workeru, rozpracovane joby se pri ukonceni oznaci jako failed, nezmizi potichu - strukturovane JSON logovani s job_id - vsechny limity vypnute ve vychozim stavu Dockerfile je dvoufazovy, obsahuje zavislosti WeasyPrintu, Chromium a fonty s ceskou diakritikou. Autentizace zamerne neni implementovana, zpusob predavani neni domluveny. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
79 lines
2.5 KiB
Python
79 lines
2.5 KiB
Python
"""Synchronous conversion.
|
|
|
|
Suitable for smaller documents. Anything that does not finish within
|
|
SYNC_TIMEOUT_SECONDS is cancelled and the caller is pointed at /jobs.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import logging
|
|
|
|
from fastapi import APIRouter, Response
|
|
from fastapi.responses import FileResponse
|
|
from starlette.background import BackgroundTask
|
|
|
|
from ..deps import get_container
|
|
from ..errors import ConversionError, SyncTooLongError, error_from_code
|
|
from ..models import ConvertRequest
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(tags=["konverze"])
|
|
|
|
|
|
@router.post(
|
|
"/convert",
|
|
summary="Synchronni prevod HTML na PDF",
|
|
response_class=Response,
|
|
responses={
|
|
200: {"content": {"application/pdf": {}}, "description": "Hotove PDF."},
|
|
413: {"description": "Konverze trvala dele nez limit, pouzijte POST /jobs."},
|
|
},
|
|
)
|
|
async def convert(request: ConvertRequest):
|
|
container = get_container()
|
|
settings = container.settings
|
|
manager = container.jobs
|
|
|
|
job = manager.submit(request)
|
|
|
|
try:
|
|
await asyncio.wait_for(job.done.wait(), timeout=settings.sync_timeout_seconds)
|
|
except asyncio.TimeoutError as exc:
|
|
manager.cancel(job.id)
|
|
logger.warning(
|
|
"Synchronous conversion exceeded its budget",
|
|
extra={"job_id": job.id, "limit_seconds": settings.sync_timeout_seconds},
|
|
)
|
|
raise SyncTooLongError(
|
|
"Konverze presahla limit pro synchronni pozadavek. Pouzijte asynchronni endpoint POST /jobs.",
|
|
{"limit_seconds": settings.sync_timeout_seconds},
|
|
) from exc
|
|
|
|
if job.state.status != "done":
|
|
error = job.state.error
|
|
if error is not None:
|
|
raise error_from_code(error.error_code, error.message, error.detail)
|
|
raise ConversionError("Konverze skoncila ve stavu " + job.state.status + ".")
|
|
|
|
path = container.storage.result_path(job.id)
|
|
filename = request.filename or "dokument.pdf"
|
|
|
|
headers = {
|
|
"X-Page-Count": str(job.state.page_count or 0),
|
|
"X-Engine-Used": job.state.engine_used or "",
|
|
}
|
|
if job.state.missing_assets:
|
|
headers["X-Missing-Assets"] = str(len(job.state.missing_assets))
|
|
if job.state.warnings:
|
|
headers["X-Warnings"] = str(len(job.state.warnings))
|
|
|
|
return FileResponse(
|
|
path,
|
|
media_type="application/pdf",
|
|
filename=filename,
|
|
headers=headers,
|
|
background=BackgroundTask(container.storage.discard, job.id),
|
|
)
|