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>
70 lines
1.8 KiB
Python
70 lines
1.8 KiB
Python
"""HTTP surface of the service."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
from fastapi.testclient import TestClient
|
|
|
|
from app.main import app
|
|
|
|
|
|
@pytest.fixture
|
|
def client():
|
|
with TestClient(app) as test_client:
|
|
yield test_client
|
|
|
|
|
|
def test_health_is_available(client) -> None:
|
|
response = client.get("/health")
|
|
|
|
assert response.status_code == 200
|
|
body = response.json()
|
|
assert body["status"] in ("ok", "degraded")
|
|
assert "engines" in body
|
|
|
|
|
|
def test_version_reports_the_application(client) -> None:
|
|
response = client.get("/version")
|
|
|
|
assert response.status_code == 200
|
|
assert response.json()["language"] == "python"
|
|
|
|
|
|
def test_openapi_is_generated(client) -> None:
|
|
response = client.get("/openapi.json")
|
|
|
|
assert response.status_code == 200
|
|
paths = response.json()["paths"]
|
|
assert "/convert" in paths
|
|
assert "/jobs" in paths
|
|
assert "/jobs/{job_id}/result" in paths
|
|
|
|
|
|
def test_source_requires_exactly_one_input(client) -> None:
|
|
response = client.post(
|
|
"/convert",
|
|
json={"source": {"url": "https://example.com/a.html", "html": "<html></html>"}},
|
|
)
|
|
|
|
assert response.status_code == 422
|
|
|
|
|
|
def test_empty_source_is_rejected(client) -> None:
|
|
response = client.post("/convert", json={"source": {}})
|
|
|
|
assert response.status_code == 422
|
|
|
|
|
|
def test_private_address_is_refused(client) -> None:
|
|
response = client.post("/convert", json={"source": {"url": "http://127.0.0.1:8000/a.html"}})
|
|
|
|
assert response.status_code == 400
|
|
assert response.json()["error_code"] == "blocked_target"
|
|
|
|
|
|
def test_unknown_job_returns_404(client) -> None:
|
|
response = client.get("/jobs/00000000-0000-0000-0000-000000000000")
|
|
|
|
assert response.status_code == 404
|
|
assert response.json()["error_code"] == "job_not_found"
|