Files
osint_web/tests/test_server.py
T
agent 5b51e3d035 feat: FastAPI backend (vault osint + agenda/calendario Xandikos)
Reescribe el backend a FastAPI + uvicorn y añade los endpoints DAV
(CardDAV/CalDAV) sobre el servidor Xandikos, además de las vistas del vault
osint de Obsidian.

Vault (grupo obsidian del registry):
- /api/graph, /api/nodes, /api/node/{slug}, /api/attachment, /api/search,
  /api/refresh. Allowlist estricta de path traversal en /api/attachment.
- Resolución de embeds por path relativo al vault y por basename (registry).

Xandikos (grupo dav del registry + pass_get_secret):
- /api/contacts, /api/contact/{uid} (CardDAV, parseo vCard a JSON).
- /api/calendar?from=&to= (CalDAV, parseo VEVENT a JSON, filtro por rango).
- Credencial vía pass dav/xandikos-enmanuel; degradación clara sin red (502/503).

Solo escucha en 127.0.0.1 (datos sensibles). 13 tests verdes (pytest).
frontend/README.md describe el montaje React+Vite+Mantine+sigma.js posterior.
2026-06-11 22:47:51 +02:00

253 lines
8.7 KiB
Python

"""Tests del backend osint_web.
Cubren el contrato del DoD del issue 0172 sin depender de la red (Xandikos):
- Path traversal en /api/attachment (seguridad obligatoria).
- Vault inexistente -> error claro al arrancar, no 500.
- Grafo / tablas filtradas por tipo / ficha con attachments sobre un vault
mínimo sintético construido en un tmpdir.
- Endpoints DAV: degradación clara (no crash) cuando Xandikos no responde, y
parseo vCard/iCalendar a JSON sin red.
Se usa el ``TestClient`` de Starlette/FastAPI sobre un vault temporal, así los
tests son herméticos y deterministas (no tocan el vault real con PII).
"""
import os
import sys
import pytest
from fastapi.testclient import TestClient
# El backend orquesta funciones del registry: hay que poder importarlas.
_HERE = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, os.path.join(_HERE, "..", "server"))
import main as srv # noqa: E402
# ---------------------------------------------------------------------------
# Fixtures: vault sintético mínimo
# ---------------------------------------------------------------------------
def _write(path: str, content: str) -> None:
os.makedirs(os.path.dirname(path), exist_ok=True)
with open(path, "w", encoding="utf-8") as f:
f.write(content)
@pytest.fixture()
def vault(tmp_path):
"""Construye un vault de Obsidian mínimo con personas, una org y un attachment."""
root = tmp_path / "osint"
# Una persona con foto embebida (por path) y un wikilink a una org y a una
# persona inexistente.
_write(
str(root / "personas" / "ana-gomez.md"),
"---\n"
"tipo: persona\n"
"nombre: Ana Gómez\n"
"dni: 12345678A\n"
"tags: [objetivo]\n"
"---\n\n"
"## Relaciones\n"
"- [[acme-sl]]\n"
"- [[Persona-Inexistente]]\n\n"
"## Documentos\n"
"![[attachments/personas/ana-gomez/ana-foto.jpg]]\n",
)
_write(
str(root / "organizaciones" / "acme-sl.md"),
"---\ntipo: organizacion\nnombre: Acme SL\ncif: B12345678\n---\n\nOrg de prueba.\n",
)
# El attachment embebido (basta un archivo cualquiera).
_write(str(root / "attachments" / "personas" / "ana-gomez" / "ana-foto.jpg"), "FAKEJPEGDATA")
# Un archivo secreto FUERA del vault, para el test de path traversal.
_write(str(tmp_path / "secret.txt"), "TOP SECRET")
return str(root)
@pytest.fixture()
def client(vault):
app = srv.create_app(vault)
return TestClient(app)
# ---------------------------------------------------------------------------
# Golden: grafo carga el vault
# ---------------------------------------------------------------------------
def test_graph_loads_vault(client):
resp = client.get("/api/graph")
assert resp.status_code == 200
data = resp.json()
# 2 notas reales (ana, acme) + 1 nodo fantasma (Persona-Inexistente).
ids = {n["id"] for n in data["nodes"]}
assert "ana-gomez" in ids
assert "acme-sl" in ids
assert data["total_edges"] >= 1
# Conteos por tipo presentes para la leyenda.
assert data["counts"].get("persona") == 1
assert data["counts"].get("organizacion") == 1
def test_node_card_with_attachments(client):
resp = client.get("/api/node/ana-gomez")
assert resp.status_code == 200
data = resp.json()
assert data["frontmatter"]["nombre"] == "Ana Gómez"
assert data["body"].strip() != ""
# La galería de attachments resuelve la foto embebida (por path).
foto = next(a for a in data["attachments"] if a["name"].endswith("ana-foto.jpg"))
assert foto["kind"] == "image"
assert foto["path"] # path relativo al vault, no vacío
# ---------------------------------------------------------------------------
# Edge: tabla filtrada por tipo
# ---------------------------------------------------------------------------
def test_nodes_filtered_by_tipo(client):
resp = client.get("/api/nodes", params={"tipo": "organizacion"})
assert resp.status_code == 200
data = resp.json()
assert data["count"] == 1
assert all(r["tipo"] == "organizacion" for r in data["rows"])
assert data["rows"][0]["id"] == "acme-sl"
# ---------------------------------------------------------------------------
# Edge: wikilink dangling -> nodo fantasma, sin crash
# ---------------------------------------------------------------------------
def test_dangling_wikilink_is_phantom(client):
data = client.get("/api/graph").json()
phantom_ids = {n["id"] for n in data["nodes"] if n.get("dangling")}
assert "persona-inexistente" in phantom_ids
# ---------------------------------------------------------------------------
# Edge: nombre con mayúsculas/acentos -> slug estable
# ---------------------------------------------------------------------------
def test_slugify_accents():
assert srv.slugify_obsidian_name("María del Mar") == "maria-del-mar"
# ---------------------------------------------------------------------------
# Error: path traversal en attachment (SEGURIDAD obligatoria)
# ---------------------------------------------------------------------------
def test_attachment_path_traversal_blocked(client):
resp = client.get("/api/attachment", params={"path": "../../etc/passwd"})
assert resp.status_code in (403, 404)
assert "root:" not in resp.text
resp2 = client.get("/api/attachment", params={"path": "../secret.txt"})
assert resp2.status_code in (403, 404)
assert "TOP SECRET" not in resp2.text
def test_attachment_legit_served(client):
rel = os.path.join("attachments", "personas", "ana-gomez", "ana-foto.jpg")
resp = client.get("/api/attachment", params={"path": rel})
assert resp.status_code == 200
assert resp.content == b"FAKEJPEGDATA"
def test_attachment_nonexistent_inside_vault_404(client):
resp = client.get("/api/attachment", params={"path": "attachments/no-existe.png"})
assert resp.status_code == 404
# ---------------------------------------------------------------------------
# Error: vault inexistente -> error claro al arrancar, no 500
# ---------------------------------------------------------------------------
def test_vault_inexistent_raises_clear_error():
with pytest.raises(FileNotFoundError):
srv.create_app("/no/existe/vault/osint")
# ---------------------------------------------------------------------------
# Búsqueda
# ---------------------------------------------------------------------------
def test_search_finds_node(client):
resp = client.get("/api/search", params={"q": "Ana"})
assert resp.status_code == 200
ids = {r["id"] for r in resp.json()["results"]}
assert "ana-gomez" in ids
# ---------------------------------------------------------------------------
# DAV: parseo a JSON (sin red) + degradación clara
# ---------------------------------------------------------------------------
def test_vcard_to_json():
vcard = (
"BEGIN:VCARD\r\n"
"VERSION:3.0\r\n"
"UID:abc-123\r\n"
"FN:Juan Pérez\r\n"
"NICKNAME:Juanito\r\n"
"ORG:Acme;Ventas\r\n"
"TEL;TYPE=CELL:+34600111222\r\n"
"EMAIL;TYPE=HOME:juan@example.com\r\n"
"NOTE:Contacto de prueba\r\n"
"END:VCARD\r\n"
)
out = srv._vcard_to_json(vcard)
assert out["uid"] == "abc-123"
assert out["fn"] == "Juan Pérez"
assert out["nickname"] == "Juanito"
assert out["org"] == "Acme Ventas"
assert out["phones"][0]["value"] == "+34600111222"
assert out["emails"][0]["value"] == "juan@example.com"
def test_vevent_to_json_and_range():
vcal = (
"BEGIN:VCALENDAR\r\n"
"BEGIN:VEVENT\r\n"
"UID:evt-1\r\n"
"SUMMARY:Reunión OSINT\r\n"
"DTSTART:20260615T090000Z\r\n"
"DTEND:20260615T100000Z\r\n"
"LOCATION:Oficina\r\n"
"END:VEVENT\r\n"
"END:VCALENDAR\r\n"
)
events = srv._vcalendar_to_events(vcal)
assert len(events) == 1
evt = events[0]
assert evt["summary"] == "Reunión OSINT"
assert evt["dtstart"].startswith("20260615")
assert srv._event_in_range(evt, "20260601", "20260630") is True
assert srv._event_in_range(evt, "20260101", "20260131") is False
def test_dav_endpoints_degrade_without_network(client, monkeypatch):
"""Sin Xandikos accesible los endpoints DAV devuelven error claro, no crash."""
monkeypatch.setattr(
srv, "dav_list_resources", lambda *a, **k: {"status": "error", "error": "sin red"}
)
# Evita leer pass en el test (cachea una password ficticia).
client.app.state.vault._xandikos_password = "x"
r1 = client.get("/api/contacts")
assert r1.status_code == 502
assert r1.json()["status"] == "error"
r2 = client.get("/api/calendar")
assert r2.status_code == 502
assert r2.json()["status"] == "error"