Files
graph_explorer/tests/test_vendor_script.py
T
egutierrez 7a94160fd2 feat: catch-up de decisiones previas (Webpage→Url, anti-bot, UI 2-col, tests cross-platform)
Bloque de cambios revisados y validados con el usuario en sesiones
previas que no habian aterrizado en commits propios. Lista por tema:

* enrichers: web_search ahora usa lite.duckduckgo.com como endpoint
  primario (mas tolerante con bot detection desde IP residencial),
  con fallback al endpoint html. Detecta pagina captcha y emite
  error claro si ambos fallan. Anyade _DDGLiteParser para el formato
  lite + auto-pick de parser por contenido.

* enrichers: tipo Webpage unificado en Url (campos de cuerpo
  cacheado viven en metadata del Url). Manifests actualizados
  (applies_to: [Url]). fetch_webpage ya no convierte Url->Webpage.

* enrichers/manifest: campo `params` parseado a EnricherSpec.params
  (name, type, default_value, description). UI puede renderizar
  dialog de configuracion.

* jobs: fix de path conversion para Python embebido nativo Windows
  (no convertir a /mnt/c/... cuando el subproceso es Windows-native;
  solo cuando es bash o python via WSL).

* main.cpp: ventana ImGui (no modal) "Run enricher" con layout
  2-col (label izq, input der). Inserta job con JSON tipado. Layout
  clustering apretado: hijos del mismo anchor en un solo anillo
  alrededor del padre, sin desperdigar por anillos crecientes.

* views: inspector con layout 2-col via BeginTable (Identity,
  Schema fields, Extras). Description full-width debajo de su label.

* tests: portable conftest (auto-detecta REGISTRY_ROOT, PYTHON_BIN,
  ENRICHERS_DIR para WSL y Windows portable). _runner.py trampoline
  inyecta stub via sys.path porque embedded Python ignora PYTHONPATH.
  Tests bash-only (vendor_script, freeze, dispatcher bash, resolver
  Linux-binary) skipean en Windows. Tests existentes adaptados a
  Webpage->Url.

Resultado actual: 32 passed WSL, 21 passed + 11 skipped Windows.
2026-05-03 14:41:28 +02:00

146 lines
5.2 KiB
Python

"""Tests del script tools/vendor_enricher_python.sh (issue 0033b).
Verifica:
- manifest sin uses_functions Python -> no crea _vendored/.
- manifest con un uses_functions -> copia el .py + __init__.
- dep transitiva (extract_iocs importa siblings) -> copia siblings.
- .vendor.lock con SHA256 + path origen.
- Idempotencia: 2da llamada con mismo estado no rehace nada.
- Cambio en el manifest invalida el lock.
"""
from __future__ import annotations
import hashlib
import os
import shutil
import subprocess
from pathlib import Path
import pytest
from conftest import APP_DIR_SRC, REGISTRY_ROOT
SCRIPT = APP_DIR_SRC / "tools" / "vendor_enricher_python.sh"
# El script vendor es bash-only y vive en el repo dev. En la carpeta
# portable de Windows no esta presente; ademas necesitaria un bash
# real para ejecutarse. Saltamos toda la suite si:
# - no encontramos `bash` en PATH (Windows), o
# - el script no existe (deploy portable sin tools/).
pytestmark = pytest.mark.skipif(
shutil.which("bash") is None or not SCRIPT.exists(),
reason="bash o tools/vendor_enricher_python.sh no disponible "
"(esperado en deploy portable)",
)
def _make_enricher_dir(tmp_path: Path, manifest: str) -> Path:
enr = tmp_path / "test_enricher"
enr.mkdir()
(enr / "manifest.yaml").write_text(manifest, encoding="utf-8")
(enr / "run.py").write_text("# stub\n", encoding="utf-8")
return enr
def _run_vendor(enr_dir: Path) -> subprocess.CompletedProcess:
return subprocess.run(
["bash", str(SCRIPT), str(enr_dir), str(REGISTRY_ROOT)],
capture_output=True, text=True, timeout=20,
)
def test_no_uses_functions_does_not_create_vendored(tmp_path):
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [text]\n")
proc = _run_vendor(enr)
assert proc.returncode == 0, proc.stderr
assert not (enr / "_vendored").exists()
assert not (enr / ".vendor.lock").exists()
def test_single_dep_creates_vendored_layout(tmp_path):
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [Url]\n"
"uses_functions:\n"
" - normalize_url_py_cybersecurity\n")
proc = _run_vendor(enr)
assert proc.returncode == 0, proc.stderr
assert (enr / "_vendored" / "__init__.py").exists()
assert (enr / "_vendored" / "cybersecurity" / "__init__.py").exists()
assert (enr / "_vendored" / "cybersecurity" / "cybersecurity.py").exists()
assert (enr / ".vendor.lock").exists()
lock = (enr / ".vendor.lock").read_text()
assert "normalize_url_py_cybersecurity" in lock
def test_transitive_siblings_are_copied(tmp_path):
"""extract_iocs.py importa 7 modulos siblings — todos deben venir."""
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [Webpage]\n"
"uses_functions:\n"
" - extract_iocs_py_cybersecurity\n")
proc = _run_vendor(enr)
assert proc.returncode == 0, proc.stderr
cyb = enr / "_vendored" / "cybersecurity"
assert (cyb / "extract_iocs.py").exists()
expected_siblings = {
"extract_ip_addresses.py", "extract_emails.py",
"extract_domains.py", "extract_file_hashes.py",
"extract_crypto_wallets.py", "extract_cve_ids.py",
"extract_mac_addresses.py", "extract_phone_numbers.py",
}
found = {p.name for p in cyb.glob("*.py")}
missing = expected_siblings - found
assert not missing, f"siblings no copiados: {missing}"
def test_lock_contains_correct_sha256(tmp_path):
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [Url]\n"
"uses_functions:\n - normalize_url_py_cybersecurity\n")
proc = _run_vendor(enr)
assert proc.returncode == 0, proc.stderr
src = REGISTRY_ROOT / "python" / "functions" / "cybersecurity" / "cybersecurity.py"
expected_sha = hashlib.sha256(src.read_bytes()).hexdigest()
lock = (enr / ".vendor.lock").read_text()
assert expected_sha in lock, lock
def test_idempotency_skips_when_unchanged(tmp_path):
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [Url]\n"
"uses_functions:\n - normalize_url_py_cybersecurity\n")
p1 = _run_vendor(enr)
assert p1.returncode == 0
p2 = _run_vendor(enr)
assert p2.returncode == 0
assert "sin cambios" in p2.stdout, p2.stdout
def test_vendored_module_can_be_imported_in_isolation(tmp_path):
"""Smoke: el _vendored/ resultante es importable sin registry_root."""
enr = _make_enricher_dir(tmp_path,
"id: x\nname: x\napplies_to: [Webpage]\n"
"uses_functions:\n - extract_urls_py_cybersecurity\n")
proc = _run_vendor(enr)
assert proc.returncode == 0, proc.stderr
# Lanzamos un Python externo con _vendored como unico path adicional.
code = (
"import sys; sys.path.insert(0, 'enrichers_test/_vendored');"
"from cybersecurity.cybersecurity import extract_urls;"
"print(len(extract_urls('foo http://x.com bar')))"
)
# Crear symlink temporal con el nombre esperado.
fake = tmp_path / "enrichers_test"
fake.symlink_to(enr)
proc2 = subprocess.run(
["python3", "-c", code],
cwd=str(tmp_path), capture_output=True, text=True, timeout=10,
)
assert proc2.returncode == 0, proc2.stderr
assert proc2.stdout.strip() == "1"