Fix httpx.Timeout configuration in PyPI proxy

This commit is contained in:
Mondo Diaz
2026-02-05 10:31:04 -06:00
parent 11c5aee0f1
commit dfa089376a
76 changed files with 9384 additions and 4407 deletions

View File

@@ -17,21 +17,31 @@ class TestPyPIProxyEndpoints:
"""
@pytest.mark.integration
def test_pypi_simple_index_no_sources(self):
"""Test that /pypi/simple/ returns 503 when no sources configured."""
def test_pypi_simple_index(self):
"""Test that /pypi/simple/ returns HTML response."""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
response = client.get("/pypi/simple/")
# Should return 503 when no PyPI upstream sources are configured
assert response.status_code == 503
assert "No PyPI upstream sources configured" in response.json()["detail"]
# Returns 200 if sources configured, 503 if not
assert response.status_code in (200, 503)
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
else:
assert "No PyPI upstream sources configured" in response.json()["detail"]
@pytest.mark.integration
def test_pypi_package_no_sources(self):
"""Test that /pypi/simple/{package}/ returns 503 when no sources configured."""
def test_pypi_package_endpoint(self):
"""Test that /pypi/simple/{package}/ returns appropriate response."""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
response = client.get("/pypi/simple/requests/")
assert response.status_code == 503
assert "No PyPI upstream sources configured" in response.json()["detail"]
# Returns 200 if sources configured and package found,
# 404 if package not found, 503 if no sources
assert response.status_code in (200, 404, 503)
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
elif response.status_code == 404:
assert "not found" in response.json()["detail"].lower()
else: # 503
assert "No PyPI upstream sources configured" in response.json()["detail"]
@pytest.mark.integration
def test_pypi_download_missing_upstream_param(self):
@@ -58,7 +68,13 @@ class TestPyPILinkRewriting:
</html>
'''
result = _rewrite_package_links(html, "http://localhost:8080", "requests")
# upstream_base_url is used to resolve relative URLs (not needed here since URLs are absolute)
result = _rewrite_package_links(
html,
"http://localhost:8080",
"requests",
"https://pypi.org/simple/requests/"
)
# Links should be rewritten to go through our proxy
assert "/pypi/simple/requests/requests-2.31.0.tar.gz?upstream=" in result
@@ -69,25 +85,69 @@ class TestPyPILinkRewriting:
assert "#sha256=abc123" in result
assert "#sha256=def456" in result
def test_rewrite_relative_links(self):
"""Test that relative URLs are resolved to absolute URLs."""
from app.pypi_proxy import _rewrite_package_links
# Artifactory-style relative URLs
html = '''
<html>
<body>
<a href="../../packages/ab/cd/requests-2.31.0.tar.gz#sha256=abc123">requests-2.31.0.tar.gz</a>
</body>
</html>
'''
result = _rewrite_package_links(
html,
"https://orchard.example.com",
"requests",
"https://artifactory.example.com/api/pypi/pypi-remote/simple/requests/"
)
# The relative URL should be resolved to absolute
# ../../packages/ab/cd/... from /api/pypi/pypi-remote/simple/requests/ resolves to /api/pypi/pypi-remote/packages/ab/cd/...
assert "upstream=https%3A%2F%2Fartifactory.example.com%2Fapi%2Fpypi%2Fpypi-remote%2Fpackages" in result
# Hash fragment should be preserved
assert "#sha256=abc123" in result
class TestPyPIPackageNormalization:
"""Tests for PyPI package name normalization."""
@pytest.mark.integration
def test_package_name_normalized(self):
"""Test that package names are normalized per PEP 503."""
# These should all be treated the same:
# requests, Requests, requests_, requests-
# The endpoint normalizes to lowercase with hyphens
"""Test that package names are normalized per PEP 503.
Different capitalizations/separators should all be valid paths.
The endpoint normalizes to lowercase with hyphens before lookup.
"""
with httpx.Client(base_url=get_base_url(), timeout=30.0) as client:
# Without upstream sources, we get 503, but the normalization
# happens before the source lookup
response = client.get("/pypi/simple/Requests/")
assert response.status_code == 503 # No sources, but path was valid
# Test various name formats - all should be valid endpoint paths
for package_name in ["Requests", "some_package", "some-package"]:
response = client.get(f"/pypi/simple/{package_name}/")
# 200 = found, 404 = not found, 503 = no sources configured
assert response.status_code in (200, 404, 503), \
f"Unexpected status {response.status_code} for {package_name}"
response = client.get("/pypi/simple/some_package/")
assert response.status_code == 503
# Verify response is appropriate for the status code
if response.status_code == 200:
assert "text/html" in response.headers.get("content-type", "")
elif response.status_code == 503:
assert "No PyPI upstream sources configured" in response.json()["detail"]
response = client.get("/pypi/simple/some-package/")
assert response.status_code == 503
class TestPyPIProxyInfrastructure:
"""Tests for PyPI proxy infrastructure integration."""
@pytest.mark.integration
def test_health_endpoint_includes_infrastructure(self, integration_client):
"""Health endpoint should report infrastructure status."""
response = integration_client.get("/health")
assert response.status_code == 200
data = response.json()
assert data["status"] == "ok"
# Infrastructure status should be present
assert "http_pool" in data
assert "cache" in data