Compare commits

..

6 Commits

Author SHA1 Message Date
unkinben b8bc7f8714 Merge pull request 'chore: cleanup the readme' (#23) from benvin/readme-refactor into master
Reviewed-on: #23
2026-04-28 22:00:32 +10:00
unkinben 0c780c1bd1 chore: cleanup the readme
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-04-28 21:57:14 +10:00
unkinben 173b5d8b10 Merge pull request 'refactor: simplify pypi and npm URL rewriting' (#18) from benvin/simplify-remote-url-rewriting into master
Reviewed-on: #18
2026-04-27 22:43:33 +10:00
unkinben 3352a3e886 refactor: simplify pypi and npm URL rewriting — single remote, no redundant config keys
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
- npm: remove npm_files_url/npm_files_remote; rewrite uses base_url and
  remote name directly (same approach as helm)
- npm: replace hardcoded .tgz extension check with immutable_patterns match
- pypi: collapse pypi + pypi-files into a single remote (base_url points
  to files.pythonhosted.org); simple/ requests are transparently fetched
  from pypi.org with no extra config required
- pypi: remove pypi_files_url/pypi_files_remote from pypi and pypi-gitea
- pypi: rewrite check now uses immutable_patterns (consistent with npm)
- Update README for both pypi and npm sections
- Update tests and fixtures to reflect single-remote pypi config
2026-04-27 22:42:23 +10:00
unkinben 8adcbac405 Merge pull request 'feat: add helm chart repository caching proxy' (#17) from benvin/helm-remote into master
ci/woodpecker/tag/docker Pipeline was successful
Reviewed-on: #17
2026-04-27 22:22:36 +10:00
unkinben 4ca89b9159 feat: add helm chart repository caching proxy
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
- Add helm package type with index.yaml as mutable (TTL-based) and
  .tgz chart tarballs as immutable
- Rewrite chart URLs in index.yaml to serve tarballs via proxy cache
- Add text/yaml content-type detection for .yaml/.yml files
- Add hashicorp-helm example remote in remotes.yaml
- Update README with Helm chart repository proxy section
- Add tests for helm mutable patterns and route behaviour
2026-04-27 22:17:31 +10:00
7 changed files with 327 additions and 1002 deletions
+152 -933
View File
File diff suppressed because it is too large Load Diff
+23 -28
View File
@@ -195,15 +195,19 @@ remotes:
mutable_ttl: 300
pypi:
base_url: "https://pypi.org"
base_url: "https://files.pythonhosted.org"
type: "remote"
package: "pypi"
description: "Python Package Index — simple repository API"
# pypi_files_url: the upstream host used in simple-index hrefs (default: files.pythonhosted.org)
# pypi_files_remote: our proxy remote that will serve those files (default: pypi-files)
pypi_files_url: "https://files.pythonhosted.org"
pypi_files_remote: "pypi-files"
description: "Python Package Index — simple index and package files via a single remote"
# simple/ requests are transparently fetched from pypi.org; package files come from
# files.pythonhosted.org (base_url). URLs in the simple index are rewritten to this remote.
check_mutable_updates: true
immutable_patterns:
- "packages/.*\\.whl$"
- "packages/.*\\.whl\\.metadata$"
- "packages/.*\\.tar\\.gz$"
- "packages/.*\\.zip$"
- "packages/.*\\.egg$"
cache:
immutable_ttl: 0
mutable_ttl: 600 # Simple index pages refreshed after 10 minutes
@@ -212,12 +216,9 @@ remotes:
base_url: "https://gitea.example.com/api/packages/myorg/pypi"
type: "remote"
package: "pypi"
description: "Private Gitea PyPI registry"
description: "Private Gitea PyPI registry — simple index and files at the same host"
# username: "your-gitea-username"
# password: "your-personal-access-token" # needs package:read scope
# Files are served from the same Gitea instance — rewrite back to this same remote
pypi_files_url: "https://gitea.example.com/api/packages/myorg/pypi"
pypi_files_remote: "pypi-gitea"
check_mutable_updates: true
immutable_patterns:
- "files/.*\\.whl$"
@@ -229,29 +230,11 @@ remotes:
immutable_ttl: 0
mutable_ttl: 600
pypi-files:
base_url: "https://files.pythonhosted.org"
type: "remote"
package: "generic"
description: "Python Package Index — file storage (wheels, sdists)"
immutable_patterns:
- "packages/.*\\.whl$"
- "packages/.*\\.whl\\.metadata$"
- "packages/.*\\.tar\\.gz$"
- "packages/.*\\.zip$"
- "packages/.*\\.egg$"
cache:
immutable_ttl: 0 # Package files are content-addressed — cache forever
npm:
base_url: "https://registry.npmjs.org"
type: "remote"
package: "npm"
description: "npm registry — package metadata with tarball URL rewriting"
# npm_files_url: the upstream host used in metadata tarball hrefs (default: https://registry.npmjs.org)
# npm_files_remote: our proxy remote that will serve those tarballs (default: npm-files)
npm_files_url: "https://registry.npmjs.org"
npm_files_remote: "npm"
check_mutable_updates: true
immutable_patterns:
- \.tgz$
@@ -261,6 +244,18 @@ remotes:
immutable_ttl: 0
mutable_ttl: 600 # Package metadata refreshed after 10 minutes
hashicorp-helm:
base_url: "https://helm.releases.hashicorp.com"
type: "remote"
package: "helm"
description: "HashiCorp Helm chart repository (Vault, Consul, Nomad, etc.)"
check_mutable_updates: true
immutable_patterns:
- "\\.tgz$"
cache:
immutable_ttl: 0 # Chart tarballs are versioned — cache forever
mutable_ttl: 3600 # index.yaml refreshed after 1 hour
local-generic:
type: "local"
package: "generic"
+3
View File
@@ -22,6 +22,9 @@ _PACKAGE_MUTABLE_PATTERNS: dict[str, list[str]] = {
r"simple/", # Per-package and top-level simple index pages
],
"npm": [],
"helm": [
r"index\.yaml$",
],
"generic": [],
}
+34 -20
View File
@@ -160,12 +160,13 @@ async def construct_remote_url(remote_name: str, path: str) -> str:
if not base_url:
raise HTTPException(status_code=500, detail=f"No base_url configured for remote '{remote_name}'")
# Handle Docker registry URLs
if remote_config.get("package") == "docker":
# Convert Docker paths to v2 API format
# e.g., library/nginx/manifests/latest -> v2/library/nginx/manifests/latest
return f"{base_url}/v2/{path}"
# PyPI splits index and files across two hosts; redirect simple/ requests to pypi.org
if remote_config.get("package") == "pypi" and base_url.rstrip("/") == "https://files.pythonhosted.org" and "simple/" in path:
return f"https://pypi.org/{path}"
return f"{base_url}/{path}"
@@ -349,6 +350,8 @@ def _get_content_type(filename: str) -> str:
return "application/xml"
if filename.endswith((".xml.gz", ".xml.bz2", ".xml.xz")):
return "application/gzip"
if filename.endswith((".yaml", ".yml")):
return "text/yaml"
return "application/octet-stream"
@@ -358,26 +361,37 @@ def _resolve_content(
filename: str,
remote_config: dict,
request: Request,
remote_name: str = "",
) -> tuple[bytes, str]:
"""Return (possibly-rewritten data, content_type) for a cached artifact."""
if remote_config.get("package") == "pypi" and "simple/" in path:
files_url = remote_config.get("pypi_files_url", "https://files.pythonhosted.org")
files_remote = remote_config.get("pypi_files_remote", "pypi-files")
if remote_config.get("package") == "pypi":
immutable = remote_config.get("immutable_patterns", [])
if not any(re.search(p, path) for p in immutable):
proxy_base = str(request.base_url).rstrip("/")
base_url = remote_config.get("base_url", "").rstrip("/")
data = data.replace(
base_url.encode(),
f"{proxy_base}/api/v1/remote/{remote_name}".encode(),
)
return data, "text/html; charset=utf-8"
if remote_config.get("package") == "npm":
immutable = remote_config.get("immutable_patterns", [])
if not any(re.search(p, path) for p in immutable):
proxy_base = str(request.base_url).rstrip("/")
base_url = remote_config.get("base_url", "").rstrip("/")
data = data.replace(
base_url.encode(),
f"{proxy_base}/api/v1/remote/{remote_name}".encode(),
)
return data, "application/json"
if remote_config.get("package") == "helm" and filename == "index.yaml":
proxy_base = str(request.base_url).rstrip("/")
base_url = remote_config.get("base_url", "").rstrip("/")
data = data.replace(
files_url.rstrip("/").encode(),
f"{proxy_base}/api/v1/remote/{files_remote}".encode(),
base_url.encode(),
f"{proxy_base}/api/v1/remote/{remote_name}".encode(),
)
return data, "text/html; charset=utf-8"
if remote_config.get("package") == "npm" and not path.endswith(".tgz"):
files_url = remote_config.get("npm_files_url", "https://registry.npmjs.org")
files_remote = remote_config.get("npm_files_remote", "npm-files")
proxy_base = str(request.base_url).rstrip("/")
data = data.replace(
files_url.rstrip("/").encode(),
f"{proxy_base}/api/v1/remote/{files_remote}".encode(),
)
return data, "application/json"
return data, "text/yaml"
return data, _get_content_type(filename)
@@ -445,7 +459,7 @@ async def get_artifact(request: Request, remote_name: str, path: str):
try:
artifact_data = storage.download_object(cached_key)
filename = os.path.basename(path)
artifact_data, content_type = _resolve_content(artifact_data, path, filename, remote_config, request)
artifact_data, content_type = _resolve_content(artifact_data, path, filename, remote_config, request, remote_name)
logger.info(f"Cache HIT: {remote_name}/{path} (size: {len(artifact_data)} bytes, key: {cached_key})")
@@ -486,7 +500,7 @@ async def get_artifact(request: Request, remote_name: str, path: str):
cache_key = storage.get_object_key(remote_name, path)
artifact_data = storage.download_object(cache_key)
filename = os.path.basename(path)
artifact_data, content_type = _resolve_content(artifact_data, path, filename, remote_config, request)
artifact_data, content_type = _resolve_content(artifact_data, path, filename, remote_config, request, remote_name)
metrics.record_cache_miss(remote_name, len(artifact_data))
cache_key = storage.get_object_key(remote_name, path)
+12 -15
View File
@@ -73,34 +73,31 @@ TEST_REMOTES = {
"cache": {"immutable_ttl": 0, "mutable_ttl": 0},
},
"pypi-test": {
"base_url": "https://pypi.org",
"type": "remote",
"package": "pypi",
"pypi_files_url": "https://files.pythonhosted.org",
"pypi_files_remote": "pypi-files-test",
"cache": {"immutable_ttl": 0, "mutable_ttl": 600},
},
"pypi-files-test": {
"base_url": "https://files.pythonhosted.org",
"type": "remote",
"package": "generic",
"package": "pypi",
"immutable_patterns": [
"packages/.*\\.whl$",
"packages/.*\\.whl\\.metadata$",
"packages/.*\\.tar\\.gz$",
r"packages/.*\.whl$",
r"packages/.*\.whl\.metadata$",
r"packages/.*\.tar\.gz$",
],
"cache": {"immutable_ttl": 0, "mutable_ttl": 0},
"cache": {"immutable_ttl": 0, "mutable_ttl": 600},
},
"npm-test": {
"base_url": "https://registry.npmjs.org",
"type": "remote",
"package": "npm",
"npm_files_url": "https://registry.npmjs.org",
"npm_files_remote": "npm-test",
"immutable_patterns": [r"\.tgz$"],
"mutable_patterns": [r"^(?!.*\.tgz$).*"],
"cache": {"immutable_ttl": 0, "mutable_ttl": 600},
},
"helm-test": {
"base_url": "https://helm.releases.hashicorp.com",
"type": "remote",
"package": "helm",
"immutable_patterns": [r"\.tgz$"],
"cache": {"immutable_ttl": 0, "mutable_ttl": 3600},
},
}
}
+14
View File
@@ -154,6 +154,20 @@ class TestGetMutablePatterns:
assert any(re.search(p, "express") for p in patterns)
assert any(re.search(p, "@babel/core") for p in patterns)
def test_helm_returns_index_yaml_as_mutable(self, make_config):
cfg = make_config({"r": {"type": "remote", "package": "helm", "base_url": "https://helm.example.com"}})
patterns = cfg.get_mutable_patterns("r")
assert r"index\.yaml$" in patterns
def test_helm_chart_tarballs_not_mutable_by_default(self, make_config):
import re
cfg = make_config({"r": {"type": "remote", "package": "helm", "base_url": "https://helm.example.com"}})
patterns = cfg.get_mutable_patterns("r")
# Only index.yaml is mutable; .tgz chart tarballs are not
assert not any(re.search(p, "vault-0.29.1.tgz") for p in patterns)
assert not any(re.search(p, "consul-1.5.0.tgz") for p in patterns)
def test_npm_explicit_mutable_pattern_excludes_tarballs(self, make_config):
import re
+89 -6
View File
@@ -685,7 +685,7 @@ class TestPyPIRemote:
response = client.get("/api/v1/remote/pypi-test/simple/requests/")
assert response.status_code == 200
assert b"files.pythonhosted.org" not in response.content
assert b"/api/v1/remote/pypi-files-test/packages/requests-2.31.0.tar.gz" in response.content
assert b"/api/v1/remote/pypi-test/packages/requests-2.31.0.tar.gz" in response.content
def test_simple_index_content_type_is_html(self, client, patched_deps):
deps = patched_deps
@@ -722,7 +722,7 @@ class TestPyPIRemote:
deps["storage"].download_object.return_value = b"PK wheel bytes"
deps["cache"].is_mutable_file.return_value = False
response = client.get("/api/v1/remote/pypi-files-test/packages/requests-2.31.0-py3-none-any.whl")
response = client.get("/api/v1/remote/pypi-test/packages/requests-2.31.0-py3-none-any.whl")
assert response.status_code == 200
assert "application/zip" in response.headers["content-type"]
assert response.headers["X-Artifact-Source"] == "cache"
@@ -733,13 +733,13 @@ class TestPyPIRemote:
deps["storage"].download_object.return_value = b"tar bytes"
deps["cache"].is_mutable_file.return_value = False
response = client.get("/api/v1/remote/pypi-files-test/packages/requests-2.31.0.tar.gz")
response = client.get("/api/v1/remote/pypi-test/packages/requests-2.31.0.tar.gz")
assert response.status_code == 200
assert "application/gzip" in response.headers["content-type"]
def test_blocked_path_on_files_remote_returns_403(self, client, patched_deps):
"""Paths that don't match immutable_patterns on pypi-files-test are blocked."""
response = client.get("/api/v1/remote/pypi-files-test/packages/requests.unknown")
def test_unknown_extension_on_pypi_remote_returns_403(self, client, patched_deps):
"""Paths that don't match immutable_patterns and aren't mutable are blocked."""
response = client.get("/api/v1/remote/pypi-test/packages/requests.unknown")
assert response.status_code == 403
@@ -841,3 +841,86 @@ class TestNpmRemote:
response = client.get("/api/v1/remote/npm-test/express/-/express-4.18.2.tgz")
assert response.status_code == 200
assert "application/gzip" in response.headers["content-type"]
# ---------------------------------------------------------------------------
# Helm remote /api/v1/remote/helm-test/...
# ---------------------------------------------------------------------------
class TestHelmRemote:
def test_index_yaml_is_mutable(self, client, patched_deps):
"""index.yaml is detected as mutable (package-type default)."""
deps = patched_deps
index = b"apiVersion: v1\nentries:\n vault:\n - urls:\n - https://helm.releases.hashicorp.com/vault-0.29.1.tgz\n"
deps["storage"].exists.return_value = True
deps["storage"].download_object.return_value = index
deps["cache"].is_mutable_file.return_value = True
deps["cache"].is_index_valid.return_value = True
response = client.get("/api/v1/remote/helm-test/index.yaml")
assert response.status_code == 200
deps["cache"].mark_index_cached.assert_not_called()
def test_index_yaml_urls_rewritten_to_proxy(self, client, patched_deps):
"""base_url chart URLs in a cached index.yaml are rewritten to our proxy."""
deps = patched_deps
index = b"apiVersion: v1\nentries:\n vault:\n - urls:\n - https://helm.releases.hashicorp.com/vault-0.29.1.tgz\n"
deps["storage"].exists.return_value = True
deps["storage"].download_object.return_value = index
deps["cache"].is_mutable_file.return_value = True
deps["cache"].is_index_valid.return_value = True
response = client.get("/api/v1/remote/helm-test/index.yaml")
assert response.status_code == 200
assert b"helm.releases.hashicorp.com" not in response.content
assert b"/api/v1/remote/helm-test/vault-0.29.1.tgz" in response.content
def test_index_yaml_content_type_is_yaml(self, client, patched_deps):
deps = patched_deps
deps["storage"].exists.return_value = True
deps["storage"].download_object.return_value = b"apiVersion: v1\nentries: {}\n"
deps["cache"].is_mutable_file.return_value = True
deps["cache"].is_index_valid.return_value = True
response = client.get("/api/v1/remote/helm-test/index.yaml")
assert response.status_code == 200
assert "text/yaml" in response.headers["content-type"]
def test_chart_tarball_immutable_returns_gzip_content_type(self, client, patched_deps):
"""Versioned chart tarballs match immutable_patterns and are served as binary."""
deps = patched_deps
deps["storage"].exists.return_value = True
deps["storage"].download_object.return_value = b"\x1f\x8b chart bytes"
deps["cache"].is_mutable_file.return_value = False
response = client.get("/api/v1/remote/helm-test/vault-0.29.1.tgz")
assert response.status_code == 200
assert "application/gzip" in response.headers["content-type"]
assert response.headers["X-Artifact-Source"] == "cache"
def test_index_yaml_cache_miss_fetches_upstream(self, client, patched_deps):
deps = patched_deps
index = b"apiVersion: v1\nentries:\n vault:\n - urls:\n - https://helm.releases.hashicorp.com/vault-0.29.1.tgz\n"
deps["storage"].exists.return_value = False
deps["storage"].download_object.return_value = index
deps["cache"].is_mutable_file.return_value = True
with patch(
"artifactapi.main.cache_single_artifact",
new_callable=AsyncMock,
return_value={"status": "cached"},
) as mock_fetch:
response = client.get("/api/v1/remote/helm-test/index.yaml")
mock_fetch.assert_called_once()
assert response.status_code == 200
assert b"helm.releases.hashicorp.com" not in response.content
def test_non_tgz_non_yaml_path_blocked_by_pattern(self, client, patched_deps):
"""Paths that don't match immutable_patterns and aren't mutable are blocked."""
deps = patched_deps
deps["cache"].is_mutable_file.return_value = False
response = client.get("/api/v1/remote/helm-test/vault.zip")
assert response.status_code == 403