Compare commits
2 Commits
v2.4.0
..
bd1faeee9b
| Author | SHA1 | Date | |
|---|---|---|---|
 unkinben
|
bd1faeee9b | ||
|
unkinben
|
b50abe304e |
@@ -6,14 +6,10 @@ A generic FastAPI-based artifact caching system that downloads and stores files
|
||||
|
||||
- **Generic Remote Support**: Works with any HTTP-based file server (GitHub, Gitea, HashiCorp, custom servers)
|
||||
- **Configuration-Based**: YAML configuration for remotes, patterns, and access control
|
||||
- **Direct URL API**: Access cached files via clean URLs like `/api/v1/remote/github/owner/repo/path/file.tar.gz`
|
||||
- **Immutable/Mutable Pattern Model**: Per-remote regex patterns distinguish forever-cached artifacts from TTL-expiring metadata
|
||||
- **Direct URL API**: Access cached files via clean URLs like `/api/github/owner/repo/path/file.tar.gz`
|
||||
- **Pattern Filtering**: Regex-based inclusion patterns for security and organization
|
||||
- **Smart Caching**: Automatic download and cache on first access, serve from cache afterward
|
||||
- **Conditional Revalidation**: Optional `check_mutable_updates` flag — sends `If-None-Match`/`If-Modified-Since` on expiry; skips re-download on 304
|
||||
- **Stale-on-Upstream-Error**: Expired mutable files are kept and their TTL refreshed when the backend cannot be reached, so cached data remains available during upstream outages
|
||||
- **S3 Storage**: MinIO/S3 backend with predictable paths
|
||||
- **Docker Registry Proxy**: Full Docker Registry HTTP API v2 for transparent container image caching
|
||||
- **npm Package Proxy**: Caching proxy for the npm registry with metadata URL rewriting so tarballs also pass through cache
|
||||
- **Content-Type Detection**: Automatic MIME type detection for downloads
|
||||
|
||||
## Architecture
|
||||
@@ -75,18 +71,15 @@ The system uses `remotes.yaml` to define remote repositories and access patterns
|
||||
remotes:
|
||||
remote-name:
|
||||
base_url: "https://example.com" # Base URL for the remote
|
||||
type: "remote" # "remote" or "local"
|
||||
package: "generic" # "generic", "alpine", "rpm", or "docker"
|
||||
type: "remote" # Type: "remote" or "local"
|
||||
package: "generic" # Package type: "generic", "alpine", "rpm"
|
||||
description: "Human readable description"
|
||||
immutable_patterns: # Files cached forever (release binaries, versioned tags)
|
||||
include_patterns: # Regex patterns for allowed files
|
||||
- "pattern1"
|
||||
- "pattern2"
|
||||
mutable_patterns: # Files that expire after mutable_ttl (optional)
|
||||
- "pattern3"
|
||||
check_mutable_updates: false # Enable conditional HEAD before re-fetching (optional)
|
||||
cache:
|
||||
immutable_ttl: 0 # TTL for immutable files (0 = indefinitely)
|
||||
mutable_ttl: 3600 # TTL in seconds for mutable files
|
||||
cache: # Cache configuration (optional)
|
||||
file_ttl: 0 # File cache TTL (0 = indefinite)
|
||||
index_ttl: 300 # Index file TTL in seconds
|
||||
```
|
||||
|
||||
### Remote Types
|
||||
@@ -101,30 +94,30 @@ remotes:
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
description: "GitHub releases and files"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- "gruntwork-io/terragrunt/.*terragrunt_linux_amd64.*"
|
||||
- "lxc/incus/.*\\.tar\\.gz$"
|
||||
- "prometheus/node_exporter/.*/node_exporter-.*\\.linux-amd64\\.tar\\.gz$"
|
||||
cache:
|
||||
immutable_ttl: 0 # Cache files indefinitely
|
||||
file_ttl: 0 # Cache files indefinitely
|
||||
index_ttl: 0 # No index files for generic remotes
|
||||
|
||||
github-archive:
|
||||
base_url: "https://github.com"
|
||||
hashicorp-releases:
|
||||
base_url: "https://releases.hashicorp.com"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
description: "GitHub repository archive tarballs"
|
||||
immutable_patterns:
|
||||
- ".*/archive/refs/tags/.*\\.tar\\.gz$" # tag archives never change
|
||||
mutable_patterns:
|
||||
- ".*/archive/refs/heads/main\\.tar\\.gz$" # branch archives can change
|
||||
check_mutable_updates: true # send If-None-Match on expiry; skip re-download on 304
|
||||
description: "HashiCorp product releases"
|
||||
include_patterns:
|
||||
- "terraform/.*terraform_.*_linux_amd64\\.zip$"
|
||||
- "vault/.*vault_.*_linux_amd64\\.zip$"
|
||||
- "consul/.*/consul_.*_linux_amd64\\.zip$"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 86400 # re-check branch archives after 1 day
|
||||
file_ttl: 0
|
||||
index_ttl: 0
|
||||
```
|
||||
|
||||
#### Package Repository Remotes
|
||||
For Linux package repositories:
|
||||
For Linux package repositories with index files:
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
@@ -133,25 +126,23 @@ remotes:
|
||||
type: "remote"
|
||||
package: "alpine"
|
||||
description: "Alpine Linux APK package repository"
|
||||
immutable_patterns:
|
||||
- ".*/x86_64/.*\\.apk$" # packages are immutable by content-hash
|
||||
# APKINDEX.tar.gz is a package-type default mutable file — no mutable_patterns needed
|
||||
include_patterns:
|
||||
- ".*/x86_64/.*\\.apk$" # Only x86_64 packages
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 7200 # re-fetch APKINDEX.tar.gz after 2 hours
|
||||
file_ttl: 0 # Cache packages indefinitely
|
||||
index_ttl: 7200 # Cache APKINDEX.tar.gz for 2 hours
|
||||
|
||||
almalinux:
|
||||
base_url: "https://mirror.example.com/almalinux"
|
||||
base_url: "http://mirror.aarnet.edu.au/pub/almalinux"
|
||||
type: "remote"
|
||||
package: "rpm"
|
||||
description: "AlmaLinux RPM package repository"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- ".*/x86_64/.*\\.rpm$"
|
||||
- ".*/noarch/.*\\.rpm$"
|
||||
# repomd.xml and repodata/* are package-type defaults
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 7200
|
||||
file_ttl: 0
|
||||
index_ttl: 7200 # Cache metadata files for 2 hours
|
||||
```
|
||||
|
||||
#### Local Repositories
|
||||
@@ -164,45 +155,62 @@ remotes:
|
||||
package: "generic"
|
||||
description: "Local generic file repository"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 0
|
||||
file_ttl: 0
|
||||
index_ttl: 0
|
||||
```
|
||||
|
||||
### Immutable Patterns
|
||||
### Include Patterns
|
||||
|
||||
`immutable_patterns` are regular expressions that control which files can be accessed. Patterns use Python `re.search`, so they match anywhere in the path unless anchored with `^` or `$`. Only files matching at least one pattern are served; all others return HTTP 403.
|
||||
|
||||
Matched files are cached with `immutable_ttl` (default 0 = forever). Use these for versioned release artifacts that never change once published.
|
||||
Include patterns are regular expressions that control which files can be accessed. Patterns use Python `re.search`, so they match anywhere in the path unless anchored with `^` or `$`. Only files matching at least one pattern are served; all others return HTTP 403.
|
||||
|
||||
```yaml
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
# Exact project + architecture — most restrictive
|
||||
- "^gruntwork-io/terragrunt/releases/download/.*/terragrunt_linux_amd64$"
|
||||
|
||||
# Any release asset for a project, any version
|
||||
- "gruntwork-io/terragrunt/.*terragrunt_linux_amd64.*"
|
||||
|
||||
# File extension only — allow all files of a given type from any path
|
||||
- ".*\\.tar\\.gz$"
|
||||
- ".*\\.rpm$"
|
||||
- ".*\\.zip$"
|
||||
|
||||
# Architecture subtree — allow everything under x86_64/
|
||||
- ".*/x86_64/.*"
|
||||
|
||||
# Combined: architecture + extension
|
||||
- ".*/x86_64/.*\\.rpm$"
|
||||
- ".*/noarch/.*\\.rpm$"
|
||||
|
||||
# Docker image names (used with package: docker remotes)
|
||||
- "^library/nginx" # nginx official images only
|
||||
- "^rancher/" # all rancher/* images
|
||||
- "^rancher/rke2-runtime" # specific image
|
||||
|
||||
# Repodata directories — allow all metadata for an RPM repo
|
||||
- ".*/repodata/.*$"
|
||||
```
|
||||
|
||||
**Security note**: Omitting `immutable_patterns` entirely allows all files from that remote.
|
||||
**Security note**: Omitting `include_patterns` entirely allows all files from that remote. Index files (e.g. `APKINDEX.tar.gz`, `repomd.xml`, tag manifests) always bypass pattern enforcement — they are served unconditionally so clients can discover available packages.
|
||||
|
||||
### Mutable Patterns
|
||||
### Index Patterns
|
||||
|
||||
`mutable_patterns` identify files that change over time (index files, branch archives, metadata). Mutable files:
|
||||
- **Always served** regardless of `immutable_patterns`
|
||||
- **Cached with `mutable_ttl`** and re-fetched from upstream when the TTL expires
|
||||
- **Kept stale** when the upstream backend is unreachable — TTL is refreshed automatically so the cached copy remains available until the backend recovers (see below)
|
||||
Index patterns identify repository metadata files. Index files get special treatment:
|
||||
- **Always served** regardless of `include_patterns`
|
||||
- **Cached with `index_ttl`** instead of `file_ttl`
|
||||
- **Automatically refreshed** when the TTL expires — the cached copy is evicted and re-fetched on next request
|
||||
|
||||
Built-in defaults per package type (no configuration needed):
|
||||
Built-in defaults per package type:
|
||||
|
||||
| Package type | Built-in mutable patterns |
|
||||
| Package type | Built-in index patterns |
|
||||
|---|---|
|
||||
| `alpine` | `APKINDEX\.tar\.gz$` |
|
||||
| `rpm` | `repomd\.xml$`, `repodata/` metadata (xml, sqlite, yaml, asc, txt variants), `Packages\.gz$` |
|
||||
| `docker` | Tag manifests (non-digest refs), `/tags/list` |
|
||||
| `generic` | *(none)* |
|
||||
|
||||
Use `mutable_patterns` to add extra patterns on top of the defaults. Duplicates are ignored automatically.
|
||||
Use `index_patterns` to add extra patterns on top of the defaults. Duplicates are ignored automatically.
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
@@ -210,74 +218,60 @@ remotes:
|
||||
base_url: "https://charts.example.com"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
immutable_patterns:
|
||||
- ".*\\.tgz$"
|
||||
mutable_patterns:
|
||||
- "index\\.yaml$" # Helm repo index
|
||||
include_patterns:
|
||||
- ".*\\.tgz$" # chart archives
|
||||
index_patterns:
|
||||
- "index\\.yaml$" # Helm repo index — re-fetched on every TTL expiry
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600 # re-check the index every 10 minutes
|
||||
file_ttl: 0
|
||||
index_ttl: 600 # re-check the index every 10 minutes
|
||||
|
||||
apt-mirror:
|
||||
base_url: "https://apt.example.com"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- ".*\\.deb$"
|
||||
mutable_patterns:
|
||||
- "InRelease$"
|
||||
- "Release$"
|
||||
- "Packages\\.gz$"
|
||||
index_patterns:
|
||||
- "InRelease$" # signed APT release file
|
||||
- "Release$" # unsigned APT release file
|
||||
- "Packages\\.gz$" # compressed package list
|
||||
- "Packages\\.xz$"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 3600
|
||||
```
|
||||
file_ttl: 0
|
||||
index_ttl: 3600 # hourly index refresh
|
||||
|
||||
### Conditional Revalidation (`check_mutable_updates`)
|
||||
|
||||
By default, when a mutable file's TTL expires the cached copy is evicted and the full file is re-downloaded on the next request. Setting `check_mutable_updates: true` on a remote enables a cheaper conditional check first:
|
||||
|
||||
1. On TTL expiry, a `HEAD` request is sent to the upstream with `If-None-Match` / `If-Modified-Since` headers (populated from the original download).
|
||||
2. If the upstream replies **304 Not Modified**, the TTL is refreshed in place — no re-download, no S3 traffic.
|
||||
3. If the upstream replies **200**, the cached copy is evicted and re-downloaded normally.
|
||||
|
||||
This only applies to user-defined `mutable_patterns`. Package-type built-in patterns (APKINDEX, repomd.xml, Docker manifests) are always re-fetched unconditionally.
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
github-archive:
|
||||
base_url: "https://github.com"
|
||||
almalinux-with-extras:
|
||||
base_url: "https://mirror.example.com/almalinux"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
immutable_patterns:
|
||||
- ".*/archive/refs/tags/.*\\.tar\\.gz$"
|
||||
mutable_patterns:
|
||||
- ".*/archive/refs/heads/main\\.tar\\.gz$"
|
||||
check_mutable_updates: true
|
||||
package: "rpm" # inherits repomd.xml + repodata/* defaults
|
||||
include_patterns:
|
||||
- ".*/x86_64/.*\\.rpm$"
|
||||
- ".*/noarch/.*\\.rpm$"
|
||||
index_patterns:
|
||||
- "comps\\.xml$" # optional group metadata (adds to rpm defaults)
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 86400
|
||||
file_ttl: 0
|
||||
index_ttl: 7200
|
||||
```
|
||||
|
||||
### Stale-on-Upstream-Error
|
||||
|
||||
When a mutable file's TTL expires and the upstream backend **cannot be reached** (connection refused, DNS failure, timeout), the cached copy is **kept and its TTL refreshed** rather than evicted. This means:
|
||||
|
||||
- RPM repodata, Alpine indexes, branch archives, and other mutable files remain available during upstream outages.
|
||||
- Clients continue to receive the last-known-good copy without errors.
|
||||
- Once the backend recovers and the refreshed TTL next expires, normal eviction resumes.
|
||||
|
||||
This behaviour is automatic and requires no configuration. Only network-level failures trigger it — HTTP error responses (404, 503, etc.) are treated as the backend being reachable and proceed with normal expiry.
|
||||
Pattern matching uses `re.search`, so `"index\\.yaml$"` matches `/stable/index.yaml` and `/index.yaml`. Anchor with `^` to restrict to the path root.
|
||||
|
||||
### Cache Configuration
|
||||
|
||||
Control how long different file types are cached:
|
||||
|
||||
```yaml
|
||||
cache:
|
||||
immutable_ttl: 0 # Immutable files (0 = cache indefinitely, rarely changed)
|
||||
mutable_ttl: 3600 # Mutable files — TTL in seconds before re-fetch is attempted
|
||||
file_ttl: 0 # Regular files (0 = cache indefinitely)
|
||||
index_ttl: 300 # Index files like APKINDEX.tar.gz (seconds)
|
||||
```
|
||||
|
||||
**Index Files**: Repository metadata files that change frequently:
|
||||
- Alpine: `APKINDEX.tar.gz`
|
||||
- RPM: `repomd.xml`, `*-primary.xml.gz`, etc.
|
||||
- These are automatically detected and use `index_ttl`
|
||||
|
||||
### Environment Variables
|
||||
|
||||
All runtime configuration comes from environment variables:
|
||||
@@ -357,26 +351,26 @@ data:
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
description: "GitHub releases and files"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- "gruntwork-io/terragrunt/.*terragrunt_linux_amd64.*"
|
||||
- "lxc/incus/.*\\.tar\\.gz$"
|
||||
- "prometheus/node_exporter/.*/node_exporter-.*\\.linux-amd64\\.tar\\.gz$"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 0
|
||||
file_ttl: 0
|
||||
index_ttl: 0
|
||||
|
||||
hashicorp-releases:
|
||||
base_url: "https://releases.hashicorp.com"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
description: "HashiCorp product releases"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- "terraform/.*terraform_.*_linux_amd64\\.zip$"
|
||||
- "vault/.*vault_.*_linux_amd64\\.zip$"
|
||||
- "consul/.*/consul_.*_linux_amd64\\.zip$"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 0
|
||||
file_ttl: 0
|
||||
index_ttl: 0
|
||||
```
|
||||
|
||||
### 3. Secret for Environment Variables
|
||||
@@ -784,8 +778,8 @@ remotes:
|
||||
username: "your-dockerhub-username"
|
||||
password: "your-dockerhub-token" # PAT with read scope
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 300
|
||||
file_ttl: 0
|
||||
index_ttl: 300
|
||||
```
|
||||
|
||||
A pull of `nginx:latest` becomes `/v2/dockerhub/library/nginx/manifests/latest` on the artifact API.
|
||||
@@ -810,8 +804,8 @@ remotes:
|
||||
username: "your-github-username"
|
||||
password: "ghp_your_github_pat" # read:packages scope required
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 300
|
||||
file_ttl: 0
|
||||
index_ttl: 300
|
||||
```
|
||||
|
||||
A pull of `ghcr.io/rancher/rke2-runtime:v1.30.0-rke2r1` becomes `/v2/ghcr/rancher/rke2-runtime/manifests/v1.30.0-rke2r1`.
|
||||
@@ -850,7 +844,7 @@ Each entry needs a matching remote in `remotes.yaml` using the name from the rew
|
||||
|
||||
#### Restricting which images are cached
|
||||
|
||||
Use `immutable_patterns` on the remote to allow only specific images through the proxy. Requests for images not matching any pattern return HTTP 403 to the node.
|
||||
Use `include_patterns` on the remote to allow only specific images through the proxy. Requests for images not matching any pattern return HTTP 403 to the node.
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
@@ -858,17 +852,17 @@ remotes:
|
||||
base_url: "https://registry-1.docker.io"
|
||||
type: "remote"
|
||||
package: "docker"
|
||||
immutable_patterns:
|
||||
include_patterns:
|
||||
- "^library/nginx" # official nginx only
|
||||
- "^library/redis" # official redis only
|
||||
- "^rancher/" # all rancher images
|
||||
- "^grafana/grafana" # specific image
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 300
|
||||
file_ttl: 0
|
||||
index_ttl: 300
|
||||
```
|
||||
|
||||
Omit `immutable_patterns` to allow all images from that registry.
|
||||
Omit `include_patterns` to allow all images from that registry.
|
||||
|
||||
#### TLS configuration
|
||||
|
||||
@@ -933,167 +927,3 @@ curl -I https://artifacts.example.com/v2/dockerhub/library/nginx/manifests/lates
|
||||
# Check what's stored in the cache
|
||||
curl https://artifacts.example.com/ | jq '.remotes'
|
||||
```
|
||||
|
||||
## Python Package Proxy with uv
|
||||
|
||||
The `pypi` package type turns the artifact API into a caching PyPI proxy. Simple index pages (`/simple/{package}/`) are mutable and expire after `mutable_ttl`; package files (wheels, sdists, metadata) are immutable and cached forever. URLs in the simple index HTML are rewritten on the fly to point back through the proxy, so both the index lookup and the file download are served from cache.
|
||||
|
||||
### remotes.yaml
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
pypi:
|
||||
base_url: "https://pypi.org"
|
||||
type: "remote"
|
||||
package: "pypi"
|
||||
pypi_files_url: "https://files.pythonhosted.org" # host to rewrite in index HTML
|
||||
pypi_files_remote: "pypi-files" # our proxy remote to replace it with
|
||||
check_mutable_updates: true
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600 # re-check simple indexes after 10 minutes
|
||||
|
||||
pypi-files:
|
||||
base_url: "https://files.pythonhosted.org"
|
||||
type: "remote"
|
||||
package: "generic"
|
||||
immutable_patterns:
|
||||
- "packages/.*\\.whl$"
|
||||
- "packages/.*\\.whl\\.metadata$"
|
||||
- "packages/.*\\.tar\\.gz$"
|
||||
- "packages/.*\\.zip$"
|
||||
- "packages/.*\\.egg$"
|
||||
cache:
|
||||
immutable_ttl: 0 # package files are content-addressed — cache forever
|
||||
|
||||
# Self-hosted Gitea PyPI registry (index and files share the same base URL)
|
||||
pypi-gitea:
|
||||
base_url: "https://gitea.example.com/api/packages/myorg/pypi"
|
||||
type: "remote"
|
||||
package: "pypi"
|
||||
# username: "your-gitea-username"
|
||||
# password: "your-personal-access-token" # needs package:read scope
|
||||
pypi_files_url: "https://gitea.example.com/api/packages/myorg/pypi"
|
||||
pypi_files_remote: "pypi-gitea" # point back to itself — Gitea serves both index and files
|
||||
check_mutable_updates: true
|
||||
immutable_patterns:
|
||||
- "files/.*\\.whl$"
|
||||
- "files/.*\\.whl\\.metadata$"
|
||||
- "files/.*\\.tar\\.gz$"
|
||||
- "files/.*\\.zip$"
|
||||
- "files/.*\\.egg$"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600
|
||||
```
|
||||
|
||||
### Configuring uv system- or user-wide
|
||||
|
||||
uv reads `uv.toml` from two locations outside any project, applied in order from broadest to narrowest scope:
|
||||
|
||||
| Scope | Path (Linux/macOS) |
|
||||
|---|---|
|
||||
| System | `/etc/uv/uv.toml` |
|
||||
| User | `~/.config/uv/uv.toml` |
|
||||
|
||||
Use these files to route **all** package installs on a machine through the proxy without touching individual projects or their `pyproject.toml`.
|
||||
|
||||
**`/etc/uv/uv.toml`** — applies to every user on the host:
|
||||
|
||||
```toml
|
||||
# Replace the default PyPI index with the caching proxy
|
||||
[[index]]
|
||||
url = "https://artifacts.example.com/api/v1/remote/pypi/simple"
|
||||
default = true
|
||||
|
||||
# Optionally add a private index (searched alongside the default)
|
||||
[[index]]
|
||||
url = "https://artifacts.example.com/api/v1/remote/pypi-gitea/simple"
|
||||
name = "gitea"
|
||||
```
|
||||
|
||||
**`~/.config/uv/uv.toml`** — same syntax, single-user scope:
|
||||
|
||||
```toml
|
||||
[[index]]
|
||||
url = "https://artifacts.example.com/api/v1/remote/pypi/simple"
|
||||
default = true
|
||||
```
|
||||
|
||||
Setting `default = true` replaces uv's built-in PyPI index. The first install of a package fetches it from upstream and populates the cache; every subsequent install — from any machine or fresh environment pointing at the same proxy — is served directly from S3.
|
||||
|
||||
### How the rewriting works
|
||||
|
||||
When uv requests the simple index for a package, the proxy:
|
||||
|
||||
1. Fetches `https://pypi.org/simple/{package}/` (or returns a valid cached copy within `mutable_ttl`)
|
||||
2. Rewrites every `https://files.pythonhosted.org/...` href to `https://artifacts.example.com/api/v1/remote/pypi-files/...`
|
||||
3. Returns the rewritten HTML to uv
|
||||
|
||||
uv then downloads wheels and `.whl.metadata` files via the rewritten URLs, which also pass through the proxy and are cached as immutable artifacts.
|
||||
|
||||
For self-hosted registries like Gitea, both the index and file downloads share the same base URL. Setting `pypi_files_url` and `pypi_files_remote` to the same remote causes file links to be rewritten back through the same proxy entry.
|
||||
|
||||
## npm Package Proxy
|
||||
|
||||
The `npm` package type turns the artifact API into a caching npm registry proxy. Since the npm registry serves both metadata and tarballs from the same host, a single remote handles everything. Package metadata (e.g. `GET /express`) is mutable and expires after `mutable_ttl`; tarballs (`.tgz`) are immutable and cached forever. `dist.tarball` URLs in metadata JSON are rewritten on the fly to point back through the same remote, so both the metadata lookup and the tarball download are served from cache.
|
||||
|
||||
### remotes.yaml
|
||||
|
||||
```yaml
|
||||
remotes:
|
||||
npm:
|
||||
base_url: "https://registry.npmjs.org"
|
||||
type: "remote"
|
||||
package: "npm"
|
||||
npm_files_url: "https://registry.npmjs.org" # URL prefix to rewrite in metadata JSON
|
||||
npm_files_remote: "npm" # rewrite back to this same remote
|
||||
check_mutable_updates: true
|
||||
immutable_patterns:
|
||||
- "\.tgz$" # versioned tarballs are content-addressed — cache forever
|
||||
mutable_patterns:
|
||||
- "^(?!.*\.tgz$).*" # everything else (package metadata) expires after mutable_ttl
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600 # re-check package metadata after 10 minutes
|
||||
```
|
||||
|
||||
### Configuring npm / yarn / pnpm
|
||||
|
||||
**npm** — per-project `.npmrc` or `~/.npmrc`:
|
||||
|
||||
```ini
|
||||
registry=https://artifacts.example.com/api/v1/remote/npm/
|
||||
```
|
||||
|
||||
**yarn** — `~/.yarnrc.yml`:
|
||||
|
||||
```yaml
|
||||
npmRegistryServer: "https://artifacts.example.com/api/v1/remote/npm/"
|
||||
```
|
||||
|
||||
**pnpm** — `.npmrc`:
|
||||
|
||||
```ini
|
||||
registry=https://artifacts.example.com/api/v1/remote/npm/
|
||||
```
|
||||
|
||||
### How the rewriting works
|
||||
|
||||
When a client requests package metadata, the proxy:
|
||||
|
||||
1. Fetches `https://registry.npmjs.org/{package}` (or returns a cached copy within `mutable_ttl`)
|
||||
2. Rewrites every `https://registry.npmjs.org/...` tarball URL to `https://artifacts.example.com/api/v1/remote/npm/...`
|
||||
3. Returns the rewritten JSON to the client
|
||||
|
||||
The client then downloads the tarball via the rewritten URL, which hits the same `npm` remote and is cached as an immutable artifact. Subsequent installs of the same package version are served entirely from S3.
|
||||
|
||||
### Mutable vs immutable paths
|
||||
|
||||
| Path pattern | Type | Example |
|
||||
|---|---|---|
|
||||
| `/{package}` | Mutable (TTL) | `/express` |
|
||||
| `/@{scope}/{package}` | Mutable (TTL) | `/@babel/core` |
|
||||
| `/-/all` | Mutable (TTL) | `/-/all` |
|
||||
| `/{package}/-/{package}-{version}.tgz` | Immutable (forever) | `/express/-/express-4.18.2.tgz` |
|
||||
| `/@{scope}/{pkg}/-/{pkg}-{ver}.tgz` | Immutable (forever) | `/@babel/core/-/core-7.21.0.tgz` |
|
||||
+17
-68
@@ -154,7 +154,7 @@ remotes:
|
||||
- ".*/repodata/.*$"
|
||||
cache:
|
||||
immutable_ttl: 0 # Files cached indefinitely
|
||||
mutable_ttl: 7200 # Metadata files cached for 2 hours
|
||||
mutable_ttl: 7200 # Metadata files cached for 1 hour
|
||||
|
||||
fedora:
|
||||
base_url: "https://gsl-syd.mm.fcix.net/fedora/linux"
|
||||
@@ -171,6 +171,20 @@ remotes:
|
||||
immutable_ttl: 0 # Files cached indefinitely
|
||||
mutable_ttl: 300 # Metadata files cached for 5 minutes
|
||||
|
||||
almalinux-gsl:
|
||||
base_url: "https://gsl-syd.mm.fcix.net/almalinux"
|
||||
type: "remote"
|
||||
package: "rpm"
|
||||
description: "AlmaLinux RPM package repository (GSL mirror)"
|
||||
immutable_patterns:
|
||||
- ".*/x86_64/.*\\.rpm$"
|
||||
- ".*/noarch/.*\\.rpm$"
|
||||
- ".*/repodata/.*$"
|
||||
- ".*\\.rpm$" # Allow all RPM files
|
||||
cache:
|
||||
immutable_ttl: 0 # Files cached indefinitely
|
||||
mutable_ttl: 7200 # Metadata files cached for 2 hours
|
||||
|
||||
ghcr:
|
||||
base_url: "https://ghcr.io"
|
||||
type: "remote"
|
||||
@@ -190,77 +204,12 @@ remotes:
|
||||
type: "remote"
|
||||
package: "docker"
|
||||
description: "Docker Hub registry"
|
||||
username: "neotheo10"
|
||||
password: "dckr_pat_smIUKN6m2N1ghbxwRFEcrIByta4"
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 300
|
||||
|
||||
pypi:
|
||||
base_url: "https://pypi.org"
|
||||
type: "remote"
|
||||
package: "pypi"
|
||||
description: "Python Package Index — simple repository API"
|
||||
# pypi_files_url: the upstream host used in simple-index hrefs (default: files.pythonhosted.org)
|
||||
# pypi_files_remote: our proxy remote that will serve those files (default: pypi-files)
|
||||
pypi_files_url: "https://files.pythonhosted.org"
|
||||
pypi_files_remote: "pypi-files"
|
||||
check_mutable_updates: true
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600 # Simple index pages refreshed after 10 minutes
|
||||
|
||||
pypi-gitea:
|
||||
base_url: "https://gitea.example.com/api/packages/myorg/pypi"
|
||||
type: "remote"
|
||||
package: "pypi"
|
||||
description: "Private Gitea PyPI registry"
|
||||
# username: "your-gitea-username"
|
||||
# password: "your-personal-access-token" # needs package:read scope
|
||||
# Files are served from the same Gitea instance — rewrite back to this same remote
|
||||
pypi_files_url: "https://gitea.example.com/api/packages/myorg/pypi"
|
||||
pypi_files_remote: "pypi-gitea"
|
||||
check_mutable_updates: true
|
||||
immutable_patterns:
|
||||
- "files/.*\\.whl$"
|
||||
- "files/.*\\.whl\\.metadata$"
|
||||
- "files/.*\\.tar\\.gz$"
|
||||
- "files/.*\\.zip$"
|
||||
- "files/.*\\.egg$"
|
||||
cache:
|
||||
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$"
|
||||
cache:
|
||||
immutable_ttl: 0 # Package files are content-addressed — cache forever
|
||||
|
||||
npm:
|
||||
base_url: "https://registry.npmjs.org"
|
||||
type: "remote"
|
||||
package: "npm"
|
||||
description: "npm registry — package metadata with tarball URL rewriting"
|
||||
# npm_files_url: the upstream host used in metadata tarball hrefs (default: https://registry.npmjs.org)
|
||||
# npm_files_remote: our proxy remote that will serve those tarballs (default: npm-files)
|
||||
npm_files_url: "https://registry.npmjs.org"
|
||||
npm_files_remote: "npm"
|
||||
check_mutable_updates: true
|
||||
immutable_patterns:
|
||||
- \.tgz$
|
||||
mutable_patterns:
|
||||
- ^(?!.*\.tgz$).*
|
||||
cache:
|
||||
immutable_ttl: 0
|
||||
mutable_ttl: 600 # Package metadata refreshed after 10 minutes
|
||||
|
||||
local-generic:
|
||||
type: "local"
|
||||
package: "generic"
|
||||
|
||||
@@ -18,10 +18,6 @@ _PACKAGE_MUTABLE_PATTERNS: dict[str, list[str]] = {
|
||||
r"/manifests/(?!sha256:)[^/]+$",
|
||||
r"/tags/list$",
|
||||
],
|
||||
"pypi": [
|
||||
r"simple/", # Per-package and top-level simple index pages
|
||||
],
|
||||
"npm": [],
|
||||
"generic": [],
|
||||
}
|
||||
|
||||
|
||||
+76
-121
@@ -1,4 +1,3 @@
|
||||
import base64
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
@@ -33,10 +32,6 @@ class ArtifactRequest(BaseModel):
|
||||
include_pattern: str
|
||||
|
||||
|
||||
class UpstreamUnreachable(Exception):
|
||||
"""Raised when the upstream backend cannot be contacted (network or timeout error)."""
|
||||
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s")
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -209,11 +204,8 @@ async def cache_single_artifact(url: str, remote_name: str, path: str) -> dict:
|
||||
remote_config = config.get_remote_config(remote_name) or {}
|
||||
is_docker = remote_config.get("package") == "docker" or "/v2/" in url
|
||||
|
||||
# Prepare headers
|
||||
# Prepare headers for Docker registry requests
|
||||
headers = {}
|
||||
username = remote_config.get("username")
|
||||
password = remote_config.get("password")
|
||||
|
||||
if is_docker:
|
||||
if "/manifests/" in url:
|
||||
headers["Accept"] = (
|
||||
@@ -224,8 +216,6 @@ async def cache_single_artifact(url: str, remote_name: str, path: str) -> dict:
|
||||
)
|
||||
elif "/blobs/" in url:
|
||||
headers["Accept"] = "application/octet-stream"
|
||||
elif username and password:
|
||||
headers["Authorization"] = "Basic " + base64.b64encode(f"{username}:{password}".encode()).decode()
|
||||
|
||||
async with httpx.AsyncClient(follow_redirects=True) as client:
|
||||
response = await client.get(url, headers=headers)
|
||||
@@ -260,129 +250,30 @@ async def cache_single_artifact(url: str, remote_name: str, path: str) -> dict:
|
||||
return {"url": url, "status": "error", "error": str(e)}
|
||||
|
||||
|
||||
def _basic_auth_header(remote_cfg: dict) -> dict[str, str]:
|
||||
username = remote_cfg.get("username")
|
||||
password = remote_cfg.get("password")
|
||||
if username and password:
|
||||
token = base64.b64encode(f"{username}:{password}".encode()).decode()
|
||||
return {"Authorization": f"Basic {token}"}
|
||||
return {}
|
||||
|
||||
|
||||
async def _upstream_reachable(url: str, auth_headers: dict | None = None) -> bool:
|
||||
"""HEAD with a short timeout. Returns False only on network/timeout errors."""
|
||||
try:
|
||||
async with httpx.AsyncClient(follow_redirects=True) as client:
|
||||
await client.head(url, headers=auth_headers or {}, timeout=10.0)
|
||||
return True
|
||||
except (httpx.NetworkError, httpx.TimeoutException):
|
||||
return False
|
||||
except Exception:
|
||||
return True # 4xx/5xx means backend is up
|
||||
|
||||
|
||||
async def check_upstream_changed(remote_url: str, remote_name: str, path: str, auth_headers: dict | None = None) -> bool:
|
||||
"""Conditional HEAD against upstream. Returns False only on a definitive 304.
|
||||
Raises UpstreamUnreachable if the backend cannot be contacted."""
|
||||
async def check_upstream_changed(remote_url: str, remote_name: str, path: str) -> bool:
|
||||
"""Conditional HEAD against upstream. Returns False only on a definitive 304."""
|
||||
meta = cache.get_mutable_meta(remote_name, path)
|
||||
if not meta:
|
||||
return True
|
||||
|
||||
headers = dict(auth_headers or {})
|
||||
headers = {}
|
||||
if meta.get("etag"):
|
||||
headers["If-None-Match"] = meta["etag"]
|
||||
if meta.get("last_modified"):
|
||||
headers["If-Modified-Since"] = meta["last_modified"]
|
||||
if not (meta.get("etag") or meta.get("last_modified")):
|
||||
if not headers:
|
||||
return True
|
||||
|
||||
try:
|
||||
async with httpx.AsyncClient(follow_redirects=True) as client:
|
||||
response = await client.head(remote_url, headers=headers)
|
||||
return response.status_code != 304
|
||||
except (httpx.NetworkError, httpx.TimeoutException) as exc:
|
||||
raise UpstreamUnreachable(str(exc)) from exc
|
||||
|
||||
|
||||
async def handle_expired_mutable(remote_name: str, path: str, remote_url: str) -> bool:
|
||||
"""Handle an expired mutable file. Returns True if the cached copy is still valid."""
|
||||
mutable_ttl = config.get_cache_config(remote_name).get("mutable_ttl", 3600)
|
||||
|
||||
remote_cfg = config.get_remote_config(remote_name) or {}
|
||||
auth = _basic_auth_header(remote_cfg)
|
||||
check_updates = remote_cfg.get("check_mutable_updates", False)
|
||||
user_mutable = check_updates and cache.is_mutable_file(path, config.get_user_mutable_patterns(remote_name))
|
||||
|
||||
if user_mutable:
|
||||
try:
|
||||
changed = await check_upstream_changed(remote_url, remote_name, path, auth)
|
||||
except UpstreamUnreachable:
|
||||
cache.mark_index_cached(remote_name, path, mutable_ttl)
|
||||
logger.warning(f"Mutable STALE (backend unreachable): {remote_name}/{path} - TTL extended ({mutable_ttl}s)")
|
||||
return True
|
||||
if not changed:
|
||||
cache.mark_index_cached(remote_name, path, mutable_ttl)
|
||||
logger.info(f"Mutable file UNCHANGED: {remote_name}/{path} - TTL refreshed ({mutable_ttl}s)")
|
||||
return True
|
||||
logger.info(f"Mutable file CHANGED: {remote_name}/{path} - re-downloading")
|
||||
else:
|
||||
if not await _upstream_reachable(remote_url, auth):
|
||||
cache.mark_index_cached(remote_name, path, mutable_ttl)
|
||||
logger.warning(f"Mutable STALE (backend unreachable): {remote_name}/{path} - TTL extended ({mutable_ttl}s)")
|
||||
return True
|
||||
logger.info(f"Mutable file EXPIRED: {remote_name}/{path} - removing from cache")
|
||||
|
||||
cache.cleanup_expired_index(storage, remote_name, path)
|
||||
return False
|
||||
|
||||
|
||||
def _get_content_type(filename: str) -> str:
|
||||
if filename.endswith((".tar.gz", ".tgz")):
|
||||
return "application/gzip"
|
||||
if filename.endswith(".zip") or filename.endswith(".whl"):
|
||||
return "application/zip"
|
||||
if filename.endswith(".exe"):
|
||||
return "application/x-msdownload"
|
||||
if filename.endswith(".rpm"):
|
||||
return "application/x-rpm"
|
||||
if filename.endswith(".xml"):
|
||||
return "application/xml"
|
||||
if filename.endswith((".xml.gz", ".xml.bz2", ".xml.xz")):
|
||||
return "application/gzip"
|
||||
return "application/octet-stream"
|
||||
|
||||
|
||||
def _resolve_content(
|
||||
data: bytes,
|
||||
path: str,
|
||||
filename: str,
|
||||
remote_config: dict,
|
||||
request: Request,
|
||||
) -> 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")
|
||||
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, "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, _get_content_type(filename)
|
||||
except Exception:
|
||||
return True
|
||||
|
||||
|
||||
@app.get("/api/v1/remote/{remote_name}/{path:path}")
|
||||
async def get_artifact(request: Request, remote_name: str, path: str):
|
||||
async def get_artifact(remote_name: str, path: str):
|
||||
# Check if remote is configured
|
||||
remote_config = config.get_remote_config(remote_name)
|
||||
if not remote_config:
|
||||
@@ -437,7 +328,22 @@ async def get_artifact(request: Request, remote_name: str, path: str):
|
||||
|
||||
if cached_key and is_mutable:
|
||||
if not cache.is_index_valid(remote_name, path):
|
||||
if not await handle_expired_mutable(remote_name, path, remote_url):
|
||||
remote_cfg = config.get_remote_config(remote_name) or {}
|
||||
check_updates = remote_cfg.get("check_mutable_updates", False)
|
||||
user_mutable = check_updates and cache.is_mutable_file(path, config.get_user_mutable_patterns(remote_name))
|
||||
if user_mutable:
|
||||
changed = await check_upstream_changed(remote_url, remote_name, path)
|
||||
if not changed:
|
||||
mutable_ttl = config.get_cache_config(remote_name).get("mutable_ttl", 3600)
|
||||
cache.mark_index_cached(remote_name, path, mutable_ttl)
|
||||
logger.info(f"Mutable file UNCHANGED: {remote_name}/{path} - TTL refreshed ({mutable_ttl}s)")
|
||||
else:
|
||||
logger.info(f"Mutable file CHANGED: {remote_name}/{path} - re-downloading")
|
||||
cache.cleanup_expired_index(storage, remote_name, path)
|
||||
cached_key = None
|
||||
else:
|
||||
logger.info(f"Mutable file EXPIRED: {remote_name}/{path} - removing from cache")
|
||||
cache.cleanup_expired_index(storage, remote_name, path)
|
||||
cached_key = None
|
||||
|
||||
if cached_key:
|
||||
@@ -445,11 +351,29 @@ 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)
|
||||
|
||||
# Log cache hit
|
||||
logger.info(f"Cache HIT: {remote_name}/{path} (size: {len(artifact_data)} bytes, key: {cached_key})")
|
||||
|
||||
# Determine content type based on file extension
|
||||
content_type = "application/octet-stream"
|
||||
if filename.endswith(".tar.gz"):
|
||||
content_type = "application/gzip"
|
||||
elif filename.endswith(".zip"):
|
||||
content_type = "application/zip"
|
||||
elif filename.endswith(".exe"):
|
||||
content_type = "application/x-msdownload"
|
||||
elif filename.endswith(".rpm"):
|
||||
content_type = "application/x-rpm"
|
||||
elif filename.endswith(".xml"):
|
||||
content_type = "application/xml"
|
||||
elif filename.endswith((".xml.gz", ".xml.bz2", ".xml.xz")):
|
||||
content_type = "application/gzip"
|
||||
|
||||
# Record cache hit metrics
|
||||
metrics.record_cache_hit(remote_name, len(artifact_data))
|
||||
|
||||
# Record artifact mapping in database if not already recorded
|
||||
database.record_artifact_mapping(cached_key, remote_name, path, len(artifact_data))
|
||||
|
||||
return Response(
|
||||
@@ -486,9 +410,25 @@ 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)
|
||||
|
||||
content_type = "application/octet-stream"
|
||||
if filename.endswith(".tar.gz"):
|
||||
content_type = "application/gzip"
|
||||
elif filename.endswith(".zip"):
|
||||
content_type = "application/zip"
|
||||
elif filename.endswith(".exe"):
|
||||
content_type = "application/x-msdownload"
|
||||
elif filename.endswith(".rpm"):
|
||||
content_type = "application/x-rpm"
|
||||
elif filename.endswith(".xml"):
|
||||
content_type = "application/xml"
|
||||
elif filename.endswith((".xml.gz", ".xml.bz2", ".xml.xz")):
|
||||
content_type = "application/gzip"
|
||||
|
||||
# Record cache miss metrics
|
||||
metrics.record_cache_miss(remote_name, len(artifact_data))
|
||||
|
||||
# Record artifact mapping in database
|
||||
cache_key = storage.get_object_key(remote_name, path)
|
||||
database.record_artifact_mapping(cache_key, remote_name, path, len(artifact_data))
|
||||
|
||||
@@ -541,7 +481,22 @@ async def docker_v2_proxy(request: Request, remote_name: str, path: str):
|
||||
|
||||
if cached_key and is_mutable:
|
||||
if not cache.is_index_valid(remote_name, path):
|
||||
if not await handle_expired_mutable(remote_name, path, remote_url):
|
||||
remote_cfg = config.get_remote_config(remote_name) or {}
|
||||
check_updates = remote_cfg.get("check_mutable_updates", False)
|
||||
user_mutable = check_updates and cache.is_mutable_file(path, config.get_user_mutable_patterns(remote_name))
|
||||
if user_mutable:
|
||||
changed = await check_upstream_changed(remote_url, remote_name, path)
|
||||
if not changed:
|
||||
mutable_ttl = config.get_cache_config(remote_name).get("mutable_ttl", 3600)
|
||||
cache.mark_index_cached(remote_name, path, mutable_ttl)
|
||||
logger.info(f"Mutable file UNCHANGED: {remote_name}/{path} - TTL refreshed ({mutable_ttl}s)")
|
||||
else:
|
||||
logger.info(f"Mutable file CHANGED: {remote_name}/{path} - re-downloading")
|
||||
cache.cleanup_expired_index(storage, remote_name, path)
|
||||
cached_key = None
|
||||
else:
|
||||
logger.info(f"Mutable file EXPIRED: {remote_name}/{path} - removing from cache")
|
||||
cache.cleanup_expired_index(storage, remote_name, path)
|
||||
cached_key = None
|
||||
|
||||
if not cached_key:
|
||||
|
||||
@@ -72,35 +72,6 @@ TEST_REMOTES = {
|
||||
"package": "generic",
|
||||
"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",
|
||||
"immutable_patterns": [
|
||||
"packages/.*\\.whl$",
|
||||
"packages/.*\\.whl\\.metadata$",
|
||||
"packages/.*\\.tar\\.gz$",
|
||||
],
|
||||
"cache": {"immutable_ttl": 0, "mutable_ttl": 0},
|
||||
},
|
||||
"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},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -133,44 +133,6 @@ class TestGetMutablePatterns:
|
||||
assert r"repomd\.xml$" in patterns
|
||||
assert r"custom-meta\.xml$" in patterns
|
||||
|
||||
def test_npm_has_no_package_defaults(self, make_config):
|
||||
cfg = make_config({"r": {"type": "remote", "package": "npm", "base_url": "https://x.com"}})
|
||||
assert cfg.get_mutable_patterns("r") == []
|
||||
|
||||
def test_npm_explicit_mutable_pattern_matches_metadata(self, make_config):
|
||||
import re
|
||||
|
||||
cfg = make_config(
|
||||
{
|
||||
"r": {
|
||||
"type": "remote",
|
||||
"package": "npm",
|
||||
"base_url": "https://x.com",
|
||||
"mutable_patterns": [r"^(?!.*\.tgz$).*"],
|
||||
}
|
||||
}
|
||||
)
|
||||
patterns = cfg.get_mutable_patterns("r")
|
||||
assert any(re.search(p, "express") for p in patterns)
|
||||
assert any(re.search(p, "@babel/core") for p in patterns)
|
||||
|
||||
def test_npm_explicit_mutable_pattern_excludes_tarballs(self, make_config):
|
||||
import re
|
||||
|
||||
cfg = make_config(
|
||||
{
|
||||
"r": {
|
||||
"type": "remote",
|
||||
"package": "npm",
|
||||
"base_url": "https://x.com",
|
||||
"mutable_patterns": [r"^(?!.*\.tgz$).*"],
|
||||
}
|
||||
}
|
||||
)
|
||||
patterns = cfg.get_mutable_patterns("r")
|
||||
assert not any(re.search(p, "express-4.18.2.tgz") for p in patterns)
|
||||
assert not any(re.search(p, "express/-/express-4.18.2.tgz") for p in patterns)
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# get_immutable_patterns
|
||||
|
||||
+6
-246
@@ -248,13 +248,12 @@ class TestDockerProxy:
|
||||
deps["cache"].is_index_valid.return_value = False # but TTL expired
|
||||
deps["storage"].download_object.return_value = manifest
|
||||
|
||||
with patch("artifactapi.main._upstream_reachable", new_callable=AsyncMock, return_value=True):
|
||||
with patch(
|
||||
"artifactapi.main.cache_single_artifact",
|
||||
new_callable=AsyncMock,
|
||||
return_value={"status": "cached"},
|
||||
) as mock_fetch:
|
||||
response = client.get("/v2/docker-test/library/nginx/manifests/latest")
|
||||
with patch(
|
||||
"artifactapi.main.cache_single_artifact",
|
||||
new_callable=AsyncMock,
|
||||
return_value={"status": "cached"},
|
||||
) as mock_fetch:
|
||||
response = client.get("/v2/docker-test/library/nginx/manifests/latest")
|
||||
|
||||
mock_fetch.assert_called_once()
|
||||
assert response.status_code == 200
|
||||
@@ -453,56 +452,6 @@ class TestGenericArtifactRoute:
|
||||
|
||||
assert response.status_code == 502
|
||||
|
||||
def test_mutable_changed_redownloads_successfully(self, client, patched_deps):
|
||||
"""When check_mutable_updates=True and upstream says 200, fresh copy is fetched and served."""
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"fresh metadata"
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = False
|
||||
deps["cache"].get_mutable_meta.return_value = {"etag": '"abc"'}
|
||||
|
||||
with patch("artifactapi.main.check_upstream_changed", new_callable=AsyncMock, return_value=True):
|
||||
with patch("artifactapi.main.cache_single_artifact", new_callable=AsyncMock) as mock_cache:
|
||||
mock_cache.return_value = {"status": "cached", "etag": '"def"', "last_modified": None}
|
||||
response = client.get("/api/v1/remote/check-mutable-test/metadata.json")
|
||||
|
||||
assert response.status_code == 200
|
||||
mock_cache.assert_called_once()
|
||||
|
||||
def test_mutable_backend_unreachable_on_check_updates_keeps_stale(self, client, patched_deps):
|
||||
"""When check_mutable_updates=True and backend is unreachable, stale copy is kept and TTL refreshed."""
|
||||
from artifactapi.main import UpstreamUnreachable
|
||||
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"stale metadata"
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = False
|
||||
deps["cache"].get_mutable_meta.return_value = {"etag": '"abc"'}
|
||||
|
||||
with patch("artifactapi.main.check_upstream_changed", side_effect=UpstreamUnreachable("connection refused")):
|
||||
response = client.get("/api/v1/remote/check-mutable-test/metadata.json")
|
||||
|
||||
assert response.status_code == 200
|
||||
deps["cache"].mark_index_cached.assert_called()
|
||||
deps["storage"].client.delete_object.assert_not_called()
|
||||
|
||||
def test_mutable_backend_unreachable_on_expiry_keeps_stale(self, client, patched_deps):
|
||||
"""When a regular mutable file expires and backend is unreachable, stale copy is kept and TTL refreshed."""
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"stale APKINDEX"
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = False
|
||||
|
||||
with patch("artifactapi.main._upstream_reachable", new_callable=AsyncMock, return_value=False):
|
||||
response = client.get("/api/v1/remote/alpine-test/alpine/v3.18/x86_64/APKINDEX.tar.gz")
|
||||
|
||||
assert response.status_code == 200
|
||||
deps["cache"].mark_index_cached.assert_called()
|
||||
deps["storage"].client.delete_object.assert_not_called()
|
||||
|
||||
def test_mutable_flag_off_skips_conditional_check(self, client, patched_deps):
|
||||
"""When check_mutable_updates is not set, expired mutable files are always re-fetched."""
|
||||
deps = patched_deps
|
||||
@@ -652,192 +601,3 @@ class TestConfigEndpoint:
|
||||
data = response.json()
|
||||
assert "remotes" in data
|
||||
assert "alpine-test" in data["remotes"]
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# PyPI remote /api/v1/remote/pypi-test/...
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestPyPIRemote:
|
||||
def test_simple_index_is_mutable(self, client, patched_deps):
|
||||
"""simple/ paths are detected as mutable (package-type default)."""
|
||||
deps = patched_deps
|
||||
html = b"<html><body><a href='https://files.pythonhosted.org/packages/requests-2.31.0.tar.gz'>...</a></body></html>"
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = html
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/pypi-test/simple/requests/")
|
||||
assert response.status_code == 200
|
||||
deps["cache"].mark_index_cached.assert_not_called()
|
||||
|
||||
def test_simple_index_urls_rewritten_to_proxy(self, client, patched_deps):
|
||||
"""files.pythonhosted.org URLs in a cached simple index are rewritten to our proxy."""
|
||||
deps = patched_deps
|
||||
html = b"<html><body><a href='https://files.pythonhosted.org/packages/requests-2.31.0.tar.gz'>...</a></body></html>"
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = html
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
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
|
||||
|
||||
def test_simple_index_content_type_is_html(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"<html></html>"
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/pypi-test/simple/requests/")
|
||||
assert response.status_code == 200
|
||||
assert "text/html" in response.headers["content-type"]
|
||||
|
||||
def test_simple_index_cache_miss_fetches_upstream(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
html = b"<html><body><a href='https://files.pythonhosted.org/packages/p-1.0.whl'>...</a></body></html>"
|
||||
deps["storage"].exists.return_value = False
|
||||
deps["storage"].download_object.return_value = html
|
||||
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/pypi-test/simple/requests/")
|
||||
|
||||
mock_fetch.assert_called_once()
|
||||
assert response.status_code == 200
|
||||
assert b"files.pythonhosted.org" not in response.content
|
||||
|
||||
def test_wheel_file_immutable_returns_correct_content_type(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
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")
|
||||
assert response.status_code == 200
|
||||
assert "application/zip" in response.headers["content-type"]
|
||||
assert response.headers["X-Artifact-Source"] == "cache"
|
||||
|
||||
def test_sdist_immutable_returns_correct_content_type(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
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")
|
||||
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")
|
||||
assert response.status_code == 403
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# npm remote /api/v1/remote/npm-test/...
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
class TestNpmRemote:
|
||||
def test_package_metadata_is_mutable(self, client, patched_deps):
|
||||
"""Top-level package metadata paths are detected as mutable."""
|
||||
deps = patched_deps
|
||||
meta = b'{"name":"express","versions":{}}'
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = meta
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/npm-test/express")
|
||||
assert response.status_code == 200
|
||||
deps["cache"].mark_index_cached.assert_not_called()
|
||||
|
||||
def test_metadata_tarball_urls_rewritten_to_proxy(self, client, patched_deps):
|
||||
"""registry.npmjs.org tarball URLs in metadata JSON are rewritten to our proxy."""
|
||||
deps = patched_deps
|
||||
meta = b'{"dist":{"tarball":"https://registry.npmjs.org/express/-/express-4.18.2.tgz"}}'
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = meta
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/npm-test/express")
|
||||
assert response.status_code == 200
|
||||
assert b"registry.npmjs.org" not in response.content
|
||||
assert b"/api/v1/remote/npm-test/express/-/express-4.18.2.tgz" in response.content
|
||||
|
||||
def test_metadata_content_type_is_json(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b'{"name":"express"}'
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/npm-test/express")
|
||||
assert response.status_code == 200
|
||||
assert "application/json" in response.headers["content-type"]
|
||||
|
||||
def test_scoped_package_metadata_rewritten(self, client, patched_deps):
|
||||
"""@scope/package metadata URLs are also rewritten back to the same npm-test remote."""
|
||||
deps = patched_deps
|
||||
meta = b'{"dist":{"tarball":"https://registry.npmjs.org/@babel/core/-/core-7.21.0.tgz"}}'
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = meta
|
||||
deps["cache"].is_mutable_file.return_value = True
|
||||
deps["cache"].is_index_valid.return_value = True
|
||||
|
||||
response = client.get("/api/v1/remote/npm-test/@babel/core")
|
||||
assert response.status_code == 200
|
||||
assert b"registry.npmjs.org" not in response.content
|
||||
assert b"/api/v1/remote/npm-test/@babel/core/-/core-7.21.0.tgz" in response.content
|
||||
|
||||
def test_tarball_not_rewritten(self, client, patched_deps):
|
||||
"""Tarball requests (.tgz) bypass URL rewriting and return binary."""
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"\x1f\x8b tgz bytes"
|
||||
deps["cache"].is_mutable_file.return_value = False
|
||||
|
||||
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"]
|
||||
assert response.headers["X-Artifact-Source"] == "cache"
|
||||
|
||||
def test_metadata_cache_miss_fetches_upstream(self, client, patched_deps):
|
||||
deps = patched_deps
|
||||
meta = b'{"dist":{"tarball":"https://registry.npmjs.org/lodash/-/lodash-4.17.21.tgz"}}'
|
||||
deps["storage"].exists.return_value = False
|
||||
deps["storage"].download_object.return_value = meta
|
||||
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/npm-test/lodash")
|
||||
|
||||
mock_fetch.assert_called_once()
|
||||
assert response.status_code == 200
|
||||
assert b"registry.npmjs.org" not in response.content
|
||||
|
||||
def test_tarball_immutable_allowed_on_npm_remote(self, client, patched_deps):
|
||||
"""Tarballs (.tgz) match immutable_patterns and are served without rewriting."""
|
||||
deps = patched_deps
|
||||
deps["storage"].exists.return_value = True
|
||||
deps["storage"].download_object.return_value = b"tgz bytes"
|
||||
deps["cache"].is_mutable_file.return_value = False
|
||||
|
||||
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"]
|
||||
|
||||
Reference in New Issue
Block a user