Watch
1
0
Fork
You've already forked pkg-proxy
1
mirror of https://github.com/git-pkgs/proxy.git synced 2026-11-09 15:49:16 -05:00
pkg-proxy/internal/handler/package_routes.go
simon chrzanowski 832a441781
Add package routes for private Composer and npm registries (#426)
* Add Composer package routes for private repositories

- Add upstream.composer_routes mapping package name patterns to repositories
- Serve matching packages only from their route, with no fallback to the default repository
- Qualify metadata and artifact cache keys with the route's upstream
- Give routed versions an empty notification-url so installs are not reported to notify-batch
- Document routes in configuration docs, example config and README

* Add npm package routes for private registries

- Add upstream.npm_routes mapping package name patterns to registries
- Serve matching packages only from their route, with no fallback to upstream.npm
- Resolve and validate tarball URLs against the route's registry
- Qualify metadata and artifact cache keys with the route's upstream
- Document npm routes and the audit endpoint limitation

* Share routed artifact filename qualification between handlers

* Match Composer routes without the ~dev suffix

Packagist serves a package's dev versions from {name}~dev.json, and the
handler matched routes against the name with ~dev still attached. An exact
route for example/library therefore missed /p2/example/library~dev.json, and
the private package's dev metadata came from the default repository.

- Match routes against the package name without ~dev, keeping it in the
  upstream URL and the cache key so the two files stay apart
- Add a regression test with an exact route

* Keep routed npm publish times out of the shared versions row

The download cooldown check stores publish times under the plain version
PURL, which does not say which registry a version came from. A time read
from the default registry was trusted for a private version of the same
name, so a private release published an hour ago passed a seven-day
cooldown when the public one was a month old.

- Skip the stored row for routed packages, both reading and writing, and
  take the publish time from the route's metadata, which is cached under
  the route
- This also stops a private time from holding back the public version, and
  a route's previous upstream from lending its times to the new one
- Cover adding a route after a public download, the reverse order, and
  moving a route to another upstream
2026-10-11 18:06:18 +01:00

74 lines
2.3 KiB
Go

package handler
import (
"crypto/sha256"
"encoding/hex"
"path"
"sort"
"strings"
)
// routeIDLength is the number of hex characters of the upstream URL digest
// that qualify cache entries of a routed package.
const routeIDLength = 16
// packageRoutes sends packages whose names match a pattern to a dedicated
// upstream instead of the ecosystem's default registry. A matched package is
// never looked up anywhere else, so a public package with the same name cannot
// replace it.
type packageRoutes struct {
routes []packageRoute // longest pattern first
}
type packageRoute struct {
pattern string
url string
id string
}
func newPackageRoutes(patterns map[string]string) packageRoutes {
routes := make([]packageRoute, 0, len(patterns))
for pattern, upstreamURL := range patterns {
upstreamURL = strings.TrimSuffix(upstreamURL, "/")
digest := sha256.Sum256([]byte(upstreamURL))
routes = append(routes, packageRoute{
pattern: strings.ToLower(pattern),
url: upstreamURL,
id: hex.EncodeToString(digest[:])[:routeIDLength],
})
}
sort.Slice(routes, func(i, j int) bool {
if len(routes[i].pattern) != len(routes[j].pattern) {
return len(routes[i].pattern) > len(routes[j].pattern)
}
return routes[i].pattern < routes[j].pattern
})
return packageRoutes{routes: routes}
}
// match returns the route for a package name, if any pattern matches it.
func (r packageRoutes) match(packageName string) (packageRoute, bool) {
name := strings.ToLower(packageName)
for _, route := range r.routes {
if ok, _ := path.Match(route.pattern, name); ok {
return route, true
}
}
return packageRoute{}, false
}
// cacheKey qualifies a package's metadata cache key with the route's upstream,
// so entries cached from the default registry, or from a route's previous
// upstream, are never served for a routed package.
func (r packageRoute) cacheKey(packageName string) string {
return "routes/" + r.id + "/" + packageName
}
// cacheFilename qualifies a routed package's artifact filename the same way as
// cacheKey, and leaves other packages' filenames unchanged.
func (r packageRoutes) cacheFilename(packageName, filename string) string {
if route, routed := r.match(packageName); routed {
return route.id + "/" + filename
}
return filename
}