Files
artifactapi/internal/api/v1/proxy.go
T
unkinben d154fbf3f3 feat: github_rpm metadata-only remote (GitHub releases as a yum repo, no precache) (#107)
## Why

Publishing RPMs to GitHub releases is common, but consuming them with `dnf` requires repodata GitHub does not provide, and mirroring every package into a local repo wastes storage and staleness-tracking on artifacts that already have a durable home. This exposes GitHub releases as a first-class RPM source that synthesizes repodata on the fly and **never precaches the packages**.

## What

Add a `github_rpm` remote package type backed by a metadata-only provider.

- Introduce a `RemoteServer` interception hook (the remote-side analog of `LocalIndexer`): `handleProxy` lets a provider fully answer a request before the byte-proxy engine, passing the request-derived proxy base URL and the DB as a `RemoteMetadataStore`.
- Scan a repo's releases via the GitHub API (`base_url` = the releases API root) for `.rpm` assets, filtered by the remote's `patterns` (regex on asset filename), and reuse the existing local-rpm repodata generators to emit `repomd.xml`/`primary`/`filelists`/`other`.
- Derive per-asset metadata without precaching: fetch only the RPM header via a ranged GET (retrying with a larger range on a truncated-header parse) for NEVRA, requires/provides/conflicts/obsoletes and files; take the sha256 from the GitHub asset `digest` when present, else compute it once by streaming.
- Cache derived metadata in `rpm_metadata` keyed by asset path; re-scan no more often than `mutable_ttl`, pruning assets that disappear upstream.
- Serve each package's `<location>` as the github-relative download path so the client comes back to this remote, which **302-redirects** to the `releases_remote` (an existing generic github.com remote) that streams the actual bytes.

Reuse the existing `releases_remote` field as the redirect target — it already carries exactly this "downloads served by remote X" semantic end to end, so no new schema/model field is needed.

Extend the shared RPM metadata model with conflicts/obsoletes (JSONB columns, added idempotently) so both local and `github_rpm` repodata resolve upgrades and conflicts; the local upload path records them too.

## No-precache mechanics

- **Dependency metadata**: always from the ranged header fetch (header precedes payload; `rpm.Read` stops at the payload boundary), giving `dnf` full resolution. Default range 1 MiB, doubling to 16 MiB.
- **Checksum**: prefer the GitHub asset `digest` (no download); fall back to a one-time streamed sha256 only when absent. Header-only "minimal mode" (no deps) is rejected as a default because `dnf` needs accurate provides/requires and a correct pkgid checksum to install.

## Tests

Header-range parsing incl. the retry loop, digest-vs-computed checksum selection, repodata synthesis with the redirect-able `<location href>`, the 302 redirect path (and the guard when `releases_remote` is unset), asset pattern filtering, and stale-asset pruning. `go build`/`vet`/`test` green; pre-commit clean.

## Follow-ups

- `github_apk` / `github_deb` metadata-only remotes (same pattern; not in this PR).
- Terraform provider support for `artifactapi_remote_github_rpm` ships as a separate PR against `terraform-provider-artifactapi` (depends on this API surface).

Reviewed-on: #107
Co-authored-by: Ben Vincent <ben@unkin.net>
Co-committed-by: Ben Vincent <ben@unkin.net>
2026-08-10 20:54:44 +10:00

235 lines
7.0 KiB
Go

package v1
import (
"errors"
"fmt"
"io"
"log/slog"
"net/http"
"github.com/go-chi/chi/v5"
v2 "git.unkin.net/unkin/artifactapi/internal/api/v2"
"git.unkin.net/unkin/artifactapi/internal/database"
"git.unkin.net/unkin/artifactapi/internal/provider"
"git.unkin.net/unkin/artifactapi/internal/proxy"
"git.unkin.net/unkin/artifactapi/internal/storage"
"git.unkin.net/unkin/artifactapi/internal/virtual"
)
type ProxyHandler struct {
engine *proxy.Engine
virtualEngine *virtual.Engine
db *database.DB
store *storage.S3
local *v2.LocalHandler
cas *storage.CAS
}
func NewProxyHandler(engine *proxy.Engine, virtualEngine *virtual.Engine, db *database.DB, store *storage.S3, local *v2.LocalHandler) *ProxyHandler {
return &ProxyHandler{
engine: engine,
virtualEngine: virtualEngine,
db: db,
store: store,
local: local,
cas: storage.NewCAS(store),
}
}
func (h *ProxyHandler) Routes() chi.Router {
r := chi.NewRouter()
r.Get("/remote/{remoteName}/*", h.handleProxy)
r.Get("/local/{localName}/*", h.handleLocal)
r.Get("/virtual/{virtualName}/*", h.handleVirtual)
return r
}
// DockerV2Routes mounts the Docker Registry HTTP API V2. Reads (GET/HEAD)
// dispatch to a local registry implementation for local docker repos and fall
// through to the upstream proxy otherwise; writes (POST/PATCH/PUT/DELETE) are
// only valid for local docker repos and drive push.
func (h *ProxyHandler) DockerV2Routes() chi.Router {
r := chi.NewRouter()
r.Get("/", h.handleDockerPing)
r.Head("/", h.handleDockerPing)
r.Get("/{remoteName}/*", h.dockerGet)
r.Head("/{remoteName}/*", h.dockerHead)
r.Post("/{remoteName}/*", h.dockerPost)
r.Patch("/{remoteName}/*", h.dockerPatch)
r.Put("/{remoteName}/*", h.dockerPut)
r.Delete("/{remoteName}/*", h.dockerDelete)
return r
}
func (h *ProxyHandler) handleDockerPing(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Docker-Distribution-Api-Version", "registry/2.0")
w.WriteHeader(http.StatusOK)
}
func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
remoteName := chi.URLParam(r, "remoteName")
path := chi.URLParam(r, "*")
remote, err := h.db.GetRemote(r.Context(), remoteName)
if err != nil {
http.Error(w, fmt.Sprintf("remote %q not found", remoteName), http.StatusNotFound)
return
}
prov, err := provider.Get(remote.PackageType)
if err != nil {
http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
return
}
// Metadata-only remotes (e.g. github_rpm) synthesize their own responses and
// redirect package downloads to a backend remote instead of proxying bytes.
if rs, ok := prov.(provider.RemoteServer); ok {
proxyBaseURL := fmt.Sprintf("%s://%s", scheme(r), r.Host)
if rs.ServeRemote(w, r, *remote, path, proxyBaseURL, h.db) {
return
}
}
result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
if err != nil {
var proxyErr *proxy.ProxyError
if errors.As(err, &proxyErr) {
http.Error(w, proxyErr.Message, proxyErr.Status)
return
}
slog.Error("proxy fetch failed", "remote", remoteName, "path", path, "error", err)
http.Error(w, "bad gateway", http.StatusBadGateway)
return
}
defer result.Reader.Close()
w.Header().Set("Content-Type", result.ContentType)
w.Header().Set("X-Artifact-Source", result.Source)
if result.Size > 0 {
w.Header().Set("X-Artifact-Size", fmt.Sprintf("%d", result.Size))
}
w.WriteHeader(http.StatusOK)
io.Copy(w, result.Reader)
}
func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
remoteName := chi.URLParam(r, "remoteName")
path := chi.URLParam(r, "*")
remote, err := h.db.GetRemote(r.Context(), remoteName)
if err != nil {
http.Error(w, fmt.Sprintf("remote %q not found", remoteName), http.StatusNotFound)
return
}
prov, err := provider.Get(remote.PackageType)
if err != nil {
http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
return
}
result, err := h.engine.Head(r.Context(), *remote, path, prov)
if err != nil {
var proxyErr *proxy.ProxyError
if errors.As(err, &proxyErr) {
http.Error(w, proxyErr.Message, proxyErr.Status)
return
}
slog.Error("proxy head failed", "remote", remoteName, "path", path, "error", err)
http.Error(w, "bad gateway", http.StatusBadGateway)
return
}
w.Header().Set("Content-Type", result.ContentType)
w.Header().Set("X-Artifact-Source", result.Source)
if result.Size > 0 {
w.Header().Set("Content-Length", fmt.Sprintf("%d", result.Size))
}
w.WriteHeader(http.StatusOK)
}
func (h *ProxyHandler) handleVirtual(w http.ResponseWriter, r *http.Request) {
virtualName := chi.URLParam(r, "virtualName")
path := chi.URLParam(r, "*")
virt, err := h.db.GetVirtual(r.Context(), virtualName)
if err != nil {
http.Error(w, fmt.Sprintf("virtual %q not found", virtualName), http.StatusNotFound)
return
}
proxyBaseURL := fmt.Sprintf("%s://%s", scheme(r), r.Host)
body, contentType, err := h.virtualEngine.Fetch(r.Context(), *virt, path, proxyBaseURL)
if err != nil {
slog.Error("virtual fetch failed", "virtual", virtualName, "path", path, "error", err)
http.Error(w, "bad gateway", http.StatusBadGateway)
return
}
w.Header().Set("Content-Type", contentType)
w.Header().Set("X-Artifact-Source", "virtual")
w.WriteHeader(http.StatusOK)
w.Write(body)
}
func (h *ProxyHandler) handleLocal(w http.ResponseWriter, r *http.Request) {
localName := chi.URLParam(r, "localName")
path := chi.URLParam(r, "*")
remote, err := h.db.GetRemote(r.Context(), localName)
if err != nil {
http.Error(w, fmt.Sprintf("local %q not found", localName), http.StatusNotFound)
return
}
prov, _ := provider.Get(remote.PackageType)
if indexer, ok := prov.(provider.LocalIndexer); ok {
if indexer.ServeLocalIndex(w, r, h.db, remote.Name, path) {
return
}
}
h.serveLocalFile(w, r, localName, path)
}
func (h *ProxyHandler) serveLocalFile(w http.ResponseWriter, r *http.Request, repoName, path string) {
file, err := h.db.GetLocalFile(r.Context(), repoName, path)
if err != nil {
slog.Error("local file lookup failed", "repo", repoName, "path", path, "error", err)
http.Error(w, "internal error", http.StatusInternalServerError)
return
}
if file == nil {
http.Error(w, "not found", http.StatusNotFound)
return
}
s3Key := storage.BlobKey(file.ContentHash[len("sha256:"):])
reader, info, err := h.store.Download(r.Context(), s3Key)
if err != nil {
slog.Error("local file download failed", "repo", repoName, "path", path, "error", err)
http.Error(w, "internal error", http.StatusInternalServerError)
return
}
defer reader.Close()
w.Header().Set("Content-Type", info.ContentType)
w.Header().Set("Content-Length", fmt.Sprintf("%d", info.Size))
w.Header().Set("X-Artifact-Source", "local")
w.WriteHeader(http.StatusOK)
io.Copy(w, reader)
}
func scheme(r *http.Request) string {
if r.TLS != nil {
return "https"
}
if fwd := r.Header.Get("X-Forwarded-Proto"); fwd != "" {
return fwd
}
return "http"
}