Files
artifactapi/internal/api/v2/remotes.go
T
unkin-agent 5fde0ee58e
ci/woodpecker/tag/docker Pipeline was successful
Add github_deb metadata-only package type (#112)
## Why

This stacks the Debian/apt analog of `github_rpm` on top of the deb local+remote work (#111). It lets a GitHub repo's `.deb` release assets be consumed as a real apt repository without artifactapi ever precaching whole packages: it derives per-asset control metadata from a ranged prefix fetch, synthesizes a flat apt repo from the cache, and redirects the actual `.deb` downloads to a backend `releases_remote` (the generic github.com remote).

Base is `benvin/deb-local-remote` (stacked) to keep the diff atomic.

## How

- Adds `github_deb` to the package-type enum and validity map.
- Adds the `github_deb` provider mirroring `github_rpm`: `ServeRemote` serves `Packages`/`Packages.gz`/`Release`, returns 404 for `InRelease`/`Release.gpg` (unsigned, consumed via `[trusted=yes]`), and 302-redirects `*.deb` to `{proxyBaseURL}/api/v1/remote/{releases_remote}/{path}`; cold-start prime with a retryable 503.
- `deriveAsset` ranged-GETs the front of the `.deb` (an `ar` archive), locates and fully reads `control.tar.*`, and parses the control paragraph — doubling the range if the control member is truncated. The Packages `SHA256` comes from the GitHub asset `digest` when present, else a one-time full stream; `MD5sum` is left unset (apt verifies against SHA256 under `[trusted=yes]`).
- Adds a `github_deb` background Syncer (own worker pool, shared rate limiter, deduped queue) with per-remote DB-lease-gated scans so only one replica scans per window.
- Adds the `github_deb_sync_state` table plus `ListGitHubDebRemotes` / `ClaimGitHubDebSyncLease` / `ReleaseGitHubDebSyncLease` DB helpers, kept separate from the rpm ones.
- Primes `github_deb` remotes on create and runs the deb syncer alongside the rpm one; prime-on-create is routed by package type.
- Reuses the deb apt-index generators and control parser; the Packages generator now skips empty hash lines so a SHA256-only entry is valid.

## Notes / deviations

- **Filename convention:** the `Filename` stored in the Packages index is the **github-relative** asset path (same as rpm's `assetPath`), not `pool/<asset>`. This is required for the `.deb` 302 to `{releases_remote=github}/{path}` to resolve against github.com; it still matches the `*.deb` redirect rule.
- **GitHub client helpers** (releases pagination, ranged GET, auth headers) are duplicated into the deb package rather than shared, because the rpm equivalents are unexported in `package rpm` and the task requires not modifying the rpm provider.
- `go build`, `go vet`, `go mod tidy`, and `make test` (`-race`, incl. the Postgres lease integration tests) all pass; pre-commit clean.

Do not merge — for review.

---------

Co-authored-by: unkin-agent <unkin-agent@git.unkin.net>
Reviewed-on: #112
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>
2026-08-11 23:28:11 +10:00

130 lines
3.8 KiB
Go

package v2
import (
"encoding/json"
"fmt"
"net/http"
"github.com/go-chi/chi/v5"
"git.unkin.net/unkin/artifactapi/internal/database"
"git.unkin.net/unkin/artifactapi/pkg/models"
)
// Primer enqueues a background metadata prime for a newly created remote so the
// create call never blocks on a derive. *rpm.Syncer and *deb.Syncer satisfy it.
type Primer interface {
EnqueuePrime(remote models.Remote)
}
type RemotesHandler struct {
db *database.DB
primers map[models.PackageType]Primer
}
// NewRemotesHandler wires the handler to the per-type metadata primers. primers
// may be nil; a package type with no registered primer simply skips priming.
func NewRemotesHandler(db *database.DB, primers map[models.PackageType]Primer) *RemotesHandler {
return &RemotesHandler{db: db, primers: primers}
}
func (h *RemotesHandler) Routes() chi.Router {
r := chi.NewRouter()
r.Get("/", h.list)
r.Post("/", h.create)
r.Get("/{name}", h.get)
r.Put("/{name}", h.update)
r.Delete("/{name}", h.del)
return r
}
func (h *RemotesHandler) list(w http.ResponseWriter, r *http.Request) {
remotes, err := h.db.ListRemotes(r.Context())
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
writeJSON(w, http.StatusOK, remotes)
}
func (h *RemotesHandler) get(w http.ResponseWriter, r *http.Request) {
name := chi.URLParam(r, "name")
remote, err := h.db.GetRemote(r.Context(), name)
if err != nil {
http.Error(w, fmt.Sprintf("remote %q not found", name), http.StatusNotFound)
return
}
writeJSON(w, http.StatusOK, remote)
}
func (h *RemotesHandler) create(w http.ResponseWriter, r *http.Request) {
var remote models.Remote
if err := json.NewDecoder(r.Body).Decode(&remote); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
if !remote.PackageType.Valid() {
http.Error(w, fmt.Sprintf("invalid package type: %q", remote.PackageType), http.StatusBadRequest)
return
}
if remote.RepoType == "" {
remote.RepoType = models.RepoTypeRemote
}
if !remote.RepoType.Valid() {
http.Error(w, fmt.Sprintf("invalid repo type: %q", remote.RepoType), http.StatusBadRequest)
return
}
if remote.RepoType == models.RepoTypeRemote && remote.BaseURL == "" {
http.Error(w, "base_url is required for remote repositories", http.StatusBadRequest)
return
}
if err := remote.ValidatePatterns(); err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
if err := h.db.CreateRemote(r.Context(), &remote); err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
// Prime a metadata-only remote (github_rpm/github_deb) in the background so
// its first index request is served from cache instead of a cold derive.
if primer := h.primers[remote.PackageType]; primer != nil {
primer.EnqueuePrime(remote)
}
writeJSON(w, http.StatusCreated, remote)
}
func (h *RemotesHandler) update(w http.ResponseWriter, r *http.Request) {
name := chi.URLParam(r, "name")
var remote models.Remote
if err := json.NewDecoder(r.Body).Decode(&remote); err != nil {
http.Error(w, "invalid json", http.StatusBadRequest)
return
}
remote.Name = name
if err := remote.ValidatePatterns(); err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
if err := h.db.UpdateRemote(r.Context(), &remote); err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
writeJSON(w, http.StatusOK, remote)
}
func (h *RemotesHandler) del(w http.ResponseWriter, r *http.Request) {
name := chi.URLParam(r, "name")
if err := h.db.DeleteRemote(r.Context(), name); err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
w.WriteHeader(http.StatusNoContent)
}
func writeJSON(w http.ResponseWriter, status int, v any) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(status)
json.NewEncoder(w).Encode(v)
}