feat: github_deb metadata-only package type

Add the Debian/apt analog of github_rpm: a metadata-only remote that scans a GitHub repo's releases for .deb assets, derives per-asset control metadata via a ranged prefix fetch (never downloading whole packages), synthesizes a flat apt repository, and redirects .deb downloads to a backend releases_remote. - Add PackageGitHubDeb to the package-type enum + validity map. - Add the github_deb provider (internal/provider/deb/github.go): ServeRemote serves Packages/Packages.gz/Release, 404s the signed index variants (consumed via [trusted=yes]), and 302-redirects *.deb to the releases_remote; deriveAsset ranged-GETs the ar prefix, locates control.tar.*, and parses the control paragraph, doubling the range on truncation; sha256 comes from the asset digest when present, else a one-time full stream. - Add the github_deb background Syncer (internal/provider/deb/syncer.go): its own worker pool, shared rate limiter, deduped queue, and DB-lease-gated scans. - Add github_deb_sync_state table plus ListGitHubDebRemotes/Claim/Release DB helpers (separate from the rpm ones). - Prime github_deb remotes on create and run the deb syncer alongside the rpm one; route prime-on-create by package type. - Reuse the deb apt-index generators and control parser; skip empty hash lines in the Packages index so a SHA256-only metadata entry is valid.
2026-08-11 22:21:05 +10:00
parent 60f008debc
commit b2a6be8eb5
11 changed files with 1889 additions and 14 deletions
@@ -0,0 +1,300 @@
+package deb
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"sync"
+	"testing"
+	"time"
+
+	"golang.org/x/time/rate"
+
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/internal/testsupport"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
+)
+
+// fakeSyncStore is an in-memory SyncStore: the metadata cache (via the embedded
+// fakeStore) plus the shared sync-state lease, whose claim mirrors the atomic
+// semantics of the real SQL (recency gate AND no live lease).
+type fakeSyncStore struct {
+	*fakeStore
+
+	mu         sync.Mutex
+	remotes    []models.Remote
+	leaseOwner map[string]string
+	leaseExp   map[string]time.Time
+	lastSynced map[string]time.Time
+	etags      map[string]string
+}
+
+func newFakeSyncStore() *fakeSyncStore {
+	return &fakeSyncStore{
+		fakeStore:  newFakeStore(),
+		leaseOwner: map[string]string{},
+		leaseExp:   map[string]time.Time{},
+		lastSynced: map[string]time.Time{},
+		etags:      map[string]string{},
+	}
+}
+
+func (f *fakeSyncStore) ListGitHubDebRemotes(_ context.Context) ([]models.Remote, error) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return append([]models.Remote(nil), f.remotes...), nil
+}
+
+func (f *fakeSyncStore) ClaimGitHubDebSyncLease(_ context.Context, name, owner string, freshness, lease time.Duration) (bool, string, error) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	now := time.Now()
+	ls, hasLS := f.lastSynced[name]
+	exp, hasExp := f.leaseExp[name]
+	freshOK := !hasLS || now.Sub(ls) >= freshness
+	leaseOK := !hasExp || exp.Before(now)
+	if freshOK && leaseOK {
+		f.leaseOwner[name] = owner
+		f.leaseExp[name] = now.Add(lease)
+		return true, f.etags[name], nil
+	}
+	return false, "", nil
+}
+
+func (f *fakeSyncStore) ReleaseGitHubDebSyncLease(_ context.Context, name, owner, etag string, syncedAt time.Time) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	if f.leaseOwner[name] != owner {
+		return nil
+	}
+	f.lastSynced[name] = syncedAt
+	f.etags[name] = etag
+	delete(f.leaseOwner, name)
+	delete(f.leaseExp, name)
+	return nil
+}
+
+func testSyncConfig() SyncConfig {
+	return SyncConfig{RatePerSec: 1000, Burst: 100, Workers: 1, PollInterval: time.Hour}
+}
+
+// (a) A 304 conditional response must derive nothing: no asset fetches and
+// changed=false, so an unchanged repo is nearly free.
+func TestSyncerConditionalNotModifiedSkipsDerive(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	fx.etag = `"v1"`
+	p := newTestProvider()
+	store := newFakeStore()
+	remote := fx.remote()
+
+	etag1, changed, err := p.scanWithState(context.Background(), remote, store, "")
+	if err != nil {
+		t.Fatalf("first scan: %v", err)
+	}
+	if !changed || etag1 != `"v1"` {
+		t.Fatalf("first scan changed=%v etag=%q, want true and \"v1\"", changed, etag1)
+	}
+	priorRange := fx.rangeHit["demo_1.2-3_amd64.deb"]
+	if priorRange == 0 {
+		t.Fatal("first scan should have fetched the asset control")
+	}
+
+	etag2, changed2, err := p.scanWithState(context.Background(), remote, store, etag1)
+	if err != nil {
+		t.Fatalf("second scan: %v", err)
+	}
+	if changed2 {
+		t.Fatal("304 scan must report changed=false")
+	}
+	if etag2 != etag1 {
+		t.Fatalf("etag changed across 304: %q -> %q", etag1, etag2)
+	}
+	if fx.notModHit != 1 {
+		t.Fatalf("want exactly one 304 releases response, got %d", fx.notModHit)
+	}
+	if got := fx.rangeHit["demo_1.2-3_amd64.deb"]; got != priorRange {
+		t.Fatalf("304 scan re-fetched asset control: %d -> %d", priorRange, got)
+	}
+}
+
+// (b) On a real change, only the newly added asset is derived.
+func TestSyncerIncrementalDerivesOnlyNewAsset(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	fx.etag = `"v1"`
+	p := newTestProvider()
+	store := newFakeStore()
+	remote := fx.remote()
+
+	if _, _, err := p.scanWithState(context.Background(), remote, store, ""); err != nil {
+		t.Fatalf("first scan: %v", err)
+	}
+	demoRange := fx.rangeHit["demo_1.2-3_amd64.deb"]
+
+	fx.debBytes["other_9_arm64.deb"] = testsupport.MinimalDeb("other", "9", "arm64")
+	fx.etag = `"v2"`
+
+	if _, changed, err := p.scanWithState(context.Background(), remote, store, `"v1"`); err != nil || !changed {
+		t.Fatalf("second scan changed=%v err=%v", changed, err)
+	}
+
+	rows, _ := store.ListDebMetadataEntries(context.Background(), remote.Name)
+	if len(rows) != 2 {
+		t.Fatalf("want 2 cached rows after incremental derive, got %d", len(rows))
+	}
+	if got := fx.rangeHit["demo_1.2-3_amd64.deb"]; got != demoRange {
+		t.Fatalf("already-cached asset was re-fetched: %d -> %d", demoRange, got)
+	}
+	if fx.rangeHit["other_9_arm64.deb"] == 0 {
+		t.Fatal("newly added asset was not derived")
+	}
+}
+
+// (c) The shared limiter caps the request rate.
+func TestRateLimiterCapsRequestRate(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	p := newTestProvider()
+	p.limiter = rate.NewLimiter(rate.Every(120*time.Millisecond), 1)
+	remote := fx.remote()
+
+	start := time.Now()
+	for i := 0; i < 3; i++ {
+		if _, _, _, err := p.fetchReleases(context.Background(), remote, ""); err != nil {
+			t.Fatalf("fetchReleases %d: %v", i, err)
+		}
+	}
+	if elapsed := time.Since(start); elapsed < 200*time.Millisecond {
+		t.Fatalf("rate limiter did not throttle: 3 calls took %v, want >= 200ms", elapsed)
+	}
+}
+
+// (d) Concurrent enqueues for the same remote coalesce to a single queued job.
+func TestSyncerEnqueueDedup(t *testing.T) {
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	s := newSyncer(store, p, testSyncConfig())
+	remote := models.Remote{Name: "acme-deb", PackageType: models.PackageGitHubDeb, MutableTTL: 3600}
+
+	var wg sync.WaitGroup
+	for i := 0; i < 10; i++ {
+		wg.Add(1)
+		go func() { defer wg.Done(); s.enqueue(remote, false) }()
+	}
+	wg.Wait()
+
+	if got := len(s.jobs); got != 1 {
+		t.Fatalf("want exactly 1 coalesced job, got %d", got)
+	}
+}
+
+// (e) Prime-on-create enqueues a prime job.
+func TestSyncerEnqueuePrime(t *testing.T) {
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	s := newSyncer(store, p, testSyncConfig())
+	remote := models.Remote{Name: "acme-deb", PackageType: models.PackageGitHubDeb, MutableTTL: 3600}
+
+	s.EnqueuePrime(remote)
+	select {
+	case job := <-s.jobs:
+		if !job.prime || job.remote.Name != "acme-deb" {
+			t.Fatalf("bad prime job: %+v", job)
+		}
+	default:
+		t.Fatal("EnqueuePrime did not enqueue a job")
+	}
+}
+
+// (f) A held lease prevents a second replica from scanning.
+func TestSyncerLeasePreventsSecondReplica(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	fx.etag = `"v1"`
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	s := newSyncer(store, p, testSyncConfig())
+	remote := fx.remote()
+
+	claimed, _, err := store.ClaimGitHubDebSyncLease(context.Background(), remote.Name, "replica-1", time.Duration(remote.MutableTTL)*time.Second, syncLeaseDuration)
+	if err != nil || !claimed {
+		t.Fatalf("replica-1 claim: claimed=%v err=%v", claimed, err)
+	}
+
+	s.process(context.Background(), syncJob{remote: remote})
+
+	if fx.releasesHit != 0 {
+		t.Fatalf("second replica scanned while lease held: %d releases calls", fx.releasesHit)
+	}
+	if rows, _ := store.ListDebMetadataEntries(context.Background(), remote.Name); len(rows) != 0 {
+		t.Fatalf("second replica derived metadata while lease held: %d rows", len(rows))
+	}
+}
+
+// With the syncer wired and the cache empty, an index request enqueues a prime
+// and returns a retryable 503 when it has not landed within the cold wait.
+func TestServeRemoteColdStartReturns503(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	p.coldWait = 300 * time.Millisecond
+	_ = newSyncer(store, p, testSyncConfig()) // binds p.syncer, but no workers running
+	remote := fx.remote()
+
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodGet, "/api/v1/remote/acme-deb/Packages", nil)
+	if !p.ServeRemote(rec, req, remote, "Packages", "https://x", store) {
+		t.Fatal("ServeRemote did not handle Packages")
+	}
+	if rec.Code != http.StatusServiceUnavailable {
+		t.Fatalf("cold empty cache must return 503, got %d", rec.Code)
+	}
+	if rec.Header().Get("Retry-After") == "" {
+		t.Fatal("503 should carry Retry-After")
+	}
+	if got := len(p.syncer.jobs); got != 1 {
+		t.Fatalf("cold start did not enqueue a prime, jobs=%d", got)
+	}
+}
+
+// With the cache warm, the same request serves the index immediately (no 503).
+func TestServeRemoteWarmCacheServesImmediately(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	_ = newSyncer(store, p, testSyncConfig())
+	remote := fx.remote()
+
+	if err := p.scan(context.Background(), remote, store); err != nil {
+		t.Fatalf("warm scan: %v", err)
+	}
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodGet, "/api/v1/remote/acme-deb/Packages", nil)
+	if !p.ServeRemote(rec, req, remote, "Packages", "https://x", store) {
+		t.Fatal("ServeRemote did not handle Packages")
+	}
+	if rec.Code != http.StatusOK {
+		t.Fatalf("warm cache must serve 200, got %d body=%s", rec.Code, rec.Body.String())
+	}
+}
+
+// A prime job (freshness 0) runs even right after a sync; a periodic job at the
+// same moment is gated by the recency window.
+func TestSyncerPrimeBypassesRecencyPeriodicDoesNot(t *testing.T) {
+	fx := newGitHubFixture(t, true)
+	fx.etag = `"v1"`
+	store := newFakeSyncStore()
+	p := newTestProvider()
+	s := newSyncer(store, p, testSyncConfig())
+	remote := fx.remote()
+
+	var _ provider.RemoteMetadataStore = store
+
+	s.process(context.Background(), syncJob{remote: remote, prime: true})
+	if rows, _ := store.ListDebMetadataEntries(context.Background(), remote.Name); len(rows) != 1 {
+		t.Fatalf("prime did not derive: %d rows", len(rows))
+	}
+	releasesAfterPrime := fx.releasesHit
+
+	s.process(context.Background(), syncJob{remote: remote, prime: false})
+	if fx.releasesHit != releasesAfterPrime {
+		t.Fatalf("periodic scan ran inside recency window: %d -> %d releases calls", releasesAfterPrime, fx.releasesHit)
+	}
+}