Add gems remote type for RubyGems

- add gems package type proxying the compact index and .gem/quick gemspec downloads
- route HEAD on /api/v1/remote/* so gem detects the compact index

README.md

@@ -1,6 +1,6 @@
 # ArtifactAPI
 
-Caching proxy for package repositories. Single Go binary, 12 package types, content-addressable storage, managed by Terraform.
+Caching proxy for package repositories. Single Go binary, 11 package types, content-addressable storage, managed by Terraform.
 
 ## Quick Start
 
@@ -33,7 +33,7 @@ API: `http://localhost:8000` | Frontend: `http://localhost:5173`
 | `terraform` | `*/versions` | `*/download/*/*` |
 | `goproxy` | `@v/list`, `@latest` | `.info`, `.mod`, `.zip` |
 | `cargo` | sparse index files (`config.json` synthesized) | `crates/*/*.crate` |
-| `ansible` | Galaxy `api/` JSON (links rewritten) | `*.tar.gz` |
+| `gems` | compact index (`versions`, `info/*`, `names`), `*specs.4.8.gz` | `gems/*.gem`, `quick/Marshal.4.8/*.gemspec.rz` |
 | `github_rpm` | `repodata/*` (synthesized) | `.rpm` (redirected) |
 
 Providers classify paths automatically. Users only configure what to proxy and TTLs.

e2e-docker/README.md

@@ -23,7 +23,7 @@ already-running stack.
 
 - **Repository lifecycle** — add / change / delete for remote, local and virtual repos.
 - **Caching** — one immutable artifact per remote package type (generic, docker,
-  helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy, cargo, ansible) proxied through the
+  helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy, cargo, gems) proxied through the
   mock upstream: first fetch `X-Artifact-Source: remote`, second `cache`, bytes
   verified against the origin fixture.
 - **Local uploads** — generic (upload/download), pypi (wheel + generated `simple/`

e2e-docker/caching_test.go

@@ -30,7 +30,7 @@ func TestCachingPerProvider(t *testing.T) {
 		{"puppet", "puppet-releases/author-mod-1.0.0.tar.gz", "puppet-releases/author-mod-1.0.0.tar.gz"},
 		{"goproxy", "goproxy/example.com/mod/@v/v1.0.0.zip", "goproxy/example.com/mod/@v/v1.0.0.zip"},
 		{"cargo", "crates/mycrate/mycrate-1.0.0.crate", "crates/mycrate/mycrate-1.0.0.crate"},
-		{"ansible", "galaxy/artifacts/ns-col-1.0.0.tar.gz", "galaxy/artifacts/ns-col-1.0.0.tar.gz"},
+		{"gems", "gems/mygem-1.0.0.gem", "gems/mygem-1.0.0.gem"},
 		{"terraform", "hashicorp/aws/download/pkg.zip", "v1/providers/hashicorp/aws/download/pkg.zip"},
 		{"docker", "library/testimg/blobs/blobdata", "v2/library/testimg/blobs/blobdata"},
 	}

e2e-docker/fixtures/gems/mygem-1.0.0.gem

@@ -0,0 +1 @@
+mygem-1.0.0 e2e fixture

internal/api/v1/proxy.go

@@ -40,6 +40,7 @@ func NewProxyHandler(engine *proxy.Engine, virtualEngine *virtual.Engine, db *da
 func (h *ProxyHandler) Routes() chi.Router {
 	r := chi.NewRouter()
 	r.Get("/remote/{remoteName}/*", h.handleProxy)
+	r.Head("/remote/{remoteName}/*", h.handleProxyHead)
 	r.Get("/local/{localName}/*", h.handleLocal)
 	r.Get("/virtual/{virtualName}/*", h.handleVirtual)
 	return r
@@ -92,10 +93,6 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 		}
 	}
 
-	if _, ok := prov.(provider.QueryForwarder); ok && r.URL.RawQuery != "" {
-		path += "?" + r.URL.RawQuery
-	}
-
 	result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
 	if err != nil {
 		var proxyErr *proxy.ProxyError

internal/api/v1/routes_test.go

@@ -0,0 +1,17 @@
+package v1
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/go-chi/chi/v5"
+)
+
+func TestRoutesRemoteHead(t *testing.T) {
+	r := (&ProxyHandler{}).Routes()
+	for _, m := range []string{http.MethodGet, http.MethodHead} {
+		if !r.Match(chi.NewRouteContext(), m, "/remote/rubygems/versions") {
+			t.Errorf("%s /remote/rubygems/versions not routed", m)
+		}
+	}
+}

internal/provider/ansible/ansible.go

@@ -1,65 +0,0 @@
-// Package ansible proxies an Ansible Galaxy server (v3 collections API):
-// mutable JSON metadata whose links are rewritten back to the remote, plus
-// immutable collection tarballs.
-package ansible
-
-import (
-	"context"
-	"encoding/json"
-	"net/http"
-	"strings"
-
-	"git.unkin.net/unkin/artifactapi/internal/auth"
-	"git.unkin.net/unkin/artifactapi/internal/provider"
-	"git.unkin.net/unkin/artifactapi/pkg/models"
-)
-
-func init() {
-	provider.Register(&Provider{})
-}
-
-type Provider struct{}
-
-func (p *Provider) Type() models.PackageType { return models.PackageAnsible }
-
-func (p *Provider) Classify(path string) provider.Mutability {
-	if isArtifact(path) {
-		return provider.Immutable
-	}
-	return provider.Mutable
-}
-
-func (p *Provider) ContentType(path string) string {
-	if isArtifact(path) {
-		return "application/gzip"
-	}
-	return "application/json"
-}
-
-func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
-	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
-}
-
-// ForwardQuery keeps limit/offset pagination in the proxied path.
-func (p *Provider) ForwardQuery() {}
-
-// RewriteResponse points root-relative hrefs/links and absolute download_url
-// values at the remote. Links stay root-relative, which ansible-galaxy joins
-// onto the server URL, so the cached body is independent of the request host.
-func (p *Provider) RewriteResponse(body []byte, remote models.Remote, _ string) ([]byte, error) {
-	if !json.Valid(body) {
-		return nil, nil
-	}
-	prefix := `"/api/v1/remote/` + remote.Name + `/`
-	content := strings.ReplaceAll(string(body), `"/api/`, prefix+`api/`)
-	content = strings.ReplaceAll(content, `"`+strings.TrimRight(remote.BaseURL, "/")+`/`, prefix)
-	return []byte(content), nil
-}
-
-func (p *Provider) AuthHeaders(_ context.Context, remote models.Remote) (http.Header, error) {
-	return auth.BasicHeaders(remote), nil
-}
-
-func isArtifact(path string) bool {
-	return strings.HasSuffix(path, ".tar.gz")
-}

internal/provider/ansible/ansible_test.go

@@ -1,85 +0,0 @@
-package ansible
-
-import (
-	"encoding/json"
-	"testing"
-
-	"git.unkin.net/unkin/artifactapi/internal/provider"
-	"git.unkin.net/unkin/artifactapi/pkg/models"
-)
-
-func TestClassify(t *testing.T) {
-	p := &Provider{}
-	tests := []struct {
-		path string
-		want provider.Mutability
-	}{
-		{"api/", provider.Mutable},
-		{"api/v3/collections/community/general/versions/?limit=100", provider.Mutable},
-		{"api/v3/collections/ansible/posix/versions/2.0.0/", provider.Mutable},
-		{"api/v3/plugin/ansible/content/published/collections/artifacts/ansible-posix-2.0.0.tar.gz", provider.Immutable},
-	}
-	for _, tt := range tests {
-		if got := p.Classify(tt.path); got != tt.want {
-			t.Errorf("Classify(%q) = %v, want %v", tt.path, got, tt.want)
-		}
-	}
-}
-
-func TestUpstreamURLKeepsQuery(t *testing.T) {
-	p := &Provider{}
-	got := p.UpstreamURL(models.Remote{BaseURL: "https://galaxy.ansible.com/"}, "api/v3/collections/a/b/versions/?limit=100&offset=100")
-	want := "https://galaxy.ansible.com/api/v3/collections/a/b/versions/?limit=100&offset=100"
-	if got != want {
-		t.Errorf("UpstreamURL = %q, want %q", got, want)
-	}
-}
-
-func TestRewriteResponse(t *testing.T) {
-	p := &Provider{}
-	remote := models.Remote{Name: "galaxy", BaseURL: "https://galaxy.ansible.com/"}
-	body := `{"links":{"next":"/api/v3/plugin/ansible/content/published/collections/index/a/b/versions/?limit=10&offset=10","previous":null},` +
-		`"href":"/api/content/published/v3/plugin/ansible/content/published/collections/index/a/b/versions/1.0.0/",` +
-		`"download_url":"https://galaxy.ansible.com/api/v3/plugin/ansible/content/published/collections/artifacts/a-b-1.0.0.tar.gz",` +
-		`"metadata":{"repository":"https://github.com/a/b"}}`
-
-	out, err := p.RewriteResponse([]byte(body), remote, "")
-	if err != nil {
-		t.Fatal(err)
-	}
-	var got struct {
-		Links       map[string]any `json:"links"`
-		Href        string         `json:"href"`
-		DownloadURL string         `json:"download_url"`
-		Metadata    map[string]any `json:"metadata"`
-	}
-	if err := json.Unmarshal(out, &got); err != nil {
-		t.Fatalf("rewritten body is not JSON: %v", err)
-	}
-	pre := "/api/v1/remote/galaxy/"
-	if want := pre + "api/v3/plugin/ansible/content/published/collections/index/a/b/versions/?limit=10&offset=10"; got.Links["next"] != want {
-		t.Errorf("next = %v, want %q", got.Links["next"], want)
-	}
-	if want := pre + "api/content/published/v3/plugin/ansible/content/published/collections/index/a/b/versions/1.0.0/"; got.Href != want {
-		t.Errorf("href = %q, want %q", got.Href, want)
-	}
-	if want := pre + "api/v3/plugin/ansible/content/published/collections/artifacts/a-b-1.0.0.tar.gz"; got.DownloadURL != want {
-		t.Errorf("download_url = %q, want %q", got.DownloadURL, want)
-	}
-	if got.Metadata["repository"] != "https://github.com/a/b" {
-		t.Errorf("unrelated URL rewritten: %v", got.Metadata["repository"])
-	}
-}
-
-func TestRewriteResponseSkipsNonJSON(t *testing.T) {
-	out, err := (&Provider{}).RewriteResponse([]byte("<html>"), models.Remote{Name: "g"}, "")
-	if err != nil || out != nil {
-		t.Errorf("got %q, %v; want nil, nil", out, err)
-	}
-}
-
-func TestForwardsQuery(t *testing.T) {
-	if _, ok := any(&Provider{}).(provider.QueryForwarder); !ok {
-		t.Error("ansible provider must forward the query string for pagination")
-	}
-}

internal/provider/gems/gems.go

@@ -0,0 +1,59 @@
+// Package gems proxies a RubyGems source: mutable compact index (versions,
+// info/*, names) and legacy specs indexes, plus immutable .gem and
+// quick/Marshal.4.8 gemspec downloads.
+package gems
+
+import (
+	"context"
+	"net/http"
+	"strings"
+
+	"git.unkin.net/unkin/artifactapi/internal/auth"
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
+)
+
+func init() {
+	provider.Register(&Provider{})
+}
+
+type Provider struct{}
+
+func (p *Provider) Type() models.PackageType { return models.PackageGems }
+
+func (p *Provider) Classify(path string) provider.Mutability {
+	if isGem(path) || isQuickSpec(path) {
+		return provider.Immutable
+	}
+	return provider.Mutable
+}
+
+func (p *Provider) ContentType(path string) string {
+	path = strings.TrimLeft(path, "/")
+	if path == "versions" || path == "names" || strings.HasPrefix(path, "info/") {
+		return "text/plain; charset=utf-8"
+	}
+	return "application/octet-stream"
+}
+
+func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
+	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
+}
+
+func (p *Provider) RewriteResponse(_ []byte, _ models.Remote, _ string) ([]byte, error) {
+	return nil, nil
+}
+
+func (p *Provider) AuthHeaders(_ context.Context, remote models.Remote) (http.Header, error) {
+	return auth.BasicHeaders(remote), nil
+}
+
+func isGem(path string) bool {
+	path = strings.TrimLeft(path, "/")
+	return strings.HasPrefix(path, "gems/") && strings.HasSuffix(path, ".gem")
+}
+
+func isQuickSpec(path string) bool {
+	path = strings.TrimLeft(path, "/")
+	return strings.HasPrefix(path, "quick/Marshal.4.8/") && strings.HasSuffix(path, ".gemspec.rz")
+}

internal/provider/gems/gems_test.go

@@ -0,0 +1,58 @@
+package gems
+
+import (
+	"testing"
+
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
+)
+
+func TestClassify(t *testing.T) {
+	p := &Provider{}
+	tests := []struct {
+		path string
+		want provider.Mutability
+	}{
+		{"gems/rack-3.1.8.gem", provider.Immutable},
+		{"/gems/nokogiri-1.16.7-x86_64-linux.gem", provider.Immutable},
+		{"quick/Marshal.4.8/rack-3.1.8.gemspec.rz", provider.Immutable},
+		{"versions", provider.Mutable},
+		{"names", provider.Mutable},
+		{"info/rack", provider.Mutable},
+		{"info/gems", provider.Mutable},
+		{"specs.4.8.gz", provider.Mutable},
+		{"latest_specs.4.8.gz", provider.Mutable},
+		{"prerelease_specs.4.8.gz", provider.Mutable},
+		{"api/v1/dependencies", provider.Mutable},
+		{"quick/Marshal.4.8/", provider.Mutable},
+	}
+	for _, tt := range tests {
+		if got := p.Classify(tt.path); got != tt.want {
+			t.Errorf("Classify(%q) = %v, want %v", tt.path, got, tt.want)
+		}
+	}
+}
+
+func TestContentType(t *testing.T) {
+	p := &Provider{}
+	tests := map[string]string{
+		"versions":            "text/plain; charset=utf-8",
+		"info/rack":           "text/plain; charset=utf-8",
+		"names":               "text/plain; charset=utf-8",
+		"gems/rack-3.1.8.gem": "application/octet-stream",
+		"specs.4.8.gz":        "application/octet-stream",
+	}
+	for path, want := range tests {
+		if got := p.ContentType(path); got != want {
+			t.Errorf("ContentType(%q) = %q, want %q", path, got, want)
+		}
+	}
+}
+
+func TestUpstreamURL(t *testing.T) {
+	p := &Provider{}
+	r := models.Remote{BaseURL: "https://rubygems.org/"}
+	if got := p.UpstreamURL(r, "/info/rack"); got != "https://rubygems.org/info/rack" {
+		t.Errorf("UpstreamURL = %q", got)
+	}
+}

internal/provider/provider.go

@@ -65,13 +65,6 @@ type MetadataStore interface {
 	InsertDebMetadata(ctx context.Context, meta *DebMetadata) error
 }
 
-// QueryForwarder marks a remote provider whose upstream answers depend on the
-// query string (e.g. paginated JSON APIs); the query is kept as part of the
-// proxied and cached path.
-type QueryForwarder interface {
-	ForwardQuery()
-}
-
 // RemoteServer lets a remote provider fully answer a request itself instead of
 // going through the byte-proxy engine. It is the remote-side analog of
 // LocalIndexer: a metadata-only remote (e.g. github_rpm) uses it to synthesize

internal/server/server.go

@@ -22,10 +22,10 @@ import (
 	"git.unkin.net/unkin/artifactapi/internal/gc"
 	"git.unkin.net/unkin/artifactapi/internal/githubauth"
 	"git.unkin.net/unkin/artifactapi/internal/provider/alpine"
-	_ "git.unkin.net/unkin/artifactapi/internal/provider/ansible"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/cargo"
 	"git.unkin.net/unkin/artifactapi/internal/provider/deb"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/docker"
+	_ "git.unkin.net/unkin/artifactapi/internal/provider/gems"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/generic"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/goproxy"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/helm"

pkg/models/package_type.go

@@ -17,7 +17,7 @@ const (
 	PackageTerraform    PackageType = "terraform"
 	PackageGoProxy      PackageType = "goproxy"
 	PackageCargo        PackageType = "cargo"
-	PackageAnsible      PackageType = "ansible"
+	PackageGems         PackageType = "gems"
 	PackageGitHubRPM    PackageType = "github_rpm"
 	PackageGitHubDeb    PackageType = "github_deb"
 	PackageGitHubAlpine PackageType = "github_alpine"
@@ -36,7 +36,7 @@ var validPackageTypes = map[PackageType]bool{
 	PackageTerraform:    true,
 	PackageGoProxy:      true,
 	PackageCargo:        true,
-	PackageAnsible:      true,
+	PackageGems:         true,
 	PackageGitHubRPM:    true,
 	PackageGitHubDeb:    true,
 	PackageGitHubAlpine: true,

pkg/models/package_type_test.go

@@ -19,7 +19,7 @@ func TestPackageTypeValid(t *testing.T) {
 		models.PackageTerraform,
 		models.PackageGoProxy,
 		models.PackageCargo,
-		models.PackageAnsible,
+		models.PackageGems,
 		models.PackageGitHubRPM,
 		models.PackageGitHubDeb,
 		models.PackageGitHubAlpine,

ui/src/components/UsageInstructions.tsx

@@ -243,12 +243,13 @@ index = "sparse+${proxy}/"`,
         },
       ];
 
-    case 'ansible':
+    case 'gems':
       return [
         {
-          title: 'Install collections through this Galaxy proxy',
+          title: 'Use this remote as the RubyGems source',
           language: 'bash',
-          code: `ansible-galaxy collection install community.general -s ${proxy}/api/`,
+          code: `gem sources --clear-all --add ${proxy}/
+bundle config mirror.https://rubygems.org ${proxy}`,
         },
       ];
 

ui/src/pages/Locals.tsx

@@ -18,6 +18,7 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
   terraform: 'blue',
   goproxy: 'green',
   cargo: 'yellow',
+  gems: 'red',
 };
 
 export function Locals() {

ui/src/pages/Remotes.tsx

@@ -18,7 +18,7 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
   terraform: 'blue',
   goproxy: 'green',
   cargo: 'yellow',
-  ansible: 'red',
+  gems: 'red',
 };
 
 export function Remotes() {