Add gems remote type for RubyGems (#142)

Ruby builds fetch gems from rubygems.org directly because artifactapi has no RubyGems remote type.

- add `gems` package type proxying `https://rubygems.org`-style sources
- treat `versions`, `names`, `info/*` and `*specs.4.8.gz` as mutable, `gems/*.gem` and `quick/Marshal.4.8/*.gemspec.rz` as immutable
- serve `api/v1/*.json` as `application/json`
- add a gem/bundler usage snippet to the UI and a gems e2e caching case

Requires unkin/artifactapi#148 (HEAD route; RubyGems probes `HEAD /versions`).

Reviewed-on: #142
Co-authored-by: unkin-agent <unkin-agent@unkin.net>
Co-committed-by: unkin-agent <unkin-agent@unkin.net>

README.md

@@ -1,6 +1,6 @@
 # ArtifactAPI
 
-Caching proxy for package repositories. Single Go binary, 11 package types, content-addressable storage, managed by Terraform.
+Caching proxy for package repositories. Single Go binary, 12 package types, content-addressable storage, managed by Terraform.
 
 ## Quick Start
 
@@ -33,6 +33,8 @@ 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` |
+| `gems` | compact index (`versions`, `info/*`, `names`), `*specs.4.8.gz` | `gems/*.gem`, `quick/Marshal.4.8/*.gemspec.rz` |
+| `nuget` | `index.json` (service index), registration and flat container indexes | `.nupkg`, `.nuspec` |
 | `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) proxied through the
+  helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy, cargo, gems, nuget) 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

@@ -30,6 +30,8 @@ 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"},
+		{"gems", "gems/mygem-1.0.0.gem", "gems/mygem-1.0.0.gem"},
+		{"nuget", "nuget/e2epkg/1.0.0/e2epkg.1.0.0.nupkg", "nuget/e2epkg/1.0.0/e2epkg.1.0.0.nupkg"},
 		{"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

e2e/head_test.go

@@ -0,0 +1,168 @@
+//go:build e2e
+
+package e2e
+
+import (
+	"encoding/json"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strconv"
+	"strings"
+	"testing"
+	"time"
+
+	"git.unkin.net/unkin/artifactapi/internal/testsupport"
+)
+
+// assertHeadMatchesGet checks HEAD returns GET's status, type and length with no body.
+func assertHeadMatchesGet(t *testing.T, url string) {
+	t.Helper()
+	get, err := http.Get(url)
+	if err != nil {
+		t.Fatalf("GET: %v", err)
+	}
+	body, _ := io.ReadAll(get.Body)
+	get.Body.Close()
+	if get.StatusCode != http.StatusOK {
+		t.Fatalf("GET %s: %d %s", url, get.StatusCode, body)
+	}
+
+	head, err := http.Head(url)
+	if err != nil {
+		t.Fatalf("HEAD: %v", err)
+	}
+	hb, _ := io.ReadAll(head.Body)
+	head.Body.Close()
+	if head.StatusCode != http.StatusOK {
+		t.Fatalf("HEAD %s: got %d, want 200", url, head.StatusCode)
+	}
+	if len(hb) != 0 {
+		t.Errorf("HEAD returned a %d-byte body", len(hb))
+	}
+	if head.Header.Get("Content-Type") != get.Header.Get("Content-Type") {
+		t.Errorf("HEAD Content-Type %q, GET %q", head.Header.Get("Content-Type"), get.Header.Get("Content-Type"))
+	}
+	if head.ContentLength != int64(len(body)) {
+		t.Errorf("HEAD Content-Length %d, GET body %d bytes", head.ContentLength, len(body))
+	}
+}
+
+func TestProxyHeadNuGetRewritten(t *testing.T) {
+	var upstream *httptest.Server
+	upstream = httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		json.NewEncoder(w).Encode(map[string]any{"version": "3.0.0", "resources": []map[string]string{
+			{"@id": upstream.URL + "/v3-flatcontainer/", "@type": "PackageBaseAddress/3.0.0"},
+		}})
+	}))
+	defer upstream.Close()
+
+	createRemote(t, mustFormat(`{"name": "head-nuget", "package_type": "nuget", "base_url": %q}`, upstream.URL+"/v3/index.json"))
+	defer deleteRemote(t, "head-nuget")
+
+	assertHeadMatchesGet(t, apiURL("/api/v1/remote/head-nuget/index.json"))
+}
+
+func TestProxyHeadGitHubRPMRepodata(t *testing.T) {
+	rpm := testsupport.MinimalRPM("demo", "1.2", "3", "x86_64")
+	var gh *httptest.Server
+	mux := http.NewServeMux()
+	mux.HandleFunc("/repos/acme/tools/releases", func(w http.ResponseWriter, r *http.Request) {
+		if p := r.URL.Query().Get("page"); p != "" && p != "1" {
+			w.Write([]byte("[]"))
+			return
+		}
+		json.NewEncoder(w).Encode([]map[string]any{{"tag_name": "v1.2-3", "assets": []map[string]any{{
+			"name":                 "demo-1.2-3.x86_64.rpm",
+			"size":                 len(rpm),
+			"browser_download_url": gh.URL + "/acme/tools/releases/download/v1.2-3/demo-1.2-3.x86_64.rpm",
+		}}}})
+	})
+	mux.HandleFunc("/acme/tools/releases/download/", func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Length", strconv.Itoa(len(rpm)))
+		w.Write(rpm)
+	})
+	gh = httptest.NewServer(mux)
+	defer gh.Close()
+
+	createRemote(t, mustFormat(`{"name": "head-ghrpm", "package_type": "github_rpm", "base_url": %q, "releases_remote": "github"}`, gh.URL+"/repos/acme/tools"))
+	defer deleteRemote(t, "head-ghrpm")
+
+	url := apiURL("/api/v1/remote/head-ghrpm/repodata/repomd.xml")
+	deadline := time.Now().Add(30 * time.Second)
+	for {
+		if _, status := getBody(t, url); status == http.StatusOK || time.Now().After(deadline) {
+			break
+		}
+		time.Sleep(500 * time.Millisecond)
+	}
+	assertHeadMatchesGet(t, url)
+}
+
+func TestProxyHeadNpmUncachedPackument(t *testing.T) {
+	const abbreviated = "application/vnd.npm.install-v1+json"
+	upstream := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "application/json")
+		doc := map[string]any{"name": "left-pad", "versions": map[string]any{"1.3.0": map[string]any{}}}
+		if r.Header.Get("Accept") != abbreviated {
+			doc["readme"] = strings.Repeat("full packument ", 200)
+		}
+		json.NewEncoder(w).Encode(doc)
+	}))
+	defer upstream.Close()
+
+	createRemote(t, mustFormat(`{"name": "head-npm", "package_type": "npm", "base_url": %q}`, upstream.URL))
+	defer deleteRemote(t, "head-npm")
+
+	url := apiURL("/api/v1/remote/head-npm/left-pad")
+	do := func(method string) (*http.Response, []byte) {
+		req, _ := http.NewRequest(method, url, nil)
+		req.Header.Set("Accept", abbreviated)
+		resp, err := http.DefaultClient.Do(req)
+		if err != nil {
+			t.Fatalf("%s: %v", method, err)
+		}
+		defer resp.Body.Close()
+		b, _ := io.ReadAll(resp.Body)
+		return resp, b
+	}
+	head, _ := do(http.MethodHead)
+	get, body := do(http.MethodGet)
+	if head.StatusCode != http.StatusOK || get.StatusCode != http.StatusOK {
+		t.Fatalf("HEAD %d, GET %d", head.StatusCode, get.StatusCode)
+	}
+	if head.ContentLength != int64(len(body)) {
+		t.Errorf("uncached HEAD Content-Length %d, GET body %d bytes", head.ContentLength, len(body))
+	}
+}
+
+func TestProxyHeadNonRewritingUsesUpstreamHead(t *testing.T) {
+	methods := make(chan string, 4)
+	upstream := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		methods <- r.Method
+		w.Header().Set("Content-Type", "text/xml")
+		w.Write([]byte("<repomd/>"))
+	}))
+	defer upstream.Close()
+
+	createRemote(t, mustFormat(`{"name": "head-rpm", "package_type": "rpm", "base_url": %q}`, upstream.URL))
+	defer deleteRemote(t, "head-rpm")
+
+	resp, err := http.Head(apiURL("/api/v1/remote/head-rpm/repodata/repomd.xml"))
+	if err != nil {
+		t.Fatalf("HEAD: %v", err)
+	}
+	resp.Body.Close()
+	if resp.StatusCode != http.StatusOK || resp.Header.Get("X-Artifact-Source") != "remote" {
+		t.Fatalf("HEAD %d source %q", resp.StatusCode, resp.Header.Get("X-Artifact-Source"))
+	}
+	close(methods)
+	var seen []string
+	for m := range methods {
+		seen = append(seen, m)
+	}
+	if len(seen) != 1 || seen[0] != http.MethodHead {
+		t.Errorf("upstream saw %v, want a single HEAD", seen)
+	}
+}

internal/api/v1/proxy.go

@@ -1,6 +1,7 @@
 package v1
 
 import (
+	"bytes"
 	"errors"
 	"fmt"
 	"io"
@@ -15,6 +16,7 @@ import (
 	"git.unkin.net/unkin/artifactapi/internal/proxy"
 	"git.unkin.net/unkin/artifactapi/internal/storage"
 	"git.unkin.net/unkin/artifactapi/internal/virtual"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
 )
 
 type ProxyHandler struct {
@@ -40,6 +42,7 @@ 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
@@ -67,31 +70,43 @@ func (h *ProxyHandler) handleDockerPing(w http.ResponseWriter, r *http.Request)
 	w.WriteHeader(http.StatusOK)
 }
 
-func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
+// remoteFor resolves the remote and provider named in the request, writing the
+// error response itself when either is missing.
+func (h *ProxyHandler) remoteFor(w http.ResponseWriter, r *http.Request) (*models.Remote, provider.Provider, bool) {
 	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
+		return nil, nil, false
 	}
-
 	prov, err := provider.Get(remote.PackageType)
 	if err != nil {
 		http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
+		return nil, nil, false
+	}
+	return remote, prov, true
+}
+
+// serveRemote lets metadata-only remotes (e.g. github_rpm) synthesize their own
+// responses and redirect package downloads instead of proxying bytes.
+func (h *ProxyHandler) serveRemote(w http.ResponseWriter, r *http.Request, remote *models.Remote, prov provider.Provider, path string) bool {
+	rs, ok := prov.(provider.RemoteServer)
+	return ok && rs.ServeRemote(w, r, *remote, path, fmt.Sprintf("%s://%s", scheme(r), r.Host), h.db)
+}
+
+func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
+	remote, prov, ok := h.remoteFor(w, r)
+	if !ok {
 		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
-		}
+	path := chi.URLParam(r, "*")
+	if h.serveRemote(w, r, remote, prov, path) {
+		return
 	}
+	h.serveFetch(w, r, remote, prov, path)
+}
 
+func (h *ProxyHandler) serveFetch(w http.ResponseWriter, r *http.Request, remote *models.Remote, prov provider.Provider, path string) {
 	result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
 	if err != nil {
 		var proxyErr *proxy.ProxyError
@@ -99,34 +114,53 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 			http.Error(w, proxyErr.Message, proxyErr.Status)
 			return
 		}
-		slog.Error("proxy fetch failed", "remote", remoteName, "path", path, "error", err)
+		slog.Error("proxy fetch failed", "remote", remote.Name, "path", path, "error", err)
 		http.Error(w, "bad gateway", http.StatusBadGateway)
 		return
 	}
 	defer result.Reader.Close()
 
+	var body io.Reader = result.Reader
+	if sr, ok := prov.(provider.ServeRewriter); ok && prov.Classify(path) == provider.Mutable {
+		raw, err := io.ReadAll(result.Reader)
+		if err != nil {
+			http.Error(w, "bad gateway", http.StatusBadGateway)
+			return
+		}
+		raw = sr.RewriteServed(raw, *remote, fmt.Sprintf("%s://%s", scheme(r), r.Host))
+		body, result.Size = bytes.NewReader(raw), int64(len(raw))
+	}
+
 	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.Header().Set("X-Artifact-Size", fmt.Sprintf("%d", result.Size))
 	}
 	w.WriteHeader(http.StatusOK)
-	io.Copy(w, result.Reader)
+	io.Copy(w, body)
 }
 
-func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
-	remoteName := chi.URLParam(r, "remoteName")
-	path := chi.URLParam(r, "*")
+func rewritesMutable(prov provider.Provider, path string) bool {
+	_, sr := prov.(provider.ServeRewriter)
+	_, rr := prov.(provider.ResponseRewriter)
+	return (sr || rr) && prov.Classify(path) == provider.Mutable
+}
 
-	remote, err := h.db.GetRemote(r.Context(), remoteName)
-	if err != nil {
-		http.Error(w, fmt.Sprintf("remote %q not found", remoteName), http.StatusNotFound)
+// handleProxyHead answers HEAD like GET without a body. Responses a provider
+// synthesizes or rewrites per request go through the GET path so their headers
+// match; everything else is answered from store metadata or an upstream HEAD.
+func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
+	remote, prov, ok := h.remoteFor(w, r)
+	if !ok {
 		return
 	}
-
-	prov, err := provider.Get(remote.PackageType)
-	if err != nil {
-		http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
+	path := chi.URLParam(r, "*")
+	if h.serveRemote(w, r, remote, prov, path) {
+		return
+	}
+	if rewritesMutable(prov, path) {
+		h.serveFetch(w, r, remote, prov, path)
 		return
 	}
 
@@ -137,7 +171,7 @@ func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
 			http.Error(w, proxyErr.Message, proxyErr.Status)
 			return
 		}
-		slog.Error("proxy head failed", "remote", remoteName, "path", path, "error", err)
+		slog.Error("proxy head failed", "remote", remote.Name, "path", path, "error", err)
 		http.Error(w, "bad gateway", http.StatusBadGateway)
 		return
 	}

internal/api/v1/routes_test.go

@@ -0,0 +1,41 @@
+package v1
+
+import (
+	"net/http"
+	"testing"
+
+	"github.com/go-chi/chi/v5"
+
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/internal/provider/npm"
+	"git.unkin.net/unkin/artifactapi/internal/provider/nuget"
+	"git.unkin.net/unkin/artifactapi/internal/provider/rpm"
+)
+
+func TestRoutesRemoteHead(t *testing.T) {
+	r := (&ProxyHandler{}).Routes()
+	for _, m := range []string{http.MethodGet, http.MethodHead} {
+		if !r.Match(chi.NewRouteContext(), m, "/remote/myremote/some/path") {
+			t.Errorf("%s /remote/myremote/some/path not routed", m)
+		}
+	}
+}
+
+func TestRewritesMutable(t *testing.T) {
+	tests := []struct {
+		name string
+		prov provider.Provider
+		path string
+		want bool
+	}{
+		{"npm packument", &npm.Provider{}, "left-pad", true},
+		{"npm tarball", &npm.Provider{}, "left-pad/-/left-pad-1.3.0.tgz", false},
+		{"nuget index", &nuget.Provider{}, "index.json", true},
+		{"rpm repodata", &rpm.Provider{}, "repodata/repomd.xml", false},
+	}
+	for _, tc := range tests {
+		if got := rewritesMutable(tc.prov, tc.path); got != tc.want {
+			t.Errorf("%s: rewritesMutable = %v, want %v", tc.name, got, tc.want)
+		}
+	}
+}

internal/provider/gems/gems.go

@@ -0,0 +1,62 @@
+// 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"
+	}
+	if strings.HasPrefix(path, "api/v1/") && strings.HasSuffix(path, ".json") {
+		return "application/json"
+	}
+	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 +1,61 @@
+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",
+		"api/v1/gems/rack.json":    "application/json",
+		"api/v1/dependencies.json": "application/json",
+		"api/v1/dependencies":      "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/helm/helm.go

@@ -39,6 +39,8 @@ func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
 	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
 }
 
+func (p *Provider) RewritesResponse() {}
+
 func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
 	if proxyBaseURL == "" {
 		return nil, nil

internal/provider/npm/npm.go

@@ -37,6 +37,8 @@ func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
 	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
 }
 
+func (p *Provider) RewritesResponse() {}
+
 func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
 	if proxyBaseURL == "" || !json.Valid(body) {
 		return nil, nil

internal/provider/nuget/nuget.go

@@ -0,0 +1,85 @@
+// Package nuget proxies a NuGet v3 feed: the service index, registration pages
+// and flat container indexes are mutable, .nupkg/.nuspec downloads immutable.
+package nuget
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/url"
+	"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{})
+}
+
+// serviceIndex is the path clients use as their source URL; it maps to base_url.
+const serviceIndex = "index.json"
+
+type Provider struct{}
+
+func (p *Provider) Type() models.PackageType { return models.PackageNuGet }
+
+func (p *Provider) Classify(path string) provider.Mutability {
+	if isPackage(path) {
+		return provider.Immutable
+	}
+	return provider.Mutable
+}
+
+func (p *Provider) ContentType(path string) string {
+	switch {
+	case strings.HasSuffix(path, ".nupkg"):
+		return "application/octet-stream"
+	case strings.HasSuffix(path, ".nuspec"):
+		return "application/xml"
+	}
+	return "application/json"
+}
+
+// UpstreamURL maps index.json to base_url (the upstream service index) and any
+// other path to the same path on the base_url's origin, where nuget.org serves
+// v3-flatcontainer/ and v3/registration*/.
+func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
+	path = strings.TrimLeft(path, "/")
+	if path == serviceIndex {
+		return remote.BaseURL
+	}
+	return origin(remote.BaseURL) + "/" + path
+}
+
+func (p *Provider) RewriteResponse(_ []byte, _ models.Remote, _ string) ([]byte, error) {
+	return nil, nil
+}
+
+// RewriteServed points upstream-origin URLs in cached JSON back at this remote.
+// It runs per request because the URLs must name the requesting host.
+func (p *Provider) RewriteServed(body []byte, remote models.Remote, proxyBaseURL string) []byte {
+	from := origin(remote.BaseURL)
+	if from == "" || !json.Valid(body) {
+		return body
+	}
+	to := strings.TrimRight(proxyBaseURL, "/") + "/api/v1/remote/" + remote.Name
+	return []byte(strings.ReplaceAll(string(body), from, to))
+}
+
+func (p *Provider) AuthHeaders(_ context.Context, remote models.Remote) (http.Header, error) {
+	return auth.BasicHeaders(remote), nil
+}
+
+func origin(baseURL string) string {
+	u, err := url.Parse(baseURL)
+	if err != nil || u.Host == "" {
+		return ""
+	}
+	return u.Scheme + "://" + u.Host
+}
+
+func isPackage(path string) bool {
+	return strings.HasSuffix(path, ".nupkg") || strings.HasSuffix(path, ".nuspec")
+}

internal/provider/nuget/nuget_test.go

@@ -0,0 +1,68 @@
+package nuget
+
+import (
+	"testing"
+
+	"git.unkin.net/unkin/artifactapi/internal/provider"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
+)
+
+var _ provider.ServeRewriter = (*Provider)(nil)
+
+var nugetOrg = models.Remote{Name: "nuget-org", BaseURL: "https://api.nuget.org/v3/index.json"}
+
+func TestClassify(t *testing.T) {
+	p := &Provider{}
+	tests := []struct {
+		path string
+		want provider.Mutability
+	}{
+		{"v3-flatcontainer/newtonsoft.json/13.0.3/newtonsoft.json.13.0.3.nupkg", provider.Immutable},
+		{"v3-flatcontainer/newtonsoft.json/13.0.3/newtonsoft.json.nuspec", provider.Immutable},
+		{"v3-flatcontainer/newtonsoft.json/index.json", provider.Mutable},
+		{"v3/registration5-gz-semver2/newtonsoft.json/index.json", provider.Mutable},
+		{"index.json", 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 TestUpstreamURL(t *testing.T) {
+	p := &Provider{}
+	tests := []struct {
+		path, want string
+	}{
+		{"index.json", "https://api.nuget.org/v3/index.json"},
+		{"/index.json", "https://api.nuget.org/v3/index.json"},
+		{"v3-flatcontainer/serilog/index.json", "https://api.nuget.org/v3-flatcontainer/serilog/index.json"},
+		{"v3/registration5-gz-semver2/serilog/index.json", "https://api.nuget.org/v3/registration5-gz-semver2/serilog/index.json"},
+	}
+	for _, tt := range tests {
+		if got := p.UpstreamURL(nugetOrg, tt.path); got != tt.want {
+			t.Errorf("UpstreamURL(%q) = %q, want %q", tt.path, got, tt.want)
+		}
+	}
+}
+
+func TestRewriteServed(t *testing.T) {
+	p := &Provider{}
+	body := `{"resources":[` +
+		`{"@id":"https://api.nuget.org/v3-flatcontainer/","@type":"PackageBaseAddress/3.0.0"},` +
+		`{"@id":"https://azuresearch-usnc.nuget.org/query","@type":"SearchQueryService"}]}`
+	want := `{"resources":[` +
+		`{"@id":"http://aa.example:8000/api/v1/remote/nuget-org/v3-flatcontainer/","@type":"PackageBaseAddress/3.0.0"},` +
+		`{"@id":"https://azuresearch-usnc.nuget.org/query","@type":"SearchQueryService"}]}`
+	if got := string(p.RewriteServed([]byte(body), nugetOrg, "http://aa.example:8000/")); got != want {
+		t.Errorf("RewriteServed =\n%s\nwant\n%s", got, want)
+	}
+	if got := string(p.RewriteServed([]byte(body), models.Remote{Name: "x"}, "http://aa.example")); got != body {
+		t.Error("remote without a parseable base_url must pass the body through")
+	}
+	cert := "\x30\x82https://api.nuget.org"
+	if got := string(p.RewriteServed([]byte(cert), nugetOrg, "http://aa.example")); got != cert {
+		t.Error("non-JSON bodies must pass through untouched")
+	}
+}

internal/provider/provider.go

@@ -75,6 +75,19 @@ type RemoteServer interface {
 	ServeRemote(w http.ResponseWriter, r *http.Request, remote models.Remote, path, proxyBaseURL string, store RemoteMetadataStore) bool
 }
 
+// ServeRewriter rewrites a cached mutable remote response per request, for
+// indexes whose URLs must name the requesting host and so cannot be rewritten
+// before caching.
+type ServeRewriter interface {
+	RewriteServed(body []byte, remote models.Remote, proxyBaseURL string) []byte
+}
+
+// ResponseRewriter marks providers whose RewriteResponse changes mutable
+// bodies, so the served length is only known after a fetch.
+type ResponseRewriter interface {
+	RewritesResponse()
+}
+
 // RemoteMetadataStore is the persistence surface a RemoteServer needs to cache
 // and read the metadata it derives per upstream asset. *database.DB satisfies it.
 type RemoteMetadataStore interface {

internal/provider/puppet/puppet.go

@@ -39,6 +39,8 @@ func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
 	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
 }
 
+func (p *Provider) RewritesResponse() {}
+
 func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
 	if proxyBaseURL == "" {
 		return nil, nil

internal/provider/pypi/pypi.go

@@ -52,6 +52,8 @@ func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
 	return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
 }
 
+func (p *Provider) RewritesResponse() {}
+
 func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
 	if proxyBaseURL == "" {
 		return nil, nil

internal/provider/terraform/terraform.go

@@ -73,6 +73,8 @@ func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
 	return strings.TrimRight(remote.BaseURL, "/") + "/v1/providers/" + strings.TrimLeft(path, "/")
 }
 
+func (p *Provider) RewritesResponse() {}
+
 func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
 	if remote.ReleasesRemote == "" {
 		return nil, nil

internal/proxy/engine.go

@@ -353,7 +353,7 @@ func (e *Engine) headUpstreamOnce(ctx context.Context, remote models.Remote, pat
 				req.Header.Set(k, v)
 			}
 		}
-		return http.DefaultClient.Do(req)
+		return clientForRemote(remote).Do(req)
 	}
 
 	resp, err := doHead(nil)

internal/proxy/engine_test.go

@@ -216,6 +216,20 @@ func TestHead(t *testing.T) {
 	}
 }
 
+func TestHeadUpstreamUsesRemoteTimeout(t *testing.T) {
+	slow := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		time.Sleep(3 * time.Second)
+	}))
+	defer slow.Close()
+	r := models.Remote{Name: "slow-head", PackageType: models.PackageGeneric, BaseURL: slow.URL, UpstreamResponseHeaderTimeout: 1}
+
+	start := time.Now()
+	_, err := (&Engine{}).headUpstreamOnce(context.Background(), r, "blob.bin", prov(t, models.PackageGeneric))
+	if err == nil || time.Since(start) > 2*time.Second {
+		t.Fatalf("HEAD ignored the remote's response header timeout: err=%v after %s", err, time.Since(start))
+	}
+}
+
 func TestStaleOnError(t *testing.T) {
 	requireStack(t)
 	ctx := context.Background()

internal/server/server.go

@@ -25,10 +25,12 @@ import (
 	_ "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"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/npm"
+	_ "git.unkin.net/unkin/artifactapi/internal/provider/nuget"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/puppet"
 	_ "git.unkin.net/unkin/artifactapi/internal/provider/pypi"
 	"git.unkin.net/unkin/artifactapi/internal/provider/rpm"

pkg/models/package_type.go

@@ -17,6 +17,8 @@ const (
 	PackageTerraform    PackageType = "terraform"
 	PackageGoProxy      PackageType = "goproxy"
 	PackageCargo        PackageType = "cargo"
+	PackageGems         PackageType = "gems"
+	PackageNuGet        PackageType = "nuget"
 	PackageGitHubRPM    PackageType = "github_rpm"
 	PackageGitHubDeb    PackageType = "github_deb"
 	PackageGitHubAlpine PackageType = "github_alpine"
@@ -35,6 +37,8 @@ var validPackageTypes = map[PackageType]bool{
 	PackageTerraform:    true,
 	PackageGoProxy:      true,
 	PackageCargo:        true,
+	PackageGems:         true,
+	PackageNuGet:        true,
 	PackageGitHubRPM:    true,
 	PackageGitHubDeb:    true,
 	PackageGitHubAlpine: true,

pkg/models/package_type_test.go

@@ -19,6 +19,8 @@ func TestPackageTypeValid(t *testing.T) {
 		models.PackageTerraform,
 		models.PackageGoProxy,
 		models.PackageCargo,
+		models.PackageGems,
+		models.PackageNuGet,
 		models.PackageGitHubRPM,
 		models.PackageGitHubDeb,
 		models.PackageGitHubAlpine,

ui/src/components/UsageInstructions.tsx

@@ -243,6 +243,32 @@ index = "sparse+${proxy}/"`,
         },
       ];
 
+    case 'gems':
+      return [
+        {
+          title: 'Use this remote as the RubyGems source',
+          language: 'bash',
+          code: `gem sources --clear-all --add ${proxy}/
+bundle config mirror.https://rubygems.org ${proxy}`,
+        },
+      ];
+
+    case 'nuget':
+      return [
+        {
+          title: 'Use this feed instead of nuget.org',
+          language: 'xml',
+          code: `<!-- nuget.config -->
+<configuration>
+  <packageSources>
+    <clear />
+    <add key="${name}" value="${proxy}/index.json" protocolVersion="3" />
+  </packageSources>
+</configuration>`,
+          note: 'Serve artifactapi over HTTPS: NuGet rejects the repository signatures resource over plain HTTP.',
+        },
+      ];
+
     case 'puppet':
       return [
         {

ui/src/pages/Locals.tsx

@@ -18,6 +18,8 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
   terraform: 'blue',
   goproxy: 'green',
   cargo: 'yellow',
+  gems: 'red',
+  nuget: 'blue',
 };
 
 export function Locals() {

ui/src/pages/Remotes.tsx

@@ -18,6 +18,8 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
   terraform: 'blue',
   goproxy: 'green',
   cargo: 'yellow',
+  gems: 'red',
+  nuget: 'blue',
 };
 
 export function Remotes() {