Add nuget v3 remote type (#141)

.NET builds restore from nuget.org directly because artifactapi has no NuGet remote type. - add `nuget` package type proxying a NuGet v3 feed; `index.json` maps to the upstream service index - add a `ServeRewriter` provider hook so cached JSON has upstream-origin URLs pointed back at the requesting host per request - treat `.nupkg`/`.nuspec` as immutable and service, registration and flat container indexes as mutable - add a `nuget.config` usage snippet to the UI and a nuget e2e caching case Reviewed-on: #141 Co-authored-by: unkin-agent <unkin-agent@unkin.net> Co-committed-by: unkin-agent <unkin-agent@unkin.net>
2026-10-17 12:19:51 +11:00
parent 9161558334
commit bc68eb75fc
14 changed files with 199 additions and 3 deletions
@@ -1,6 +1,7 @@
 package v1

 import (
+	"bytes"
 	"errors"
 	"fmt"
 	"io"
@@ -105,13 +106,24 @@ func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
 	}
 	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("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) {
@@ -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")
+}
@@ -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")
+	}
+}
@@ -75,6 +75,13 @@ 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
+}
+
 // 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 {
@@ -29,6 +29,7 @@ import (
 	_ "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"