Compare commits

..

8 Commits

Author SHA1 Message Date
unkin-agent c3862fbd5f Merge remote-tracking branch 'origin/benvin/remote-head-route' into benvin/nuget-followups
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 13:01:01 +11:00
unkin-agent 7769902530 Fetch rewritten mutable responses on HEAD to match GET length
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:59:33 +11:00
unkin-agent fe10a50d27 Share strict X-Forwarded-Proto parsing and reject empty Host ports
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:56:29 +11:00
unkin-agent d0c30e145e Merge remote-tracking branch 'origin/benvin/remote-head-route' into benvin/nuget-followups 2026-10-17 12:48:05 +11:00
unkin-agent a7aa37982a Leave remote HEAD routing to the generic HEAD fix
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:43:01 +11:00
unkin-agent 3dd4acd233 Add HEAD route for remotes matching GET headers
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:40:33 +11:00
unkin-agent 3b69b58ba3 Harden nuget per-request rewrite and fix HEAD length
- set Cache-Control no-store and Vary on rewritten responses
- accept only http/https X-Forwarded-Proto
- reject invalid Host headers and JSON-escape the injected base URL
- route remote HEAD and serve rewritten HEAD via the GET path
- classify snupkg, readme and icon as immutable
2026-10-17 12:39:02 +11:00
unkin-agent bc68eb75fc 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
27 changed files with 750 additions and 43 deletions
+2 -1
View File
@@ -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 +33,7 @@ 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` |
| `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.
+1 -1
View File
@@ -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, 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/`
+1
View File
@@ -30,6 +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"},
{"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"},
}
+182
View File
@@ -0,0 +1,182 @@
//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))
}
for _, h := range []string{"Content-Type", "Cache-Control", "Vary"} {
if head.Header.Get(h) != get.Header.Get(h) {
t.Errorf("HEAD %s %q, GET %q", h, head.Header.Get(h), get.Header.Get(h))
}
}
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")
url := apiURL("/api/v1/remote/head-nuget/index.json")
assertHeadMatchesGet(t, url)
req, _ := http.NewRequest(http.MethodHead, url, nil)
req.Host = "evil.example:"
resp, err := http.DefaultClient.Do(req)
if err != nil {
t.Fatal(err)
}
resp.Body.Close()
if resp.StatusCode != http.StatusBadRequest {
t.Errorf("HEAD with invalid Host: got %d, want 400", resp.StatusCode)
}
}
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)
}
}
+59
View File
@@ -0,0 +1,59 @@
//go:build e2e
package e2e
import (
"encoding/json"
"net/http"
"strings"
"testing"
)
func getForwardedHTTPS(t *testing.T, url string) *http.Response {
t.Helper()
req, _ := http.NewRequest(http.MethodGet, url, nil)
req.Header.Set("X-Forwarded-Proto", "https")
client := &http.Client{CheckRedirect: func(*http.Request, []*http.Request) error { return http.ErrUseLastResponse }}
resp, err := client.Do(req)
if err != nil {
t.Fatalf("GET %s: %v", url, err)
}
return resp
}
func TestForwardedProtoCargoConfig(t *testing.T) {
createRemote(t, `{"name": "scheme-cargo", "package_type": "cargo", "base_url": "https://index.crates.io"}`)
defer deleteRemote(t, "scheme-cargo")
resp := getForwardedHTTPS(t, apiURL("/api/v1/remote/scheme-cargo/config.json"))
defer resp.Body.Close()
var cfg map[string]string
if err := json.NewDecoder(resp.Body).Decode(&cfg); err != nil {
t.Fatal(err)
}
if want := "https://" + strings.TrimPrefix(baseURL, "http://") + "/api/v1/remote/scheme-cargo/"; !strings.HasPrefix(cfg["dl"], want) {
t.Errorf("dl = %q, want prefix %q", cfg["dl"], want)
}
}
func TestForwardedProtoVirtualRedirect(t *testing.T) {
createRemote(t, `{"name": "scheme-rpm", "package_type": "rpm", "base_url": "https://rpm.example.com"}`)
defer deleteRemote(t, "scheme-rpm")
resp, err := http.Post(apiURL("/api/v2/virtuals"), "application/json",
strings.NewReader(`{"name": "scheme-virt", "package_type": "rpm", "members": ["scheme-rpm"]}`))
if err != nil {
t.Fatal(err)
}
resp.Body.Close()
if resp.StatusCode != http.StatusCreated {
t.Fatalf("create virtual: status %d", resp.StatusCode)
}
defer deleteRequest(t, apiURL("/api/v2/virtuals/scheme-virt"))
resp = getForwardedHTTPS(t, apiURL("/api/v1/virtual/scheme-virt/scheme-rpm/Packages/a.rpm"))
resp.Body.Close()
loc := resp.Header.Get("Location")
if want := "https://" + strings.TrimPrefix(baseURL, "http://") + "/api/v1/remote/scheme-rpm/Packages/a.rpm"; resp.StatusCode != http.StatusFound || loc != want {
t.Errorf("redirect = %d %q, want 302 %q", resp.StatusCode, loc, want)
}
}
+2 -8
View File
@@ -13,6 +13,7 @@ import (
"github.com/go-chi/chi/v5"
v1 "git.unkin.net/unkin/artifactapi/internal/api/v1"
"git.unkin.net/unkin/artifactapi/internal/database"
tfprov "git.unkin.net/unkin/artifactapi/internal/provider/terraform"
"git.unkin.net/unkin/artifactapi/internal/tfsign"
@@ -290,12 +291,5 @@ func writeJSON(w http.ResponseWriter, v any) {
}
func baseURL(r *http.Request) string {
scheme := "http"
if r.TLS != nil {
scheme = "https"
}
if fwd := r.Header.Get("X-Forwarded-Proto"); fwd != "" {
scheme = fwd
}
return scheme + "://" + r.Host
return v1.Scheme(r) + "://" + r.Host
}
+120 -29
View File
@@ -1,11 +1,15 @@
package v1
import (
"bytes"
"errors"
"fmt"
"io"
"log/slog"
"net"
"net/http"
"strconv"
"strings"
"github.com/go-chi/chi/v5"
@@ -15,6 +19,7 @@ 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 +45,7 @@ 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 +73,43 @@ 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 +117,51 @@ 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, ok := rewriteServed(w, r, sr, *remote, result.Reader)
if !ok {
return
}
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 +172,7 @@ 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
}
@@ -160,7 +195,7 @@ func (h *ProxyHandler) handleVirtual(w http.ResponseWriter, r *http.Request) {
return
}
proxyBaseURL := fmt.Sprintf("%s://%s", scheme(r), r.Host)
proxyBaseURL := fmt.Sprintf("%s://%s", Scheme(r), r.Host)
loc, ok, err := h.virtualEngine.MemberRedirect(r.Context(), *virt, path, r.URL.RawQuery, proxyBaseURL)
if err != nil {
@@ -237,12 +272,68 @@ func (h *ProxyHandler) serveLocalFile(w http.ResponseWriter, r *http.Request, re
io.Copy(w, reader)
}
func scheme(r *http.Request) string {
// Scheme returns the client-facing scheme: TLS, else the first
// X-Forwarded-Proto value when it is http or https, else http.
func Scheme(r *http.Request) string {
if r.TLS != nil {
return "https"
}
if fwd := r.Header.Get("X-Forwarded-Proto"); fwd != "" {
fwd, _, _ := strings.Cut(r.Header.Get("X-Forwarded-Proto"), ",")
if fwd = strings.ToLower(strings.TrimSpace(fwd)); fwd == "https" {
return fwd
}
return "http"
}
// rewriteServed rewrites a cached body for the requesting host and marks the
// response uncacheable by shared caches, since it varies per Host.
func rewriteServed(w http.ResponseWriter, r *http.Request, sr provider.ServeRewriter, remote models.Remote, src io.Reader) ([]byte, bool) {
if !validHost(r.Host) {
http.Error(w, "invalid host header", http.StatusBadRequest)
return nil, false
}
raw, err := io.ReadAll(src)
if err != nil {
http.Error(w, "bad gateway", http.StatusBadGateway)
return nil, false
}
raw = sr.RewriteServed(raw, remote, fmt.Sprintf("%s://%s", Scheme(r), r.Host))
w.Header().Set("Cache-Control", "no-store")
w.Header().Set("Vary", "Host, X-Forwarded-Proto")
w.Header().Set("Content-Length", strconv.Itoa(len(raw)))
return raw, true
}
// validHost accepts host[:port] where host is a DNS name or IP literal.
func validHost(hostport string) bool {
host, port := hostport, ""
if h, p, err := net.SplitHostPort(hostport); err == nil {
if p == "" {
return false
}
host, port = h, p
} else if strings.HasPrefix(hostport, "[") {
return strings.HasSuffix(hostport, "]") && net.ParseIP(hostport[1:len(hostport)-1]) != nil
}
if port != "" {
if n, err := strconv.Atoi(port); err != nil || n < 1 || n > 65535 {
return false
}
}
if net.ParseIP(host) != nil {
return true
}
if strings.HasPrefix(hostport, "[") {
return false
}
if host == "" || len(host) > 253 {
return false
}
for _, label := range strings.Split(strings.TrimSuffix(host, "."), ".") {
if label == "" || len(label) > 63 || label[0] == '-' || label[len(label)-1] == '-' ||
strings.Trim(strings.ToLower(label), "abcdefghijklmnopqrstuvwxyz0123456789-_") != "" {
return false
}
}
return true
}
+74
View File
@@ -0,0 +1,74 @@
package v1
import (
"net/http"
"net/http/httptest"
"strings"
"testing"
"git.unkin.net/unkin/artifactapi/internal/provider/nuget"
"git.unkin.net/unkin/artifactapi/pkg/models"
)
func TestValidHost(t *testing.T) {
for _, h := range []string{"aa.example", "aa.example:8443", "artifactapi.k8s.syd1.au.unkin.net", "10.0.0.1:80", "[::1]:8080", "[::1]", "::1", "localhost", "my_host.local"} {
if !validHost(h) {
t.Errorf("validHost(%q) = false, want true", h)
}
}
for _, h := range []string{"", "evil\".example", "a b", "aa.example:0", "aa.example:99999", "aa.example:x", "aa.example:", ":8080", "-bad.example", "a..b", "[::1", "[nope]:80", "a/b", "a<script>", strings.Repeat("a", 64) + ".example"} {
if validHost(h) {
t.Errorf("validHost(%q) = true, want false", h)
}
}
}
var nugetOrg = models.Remote{Name: "nuget-org", BaseURL: "https://api.nuget.org/v3/index.json"}
const serviceIndex = `{"resources":[{"@id":"https://api.nuget.org/v3-flatcontainer/"}]}`
func rewrite(t *testing.T, host, proto string) (*httptest.ResponseRecorder, string, bool) {
t.Helper()
r := httptest.NewRequest(http.MethodGet, "/api/v1/remote/nuget-org/index.json", nil)
r.Host = host
if proto != "" {
r.Header.Set("X-Forwarded-Proto", proto)
}
w := httptest.NewRecorder()
raw, ok := rewriteServed(w, r, &nuget.Provider{}, nugetOrg, strings.NewReader(serviceIndex))
return w, string(raw), ok
}
func TestRewriteServedHeaders(t *testing.T) {
w, body, ok := rewrite(t, "aa.example:8443", "https")
if !ok {
t.Fatal("valid request rejected")
}
if want := `{"resources":[{"@id":"https://aa.example:8443/api/v1/remote/nuget-org/v3-flatcontainer/"}]}`; body != want {
t.Errorf("body = %s, want %s", body, want)
}
if got := w.Header().Get("Cache-Control"); got != "no-store" {
t.Errorf("Cache-Control = %q, want no-store", got)
}
if got := w.Header().Get("Vary"); got != "Host, X-Forwarded-Proto" {
t.Errorf("Vary = %q", got)
}
if got := w.Header().Get("Content-Length"); got != "91" || len(body) != 91 {
t.Errorf("Content-Length = %q, body len %d", got, len(body))
}
}
func TestRewriteServedIgnoresBogusProto(t *testing.T) {
_, plain, _ := rewrite(t, "aa.example", "")
_, bogus, _ := rewrite(t, "aa.example", "javascript")
if bogus != plain || !strings.Contains(bogus, `"http://aa.example/`) {
t.Errorf("bogus X-Forwarded-Proto changed the body: %s", bogus)
}
}
func TestRewriteServedRejectsInvalidHost(t *testing.T) {
w, _, ok := rewrite(t, `evil"},{"x":"`, "")
if ok || w.Code != http.StatusBadRequest {
t.Errorf("invalid host: ok=%v code=%d, want rejected with 400", ok, w.Code)
}
}
+41
View File
@@ -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)
}
}
}
+17 -3
View File
@@ -7,14 +7,28 @@ import (
)
func TestScheme(t *testing.T) {
if got := scheme(&http.Request{TLS: &tls.ConnectionState{}}); got != "https" {
if got := Scheme(&http.Request{TLS: &tls.ConnectionState{}}); got != "https" {
t.Errorf("TLS request scheme = %q, want https", got)
}
r := &http.Request{Header: http.Header{"X-Forwarded-Proto": {"https"}}}
if got := scheme(r); got != "https" {
if got := Scheme(r); got != "https" {
t.Errorf("X-Forwarded-Proto scheme = %q, want https", got)
}
if got := scheme(&http.Request{Header: http.Header{}}); got != "http" {
for fwd, want := range map[string]string{
"https, http": "https",
"http, https": "http",
"HTTPS": "https",
" https ": "https",
"javascript": "http",
"ftp": "http",
"https;evil": "http",
} {
r := &http.Request{Header: http.Header{"X-Forwarded-Proto": {fwd}}}
if got := Scheme(r); got != want {
t.Errorf("X-Forwarded-Proto %q scheme = %q, want %s", fwd, got, want)
}
}
if got := Scheme(&http.Request{Header: http.Header{}}); got != "http" {
t.Errorf("default scheme = %q, want http", got)
}
}
+2
View File
@@ -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
+2
View File
@@ -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
+97
View File
@@ -0,0 +1,97 @@
// Package nuget proxies a NuGet v3 feed: the service index, registration pages
// and flat container indexes are mutable; package, symbol, nuspec, readme and
// icon blobs are immutable.
package nuget
import (
"context"
"encoding/json"
"net/http"
"net/url"
pathpkg "path"
"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"), strings.HasSuffix(path, ".snupkg"), pathpkg.Base(path) == "icon":
return "application/octet-stream"
case strings.HasSuffix(path, ".nuspec"):
return "application/xml"
case pathpkg.Base(path) == "readme":
return "text/markdown"
}
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, _ := json.Marshal(strings.TrimRight(proxyBaseURL, "/") + "/api/v1/remote/" + remote.Name)
return []byte(strings.ReplaceAll(string(body), from, string(to[1:len(to)-1])))
}
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
}
// isPackage matches flat container blobs: {id}.{ver}.(s)nupkg, {id}.nuspec and
// the {id}/{ver}/readme and {id}/{ver}/icon files.
func isPackage(path string) bool {
for _, ext := range []string{".nupkg", ".snupkg", ".nuspec"} {
if strings.HasSuffix(path, ext) {
return true
}
}
base := pathpkg.Base(path)
return (base == "readme" || base == "icon") && strings.Count(strings.Trim(path, "/"), "/") >= 2
}
+94
View File
@@ -0,0 +1,94 @@
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/13.0.3/newtonsoft.json.13.0.3.snupkg", provider.Immutable},
{"v3-flatcontainer/newtonsoft.json/13.0.3/readme", provider.Immutable},
{"v3-flatcontainer/newtonsoft.json/13.0.3/icon", provider.Immutable},
{"v3-flatcontainer/newtonsoft.json/index.json", provider.Mutable},
{"readme", 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 TestContentType(t *testing.T) {
p := &Provider{}
for path, want := range map[string]string{
"v3-flatcontainer/a/1.0.0/a.1.0.0.snupkg": "application/octet-stream",
"v3-flatcontainer/a/1.0.0/icon": "application/octet-stream",
"v3-flatcontainer/a/1.0.0/readme": "text/markdown",
"v3-flatcontainer/a/index.json": "application/json",
} {
if got := p.ContentType(path); got != want {
t.Errorf("ContentType(%q) = %q, want %q", path, got, want)
}
}
}
func TestRewriteServedEscapesJSON(t *testing.T) {
body := `{"@id":"https://api.nuget.org/v3-flatcontainer/"}`
got := (&Provider{}).RewriteServed([]byte(body), nugetOrg, `http://evil"<x>`)
if want := `{"@id":"http://evil\"\u003cx\u003e/api/v1/remote/nuget-org/v3-flatcontainer/"}`; string(got) != want {
t.Errorf("RewriteServed = %s, want %s", got, 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")
}
}
+13
View File
@@ -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 {
+2
View File
@@ -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
+2
View File
@@ -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
+2
View File
@@ -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
+1 -1
View File
@@ -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)
+14
View File
@@ -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()
+1
View File
@@ -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"
+2
View File
@@ -17,6 +17,7 @@ const (
PackageTerraform PackageType = "terraform"
PackageGoProxy PackageType = "goproxy"
PackageCargo PackageType = "cargo"
PackageNuGet PackageType = "nuget"
PackageGitHubRPM PackageType = "github_rpm"
PackageGitHubDeb PackageType = "github_deb"
PackageGitHubAlpine PackageType = "github_alpine"
@@ -35,6 +36,7 @@ var validPackageTypes = map[PackageType]bool{
PackageTerraform: true,
PackageGoProxy: true,
PackageCargo: true,
PackageNuGet: true,
PackageGitHubRPM: true,
PackageGitHubDeb: true,
PackageGitHubAlpine: true,
+1
View File
@@ -19,6 +19,7 @@ func TestPackageTypeValid(t *testing.T) {
models.PackageTerraform,
models.PackageGoProxy,
models.PackageCargo,
models.PackageNuGet,
models.PackageGitHubRPM,
models.PackageGitHubDeb,
models.PackageGitHubAlpine,
+16
View File
@@ -243,6 +243,22 @@ index = "sparse+${proxy}/"`,
},
];
case 'nuget':
return [
{
title: 'Use this feed instead of nuget.org',
language: 'xml',
code: `<!-- nuget.config -->
<configuration>
<packageSources>
<clear />
<add key="${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 [
{
+1
View File
@@ -18,6 +18,7 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
terraform: 'blue',
goproxy: 'green',
cargo: 'yellow',
nuget: 'blue',
};
export function Locals() {
+1
View File
@@ -18,6 +18,7 @@ const typeColors: Record<string, 'blue' | 'green' | 'yellow' | 'red' | 'default'
terraform: 'blue',
goproxy: 'green',
cargo: 'yellow',
nuget: 'blue',
};
export function Remotes() {