Files
artifactapi/internal/api/v1/proxy.go
T
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

326 lines
9.7 KiB
Go

package v1
import (
"bytes"
"errors"
"fmt"
"io"
"log/slog"
"net"
"net/http"
"strconv"
"strings"
"github.com/go-chi/chi/v5"
v2 "git.unkin.net/unkin/artifactapi/internal/api/v2"
"git.unkin.net/unkin/artifactapi/internal/database"
"git.unkin.net/unkin/artifactapi/internal/provider"
"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 {
engine *proxy.Engine
virtualEngine *virtual.Engine
db *database.DB
store *storage.S3
local *v2.LocalHandler
cas *storage.CAS
}
func NewProxyHandler(engine *proxy.Engine, virtualEngine *virtual.Engine, db *database.DB, store *storage.S3, local *v2.LocalHandler) *ProxyHandler {
return &ProxyHandler{
engine: engine,
virtualEngine: virtualEngine,
db: db,
store: store,
local: local,
cas: storage.NewCAS(store),
}
}
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
}
// DockerV2Routes mounts the Docker Registry HTTP API V2. Reads (GET/HEAD)
// dispatch to a local registry implementation for local docker repos and fall
// through to the upstream proxy otherwise; writes (POST/PATCH/PUT/DELETE) are
// only valid for local docker repos and drive push.
func (h *ProxyHandler) DockerV2Routes() chi.Router {
r := chi.NewRouter()
r.Get("/", h.handleDockerPing)
r.Head("/", h.handleDockerPing)
r.Get("/{remoteName}/*", h.dockerGet)
r.Head("/{remoteName}/*", h.dockerHead)
r.Post("/{remoteName}/*", h.dockerPost)
r.Patch("/{remoteName}/*", h.dockerPatch)
r.Put("/{remoteName}/*", h.dockerPut)
r.Delete("/{remoteName}/*", h.dockerDelete)
return r
}
func (h *ProxyHandler) handleDockerPing(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Docker-Distribution-Api-Version", "registry/2.0")
w.WriteHeader(http.StatusOK)
}
func (h *ProxyHandler) handleProxy(w http.ResponseWriter, r *http.Request) {
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
}
prov, err := provider.Get(remote.PackageType)
if err != nil {
http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
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
}
}
result, err := h.engine.Fetch(r.Context(), *remote, path, prov, r.Header)
if err != nil {
var proxyErr *proxy.ProxyError
if errors.As(err, &proxyErr) {
http.Error(w, proxyErr.Message, proxyErr.Status)
return
}
slog.Error("proxy fetch failed", "remote", remoteName, "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 := serveRewriter(prov, path); ok {
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("X-Artifact-Size", fmt.Sprintf("%d", result.Size))
}
w.WriteHeader(http.StatusOK)
io.Copy(w, body)
}
func (h *ProxyHandler) handleProxyHead(w http.ResponseWriter, r *http.Request) {
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
}
prov, err := provider.Get(remote.PackageType)
if err != nil {
http.Error(w, fmt.Sprintf("no provider for %q", remote.PackageType), http.StatusInternalServerError)
return
}
// Rewritten bodies differ in size from the cached object, so HEAD takes the
// GET path; net/http discards the body for HEAD.
if _, ok := serveRewriter(prov, path); ok {
h.handleProxy(w, r)
return
}
result, err := h.engine.Head(r.Context(), *remote, path, prov)
if err != nil {
var proxyErr *proxy.ProxyError
if errors.As(err, &proxyErr) {
http.Error(w, proxyErr.Message, proxyErr.Status)
return
}
slog.Error("proxy head failed", "remote", remoteName, "path", path, "error", err)
http.Error(w, "bad gateway", http.StatusBadGateway)
return
}
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.WriteHeader(http.StatusOK)
}
func (h *ProxyHandler) handleVirtual(w http.ResponseWriter, r *http.Request) {
virtualName := chi.URLParam(r, "virtualName")
path := chi.URLParam(r, "*")
virt, err := h.db.GetVirtual(r.Context(), virtualName)
if err != nil {
http.Error(w, fmt.Sprintf("virtual %q not found", virtualName), http.StatusNotFound)
return
}
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 {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
if ok {
http.Redirect(w, r, loc, http.StatusFound)
return
}
body, contentType, err := h.virtualEngine.Fetch(r.Context(), *virt, path, proxyBaseURL)
if errors.Is(err, virtual.ErrNotFound) {
http.Error(w, "not found", http.StatusNotFound)
return
}
if err != nil {
slog.Error("virtual fetch failed", "virtual", virtualName, "path", path, "error", err)
http.Error(w, "bad gateway", http.StatusBadGateway)
return
}
w.Header().Set("Content-Type", contentType)
w.Header().Set("X-Artifact-Source", "virtual")
w.WriteHeader(http.StatusOK)
w.Write(body)
}
func (h *ProxyHandler) handleLocal(w http.ResponseWriter, r *http.Request) {
localName := chi.URLParam(r, "localName")
path := chi.URLParam(r, "*")
remote, err := h.db.GetRemote(r.Context(), localName)
if err != nil {
http.Error(w, fmt.Sprintf("local %q not found", localName), http.StatusNotFound)
return
}
prov, _ := provider.Get(remote.PackageType)
if indexer, ok := prov.(provider.LocalIndexer); ok {
if indexer.ServeLocalIndex(w, r, h.db, remote.Name, path) {
return
}
}
h.serveLocalFile(w, r, localName, path)
}
func (h *ProxyHandler) serveLocalFile(w http.ResponseWriter, r *http.Request, repoName, path string) {
file, err := h.db.GetLocalFile(r.Context(), repoName, path)
if err != nil {
slog.Error("local file lookup failed", "repo", repoName, "path", path, "error", err)
http.Error(w, "internal error", http.StatusInternalServerError)
return
}
if file == nil {
http.Error(w, "not found", http.StatusNotFound)
return
}
s3Key := storage.BlobKey(file.ContentHash[len("sha256:"):])
reader, info, err := h.store.Download(r.Context(), s3Key)
if err != nil {
slog.Error("local file download failed", "repo", repoName, "path", path, "error", err)
http.Error(w, "internal error", http.StatusInternalServerError)
return
}
defer reader.Close()
w.Header().Set("Content-Type", info.ContentType)
w.Header().Set("Content-Length", fmt.Sprintf("%d", info.Size))
w.Header().Set("X-Artifact-Source", "local")
w.WriteHeader(http.StatusOK)
io.Copy(w, reader)
}
func scheme(r *http.Request) string {
if r.TLS != nil {
return "https"
}
if fwd := r.Header.Get("X-Forwarded-Proto"); fwd == "http" || 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
}
func serveRewriter(prov provider.Provider, path string) (provider.ServeRewriter, bool) {
sr, ok := prov.(provider.ServeRewriter)
return sr, ok && prov.Classify(path) == provider.Mutable
}
// 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 {
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
}