From 2c200095994938136529f83efef29caf5285c8c0 Mon Sep 17 00:00:00 2001 From: unkin-agent Date: Sat, 17 Oct 2026 17:00:45 +1100 Subject: [PATCH] Add npm virtual repositories --- README.md | 2 +- docs/npm/virtual.md | 30 +++ e2e-docker/README.md | 3 +- e2e-docker/npm_virtual_test.go | 68 +++++++ internal/api/v1/npm_virtual.go | 26 +++ internal/api/v1/proxy.go | 10 +- internal/server/server.go | 1 + internal/virtual/engine.go | 20 +- internal/virtual/npm_merger.go | 267 +++++++++++++++++++++++++ internal/virtual/npm_merger_test.go | 289 ++++++++++++++++++++++++++++ 10 files changed, 709 insertions(+), 7 deletions(-) create mode 100644 docs/npm/virtual.md create mode 100644 e2e-docker/npm_virtual_test.go create mode 100644 internal/api/v1/npm_virtual.go create mode 100644 internal/virtual/npm_merger.go create mode 100644 internal/virtual/npm_merger_test.go diff --git a/README.md b/README.md index c2984e1..cefeede 100644 --- a/README.md +++ b/README.md @@ -33,7 +33,7 @@ Each type's paths, Terraform examples and local/virtual behaviour are in `docs/< - `generic`: [remote](docs/generic/remote.md) - `goproxy`: [remote](docs/goproxy/remote.md) - `helm`: [remote](docs/helm/remote.md), [local](docs/helm/local.md), [virtual](docs/helm/virtual.md) -- `npm`: [remote](docs/npm/remote.md), [local](docs/npm/local.md) +- `npm`: [remote](docs/npm/remote.md), [local](docs/npm/local.md), [virtual](docs/npm/virtual.md) - `nuget`: [remote](docs/nuget/remote.md) - `puppet`: [remote](docs/puppet/remote.md), [local](docs/puppet/local.md) - `pypi`: [remote](docs/pypi/remote.md) diff --git a/docs/npm/virtual.md b/docs/npm/virtual.md new file mode 100644 index 0000000..19deb9a --- /dev/null +++ b/docs/npm/virtual.md @@ -0,0 +1,30 @@ +# `npm` virtual + +An npm virtual serves one registry over local and remote npm members: +`npm install` and `npm view` work against `/api/v1/virtual//`. + +- Versions are the union across members; on a duplicate version the earlier + member wins. +- Each dist-tag comes from the first member defining it, and is dropped if it + names a version missing from the merged set. +- Tarball URLs point at the virtual (`/`), which 302s to the + owning member. +- Full and abbreviated (`application/vnd.npm.install-v1+json`) packuments are + both served. +- A member error fails the request with 502; a member without the package is + skipped. Merges are cached for 60s per package. + +```hcl +resource "artifactapi_virtual" "npm" { + name = "npm" + package_type = "npm" + members = [artifactapi_local_npm.internal.name, artifactapi_remote_npm.npmjs.name] +} +``` + +```ini +# .npmrc +registry=https://artifactapi.example.com/api/v1/virtual/npm/ +``` + +Publish to the local member directly; the virtual is read-only. diff --git a/e2e-docker/README.md b/e2e-docker/README.md index 85364c2..35816cc 100644 --- a/e2e-docker/README.md +++ b/e2e-docker/README.md @@ -31,7 +31,8 @@ already-running stack. `node:22` client: `npm publish` unscoped + scoped, `npm install` + `require()`, second version, republish rejected). - **Virtual repositories** — pypi simple-index merge and helm `index.yaml` merge - across two members. + across two members; npm packument merge over two locals via a stock `node:22` + client (merged versions, install through the member redirect). - **Mirrorlist** — an rpm remote with a `mirrorlist` of extra upstream mirrors (pool = `base_url` + `mirrorlist`): round-robin distribution across both mirrors (constant-body `mockupstreama` / `mockupstreamb`), failover past a dead primary, diff --git a/e2e-docker/npm_virtual_test.go b/e2e-docker/npm_virtual_test.go new file mode 100644 index 0000000..31f92b0 --- /dev/null +++ b/e2e-docker/npm_virtual_test.go @@ -0,0 +1,68 @@ +//go:build dockere2e + +package e2edocker + +import ( + "fmt" + "os" + "os/exec" + "strings" + "testing" + "time" +) + +// TestVirtualNPMInstall publishes to two local npm repos and drives a stock +// npm client through a virtual over both: merged versions and dist-tags, and +// an install whose tarballs resolve via the virtual's member redirect. +func TestVirtualNPMInstall(t *testing.T) { + network := os.Getenv("COMPOSE_NETWORK") + internal := os.Getenv("ARTIFACTAPI_INTERNAL") + if network == "" || internal == "" { + t.Skip("COMPOSE_NETWORK/ARTIFACTAPI_INTERNAL not set; run via scripts/docker-e2e.sh") + } + if _, err := exec.LookPath("docker"); err != nil { + t.Skip("docker not available on the test host") + } + + id := time.Now().UnixNano() + a, b, virt := fmt.Sprintf("e2e-npm-a-%d", id), fmt.Sprintf("e2e-npm-b-%d", id), fmt.Sprintf("e2e-npm-v-%d", id) + for _, name := range []string{a, b} { + createRepo(t, fmt.Sprintf(`{"name":%q,"package_type":"npm","repo_type":"local"}`, name)) + defer deleteRepo(t, name) + } + createVirtual(t, fmt.Sprintf(`{"name":%q,"package_type":"npm","members":[%q,%q]}`, virt, a, b)) + defer deleteVirtual(t, virt) + + base := strings.TrimRight(internal, "/") + script := `set -euo pipefail +pub() { d="/w/src/$2-$3-$1"; mkdir -p "$d"; cd "$d" + printf '{"name":"%s","version":"%s","main":"index.js"}' "$2" "$3" > package.json + echo "module.exports = '$1:$2@$3';" > index.js + printf 'registry=%s\n%s:_authToken=unused\n' "$BASE/api/v1/local/$1/" "${BASE#http:}/api/v1/local/$1/" > .npmrc + npm publish; } +pub "$A" @e2e/virt 1.0.0 +pub "$B" @e2e/virt 1.0.0 +pub "$B" @e2e/virt 1.1.0 +mkdir -p /w/app && cd /w/app && npm init -y >/dev/null +echo "registry=$BASE/api/v1/virtual/$V/" > .npmrc +echo "VERSIONS $(npm view @e2e/virt versions --json | tr -d ' \n')" +npm install --no-audit --cache /tmp/fresh-cache @e2e/virt@1.0.0 +node -e "console.log('REQ', require('@e2e/virt'))" +echo "RESOLVED $(node -p "require('./package-lock.json').packages['node_modules/@e2e/virt'].resolved")"` + + out, err := exec.Command("docker", "run", "--rm", "--network", network, + "-e", "BASE="+base, "-e", "A="+a, "-e", "B="+b, "-e", "V="+virt, + "node:22", "bash", "-c", script).CombinedOutput() + if err != nil { + t.Fatalf("npm client run failed: %v\n%s", err, out) + } + for _, want := range []string{ + `VERSIONS ["1.0.0","1.1.0"]`, + "REQ " + a + ":@e2e/virt@1.0.0", + "RESOLVED " + base + "/api/v1/virtual/" + virt + "/" + a + "/@e2e/virt/-/virt-1.0.0.tgz", + } { + if !strings.Contains(string(out), want) { + t.Fatalf("missing %q in npm output:\n%s", want, out) + } + } +} diff --git a/internal/api/v1/npm_virtual.go b/internal/api/v1/npm_virtual.go new file mode 100644 index 0000000..7ac006b --- /dev/null +++ b/internal/api/v1/npm_virtual.go @@ -0,0 +1,26 @@ +package v1 + +import ( + "context" + "encoding/json" + + "git.unkin.net/unkin/artifactapi/internal/virtual" +) + +// LocalNPMPackument serves a local npm repo's packument to npm virtuals, with +// tarball paths relative to the repo. +func (h *ProxyHandler) LocalNPMPackument(ctx context.Context, repo, pkg string) ([]byte, error) { + files, err := h.db.ListLocalFilesByPrefix(ctx, repo, pkg+"/-/") + if err != nil { + return nil, err + } + read := func(hash string) ([]byte, error) { return h.readLocalBlob(ctx, hash) } + doc, err := buildNPMPackument(pkg, files, read, "") + if err != nil { + return nil, err + } + if doc == nil { + return nil, virtual.ErrNotFound + } + return json.Marshal(doc) +} diff --git a/internal/api/v1/proxy.go b/internal/api/v1/proxy.go index 27395d0..2ff961b 100644 --- a/internal/api/v1/proxy.go +++ b/internal/api/v1/proxy.go @@ -7,6 +7,7 @@ import ( "io" "log/slog" "net/http" + "strings" "github.com/go-chi/chi/v5" @@ -186,7 +187,14 @@ func (h *ProxyHandler) handleVirtual(w http.ResponseWriter, r *http.Request) { return } - body, contentType, err := h.virtualEngine.Fetch(r.Context(), *virt, path, proxyBaseURL) + var body []byte + var contentType string + if virt.PackageType == models.PackageNPM { + abbreviated := strings.Contains(r.Header.Get("Accept"), virtual.NPMAbbreviatedType) + body, contentType, err = h.virtualEngine.FetchNPM(r.Context(), *virt, path, proxyBaseURL, abbreviated) + } else { + 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 diff --git a/internal/server/server.go b/internal/server/server.go index bb61795..b9d8a35 100644 --- a/internal/server/server.go +++ b/internal/server/server.go @@ -166,6 +166,7 @@ func (s *Server) routes() chi.Router { r.Mount(tfregistry.MountPath, s.tfRegistry.Routes()) proxyHandler := v1.NewProxyHandler(s.engine, s.virtEngine, s.db, s.store, s.localHandler) + s.virtEngine.NPMLocal = proxyHandler.LocalNPMPackument r.Mount("/api/v1", proxyHandler.Routes()) r.Mount("/v2", proxyHandler.DockerV2Routes()) diff --git a/internal/virtual/engine.go b/internal/virtual/engine.go index 1f8bf7c..0ac8687 100644 --- a/internal/virtual/engine.go +++ b/internal/virtual/engine.go @@ -26,6 +26,11 @@ type Engine struct { proxyEngine *proxy.Engine getRemote func(context.Context, string) (*models.Remote, error) rpmMember func(context.Context, string) (*RPMMember, error) + npmMember func(ctx context.Context, name, pkg string) (*NPMMember, error) + + // NPMLocal returns a local npm repo's packument with tarball paths relative + // to the repo, or ErrNotFound. + NPMLocal func(ctx context.Context, repo, pkg string) ([]byte, error) mergeTTL time.Duration @@ -55,6 +60,7 @@ const rpmMergeTTL = 60 * time.Second func NewEngine(db *database.DB, proxyEngine *proxy.Engine) *Engine { e := &Engine{db: db, proxyEngine: proxyEngine, getRemote: db.GetRemote, mergeTTL: rpmMergeTTL} e.rpmMember = e.fetchRPMMember + e.npmMember = e.fetchNPMMember return e } @@ -179,11 +185,17 @@ var ( ErrBadPath = errors.New("invalid path") ) -// MemberRedirect maps an rpm virtual package path (/, as written -// by MergeRPM) to the owning member's route. ok is false for any other path; -// ErrBadPath means the path is absolute or escapes the member. +// MemberRedirect maps an rpm or npm virtual package path (/, as +// written by MergeRPM/MergeNPM) to the owning member's route. ok is false for +// any other path; ErrBadPath means the path is absolute or escapes the member. func (e *Engine) MemberRedirect(ctx context.Context, virt models.Virtual, path, rawQuery, proxyBaseURL string) (string, bool, error) { - if virt.PackageType != models.PackageRPM || strings.HasPrefix(path, "repodata/") { + switch virt.PackageType { + case models.PackageRPM: + if strings.HasPrefix(path, "repodata/") { + return "", false, nil + } + case models.PackageNPM: + default: return "", false, nil } name, rest, found := strings.Cut(path, "/") diff --git a/internal/virtual/npm_merger.go b/internal/virtual/npm_merger.go new file mode 100644 index 0000000..3c19fc9 --- /dev/null +++ b/internal/virtual/npm_merger.go @@ -0,0 +1,267 @@ +package virtual + +import ( + "context" + "encoding/json" + "errors" + "fmt" + "net/http" + "net/url" + "regexp" + "slices" + "strings" + + "git.unkin.net/unkin/artifactapi/internal/proxy" + "git.unkin.net/unkin/artifactapi/pkg/models" +) + +const ( + NPMAbbreviatedType = "application/vnd.npm.install-v1+json" + npmAbbreviatedFile = "install-v1" + maxNPMPackuments = 1024 +) + +var npmVirtualNameRe = regexp.MustCompile(`^(@[A-Za-z0-9][A-Za-z0-9._~-]*/)?[A-Za-z0-9][A-Za-z0-9._~-]*$`) + +// npmAbbreviatedFields are the version fields kept in an install-v1 packument. +var npmAbbreviatedFields = []string{ + "name", "version", "deprecated", "dependencies", "optionalDependencies", + "devDependencies", "bundleDependencies", "peerDependencies", "peerDependenciesMeta", + "bin", "directories", "dist", "engines", "_hasShrinkwrap", "hasInstallScript", + "cpu", "os", "libc", +} + +// NPMMember is one member's full packument for a package; Doc is nil when the +// member does not have the package. Tarball URLs under one of Bases are +// rewritten to go via the virtual; with no Bases (a local) they are relative. +type NPMMember struct { + RemoteName string + Bases []string + Doc []byte +} + +// NPMPackument is a merged packument in full and install-v1 form. +type NPMPackument struct { + Full, Abbreviated []byte +} + +func (p *NPMPackument) index() []byte { return p.Full } +func (p *NPMPackument) files() map[string][]byte { + return map[string][]byte{npmAbbreviatedFile: p.Abbreviated} +} + +// MergeNPM unions versions across members (first member wins a duplicate), +// keeps the first member's value for each dist-tag, drops tags naming versions +// outside the merged set and points every owned tarball at +// tarballBase + /. ErrNotFound means no member has the package. +func MergeNPM(members []NPMMember, tarballBase string) (*NPMPackument, error) { + var base map[string]json.RawMessage + versions := map[string]map[string]json.RawMessage{} + tags := map[string]string{} + times := map[string]json.RawMessage{} + var modified string + for _, m := range members { + if m.Doc == nil { + continue + } + var doc map[string]json.RawMessage + var vs map[string]map[string]json.RawMessage + var dt map[string]string + var tm map[string]json.RawMessage + if err := json.Unmarshal(m.Doc, &doc); err != nil { + return nil, fmt.Errorf("member %q packument: %w", m.RemoteName, err) + } + for field, dst := range map[string]any{"versions": &vs, "dist-tags": &dt, "time": &tm} { + if raw, ok := doc[field]; ok { + if err := json.Unmarshal(raw, dst); err != nil { + return nil, fmt.Errorf("member %q %s: %w", m.RemoteName, field, err) + } + } + } + if base == nil { + base = doc + } + for v, man := range vs { + if _, dup := versions[v]; dup || man == nil { + continue + } + if err := rewriteNPMTarball(man, m, tarballBase); err != nil { + return nil, fmt.Errorf("member %q %s: %w", m.RemoteName, v, err) + } + versions[v] = man + } + for tag, v := range dt { + if _, ok := tags[tag]; !ok { + tags[tag] = v + } + } + for k, v := range tm { + if k == "modified" { + var s string + if json.Unmarshal(v, &s) == nil && s > modified { + modified = s + } + continue + } + if _, ok := times[k]; !ok { + times[k] = v + } + } + } + if base == nil { + return nil, ErrNotFound + } + for tag, v := range tags { + if _, ok := versions[v]; !ok { + delete(tags, tag) + } + } + if modified != "" { + times["modified"], _ = json.Marshal(modified) + } + + full := map[string]any{} + for k, v := range base { + full[k] = v + } + full["versions"], full["dist-tags"] = versions, tags + delete(full, "time") + if len(times) > 0 { + full["time"] = times + } + + abbrevVersions := make(map[string]map[string]json.RawMessage, len(versions)) + for v, man := range versions { + a := map[string]json.RawMessage{} + for _, f := range npmAbbreviatedFields { + if raw, ok := man[f]; ok { + a[f] = raw + } + } + abbrevVersions[v] = a + } + abbrev := map[string]any{"name": base["name"], "dist-tags": tags, "versions": abbrevVersions} + if modified != "" { + abbrev["modified"] = modified + } + + fullJSON, err := json.Marshal(full) + if err != nil { + return nil, err + } + abbrevJSON, err := json.Marshal(abbrev) + if err != nil { + return nil, err + } + return &NPMPackument{Full: fullJSON, Abbreviated: abbrevJSON}, nil +} + +// rewriteNPMTarball leaves a tarball outside the member's bases untouched. +func rewriteNPMTarball(man map[string]json.RawMessage, m NPMMember, tarballBase string) error { + raw, ok := man["dist"] + if !ok { + return nil + } + var dist map[string]json.RawMessage + if err := json.Unmarshal(raw, &dist); err != nil { + return fmt.Errorf("dist: %w", err) + } + var tarball string + if err := json.Unmarshal(dist["tarball"], &tarball); err != nil { + return nil + } + rel, ok := npmMemberPath(tarball, m.Bases) + if !ok { + return nil + } + dist["tarball"], _ = json.Marshal(tarballBase + url.PathEscape(m.RemoteName) + "/" + rel) + man["dist"], _ = json.Marshal(dist) + return nil +} + +func npmMemberPath(tarball string, bases []string) (string, bool) { + if len(bases) == 0 { + return tarball, tarball != "" && !strings.Contains(tarball, "://") && !strings.HasPrefix(tarball, "/") + } + for _, b := range bases { + if rel, ok := strings.CutPrefix(tarball, strings.TrimRight(b, "/")+"/"); ok && rel != "" { + return rel, true + } + } + return "", false +} + +// FetchNPM serves the merged packument for the package named by path, full or +// abbreviated (install-v1). +func (e *Engine) FetchNPM(ctx context.Context, virt models.Virtual, path, proxyBaseURL string, abbreviated bool) ([]byte, string, error) { + pkg, err := url.PathUnescape(strings.TrimSuffix(path, "/")) + if err != nil || !npmVirtualNameRe.MatchString(pkg) { + return nil, "", ErrNotFound + } + prefix := "npm\x00" + virt.Name + "\x00" + tarballBase := strings.TrimRight(proxyBaseURL, "/") + "/api/v1/virtual/" + url.PathEscape(virt.Name) + "/" + repo, err := e.merged(ctx, prefix+pkg+"\x00"+proxyBaseURL, func(ctx context.Context) (mergedRepo, error) { + members, err := fetchMembers(virt, func(name string) (*NPMMember, error) { return e.npmMember(ctx, name, pkg) }) + if err != nil { + return nil, err + } + p, err := MergeNPM(members, tarballBase) + if err != nil { + return nil, err + } + return p, nil + }) + if err != nil { + return nil, "", err + } + e.evictOldest(prefix, maxNPMPackuments) + if abbreviated { + return repo.files()[npmAbbreviatedFile], NPMAbbreviatedType, nil + } + return repo.index(), "application/json", nil +} + +// fetchNPMMember returns a member with a nil Doc when it lacks the package. +func (e *Engine) fetchNPMMember(ctx context.Context, name, pkg string) (*NPMMember, error) { + remote, err := e.getRemote(ctx, name) + if err != nil { + return nil, fmt.Errorf("remote %q: %w", name, err) + } + m := &NPMMember{RemoteName: name} + if remote.RepoType == models.RepoTypeLocal { + if e.NPMLocal == nil { + return nil, errors.New("local npm packuments are not wired") + } + m.Doc, err = e.NPMLocal(ctx, name, pkg) + } else { + m.Bases = remote.UpstreamPool() + m.Doc, err = e.fetchMemberPath(ctx, *remote, strings.Replace(pkg, "/", "%2f", 1)) + } + var pe *proxy.ProxyError + if errors.Is(err, ErrNotFound) || errors.As(err, &pe) && pe.Status == http.StatusNotFound { + return &NPMMember{RemoteName: name}, nil + } + if err != nil { + return nil, err + } + return m, nil +} + +// evictOldest drops the oldest merges under prefix beyond keep. +func (e *Engine) evictOldest(prefix string, keep int) { + e.mu.Lock() + defer e.mu.Unlock() + var keys []string + for k := range e.gens { + if strings.HasPrefix(k, prefix) { + keys = append(keys, k) + } + } + if len(keys) <= keep { + return + } + slices.SortFunc(keys, func(a, b string) int { return e.gens[b].at.Compare(e.gens[a].at) }) + for _, k := range keys[keep:] { + delete(e.gens, k) + } +} diff --git a/internal/virtual/npm_merger_test.go b/internal/virtual/npm_merger_test.go new file mode 100644 index 0000000..9536e0d --- /dev/null +++ b/internal/virtual/npm_merger_test.go @@ -0,0 +1,289 @@ +package virtual + +import ( + "context" + "encoding/json" + "errors" + "fmt" + "strings" + "sync" + "testing" + "time" + + "git.unkin.net/unkin/artifactapi/pkg/models" +) + +type npmDoc struct { + Name string `json:"name"` + Readme string `json:"readme,omitempty"` + Modified string `json:"modified,omitempty"` + DistTags map[string]string `json:"dist-tags"` + Versions map[string]map[string]any `json:"versions"` + Time map[string]string `json:"time,omitempty"` +} + +func npmVersion(name, v, tarball string) map[string]any { + return map[string]any{"name": name, "version": v, "readme": "long", "scripts": map[string]string{"test": "x"}, + "dependencies": map[string]string{"dep": "^1"}, "dist": map[string]any{"tarball": tarball, "shasum": "abc"}} +} + +func mustJSON(t *testing.T, v any) []byte { + t.Helper() + b, err := json.Marshal(v) + if err != nil { + t.Fatal(err) + } + return b +} + +func decodeNPM(t *testing.T, b []byte) npmDoc { + t.Helper() + var d npmDoc + if err := json.Unmarshal(b, &d); err != nil { + t.Fatalf("decode %s: %v", b, err) + } + return d +} + +func tarballOf(d npmDoc, v string) string { + dist, _ := d.Versions[v]["dist"].(map[string]any) + s, _ := dist["tarball"].(string) + return s +} + +func npmMembersFixture(t *testing.T) []NPMMember { + local := npmDoc{Name: "pkg", DistTags: map[string]string{"latest": "1.0.0", "beta": "9.9.9"}, + Versions: map[string]map[string]any{"1.0.0": npmVersion("pkg", "1.0.0", "pkg/-/pkg-1.0.0.tgz")}} + remote := npmDoc{Name: "pkg", Readme: "remote readme", + DistTags: map[string]string{"latest": "2.0.0", "next": "2.0.0", "beta": "1.0.0"}, + Versions: map[string]map[string]any{ + "1.0.0": npmVersion("pkg", "1.0.0", "https://registry.npmjs.org/pkg/-/pkg-1.0.0.tgz"), + "2.0.0": npmVersion("pkg", "2.0.0", "https://registry.npmjs.org/pkg/-/pkg-2.0.0.tgz"), + "3.0.0": npmVersion("pkg", "3.0.0", "https://cdn.example/pkg-3.0.0.tgz"), + }, + Time: map[string]string{"modified": "2024-01-01T00:00:00.000Z", "2.0.0": "2023-01-01T00:00:00.000Z"}} + return []NPMMember{ + {RemoteName: "internal", Doc: mustJSON(t, local)}, + {RemoteName: "absent"}, + {RemoteName: "npmjs", Bases: []string{"https://registry.npmjs.org/"}, Doc: mustJSON(t, remote)}, + } +} + +func TestMergeNPMUnionsVersionsMemberOrderWins(t *testing.T) { + p, err := MergeNPM(npmMembersFixture(t), "http://aa/api/v1/virtual/npm/") + if err != nil { + t.Fatal(err) + } + d := decodeNPM(t, p.Full) + if len(d.Versions) != 3 { + t.Fatalf("want 3 merged versions, got %v", d.Versions) + } + for v, want := range map[string]string{ + "1.0.0": "http://aa/api/v1/virtual/npm/internal/pkg/-/pkg-1.0.0.tgz", + "2.0.0": "http://aa/api/v1/virtual/npm/npmjs/pkg/-/pkg-2.0.0.tgz", + "3.0.0": "https://cdn.example/pkg-3.0.0.tgz", + } { + if got := tarballOf(d, v); got != want { + t.Errorf("%s tarball = %q, want %q", v, got, want) + } + } + if d.Readme != "" { + t.Errorf("top-level fields come from the first member with the package, got readme %q", d.Readme) + } + if d.Time["modified"] != "2024-01-01T00:00:00.000Z" || d.Time["2.0.0"] == "" { + t.Errorf("time not merged: %v", d.Time) + } +} + +func TestMergeNPMDistTags(t *testing.T) { + members := npmMembersFixture(t) + members[0].Doc = mustJSON(t, npmDoc{Name: "pkg", DistTags: map[string]string{"latest": "1.0.0", "gone": "0.0.1"}, + Versions: map[string]map[string]any{"1.0.0": npmVersion("pkg", "1.0.0", "pkg/-/pkg-1.0.0.tgz")}}) + p, err := MergeNPM(members, "http://aa/v/") + if err != nil { + t.Fatal(err) + } + got := decodeNPM(t, p.Full).DistTags + want := map[string]string{"latest": "1.0.0", "next": "2.0.0", "beta": "1.0.0"} + if fmt.Sprint(got) != fmt.Sprint(want) { + t.Fatalf("dist-tags = %v, want %v", got, want) + } +} + +func TestMergeNPMDropsFirstTagNamingMissingVersion(t *testing.T) { + // internal claims beta=9.9.9 first; it wins over npmjs's beta, and is then + // dropped because no member has 9.9.9. + p, err := MergeNPM(npmMembersFixture(t), "http://aa/v/") + if err != nil { + t.Fatal(err) + } + if tag, ok := decodeNPM(t, p.Full).DistTags["beta"]; ok { + t.Fatalf("beta should be dropped, got %q", tag) + } +} + +func TestMergeNPMAbbreviated(t *testing.T) { + p, err := MergeNPM(npmMembersFixture(t), "http://aa/v/") + if err != nil { + t.Fatal(err) + } + var a map[string]any + if err := json.Unmarshal(p.Abbreviated, &a); err != nil { + t.Fatal(err) + } + if a["modified"] != "2024-01-01T00:00:00.000Z" || a["name"] != "pkg" || a["readme"] != nil || a["time"] != nil { + t.Fatalf("bad abbreviated top level: %v", a) + } + v := a["versions"].(map[string]any)["2.0.0"].(map[string]any) + if v["readme"] != nil || v["scripts"] != nil { + t.Errorf("abbreviated version keeps non-install fields: %v", v) + } + if v["dependencies"] == nil || v["dist"].(map[string]any)["tarball"] != "http://aa/v/npmjs/pkg/-/pkg-2.0.0.tgz" { + t.Errorf("abbreviated version lost install fields: %v", v) + } +} + +func TestMergeNPMNoMemberHasPackage(t *testing.T) { + if _, err := MergeNPM([]NPMMember{{RemoteName: "a"}, {RemoteName: "b"}}, "http://aa/v/"); !errors.Is(err, ErrNotFound) { + t.Fatalf("want ErrNotFound, got %v", err) + } +} + +func TestNPMMemberPath(t *testing.T) { + for _, c := range []struct { + tarball string + bases []string + want string + ok bool + }{ + {"@s/n/-/n-1.0.0.tgz", nil, "@s/n/-/n-1.0.0.tgz", true}, + {"https://evil.example/x.tgz", nil, "", false}, + {"/abs/x.tgz", nil, "", false}, + {"https://r.example/@s/n/-/n-1.0.0.tgz", []string{"https://m.example", "https://r.example"}, "@s/n/-/n-1.0.0.tgz", true}, + {"https://r.example.evil/x.tgz", []string{"https://r.example"}, "", false}, + } { + got, ok := npmMemberPath(c.tarball, c.bases) + if ok != c.ok || ok && got != c.want { + t.Errorf("npmMemberPath(%q, %v) = %q,%v want %q,%v", c.tarball, c.bases, got, ok, c.want, c.ok) + } + } +} + +func npmEngine(fetch func(name, pkg string) (*NPMMember, error)) *Engine { + return &Engine{ + mergeTTL: time.Minute, + getRemote: func(_ context.Context, name string) (*models.Remote, error) { + return &models.Remote{Name: name, RepoType: models.RepoTypeRemote}, nil + }, + npmMember: func(_ context.Context, name, pkg string) (*NPMMember, error) { return fetch(name, pkg) }, + } +} + +func npmVirt(members ...string) models.Virtual { + return models.Virtual{Name: "npm", PackageType: models.PackageNPM, Members: members} +} + +func TestFetchNPMScopedAndAbbreviated(t *testing.T) { + var mu sync.Mutex + var asked []string + e := npmEngine(func(name, pkg string) (*NPMMember, error) { + mu.Lock() + asked = append(asked, pkg) + mu.Unlock() + if name == "b" { + return &NPMMember{RemoteName: name}, nil + } + return &NPMMember{RemoteName: name, Doc: mustJSON(t, npmDoc{Name: pkg, DistTags: map[string]string{"latest": "1.0.0"}, + Versions: map[string]map[string]any{"1.0.0": npmVersion(pkg, "1.0.0", pkg+"/-/n-1.0.0.tgz")}})}, nil + }) + body, ct, err := e.FetchNPM(context.Background(), npmVirt("a", "b"), "@s%2fn", "http://host", true) + if err != nil { + t.Fatal(err) + } + if ct != NPMAbbreviatedType || !strings.Contains(string(body), `"tarball":"http://host/api/v1/virtual/npm/a/@s/n/-/n-1.0.0.tgz"`) { + t.Fatalf("ct %q body %s", ct, body) + } + if asked[0] != "@s/n" { + t.Fatalf("member asked for %q, want decoded scoped name", asked[0]) + } + full, ct, err := e.FetchNPM(context.Background(), npmVirt("a", "b"), "@s%2fn", "http://host", false) + if err != nil || ct != "application/json" || string(full) == string(body) { + t.Fatalf("full packument: ct %q err %v", ct, err) + } + if len(asked) != 2 { + t.Fatalf("second fetch should be served from the merge cache, members asked %d times", len(asked)) + } +} + +func TestFetchNPMFailsClosed(t *testing.T) { + e := npmEngine(func(name, pkg string) (*NPMMember, error) { + if name == "b" { + return nil, errors.New("upstream down") + } + return &NPMMember{RemoteName: name, Doc: []byte(`{"name":"x","versions":{}}`)}, nil + }) + _, _, err := e.FetchNPM(context.Background(), npmVirt("a", "b"), "x", "http://host", false) + if err == nil || errors.Is(err, ErrNotFound) { + t.Fatalf("want upstream error with a member down, got %v", err) + } +} + +func TestFetchNPMNotFound(t *testing.T) { + e := npmEngine(func(name, _ string) (*NPMMember, error) { return &NPMMember{RemoteName: name}, nil }) + for _, path := range []string{"missing", "-/npm/v1/security/advisories/bulk", "a/../b", "@s"} { + if _, _, err := e.FetchNPM(context.Background(), npmVirt("a"), path, "http://host", false); !errors.Is(err, ErrNotFound) { + t.Errorf("%q: want ErrNotFound, got %v", path, err) + } + } +} + +func TestFetchNPMMemberLocalNotFound(t *testing.T) { + e := &Engine{getRemote: func(_ context.Context, name string) (*models.Remote, error) { + return &models.Remote{Name: name, RepoType: models.RepoTypeLocal}, nil + }} + e.NPMLocal = func(_ context.Context, _, pkg string) ([]byte, error) { + if pkg == "boom" { + return nil, errors.New("db down") + } + return nil, fmt.Errorf("wrapped: %w", ErrNotFound) + } + m, err := e.fetchNPMMember(context.Background(), "internal", "nope") + if err != nil || m.Doc != nil { + t.Fatalf("missing package must be an empty member, got %v %v", m, err) + } + if _, err := e.fetchNPMMember(context.Background(), "internal", "boom"); err == nil { + t.Fatal("local read errors must surface") + } +} + +func TestMemberRedirectNPM(t *testing.T) { + e := npmEngine(nil) + virt := npmVirt("internal", "npmjs") + loc, ok, err := e.MemberRedirect(context.Background(), virt, "npmjs/@s/n/-/n-1.0.0.tgz", "", "http://host") + if err != nil || !ok || loc != "http://host/api/v1/remote/npmjs/@s/n/-/n-1.0.0.tgz" { + t.Fatalf("got %q %v %v", loc, ok, err) + } + if _, ok, _ := e.MemberRedirect(context.Background(), virt, "@s/n", "", "http://host"); ok { + t.Fatal("scoped packument path must not redirect") + } + if _, _, err := e.MemberRedirect(context.Background(), virt, "npmjs/%2e%2e/x.tgz", "", "http://host"); !errors.Is(err, ErrBadPath) { + t.Fatalf("want ErrBadPath, got %v", err) + } +} + +func TestEvictOldestBoundsNPMMerges(t *testing.T) { + e := npmEngine(func(name, pkg string) (*NPMMember, error) { + return &NPMMember{RemoteName: name, Doc: mustJSON(t, npmDoc{Name: pkg, Versions: map[string]map[string]any{}})}, nil + }) + for i := range maxNPMPackuments + 5 { + if _, _, err := e.FetchNPM(context.Background(), npmVirt("a"), fmt.Sprintf("p%d", i), "http://host", false); err != nil { + t.Fatal(err) + } + } + if len(e.gens) != maxNPMPackuments { + t.Fatalf("cached merges = %d, want %d", len(e.gens), maxNPMPackuments) + } + if _, ok := e.gens["npm\x00npm\x00p0\x00http://host"]; ok { + t.Fatal("oldest merge should be evicted") + } +}