Add local npm registry publish and install

2026-10-16 23:08:20 +11:00
parent 9161558334
commit d8e2446262
7 changed files with 558 additions and 1 deletions
@@ -0,0 +1,286 @@
+package v1
+
+import (
+	"bytes"
+	"context"
+	"crypto/sha1"
+	"crypto/sha512"
+	"encoding/base64"
+	"encoding/hex"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"log/slog"
+	"net/http"
+	"net/url"
+	"regexp"
+	"strings"
+
+	"github.com/go-chi/chi/v5"
+
+	"git.unkin.net/unkin/artifactapi/internal/database"
+	"git.unkin.net/unkin/artifactapi/internal/storage"
+	"git.unkin.net/unkin/artifactapi/pkg/models"
+)
+
+// Local npm repos speak the npm registry publish/read protocol. Per package:
+//   <pkg>/-/<base>-<version>.tgz   tarball (immutable)
+//   <pkg>/-/<base>-<version>.json  version manifest (immutable)
+//   <pkg>/-/dist-tags/<tag>        version string (mutable)
+
+var (
+	npmNameRe = regexp.MustCompile(`^(@[a-z0-9][a-z0-9._~-]*/)?[a-z0-9][a-z0-9._~-]*$`)
+	npmRefRe  = regexp.MustCompile(`^[0-9A-Za-z][0-9A-Za-z.+_-]*$`)
+)
+
+func (h *ProxyHandler) localNPMRemote(r *http.Request, name string) (*models.Remote, bool) {
+	remote, err := h.db.GetRemote(r.Context(), name)
+	if err != nil {
+		return nil, false
+	}
+	return remote, remote.RepoType == models.RepoTypeLocal && remote.PackageType == models.PackageNPM
+}
+
+// npmPackageName returns the package a packument/publish path addresses, or ""
+// when the path is something else (e.g. a tarball under <pkg>/-/).
+func npmPackageName(raw string) string {
+	p, err := url.PathUnescape(raw)
+	if err != nil {
+		return ""
+	}
+	p = strings.TrimSuffix(p, "/")
+	if !npmNameRe.MatchString(p) {
+		return ""
+	}
+	return p
+}
+
+type npmRelease struct {
+	version  string
+	manifest []byte
+	tarball  []byte
+	tags     []string
+}
+
+func parseNPMPublish(body io.Reader, pkg string) (*npmRelease, error) {
+	var doc struct {
+		Name        string                     `json:"name"`
+		DistTags    map[string]string          `json:"dist-tags"`
+		Versions    map[string]json.RawMessage `json:"versions"`
+		Attachments map[string]struct {
+			Data string `json:"data"`
+		} `json:"_attachments"`
+	}
+	if err := json.NewDecoder(body).Decode(&doc); err != nil {
+		return nil, fmt.Errorf("invalid publish body: %w", err)
+	}
+	if doc.Name != pkg {
+		return nil, fmt.Errorf("body name %q does not match %q", doc.Name, pkg)
+	}
+	if len(doc.Versions) != 1 || len(doc.Attachments) != 1 {
+		return nil, errors.New("publish must carry exactly one version and one tarball")
+	}
+
+	rel := &npmRelease{}
+	for v, m := range doc.Versions {
+		rel.version, rel.manifest = v, m
+	}
+	if !npmRefRe.MatchString(rel.version) {
+		return nil, fmt.Errorf("invalid version %q", rel.version)
+	}
+	var meta struct {
+		Name    string `json:"name"`
+		Version string `json:"version"`
+		Dist    struct {
+			Integrity string `json:"integrity"`
+			Shasum    string `json:"shasum"`
+		} `json:"dist"`
+	}
+	if err := json.Unmarshal(rel.manifest, &meta); err != nil {
+		return nil, fmt.Errorf("invalid version manifest: %w", err)
+	}
+	if meta.Name != pkg || meta.Version != rel.version {
+		return nil, errors.New("version manifest name/version mismatch")
+	}
+
+	for _, a := range doc.Attachments {
+		tgz, err := base64.StdEncoding.DecodeString(a.Data)
+		if err != nil {
+			return nil, fmt.Errorf("invalid tarball encoding: %w", err)
+		}
+		rel.tarball = tgz
+	}
+	if err := verifyNPMDist(rel.tarball, meta.Dist.Integrity, meta.Dist.Shasum); err != nil {
+		return nil, err
+	}
+
+	for tag, v := range doc.DistTags {
+		if !npmRefRe.MatchString(tag) || v != rel.version {
+			return nil, fmt.Errorf("dist-tag %q must point at the published version", tag)
+		}
+		rel.tags = append(rel.tags, tag)
+	}
+	return rel, nil
+}
+
+func verifyNPMDist(tgz []byte, integrity, shasum string) error {
+	if b64, ok := strings.CutPrefix(integrity, "sha512-"); ok {
+		sum := sha512.Sum512(tgz)
+		if base64.StdEncoding.EncodeToString(sum[:]) != b64 {
+			return errors.New("tarball does not match dist.integrity")
+		}
+		return nil
+	}
+	if shasum != "" {
+		sum := sha1.Sum(tgz)
+		if hex.EncodeToString(sum[:]) != shasum {
+			return errors.New("tarball does not match dist.shasum")
+		}
+		return nil
+	}
+	return errors.New("version manifest carries no sha512 integrity or shasum")
+}
+
+func npmError(w http.ResponseWriter, status int, msg string) {
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(status)
+	json.NewEncoder(w).Encode(map[string]string{"error": msg})
+}
+
+func (h *ProxyHandler) handleLocalPut(w http.ResponseWriter, r *http.Request) {
+	remote, ok := h.localNPMRemote(r, chi.URLParam(r, "localName"))
+	if !ok {
+		npmError(w, http.StatusMethodNotAllowed, "publish is only supported on local npm repositories")
+		return
+	}
+	pkg := npmPackageName(chi.URLParam(r, "*"))
+	if pkg == "" {
+		npmError(w, http.StatusBadRequest, "invalid package name")
+		return
+	}
+	rel, err := parseNPMPublish(r.Body, pkg)
+	if err != nil {
+		npmError(w, http.StatusBadRequest, err.Error())
+		return
+	}
+
+	base := pkg[strings.LastIndex(pkg, "/")+1:]
+	stem := pkg + "/-/" + base + "-" + rel.version
+	// The tarball's immutable row is the version's uniqueness gate.
+	if err := h.npmStore(r.Context(), remote.Name, stem+".tgz", rel.tarball, "application/octet-stream", false); err != nil {
+		if errors.Is(err, database.ErrAlreadyExists) {
+			npmError(w, http.StatusConflict, fmt.Sprintf("%s@%s already exists; overwrites are not allowed", pkg, rel.version))
+			return
+		}
+		npmError(w, http.StatusInternalServerError, err.Error())
+		return
+	}
+	if err := h.npmStore(r.Context(), remote.Name, stem+".json", rel.manifest, "application/json", false); err != nil {
+		npmError(w, http.StatusInternalServerError, err.Error())
+		return
+	}
+	for _, tag := range rel.tags {
+		if err := h.npmStore(r.Context(), remote.Name, pkg+"/-/dist-tags/"+tag, []byte(rel.version), "text/plain", true); err != nil {
+			npmError(w, http.StatusInternalServerError, err.Error())
+			return
+		}
+	}
+
+	slog.Info("local npm package published", "repo", remote.Name, "package", pkg, "version", rel.version)
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(http.StatusCreated)
+	json.NewEncoder(w).Encode(map[string]any{"ok": true, "id": pkg})
+}
+
+func (h *ProxyHandler) npmStore(ctx context.Context, repo, path string, data []byte, contentType string, mutable bool) error {
+	result, err := h.cas.Store(ctx, bytes.NewReader(data), contentType)
+	if err != nil {
+		return err
+	}
+	if err := h.db.UpsertBlob(ctx, result.ContentHash, result.S3Key, result.SizeBytes, contentType); err != nil {
+		return err
+	}
+	if mutable {
+		return h.db.UpsertLocalFile(ctx, repo, path, result.ContentHash)
+	}
+	return h.db.CreateLocalFile(ctx, repo, path, result.ContentHash)
+}
+
+func (h *ProxyHandler) readLocalBlob(ctx context.Context, contentHash string) ([]byte, error) {
+	reader, _, err := h.store.Download(ctx, storage.BlobKey(strings.TrimPrefix(contentHash, "sha256:")))
+	if err != nil {
+		return nil, err
+	}
+	defer reader.Close()
+	return io.ReadAll(reader)
+}
+
+func (h *ProxyHandler) serveNPMPackument(w http.ResponseWriter, r *http.Request, remote *models.Remote, pkg string) {
+	files, err := h.db.ListLocalFilesByPrefix(r.Context(), remote.Name, pkg+"/-/")
+	if err != nil {
+		npmError(w, http.StatusInternalServerError, err.Error())
+		return
+	}
+	read := func(hash string) ([]byte, error) { return h.readLocalBlob(r.Context(), hash) }
+	tarballBase := fmt.Sprintf("%s://%s/api/v1/local/%s/", scheme(r), r.Host, remote.Name)
+	doc, err := buildNPMPackument(pkg, files, read, tarballBase)
+	if err != nil {
+		npmError(w, http.StatusInternalServerError, err.Error())
+		return
+	}
+	if doc == nil {
+		npmError(w, http.StatusNotFound, "not found")
+		return
+	}
+	w.Header().Set("Content-Type", "application/json")
+	w.Header().Set("X-Artifact-Source", "local")
+	w.WriteHeader(http.StatusOK)
+	json.NewEncoder(w).Encode(doc)
+}
+
+// buildNPMPackument returns nil when pkg has no published versions.
+func buildNPMPackument(pkg string, files []database.LocalFile, read func(hash string) ([]byte, error), tarballBase string) (map[string]any, error) {
+	prefix := pkg + "/-/"
+	versions := map[string]any{}
+	tags := map[string]string{}
+	for _, f := range files {
+		// LIKE treats '_' as a wildcard, so the prefix match can over-select.
+		rest, ok := strings.CutPrefix(f.FilePath, prefix)
+		if !ok {
+			continue
+		}
+		if tag, isTag := strings.CutPrefix(rest, "dist-tags/"); isTag {
+			v, err := read(f.ContentHash)
+			if err != nil {
+				return nil, err
+			}
+			tags[tag] = string(v)
+			continue
+		}
+		stem, isManifest := strings.CutSuffix(rest, ".json")
+		if !isManifest {
+			continue
+		}
+		raw, err := read(f.ContentHash)
+		if err != nil {
+			return nil, err
+		}
+		var m map[string]any
+		if err := json.Unmarshal(raw, &m); err != nil {
+			return nil, fmt.Errorf("manifest %s: %w", f.FilePath, err)
+		}
+		dist, _ := m["dist"].(map[string]any)
+		if dist == nil {
+			dist = map[string]any{}
+			m["dist"] = dist
+		}
+		dist["tarball"] = tarballBase + prefix + stem + ".tgz"
+		v, _ := m["version"].(string)
+		versions[v] = m
+	}
+	if len(versions) == 0 {
+		return nil, nil
+	}
+	return map[string]any{"_id": pkg, "name": pkg, "dist-tags": tags, "versions": versions}, nil
+}
@@ -0,0 +1,162 @@
+package v1
+
+import (
+	"crypto/sha1"
+	"crypto/sha512"
+	"encoding/base64"
+	"encoding/hex"
+	"encoding/json"
+	"errors"
+	"strings"
+	"testing"
+
+	"git.unkin.net/unkin/artifactapi/internal/database"
+)
+
+func TestNPMPackageName(t *testing.T) {
+	tests := map[string]string{
+		"left-pad":                "left-pad",
+		"left-pad/":               "left-pad",
+		"@acme%2fwidget":          "@acme/widget",
+		"@acme%2Fwidget":          "@acme/widget",
+		"@acme/widget":            "@acme/widget",
+		"left-pad/-/left-pad.tgz": "",
+		"@acme/widget/-/w-1.tgz":  "",
+		"a/b":                     "",
+		"../etc":                  "",
+		"Upper":                   "",
+		"":                        "",
+	}
+	for in, want := range tests {
+		if got := npmPackageName(in); got != want {
+			t.Errorf("npmPackageName(%q) = %q, want %q", in, got, want)
+		}
+	}
+}
+
+type publishOpts struct {
+	bodyName, manifestName, version, integrity, shasum string
+	tags                                               map[string]string
+	extraVersion                                       bool
+}
+
+func publishBody(t *testing.T, pkg string, tgz []byte, o publishOpts) string {
+	t.Helper()
+	sha := sha512.Sum512(tgz)
+	sh1 := sha1.Sum(tgz)
+	if o.bodyName == "" {
+		o.bodyName = pkg
+	}
+	if o.manifestName == "" {
+		o.manifestName = pkg
+	}
+	if o.version == "" {
+		o.version = "1.0.0"
+	}
+	if o.integrity == "" {
+		o.integrity = "sha512-" + base64.StdEncoding.EncodeToString(sha[:])
+	}
+	if o.shasum == "" {
+		o.shasum = hex.EncodeToString(sh1[:])
+	}
+	if o.tags == nil {
+		o.tags = map[string]string{"latest": o.version}
+	}
+	versions := map[string]any{o.version: map[string]any{
+		"name": o.manifestName, "version": o.version, "main": "index.js",
+		"dist": map[string]any{"integrity": o.integrity, "shasum": o.shasum, "tarball": "http://elsewhere/x.tgz"},
+	}}
+	if o.extraVersion {
+		versions["2.0.0"] = map[string]any{"name": pkg, "version": "2.0.0"}
+	}
+	b, _ := json.Marshal(map[string]any{
+		"_id": pkg, "name": o.bodyName, "dist-tags": o.tags, "versions": versions,
+		"_attachments": map[string]any{pkg + "-" + o.version + ".tgz": map[string]any{
+			"content_type": "application/octet-stream", "data": base64.StdEncoding.EncodeToString(tgz), "length": len(tgz),
+		}},
+	})
+	return string(b)
+}
+
+func TestParseNPMPublish(t *testing.T) {
+	tgz := []byte("fake tarball bytes")
+
+	rel, err := parseNPMPublish(strings.NewReader(publishBody(t, "@acme/widget", tgz, publishOpts{tags: map[string]string{"latest": "1.0.0", "beta": "1.0.0"}})), "@acme/widget")
+	if err != nil {
+		t.Fatalf("valid scoped publish rejected: %v", err)
+	}
+	if rel.version != "1.0.0" || string(rel.tarball) != string(tgz) || len(rel.tags) != 2 {
+		t.Fatalf("unexpected release: %+v", rel)
+	}
+
+	if _, err := parseNPMPublish(strings.NewReader(publishBody(t, "left-pad", tgz, publishOpts{integrity: "none", shasum: hex.EncodeToString(make([]byte, 20))})), "left-pad"); err == nil {
+		t.Fatal("shasum fallback should reject a mismatched tarball")
+	}
+	if _, err := parseNPMPublish(strings.NewReader(publishBody(t, "left-pad", tgz, publishOpts{integrity: "none"})), "left-pad"); err != nil {
+		t.Fatalf("matching shasum fallback rejected: %v", err)
+	}
+
+	bad := map[string]publishOpts{
+		"body name mismatch":        {bodyName: "other"},
+		"manifest name mismatch":    {manifestName: "other"},
+		"integrity mismatch":        {integrity: "sha512-AAAA"},
+		"path-like version":         {version: "../1.0.0"},
+		"tag at another version":    {tags: map[string]string{"latest": "9.9.9"}},
+		"path-like tag":             {tags: map[string]string{"../x": "1.0.0"}},
+		"multiple versions at once": {extraVersion: true},
+	}
+	for name, o := range bad {
+		if _, err := parseNPMPublish(strings.NewReader(publishBody(t, "left-pad", tgz, o)), "left-pad"); err == nil {
+			t.Errorf("%s: expected rejection", name)
+		}
+	}
+	if _, err := parseNPMPublish(strings.NewReader(`{"name":"left-pad","versions":{}}`), "left-pad"); err == nil {
+		t.Error("deprecate-style body without attachments should be rejected")
+	}
+}
+
+func TestBuildNPMPackument(t *testing.T) {
+	blobs := map[string]string{
+		"h1": `{"name":"my_pkg","version":"1.0.0","dist":{"shasum":"aa","tarball":"http://elsewhere/x.tgz"}}`,
+		"h2": `{"name":"my_pkg","version":"1.1.0"}`,
+		"h3": "1.1.0",
+		"hx": `{"name":"myXpkg","version":"6.6.6"}`,
+	}
+	read := func(h string) ([]byte, error) {
+		b, ok := blobs[h]
+		if !ok {
+			return nil, errors.New("missing blob")
+		}
+		return []byte(b), nil
+	}
+	files := []database.LocalFile{
+		{FilePath: "my_pkg/-/dist-tags/latest", ContentHash: "h3"},
+		{FilePath: "my_pkg/-/my_pkg-1.0.0.json", ContentHash: "h1"},
+		{FilePath: "my_pkg/-/my_pkg-1.0.0.tgz", ContentHash: "nope"},
+		{FilePath: "my_pkg/-/my_pkg-1.1.0.json", ContentHash: "h2"},
+		{FilePath: "myXpkg/-/myXpkg-6.6.6.json", ContentHash: "hx"},
+	}
+
+	doc, err := buildNPMPackument("my_pkg", files, read, "http://reg/api/v1/local/npm/")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if tags := doc["dist-tags"].(map[string]string); tags["latest"] != "1.1.0" {
+		t.Errorf("dist-tags = %v", tags)
+	}
+	versions := doc["versions"].(map[string]any)
+	if len(versions) != 2 {
+		t.Fatalf("versions = %v (LIKE over-match must be dropped)", versions)
+	}
+	v1 := versions["1.0.0"].(map[string]any)["dist"].(map[string]any)
+	if v1["tarball"] != "http://reg/api/v1/local/npm/my_pkg/-/my_pkg-1.0.0.tgz" || v1["shasum"] != "aa" {
+		t.Errorf("1.0.0 dist = %v", v1)
+	}
+	if versions["1.1.0"].(map[string]any)["dist"].(map[string]any)["tarball"] != "http://reg/api/v1/local/npm/my_pkg/-/my_pkg-1.1.0.tgz" {
+		t.Error("1.1.0 missing rewritten tarball")
+	}
+
+	if doc, err := buildNPMPackument("absent", files, read, "x/"); err != nil || doc != nil {
+		t.Errorf("absent package: doc=%v err=%v", doc, err)
+	}
+}
@@ -15,6 +15,7 @@ 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 {
@@ -41,6 +42,7 @@ func (h *ProxyHandler) Routes() chi.Router {
 	r := chi.NewRouter()
 	r.Get("/remote/{remoteName}/*", h.handleProxy)
 	r.Get("/local/{localName}/*", h.handleLocal)
+	r.Put("/local/{localName}/*", h.handleLocalPut)
 	r.Get("/virtual/{virtualName}/*", h.handleVirtual)
 	return r
 }
@@ -199,6 +201,13 @@ func (h *ProxyHandler) handleLocal(w http.ResponseWriter, r *http.Request) {
 		return
 	}

+	if remote.PackageType == models.PackageNPM {
+		if pkg := npmPackageName(path); pkg != "" {
+			h.serveNPMPackument(w, r, remote, pkg)
+			return
+		}
+	}
+
 	prov, _ := provider.Get(remote.PackageType)
 	if indexer, ok := prov.(provider.LocalIndexer); ok {
 		if indexer.ServeLocalIndex(w, r, h.db, remote.Name, path) {